[INFO] cloning repository https://github.com/maxjeffos/rust-neural-network-experiments
[INFO] running `Command { std: "git" "-c" "credential.helper=" "-c" "credential.helper=/workspace/cargo-home/bin/git-credential-null" "clone" "--bare" "https://github.com/maxjeffos/rust-neural-network-experiments" "/workspace/cache/git-repos/https%3A%2F%2Fgithub.com%2Fmaxjeffos%2Frust-neural-network-experiments", kill_on_drop: false }`
[INFO] [stderr] Cloning into bare repository '/workspace/cache/git-repos/https%3A%2F%2Fgithub.com%2Fmaxjeffos%2Frust-neural-network-experiments'...
[INFO] running `Command { std: "git" "rev-parse" "HEAD", kill_on_drop: false }`
[INFO] [stdout] c4c2539f42a371031368d45b92d7a75516ec12f0
[INFO] testing maxjeffos/rust-neural-network-experiments against master#ec6f9a5b4413f74386267ef8efc93712c2ce6db6 for pr-155739
[INFO] running `Command { std: "git" "clone" "/workspace/cache/git-repos/https%3A%2F%2Fgithub.com%2Fmaxjeffos%2Frust-neural-network-experiments" "/workspace/builds/worker-0-tc1/source", kill_on_drop: false }`
[INFO] [stderr] Cloning into '/workspace/builds/worker-0-tc1/source'...
[INFO] [stderr] done.
[INFO] started tweaking git repo https://github.com/maxjeffos/rust-neural-network-experiments
[INFO] finished tweaking git repo https://github.com/maxjeffos/rust-neural-network-experiments
[INFO] tweaked toml for git repo https://github.com/maxjeffos/rust-neural-network-experiments written to /workspace/builds/worker-0-tc1/source/Cargo.toml
[INFO] validating manifest of git repo https://github.com/maxjeffos/rust-neural-network-experiments on toolchain ec6f9a5b4413f74386267ef8efc93712c2ce6db6
[INFO] running `Command { std: CARGO_HOME="/workspace/cargo-home" RUSTUP_HOME="/workspace/rustup-home" "/workspace/cargo-home/bin/cargo" "+ec6f9a5b4413f74386267ef8efc93712c2ce6db6" "metadata" "--manifest-path" "Cargo.toml" "--no-deps", kill_on_drop: false }`
[INFO] crate git repo https://github.com/maxjeffos/rust-neural-network-experiments already has a lockfile, it will not be regenerated
[INFO] running `Command { std: CARGO_HOME="/workspace/cargo-home" RUSTUP_HOME="/workspace/rustup-home" "/workspace/cargo-home/bin/cargo" "+ec6f9a5b4413f74386267ef8efc93712c2ce6db6" "fetch" "--manifest-path" "Cargo.toml", kill_on_drop: false }`
[INFO] [stderr] warning: virtual workspace defaulting to `resolver = "1"` despite one or more workspace members being on edition 2021 which implies `resolver = "2"`
[INFO] [stderr]   |
[INFO] [stderr]   = note: to keep the current resolver, specify `workspace.resolver = "1"` in the workspace root's manifest
[INFO] [stderr]   = note: to use the edition 2021 resolver, specify `workspace.resolver = "2"` in the workspace root's manifest
[INFO] [stderr]   = note: for more details see https://doc.rust-lang.org/cargo/reference/resolver.html#resolver-versions
[INFO] [stderr]     Updating crates.io index
[INFO] [stderr]  Downloading crates ...
[INFO] [stderr]   Downloaded mnist v0.5.0
[INFO] [stderr]   Downloaded time-test v0.2.2
[INFO] [stderr]   Downloaded autodiff v0.4.0
[INFO] [stderr]   Downloaded crossbeam-epoch v0.9.6
[INFO] [stderr]   Downloaded rand_distr v0.4.2
[INFO] running `Command { std: "docker" "create" "-v" "/var/lib/crater-agent-workspace/builds/worker-0-tc1/target:/opt/rustwide/target:rw,Z" "-v" "/var/lib/crater-agent-workspace/builds/worker-0-tc1/source:/opt/rustwide/workdir:ro,Z" "-v" "/var/lib/crater-agent-workspace/cargo-home:/opt/rustwide/cargo-home:ro,Z" "-v" "/var/lib/crater-agent-workspace/rustup-home:/opt/rustwide/rustup-home:ro,Z" "-e" "SOURCE_DIR=/opt/rustwide/workdir" "-e" "CARGO_TARGET_DIR=/opt/rustwide/target" "-e" "CARGO_HOME=/opt/rustwide/cargo-home" "-e" "RUSTUP_HOME=/opt/rustwide/rustup-home" "-w" "/opt/rustwide/workdir" "-m" "1610612736" "--user" "0:0" "--network" "none" "ghcr.io/rust-lang/crates-build-env/linux@sha256:d429b63d4308055ea97f60fb1d3dfca48854a00942f1bd2ad806beaf015945ec" "/opt/rustwide/cargo-home/bin/cargo" "+ec6f9a5b4413f74386267ef8efc93712c2ce6db6" "metadata" "--no-deps" "--format-version=1", kill_on_drop: false }`
[INFO] [stdout] 4af374a71854af8f582fb3f5c6a3ff0596a4f995c265a684bae4a034908e5438
[INFO] running `Command { std: "docker" "start" "-a" "4af374a71854af8f582fb3f5c6a3ff0596a4f995c265a684bae4a034908e5438", kill_on_drop: false }`
[INFO] running `Command { std: "docker" "inspect" "4af374a71854af8f582fb3f5c6a3ff0596a4f995c265a684bae4a034908e5438", kill_on_drop: false }`
[INFO] running `Command { std: "docker" "rm" "-f" "4af374a71854af8f582fb3f5c6a3ff0596a4f995c265a684bae4a034908e5438", kill_on_drop: false }`
[INFO] [stdout] 4af374a71854af8f582fb3f5c6a3ff0596a4f995c265a684bae4a034908e5438
[INFO] running `Command { std: "docker" "create" "-v" "/var/lib/crater-agent-workspace/builds/worker-0-tc1/target:/opt/rustwide/target:rw,Z" "-v" "/var/lib/crater-agent-workspace/builds/worker-0-tc1/source:/opt/rustwide/workdir:ro,Z" "-v" "/var/lib/crater-agent-workspace/cargo-home:/opt/rustwide/cargo-home:ro,Z" "-v" "/var/lib/crater-agent-workspace/rustup-home:/opt/rustwide/rustup-home:ro,Z" "-e" "SOURCE_DIR=/opt/rustwide/workdir" "-e" "CARGO_TARGET_DIR=/opt/rustwide/target" "-e" "CARGO_INCREMENTAL=0" "-e" "RUST_BACKTRACE=full" "-e" "RUSTFLAGS=--cap-lints=forbid" "-e" "RUSTDOCFLAGS=--cap-lints=forbid" "-e" "CARGO_HOME=/opt/rustwide/cargo-home" "-e" "RUSTUP_HOME=/opt/rustwide/rustup-home" "-w" "/opt/rustwide/workdir" "-m" "1610612736" "--user" "0:0" "--network" "none" "ghcr.io/rust-lang/crates-build-env/linux@sha256:d429b63d4308055ea97f60fb1d3dfca48854a00942f1bd2ad806beaf015945ec" "/opt/rustwide/cargo-home/bin/cargo" "+ec6f9a5b4413f74386267ef8efc93712c2ce6db6" "build" "--frozen" "--message-format=json", kill_on_drop: false }`
[INFO] [stdout] 2ee21a0544f5a1f9aeb2ec0a2234cd7af73910e247f84a47c9818a77a0d4cdb0
[INFO] running `Command { std: "docker" "start" "-a" "2ee21a0544f5a1f9aeb2ec0a2234cd7af73910e247f84a47c9818a77a0d4cdb0", kill_on_drop: false }`
[INFO] [stderr] warning: virtual workspace defaulting to `resolver = "1"` despite one or more workspace members being on edition 2021 which implies `resolver = "2"`
[INFO] [stderr]   |
[INFO] [stderr]   = note: to keep the current resolver, specify `workspace.resolver = "1"` in the workspace root's manifest
[INFO] [stderr]   = note: to use the edition 2021 resolver, specify `workspace.resolver = "2"` in the workspace root's manifest
[INFO] [stderr]   = note: for more details see https://doc.rust-lang.org/cargo/reference/resolver.html#resolver-versions
[INFO] [stderr]    Compiling num-traits v0.2.14
[INFO] [stderr]    Compiling crossbeam-utils v0.8.6
[INFO] [stderr]    Compiling memoffset v0.6.5
[INFO] [stderr]    Compiling crossbeam-epoch v0.9.6
[INFO] [stderr]    Compiling rayon-core v1.9.1
[INFO] [stderr]    Compiling rayon v1.5.1
[INFO] [stderr]    Compiling num-integer v0.1.44
[INFO] [stderr]    Compiling rawpointer v0.2.1
[INFO] [stderr]    Compiling serde v1.0.136
[INFO] [stderr]    Compiling syn v1.0.85
[INFO] [stderr]    Compiling serde_derive v1.0.136
[INFO] [stderr]    Compiling serde_json v1.0.78
[INFO] [stderr]    Compiling mnist v0.5.0
[INFO] [stderr]    Compiling getrandom v0.2.4
[INFO] [stderr]    Compiling num_cpus v1.13.1
[INFO] [stderr]    Compiling itoa v1.0.1
[INFO] [stderr]    Compiling matrixmultiply v0.3.2
[INFO] [stderr]    Compiling ryu v1.0.9
[INFO] [stderr]    Compiling anyhow v1.0.82
[INFO] [stderr]    Compiling rand_core v0.6.3
[INFO] [stderr]    Compiling crossbeam-channel v0.5.2
[INFO] [stderr]    Compiling rand_chacha v0.3.1
[INFO] [stderr]    Compiling rand v0.8.4
[INFO] [stderr]    Compiling crossbeam-deque v0.8.1
[INFO] [stderr]    Compiling num-complex v0.4.0
[INFO] [stderr]    Compiling autodiff v0.4.0
[INFO] [stderr]    Compiling test1-autodiff v0.1.0 (/opt/rustwide/workdir/test1-autodiff)
[INFO] [stdout] warning: function `e_to_the_x` is never used
[INFO] [stdout]  --> test1-autodiff/src/main.rs:3:4
[INFO] [stdout]   |
[INFO] [stdout] 3 | fn e_to_the_x(x: FT<f64>) -> FT<f64> {
[INFO] [stdout]   |    ^^^^^^^^^^
[INFO] [stdout]   |
[INFO] [stdout]   = note: `#[warn(dead_code)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stderr]    Compiling ndarray v0.15.4
[INFO] [stderr]    Compiling rand_distr v0.4.2
[INFO] [stderr]    Compiling common v0.1.0 (/opt/rustwide/workdir/common)
[INFO] [stdout] warning: enum `Quadrant` is never used
[INFO] [stdout]  --> common/src/point.rs:7:6
[INFO] [stdout]   |
[INFO] [stdout] 7 | enum Quadrant {
[INFO] [stdout]   |      ^^^^^^^^
[INFO] [stdout]   |
[INFO] [stdout]   = note: `#[warn(dead_code)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: function `softmax` is never used
[INFO] [stdout]  --> common/src/softmax.rs:1:4
[INFO] [stdout]   |
[INFO] [stdout] 1 | fn softmax(logits: &[f64]) -> Vec<f64> {
[INFO] [stdout]   |    ^^^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: function `softmax_derivative` is never used
[INFO] [stdout]   --> common/src/softmax.rs:16:4
[INFO] [stdout]    |
[INFO] [stdout] 16 | fn softmax_derivative(logits: &[f64]) -> Vec<Vec<f64>> {
[INFO] [stdout]    |    ^^^^^^^^^^^^^^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: hiding a lifetime that's named elsewhere is confusing
[INFO] [stdout]    --> common/src/linalg/mod.rs:714:64
[INFO] [stdout]     |
[INFO] [stdout] 714 |     pub fn iter_with<'a>(&'a self, other: &'a ColumnVector) -> IterWith {
[INFO] [stdout]     |                           --               --                  ^^^^^^^^ the same lifetime is hidden here
[INFO] [stdout]     |                           |                |
[INFO] [stdout]     |                           |                the lifetime is named here
[INFO] [stdout]     |                           the lifetime is named here
[INFO] [stdout]     |
[INFO] [stdout]     = help: the same lifetime is referred to in inconsistent ways, making the signature confusing
[INFO] [stdout]     = note: `#[warn(mismatched_lifetime_syntaxes)]` on by default
[INFO] [stdout] help: consistently use `'a`
[INFO] [stdout]     |
[INFO] [stdout] 714 |     pub fn iter_with<'a>(&'a self, other: &'a ColumnVector) -> IterWith<'a> {
[INFO] [stdout]     |                                                                        ++++
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stderr]    Compiling test3-simple-linear-regression v0.1.0 (/opt/rustwide/workdir/test3-simple-linear-regression)
[INFO] [stderr]    Compiling test5-playing-with-matrix-ideas v0.1.0 (/opt/rustwide/workdir/test5-playing-with-matrix-ideas)
[INFO] [stderr]    Compiling test4-multivariable-regression v0.1.0 (/opt/rustwide/workdir/test4-multivariable-regression)
[INFO] [stderr]    Compiling metrics v0.1.0 (/opt/rustwide/workdir/metrics)
[INFO] [stdout] warning: enum `MultivariableRegressionError` is never used
[INFO] [stdout]   --> test4-multivariable-regression/src/main.rs:36:6
[INFO] [stdout]    |
[INFO] [stdout] 36 | enum MultivariableRegressionError {
[INFO] [stdout]    |      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[INFO] [stdout]    |
[INFO] [stdout]    = note: `#[warn(dead_code)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: enum `InvalidDataError` is never used
[INFO] [stdout]   --> test4-multivariable-regression/src/main.rs:43:6
[INFO] [stdout]    |
[INFO] [stdout] 43 | enum InvalidDataError {
[INFO] [stdout]    |      ^^^^^^^^^^^^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: function `predict` is never used
[INFO] [stdout]   --> test4-multivariable-regression/src/main.rs:87:4
[INFO] [stdout]    |
[INFO] [stdout] 87 | fn predict(theta: &[f64], independant: &[f64]) -> f64 {
[INFO] [stdout]    |    ^^^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stderr]    Compiling mnist-data v0.1.0 (/opt/rustwide/workdir/mnist-data)
[INFO] [stderr]    Compiling test6-nn v0.1.0 (/opt/rustwide/workdir/test6-nn)
[INFO] [stderr]    Compiling test7-nn-mnist-classifier v0.1.0 (/opt/rustwide/workdir/test7-nn-mnist-classifier)
[INFO] [stderr]    Compiling test2-mlp-classifier v0.1.0 (/opt/rustwide/workdir/test2-mlp-classifier)
[INFO] [stdout] warning: unused variable: `normalized_distance`
[INFO] [stdout]    --> test7-nn-mnist-classifier/src/lib.rs:639:21
[INFO] [stdout]     |
[INFO] [stdout] 639 |                 let normalized_distance = euclidian_distance(&approx_gradients_big_v, &d_vec)
[INFO] [stdout]     |                     ^^^^^^^^^^^^^^^^^^^ help: if this is intentional, prefix it with an underscore: `_normalized_distance`
[INFO] [stdout]     |
[INFO] [stdout]     = note: `#[warn(unused_variables)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: variant `blue` should have an upper camel case name
[INFO] [stdout]   --> test2-mlp-classifier/src/main.rs:59:5
[INFO] [stdout]    |
[INFO] [stdout] 59 |     blue,
[INFO] [stdout]    |     ^^^^ help: convert the identifier to upper camel case: `Blue`
[INFO] [stdout]    |
[INFO] [stdout]    = note: `#[warn(non_camel_case_types)]` (part of `#[warn(nonstandard_style)]`) on by default
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: variant `orange` should have an upper camel case name
[INFO] [stdout]   --> test2-mlp-classifier/src/main.rs:60:5
[INFO] [stdout]    |
[INFO] [stdout] 60 |     orange,
[INFO] [stdout]    |     ^^^^^^ help: convert the identifier to upper camel case (notice the capitalization): `Orange`
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: struct `LayerGradients` is never constructed
[INFO] [stdout]   --> test7-nn-mnist-classifier/src/lib.rs:81:8
[INFO] [stdout]    |
[INFO] [stdout] 81 | struct LayerGradients {
[INFO] [stdout]    |        ^^^^^^^^^^^^^^
[INFO] [stdout]    |
[INFO] [stdout]    = note: `#[warn(dead_code)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: associated function `new` is never used
[INFO] [stdout]   --> test7-nn-mnist-classifier/src/lib.rs:87:8
[INFO] [stdout]    |
[INFO] [stdout] 86 | impl LayerGradients {
[INFO] [stdout]    | ------------------- associated function in this implementation
[INFO] [stdout] 87 |     fn new(weight_gradients: Matrix, bias_gradients: ColumnVector) -> Self {
[INFO] [stdout]    |        ^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: constant `GRADIENT_CHECK_EPSILON_SQUARED` is never used
[INFO] [stdout]    --> test7-nn-mnist-classifier/src/lib.rs:118:7
[INFO] [stdout]     |
[INFO] [stdout] 118 | const GRADIENT_CHECK_EPSILON_SQUARED: f64 = GRADIENT_CHECK_EPSILON * GRADIENT_CHECK_EPSILON;
[INFO] [stdout]     |       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: methods `err_output_layer` and `unroll_gradients` are never used
[INFO] [stdout]     --> test7-nn-mnist-classifier/src/lib.rs:328:8
[INFO] [stdout]      |
[INFO] [stdout]  148 | impl NeuralNetwork {
[INFO] [stdout]      | ------------------ methods in this implementation
[INFO] [stdout] ...
[INFO] [stdout]  328 |     fn err_output_layer(
[INFO] [stdout]      |        ^^^^^^^^^^^^^^^^
[INFO] [stdout] ...
[INFO] [stdout] 1128 |     fn unroll_gradients(
[INFO] [stdout]      |        ^^^^^^^^^^^^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unused `Result` that must be used
[INFO] [stdout]    --> test7-nn-mnist-classifier/src/lib.rs:719:13
[INFO] [stdout]     |
[INFO] [stdout] 719 |             session_logger.write_training_session_file(initial_cost, network_config, optimizer_str);
[INFO] [stdout]     |             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[INFO] [stdout]     |
[INFO] [stdout]     = note: this `Result` may be an `Err` variant, which should be handled
[INFO] [stdout]     = note: `#[warn(unused_must_use)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] help: use `let _ = ...` to ignore the resulting value
[INFO] [stdout]     |
[INFO] [stdout] 719 |             let _ = session_logger.write_training_session_file(initial_cost, network_config, optimizer_str);
[INFO] [stdout]     |             +++++++
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unused import: `ndarray`
[INFO] [stdout]  --> test2-mlp-classifier/src/main.rs:5:5
[INFO] [stdout]   |
[INFO] [stdout] 5 | use ndarray::*;
[INFO] [stdout]   |     ^^^^^^^
[INFO] [stdout]   |
[INFO] [stdout]   = note: `#[warn(unused_imports)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unused variable: `i`
[INFO] [stdout]   --> test2-mlp-classifier/src/main.rs:80:9
[INFO] [stdout]    |
[INFO] [stdout] 80 |     for i in 0..n {
[INFO] [stdout]    |         ^ help: if this is intentional, prefix it with an underscore: `_i`
[INFO] [stdout]    |
[INFO] [stdout]    = note: `#[warn(unused_variables)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: struct `MultilayerPerceptron` is never constructed
[INFO] [stdout]  --> test2-mlp-classifier/src/main.rs:7:8
[INFO] [stdout]   |
[INFO] [stdout] 7 | struct MultilayerPerceptron {
[INFO] [stdout]   |        ^^^^^^^^^^^^^^^^^^^^
[INFO] [stdout]   |
[INFO] [stdout]   = note: `#[warn(dead_code)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: struct `MLPArchitecture` is never constructed
[INFO] [stdout]   --> test2-mlp-classifier/src/main.rs:14:8
[INFO] [stdout]    |
[INFO] [stdout] 14 | struct MLPArchitecture {
[INFO] [stdout]    |        ^^^^^^^^^^^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: associated function `new` is never used
[INFO] [stdout]   --> test2-mlp-classifier/src/main.rs:21:8
[INFO] [stdout]    |
[INFO] [stdout] 20 | impl MLPArchitecture {
[INFO] [stdout]    | -------------------- associated function in this implementation
[INFO] [stdout] 21 |     fn new(input_size: usize, hidden_layers: Vec<usize>, output_size: usize) -> Self {
[INFO] [stdout]    |        ^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unused variable: `normalized_distance`
[INFO] [stdout]    --> test6-nn/src/lib.rs:585:21
[INFO] [stdout]     |
[INFO] [stdout] 585 |                 let normalized_distance = euclidian_distance(&approx_gradients_big_v, &d_vec)
[INFO] [stdout]     |                     ^^^^^^^^^^^^^^^^^^^ help: if this is intentional, prefix it with an underscore: `_normalized_distance`
[INFO] [stdout]     |
[INFO] [stdout]     = note: `#[warn(unused_variables)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: struct `LayerGradients` is never constructed
[INFO] [stdout]   --> test6-nn/src/lib.rs:81:8
[INFO] [stdout]    |
[INFO] [stdout] 81 | struct LayerGradients {
[INFO] [stdout]    |        ^^^^^^^^^^^^^^
[INFO] [stdout]    |
[INFO] [stdout]    = note: `#[warn(dead_code)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: associated function `new` is never used
[INFO] [stdout]   --> test6-nn/src/lib.rs:87:8
[INFO] [stdout]    |
[INFO] [stdout] 86 | impl LayerGradients {
[INFO] [stdout]    | ------------------- associated function in this implementation
[INFO] [stdout] 87 |     fn new(weight_gradients: Matrix, bias_gradients: ColumnVector) -> Self {
[INFO] [stdout]    |        ^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: constant `GRADIENT_CHECK_EPSILON_SQUARED` is never used
[INFO] [stdout]    --> test6-nn/src/lib.rs:118:7
[INFO] [stdout]     |
[INFO] [stdout] 118 | const GRADIENT_CHECK_EPSILON_SQUARED: f64 = GRADIENT_CHECK_EPSILON * GRADIENT_CHECK_EPSILON;
[INFO] [stdout]     |       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: method `unroll_gradients` is never used
[INFO] [stdout]     --> test6-nn/src/lib.rs:1074:8
[INFO] [stdout]      |
[INFO] [stdout]  146 | impl SimpleNeuralNetwork {
[INFO] [stdout]      | ------------------------ method in this implementation
[INFO] [stdout] ...
[INFO] [stdout] 1074 |     fn unroll_gradients(
[INFO] [stdout]      |        ^^^^^^^^^^^^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: struct `JELU` is never constructed
[INFO] [stdout]  --> test6-nn/src/activation/activator/jelu.rs:4:8
[INFO] [stdout]   |
[INFO] [stdout] 4 | struct JELU {
[INFO] [stdout]   |        ^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: associated function `new` is never used
[INFO] [stdout]   --> test6-nn/src/activation/activator/jelu.rs:12:12
[INFO] [stdout]    |
[INFO] [stdout] 11 | impl JELU {
[INFO] [stdout]    | --------- associated function in this implementation
[INFO] [stdout] 12 |     pub fn new(crossover_point: f64) -> JELU {
[INFO] [stdout]    |            ^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unused `Result` that must be used
[INFO] [stdout]    --> test6-nn/src/lib.rs:665:13
[INFO] [stdout]     |
[INFO] [stdout] 665 |             session_logger.write_training_session_file(initial_cost, network_config, optimizer_str);
[INFO] [stdout]     |             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[INFO] [stdout]     |
[INFO] [stdout]     = note: this `Result` may be an `Err` variant, which should be handled
[INFO] [stdout]     = note: `#[warn(unused_must_use)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] help: use `let _ = ...` to ignore the resulting value
[INFO] [stdout]     |
[INFO] [stdout] 665 |             let _ = session_logger.write_training_session_file(initial_cost, network_config, optimizer_str);
[INFO] [stdout]     |             +++++++
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unused `Result` that must be used
[INFO] [stdout]    --> test7-nn-mnist-classifier/src/main.rs:99:5
[INFO] [stdout]     |
[INFO] [stdout]  99 | /     nn.train_stochastic(
[INFO] [stdout] 100 | |         &training_data,
[INFO] [stdout] 101 | |         10_000,
[INFO] [stdout] ...   |
[INFO] [stdout] 110 | |         Some(session_logger),
[INFO] [stdout] 111 | |     );
[INFO] [stdout]     | |_____^
[INFO] [stdout]     |
[INFO] [stdout]     = note: this `Result` may be an `Err` variant, which should be handled
[INFO] [stdout]     = note: `#[warn(unused_must_use)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] help: use `let _ = ...` to ignore the resulting value
[INFO] [stdout]     |
[INFO] [stdout]  99 |     let _ = nn.train_stochastic(
[INFO] [stdout]     |     +++++++
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unused `Result` that must be used
[INFO] [stdout]    --> test6-nn/src/main.rs:92:5
[INFO] [stdout]     |
[INFO] [stdout]  92 | /     nn.train_stochastic(
[INFO] [stdout]  93 | |         &training_data,
[INFO] [stdout]  94 | |         10_000,
[INFO] [stdout] ...   |
[INFO] [stdout] 103 | |         Some(session_logger),
[INFO] [stdout] 104 | |     );
[INFO] [stdout]     | |_____^
[INFO] [stdout]     |
[INFO] [stdout]     = note: this `Result` may be an `Err` variant, which should be handled
[INFO] [stdout]     = note: `#[warn(unused_must_use)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] help: use `let _ = ...` to ignore the resulting value
[INFO] [stdout]     |
[INFO] [stdout]  92 |     let _ = nn.train_stochastic(
[INFO] [stdout]     |     +++++++
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stderr]     Finished `dev` profile [unoptimized + debuginfo] target(s) in 11.29s
[INFO] running `Command { std: "docker" "inspect" "2ee21a0544f5a1f9aeb2ec0a2234cd7af73910e247f84a47c9818a77a0d4cdb0", kill_on_drop: false }`
[INFO] running `Command { std: "docker" "rm" "-f" "2ee21a0544f5a1f9aeb2ec0a2234cd7af73910e247f84a47c9818a77a0d4cdb0", kill_on_drop: false }`
[INFO] [stdout] 2ee21a0544f5a1f9aeb2ec0a2234cd7af73910e247f84a47c9818a77a0d4cdb0
[INFO] running `Command { std: "docker" "create" "-v" "/var/lib/crater-agent-workspace/builds/worker-0-tc1/target:/opt/rustwide/target:rw,Z" "-v" "/var/lib/crater-agent-workspace/builds/worker-0-tc1/source:/opt/rustwide/workdir:ro,Z" "-v" "/var/lib/crater-agent-workspace/cargo-home:/opt/rustwide/cargo-home:ro,Z" "-v" "/var/lib/crater-agent-workspace/rustup-home:/opt/rustwide/rustup-home:ro,Z" "-e" "SOURCE_DIR=/opt/rustwide/workdir" "-e" "CARGO_TARGET_DIR=/opt/rustwide/target" "-e" "CARGO_INCREMENTAL=0" "-e" "RUST_BACKTRACE=full" "-e" "RUSTFLAGS=--cap-lints=forbid" "-e" "RUSTDOCFLAGS=--cap-lints=forbid" "-e" "CARGO_HOME=/opt/rustwide/cargo-home" "-e" "RUSTUP_HOME=/opt/rustwide/rustup-home" "-w" "/opt/rustwide/workdir" "-m" "1610612736" "--user" "0:0" "--network" "none" "ghcr.io/rust-lang/crates-build-env/linux@sha256:d429b63d4308055ea97f60fb1d3dfca48854a00942f1bd2ad806beaf015945ec" "/opt/rustwide/cargo-home/bin/cargo" "+ec6f9a5b4413f74386267ef8efc93712c2ce6db6" "test" "--frozen" "--no-run" "--message-format=json", kill_on_drop: false }`
[INFO] [stdout] c7614941f6171fbf0cac1489305bad3ac759bbcff1c7be282cdde8412b6f2181
[INFO] running `Command { std: "docker" "start" "-a" "c7614941f6171fbf0cac1489305bad3ac759bbcff1c7be282cdde8412b6f2181", kill_on_drop: false }`
[INFO] [stderr] warning: virtual workspace defaulting to `resolver = "1"` despite one or more workspace members being on edition 2021 which implies `resolver = "2"`
[INFO] [stderr]   |
[INFO] [stderr]   = note: to keep the current resolver, specify `workspace.resolver = "1"` in the workspace root's manifest
[INFO] [stderr]   = note: to use the edition 2021 resolver, specify `workspace.resolver = "2"` in the workspace root's manifest
[INFO] [stderr]   = note: for more details see https://doc.rust-lang.org/cargo/reference/resolver.html#resolver-versions
[INFO] [stderr]    Compiling time v0.1.43
[INFO] [stderr]    Compiling float-cmp v0.9.0
[INFO] [stderr]    Compiling test1-autodiff v0.1.0 (/opt/rustwide/workdir/test1-autodiff)
[INFO] [stderr]    Compiling metrics v0.1.0 (/opt/rustwide/workdir/metrics)
[INFO] [stderr]    Compiling test2-mlp-classifier v0.1.0 (/opt/rustwide/workdir/test2-mlp-classifier)
[INFO] [stdout] warning: enum `Quadrant` is never used
[INFO] [stdout]  --> common/src/point.rs:7:6
[INFO] [stdout]   |
[INFO] [stdout] 7 | enum Quadrant {
[INFO] [stdout]   |      ^^^^^^^^
[INFO] [stdout]   |
[INFO] [stdout]   = note: `#[warn(dead_code)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: function `softmax` is never used
[INFO] [stdout]  --> common/src/softmax.rs:1:4
[INFO] [stdout]   |
[INFO] [stdout] 1 | fn softmax(logits: &[f64]) -> Vec<f64> {
[INFO] [stdout]   |    ^^^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: function `softmax_derivative` is never used
[INFO] [stdout]   --> common/src/softmax.rs:16:4
[INFO] [stdout]    |
[INFO] [stdout] 16 | fn softmax_derivative(logits: &[f64]) -> Vec<Vec<f64>> {
[INFO] [stdout]    |    ^^^^^^^^^^^^^^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: hiding a lifetime that's named elsewhere is confusing
[INFO] [stdout]    --> common/src/linalg/mod.rs:714:64
[INFO] [stdout]     |
[INFO] [stdout] 714 |     pub fn iter_with<'a>(&'a self, other: &'a ColumnVector) -> IterWith {
[INFO] [stdout]     |                           --               --                  ^^^^^^^^ the same lifetime is hidden here
[INFO] [stdout]     |                           |                |
[INFO] [stdout]     |                           |                the lifetime is named here
[INFO] [stdout]     |                           the lifetime is named here
[INFO] [stdout]     |
[INFO] [stdout]     = help: the same lifetime is referred to in inconsistent ways, making the signature confusing
[INFO] [stdout]     = note: `#[warn(mismatched_lifetime_syntaxes)]` on by default
[INFO] [stdout] help: consistently use `'a`
[INFO] [stdout]     |
[INFO] [stdout] 714 |     pub fn iter_with<'a>(&'a self, other: &'a ColumnVector) -> IterWith<'a> {
[INFO] [stdout]     |                                                                        ++++
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stderr]    Compiling common v0.1.0 (/opt/rustwide/workdir/common)
[INFO] [stderr]    Compiling test3-simple-linear-regression v0.1.0 (/opt/rustwide/workdir/test3-simple-linear-regression)
[INFO] [stderr]    Compiling mnist-data v0.1.0 (/opt/rustwide/workdir/mnist-data)
[INFO] [stderr]    Compiling test5-playing-with-matrix-ideas v0.1.0 (/opt/rustwide/workdir/test5-playing-with-matrix-ideas)
[INFO] [stdout] warning: unused variable: `normalized_distance`
[INFO] [stdout]    --> test6-nn/src/lib.rs:585:21
[INFO] [stdout]     |
[INFO] [stdout] 585 |                 let normalized_distance = euclidian_distance(&approx_gradients_big_v, &d_vec)
[INFO] [stdout]     |                     ^^^^^^^^^^^^^^^^^^^ help: if this is intentional, prefix it with an underscore: `_normalized_distance`
[INFO] [stdout]     |
[INFO] [stdout]     = note: `#[warn(unused_variables)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: struct `LayerGradients` is never constructed
[INFO] [stdout]   --> test6-nn/src/lib.rs:81:8
[INFO] [stdout]    |
[INFO] [stdout] 81 | struct LayerGradients {
[INFO] [stdout]    |        ^^^^^^^^^^^^^^
[INFO] [stdout]    |
[INFO] [stdout]    = note: `#[warn(dead_code)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: associated function `new` is never used
[INFO] [stdout]   --> test6-nn/src/lib.rs:87:8
[INFO] [stdout]    |
[INFO] [stdout] 86 | impl LayerGradients {
[INFO] [stdout]    | ------------------- associated function in this implementation
[INFO] [stdout] 87 |     fn new(weight_gradients: Matrix, bias_gradients: ColumnVector) -> Self {
[INFO] [stdout]    |        ^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: constant `GRADIENT_CHECK_EPSILON_SQUARED` is never used
[INFO] [stdout]    --> test6-nn/src/lib.rs:118:7
[INFO] [stdout]     |
[INFO] [stdout] 118 | const GRADIENT_CHECK_EPSILON_SQUARED: f64 = GRADIENT_CHECK_EPSILON * GRADIENT_CHECK_EPSILON;
[INFO] [stdout]     |       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: method `unroll_gradients` is never used
[INFO] [stdout]     --> test6-nn/src/lib.rs:1074:8
[INFO] [stdout]      |
[INFO] [stdout]  146 | impl SimpleNeuralNetwork {
[INFO] [stdout]      | ------------------------ method in this implementation
[INFO] [stdout] ...
[INFO] [stdout] 1074 |     fn unroll_gradients(
[INFO] [stdout]      |        ^^^^^^^^^^^^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: struct `JELU` is never constructed
[INFO] [stdout]  --> test6-nn/src/activation/activator/jelu.rs:4:8
[INFO] [stdout]   |
[INFO] [stdout] 4 | struct JELU {
[INFO] [stdout]   |        ^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: associated function `new` is never used
[INFO] [stdout]   --> test6-nn/src/activation/activator/jelu.rs:12:12
[INFO] [stdout]    |
[INFO] [stdout] 11 | impl JELU {
[INFO] [stdout]    | --------- associated function in this implementation
[INFO] [stdout] 12 |     pub fn new(crossover_point: f64) -> JELU {
[INFO] [stdout]    |            ^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unused `Result` that must be used
[INFO] [stdout]    --> test6-nn/src/lib.rs:665:13
[INFO] [stdout]     |
[INFO] [stdout] 665 |             session_logger.write_training_session_file(initial_cost, network_config, optimizer_str);
[INFO] [stdout]     |             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[INFO] [stdout]     |
[INFO] [stdout]     = note: this `Result` may be an `Err` variant, which should be handled
[INFO] [stdout]     = note: `#[warn(unused_must_use)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] help: use `let _ = ...` to ignore the resulting value
[INFO] [stdout]     |
[INFO] [stdout] 665 |             let _ = session_logger.write_training_session_file(initial_cost, network_config, optimizer_str);
[INFO] [stdout]     |             +++++++
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unused variable: `normalized_distance`
[INFO] [stdout]    --> test7-nn-mnist-classifier/src/lib.rs:639:21
[INFO] [stdout]     |
[INFO] [stdout] 639 |                 let normalized_distance = euclidian_distance(&approx_gradients_big_v, &d_vec)
[INFO] [stdout]     |                     ^^^^^^^^^^^^^^^^^^^ help: if this is intentional, prefix it with an underscore: `_normalized_distance`
[INFO] [stdout]     |
[INFO] [stdout]     = note: `#[warn(unused_variables)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: struct `LayerGradients` is never constructed
[INFO] [stdout]   --> test7-nn-mnist-classifier/src/lib.rs:81:8
[INFO] [stdout]    |
[INFO] [stdout] 81 | struct LayerGradients {
[INFO] [stdout]    |        ^^^^^^^^^^^^^^
[INFO] [stdout]    |
[INFO] [stdout]    = note: `#[warn(dead_code)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: associated function `new` is never used
[INFO] [stdout]   --> test7-nn-mnist-classifier/src/lib.rs:87:8
[INFO] [stdout]    |
[INFO] [stdout] 86 | impl LayerGradients {
[INFO] [stdout]    | ------------------- associated function in this implementation
[INFO] [stdout] 87 |     fn new(weight_gradients: Matrix, bias_gradients: ColumnVector) -> Self {
[INFO] [stdout]    |        ^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: constant `GRADIENT_CHECK_EPSILON_SQUARED` is never used
[INFO] [stdout]    --> test7-nn-mnist-classifier/src/lib.rs:118:7
[INFO] [stdout]     |
[INFO] [stdout] 118 | const GRADIENT_CHECK_EPSILON_SQUARED: f64 = GRADIENT_CHECK_EPSILON * GRADIENT_CHECK_EPSILON;
[INFO] [stdout]     |       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: methods `err_output_layer` and `unroll_gradients` are never used
[INFO] [stdout]     --> test7-nn-mnist-classifier/src/lib.rs:328:8
[INFO] [stdout]      |
[INFO] [stdout]  148 | impl NeuralNetwork {
[INFO] [stdout]      | ------------------ methods in this implementation
[INFO] [stdout] ...
[INFO] [stdout]  328 |     fn err_output_layer(
[INFO] [stdout]      |        ^^^^^^^^^^^^^^^^
[INFO] [stdout] ...
[INFO] [stdout] 1128 |     fn unroll_gradients(
[INFO] [stdout]      |        ^^^^^^^^^^^^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unused `Result` that must be used
[INFO] [stdout]    --> test7-nn-mnist-classifier/src/lib.rs:719:13
[INFO] [stdout]     |
[INFO] [stdout] 719 |             session_logger.write_training_session_file(initial_cost, network_config, optimizer_str);
[INFO] [stdout]     |             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[INFO] [stdout]     |
[INFO] [stdout]     = note: this `Result` may be an `Err` variant, which should be handled
[INFO] [stdout]     = note: `#[warn(unused_must_use)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] help: use `let _ = ...` to ignore the resulting value
[INFO] [stdout]     |
[INFO] [stdout] 719 |             let _ = session_logger.write_training_session_file(initial_cost, network_config, optimizer_str);
[INFO] [stdout]     |             +++++++
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: variant `blue` should have an upper camel case name
[INFO] [stdout]   --> test2-mlp-classifier/src/main.rs:59:5
[INFO] [stdout]    |
[INFO] [stdout] 59 |     blue,
[INFO] [stdout]    |     ^^^^ help: convert the identifier to upper camel case: `Blue`
[INFO] [stdout]    |
[INFO] [stdout]    = note: `#[warn(non_camel_case_types)]` (part of `#[warn(nonstandard_style)]`) on by default
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: variant `orange` should have an upper camel case name
[INFO] [stdout]   --> test2-mlp-classifier/src/main.rs:60:5
[INFO] [stdout]    |
[INFO] [stdout] 60 |     orange,
[INFO] [stdout]    |     ^^^^^^ help: convert the identifier to upper camel case (notice the capitalization): `Orange`
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: function `e_to_the_x` is never used
[INFO] [stdout]  --> test1-autodiff/src/main.rs:3:4
[INFO] [stdout]   |
[INFO] [stdout] 3 | fn e_to_the_x(x: FT<f64>) -> FT<f64> {
[INFO] [stdout]   |    ^^^^^^^^^^
[INFO] [stdout]   |
[INFO] [stdout]   = note: `#[warn(dead_code)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unused import: `ndarray`
[INFO] [stdout]  --> test2-mlp-classifier/src/main.rs:5:5
[INFO] [stdout]   |
[INFO] [stdout] 5 | use ndarray::*;
[INFO] [stdout]   |     ^^^^^^^
[INFO] [stdout]   |
[INFO] [stdout]   = note: `#[warn(unused_imports)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unused variable: `i`
[INFO] [stdout]   --> test2-mlp-classifier/src/main.rs:80:9
[INFO] [stdout]    |
[INFO] [stdout] 80 |     for i in 0..n {
[INFO] [stdout]    |         ^ help: if this is intentional, prefix it with an underscore: `_i`
[INFO] [stdout]    |
[INFO] [stdout]    = note: `#[warn(unused_variables)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: struct `MultilayerPerceptron` is never constructed
[INFO] [stdout]  --> test2-mlp-classifier/src/main.rs:7:8
[INFO] [stdout]   |
[INFO] [stdout] 7 | struct MultilayerPerceptron {
[INFO] [stdout]   |        ^^^^^^^^^^^^^^^^^^^^
[INFO] [stdout]   |
[INFO] [stdout]   = note: `#[warn(dead_code)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: struct `MLPArchitecture` is never constructed
[INFO] [stdout]   --> test2-mlp-classifier/src/main.rs:14:8
[INFO] [stdout]    |
[INFO] [stdout] 14 | struct MLPArchitecture {
[INFO] [stdout]    |        ^^^^^^^^^^^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: associated function `new` is never used
[INFO] [stdout]   --> test2-mlp-classifier/src/main.rs:21:8
[INFO] [stdout]    |
[INFO] [stdout] 20 | impl MLPArchitecture {
[INFO] [stdout]    | -------------------- associated function in this implementation
[INFO] [stdout] 21 |     fn new(input_size: usize, hidden_layers: Vec<usize>, output_size: usize) -> Self {
[INFO] [stdout]    |        ^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stderr]    Compiling test4-multivariable-regression v0.1.0 (/opt/rustwide/workdir/test4-multivariable-regression)
[INFO] [stdout] warning: enum `MultivariableRegressionError` is never used
[INFO] [stdout]   --> test4-multivariable-regression/src/main.rs:36:6
[INFO] [stdout]    |
[INFO] [stdout] 36 | enum MultivariableRegressionError {
[INFO] [stdout]    |      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[INFO] [stdout]    |
[INFO] [stdout]    = note: `#[warn(dead_code)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: enum `InvalidDataError` is never used
[INFO] [stdout]   --> test4-multivariable-regression/src/main.rs:43:6
[INFO] [stdout]    |
[INFO] [stdout] 43 | enum InvalidDataError {
[INFO] [stdout]    |      ^^^^^^^^^^^^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stderr]    Compiling time-test v0.2.2
[INFO] [stderr]    Compiling test7-nn-mnist-classifier v0.1.0 (/opt/rustwide/workdir/test7-nn-mnist-classifier)
[INFO] [stderr]    Compiling test6-nn v0.1.0 (/opt/rustwide/workdir/test6-nn)
[INFO] [stdout] warning: unused `Result` that must be used
[INFO] [stdout]    --> test7-nn-mnist-classifier/src/main.rs:99:5
[INFO] [stdout]     |
[INFO] [stdout]  99 | /     nn.train_stochastic(
[INFO] [stdout] 100 | |         &training_data,
[INFO] [stdout] 101 | |         10_000,
[INFO] [stdout] ...   |
[INFO] [stdout] 110 | |         Some(session_logger),
[INFO] [stdout] 111 | |     );
[INFO] [stdout]     | |_____^
[INFO] [stdout]     |
[INFO] [stdout]     = note: this `Result` may be an `Err` variant, which should be handled
[INFO] [stdout]     = note: `#[warn(unused_must_use)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] help: use `let _ = ...` to ignore the resulting value
[INFO] [stdout]     |
[INFO] [stdout]  99 |     let _ = nn.train_stochastic(
[INFO] [stdout]     |     +++++++
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unused `Result` that must be used
[INFO] [stdout]    --> test6-nn/src/main.rs:92:5
[INFO] [stdout]     |
[INFO] [stdout]  92 | /     nn.train_stochastic(
[INFO] [stdout]  93 | |         &training_data,
[INFO] [stdout]  94 | |         10_000,
[INFO] [stdout] ...   |
[INFO] [stdout] 103 | |         Some(session_logger),
[INFO] [stdout] 104 | |     );
[INFO] [stdout]     | |_____^
[INFO] [stdout]     |
[INFO] [stdout]     = note: this `Result` may be an `Err` variant, which should be handled
[INFO] [stdout]     = note: `#[warn(unused_must_use)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] help: use `let _ = ...` to ignore the resulting value
[INFO] [stdout]     |
[INFO] [stdout]  92 |     let _ = nn.train_stochastic(
[INFO] [stdout]     |     +++++++
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: variable does not need to be mutable
[INFO] [stdout]    --> test7-nn-mnist-classifier/src/big_theta.rs:381:13
[INFO] [stdout]     |
[INFO] [stdout] 381 |         let mut big_theta = create_big_theta_for_test(&sizes);
[INFO] [stdout]     |             ----^^^^^^^^^
[INFO] [stdout]     |             |
[INFO] [stdout]     |             help: remove this `mut`
[INFO] [stdout]     |
[INFO] [stdout]     = note: `#[warn(unused_mut)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unused variable: `normalized_distance`
[INFO] [stdout]    --> test7-nn-mnist-classifier/src/lib.rs:639:21
[INFO] [stdout]     |
[INFO] [stdout] 639 |                 let normalized_distance = euclidian_distance(&approx_gradients_big_v, &d_vec)
[INFO] [stdout]     |                     ^^^^^^^^^^^^^^^^^^^ help: if this is intentional, prefix it with an underscore: `_normalized_distance`
[INFO] [stdout]     |
[INFO] [stdout]     = note: `#[warn(unused_variables)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unused variable: `lr`
[INFO] [stdout]     --> test7-nn-mnist-classifier/src/lib.rs:2242:13
[INFO] [stdout]      |
[INFO] [stdout] 2242 |         let lr = LeakyReLU::new(0.1);
[INFO] [stdout]      |             ^^ help: if this is intentional, prefix it with an underscore: `_lr`
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: constant `GRADIENT_CHECK_EPSILON_SQUARED` is never used
[INFO] [stdout]    --> test7-nn-mnist-classifier/src/lib.rs:118:7
[INFO] [stdout]     |
[INFO] [stdout] 118 | const GRADIENT_CHECK_EPSILON_SQUARED: f64 = GRADIENT_CHECK_EPSILON * GRADIENT_CHECK_EPSILON;
[INFO] [stdout]     |       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[INFO] [stdout]     |
[INFO] [stdout]     = note: `#[warn(dead_code)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: method `err_output_layer` is never used
[INFO] [stdout]    --> test7-nn-mnist-classifier/src/lib.rs:328:8
[INFO] [stdout]     |
[INFO] [stdout] 148 | impl NeuralNetwork {
[INFO] [stdout]     | ------------------ method in this implementation
[INFO] [stdout] ...
[INFO] [stdout] 328 |     fn err_output_layer(
[INFO] [stdout]     |        ^^^^^^^^^^^^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: variable does not need to be mutable
[INFO] [stdout]    --> test6-nn/src/big_theta.rs:381:13
[INFO] [stdout]     |
[INFO] [stdout] 381 |         let mut big_theta = create_big_theta_for_test(&sizes);
[INFO] [stdout]     |             ----^^^^^^^^^
[INFO] [stdout]     |             |
[INFO] [stdout]     |             help: remove this `mut`
[INFO] [stdout]     |
[INFO] [stdout]     = note: `#[warn(unused_mut)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unused `Result` that must be used
[INFO] [stdout]    --> test7-nn-mnist-classifier/src/lib.rs:719:13
[INFO] [stdout]     |
[INFO] [stdout] 719 |             session_logger.write_training_session_file(initial_cost, network_config, optimizer_str);
[INFO] [stdout]     |             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[INFO] [stdout]     |
[INFO] [stdout]     = note: this `Result` may be an `Err` variant, which should be handled
[INFO] [stdout]     = note: `#[warn(unused_must_use)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] help: use `let _ = ...` to ignore the resulting value
[INFO] [stdout]     |
[INFO] [stdout] 719 |             let _ = session_logger.write_training_session_file(initial_cost, network_config, optimizer_str);
[INFO] [stdout]     |             +++++++
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unused variable: `normalized_distance`
[INFO] [stdout]    --> test6-nn/src/lib.rs:585:21
[INFO] [stdout]     |
[INFO] [stdout] 585 |                 let normalized_distance = euclidian_distance(&approx_gradients_big_v, &d_vec)
[INFO] [stdout]     |                     ^^^^^^^^^^^^^^^^^^^ help: if this is intentional, prefix it with an underscore: `_normalized_distance`
[INFO] [stdout]     |
[INFO] [stdout]     = note: `#[warn(unused_variables)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: enum `Quadrant` is never used
[INFO] [stdout]  --> common/src/point.rs:7:6
[INFO] [stdout]   |
[INFO] [stdout] 7 | enum Quadrant {
[INFO] [stdout]   |      ^^^^^^^^
[INFO] [stdout]   |
[INFO] [stdout]   = note: `#[warn(dead_code)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: hiding a lifetime that's named elsewhere is confusing
[INFO] [stdout]    --> common/src/linalg/mod.rs:714:64
[INFO] [stdout]     |
[INFO] [stdout] 714 |     pub fn iter_with<'a>(&'a self, other: &'a ColumnVector) -> IterWith {
[INFO] [stdout]     |                           --               --                  ^^^^^^^^ the same lifetime is hidden here
[INFO] [stdout]     |                           |                |
[INFO] [stdout]     |                           |                the lifetime is named here
[INFO] [stdout]     |                           the lifetime is named here
[INFO] [stdout]     |
[INFO] [stdout]     = help: the same lifetime is referred to in inconsistent ways, making the signature confusing
[INFO] [stdout]     = note: `#[warn(mismatched_lifetime_syntaxes)]` on by default
[INFO] [stdout] help: consistently use `'a`
[INFO] [stdout]     |
[INFO] [stdout] 714 |     pub fn iter_with<'a>(&'a self, other: &'a ColumnVector) -> IterWith<'a> {
[INFO] [stdout]     |                                                                        ++++
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: constant `GRADIENT_CHECK_EPSILON_SQUARED` is never used
[INFO] [stdout]    --> test6-nn/src/lib.rs:118:7
[INFO] [stdout]     |
[INFO] [stdout] 118 | const GRADIENT_CHECK_EPSILON_SQUARED: f64 = GRADIENT_CHECK_EPSILON * GRADIENT_CHECK_EPSILON;
[INFO] [stdout]     |       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[INFO] [stdout]     |
[INFO] [stdout]     = note: `#[warn(dead_code)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unused `Result` that must be used
[INFO] [stdout]    --> test6-nn/src/lib.rs:665:13
[INFO] [stdout]     |
[INFO] [stdout] 665 |             session_logger.write_training_session_file(initial_cost, network_config, optimizer_str);
[INFO] [stdout]     |             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[INFO] [stdout]     |
[INFO] [stdout]     = note: this `Result` may be an `Err` variant, which should be handled
[INFO] [stdout]     = note: `#[warn(unused_must_use)]` (part of `#[warn(unused)]`) on by default
[INFO] [stdout] help: use `let _ = ...` to ignore the resulting value
[INFO] [stdout]     |
[INFO] [stdout] 665 |             let _ = session_logger.write_training_session_file(initial_cost, network_config, optimizer_str);
[INFO] [stdout]     |             +++++++
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stderr]     Finished `test` profile [unoptimized + debuginfo] target(s) in 3.83s
[INFO] running `Command { std: "docker" "inspect" "c7614941f6171fbf0cac1489305bad3ac759bbcff1c7be282cdde8412b6f2181", kill_on_drop: false }`
[INFO] running `Command { std: "docker" "rm" "-f" "c7614941f6171fbf0cac1489305bad3ac759bbcff1c7be282cdde8412b6f2181", kill_on_drop: false }`
[INFO] [stdout] c7614941f6171fbf0cac1489305bad3ac759bbcff1c7be282cdde8412b6f2181
[INFO] running `Command { std: "docker" "create" "-v" "/var/lib/crater-agent-workspace/builds/worker-0-tc1/target:/opt/rustwide/target:rw,Z" "-v" "/var/lib/crater-agent-workspace/builds/worker-0-tc1/source:/opt/rustwide/workdir:ro,Z" "-v" "/var/lib/crater-agent-workspace/cargo-home:/opt/rustwide/cargo-home:ro,Z" "-v" "/var/lib/crater-agent-workspace/rustup-home:/opt/rustwide/rustup-home:ro,Z" "-e" "SOURCE_DIR=/opt/rustwide/workdir" "-e" "CARGO_TARGET_DIR=/opt/rustwide/target" "-e" "CARGO_INCREMENTAL=0" "-e" "RUST_BACKTRACE=full" "-e" "RUSTFLAGS=--cap-lints=forbid" "-e" "RUSTDOCFLAGS=--cap-lints=forbid" "-e" "CARGO_HOME=/opt/rustwide/cargo-home" "-e" "RUSTUP_HOME=/opt/rustwide/rustup-home" "-w" "/opt/rustwide/workdir" "-m" "1610612736" "--user" "0:0" "--network" "none" "ghcr.io/rust-lang/crates-build-env/linux@sha256:d429b63d4308055ea97f60fb1d3dfca48854a00942f1bd2ad806beaf015945ec" "/opt/rustwide/cargo-home/bin/cargo" "+ec6f9a5b4413f74386267ef8efc93712c2ce6db6" "test" "--frozen", kill_on_drop: false }`
[INFO] [stdout] f3d6c5e1b298063b6465a4c819f30a9c5533ae7fbbe0338ee16ee693d293a08c
[INFO] running `Command { std: "docker" "start" "-a" "f3d6c5e1b298063b6465a4c819f30a9c5533ae7fbbe0338ee16ee693d293a08c", kill_on_drop: false }`
[INFO] [stderr] warning: virtual workspace defaulting to `resolver = "1"` despite one or more workspace members being on edition 2021 which implies `resolver = "2"`
[INFO] [stderr]   |
[INFO] [stderr]   = note: to keep the current resolver, specify `workspace.resolver = "1"` in the workspace root's manifest
[INFO] [stderr]   = note: to use the edition 2021 resolver, specify `workspace.resolver = "2"` in the workspace root's manifest
[INFO] [stderr]   = note: for more details see https://doc.rust-lang.org/cargo/reference/resolver.html#resolver-versions
[INFO] [stderr] warning: function `e_to_the_x` is never used
[INFO] [stderr]  --> test1-autodiff/src/main.rs:3:4
[INFO] [stderr]   |
[INFO] [stderr] 3 | fn e_to_the_x(x: FT<f64>) -> FT<f64> {
[INFO] [stderr]   |    ^^^^^^^^^^
[INFO] [stderr]   |
[INFO] [stderr]   = note: `#[warn(dead_code)]` (part of `#[warn(unused)]`) on by default
[INFO] [stderr] 
[INFO] [stderr] warning: `test1-autodiff` (bin "test1-autodiff" test) generated 1 warning
[INFO] [stderr] warning: variant `blue` should have an upper camel case name
[INFO] [stderr]   --> test2-mlp-classifier/src/main.rs:59:5
[INFO] [stderr]    |
[INFO] [stderr] 59 |     blue,
[INFO] [stderr]    |     ^^^^ help: convert the identifier to upper camel case: `Blue`
[INFO] [stderr]    |
[INFO] [stderr]    = note: `#[warn(non_camel_case_types)]` (part of `#[warn(nonstandard_style)]`) on by default
[INFO] [stderr] 
[INFO] [stderr] warning: variant `orange` should have an upper camel case name
[INFO] [stderr]   --> test2-mlp-classifier/src/main.rs:60:5
[INFO] [stderr]    |
[INFO] [stderr] 60 |     orange,
[INFO] [stderr]    |     ^^^^^^ help: convert the identifier to upper camel case (notice the capitalization): `Orange`
[INFO] [stderr] 
[INFO] [stderr] warning: unused import: `ndarray`
[INFO] [stderr]  --> test2-mlp-classifier/src/main.rs:5:5
[INFO] [stderr]   |
[INFO] [stderr] 5 | use ndarray::*;
[INFO] [stderr]   |     ^^^^^^^
[INFO] [stderr]   |
[INFO] [stderr]   = note: `#[warn(unused_imports)]` (part of `#[warn(unused)]`) on by default
[INFO] [stderr] 
[INFO] [stderr] warning: unused variable: `i`
[INFO] [stderr]   --> test2-mlp-classifier/src/main.rs:80:9
[INFO] [stderr]    |
[INFO] [stderr] 80 |     for i in 0..n {
[INFO] [stderr]    |         ^ help: if this is intentional, prefix it with an underscore: `_i`
[INFO] [stderr]    |
[INFO] [stderr]    = note: `#[warn(unused_variables)]` (part of `#[warn(unused)]`) on by default
[INFO] [stderr] 
[INFO] [stderr] warning: struct `MultilayerPerceptron` is never constructed
[INFO] [stderr]  --> test2-mlp-classifier/src/main.rs:7:8
[INFO] [stderr]   |
[INFO] [stderr] 7 | struct MultilayerPerceptron {
[INFO] [stderr]   |        ^^^^^^^^^^^^^^^^^^^^
[INFO] [stderr]   |
[INFO] [stderr]   = note: `#[warn(dead_code)]` (part of `#[warn(unused)]`) on by default
[INFO] [stderr] 
[INFO] [stderr] warning: struct `MLPArchitecture` is never constructed
[INFO] [stderr]   --> test2-mlp-classifier/src/main.rs:14:8
[INFO] [stderr]    |
[INFO] [stderr] 14 | struct MLPArchitecture {
[INFO] [stderr]    |        ^^^^^^^^^^^^^^^
[INFO] [stderr] 
[INFO] [stderr] warning: associated function `new` is never used
[INFO] [stderr]   --> test2-mlp-classifier/src/main.rs:21:8
[INFO] [stderr]    |
[INFO] [stderr] 20 | impl MLPArchitecture {
[INFO] [stderr]    | -------------------- associated function in this implementation
[INFO] [stderr] 21 |     fn new(input_size: usize, hidden_layers: Vec<usize>, output_size: usize) -> Self {
[INFO] [stderr]    |        ^^^
[INFO] [stderr] 
[INFO] [stderr] warning: `test2-mlp-classifier` (bin "test2-mlp-classifier" test) generated 7 warnings (run `cargo fix --bin "test2-mlp-classifier" -p test2-mlp-classifier --tests` to apply 1 suggestion)
[INFO] [stderr] warning: enum `Quadrant` is never used
[INFO] [stderr]  --> common/src/point.rs:7:6
[INFO] [stderr]   |
[INFO] [stderr] 7 | enum Quadrant {
[INFO] [stderr]   |      ^^^^^^^^
[INFO] [stderr]   |
[INFO] [stderr]   = note: `#[warn(dead_code)]` (part of `#[warn(unused)]`) on by default
[INFO] [stderr] 
[INFO] [stderr] warning: function `softmax` is never used
[INFO] [stderr]  --> common/src/softmax.rs:1:4
[INFO] [stderr]   |
[INFO] [stderr] 1 | fn softmax(logits: &[f64]) -> Vec<f64> {
[INFO] [stderr]   |    ^^^^^^^
[INFO] [stderr] 
[INFO] [stderr] warning: function `softmax_derivative` is never used
[INFO] [stderr]   --> common/src/softmax.rs:16:4
[INFO] [stderr]    |
[INFO] [stderr] 16 | fn softmax_derivative(logits: &[f64]) -> Vec<Vec<f64>> {
[INFO] [stderr]    |    ^^^^^^^^^^^^^^^^^^
[INFO] [stderr] 
[INFO] [stderr] warning: hiding a lifetime that's named elsewhere is confusing
[INFO] [stderr]    --> common/src/linalg/mod.rs:714:64
[INFO] [stderr]     |
[INFO] [stderr] 714 |     pub fn iter_with<'a>(&'a self, other: &'a ColumnVector) -> IterWith {
[INFO] [stderr]     |                           --               --                  ^^^^^^^^ the same lifetime is hidden here
[INFO] [stderr]     |                           |                |
[INFO] [stderr]     |                           |                the lifetime is named here
[INFO] [stderr]     |                           the lifetime is named here
[INFO] [stderr]     |
[INFO] [stderr]     = help: the same lifetime is referred to in inconsistent ways, making the signature confusing
[INFO] [stderr]     = note: `#[warn(mismatched_lifetime_syntaxes)]` on by default
[INFO] [stderr] help: consistently use `'a`
[INFO] [stderr]     |
[INFO] [stderr] 714 |     pub fn iter_with<'a>(&'a self, other: &'a ColumnVector) -> IterWith<'a> {
[INFO] [stderr]     |                                                                        ++++
[INFO] [stderr] 
[INFO] [stderr] warning: `common` (lib) generated 4 warnings (run `cargo fix --lib -p common` to apply 1 suggestion)
[INFO] [stderr] warning: `common` (lib test) generated 2 warnings (2 duplicates)
[INFO] [stderr] warning: enum `MultivariableRegressionError` is never used
[INFO] [stderr]   --> test4-multivariable-regression/src/main.rs:36:6
[INFO] [stderr]    |
[INFO] [stderr] 36 | enum MultivariableRegressionError {
[INFO] [stderr]    |      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[INFO] [stderr]    |
[INFO] [stderr]    = note: `#[warn(dead_code)]` (part of `#[warn(unused)]`) on by default
[INFO] [stderr] 
[INFO] [stderr] warning: enum `InvalidDataError` is never used
[INFO] [stderr]   --> test4-multivariable-regression/src/main.rs:43:6
[INFO] [stderr]    |
[INFO] [stderr] 43 | enum InvalidDataError {
[INFO] [stderr]    |      ^^^^^^^^^^^^^^^^
[INFO] [stderr] 
[INFO] [stderr] warning: `test4-multivariable-regression` (bin "test4-multivariable-regression" test) generated 2 warnings
[INFO] [stderr] warning: unused variable: `normalized_distance`
[INFO] [stderr]    --> test6-nn/src/lib.rs:585:21
[INFO] [stderr]     |
[INFO] [stderr] 585 |                 let normalized_distance = euclidian_distance(&approx_gradients_big_v, &d_vec)
[INFO] [stderr]     |                     ^^^^^^^^^^^^^^^^^^^ help: if this is intentional, prefix it with an underscore: `_normalized_distance`
[INFO] [stderr]     |
[INFO] [stderr]     = note: `#[warn(unused_variables)]` (part of `#[warn(unused)]`) on by default
[INFO] [stderr] 
[INFO] [stderr] warning: struct `LayerGradients` is never constructed
[INFO] [stderr]   --> test6-nn/src/lib.rs:81:8
[INFO] [stderr]    |
[INFO] [stderr] 81 | struct LayerGradients {
[INFO] [stderr]    |        ^^^^^^^^^^^^^^
[INFO] [stderr]    |
[INFO] [stderr]    = note: `#[warn(dead_code)]` (part of `#[warn(unused)]`) on by default
[INFO] [stderr] 
[INFO] [stderr] warning: associated function `new` is never used
[INFO] [stderr]   --> test6-nn/src/lib.rs:87:8
[INFO] [stderr]    |
[INFO] [stderr] 86 | impl LayerGradients {
[INFO] [stderr]    | ------------------- associated function in this implementation
[INFO] [stderr] 87 |     fn new(weight_gradients: Matrix, bias_gradients: ColumnVector) -> Self {
[INFO] [stderr]    |        ^^^
[INFO] [stderr] 
[INFO] [stderr] warning: constant `GRADIENT_CHECK_EPSILON_SQUARED` is never used
[INFO] [stderr]    --> test6-nn/src/lib.rs:118:7
[INFO] [stderr]     |
[INFO] [stderr] 118 | const GRADIENT_CHECK_EPSILON_SQUARED: f64 = GRADIENT_CHECK_EPSILON * GRADIENT_CHECK_EPSILON;
[INFO] [stderr]     |       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[INFO] [stderr] 
[INFO] [stderr] warning: method `unroll_gradients` is never used
[INFO] [stderr]     --> test6-nn/src/lib.rs:1074:8
[INFO] [stderr]      |
[INFO] [stderr]  146 | impl SimpleNeuralNetwork {
[INFO] [stderr]      | ------------------------ method in this implementation
[INFO] [stderr] ...
[INFO] [stderr] 1074 |     fn unroll_gradients(
[INFO] [stderr]      |        ^^^^^^^^^^^^^^^^
[INFO] [stderr] 
[INFO] [stderr] warning: struct `JELU` is never constructed
[INFO] [stderr]  --> test6-nn/src/activation/activator/jelu.rs:4:8
[INFO] [stderr]   |
[INFO] [stderr] 4 | struct JELU {
[INFO] [stderr]   |        ^^^^
[INFO] [stderr] 
[INFO] [stderr] warning: associated function `new` is never used
[INFO] [stderr]   --> test6-nn/src/activation/activator/jelu.rs:12:12
[INFO] [stderr]    |
[INFO] [stderr] 11 | impl JELU {
[INFO] [stderr]    | --------- associated function in this implementation
[INFO] [stderr] 12 |     pub fn new(crossover_point: f64) -> JELU {
[INFO] [stderr]    |            ^^^
[INFO] [stderr] 
[INFO] [stderr] warning: unused `Result` that must be used
[INFO] [stderr]    --> test6-nn/src/lib.rs:665:13
[INFO] [stderr]     |
[INFO] [stderr] 665 |             session_logger.write_training_session_file(initial_cost, network_config, optimizer_str);
[INFO] [stderr]     |             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[INFO] [stderr]     |
[INFO] [stderr]     = note: this `Result` may be an `Err` variant, which should be handled
[INFO] [stderr]     = note: `#[warn(unused_must_use)]` (part of `#[warn(unused)]`) on by default
[INFO] [stderr] help: use `let _ = ...` to ignore the resulting value
[INFO] [stderr]     |
[INFO] [stderr] 665 |             let _ = session_logger.write_training_session_file(initial_cost, network_config, optimizer_str);
[INFO] [stderr]     |             +++++++
[INFO] [stderr] 
[INFO] [stderr] warning: unused variable: `normalized_distance`
[INFO] [stderr]    --> test7-nn-mnist-classifier/src/lib.rs:639:21
[INFO] [stderr]     |
[INFO] [stderr] 639 |                 let normalized_distance = euclidian_distance(&approx_gradients_big_v, &d_vec)
[INFO] [stderr]     |                     ^^^^^^^^^^^^^^^^^^^ help: if this is intentional, prefix it with an underscore: `_normalized_distance`
[INFO] [stderr]     |
[INFO] [stderr]     = note: `#[warn(unused_variables)]` (part of `#[warn(unused)]`) on by default
[INFO] [stderr] 
[INFO] [stderr] warning: struct `LayerGradients` is never constructed
[INFO] [stderr]   --> test7-nn-mnist-classifier/src/lib.rs:81:8
[INFO] [stderr]    |
[INFO] [stderr] 81 | struct LayerGradients {
[INFO] [stderr]    |        ^^^^^^^^^^^^^^
[INFO] [stderr]    |
[INFO] [stderr]    = note: `#[warn(dead_code)]` (part of `#[warn(unused)]`) on by default
[INFO] [stderr] 
[INFO] [stderr] warning: associated function `new` is never used
[INFO] [stderr]   --> test7-nn-mnist-classifier/src/lib.rs:87:8
[INFO] [stderr]    |
[INFO] [stderr] 86 | impl LayerGradients {
[INFO] [stderr]    | ------------------- associated function in this implementation
[INFO] [stderr] 87 |     fn new(weight_gradients: Matrix, bias_gradients: ColumnVector) -> Self {
[INFO] [stderr]    |        ^^^
[INFO] [stderr] 
[INFO] [stderr] warning: constant `GRADIENT_CHECK_EPSILON_SQUARED` is never used
[INFO] [stderr]    --> test7-nn-mnist-classifier/src/lib.rs:118:7
[INFO] [stderr]     |
[INFO] [stderr] 118 | const GRADIENT_CHECK_EPSILON_SQUARED: f64 = GRADIENT_CHECK_EPSILON * GRADIENT_CHECK_EPSILON;
[INFO] [stderr]     |       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[INFO] [stderr] 
[INFO] [stderr] warning: methods `err_output_layer` and `unroll_gradients` are never used
[INFO] [stderr]     --> test7-nn-mnist-classifier/src/lib.rs:328:8
[INFO] [stderr]      |
[INFO] [stderr]  148 | impl NeuralNetwork {
[INFO] [stderr]      | ------------------ methods in this implementation
[INFO] [stderr] ...
[INFO] [stderr]  328 |     fn err_output_layer(
[INFO] [stderr]      |        ^^^^^^^^^^^^^^^^
[INFO] [stderr] ...
[INFO] [stderr] 1128 |     fn unroll_gradients(
[INFO] [stderr]      |        ^^^^^^^^^^^^^^^^
[INFO] [stderr] 
[INFO] [stderr] warning: unused `Result` that must be used
[INFO] [stderr]    --> test7-nn-mnist-classifier/src/lib.rs:719:13
[INFO] [stderr]     |
[INFO] [stderr] 719 |             session_logger.write_training_session_file(initial_cost, network_config, optimizer_str);
[INFO] [stderr]     |             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[INFO] [stderr]     |
[INFO] [stderr]     = note: this `Result` may be an `Err` variant, which should be handled
[INFO] [stderr]     = note: `#[warn(unused_must_use)]` (part of `#[warn(unused)]`) on by default
[INFO] [stderr] help: use `let _ = ...` to ignore the resulting value
[INFO] [stderr]     |
[INFO] [stderr] 719 |             let _ = session_logger.write_training_session_file(initial_cost, network_config, optimizer_str);
[INFO] [stderr]     |             +++++++
[INFO] [stderr] 
[INFO] [stderr] warning: variable does not need to be mutable
[INFO] [stderr]    --> test6-nn/src/big_theta.rs:381:13
[INFO] [stderr]     |
[INFO] [stderr] 381 |         let mut big_theta = create_big_theta_for_test(&sizes);
[INFO] [stderr]     |             ----^^^^^^^^^
[INFO] [stderr]     |             |
[INFO] [stderr]     |             help: remove this `mut`
[INFO] [stderr]     |
[INFO] [stderr]     = note: `#[warn(unused_mut)]` (part of `#[warn(unused)]`) on by default
[INFO] [stderr] 
[INFO] [stderr] warning: constant `GRADIENT_CHECK_EPSILON_SQUARED` is never used
[INFO] [stderr]    --> test6-nn/src/lib.rs:118:7
[INFO] [stderr]     |
[INFO] [stderr] 118 | const GRADIENT_CHECK_EPSILON_SQUARED: f64 = GRADIENT_CHECK_EPSILON * GRADIENT_CHECK_EPSILON;
[INFO] [stderr]     |       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[INFO] [stderr]     |
[INFO] [stderr]     = note: `#[warn(dead_code)]` (part of `#[warn(unused)]`) on by default
[INFO] [stderr] 
[INFO] [stderr] warning: variable does not need to be mutable
[INFO] [stderr]    --> test7-nn-mnist-classifier/src/big_theta.rs:381:13
[INFO] [stderr]     |
[INFO] [stderr] 381 |         let mut big_theta = create_big_theta_for_test(&sizes);
[INFO] [stderr]     |             ----^^^^^^^^^
[INFO] [stderr]     |             |
[INFO] [stderr]     |             help: remove this `mut`
[INFO] [stderr]     |
[INFO] [stderr]     = note: `#[warn(unused_mut)]` (part of `#[warn(unused)]`) on by default
[INFO] [stderr] 
[INFO] [stderr] warning: unused variable: `lr`
[INFO] [stderr]     --> test7-nn-mnist-classifier/src/lib.rs:2242:13
[INFO] [stderr]      |
[INFO] [stderr] 2242 |         let lr = LeakyReLU::new(0.1);
[INFO] [stderr]      |             ^^ help: if this is intentional, prefix it with an underscore: `_lr`
[INFO] [stderr] 
[INFO] [stderr] warning: constant `GRADIENT_CHECK_EPSILON_SQUARED` is never used
[INFO] [stderr]    --> test7-nn-mnist-classifier/src/lib.rs:118:7
[INFO] [stderr]     |
[INFO] [stderr] 118 | const GRADIENT_CHECK_EPSILON_SQUARED: f64 = GRADIENT_CHECK_EPSILON * GRADIENT_CHECK_EPSILON;
[INFO] [stderr]     |       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[INFO] [stderr]     |
[INFO] [stderr]     = note: `#[warn(dead_code)]` (part of `#[warn(unused)]`) on by default
[INFO] [stderr] 
[INFO] [stderr] warning: method `err_output_layer` is never used
[INFO] [stderr]    --> test7-nn-mnist-classifier/src/lib.rs:328:8
[INFO] [stderr]     |
[INFO] [stderr] 148 | impl NeuralNetwork {
[INFO] [stderr]     | ------------------ method in this implementation
[INFO] [stderr] ...
[INFO] [stderr] 328 |     fn err_output_layer(
[INFO] [stderr]     |        ^^^^^^^^^^^^^^^^
[INFO] [stderr] 
[INFO] [stderr] warning: `test6-nn` (lib) generated 8 warnings (run `cargo fix --lib -p test6-nn` to apply 1 suggestion)
[INFO] [stderr] warning: `test7-nn-mnist-classifier` (lib) generated 6 warnings (run `cargo fix --lib -p test7-nn-mnist-classifier` to apply 1 suggestion)
[INFO] [stderr] warning: `test6-nn` (lib test) generated 4 warnings (2 duplicates) (run `cargo fix --lib -p test6-nn --tests` to apply 1 suggestion)
[INFO] [stderr] warning: `test7-nn-mnist-classifier` (lib test) generated 6 warnings (2 duplicates) (run `cargo fix --lib -p test7-nn-mnist-classifier --tests` to apply 2 suggestions)
[INFO] [stderr] warning: unused `Result` that must be used
[INFO] [stderr]    --> test7-nn-mnist-classifier/src/main.rs:99:5
[INFO] [stderr]     |
[INFO] [stderr]  99 | /     nn.train_stochastic(
[INFO] [stderr] 100 | |         &training_data,
[INFO] [stderr] 101 | |         10_000,
[INFO] [stderr] ...   |
[INFO] [stderr] 110 | |         Some(session_logger),
[INFO] [stderr] 111 | |     );
[INFO] [stderr]     | |_____^
[INFO] [stderr]     |
[INFO] [stderr]     = note: this `Result` may be an `Err` variant, which should be handled
[INFO] [stderr]     = note: `#[warn(unused_must_use)]` (part of `#[warn(unused)]`) on by default
[INFO] [stderr] help: use `let _ = ...` to ignore the resulting value
[INFO] [stderr]     |
[INFO] [stderr]  99 |     let _ = nn.train_stochastic(
[INFO] [stderr]     |     +++++++
[INFO] [stderr] 
[INFO] [stderr] warning: unused `Result` that must be used
[INFO] [stderr]    --> test6-nn/src/main.rs:92:5
[INFO] [stderr]     |
[INFO] [stderr]  92 | /     nn.train_stochastic(
[INFO] [stderr]  93 | |         &training_data,
[INFO] [stderr]  94 | |         10_000,
[INFO] [stderr] ...   |
[INFO] [stderr] 103 | |         Some(session_logger),
[INFO] [stderr] 104 | |     );
[INFO] [stderr]     | |_____^
[INFO] [stderr]     |
[INFO] [stderr]     = note: this `Result` may be an `Err` variant, which should be handled
[INFO] [stderr]     = note: `#[warn(unused_must_use)]` (part of `#[warn(unused)]`) on by default
[INFO] [stderr] help: use `let _ = ...` to ignore the resulting value
[INFO] [stderr]     |
[INFO] [stderr]  92 |     let _ = nn.train_stochastic(
[INFO] [stderr]     |     +++++++
[INFO] [stderr] 
[INFO] [stderr] warning: `test7-nn-mnist-classifier` (bin "test7-nn-mnist-classifier" test) generated 1 warning
[INFO] [stderr] warning: `test6-nn` (bin "test6-nn" test) generated 1 warning
[INFO] [stderr]     Finished `test` profile [unoptimized + debuginfo] target(s) in 0.10s
[INFO] [stderr]      Running unittests src/lib.rs (/opt/rustwide/target/debug/deps/common-368a1ee38d35884c)
[INFO] [stdout] 
[INFO] [stdout] running 104 tests
[INFO] [stdout] test linalg::column_vector_tests::add_mut_works ... ok
[INFO] [stdout] test linalg::column_vector_tests::div_scalar_mut_works ... ok
[INFO] [stdout] test linalg::column_vector_tests::div_scalar_works ... ok
[INFO] [stdout] test linalg::column_vector_tests::dot_product_works ... ok
[INFO] [stdout] test linalg::column_vector_tests::elementwise_divide_in_place_works ... ok
[INFO] [stdout] test linalg::column_vector_tests::elementwise_divide_works ... ok
[INFO] [stdout] test linalg::column_vector_tests::can_create_a_column_vector_and_use_from_and_into ... ok
[INFO] [stdout] test linalg::column_vector_tests::empty_works ... ok
[INFO] [stdout] test linalg::column_vector_tests::fill_new_works ... ok
[INFO] [stdout] test linalg::column_vector_tests::hadamard_product_chaining_works ... ok
[INFO] [stdout] test linalg::column_vector_tests::add_works ... ok
[INFO] [stdout] test linalg::column_vector_tests::hadamard_product_in_place_works ... ok
[INFO] [stdout] test linalg::column_vector_tests::into_value_works ... ok
[INFO] [stdout] test linalg::column_vector_tests::minus_in_place_works ... ok
[INFO] [stdout] test linalg::column_vector_tests::hadamard_product_works ... ok
[INFO] [stdout] test linalg::column_vector_tests::mult_by_matrix_works ... ok
[INFO] [stdout] test linalg::column_vector_tests::multiply_by_scalar_works ... ok
[INFO] [stdout] test linalg::column_vector_tests::new_zero_vector_works ... ok
[INFO] [stdout] test linalg::column_vector_tests::plus_works ... ok
[INFO] [stdout] test linalg::column_vector_tests::test_basics ... ok
[INFO] [stdout] test linalg::column_vector_tests::test_add_scalar_to_each_element_in_place ... ok
[INFO] [stdout] test linalg::column_vector_tests::test_can_iterate_mutably_over_column_vector ... ok
[INFO] [stdout] test linalg::column_vector_tests::test_can_iterate_over_column_vector ... ok
[INFO] [stdout] test linalg::column_vector_tests::subtract_works ... ok
[INFO] [stdout] test linalg::column_vector_tests::test_elementwise_square_root_in_place ... ok
[INFO] [stdout] test linalg::column_vector_tests::test_mult_scalar_mut ... ok
[INFO] [stdout] test linalg::column_vector_tests::test_outer_product ... ok
[INFO] [stdout] test linalg::column_vector_tests::test_vec_length ... ok
[INFO] [stdout] test linalg::column_vector_tests::transpose_into_row_vector_matrix_works ... ok
[INFO] [stdout] test linalg::column_vector_tests::transpose_works ... ok
[INFO] [stdout] test linalg::column_vector_tests::test_can_do_double_iterate_over_column_vectors ... ok
[INFO] [stdout] test linalg::columns_matrix_builder_tests::test_columns_matrix_builder_with_chaining ... ok
[INFO] [stdout] test linalg::columns_matrix_builder_tests::test_columns_matrix_builder_with_non_chaining ... ok
[INFO] [stdout] test linalg::rows_matrix_builder_tests::test_row_matrix_builder_with_non_chaining ... ok
[INFO] [stdout] test linalg::rows_matrix_builder_tests::test_rows_matrix_builder_with_chaining ... ok
[INFO] [stdout] test linalg::test_components_in_the_module_root::test_euclidian_distance ... ok
[INFO] [stdout] test linalg::test_components_in_the_module_root::test_euclidian_length ... ok
[INFO] [stdout] test linalg::tests::add_in_place_serial_works ... ok
[INFO] [stdout] test linalg::tests::can_add_rows_and_get_values_at_specified_indexes ... ok
[INFO] [stdout] test linalg::tests::multiply_works ... ok
[INFO] [stdout] test linalg::tests::new_identity_matrix_works ... ok
[INFO] [stdout] test linalg::tests::plus_works ... ok
[INFO] [stdout] test linalg::tests::push_column_works ... ok
[INFO] [stdout] test linalg::tests::set_and_get_work ... ok
[INFO] [stdout] test linalg::tests::subtract ... ok
[INFO] [stdout] test linalg::tests::test_add_scalar_to_each_element_in_place ... ok
[INFO] [stdout] test linalg::tests::test_div_scalar ... ok
[INFO] [stdout] test linalg::tests::test_div_scalar_mut ... ok
[INFO] [stdout] test linalg::tests::test_elementwise_divide ... ok
[INFO] [stdout] test linalg::tests::add_in_place_par_works ... ok
[INFO] [stdout] test linalg::tests::test_elementwise_divide_product_in_place ... ok
[INFO] [stdout] test linalg::tests::test_extract_column ... ok
[INFO] [stdout] test linalg::tests::test_elementwise_square_root_in_place ... ok
[INFO] [stdout] test linalg::tests::test_extract_column_vector_as_matrix ... ok
[INFO] [stdout] test linalg::tests::add_mut_works ... ok
[INFO] [stdout] test linalg::tests::test_from_columns ... ok
[INFO] [stdout] test linalg::tests::test_hadamard_product ... ok
[INFO] [stdout] test linalg::tests::test_hadamard_product_chaining ... ok
[INFO] [stdout] test linalg::tests::test_hadamard_product_in_place ... ok
[INFO] [stdout] test linalg::tests::test_matrix_vector_multiplication ... ok
[INFO] [stdout] test linalg::tests::test_mult_scalar_mut ... ok
[INFO] [stdout] test linalg::tests::test_multiply_by_scalar ... ok
[INFO] [stdout] test linalg::tests::test_subtract_mut ... ok
[INFO] [stdout] test linalg::tests::test_vec_length ... ok
[INFO] [stdout] test linalg::tests::transpose_of_column_vector_mult_by_column_vector_works ... ok
[INFO] [stdout] test linalg::tests::transpose_works ... ok
[INFO] [stdout] test linalg::tests::transpose_works_for_column_vector ... ok
[INFO] [stdout] test old_matrix::columns_matrix_builder_tests::test_columns_matrix_builder_with_chaining ... ok
[INFO] [stdout] test old_matrix::columns_matrix_builder_tests::test_columns_matrix_builder_with_non_chaining ... ok
[INFO] [stdout] test old_matrix::rows_matrix_builder_tests::test_row_matrix_builder_with_non_chaining ... ok
[INFO] [stdout] test old_matrix::rows_matrix_builder_tests::test_rows_matrix_builder_with_chaining ... ok
[INFO] [stdout] test old_matrix::tests::add_in_place_works ... ok
[INFO] [stdout] test old_matrix::tests::can_add_rows_and_get_values_at_specified_indexes ... ok
[INFO] [stdout] test old_matrix::tests::minus_works ... ok
[INFO] [stdout] test linalg::tests::test_matrix_vector_multiplication_with_column_vector_type ... ok
[INFO] [stdout] test old_matrix::tests::multiply_works ... ok
[INFO] [stdout] test old_matrix::tests::new_identity_matrix_works ... ok
[INFO] [stdout] test old_matrix::tests::plus_works ... ok
[INFO] [stdout] test old_matrix::tests::push_column_works ... ok
[INFO] [stdout] test old_matrix::tests::set_and_get_work ... ok
[INFO] [stdout] test old_matrix::tests::subtract_works ... ok
[INFO] [stdout] test old_matrix::tests::test_div_scalar ... ok
[INFO] [stdout] test old_matrix::tests::test_divide_by_scalar_in_place ... ok
[INFO] [stdout] test old_matrix::tests::test_extract_column ... ok
[INFO] [stdout] test old_matrix::tests::test_from_columns ... ok
[INFO] [stdout] test old_matrix::tests::test_hadamard_product ... ok
[INFO] [stdout] test old_matrix::tests::test_hadamard_product_in_place ... ok
[INFO] [stdout] test old_matrix::tests::test_matrix_vector_multiplication ... ok
[INFO] [stdout] test old_matrix::tests::test_multiply_by_scalar ... ok
[INFO] [stdout] test old_matrix::tests::test_multiply_by_scalar_in_place ... ok
[INFO] [stdout] test old_matrix::tests::test_vec_length ... ok
[INFO] [stdout] test old_matrix::tests::transpose_of_column_vector_mult_by_column_vector_works ... ok
[INFO] [stdout] test old_matrix::tests::transpose_works ... ok
[INFO] [stdout] test old_matrix::tests::transpose_works_for_column_vector ... ok
[INFO] [stdout] test point::tests::it_works ... ok
[INFO] [stdout] test tests::dot_product_works ... ok
[INFO] [stdout] test tests::dot_returns_err_if_dimentions_are_zero ... ok
[INFO] [stdout] test softmax::tests::test_softmax_derivative_matrix_size ... ok
[INFO] [stdout] test softmax::tests::test_softmax_sum_to_one ... ok
[INFO] [stdout] test softmax::tests::test_softmax_output_range ... ok
[INFO] [stdout] test softmax::tests::test_softmax_derivative_uniform_input ... ok
[INFO] [stdout] test softmax::tests::test_softmax_derivative_off_diagonal ... ok
[INFO] [stdout] test softmax::tests::test_softmax_derivative_diagonal ... ok
[INFO] [stdout] test softmax::tests::test_softmax_numerical_stability ... ok
[INFO] [stdout] 
[INFO] [stdout] test result: ok. 104 passed; 0 failed; 0 ignored; 0 measured; 0 filtered out; finished in 0.05s
[INFO] [stdout] 
[INFO] [stderr]      Running unittests src/lib.rs (/opt/rustwide/target/debug/deps/metrics-013ab59ce2124619)
[INFO] [stdout] 
[INFO] [stdout] running 0 tests
[INFO] [stdout] 
[INFO] [stdout] test result: ok. 0 passed; 0 failed; 0 ignored; 0 measured; 0 filtered out; finished in 0.00s
[INFO] [stdout] 
[INFO] [stderr]      Running unittests src/lib.rs (/opt/rustwide/target/debug/deps/mnist_data-4f4e8dcd3bc0b830)
[INFO] [stdout] 
[INFO] [stdout] running 0 tests
[INFO] [stdout] 
[INFO] [stdout] test result: ok. 0 passed; 0 failed; 0 ignored; 0 measured; 0 filtered out; finished in 0.00s
[INFO] [stdout] 
[INFO] [stderr]      Running unittests src/main.rs (/opt/rustwide/target/debug/deps/test1_autodiff-2a24df975a689ff1)
[INFO] [stdout] 
[INFO] [stdout] running 0 tests
[INFO] [stdout] 
[INFO] [stdout] test result: ok. 0 passed; 0 failed; 0 ignored; 0 measured; 0 filtered out; finished in 0.00s
[INFO] [stdout] 
[INFO] [stderr]      Running unittests src/main.rs (/opt/rustwide/target/debug/deps/test2_mlp_classifier-1b0bb65920a53dfc)
[INFO] [stdout] 
[INFO] [stdout] running 0 tests
[INFO] [stdout] 
[INFO] [stdout] test result: ok. 0 passed; 0 failed; 0 ignored; 0 measured; 0 filtered out; finished in 0.00s
[INFO] [stdout] 
[INFO] [stderr]      Running unittests src/main.rs (/opt/rustwide/target/debug/deps/test3_simple_linear_regression-c1fdac3f92488ed1)
[INFO] [stdout] 
[INFO] [stdout] running 1 test
[INFO] [stdout] test tests::it_yields_the_correct_result ... ok
[INFO] [stdout] 
[INFO] [stdout] test result: ok. 1 passed; 0 failed; 0 ignored; 0 measured; 0 filtered out; finished in 0.00s
[INFO] [stdout] 
[INFO] [stderr]      Running unittests src/main.rs (/opt/rustwide/target/debug/deps/test4_multivariable_regression-af2790e59f467930)
[INFO] [stdout] 
[INFO] [stdout] running 7 tests
[INFO] [stdout] test tests::compute_partial_derivatives_v_works ... ok
[INFO] [stdout] test tests::cost_fn_works_for_non_zero_cost ... ok
[INFO] [stdout] test tests::hypothesis_v_works ... ok
[INFO] [stdout] test tests::it_yields_the_correct_result_for_2d ... ok
[INFO] [stdout] test tests::it_yields_the_correct_result_for_3d_ex1 ... ok
[INFO] [stdout] test tests::cost_fn_works_for_zero_cost ... ok
[INFO] [stdout] test tests::it_yields_the_correct_result_for_3d_ex2 ... ok
[INFO] [stdout] 
[INFO] [stdout] test result: ok. 7 passed; 0 failed; 0 ignored; 0 measured; 0 filtered out; finished in 0.00s
[INFO] [stdout] 
[INFO] [stderr]      Running unittests src/main.rs (/opt/rustwide/target/debug/deps/test5_playing_with_matrix_ideas-f9fd963292ba31ee)
[INFO] [stdout] 
[INFO] [stdout] running 0 tests
[INFO] [stdout] 
[INFO] [stdout] test result: ok. 0 passed; 0 failed; 0 ignored; 0 measured; 0 filtered out; finished in 0.00s
[INFO] [stdout] 
[INFO] [stderr]      Running unittests src/lib.rs (/opt/rustwide/target/debug/deps/test6_nn-c6794cb9103b4f63)
[INFO] [stdout] 
[INFO] [stdout] running 60 tests
[INFO] [stdout] test activation::activator::elu::tests::activate_prime_works ... ok
[INFO] [stdout] test activation::activator::jelu::tests::test_activate ... ok
[INFO] [stdout] test activation::activator::jelu::tests::test_activate_derivative ... ok
[INFO] [stdout] test activation::activator::relu::tests::activate_works ... ok
[INFO] [stdout] test activation::activator::sigmoid::tests::activate_works ... ok
[INFO] [stdout] test activation::activator::relu::tests::activate_prime_works ... ok
[INFO] [stdout] test activation::activator::tests::activate_derivative_vector_works ... ok
[INFO] [stdout] test activation::activator::tests::activate_vector_works ... ok
[INFO] [stdout] test activation::activator::sigmoid::tests::activate_derivative_works ... ok
[INFO] [stdout] test activation::elu::tests::activate_prime_works ... ok
[INFO] [stdout] test activation::elu::tests::activate_works ... ok
[INFO] [stdout] test activation::activator::elu::tests::activate_works ... ok
[INFO] [stdout] test activation::jelu::tests::test_activate ... ok
[INFO] [stdout] test activation::jelu::tests::test_activate_derivative ... ok
[INFO] [stdout] test activation::leaky_relu::tests::activate_works ... ok
[INFO] [stdout] test activation::relu::tests::activate_prime_works ... ok
[INFO] [stdout] test activation::leaky_relu::tests::activate_prime_works ... ok
[INFO] [stdout] test activation::relu::tests::activate_works ... ok
[INFO] [stdout] test activation::sigmoid::tests::activate_derivative_works ... ok
[INFO] [stdout] test activation::sigmoid::tests::activate_works ... ok
[INFO] [stdout] test big_theta::tests::create_big_theta_for_test_works ... ok
[INFO] [stdout] test big_theta::tests::create_big_theta_for_test_with_scale_factor_works ... ok
[INFO] [stdout] test big_theta::tests::divide_scalar_works ... ok
[INFO] [stdout] test big_theta::tests::test_add_in_place_works ... ok
[INFO] [stdout] test big_theta::tests::test_elementwise_divide_in_place_place_works ... ok
[INFO] [stdout] test big_theta::tests::test_get_weights_matrix_mut ... ok
[INFO] [stdout] test big_theta::tests::test_mult_scalar_return_new_works ... ok
[INFO] [stdout] test big_theta::tests::test_mult_scalar_in_place_works ... ok
[INFO] [stdout] test big_theta::tests::test_zero_from_sizes ... ok
[INFO] [stdout] test big_theta::tests::test_subtract_in_place_works ... ok
[INFO] [stdout] test big_theta::tests::test_divide_scalar_return_new_works ... ok
[INFO] [stdout] test big_theta::tests::test_elementwise_mult_in_place_place_works ... ok
[INFO] [stdout] test builder::test_nn_builder::test_nn_builder_manual_wb_values ... ok
[INFO] [stdout] test cost::tests::test_quadratic_cost_fn ... ok
[INFO] [stdout] test cost::tests::test_quadratic_cost_fn_dimension_mismatch ... ok
[INFO] [stdout] test tests::feed_forward_works_simple_three_layer ... ok
[INFO] [stdout] test tests::feed_forward_works_simple_three_layer_using_feed_forward_capturing ... ok
[INFO] [stdout] test tests::feed_forward_works_simple_two_layer ... ok
[INFO] [stdout] test tests::test_get_weight_matrix_shape ... ok
[INFO] [stdout] test tests::test_cost_single_tr_ex_multiple_output_neurons ... ok
[INFO] [stdout] test tests::test_cost_single_tr_ex_single_output_neuron ... ok
[INFO] [stdout] test tests::test_rev_layer_indexs_computation ... ok
[INFO] [stdout] test tests::test_unroll_gradients ... ok
[INFO] [stdout] test tests::test_reshape_weights_and_biases ... ok
[INFO] [stdout] test tests::test_unroll_weights_and_biases ... ok
[INFO] [stdout] test tests::test_z_vec ... ok
[INFO] [stdout] test tests::test_cost_for_training_set_iterative_impl ... ok
[INFO] [stdout] test builder::test_nn_builder::cannot_add_hiddlen_layer_before_input_layer - should panic ... ok
[INFO] [stdout] test builder::test_nn_builder::cannot_add_output_layer_before_input_layer - should panic ... ok
[INFO] [stdout] test tests::test_fan_in_fan_out ... ok
[INFO] [stdout] test builder::test_nn_builder::panics_on_hidden_layer_with_invalid_weight_or_bias_dimensions ... ok
[INFO] [stdout] test tests::test_nn_using_more_hidden_layers_with_more_neurons_with_leaky_relu_and_momentum_opt ... ok
[INFO] [stdout] test tests::test_nn_using_more_hidden_layers_with_more_neurons_with_leaky_relu_and_adam_opt ... ok
[INFO] [stdout] test tests::test_nn_using_more_hidden_layers_with_more_neurons_with_relu_hidden_layers ... ok
[INFO] [stdout] test tests::test_nn_using_more_hidden_layers_with_more_neurons ... ok
[INFO] [stdout] test tests::simple_jelu_test ... ok
[INFO] [stdout] test tests::simple_test_to_get_elu_sorted_out ... ok
[INFO] [stdout] test tests::simple_leaky_relu_test ... ok
[INFO] [stdout] test tests::test_nn_using_constructor_for_random_initial_weights_and_biases ... ok
[INFO] [stdout] test tests::test_nn ... ok
[INFO] [stdout] 
[INFO] [stdout] test result: ok. 60 passed; 0 failed; 0 ignored; 0 measured; 0 filtered out; finished in 17.67s
[INFO] [stdout] 
[INFO] [stderr] (took PT0.059050395S) (took PT0.067430285S) (took PT0.603154268S) (took PT3.618732016S) (took PT8.110553165S) (took PT17.654942007S)      Running unittests src/main.rs (/opt/rustwide/target/debug/deps/test6_nn-301afe822a4e035a)
[INFO] [stdout] 
[INFO] [stdout] running 0 tests
[INFO] [stdout] 
[INFO] [stdout] test result: ok. 0 passed; 0 failed; 0 ignored; 0 measured; 0 filtered out; finished in 0.00s
[INFO] [stdout] 
[INFO] [stderr]      Running unittests src/lib.rs (/opt/rustwide/target/debug/deps/test7_nn_mnist_classifier-f764bf58ddf160c2)
[INFO] [stdout] 
[INFO] [stdout] running 45 tests
[INFO] [stdout] test activation::relu::tests::activate_prime_works ... ok
[INFO] [stdout] test activation::leaky_relu::tests::activate_prime_works ... ok
[INFO] [stdout] test activation::relu::tests::activate_works ... ok
[INFO] [stdout] test activation::sigmoid::tests::activate_works ... ok
[INFO] [stdout] test big_theta::tests::create_big_theta_for_test_with_scale_factor_works ... ok
[INFO] [stdout] test big_theta::tests::create_big_theta_for_test_works ... ok
[INFO] [stdout] test big_theta::tests::test_add_in_place_works ... ok
[INFO] [stdout] test activation::leaky_relu::tests::activate_works ... ok
[INFO] [stdout] test big_theta::tests::divide_scalar_works ... ok
[INFO] [stdout] test activation::sigmoid::tests::activate_derivative_works ... ok
[INFO] [stdout] test big_theta::tests::test_elementwise_divide_in_place_place_works ... ok
[INFO] [stdout] test big_theta::tests::test_elementwise_mult_in_place_place_works ... ok
[INFO] [stdout] test big_theta::tests::test_get_weights_matrix_mut ... ok
[INFO] [stdout] test big_theta::tests::test_mult_scalar_in_place_works ... ok
[INFO] [stdout] test big_theta::tests::test_mult_scalar_return_new_works ... ok
[INFO] [stdout] test big_theta::tests::test_subtract_in_place_works ... ok
[INFO] [stdout] test big_theta::tests::test_zero_from_sizes ... ok
[INFO] [stdout] test builder::test_nn_builder::test_nn_builder_manual_wb_values ... ok
[INFO] [stdout] test cost::tests::test_quadratic_cost_fn ... ok
[INFO] [stdout] test cost::tests::test_quadratic_cost_fn_dimension_mismatch ... ok
[INFO] [stdout] test tests::feed_forward_works_simple_three_layer ... ok
[INFO] [stdout] test tests::feed_forward_works_simple_three_layer_using_feed_forward_capturing ... ok
[INFO] [stdout] test tests::feed_forward_works_simple_two_layer ... ok
[INFO] [stdout] test tests::test_cost_single_tr_ex_multiple_output_neurons ... ok
[INFO] [stdout] test tests::test_cost_single_tr_ex_single_output_neuron ... ok
[INFO] [stdout] test tests::test_get_weight_matrix_shape ... ok
[INFO] [stdout] test tests::test_reshape_weights_and_biases ... ok
[INFO] [stdout] test tests::test_rev_layer_indexs_computation ... ok
[INFO] [stdout] test tests::test_unroll_gradients ... ok
[INFO] [stdout] test tests::test_unroll_weights_and_biases ... ok
[INFO] [stdout] test tests::test_z_vec ... ok
[INFO] [stdout] test tests::test_cost_for_training_set_iterative_impl ... ok
[INFO] [stdout] test big_theta::tests::test_divide_scalar_return_new_works ... ok
[INFO] [stdout] test builder::test_nn_builder::cannot_add_output_layer_before_input_layer - should panic ... ok
[INFO] [stdout] test builder::test_nn_builder::panics_on_hidden_layer_with_invalid_weight_or_bias_dimensions ... ok
[INFO] [stdout] test builder::test_nn_builder::cannot_add_hiddlen_layer_before_input_layer - should panic ... ok
[INFO] [stdout] test tests::test_fan_in_fan_out ... ok
[INFO] [stdout] test tests::test_nn_using_more_hidden_layers_with_more_neurons_with_leaky_relu_and_momentum_opt ... ok
[INFO] [stdout] test tests::test_nn_using_more_hidden_layers_with_more_neurons_with_leaky_relu_and_adam_opt ... ok
[INFO] [stdout] test tests::test_nn_using_more_hidden_layers_with_more_neurons_with_relu_hidden_layers ... ok
[INFO] [stdout] test tests::test_nn_using_more_hidden_layers_with_more_neurons ... ok
[INFO] [stdout] test tests::simple_leaky_relu_test ... FAILED
[INFO] [stdout] test tests::simple_relu_test ... ok
[INFO] [stdout] test tests::test_nn_using_constructor_for_random_initial_weights_and_biases ... ok
[INFO] [stdout] test tests::test_nn ... ok
[INFO] [stdout] 
[INFO] [stdout] failures:
[INFO] [stdout] 
[INFO] [stdout] ---- tests::simple_leaky_relu_test stdout ----
[INFO] [stdout] initial weights:
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ 0.500000 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] initial biases:
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ 0.000000 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] initial cost across entire training set: 0.2550525381238995
[INFO] [stdout] finished ff for all training points - epoch 0
[INFO] [stdout] ed: 0.00000000029154188051633173
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.314657 0.596289 │
[INFO] [stdout] │ -1.290733 0.270209 │
[INFO] [stdout] │ -1.017688 -0.143997 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.362557 │
[INFO] [stdout] │ 0.595700 │
[INFO] [stdout] │ 1.408730 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 1
[INFO] [stdout] ed: 0.0000000002795790340265526
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.327406 0.609039 │
[INFO] [stdout] │ -1.287928 0.273014 │
[INFO] [stdout] │ -1.015855 -0.142163 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.356184 │
[INFO] [stdout] │ 0.597075 │
[INFO] [stdout] │ 1.409629 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 2
[INFO] [stdout] ed: 0.0000000002676548345563411
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.338733 0.620366 │
[INFO] [stdout] │ -1.285459 0.275483 │
[INFO] [stdout] │ -1.014241 -0.140549 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.350522 │
[INFO] [stdout] │ 0.598282 │
[INFO] [stdout] │ 1.410417 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 3
[INFO] [stdout] ed: 0.0000000002574574927139349
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.348894 0.630526 │
[INFO] [stdout] │ -1.283262 0.277680 │
[INFO] [stdout] │ -1.012805 -0.139113 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.345443 │
[INFO] [stdout] │ 0.599351 │
[INFO] [stdout] │ 1.411116 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 4
[INFO] [stdout] ed: 0.0000000002461656953437302
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.358083 0.639716 │
[INFO] [stdout] │ -1.281289 0.279653 │
[INFO] [stdout] │ -1.011515 -0.137823 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.340849 │
[INFO] [stdout] │ 0.600308 │
[INFO] [stdout] │ 1.411742 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 5
[INFO] [stdout] ed: 0.0000000002355629364499107
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.366455 0.648088 │
[INFO] [stdout] │ -1.279502 0.281439 │
[INFO] [stdout] │ -1.010347 -0.136656 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.336665 │
[INFO] [stdout] │ 0.601170 │
[INFO] [stdout] │ 1.412306 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 6
[INFO] [stdout] ed: 0.00000000022640135564716399
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.374130 0.655762 │
[INFO] [stdout] │ -1.277874 0.283068 │
[INFO] [stdout] │ -1.009283 -0.135591 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.332829 │
[INFO] [stdout] │ 0.601954 │
[INFO] [stdout] │ 1.412818 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 7
[INFO] [stdout] ed: 0.00000000021755900804502653
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.381204 0.662837 │
[INFO] [stdout] │ -1.276380 0.284562 │
[INFO] [stdout] │ -1.008306 -0.134615 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.329293 │
[INFO] [stdout] │ 0.602669 │
[INFO] [stdout] │ 1.413285 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 8
[INFO] [stdout] ed: 0.00000000020933304594261073
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.387758 0.669391 │
[INFO] [stdout] │ -1.275002 0.285940 │
[INFO] [stdout] │ -1.007405 -0.133714 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.326018 │
[INFO] [stdout] │ 0.603326 │
[INFO] [stdout] │ 1.413714 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 9
[INFO] [stdout] ed: 0.00000000020126327656944955
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.393856 0.675489 │
[INFO] [stdout] │ -1.273724 0.287217 │
[INFO] [stdout] │ -1.006570 -0.132879 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.322971 │
[INFO] [stdout] │ 0.603931 │
[INFO] [stdout] │ 1.414110 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 10
[INFO] [stdout] ed: 0.0000000001938825398635017
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.399553 0.681185 │
[INFO] [stdout] │ -1.272535 0.288407 │
[INFO] [stdout] │ -1.005793 -0.132101 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.320124 │
[INFO] [stdout] │ 0.604493 │
[INFO] [stdout] │ 1.414477 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 11
[INFO] [stdout] ed: 0.0000000001883301259950662
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.404893 0.686526 │
[INFO] [stdout] │ -1.271423 0.289519 │
[INFO] [stdout] │ -1.005066 -0.131374 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.317456 │
[INFO] [stdout] │ 0.605015 │
[INFO] [stdout] │ 1.414819 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 12
[INFO] [stdout] ed: 0.0000000001813312784184776
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.409915 0.691548 │
[INFO] [stdout] │ -1.270380 0.290562 │
[INFO] [stdout] │ -1.004384 -0.130693 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.314946 │
[INFO] [stdout] │ 0.605502 │
[INFO] [stdout] │ 1.415137 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 13
[INFO] [stdout] ed: 0.00000000017530498245741715
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.414652 0.696285 │
[INFO] [stdout] │ -1.269398 0.291543 │
[INFO] [stdout] │ -1.003743 -0.130051 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.312579 │
[INFO] [stdout] │ 0.605958 │
[INFO] [stdout] │ 1.415435 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 14
[INFO] [stdout] ed: 0.0000000001699084004126351
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.419132 0.700765 │
[INFO] [stdout] │ -1.268471 0.292470 │
[INFO] [stdout] │ -1.003137 -0.129445 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.310341 │
[INFO] [stdout] │ 0.606386 │
[INFO] [stdout] │ 1.415715 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 15
[INFO] [stdout] ed: 0.00000000016525936900977838
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.423380 0.705012 │
[INFO] [stdout] │ -1.267594 0.293348 │
[INFO] [stdout] │ -1.002563 -0.128872 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.308219 │
[INFO] [stdout] │ 0.606789 │
[INFO] [stdout] │ 1.415978 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 16
[INFO] [stdout] ed: 0.00000000016041887148407742
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.427416 0.709048 │
[INFO] [stdout] │ -1.266761 0.294180 │
[INFO] [stdout] │ -1.002019 -0.128327 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.306203 │
[INFO] [stdout] │ 0.607169 │
[INFO] [stdout] │ 1.416227 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 17
[INFO] [stdout] ed: 0.00000000015500003885446004
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.431259 0.712891 │
[INFO] [stdout] │ -1.265970 0.294972 │
[INFO] [stdout] │ -1.001501 -0.127810 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.304284 │
[INFO] [stdout] │ 0.607529 │
[INFO] [stdout] │ 1.416462 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 18
[INFO] [stdout] ed: 0.00000000015083071603849824
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.434925 0.716557 │
[INFO] [stdout] │ -1.265215 0.295727 │
[INFO] [stdout] │ -1.001008 -0.127316 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.302453 │
[INFO] [stdout] │ 0.607870 │
[INFO] [stdout] │ 1.416685 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 19
[INFO] [stdout] ed: 0.00000000014716306694980203
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.438428 0.720061 │
[INFO] [stdout] │ -1.264494 0.296448 │
[INFO] [stdout] │ -1.000537 -0.126845 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.300703 │
[INFO] [stdout] │ 0.608193 │
[INFO] [stdout] │ 1.416896 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 20
[INFO] [stdout] ed: 0.00000000014308560527251321
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.441782 0.723415 │
[INFO] [stdout] │ -1.263804 0.297138 │
[INFO] [stdout] │ -1.000086 -0.126394 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.299028 │
[INFO] [stdout] │ 0.608501 │
[INFO] [stdout] │ 1.417097 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 21
[INFO] [stdout] ed: 0.0000000001390534399045915
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.444998 0.726630 │
[INFO] [stdout] │ -1.263142 0.297799 │
[INFO] [stdout] │ -0.999654 -0.125962 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.297422 │
[INFO] [stdout] │ 0.608794 │
[INFO] [stdout] │ 1.417289 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 22
[INFO] [stdout] ed: 0.00000000013607588458313918
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.448085 0.729717 │
[INFO] [stdout] │ -1.262507 0.298434 │
[INFO] [stdout] │ -0.999239 -0.125547 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.295880 │
[INFO] [stdout] │ 0.609073 │
[INFO] [stdout] │ 1.417471 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 23
[INFO] [stdout] ed: 0.0000000001322878873322044
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.451053 0.732686 │
[INFO] [stdout] │ -1.261897 0.299045 │
[INFO] [stdout] │ -0.998840 -0.125148 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.294398 │
[INFO] [stdout] │ 0.609340 │
[INFO] [stdout] │ 1.417646 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 24
[INFO] [stdout] ed: 0.0000000001288219950790675
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.453910 0.735543 │
[INFO] [stdout] │ -1.261309 0.299633 │
[INFO] [stdout] │ -0.998455 -0.124764 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.292971 │
[INFO] [stdout] │ 0.609595 │
[INFO] [stdout] │ 1.417812 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 25
[INFO] [stdout] ed: 0.00000000012597251563478938
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.456664 0.738297 │
[INFO] [stdout] │ -1.260742 0.300199 │
[INFO] [stdout] │ -0.998085 -0.124393 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.291597 │
[INFO] [stdout] │ 0.609839 │
[INFO] [stdout] │ 1.417972 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 26
[INFO] [stdout] ed: 0.00000000012324960869649938
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.459321 0.740954 │
[INFO] [stdout] │ -1.260195 0.300747 │
[INFO] [stdout] │ -0.997727 -0.124036 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.290270 │
[INFO] [stdout] │ 0.610074 │
[INFO] [stdout] │ 1.418125 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 27
[INFO] [stdout] ed: 0.0000000001210502409462599
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.461887 0.743520 │
[INFO] [stdout] │ -1.259666 0.301275 │
[INFO] [stdout] │ -0.997382 -0.123690 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.288989 │
[INFO] [stdout] │ 0.610299 │
[INFO] [stdout] │ 1.418272 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 28
[INFO] [stdout] ed: 0.00000000011820066495503648
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.464369 0.746001 │
[INFO] [stdout] │ -1.259155 0.301787 │
[INFO] [stdout] │ -0.997047 -0.123356 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.287750 │
[INFO] [stdout] │ 0.610515 │
[INFO] [stdout] │ 1.418413 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 29
[INFO] [stdout] ed: 0.0000000001158205343316439
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.466770 0.748402 │
[INFO] [stdout] │ -1.258659 0.302283 │
[INFO] [stdout] │ -0.996723 -0.123032 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.286552 │
[INFO] [stdout] │ 0.610722 │
[INFO] [stdout] │ 1.418549 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 30
[INFO] [stdout] ed: 0.0000000001132293693451496
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.469096 0.750728 │
[INFO] [stdout] │ -1.258178 0.302763 │
[INFO] [stdout] │ -0.996409 -0.122718 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.285391 │
[INFO] [stdout] │ 0.610922 │
[INFO] [stdout] │ 1.418680 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 31
[INFO] [stdout] ed: 0.00000000011128370573957808
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.471350 0.752983 │
[INFO] [stdout] │ -1.257712 0.303230 │
[INFO] [stdout] │ -0.996104 -0.122413 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.284266 │
[INFO] [stdout] │ 0.611115 │
[INFO] [stdout] │ 1.418806 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 32
[INFO] [stdout] ed: 0.00000000010869900593479355
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.473538 0.755170 │
[INFO] [stdout] │ -1.257259 0.303683 │
[INFO] [stdout] │ -0.995808 -0.122117 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.283174 │
[INFO] [stdout] │ 0.611300 │
[INFO] [stdout] │ 1.418927 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 33
[INFO] [stdout] ed: 0.00000000010709907445501241
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.475662 0.757294 │
[INFO] [stdout] │ -1.256818 0.304123 │
[INFO] [stdout] │ -0.995521 -0.121829 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.282115 │
[INFO] [stdout] │ 0.611480 │
[INFO] [stdout] │ 1.419044 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 34
[INFO] [stdout] ed: 0.00000000010514065316918663
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.477726 0.759358 │
[INFO] [stdout] │ -1.256390 0.304552 │
[INFO] [stdout] │ -0.995240 -0.121549 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.281085 │
[INFO] [stdout] │ 0.611653 │
[INFO] [stdout] │ 1.419157 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 35
[INFO] [stdout] ed: 0.00000000010235547834085052
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.479732 0.761365 │
[INFO] [stdout] │ -1.255973 0.304969 │
[INFO] [stdout] │ -0.994968 -0.121276 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.280084 │
[INFO] [stdout] │ 0.611820 │
[INFO] [stdout] │ 1.419266 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 36
[INFO] [stdout] ed: 0.00000000010025791716025031
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.481685 0.763317 │
[INFO] [stdout] │ -1.255566 0.305376 │
[INFO] [stdout] │ -0.994702 -0.121010 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.279110 │
[INFO] [stdout] │ 0.611981 │
[INFO] [stdout] │ 1.419372 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 37
[INFO] [stdout] ed: 0.00000000009946669593830356
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.483586 0.765218 │
[INFO] [stdout] │ -1.255169 0.305772 │
[INFO] [stdout] │ -0.994443 -0.120751 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.278162 │
[INFO] [stdout] │ 0.612137 │
[INFO] [stdout] │ 1.419474 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 38
[INFO] [stdout] ed: 0.00000000009771007791746039
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.485437 0.767070 │
[INFO] [stdout] │ -1.254782 0.306159 │
[INFO] [stdout] │ -0.994190 -0.120498 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.277238 │
[INFO] [stdout] │ 0.612289 │
[INFO] [stdout] │ 1.419573 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 39
[INFO] [stdout] ed: 0.00000000009478040432844307
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.487242 0.768875 │
[INFO] [stdout] │ -1.254404 0.306537 │
[INFO] [stdout] │ -0.993943 -0.120251 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.276338 │
[INFO] [stdout] │ 0.612435 │
[INFO] [stdout] │ 1.419668 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 40
[INFO] [stdout] ed: 0.00000000009332818891324012
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.489003 0.770635 │
[INFO] [stdout] │ -1.254035 0.306906 │
[INFO] [stdout] │ -0.993702 -0.120010 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.275460 │
[INFO] [stdout] │ 0.612577 │
[INFO] [stdout] │ 1.419761 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 41
[INFO] [stdout] ed: 0.00000000009194131254153872
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.490720 0.772353 │
[INFO] [stdout] │ -1.253674 0.307267 │
[INFO] [stdout] │ -0.993466 -0.119774 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.274603 │
[INFO] [stdout] │ 0.612715 │
[INFO] [stdout] │ 1.419851 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 42
[INFO] [stdout] ed: 0.0000000000910261202651169
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.492397 0.774030 │
[INFO] [stdout] │ -1.253321 0.307620 │
[INFO] [stdout] │ -0.993235 -0.119544 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.273767 │
[INFO] [stdout] │ 0.612848 │
[INFO] [stdout] │ 1.419938 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 43
[INFO] [stdout] ed: 0.00000000008972035744855965
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.494035 0.775668 │
[INFO] [stdout] │ -1.252976 0.307966 │
[INFO] [stdout] │ -0.993009 -0.119318 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.272951 │
[INFO] [stdout] │ 0.612978 │
[INFO] [stdout] │ 1.420023 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 44
[INFO] [stdout] ed: 0.00000000008826975858937712
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.495636 0.777268 │
[INFO] [stdout] │ -1.252637 0.308304 │
[INFO] [stdout] │ -0.992788 -0.119097 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.272153 │
[INFO] [stdout] │ 0.613103 │
[INFO] [stdout] │ 1.420105 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 45
[INFO] [stdout] ed: 0.00000000008610029781121507
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.497201 0.778833 │
[INFO] [stdout] │ -1.252306 0.308636 │
[INFO] [stdout] │ -0.992572 -0.118880 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.271373 │
[INFO] [stdout] │ 0.613226 │
[INFO] [stdout] │ 1.420185 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 46
[INFO] [stdout] ed: 0.00000000008567362691542487
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.498732 0.780364 │
[INFO] [stdout] │ -1.251981 0.308961 │
[INFO] [stdout] │ -0.992359 -0.118668 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.270610 │
[INFO] [stdout] │ 0.613344 │
[INFO] [stdout] │ 1.420262 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 47
[INFO] [stdout] ed: 0.00000000008398956797953571
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.500229 0.781862 │
[INFO] [stdout] │ -1.251662 0.309280 │
[INFO] [stdout] │ -0.992151 -0.118459 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.269863 │
[INFO] [stdout] │ 0.613460 │
[INFO] [stdout] │ 1.420338 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 48
[INFO] [stdout] ed: 0.00000000008274729868110336
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.501695 0.783328 │
[INFO] [stdout] │ -1.251349 0.309593 │
[INFO] [stdout] │ -0.991947 -0.118255 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.269132 │
[INFO] [stdout] │ 0.613572 │
[INFO] [stdout] │ 1.420411 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 49
[INFO] [stdout] ed: 0.00000000008012775949739517
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.503131 0.784764 │
[INFO] [stdout] │ -1.251042 0.309900 │
[INFO] [stdout] │ -0.991746 -0.118054 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.268417 │
[INFO] [stdout] │ 0.613681 │
[INFO] [stdout] │ 1.420482 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 50
[INFO] [stdout] ed: 0.00000000008040237743388802
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.504538 0.786170 │
[INFO] [stdout] │ -1.250741 0.310201 │
[INFO] [stdout] │ -0.991549 -0.117857 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.267716 │
[INFO] [stdout] │ 0.613787 │
[INFO] [stdout] │ 1.420552 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 51
[INFO] [stdout] ed: 0.00000000007912338998979216
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.505916 0.787548 │
[INFO] [stdout] │ -1.250445 0.310497 │
[INFO] [stdout] │ -0.991356 -0.117664 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.267030 │
[INFO] [stdout] │ 0.613890 │
[INFO] [stdout] │ 1.420619 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 52
[INFO] [stdout] ed: 0.00000000007745352111496623
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.507267 0.788900 │
[INFO] [stdout] │ -1.250154 0.310788 │
[INFO] [stdout] │ -0.991166 -0.117474 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.266356 │
[INFO] [stdout] │ 0.613991 │
[INFO] [stdout] │ 1.420685 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 53
[INFO] [stdout] ed: 0.00000000007662966811341797
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.508592 0.790225 │
[INFO] [stdout] │ -1.249867 0.311074 │
[INFO] [stdout] │ -0.990979 -0.117287 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.265696 │
[INFO] [stdout] │ 0.614088 │
[INFO] [stdout] │ 1.420749 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 54
[INFO] [stdout] ed: 0.00000000007611353621159724
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.509892 0.791525 │
[INFO] [stdout] │ -1.249586 0.311356 │
[INFO] [stdout] │ -0.990795 -0.117103 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.265049 │
[INFO] [stdout] │ 0.614184 │
[INFO] [stdout] │ 1.420811 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 55
[INFO] [stdout] ed: 0.00000000007525632165044585
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.511168 0.792800 │
[INFO] [stdout] │ -1.249309 0.311633 │
[INFO] [stdout] │ -0.990614 -0.116922 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.264414 │
[INFO] [stdout] │ 0.614277 │
[INFO] [stdout] │ 1.420872 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 56
[INFO] [stdout] ed: 0.00000000007425223287446583
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.512420 0.794053 │
[INFO] [stdout] │ -1.249037 0.311905 │
[INFO] [stdout] │ -0.990436 -0.116744 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.263790 │
[INFO] [stdout] │ 0.614367 │
[INFO] [stdout] │ 1.420931 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 57
[INFO] [stdout] ed: 0.00000000007251687193174645
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.513649 0.795282 │
[INFO] [stdout] │ -1.248768 0.312173 │
[INFO] [stdout] │ -0.990261 -0.116569 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.263178 │
[INFO] [stdout] │ 0.614456 │
[INFO] [stdout] │ 1.420989 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 58
[INFO] [stdout] ed: 0.00000000007183693976035397
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.514857 0.796490 │
[INFO] [stdout] │ -1.248504 0.312437 │
[INFO] [stdout] │ -0.990088 -0.116396 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.262576 │
[INFO] [stdout] │ 0.614542 │
[INFO] [stdout] │ 1.421045 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 59
[INFO] [stdout] ed: 0.00000000007097267680106004
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.516043 0.797676 │
[INFO] [stdout] │ -1.248244 0.312698 │
[INFO] [stdout] │ -0.989918 -0.116226 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.261986 │
[INFO] [stdout] │ 0.614626 │
[INFO] [stdout] │ 1.421100 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 60
[INFO] [stdout] ed: 0.00000000007024323369385222
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.517209 0.798842 │
[INFO] [stdout] │ -1.247987 0.312954 │
[INFO] [stdout] │ -0.989750 -0.116059 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.261405 │
[INFO] [stdout] │ 0.614707 │
[INFO] [stdout] │ 1.421153 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 61
[INFO] [stdout] ed: 0.00000000006868770366728126
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.518355 0.799988 │
[INFO] [stdout] │ -1.247735 0.313207 │
[INFO] [stdout] │ -0.989585 -0.115894 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.260835 │
[INFO] [stdout] │ 0.614787 │
[INFO] [stdout] │ 1.421205 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 62
[INFO] [stdout] ed: 0.00000000006855426982963212
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.519482 0.801115 │
[INFO] [stdout] │ -1.247485 0.313456 │
[INFO] [stdout] │ -0.989422 -0.115731 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.260274 │
[INFO] [stdout] │ 0.614865 │
[INFO] [stdout] │ 1.421256 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 63
[INFO] [stdout] ed: 0.00000000006780387272225782
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.520590 0.802223 │
[INFO] [stdout] │ -1.247239 0.313702 │
[INFO] [stdout] │ -0.989262 -0.115570 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.259723 │
[INFO] [stdout] │ 0.614941 │
[INFO] [stdout] │ 1.421306 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 64
[INFO] [stdout] ed: 0.00000000006627650980648467
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.521680 0.803313 │
[INFO] [stdout] │ -1.246997 0.313945 │
[INFO] [stdout] │ -0.989103 -0.115412 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.259180 │
[INFO] [stdout] │ 0.615016 │
[INFO] [stdout] │ 1.421354 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 65
[INFO] [stdout] ed: 0.0000000000660557479477293
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.522753 0.804385 │
[INFO] [stdout] │ -1.246757 0.314184 │
[INFO] [stdout] │ -0.988947 -0.115255 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.258647 │
[INFO] [stdout] │ 0.615088 │
[INFO] [stdout] │ 1.421402 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 66
[INFO] [stdout] ed: 0.0000000000651690537022282
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.523809 0.805441 │
[INFO] [stdout] │ -1.246521 0.314420 │
[INFO] [stdout] │ -0.988793 -0.115101 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.258122 │
[INFO] [stdout] │ 0.615159 │
[INFO] [stdout] │ 1.421448 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 67
[INFO] [stdout] ed: 0.00000000006517113782681445
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.524848 0.806480 │
[INFO] [stdout] │ -1.246288 0.314654 │
[INFO] [stdout] │ -0.988640 -0.114949 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.257605 │
[INFO] [stdout] │ 0.615228 │
[INFO] [stdout] │ 1.421493 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 68
[INFO] [stdout] ed: 0.00000000006375566912805156
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.525871 0.807503 │
[INFO] [stdout] │ -1.246057 0.314884 │
[INFO] [stdout] │ -0.988490 -0.114798 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.257096 │
[INFO] [stdout] │ 0.615296 │
[INFO] [stdout] │ 1.421537 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 69
[INFO] [stdout] ed: 0.00000000006295309445593651
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.526878 0.808511 │
[INFO] [stdout] │ -1.245830 0.315112 │
[INFO] [stdout] │ -0.988341 -0.114649 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.256595 │
[INFO] [stdout] │ 0.615362 │
[INFO] [stdout] │ 1.421580 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 70
[INFO] [stdout] ed: 0.0000000000628103285886852
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.527871 0.809503 │
[INFO] [stdout] │ -1.245605 0.315337 │
[INFO] [stdout] │ -0.988194 -0.114503 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.256101 │
[INFO] [stdout] │ 0.615426 │
[INFO] [stdout] │ 1.421623 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 71
[INFO] [stdout] ed: 0.00000000006228441232738355
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.528848 0.810481 │
[INFO] [stdout] │ -1.245383 0.315559 │
[INFO] [stdout] │ -0.988049 -0.114358 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.255615 │
[INFO] [stdout] │ 0.615489 │
[INFO] [stdout] │ 1.421664 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 72
[INFO] [stdout] ed: 0.0000000000610145911450298
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.529812 0.811444 │
[INFO] [stdout] │ -1.245163 0.315778 │
[INFO] [stdout] │ -0.987906 -0.114214 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.255136 │
[INFO] [stdout] │ 0.615551 │
[INFO] [stdout] │ 1.421704 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 73
[INFO] [stdout] ed: 0.0000000000605851252918728
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.530761 0.812394 │
[INFO] [stdout] │ -1.244946 0.315996 │
[INFO] [stdout] │ -0.987764 -0.114072 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.254664 │
[INFO] [stdout] │ 0.615611 │
[INFO] [stdout] │ 1.421743 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 74
[INFO] [stdout] ed: 0.0000000000599121281475274
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.531697 0.813330 │
[INFO] [stdout] │ -1.244731 0.316210 │
[INFO] [stdout] │ -0.987624 -0.113932 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.254199 │
[INFO] [stdout] │ 0.615670 │
[INFO] [stdout] │ 1.421782 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 75
[INFO] [stdout] ed: 0.00000000005937657442468632
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.532620 0.814253 │
[INFO] [stdout] │ -1.244519 0.316423 │
[INFO] [stdout] │ -0.987485 -0.113793 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.253740 │
[INFO] [stdout] │ 0.615727 │
[INFO] [stdout] │ 1.421819 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 76
[INFO] [stdout] ed: 0.00000000005822719690955124
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.533530 0.815163 │
[INFO] [stdout] │ -1.244309 0.316633 │
[INFO] [stdout] │ -0.987348 -0.113656 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.253288 │
[INFO] [stdout] │ 0.615783 │
[INFO] [stdout] │ 1.421856 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 77
[INFO] [stdout] ed: 0.00000000005842624034300517
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.534428 0.816060 │
[INFO] [stdout] │ -1.244101 0.316841 │
[INFO] [stdout] │ -0.987212 -0.113520 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.252842 │
[INFO] [stdout] │ 0.615838 │
[INFO] [stdout] │ 1.421892 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 78
[INFO] [stdout] ed: 0.0000000000572949523324758
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.535313 0.816945 │
[INFO] [stdout] │ -1.243895 0.317046 │
[INFO] [stdout] │ -0.987078 -0.113386 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.252402 │
[INFO] [stdout] │ 0.615892 │
[INFO] [stdout] │ 1.421927 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 79
[INFO] [stdout] ed: 0.00000000005629718482672063
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.536186 0.817819 │
[INFO] [stdout] │ -1.243692 0.317250 │
[INFO] [stdout] │ -0.986945 -0.113253 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.251968 │
[INFO] [stdout] │ 0.615945 │
[INFO] [stdout] │ 1.421961 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 80
[INFO] [stdout] ed: 0.00000000005595872698663942
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.537048 0.818681 │
[INFO] [stdout] │ -1.243490 0.317451 │
[INFO] [stdout] │ -0.986813 -0.113121 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.251540 │
[INFO] [stdout] │ 0.615996 │
[INFO] [stdout] │ 1.421995 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 81
[INFO] [stdout] ed: 0.00000000005584488386955929
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.537899 0.819531 │
[INFO] [stdout] │ -1.243291 0.317651 │
[INFO] [stdout] │ -0.986683 -0.112991 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.251117 │
[INFO] [stdout] │ 0.616046 │
[INFO] [stdout] │ 1.422027 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 82
[INFO] [stdout] ed: 0.00000000005546438157823341
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.538738 0.820371 │
[INFO] [stdout] │ -1.243093 0.317849 │
[INFO] [stdout] │ -0.986554 -0.112862 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.250700 │
[INFO] [stdout] │ 0.616095 │
[INFO] [stdout] │ 1.422060 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 83
[INFO] [stdout] ed: 0.00000000005473802995958816
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.539567 0.821200 │
[INFO] [stdout] │ -1.242897 0.318044 │
[INFO] [stdout] │ -0.986426 -0.112734 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.250289 │
[INFO] [stdout] │ 0.616143 │
[INFO] [stdout] │ 1.422091 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 84
[INFO] [stdout] ed: 0.000000000054632871447177096
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.540386 0.822018 │
[INFO] [stdout] │ -1.242703 0.318238 │
[INFO] [stdout] │ -0.986299 -0.112608 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.249882 │
[INFO] [stdout] │ 0.616190 │
[INFO] [stdout] │ 1.422122 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 85
[INFO] [stdout] ed: 0.00000000005335073018565487
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.541194 0.822826 │
[INFO] [stdout] │ -1.242511 0.318430 │
[INFO] [stdout] │ -0.986174 -0.112482 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.249481 │
[INFO] [stdout] │ 0.616236 │
[INFO] [stdout] │ 1.422152 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 86
[INFO] [stdout] ed: 0.000000000052500475976943617
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.541992 0.823624 │
[INFO] [stdout] │ -1.242321 0.318621 │
[INFO] [stdout] │ -0.986049 -0.112358 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.249085 │
[INFO] [stdout] │ 0.616281 │
[INFO] [stdout] │ 1.422181 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 87
[INFO] [stdout] ed: 0.000000000052551060473142444
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.542780 0.824413 │
[INFO] [stdout] │ -1.242132 0.318810 │
[INFO] [stdout] │ -0.985926 -0.112235 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.248694 │
[INFO] [stdout] │ 0.616325 │
[INFO] [stdout] │ 1.422210 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 88
[INFO] [stdout] ed: 0.000000000052116329278342415
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.543559 0.825191 │
[INFO] [stdout] │ -1.241945 0.318997 │
[INFO] [stdout] │ -0.985804 -0.112112 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.248307 │
[INFO] [stdout] │ 0.616368 │
[INFO] [stdout] │ 1.422238 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 89
[INFO] [stdout] ed: 0.00000000005135406293750754
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.544328 0.825961 │
[INFO] [stdout] │ -1.241760 0.319182 │
[INFO] [stdout] │ -0.985683 -0.111991 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.247925 │
[INFO] [stdout] │ 0.616410 │
[INFO] [stdout] │ 1.422265 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 90
[INFO] [stdout] ed: 0.00000000005128814471830544
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.545089 0.826721 │
[INFO] [stdout] │ -1.241576 0.319366 │
[INFO] [stdout] │ -0.985563 -0.111871 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.247548 │
[INFO] [stdout] │ 0.616452 │
[INFO] [stdout] │ 1.422292 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 91
[INFO] [stdout] ed: 0.000000000051018535473853196
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.545840 0.827473 │
[INFO] [stdout] │ -1.241393 0.319548 │
[INFO] [stdout] │ -0.985444 -0.111752 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.247175 │
[INFO] [stdout] │ 0.616492 │
[INFO] [stdout] │ 1.422318 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 92
[INFO] [stdout] ed: 0.000000000050135150593819455
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.546583 0.828215 │
[INFO] [stdout] │ -1.241212 0.319729 │
[INFO] [stdout] │ -0.985326 -0.111634 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.246807 │
[INFO] [stdout] │ 0.616531 │
[INFO] [stdout] │ 1.422344 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 93
[INFO] [stdout] ed: 0.000000000049608671720533017
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.547317 0.828950 │
[INFO] [stdout] │ -1.241033 0.319909 │
[INFO] [stdout] │ -0.985209 -0.111517 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.246443 │
[INFO] [stdout] │ 0.616570 │
[INFO] [stdout] │ 1.422369 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 94
[INFO] [stdout] ed: 0.00000000004940913861395683
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.548043 0.829675 │
[INFO] [stdout] │ -1.240855 0.320087 │
[INFO] [stdout] │ -0.985093 -0.111401 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.246083 │
[INFO] [stdout] │ 0.616607 │
[INFO] [stdout] │ 1.422394 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 95
[INFO] [stdout] ed: 0.00000000004931632017888115
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.548760 0.830393 │
[INFO] [stdout] │ -1.240679 0.320263 │
[INFO] [stdout] │ -0.984977 -0.111286 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.245727 │
[INFO] [stdout] │ 0.616644 │
[INFO] [stdout] │ 1.422418 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 96
[INFO] [stdout] ed: 0.00000000004808825762738393
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.549470 0.831103 │
[INFO] [stdout] │ -1.240503 0.320438 │
[INFO] [stdout] │ -0.984863 -0.111171 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.245375 │
[INFO] [stdout] │ 0.616680 │
[INFO] [stdout] │ 1.422441 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 97
[INFO] [stdout] ed: 0.000000000048244293530014604
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.550172 0.831804 │
[INFO] [stdout] │ -1.240329 0.320612 │
[INFO] [stdout] │ -0.984749 -0.111058 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.245027 │
[INFO] [stdout] │ 0.616715 │
[INFO] [stdout] │ 1.422464 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 98
[INFO] [stdout] ed: 0.00000000004732864701722631
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.550866 0.832498 │
[INFO] [stdout] │ -1.240157 0.320785 │
[INFO] [stdout] │ -0.984637 -0.110945 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.244683 │
[INFO] [stdout] │ 0.616750 │
[INFO] [stdout] │ 1.422487 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 99
[INFO] [stdout] ed: 0.0000000000484094144403884
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.551553 0.833185 │
[INFO] [stdout] │ -1.239985 0.320956 │
[INFO] [stdout] │ -0.984525 -0.110833 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.244342 │
[INFO] [stdout] │ 0.616784 │
[INFO] [stdout] │ 1.422509 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 100
[INFO] [stdout] ed: 0.00000000004656958127982096
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.552232 0.833864 │
[INFO] [stdout] │ -1.239815 0.321126 │
[INFO] [stdout] │ -0.984414 -0.110722 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.244006 │
[INFO] [stdout] │ 0.616816 │
[INFO] [stdout] │ 1.422530 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 101
[INFO] [stdout] ed: 0.000000000046947567132353895
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.552904 0.834536 │
[INFO] [stdout] │ -1.239646 0.321295 │
[INFO] [stdout] │ -0.984304 -0.110612 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.243673 │
[INFO] [stdout] │ 0.616849 │
[INFO] [stdout] │ 1.422551 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 102
[INFO] [stdout] ed: 0.00000000004638113966005056
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.553569 0.835201 │
[INFO] [stdout] │ -1.239479 0.321463 │
[INFO] [stdout] │ -0.984194 -0.110502 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.243343 │
[INFO] [stdout] │ 0.616880 │
[INFO] [stdout] │ 1.422572 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 103
[INFO] [stdout] ed: 0.00000000004641867199254695
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.554227 0.835859 │
[INFO] [stdout] │ -1.239312 0.321629 │
[INFO] [stdout] │ -0.984085 -0.110394 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.243017 │
[INFO] [stdout] │ 0.616911 │
[INFO] [stdout] │ 1.422592 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 104
[INFO] [stdout] ed: 0.00000000004506626086938325
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.554878 0.836511 │
[INFO] [stdout] │ -1.239147 0.321795 │
[INFO] [stdout] │ -0.983977 -0.110286 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.242695 │
[INFO] [stdout] │ 0.616941 │
[INFO] [stdout] │ 1.422612 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 105
[INFO] [stdout] ed: 0.00000000004464395839669047
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.555523 0.837155 │
[INFO] [stdout] │ -1.238983 0.321959 │
[INFO] [stdout] │ -0.983870 -0.110178 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.242376 │
[INFO] [stdout] │ 0.616970 │
[INFO] [stdout] │ 1.422631 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 106
[INFO] [stdout] ed: 0.0000000000448752435554912
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.556161 0.837793 │
[INFO] [stdout] │ -1.238819 0.322122 │
[INFO] [stdout] │ -0.983764 -0.110072 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.242060 │
[INFO] [stdout] │ 0.616999 │
[INFO] [stdout] │ 1.422650 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 107
[INFO] [stdout] ed: 0.000000000044084185717702635
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.556792 0.838425 │
[INFO] [stdout] │ -1.238657 0.322285 │
[INFO] [stdout] │ -0.983658 -0.109966 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.241747 │
[INFO] [stdout] │ 0.617027 │
[INFO] [stdout] │ 1.422668 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 108
[INFO] [stdout] ed: 0.000000000043981122544870966
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.557417 0.839050 │
[INFO] [stdout] │ -1.238496 0.322446 │
[INFO] [stdout] │ -0.983553 -0.109861 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.241437 │
[INFO] [stdout] │ 0.617055 │
[INFO] [stdout] │ 1.422686 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 109
[INFO] [stdout] ed: 0.000000000044515917022573624
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.558037 0.839669 │
[INFO] [stdout] │ -1.238336 0.322606 │
[INFO] [stdout] │ -0.983448 -0.109756 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.241131 │
[INFO] [stdout] │ 0.617081 │
[INFO] [stdout] │ 1.422703 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 110
[INFO] [stdout] ed: 0.00000000004350485306718547
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.558650 0.840282 │
[INFO] [stdout] │ -1.238177 0.322765 │
[INFO] [stdout] │ -0.983344 -0.109653 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.240827 │
[INFO] [stdout] │ 0.617108 │
[INFO] [stdout] │ 1.422720 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 111
[INFO] [stdout] ed: 0.000000000043526233509713
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.559257 0.840889 │
[INFO] [stdout] │ -1.238019 0.322923 │
[INFO] [stdout] │ -0.983241 -0.109549 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.240527 │
[INFO] [stdout] │ 0.617133 │
[INFO] [stdout] │ 1.422737 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 112
[INFO] [stdout] ed: 0.000000000043013355746048644
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.559858 0.841491 │
[INFO] [stdout] │ -1.237861 0.323080 │
[INFO] [stdout] │ -0.983138 -0.109447 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.240229 │
[INFO] [stdout] │ 0.617158 │
[INFO] [stdout] │ 1.422753 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 113
[INFO] [stdout] ed: 0.00000000004286261572803475
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.560454 0.842086 │
[INFO] [stdout] │ -1.237705 0.323237 │
[INFO] [stdout] │ -0.983036 -0.109345 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.239935 │
[INFO] [stdout] │ 0.617183 │
[INFO] [stdout] │ 1.422769 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 114
[INFO] [stdout] ed: 0.00000000004260192570874989
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.561044 0.842676 │
[INFO] [stdout] │ -1.237550 0.323392 │
[INFO] [stdout] │ -0.982935 -0.109243 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.239643 │
[INFO] [stdout] │ 0.617206 │
[INFO] [stdout] │ 1.422785 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 115
[INFO] [stdout] ed: 0.000000000042461999937208105
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.561628 0.843261 │
[INFO] [stdout] │ -1.237395 0.323546 │
[INFO] [stdout] │ -0.982834 -0.109142 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.239354 │
[INFO] [stdout] │ 0.617230 │
[INFO] [stdout] │ 1.422800 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 116
[INFO] [stdout] ed: 0.00000000004197693641716875
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.562207 0.843839 │
[INFO] [stdout] │ -1.237242 0.323700 │
[INFO] [stdout] │ -0.982734 -0.109042 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.239067 │
[INFO] [stdout] │ 0.617252 │
[INFO] [stdout] │ 1.422815 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 117
[INFO] [stdout] ed: 0.00000000004060294146041692
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.562781 0.844413 │
[INFO] [stdout] │ -1.237089 0.323853 │
[INFO] [stdout] │ -0.982634 -0.108943 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.238784 │
[INFO] [stdout] │ 0.617274 │
[INFO] [stdout] │ 1.422829 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 118
[INFO] [stdout] ed: 0.000000000040921916206248923
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.563349 0.844981 │
[INFO] [stdout] │ -1.236937 0.324005 │
[INFO] [stdout] │ -0.982535 -0.108843 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.238503 │
[INFO] [stdout] │ 0.617296 │
[INFO] [stdout] │ 1.422843 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 119
[INFO] [stdout] ed: 0.00000000004041389169661547
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.563912 0.845545 │
[INFO] [stdout] │ -1.236786 0.324156 │
[INFO] [stdout] │ -0.982437 -0.108745 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.238224 │
[INFO] [stdout] │ 0.617317 │
[INFO] [stdout] │ 1.422857 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 120
[INFO] [stdout] ed: 0.00000000003986100723367152
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.564470 0.846103 │
[INFO] [stdout] │ -1.236636 0.324306 │
[INFO] [stdout] │ -0.982338 -0.108647 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.237948 │
[INFO] [stdout] │ 0.617338 │
[INFO] [stdout] │ 1.422871 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 121
[INFO] [stdout] ed: 0.000000000040164236336598444
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.565023 0.846656 │
[INFO] [stdout] │ -1.236486 0.324456 │
[INFO] [stdout] │ -0.982241 -0.108549 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.237675 │
[INFO] [stdout] │ 0.617358 │
[INFO] [stdout] │ 1.422884 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 122
[INFO] [stdout] ed: 0.00000000003981312003475258
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.565572 0.847204 │
[INFO] [stdout] │ -1.236337 0.324604 │
[INFO] [stdout] │ -0.982144 -0.108452 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.237404 │
[INFO] [stdout] │ 0.617377 │
[INFO] [stdout] │ 1.422896 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 123
[INFO] [stdout] ed: 0.000000000039779573720511656
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.566115 0.847748 │
[INFO] [stdout] │ -1.236189 0.324752 │
[INFO] [stdout] │ -0.982047 -0.108356 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.237135 │
[INFO] [stdout] │ 0.617396 │
[INFO] [stdout] │ 1.422909 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 124
[INFO] [stdout] ed: 0.00000000003898264671904779
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.566654 0.848286 │
[INFO] [stdout] │ -1.236042 0.324899 │
[INFO] [stdout] │ -0.981951 -0.108260 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.236869 │
[INFO] [stdout] │ 0.617415 │
[INFO] [stdout] │ 1.422921 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 125
[INFO] [stdout] ed: 0.00000000003838480591238097
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.567188 0.848820 │
[INFO] [stdout] │ -1.235896 0.325046 │
[INFO] [stdout] │ -0.981856 -0.108164 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.236605 │
[INFO] [stdout] │ 0.617433 │
[INFO] [stdout] │ 1.422932 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 126
[INFO] [stdout] ed: 0.00000000003918557107617217
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.567717 0.849350 │
[INFO] [stdout] │ -1.235750 0.325192 │
[INFO] [stdout] │ -0.981761 -0.108069 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.236344 │
[INFO] [stdout] │ 0.617450 │
[INFO] [stdout] │ 1.422944 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 127
[INFO] [stdout] ed: 0.00000000003883251360194059
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.568242 0.849875 │
[INFO] [stdout] │ -1.235605 0.325337 │
[INFO] [stdout] │ -0.981666 -0.107974 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.236085 │
[INFO] [stdout] │ 0.617467 │
[INFO] [stdout] │ 1.422955 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 128
[INFO] [stdout] ed: 0.000000000039011166142906854
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.568763 0.850395 │
[INFO] [stdout] │ -1.235461 0.325481 │
[INFO] [stdout] │ -0.981572 -0.107880 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.235828 │
[INFO] [stdout] │ 0.617484 │
[INFO] [stdout] │ 1.422966 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 129
[INFO] [stdout] ed: 0.00000000003775501685112932
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.569279 0.850912 │
[INFO] [stdout] │ -1.235317 0.325625 │
[INFO] [stdout] │ -0.981478 -0.107786 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.235573 │
[INFO] [stdout] │ 0.617500 │
[INFO] [stdout] │ 1.422976 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 130
[INFO] [stdout] ed: 0.00000000003781796641860626
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.569791 0.851423 │
[INFO] [stdout] │ -1.235174 0.325768 │
[INFO] [stdout] │ -0.981385 -0.107693 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.235320 │
[INFO] [stdout] │ 0.617516 │
[INFO] [stdout] │ 1.422987 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 131
[INFO] [stdout] ed: 0.00000000003793858817612443
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.570299 0.851931 │
[INFO] [stdout] │ -1.235032 0.325910 │
[INFO] [stdout] │ -0.981292 -0.107600 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.235070 │
[INFO] [stdout] │ 0.617531 │
[INFO] [stdout] │ 1.422997 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 132
[INFO] [stdout] ed: 0.000000000037195169432156286
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.570802 0.852435 │
[INFO] [stdout] │ -1.234890 0.326052 │
[INFO] [stdout] │ -0.981199 -0.107508 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.234821 │
[INFO] [stdout] │ 0.617546 │
[INFO] [stdout] │ 1.423006 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 133
[INFO] [stdout] ed: 0.000000000037594166809275064
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.571301 0.852934 │
[INFO] [stdout] │ -1.234749 0.326193 │
[INFO] [stdout] │ -0.981107 -0.107416 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.234575 │
[INFO] [stdout] │ 0.617560 │
[INFO] [stdout] │ 1.423016 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 134
[INFO] [stdout] ed: 0.00000000003721066238216065
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.571797 0.853429 │
[INFO] [stdout] │ -1.234608 0.326333 │
[INFO] [stdout] │ -0.981016 -0.107324 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.234330 │
[INFO] [stdout] │ 0.617574 │
[INFO] [stdout] │ 1.423025 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 135
[INFO] [stdout] ed: 0.000000000035958757030791266
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.572288 0.853921 │
[INFO] [stdout] │ -1.234468 0.326473 │
[INFO] [stdout] │ -0.980924 -0.107233 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.234088 │
[INFO] [stdout] │ 0.617587 │
[INFO] [stdout] │ 1.423034 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 136
[INFO] [stdout] ed: 0.000000000036259743448122453
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.572775 0.854408 │
[INFO] [stdout] │ -1.234329 0.326613 │
[INFO] [stdout] │ -0.980834 -0.107142 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.233848 │
[INFO] [stdout] │ 0.617601 │
[INFO] [stdout] │ 1.423042 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 137
[INFO] [stdout] ed: 0.00000000003712620291464505
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.573259 0.854892 │
[INFO] [stdout] │ -1.234190 0.326751 │
[INFO] [stdout] │ -0.980743 -0.107051 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.233609 │
[INFO] [stdout] │ 0.617613 │
[INFO] [stdout] │ 1.423050 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 138
[INFO] [stdout] ed: 0.00000000003537570310426535
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.573739 0.855371 │
[INFO] [stdout] │ -1.234052 0.326890 │
[INFO] [stdout] │ -0.980653 -0.106961 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.233373 │
[INFO] [stdout] │ 0.617626 │
[INFO] [stdout] │ 1.423058 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 139
[INFO] [stdout] ed: 0.00000000003546890003654667
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.574215 0.855847 │
[INFO] [stdout] │ -1.233915 0.327027 │
[INFO] [stdout] │ -0.980563 -0.106872 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.233138 │
[INFO] [stdout] │ 0.617637 │
[INFO] [stdout] │ 1.423066 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 140
[INFO] [stdout] ed: 0.00000000003590714853642835
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.574687 0.856320 │
[INFO] [stdout] │ -1.233777 0.327164 │
[INFO] [stdout] │ -0.980474 -0.106782 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.232905 │
[INFO] [stdout] │ 0.617649 │
[INFO] [stdout] │ 1.423074 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 141
[INFO] [stdout] ed: 0.00000000003569156249233321
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.575156 0.856788 │
[INFO] [stdout] │ -1.233641 0.327301 │
[INFO] [stdout] │ -0.980385 -0.106693 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.232674 │
[INFO] [stdout] │ 0.617660 │
[INFO] [stdout] │ 1.423081 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 142
[INFO] [stdout] ed: 0.000000000035120076727330525
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.575621 0.857254 │
[INFO] [stdout] │ -1.233505 0.327437 │
[INFO] [stdout] │ -0.980296 -0.106604 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.232445 │
[INFO] [stdout] │ 0.617671 │
[INFO] [stdout] │ 1.423088 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 143
[INFO] [stdout] ed: 0.00000000003503534777081123
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.576083 0.857715 │
[INFO] [stdout] │ -1.233370 0.327572 │
[INFO] [stdout] │ -0.980208 -0.106516 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.232217 │
[INFO] [stdout] │ 0.617681 │
[INFO] [stdout] │ 1.423095 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 144
[INFO] [stdout] ed: 0.00000000003460460937051788
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.576541 0.858173 │
[INFO] [stdout] │ -1.233235 0.327707 │
[INFO] [stdout] │ -0.980120 -0.106428 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.231992 │
[INFO] [stdout] │ 0.617691 │
[INFO] [stdout] │ 1.423101 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 145
[INFO] [stdout] ed: 0.00000000003452713835081577
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.576995 0.858628 │
[INFO] [stdout] │ -1.233100 0.327841 │
[INFO] [stdout] │ -0.980032 -0.106340 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.231768 │
[INFO] [stdout] │ 0.617701 │
[INFO] [stdout] │ 1.423107 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 146
[INFO] [stdout] ed: 0.000000000034373346404182664
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.577447 0.859079 │
[INFO] [stdout] │ -1.232966 0.327975 │
[INFO] [stdout] │ -0.979945 -0.106253 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.231546 │
[INFO] [stdout] │ 0.617710 │
[INFO] [stdout] │ 1.423113 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 147
[INFO] [stdout] ed: 0.000000000034287810145838166
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.577895 0.859527 │
[INFO] [stdout] │ -1.232833 0.328109 │
[INFO] [stdout] │ -0.979858 -0.106166 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.231325 │
[INFO] [stdout] │ 0.617719 │
[INFO] [stdout] │ 1.423119 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 148
[INFO] [stdout] ed: 0.00000000003410617267775528
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.578339 0.859972 │
[INFO] [stdout] │ -1.232700 0.328242 │
[INFO] [stdout] │ -0.979771 -0.106079 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.231106 │
[INFO] [stdout] │ 0.617727 │
[INFO] [stdout] │ 1.423125 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 149
[INFO] [stdout] ed: 0.00000000003357347688071942
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.578781 0.860413 │
[INFO] [stdout] │ -1.232567 0.328374 │
[INFO] [stdout] │ -0.979685 -0.105993 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.230889 │
[INFO] [stdout] │ 0.617736 │
[INFO] [stdout] │ 1.423130 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 150
[INFO] [stdout] ed: 0.000000000032813555699249994
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.579219 0.860852 │
[INFO] [stdout] │ -1.232435 0.328506 │
[INFO] [stdout] │ -0.979598 -0.105907 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.230673 │
[INFO] [stdout] │ 0.617743 │
[INFO] [stdout] │ 1.423135 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 151
[INFO] [stdout] ed: 0.000000000034093047660214655
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.579654 0.861287 │
[INFO] [stdout] │ -1.232304 0.328638 │
[INFO] [stdout] │ -0.979513 -0.105821 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.230459 │
[INFO] [stdout] │ 0.617751 │
[INFO] [stdout] │ 1.423140 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 152
[INFO] [stdout] ed: 0.00000000003329570392580815
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.580086 0.861719 │
[INFO] [stdout] │ -1.232173 0.328769 │
[INFO] [stdout] │ -0.979427 -0.105735 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.230246 │
[INFO] [stdout] │ 0.617758 │
[INFO] [stdout] │ 1.423145 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 153
[INFO] [stdout] ed: 0.00000000003350457024797297
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.580515 0.862148 │
[INFO] [stdout] │ -1.232042 0.328900 │
[INFO] [stdout] │ -0.979342 -0.105650 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.230035 │
[INFO] [stdout] │ 0.617765 │
[INFO] [stdout] │ 1.423149 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 154
[INFO] [stdout] ed: 0.00000000003218016885016127
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.580941 0.862574 │
[INFO] [stdout] │ -1.231912 0.329030 │
[INFO] [stdout] │ -0.979257 -0.105565 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.229826 │
[INFO] [stdout] │ 0.617771 │
[INFO] [stdout] │ 1.423153 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 155
[INFO] [stdout] ed: 0.00000000003252326581775055
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.581364 0.862996 │
[INFO] [stdout] │ -1.231782 0.329160 │
[INFO] [stdout] │ -0.979172 -0.105481 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.229618 │
[INFO] [stdout] │ 0.617777 │
[INFO] [stdout] │ 1.423157 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 156
[INFO] [stdout] ed: 0.00000000003255752007144847
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.581784 0.863416 │
[INFO] [stdout] │ -1.231652 0.329289 │
[INFO] [stdout] │ -0.979088 -0.105396 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.229411 │
[INFO] [stdout] │ 0.617783 │
[INFO] [stdout] │ 1.423161 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 157
[INFO] [stdout] ed: 0.00000000003259671033219122
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.582201 0.863833 │
[INFO] [stdout] │ -1.231523 0.329419 │
[INFO] [stdout] │ -0.979004 -0.105312 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.229206 │
[INFO] [stdout] │ 0.617789 │
[INFO] [stdout] │ 1.423165 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 158
[INFO] [stdout] ed: 0.000000000032745515716477886
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.582615 0.864248 │
[INFO] [stdout] │ -1.231394 0.329547 │
[INFO] [stdout] │ -0.978920 -0.105228 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.229003 │
[INFO] [stdout] │ 0.617794 │
[INFO] [stdout] │ 1.423168 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 159
[INFO] [stdout] ed: 0.000000000031751640177223967
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.583026 0.864659 │
[INFO] [stdout] │ -1.231266 0.329675 │
[INFO] [stdout] │ -0.978836 -0.105144 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.228801 │
[INFO] [stdout] │ 0.617799 │
[INFO] [stdout] │ 1.423171 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 160
[INFO] [stdout] ed: 0.00000000003164487343678479
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.583435 0.865068 │
[INFO] [stdout] │ -1.231138 0.329803 │
[INFO] [stdout] │ -0.978753 -0.105061 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.228600 │
[INFO] [stdout] │ 0.617803 │
[INFO] [stdout] │ 1.423174 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 161
[INFO] [stdout] ed: 0.00000000003161452960934124
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.583841 0.865473 │
[INFO] [stdout] │ -1.231011 0.329931 │
[INFO] [stdout] │ -0.978670 -0.104978 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.228400 │
[INFO] [stdout] │ 0.617808 │
[INFO] [stdout] │ 1.423177 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 162
[INFO] [stdout] ed: 0.000000000031295941113251224
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.584244 0.865876 │
[INFO] [stdout] │ -1.230884 0.330058 │
[INFO] [stdout] │ -0.978587 -0.104895 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.228202 │
[INFO] [stdout] │ 0.617812 │
[INFO] [stdout] │ 1.423180 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 163
[INFO] [stdout] ed: 0.0000000000310023762530578
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.584644 0.866277 │
[INFO] [stdout] │ -1.230757 0.330185 │
[INFO] [stdout] │ -0.978504 -0.104812 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.228006 │
[INFO] [stdout] │ 0.617815 │
[INFO] [stdout] │ 1.423182 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 164
[INFO] [stdout] ed: 0.00000000003069145274417046
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.585042 0.866674 │
[INFO] [stdout] │ -1.230631 0.330311 │
[INFO] [stdout] │ -0.978422 -0.104730 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.227810 │
[INFO] [stdout] │ 0.617819 │
[INFO] [stdout] │ 1.423184 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 165
[INFO] [stdout] ed: 0.000000000031178504720878034
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.585437 0.867070 │
[INFO] [stdout] │ -1.230505 0.330437 │
[INFO] [stdout] │ -0.978340 -0.104648 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.227616 │
[INFO] [stdout] │ 0.617822 │
[INFO] [stdout] │ 1.423186 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 166
[INFO] [stdout] ed: 0.00000000003140551564344246
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.585830 0.867462 │
[INFO] [stdout] │ -1.230379 0.330563 │
[INFO] [stdout] │ -0.978258 -0.104566 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.227424 │
[INFO] [stdout] │ 0.617824 │
[INFO] [stdout] │ 1.423188 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 167
[INFO] [stdout] ed: 0.00000000003086317207550339
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.586220 0.867852 │
[INFO] [stdout] │ -1.230254 0.330688 │
[INFO] [stdout] │ -0.978176 -0.104484 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.227232 │
[INFO] [stdout] │ 0.617827 │
[INFO] [stdout] │ 1.423190 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 168
[INFO] [stdout] ed: 0.00000000003034479786995861
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.586607 0.868239 │
[INFO] [stdout] │ -1.230129 0.330813 │
[INFO] [stdout] │ -0.978094 -0.104403 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.227042 │
[INFO] [stdout] │ 0.617829 │
[INFO] [stdout] │ 1.423191 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 169
[INFO] [stdout] ed: 0.00000000002976027744187914
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.586992 0.868624 │
[INFO] [stdout] │ -1.230004 0.330938 │
[INFO] [stdout] │ -0.978013 -0.104321 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.226853 │
[INFO] [stdout] │ 0.617831 │
[INFO] [stdout] │ 1.423192 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 170
[INFO] [stdout] ed: 0.00000000003071100947278588
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.587374 0.869007 │
[INFO] [stdout] │ -1.229879 0.331062 │
[INFO] [stdout] │ -0.977932 -0.104240 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.226666 │
[INFO] [stdout] │ 0.617833 │
[INFO] [stdout] │ 1.423193 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 171
[INFO] [stdout] ed: 0.0000000000300999095067095
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.587754 0.869387 │
[INFO] [stdout] │ -1.229755 0.331186 │
[INFO] [stdout] │ -0.977851 -0.104160 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.226479 │
[INFO] [stdout] │ 0.617834 │
[INFO] [stdout] │ 1.423194 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 172
[INFO] [stdout] ed: 0.00000000002976573268719783
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.588132 0.869765 │
[INFO] [stdout] │ -1.229632 0.331310 │
[INFO] [stdout] │ -0.977771 -0.104079 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.226294 │
[INFO] [stdout] │ 0.617835 │
[INFO] [stdout] │ 1.423195 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 173
[INFO] [stdout] ed: 0.000000000029996525028057964
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.588507 0.870140 │
[INFO] [stdout] │ -1.229508 0.331433 │
[INFO] [stdout] │ -0.977690 -0.103998 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.226110 │
[INFO] [stdout] │ 0.617836 │
[INFO] [stdout] │ 1.423196 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 174
[INFO] [stdout] ed: 0.000000000028917421516326296
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.588880 0.870513 │
[INFO] [stdout] │ -1.229385 0.331556 │
[INFO] [stdout] │ -0.977610 -0.103918 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.225927 │
[INFO] [stdout] │ 0.617837 │
[INFO] [stdout] │ 1.423196 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 175
[INFO] [stdout] ed: 0.000000000029767439142850614
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.589251 0.870883 │
[INFO] [stdout] │ -1.229262 0.331679 │
[INFO] [stdout] │ -0.977530 -0.103838 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.225746 │
[INFO] [stdout] │ 0.617837 │
[INFO] [stdout] │ 1.423196 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 176
[INFO] [stdout] ed: 0.00000000002939265831345841
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.589619 0.871252 │
[INFO] [stdout] │ -1.229140 0.331802 │
[INFO] [stdout] │ -0.977450 -0.103758 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.225565 │
[INFO] [stdout] │ 0.617837 │
[INFO] [stdout] │ 1.423196 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 177
[INFO] [stdout] ed: 0.000000000028790063618332028
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.589985 0.871618 │
[INFO] [stdout] │ -1.229018 0.331924 │
[INFO] [stdout] │ -0.977370 -0.103679 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.225386 │
[INFO] [stdout] │ 0.617837 │
[INFO] [stdout] │ 1.423196 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 178
[INFO] [stdout] ed: 0.00000000002947891287955318
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.590349 0.871981 │
[INFO] [stdout] │ -1.228896 0.332046 │
[INFO] [stdout] │ -0.977291 -0.103599 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.225207 │
[INFO] [stdout] │ 0.617836 │
[INFO] [stdout] │ 1.423196 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 179
[INFO] [stdout] ed: 0.000000000029682412852275764
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.590710 0.872343 │
[INFO] [stdout] │ -1.228774 0.332168 │
[INFO] [stdout] │ -0.977212 -0.103520 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.225030 │
[INFO] [stdout] │ 0.617835 │
[INFO] [stdout] │ 1.423195 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 180
[INFO] [stdout] ed: 0.000000000028524997593037622
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.591070 0.872702 │
[INFO] [stdout] │ -1.228653 0.332289 │
[INFO] [stdout] │ -0.977132 -0.103441 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.224854 │
[INFO] [stdout] │ 0.617834 │
[INFO] [stdout] │ 1.423195 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 181
[INFO] [stdout] ed: 0.000000000028879550490206915
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.591427 0.873060 │
[INFO] [stdout] │ -1.228531 0.332410 │
[INFO] [stdout] │ -0.977053 -0.103362 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.224679 │
[INFO] [stdout] │ 0.617833 │
[INFO] [stdout] │ 1.423194 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 182
[INFO] [stdout] ed: 0.0000000000292728885740686
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.591782 0.873415 │
[INFO] [stdout] │ -1.228411 0.332531 │
[INFO] [stdout] │ -0.976975 -0.103283 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.224506 │
[INFO] [stdout] │ 0.617832 │
[INFO] [stdout] │ 1.423193 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 183
[INFO] [stdout] ed: 0.000000000028553731056732524
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.592135 0.873768 │
[INFO] [stdout] │ -1.228290 0.332652 │
[INFO] [stdout] │ -0.976896 -0.103204 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.224333 │
[INFO] [stdout] │ 0.617830 │
[INFO] [stdout] │ 1.423192 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 184
[INFO] [stdout] ed: 0.000000000027606962502387592
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.592486 0.874118 │
[INFO] [stdout] │ -1.228170 0.332772 │
[INFO] [stdout] │ -0.976818 -0.103126 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.224161 │
[INFO] [stdout] │ 0.617828 │
[INFO] [stdout] │ 1.423190 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 185
[INFO] [stdout] ed: 0.00000000002775432430267337
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.592835 0.874467 │
[INFO] [stdout] │ -1.228050 0.332892 │
[INFO] [stdout] │ -0.976739 -0.103048 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.223990 │
[INFO] [stdout] │ 0.617826 │
[INFO] [stdout] │ 1.423189 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 186
[INFO] [stdout] ed: 0.000000000027604540714791364
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.593182 0.874814 │
[INFO] [stdout] │ -1.227930 0.333012 │
[INFO] [stdout] │ -0.976661 -0.102970 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.223821 │
[INFO] [stdout] │ 0.617823 │
[INFO] [stdout] │ 1.423187 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 187
[INFO] [stdout] ed: 0.000000000027849999202300333
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.593526 0.875159 │
[INFO] [stdout] │ -1.227810 0.333132 │
[INFO] [stdout] │ -0.976583 -0.102892 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.223652 │
[INFO] [stdout] │ 0.617820 │
[INFO] [stdout] │ 1.423185 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 188
[INFO] [stdout] ed: 0.000000000027661262059093366
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.593869 0.875502 │
[INFO] [stdout] │ -1.227691 0.333251 │
[INFO] [stdout] │ -0.976506 -0.102814 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.223484 │
[INFO] [stdout] │ 0.617818 │
[INFO] [stdout] │ 1.423184 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 189
[INFO] [stdout] ed: 0.000000000026873541479369378
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.594210 0.875842 │
[INFO] [stdout] │ -1.227572 0.333370 │
[INFO] [stdout] │ -0.976428 -0.102736 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.223318 │
[INFO] [stdout] │ 0.617814 │
[INFO] [stdout] │ 1.423181 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 190
[INFO] [stdout] ed: 0.000000000026389864502510065
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.594549 0.876181 │
[INFO] [stdout] │ -1.227453 0.333489 │
[INFO] [stdout] │ -0.976351 -0.102659 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.223152 │
[INFO] [stdout] │ 0.617811 │
[INFO] [stdout] │ 1.423179 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 191
[INFO] [stdout] ed: 0.000000000027443407856103894
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.594886 0.876518 │
[INFO] [stdout] │ -1.227334 0.333608 │
[INFO] [stdout] │ -0.976273 -0.102582 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.222987 │
[INFO] [stdout] │ 0.617807 │
[INFO] [stdout] │ 1.423177 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 192
[INFO] [stdout] ed: 0.000000000027385772054512334
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.595220 0.876853 │
[INFO] [stdout] │ -1.227216 0.333726 │
[INFO] [stdout] │ -0.976196 -0.102504 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.222824 │
[INFO] [stdout] │ 0.617803 │
[INFO] [stdout] │ 1.423174 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 193
[INFO] [stdout] ed: 0.000000000027043129299452127
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.595554 0.877186 │
[INFO] [stdout] │ -1.227097 0.333844 │
[INFO] [stdout] │ -0.976119 -0.102427 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.222661 │
[INFO] [stdout] │ 0.617799 │
[INFO] [stdout] │ 1.423172 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 194
[INFO] [stdout] ed: 0.000000000027661280061421256
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.595885 0.877517 │
[INFO] [stdout] │ -1.226979 0.333962 │
[INFO] [stdout] │ -0.976042 -0.102350 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.222499 │
[INFO] [stdout] │ 0.617795 │
[INFO] [stdout] │ 1.423169 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 195
[INFO] [stdout] ed: 0.000000000027430316804155715
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.596214 0.877847 │
[INFO] [stdout] │ -1.226861 0.334080 │
[INFO] [stdout] │ -0.975965 -0.102274 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.222338 │
[INFO] [stdout] │ 0.617790 │
[INFO] [stdout] │ 1.423166 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 196
[INFO] [stdout] ed: 0.000000000025724571219002958
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.596542 0.878174 │
[INFO] [stdout] │ -1.226744 0.334198 │
[INFO] [stdout] │ -0.975889 -0.102197 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.222178 │
[INFO] [stdout] │ 0.617786 │
[INFO] [stdout] │ 1.423163 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 197
[INFO] [stdout] ed: 0.000000000026802366667947662
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.596867 0.878500 │
[INFO] [stdout] │ -1.226626 0.334315 │
[INFO] [stdout] │ -0.975812 -0.102121 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.222019 │
[INFO] [stdout] │ 0.617781 │
[INFO] [stdout] │ 1.423160 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 198
[INFO] [stdout] ed: 0.000000000026439094772248186
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.597191 0.878824 │
[INFO] [stdout] │ -1.226509 0.334432 │
[INFO] [stdout] │ -0.975736 -0.102044 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.221861 │
[INFO] [stdout] │ 0.617775 │
[INFO] [stdout] │ 1.423156 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 199
[INFO] [stdout] ed: 0.000000000026201988273496398
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.597513 0.879146 │
[INFO] [stdout] │ -1.226392 0.334549 │
[INFO] [stdout] │ -0.975660 -0.101968 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.221704 │
[INFO] [stdout] │ 0.617770 │
[INFO] [stdout] │ 1.423153 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 200
[INFO] [stdout] ed: 0.000000000025991462180218024
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.597834 0.879466 │
[INFO] [stdout] │ -1.226275 0.334666 │
[INFO] [stdout] │ -0.975584 -0.101892 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.221548 │
[INFO] [stdout] │ 0.617764 │
[INFO] [stdout] │ 1.423149 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 201
[INFO] [stdout] ed: 0.000000000026370953589583288
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.598152 0.879785 │
[INFO] [stdout] │ -1.226159 0.334783 │
[INFO] [stdout] │ -0.975508 -0.101816 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.221392 │
[INFO] [stdout] │ 0.617759 │
[INFO] [stdout] │ 1.423145 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 202
[INFO] [stdout] ed: 0.000000000026231906492790618
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.598469 0.880102 │
[INFO] [stdout] │ -1.226042 0.334899 │
[INFO] [stdout] │ -0.975432 -0.101740 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.221237 │
[INFO] [stdout] │ 0.617752 │
[INFO] [stdout] │ 1.423141 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 203
[INFO] [stdout] ed: 0.000000000026364067515220542
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.598785 0.880417 │
[INFO] [stdout] │ -1.225926 0.335016 │
[INFO] [stdout] │ -0.975356 -0.101664 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.221084 │
[INFO] [stdout] │ 0.617746 │
[INFO] [stdout] │ 1.423137 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 204
[INFO] [stdout] ed: 0.000000000025431939777099513
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.599098 0.880731 │
[INFO] [stdout] │ -1.225810 0.335132 │
[INFO] [stdout] │ -0.975281 -0.101589 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.220931 │
[INFO] [stdout] │ 0.617740 │
[INFO] [stdout] │ 1.423133 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 205
[INFO] [stdout] ed: 0.000000000025632284092471154
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.599410 0.881043 │
[INFO] [stdout] │ -1.225694 0.335247 │
[INFO] [stdout] │ -0.975205 -0.101513 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.220779 │
[INFO] [stdout] │ 0.617733 │
[INFO] [stdout] │ 1.423129 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 206
[INFO] [stdout] ed: 0.000000000025487082492269008
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.599720 0.881353 │
[INFO] [stdout] │ -1.225578 0.335363 │
[INFO] [stdout] │ -0.975130 -0.101438 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.220628 │
[INFO] [stdout] │ 0.617726 │
[INFO] [stdout] │ 1.423124 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 207
[INFO] [stdout] ed: 0.000000000025603318198015368
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.600029 0.881661 │
[INFO] [stdout] │ -1.225463 0.335479 │
[INFO] [stdout] │ -0.975054 -0.101363 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.220477 │
[INFO] [stdout] │ 0.617719 │
[INFO] [stdout] │ 1.423119 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 208
[INFO] [stdout] ed: 0.00000000002521715670524785
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.600336 0.881968 │
[INFO] [stdout] │ -1.225348 0.335594 │
[INFO] [stdout] │ -0.974979 -0.101288 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.220328 │
[INFO] [stdout] │ 0.617712 │
[INFO] [stdout] │ 1.423115 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 209
[INFO] [stdout] ed: 0.000000000025804940367183357
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.600641 0.882274 │
[INFO] [stdout] │ -1.225232 0.335709 │
[INFO] [stdout] │ -0.974904 -0.101213 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.220179 │
[INFO] [stdout] │ 0.617704 │
[INFO] [stdout] │ 1.423110 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 210
[INFO] [stdout] ed: 0.000000000025431524501064724
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.600945 0.882578 │
[INFO] [stdout] │ -1.225117 0.335824 │
[INFO] [stdout] │ -0.974829 -0.101138 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.220031 │
[INFO] [stdout] │ 0.617696 │
[INFO] [stdout] │ 1.423105 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 211
[INFO] [stdout] ed: 0.000000000024493828075919245
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.601247 0.882880 │
[INFO] [stdout] │ -1.225002 0.335939 │
[INFO] [stdout] │ -0.974754 -0.101063 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.219884 │
[INFO] [stdout] │ 0.617689 │
[INFO] [stdout] │ 1.423100 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 212
[INFO] [stdout] ed: 0.000000000024505138750450908
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.601548 0.883180 │
[INFO] [stdout] │ -1.224888 0.336054 │
[INFO] [stdout] │ -0.974680 -0.100988 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.219737 │
[INFO] [stdout] │ 0.617681 │
[INFO] [stdout] │ 1.423094 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 213
[INFO] [stdout] ed: 0.000000000025333509698684907
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.601847 0.883480 │
[INFO] [stdout] │ -1.224773 0.336169 │
[INFO] [stdout] │ -0.974605 -0.100913 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.219592 │
[INFO] [stdout] │ 0.617672 │
[INFO] [stdout] │ 1.423089 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 214
[INFO] [stdout] ed: 0.000000000025045900250464472
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.602145 0.883777 │
[INFO] [stdout] │ -1.224659 0.336283 │
[INFO] [stdout] │ -0.974531 -0.100839 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.219447 │
[INFO] [stdout] │ 0.617664 │
[INFO] [stdout] │ 1.423083 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 215
[INFO] [stdout] ed: 0.000000000024735976939285157
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.602441 0.884073 │
[INFO] [stdout] │ -1.224544 0.336397 │
[INFO] [stdout] │ -0.974456 -0.100765 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.219303 │
[INFO] [stdout] │ 0.617655 │
[INFO] [stdout] │ 1.423078 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 216
[INFO] [stdout] ed: 0.00000000002453702369791191
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.602735 0.884368 │
[INFO] [stdout] │ -1.224430 0.336511 │
[INFO] [stdout] │ -0.974382 -0.100690 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.219159 │
[INFO] [stdout] │ 0.617646 │
[INFO] [stdout] │ 1.423072 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 217
[INFO] [stdout] ed: 0.00000000002502749111824234
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.603028 0.884661 │
[INFO] [stdout] │ -1.224316 0.336625 │
[INFO] [stdout] │ -0.974308 -0.100616 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.219017 │
[INFO] [stdout] │ 0.617637 │
[INFO] [stdout] │ 1.423066 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 218
[INFO] [stdout] ed: 0.000000000024819463091301574
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.603320 0.884953 │
[INFO] [stdout] │ -1.224202 0.336739 │
[INFO] [stdout] │ -0.974234 -0.100542 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.218875 │
[INFO] [stdout] │ 0.617628 │
[INFO] [stdout] │ 1.423060 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 219
[INFO] [stdout] ed: 0.000000000024016201311447794
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.603610 0.885243 │
[INFO] [stdout] │ -1.224089 0.336853 │
[INFO] [stdout] │ -0.974159 -0.100468 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.218734 │
[INFO] [stdout] │ 0.617618 │
[INFO] [stdout] │ 1.423054 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 220
[INFO] [stdout] ed: 0.00000000002405986340950788
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.603899 0.885532 │
[INFO] [stdout] │ -1.223975 0.336967 │
[INFO] [stdout] │ -0.974086 -0.100394 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.218594 │
[INFO] [stdout] │ 0.617609 │
[INFO] [stdout] │ 1.423048 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 221
[INFO] [stdout] ed: 0.000000000024356638549750218
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.604186 0.885819 │
[INFO] [stdout] │ -1.223862 0.337080 │
[INFO] [stdout] │ -0.974012 -0.100320 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.218454 │
[INFO] [stdout] │ 0.617599 │
[INFO] [stdout] │ 1.423041 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 222
[INFO] [stdout] ed: 0.000000000024513477551151452
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.604472 0.886105 │
[INFO] [stdout] │ -1.223748 0.337193 │
[INFO] [stdout] │ -0.973938 -0.100246 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.218315 │
[INFO] [stdout] │ 0.617589 │
[INFO] [stdout] │ 1.423035 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 223
[INFO] [stdout] ed: 0.000000000023974999358330114
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.604757 0.886389 │
[INFO] [stdout] │ -1.223635 0.337307 │
[INFO] [stdout] │ -0.973864 -0.100173 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.218177 │
[INFO] [stdout] │ 0.617579 │
[INFO] [stdout] │ 1.423028 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 224
[INFO] [stdout] ed: 0.00000000002409981333434295
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.605040 0.886672 │
[INFO] [stdout] │ -1.223522 0.337420 │
[INFO] [stdout] │ -0.973791 -0.100099 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.218039 │
[INFO] [stdout] │ 0.617568 │
[INFO] [stdout] │ 1.423021 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 225
[INFO] [stdout] ed: 0.000000000023324998834300876
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.605322 0.886954 │
[INFO] [stdout] │ -1.223409 0.337533 │
[INFO] [stdout] │ -0.973717 -0.100025 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.217902 │
[INFO] [stdout] │ 0.617558 │
[INFO] [stdout] │ 1.423015 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 226
[INFO] [stdout] ed: 0.00000000002384843895066581
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.605602 0.887235 │
[INFO] [stdout] │ -1.223296 0.337645 │
[INFO] [stdout] │ -0.973644 -0.099952 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.217766 │
[INFO] [stdout] │ 0.617547 │
[INFO] [stdout] │ 1.423008 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 227
[INFO] [stdout] ed: 0.000000000023679571017982477
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.605881 0.887514 │
[INFO] [stdout] │ -1.223183 0.337758 │
[INFO] [stdout] │ -0.973570 -0.099879 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.217631 │
[INFO] [stdout] │ 0.617536 │
[INFO] [stdout] │ 1.423000 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 228
[INFO] [stdout] ed: 0.000000000023255244701340576
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.606159 0.887791 │
[INFO] [stdout] │ -1.223071 0.337871 │
[INFO] [stdout] │ -0.973497 -0.099805 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.217496 │
[INFO] [stdout] │ 0.617525 │
[INFO] [stdout] │ 1.422993 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 229
[INFO] [stdout] ed: 0.00000000002309413308335927
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.606435 0.888068 │
[INFO] [stdout] │ -1.222958 0.337983 │
[INFO] [stdout] │ -0.973424 -0.099732 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.217362 │
[INFO] [stdout] │ 0.617514 │
[INFO] [stdout] │ 1.422986 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 230
[INFO] [stdout] ed: 0.000000000023451366417446406
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.606710 0.888343 │
[INFO] [stdout] │ -1.222846 0.338096 │
[INFO] [stdout] │ -0.973351 -0.099659 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.217228 │
[INFO] [stdout] │ 0.617503 │
[INFO] [stdout] │ 1.422978 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 231
[INFO] [stdout] ed: 0.000000000022947191760605963
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.606984 0.888617 │
[INFO] [stdout] │ -1.222734 0.338208 │
[INFO] [stdout] │ -0.973277 -0.099586 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.217096 │
[INFO] [stdout] │ 0.617491 │
[INFO] [stdout] │ 1.422971 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 232
[INFO] [stdout] ed: 0.000000000022229235545940976
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.607257 0.888889 │
[INFO] [stdout] │ -1.222622 0.338320 │
[INFO] [stdout] │ -0.973204 -0.099513 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.216964 │
[INFO] [stdout] │ 0.617479 │
[INFO] [stdout] │ 1.422963 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 233
[INFO] [stdout] ed: 0.00000000002346647818142785
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.607528 0.889160 │
[INFO] [stdout] │ -1.222509 0.338432 │
[INFO] [stdout] │ -0.973131 -0.099440 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.216832 │
[INFO] [stdout] │ 0.617467 │
[INFO] [stdout] │ 1.422955 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 234
[INFO] [stdout] ed: 0.000000000022908387578240547
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.607798 0.889430 │
[INFO] [stdout] │ -1.222397 0.338544 │
[INFO] [stdout] │ -0.973059 -0.099367 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.216701 │
[INFO] [stdout] │ 0.617455 │
[INFO] [stdout] │ 1.422948 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 235
[INFO] [stdout] ed: 0.00000000002266062844346022
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.608066 0.889699 │
[INFO] [stdout] │ -1.222286 0.338656 │
[INFO] [stdout] │ -0.972986 -0.099294 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.216571 │
[INFO] [stdout] │ 0.617443 │
[INFO] [stdout] │ 1.422940 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 236
[INFO] [stdout] ed: 0.0000000000226039782900213
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.608334 0.889966 │
[INFO] [stdout] │ -1.222174 0.338768 │
[INFO] [stdout] │ -0.972913 -0.099221 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.216441 │
[INFO] [stdout] │ 0.617430 │
[INFO] [stdout] │ 1.422931 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 237
[INFO] [stdout] ed: 0.00000000002303900577374143
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.608600 0.890233 │
[INFO] [stdout] │ -1.222062 0.338880 │
[INFO] [stdout] │ -0.972840 -0.099149 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.216312 │
[INFO] [stdout] │ 0.617418 │
[INFO] [stdout] │ 1.422923 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 238
[INFO] [stdout] ed: 0.00000000002262344876635713
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.608865 0.890498 │
[INFO] [stdout] │ -1.221951 0.338991 │
[INFO] [stdout] │ -0.972768 -0.099076 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.216184 │
[INFO] [stdout] │ 0.617405 │
[INFO] [stdout] │ 1.422915 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 239
[INFO] [stdout] ed: 0.00000000002205521739053419
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.609129 0.890762 │
[INFO] [stdout] │ -1.221839 0.339103 │
[INFO] [stdout] │ -0.972695 -0.099004 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.216056 │
[INFO] [stdout] │ 0.617392 │
[INFO] [stdout] │ 1.422906 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 240
[INFO] [stdout] ed: 0.000000000022992308221915275
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.609392 0.891024 │
[INFO] [stdout] │ -1.221728 0.339214 │
[INFO] [stdout] │ -0.972623 -0.098931 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.215929 │
[INFO] [stdout] │ 0.617379 │
[INFO] [stdout] │ 1.422898 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 241
[INFO] [stdout] ed: 0.00000000002290623142527249
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.609653 0.891286 │
[INFO] [stdout] │ -1.221616 0.339325 │
[INFO] [stdout] │ -0.972550 -0.098859 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.215803 │
[INFO] [stdout] │ 0.617365 │
[INFO] [stdout] │ 1.422889 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 242
[INFO] [stdout] ed: 0.000000000022444986371976722
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.609913 0.891546 │
[INFO] [stdout] │ -1.221505 0.339437 │
[INFO] [stdout] │ -0.972478 -0.098786 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.215677 │
[INFO] [stdout] │ 0.617352 │
[INFO] [stdout] │ 1.422881 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 243
[INFO] [stdout] ed: 0.000000000022805604534234407
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.610172 0.891805 │
[INFO] [stdout] │ -1.221394 0.339548 │
[INFO] [stdout] │ -0.972406 -0.098714 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.215551 │
[INFO] [stdout] │ 0.617338 │
[INFO] [stdout] │ 1.422872 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 244
[INFO] [stdout] ed: 0.00000000002166631517661821
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.610430 0.892063 │
[INFO] [stdout] │ -1.221283 0.339659 │
[INFO] [stdout] │ -0.972333 -0.098642 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.215427 │
[INFO] [stdout] │ 0.617325 │
[INFO] [stdout] │ 1.422863 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 245
[INFO] [stdout] ed: 0.000000000022250301594695966
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.610687 0.892320 │
[INFO] [stdout] │ -1.221172 0.339770 │
[INFO] [stdout] │ -0.972261 -0.098569 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.215303 │
[INFO] [stdout] │ 0.617311 │
[INFO] [stdout] │ 1.422854 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 246
[INFO] [stdout] ed: 0.00000000002180487808329828
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.610943 0.892575 │
[INFO] [stdout] │ -1.221061 0.339881 │
[INFO] [stdout] │ -0.972189 -0.098497 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.215179 │
[INFO] [stdout] │ 0.617296 │
[INFO] [stdout] │ 1.422844 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 247
[INFO] [stdout] ed: 0.000000000022498345220197163
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.611197 0.892830 │
[INFO] [stdout] │ -1.220950 0.339992 │
[INFO] [stdout] │ -0.972117 -0.098425 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.215056 │
[INFO] [stdout] │ 0.617282 │
[INFO] [stdout] │ 1.422835 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 248
[INFO] [stdout] ed: 0.000000000021649991898193023
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.611451 0.893083 │
[INFO] [stdout] │ -1.220839 0.340102 │
[INFO] [stdout] │ -0.972045 -0.098353 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.214933 │
[INFO] [stdout] │ 0.617268 │
[INFO] [stdout] │ 1.422826 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] finished ff for all training points - epoch 249
[INFO] [stdout] ed: 0.00000000002109832915365314
[INFO] [stdout] weights in layer 1: 
[INFO] [stdout] ╭                   ╮
[INFO] [stdout] │ 0.611703 0.893335 │
[INFO] [stdout] │ -1.220729 0.340213 │
[INFO] [stdout] │ -0.971973 -0.098281 │
[INFO] [stdout] ╰                   ╯
[INFO] [stdout] 
[INFO] [stdout] biases in layer 1: 
[INFO] [stdout] ╭          ╮
[INFO] [stdout] │ -0.214812 │
[INFO] [stdout] │ 0.617253 │
[INFO] [stdout] │ 1.422816 │
[INFO] [stdout] ╰          ╯
[INFO] [stdout] 
[INFO] [stdout] stopping after 250 epocs
[INFO] [stdout] 
[INFO] [stdout] cost across entire training set after 250 epocs: 0.2500373358720333
[INFO] [stdout] computing initial cross accross entire training dataset...
[INFO] [stdout] initial cost across entire training set: 0.2500373358720333
[INFO] [stdout] t_init_cost: t_init_cost: 0 ms
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 0
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 0: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 0: 0.2500370338495456
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 1
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 1: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 1: 0.25003673405930127
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 2
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 2: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 2: 0.25003643647218404
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 3
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 3: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 3: 0.25003614105954564
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 4
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 4: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 4: 0.2500358477931958
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 5
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 5: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 5: 0.2500355566453932
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 6
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 6: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 6: 0.2500352675888362
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 7
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 7: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 7: 0.25003498059665474
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 8
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 8: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 8: 0.250034695642401
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 9
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 9: t_compute_gradients: 3 ms
[INFO] [stdout] cost across training set after epoch 9: 0.25003441270004134
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 10
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 10: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 10: 0.2500341317439481
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 11
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 11: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 11: 0.2500338527488918
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 12
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 12: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 12: 0.25003357569003304
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 13
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 13: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 13: 0.2500333005429149
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 14
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 14: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 14: 0.25003302728345556
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 15
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 15: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 15: 0.25003275588794105
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 16
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 16: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 16: 0.2500324863330182
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 17
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 17: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 17: 0.2500322185956873
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 18
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 18: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 18: 0.25003195265329603
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 19
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 19: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 19: 0.250031688483532
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 2 ms
[INFO] [stdout] finished ff for all training points - epoch 20
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 20: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 20: 0.25003142606441664
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 21
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 21: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 21: 0.25003116537429926
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 22
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 22: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 22: 0.2500309063918498
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 23
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 23: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 23: 0.25003064909605405
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 24
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 24: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 24: 0.25003039346620654
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 25
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 25: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 25: 0.25003013948190567
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 26
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 26: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 26: 0.2500298871230472
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 27
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 27: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 27: 0.25002963636981945
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 28
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 28: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 28: 0.2500293872026976
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 29
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 29: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 29: 0.250029139602438
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 30
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 30: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 30: 0.25002889355007335
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 31
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 31: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 31: 0.2500286490269082
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 32
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 32: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 32: 0.25002840601451265
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 33
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 33: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 33: 0.25002816449471815
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 34
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 34: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 34: 0.2500279244496133
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 35
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 35: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 35: 0.25002768586153834
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 36
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 36: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 36: 0.2500274487130811
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 2 ms
[INFO] [stdout] finished ff for all training points - epoch 37
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 37: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 37: 0.2500272129870721
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 38
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 38: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 38: 0.2500269786665806
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 39
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 39: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 39: 0.25002674573491
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 40
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 40: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 40: 0.25002651417559396
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 41
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 41: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 41: 0.25002628397239224
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 42
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 42: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 42: 0.2500260551092863
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 43
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 43: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 43: 0.25002582757047576
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 44
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 44: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 44: 0.25002560134037455
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 45
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 45: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 45: 0.250025376403607
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 46
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 46: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 46: 0.25002515274500403
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 47
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 47: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 47: 0.2500249303495996
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 48
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 48: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 48: 0.2500247092026277
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 49
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 49: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 49: 0.250024489289518
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 50
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 50: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 50: 0.25002427059589283
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 51
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 51: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 51: 0.25002405310756426
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 52
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 52: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 52: 0.2500238368105299
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 53
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 53: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 53: 0.2500236216909709
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 54
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 54: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 54: 0.25002340773524767
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 55
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 55: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 55: 0.2500231949298972
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 56
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 56: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 56: 0.2500229832616308
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 57
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 57: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 57: 0.25002277271732964
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 58
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 58: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 58: 0.2500225632840432
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 59
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 59: t_compute_gradients: 2 ms
[INFO] [stdout] cost across training set after epoch 59: 0.2500223549489859
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 60
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 60: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 60: 0.25002214769953407
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 61
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 61: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 61: 0.250021941523224
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 62
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 62: t_compute_gradients: 2 ms
[INFO] [stdout] cost across training set after epoch 62: 0.2500217364077479
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 63
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 63: t_compute_gradients: 2 ms
[INFO] [stdout] cost across training set after epoch 63: 0.250021532340953
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 64
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 64: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 64: 0.2500213293108374
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 65
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 65: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 65: 0.25002112730554876
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 66
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 66: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 66: 0.25002092631338113
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 2 ms
[INFO] [stdout] finished ff for all training points - epoch 67
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 67: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 67: 0.2500207263227724
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 68
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 68: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 68: 0.2500205273223027
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 69
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 69: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 69: 0.250020329300691
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 70
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 70: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 70: 0.2500201322467939
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 71
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 71: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 71: 0.25001993614960255
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 72
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 72: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 72: 0.2500197409982409
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 73
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 73: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 73: 0.25001954678196314
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 74
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 74: t_compute_gradients: 2 ms
[INFO] [stdout] cost across training set after epoch 74: 0.2500193534901522
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 75
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 75: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 75: 0.2500191611123169
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 2 ms
[INFO] [stdout] finished ff for all training points - epoch 76
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 76: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 76: 0.25001896963809045
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 77
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 77: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 77: 0.25001877905722825
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 78
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 78: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 78: 0.25001858935960586
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 79
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 79: t_compute_gradients: 2 ms
[INFO] [stdout] cost across training set after epoch 79: 0.25001840053521707
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 80
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 80: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 80: 0.25001821257417234
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 81
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 81: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 81: 0.25001802546669627
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 3 ms
[INFO] [stdout] finished ff for all training points - epoch 82
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 82: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 82: 0.2500178392031265
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 83
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 83: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 83: 0.25001765377391116
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 84
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 84: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 84: 0.25001746916960765
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 85
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 85: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 85: 0.250017285380881
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 86
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 86: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 86: 0.25001710239850156
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 87
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 87: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 87: 0.25001692021334365
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 88
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 88: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 88: 0.2500167388163841
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 89
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 89: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 89: 0.2500165581987005
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 90
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 90: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 90: 0.2500163783514693
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 91
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 91: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 91: 0.2500161992659649
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 92
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 92: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 92: 0.25001602093355724
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 93
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 93: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 93: 0.25001584334571125
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 94
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 94: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 94: 0.2500156664939847
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 95
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 95: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 95: 0.250015490370027
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 96
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 96: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 96: 0.2500153149655776
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 97
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 97: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 97: 0.25001514027246485
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 98
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 98: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 98: 0.25001496628260444
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 99
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 99: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 99: 0.250014792987998
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 100
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 100: t_compute_gradients: 2 ms
[INFO] [stdout] cost across training set after epoch 100: 0.25001462038073186
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 101
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 101: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 101: 0.25001444845297593
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 102
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 102: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 102: 0.2500142771969817
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 103
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 103: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 103: 0.25001410660508216
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 104
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 104: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 104: 0.2500139366696892
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 105
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 105: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 105: 0.2500137673832935
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 106
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 106: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 106: 0.2500135987384626
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 107
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 107: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 107: 0.2500134307278402
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 108
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 108: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 108: 0.2500132633441445
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 109
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 109: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 109: 0.25001309658016757
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 110
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 110: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 110: 0.25001293042877387
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 111
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 111: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 111: 0.2500127648828995
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 112
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 112: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 112: 0.2500125999355503
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 113
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 113: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 113: 0.250012435579802
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 114
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 114: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 114: 0.2500122718087979
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 115
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 115: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 115: 0.25001210861574885
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 116
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 116: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 116: 0.2500119459939317
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 117
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 117: t_compute_gradients: 5 ms
[INFO] [stdout] cost across training set after epoch 117: 0.2500117839366883
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 118
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 118: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 118: 0.2500116224374247
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 119
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 119: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 119: 0.25001146148961
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 120
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 120: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 120: 0.2500113010867756
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 121
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 121: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 121: 0.250011141222514
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 122
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 122: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 122: 0.25001098189047805
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 123
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 123: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 123: 0.2500108230843799
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 3 ms
[INFO] [stdout] finished ff for all training points - epoch 124
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 124: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 124: 0.2500106647979904
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 125
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 125: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 125: 0.25001050702513794
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 126
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 126: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 126: 0.2500103497597072
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 127
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 127: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 127: 0.25001019299563937
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 128
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 128: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 128: 0.25001003672693034
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 3 ms
[INFO] [stdout] finished ff for all training points - epoch 129
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 129: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 129: 0.25000988094763005
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 130
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 130: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 130: 0.25000972565184193
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 131
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 131: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 131: 0.2500095708337221
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 132
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 132: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 132: 0.25000941648747826
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 133
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 133: t_compute_gradients: 3 ms
[INFO] [stdout] cost across training set after epoch 133: 0.25000926260736894
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 134
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 134: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 134: 0.25000910918770336
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 135
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 135: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 135: 0.2500089562228395
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 136
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 136: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 136: 0.2500088037071845
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 137
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 137: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 137: 0.2500086516351935
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 138
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 138: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 138: 0.25000850000136815
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 139
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 139: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 139: 0.2500083488002575
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 140
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 140: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 140: 0.2500081980264559
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 141
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 141: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 141: 0.25000804767460283
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 142
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 142: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 142: 0.2500078977393821
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 143
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 143: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 143: 0.2500077482155214
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 144
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 144: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 144: 0.2500075990977914
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 145
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 145: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 145: 0.25000745038100514
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 146
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 146: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 146: 0.2500073020600175
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 147
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 147: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 147: 0.2500071541297242
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 148
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 148: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 148: 0.2500070065850618
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 149
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 149: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 149: 0.2500068594210064
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 150
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 150: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 150: 0.25000671263257357
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 151
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 151: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 151: 0.25000656621481726
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 152
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 152: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 152: 0.25000642016282965
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 153
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 153: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 153: 0.25000627447174023
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 154
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 154: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 154: 0.2500061291367154
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 155
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 155: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 155: 0.2500059841529577
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 156
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 156: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 156: 0.25000583951570576
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 157
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 157: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 157: 0.250005695220233
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 158
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 158: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 158: 0.2500055512618475
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 159
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 159: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 159: 0.25000540763589163
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 160
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 160: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 160: 0.25000526433774095
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 161
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 161: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 161: 0.2500051213628042
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 162
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 162: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 162: 0.2500049787065227
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 163
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 163: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 163: 0.25000483636436943
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 164
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 164: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 164: 0.2500046943318489
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 165
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 165: t_compute_gradients: 7 ms
[INFO] [stdout] cost across training set after epoch 165: 0.250004552604497
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 166
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 166: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 166: 0.2500044111778791
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 167
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 167: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 167: 0.25000427004759157
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 168
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 168: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 168: 0.2500041292092596
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 169
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 169: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 169: 0.25000398865853757
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 170
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 170: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 170: 0.2500038483911081
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 171
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 171: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 171: 0.2500037084026824
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 172
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 172: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 172: 0.2500035686889987
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 173
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 173: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 173: 0.2500034292458226
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 174
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 174: t_compute_gradients: 5 ms
[INFO] [stdout] cost across training set after epoch 174: 0.2500032900689465
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 4 ms
[INFO] [stdout] finished ff for all training points - epoch 175
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 175: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 175: 0.2500031511541887
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 176
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 176: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 176: 0.2500030124973936
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 177
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 177: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 177: 0.25000287409443056
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 178
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 178: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 178: 0.2500027359411945
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 179
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 179: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 179: 0.2500025980336039
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 180
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 180: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 180: 0.25000246036760226
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 181
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 181: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 181: 0.25000232293915603
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 182
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 182: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 182: 0.25000218574425526
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 183
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 183: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 183: 0.2500020487789128
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 184
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 184: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 184: 0.2500019120391638
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 185
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 185: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 185: 0.2500017755210653
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 186
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 186: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 186: 0.2500016392206964
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 187
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 187: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 187: 0.2500015031341573
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 188
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 188: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 188: 0.2500013672575687
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 189
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 189: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 189: 0.2500012315870722
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 190
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 190: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 190: 0.2500010961188291
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 191
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 191: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 191: 0.2500009608490211
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 192
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 192: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 192: 0.25000082577384836
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 193
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 193: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 193: 0.2500006908895308
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 194
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 194: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 194: 0.25000055619230643
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 195
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 195: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 195: 0.2500004216784318
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 196
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 196: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 196: 0.2500002873441813
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 197
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 197: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 197: 0.2500001531858467
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 198
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 198: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 198: 0.2500000191997372
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 199
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 199: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 199: 0.2499998853821787
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 200
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 200: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 200: 0.24999975172951405
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 201
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 201: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 201: 0.2499996182381013
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 202
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 202: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 202: 0.24999948490431537
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 203
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 203: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 203: 0.24999935172454602
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 204
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 204: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 204: 0.24999921869519826
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 205
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 205: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 205: 0.24999908581269245
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 206
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 206: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 206: 0.2499989530734627
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 207
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 207: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 207: 0.24999882047395774
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 208
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 208: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 208: 0.24999868801064032
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 209
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 209: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 209: 0.24999855567998613
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 210
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 210: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 210: 0.24999842347848472
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 211
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 211: t_compute_gradients: 3 ms
[INFO] [stdout] cost across training set after epoch 211: 0.24999829140263824
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 212
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 212: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 212: 0.24999815944896153
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 213
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 213: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 213: 0.2499980276139817
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 214
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 214: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 214: 0.2499978958942377
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 215
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 215: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 215: 0.2499977642862805
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 216
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 216: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 216: 0.2499976327866722
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 217
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 217: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 217: 0.24999750139198618
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 218
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 218: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 218: 0.24999737009880635
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 219
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 219: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 219: 0.24999723890372721
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 220
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 220: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 220: 0.24999710780335355
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 221
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 221: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 221: 0.24999697679430008
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 222
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 222: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 222: 0.249996845873191
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 223
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 223: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 223: 0.2499967150366599
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 224
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 224: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 224: 0.2499965842813492
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 225
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 225: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 225: 0.2499964536039106
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 226
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 226: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 226: 0.24999632300100375
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 227
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 227: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 227: 0.24999619246929655
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 228
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 228: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 228: 0.2499960620054653
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 229
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 229: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 229: 0.2499959316061932
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 230
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 230: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 230: 0.24999580126817142
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 231
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 231: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 231: 0.24999567098809777
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 232
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 232: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 232: 0.24999554076267727
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 233
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 233: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 233: 0.24999541058862093
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 234
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 234: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 234: 0.24999528046264655
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 235
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 235: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 235: 0.24999515038147763
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 236
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 236: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 236: 0.2499950203418435
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 237
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 237: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 237: 0.24999489034047878
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 238
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 238: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 238: 0.24999476037412333
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 239
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 239: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 239: 0.2499946304395221
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 240
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 240: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 240: 0.24999450053342445
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 241
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 241: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 241: 0.24999437065258415
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 242
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 242: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 242: 0.2499942407937592
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 243
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 243: t_compute_gradients: 3 ms
[INFO] [stdout] cost across training set after epoch 243: 0.24999411095371138
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 244
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 244: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 244: 0.2499939811292061
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 245
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 245: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 245: 0.24999385131701213
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 246
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 246: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 246: 0.24999372151390092
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 247
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 247: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 247: 0.2499935917166475
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 248
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 248: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 248: 0.2499934619220287
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 249
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 249: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 249: 0.2499933321268239
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 250
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 250: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 250: 0.24999320232781472
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 251
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 251: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 251: 0.24999307252178404
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 252
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 252: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 252: 0.24999294270551684
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 253
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 253: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 253: 0.2499928128757992
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 254
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 254: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 254: 0.2499926830294176
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 255
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 255: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 255: 0.2499925531631602
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 256
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 256: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 256: 0.2499924232738148
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 257
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 257: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 257: 0.24999229335817003
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 258
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 258: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 258: 0.24999216341301406
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 259
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 259: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 259: 0.2499920334351351
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 260
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 260: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 260: 0.24999190342132066
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 261
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 261: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 261: 0.24999177336835743
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 262
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 262: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 262: 0.249991643273031
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 263
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 263: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 263: 0.2499915131321258
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 264
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 264: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 264: 0.24999138294242446
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 265
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 265: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 265: 0.24999125270070807
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 266
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 266: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 266: 0.24999112240375543
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 267
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 267: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 267: 0.24999099204834313
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 268
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 268: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 268: 0.24999086163124487
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 269
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 269: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 269: 0.24999073114923193
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 270
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 270: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 270: 0.24999060059907224
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 271
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 271: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 271: 0.24999046997753022
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 272
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 272: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 272: 0.24999033928136685
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 273
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 273: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 273: 0.2499902085073391
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 274
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 274: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 274: 0.24999007765220008
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 275
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 275: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 275: 0.24998994671269809
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 276
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 276: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 276: 0.24998981568557704
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 277
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 277: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 277: 0.24998968456757575
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 278
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 278: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 278: 0.24998955335542794
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 279
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 279: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 279: 0.2499894220458616
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 280
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 280: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 280: 0.24998929063559944
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 281
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 281: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 281: 0.24998915912135794
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 282
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 282: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 282: 0.2499890274998473
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 283
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 283: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 283: 0.2499888957677713
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 284
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 284: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 284: 0.24998876392182684
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 285
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 285: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 285: 0.24998863195870377
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 286
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 286: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 286: 0.2499884998750848
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 287
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 287: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 287: 0.24998836766764465
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 288
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 288: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 288: 0.24998823533305048
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 289
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 289: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 289: 0.24998810286796144
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 290
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 290: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 290: 0.24998797026902783
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 291
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 291: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 291: 0.24998783753289158
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 292
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 292: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 292: 0.24998770465618558
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 293
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 293: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 293: 0.24998757163553345
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 294
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 294: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 294: 0.24998743846754934
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 295
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 295: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 295: 0.24998730514883744
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 296
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 296: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 296: 0.2499871716759921
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 297
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 297: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 297: 0.24998703804559713
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 298
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 298: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 298: 0.2499869042542256
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 299
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 299: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 299: 0.2499867702984397
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 300
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 300: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 300: 0.24998663617479072
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 301
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 301: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 301: 0.2499865018798179
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 302
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 302: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 302: 0.24998636741004893
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 303
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 303: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 303: 0.2499862327619994
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 304
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 304: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 304: 0.24998609793217233
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 305
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 305: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 305: 0.24998596291705827
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 306
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 306: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 306: 0.2499858277131346
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 307
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 307: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 307: 0.24998569231686552
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 308
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 308: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 308: 0.2499855567247012
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 309
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 309: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 309: 0.24998542093307843
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 310
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 310: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 310: 0.2499852849384197
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 311
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 311: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 311: 0.24998514873713243
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 312
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 312: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 312: 0.24998501232560982
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 313
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 313: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 313: 0.24998487570022956
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 314
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 314: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 314: 0.24998473885735378
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 315
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 315: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 315: 0.24998460179332893
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 316
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 316: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 316: 0.24998446450448558
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 317
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 317: t_compute_gradients: 4 ms
[INFO] [stdout] cost across training set after epoch 317: 0.2499843269871372
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 318
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 318: t_compute_gradients: 4 ms
[INFO] [stdout] cost across training set after epoch 318: 0.2499841892375812
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 319
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 319: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 319: 0.24998405125209713
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 320
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 320: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 320: 0.2499839130269478
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 321
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 321: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 321: 0.24998377455837756
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 322
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 322: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 322: 0.24998363584261293
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 323
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 323: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 323: 0.24998349687586224
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 324
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 324: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 324: 0.24998335765431437
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 325
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 325: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 325: 0.2499832181741394
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 326
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 326: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 326: 0.24998307843148787
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 327
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 327: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 327: 0.2499829384224903
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 328
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 328: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 328: 0.2499827981432571
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 329
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 329: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 329: 0.24998265758987787
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 2 ms
[INFO] [stdout] finished ff for all training points - epoch 330
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 330: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 330: 0.2499825167584213
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 331
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 331: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 331: 0.24998237564493495
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 332
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 332: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 332: 0.2499822342454443
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 333
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 333: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 333: 0.24998209255595283
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 334
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 334: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 334: 0.24998195057244166
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 335
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 335: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 335: 0.249981808290869
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 336
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 336: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 336: 0.24998166570716954
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 337
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 337: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 337: 0.24998152281725475
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 338
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 338: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 338: 0.24998137961701156
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 339
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 339: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 339: 0.24998123610230288
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 340
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 340: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 340: 0.2499810922689663
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 341
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 341: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 341: 0.24998094811281465
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 342
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 342: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 342: 0.24998080362963462
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 343
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 343: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 343: 0.249980658815187
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 344
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 344: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 344: 0.24998051366520593
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 345
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 345: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 345: 0.24998036817539865
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 346
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 346: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 346: 0.24998022234144496
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 347
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 347: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 347: 0.24998007615899676
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 348
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 348: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 348: 0.24997992962367785
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 349
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 349: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 349: 0.24997978273108323
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 350
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 350: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 350: 0.24997963547677826
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 351
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 351: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 351: 0.2499794878562994
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 352
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 352: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 352: 0.24997933986515247
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 353
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 353: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 353: 0.2499791914988127
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 354
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 354: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 354: 0.24997904275272448
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 355
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 355: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 355: 0.2499788936223005
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 356
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 356: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 356: 0.24997874410292148
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 357
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 357: t_compute_gradients: 2 ms
[INFO] [stdout] cost across training set after epoch 357: 0.24997859418993545
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 358
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 358: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 358: 0.24997844387865756
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 359
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 359: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 359: 0.24997829316436948
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 360
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 360: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 360: 0.24997814204231833
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 361
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 361: t_compute_gradients: 2 ms
[INFO] [stdout] cost across training set after epoch 361: 0.24997799050771738
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 362
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 362: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 362: 0.24997783855574415
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 363
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 363: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 363: 0.24997768618154081
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 364
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 364: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 364: 0.2499775333802134
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 365
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 365: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 365: 0.2499773801468311
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 366
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 366: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 366: 0.24997722647642587
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 367
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 367: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 367: 0.24997707236399166
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 368
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 368: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 368: 0.2499769178044843
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 369
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 369: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 369: 0.24997676279282036
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 370
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 370: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 370: 0.24997660732387694
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 371
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 371: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 371: 0.24997645139249086
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 372
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 372: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 372: 0.24997629499345847
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 373
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 373: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 373: 0.2499761381215344
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 374
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 374: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 374: 0.24997598077143138
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 375
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 375: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 375: 0.24997582293781978
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 376
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 376: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 376: 0.24997566461532608
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 377
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 377: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 377: 0.24997550579853361
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 378
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 378: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 378: 0.24997534648198064
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 379
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 379: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 379: 0.24997518666016044
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 380
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 380: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 380: 0.24997502632752044
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 381
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 381: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 381: 0.24997486547846132
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 382
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 382: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 382: 0.24997470410733666
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 383
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 383: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 383: 0.2499745422084521
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 384
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 384: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 384: 0.24997437977606438
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 385
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 385: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 385: 0.2499742168043813
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 386
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 386: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 386: 0.2499740532875602
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 387
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 387: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 387: 0.2499738892197078
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 388
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 388: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 388: 0.249973724594879
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 389
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 389: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 389: 0.2499735594070765
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 390
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 390: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 390: 0.24997339365024987
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 391
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 391: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 391: 0.2499732273182947
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 392
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 392: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 392: 0.24997306040505202
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 393
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 393: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 393: 0.2499728929043071
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 394
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 394: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 394: 0.24997272480978916
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 395
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 395: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 395: 0.24997255611516994
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 396
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 396: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 396: 0.2499723868140634
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 397
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 397: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 397: 0.24997221690002475
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 398
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 398: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 398: 0.249972046366549
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 399
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 399: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 399: 0.24997187520707104
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 400
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 400: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 400: 0.24997170341496383
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 401
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 401: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 401: 0.24997153098353828
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 402
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 402: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 402: 0.24997135790604155
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 403
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 403: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 403: 0.24997118417565695
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 404
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 404: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 404: 0.249971009785502
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 405
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 405: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 405: 0.24997083472862855
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 406
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 406: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 406: 0.2499706589980209
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 407
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 407: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 407: 0.2499704825865952
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 408
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 408: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 408: 0.2499703054871986
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 409
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 409: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 409: 0.24997012769260768
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 410
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 410: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 410: 0.2499699491955279
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 411
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 411: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 411: 0.24996976998859224
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 412
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 412: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 412: 0.24996959006436037
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 413
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 413: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 413: 0.24996940941531753
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 414
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 414: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 414: 0.24996922803387286
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 415
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 415: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 415: 0.24996904591235913
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 416
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 416: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 416: 0.24996886304303106
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 417
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 417: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 417: 0.24996867941806408
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 418
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 418: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 418: 0.24996849502955332
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 419
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 419: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 419: 0.24996830986951263
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 420
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 420: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 420: 0.24996812392987292
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 421
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 421: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 421: 0.24996793720248095
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 422
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 422: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 422: 0.24996774967909846
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 423
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 423: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 423: 0.24996756135140039
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 424
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 424: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 424: 0.24996737221097395
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 425
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 425: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 425: 0.24996718224931697
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 426
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 426: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 426: 0.24996699145783668
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 427
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 427: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 427: 0.24996679982784858
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 428
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 428: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 428: 0.24996660735057427
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 429
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 429: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 429: 0.2499664140171411
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 430
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 430: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 430: 0.24996621981857978
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 431
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 431: t_compute_gradients: 3 ms
[INFO] [stdout] cost across training set after epoch 431: 0.24996602474582325
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 432
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 432: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 432: 0.24996582878970522
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 433
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 433: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 433: 0.24996563194095875
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 434
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 434: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 434: 0.24996543419021436
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 435
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 435: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 435: 0.24996523552799857
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 436
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 436: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 436: 0.24996503594473246
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 437
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 437: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 437: 0.24996483543072986
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 438
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 438: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 438: 0.24996463397619578
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 439
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 439: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 439: 0.2499644315712243
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 440
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 440: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 440: 0.24996422820579753
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 441
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 441: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 441: 0.24996402386978325
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 442
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 442: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 442: 0.2499638185529336
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 443
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 443: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 443: 0.2499636122448828
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 444
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 444: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 444: 0.2499634049351455
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 445
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 445: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 445: 0.249963196613115
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 446
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 446: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 446: 0.24996298726806102
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 447
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 447: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 447: 0.24996277688912794
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 448
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 448: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 448: 0.24996256546533302
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 449
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 449: t_compute_gradients: 2 ms
[INFO] [stdout] cost across training set after epoch 449: 0.24996235298556374
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 450
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 450: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 450: 0.2499621394385764
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 451
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 451: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 451: 0.2499619248129933
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 452
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 452: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 452: 0.24996170909730164
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 453
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 453: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 453: 0.24996149227984993
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 454
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 454: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 454: 0.24996127434884707
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 455
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 455: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 455: 0.24996105529235932
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 456
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 456: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 456: 0.24996083509830802
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 457
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 457: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 457: 0.2499606137544676
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 458
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 458: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 458: 0.24996039124846278
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 459
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 459: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 459: 0.24996016756776646
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 460
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 460: t_compute_gradients: 3 ms
[INFO] [stdout] cost across training set after epoch 460: 0.24995994269969674
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 461
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 461: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 461: 0.2499597166314152
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 462
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 462: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 462: 0.24995948934992315
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 463
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 463: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 463: 0.24995926084206005
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 464
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 464: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 464: 0.24995903109450043
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 465
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 465: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 465: 0.24995880009375063
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 466
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 466: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 466: 0.2499585678261469
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 467
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 467: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 467: 0.2499583342778519
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 468
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 468: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 468: 0.24995809943485217
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 469
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 469: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 469: 0.24995786328295472
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 470
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 470: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 470: 0.24995762580778433
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 471
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 471: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 471: 0.2499573869947805
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 472
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 472: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 472: 0.24995714682919404
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 473
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 473: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 473: 0.24995690529608425
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 474
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 474: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 474: 0.24995666238031497
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 475
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 475: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 475: 0.24995641806655183
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 476
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 476: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 476: 0.24995617233925893
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 477
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 477: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 477: 0.24995592518269474
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 478
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 478: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 478: 0.2499556765809091
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 479
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 479: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 479: 0.24995542651773914
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 480
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 480: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 480: 0.24995517497680625
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 481
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 481: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 481: 0.24995492194151153
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 482
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 482: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 482: 0.2499546673950323
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 483
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 483: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 483: 0.24995441132031865
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 484
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 484: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 484: 0.24995415370008822
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 485
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 485: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 485: 0.24995389451682332
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 486
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 486: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 486: 0.24995363375276605
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 487
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 487: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 487: 0.2499533713899144
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 488
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 488: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 488: 0.2499531074100177
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 489
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 489: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 489: 0.24995284179457183
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 490
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 490: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 490: 0.2499525745248154
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 491
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 491: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 491: 0.24995230558172485
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 492
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 492: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 492: 0.2499520349460093
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 493
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 493: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 493: 0.24995176259810595
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 494
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 494: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 494: 0.2499514885181755
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 1 ms
[INFO] [stdout] finished ff for all training points - epoch 495
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 495: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 495: 0.24995121268609669
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 496
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 496: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 496: 0.2499509350814609
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 497
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 497: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 497: 0.24995065568356784
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 498
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 498: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 498: 0.2499503744714186
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 499
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 499: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 499: 0.24995009142371197
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 500
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 500: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 500: 0.2499498065188374
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 501
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 501: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 501: 0.24994951973486984
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 502
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 502: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 502: 0.24994923104956362
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 503
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 503: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 503: 0.2499489404403469
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 504
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 504: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 504: 0.24994864788431478
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 505
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 505: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 505: 0.24994835335822385
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 506
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 506: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 506: 0.24994805683848495
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 507
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 507: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 507: 0.2499477583011572
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 508
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 508: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 508: 0.24994745772194094
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 509
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 509: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 509: 0.24994715507617102
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 510
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 510: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 510: 0.24994685033880998
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 511
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 511: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 511: 0.24994654348444012
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 512
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 512: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 512: 0.2499462344872568
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 513
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 513: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 513: 0.2499459233210609
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 514
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 514: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 514: 0.24994560995925091
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 515
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 515: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 515: 0.24994529437481477
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 516
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 516: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 516: 0.24994497654032263
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 517
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 517: t_compute_gradients: 1 ms
[INFO] [stdout] cost across training set after epoch 517: 0.24994465642791758
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 518
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 518: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 518: 0.249944334009308
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 519
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 519: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 519: 0.24994400925575855
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 520
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 520: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 520: 0.2499436821380813
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 521
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 521: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 521: 0.2499433526266269
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 522
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 522: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 522: 0.24994302069127466
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 523
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 523: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 523: 0.24994268630142433
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 524
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 524: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 524: 0.24994234942598476
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 525
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 525: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 525: 0.24994201003336508
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 526
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 526: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 526: 0.24994166809146395
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 527
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 527: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 527: 0.2499413235676596
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 528
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 528: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 528: 0.24994097642879837
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 529
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 529: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 529: 0.24994062664118433
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 530
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 530: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 530: 0.24994027417056758
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 531
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 531: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 531: 0.2499399189821334
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 532
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 532: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 532: 0.24993956104048945
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 533
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 533: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 533: 0.2499392003096546
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 534
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 534: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 534: 0.2499388367530458
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 535
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 535: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 535: 0.24993847033346558
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 536
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 536: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 536: 0.2499381010130893
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 537
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 537: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 537: 0.24993772875345116
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 538
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 538: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 538: 0.24993735351543117
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 539
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 539: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 539: 0.2499369752592401
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 540
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 540: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 540: 0.24993659394440626
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 541
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 541: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 541: 0.24993620952975942
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 542
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 542: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 542: 0.24993582197341652
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 543
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 543: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 543: 0.24993543123276582
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 544
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 544: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 544: 0.2499350372644503
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 545
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 545: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 545: 0.2499346400243522
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 546
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 546: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 546: 0.2499342394675755
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 547
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 547: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 547: 0.2499338355484285
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 548
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 548: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 548: 0.24993342822040665
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 549
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 549: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 549: 0.24993301743617363
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 550
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 550: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 550: 0.24993260314754315
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 551
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 551: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 551: 0.24993218530545894
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 552
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 552: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 552: 0.24993176385997593
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 553
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 553: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 553: 0.24993133876023915
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 554
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 554: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 554: 0.24993090995446318
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 555
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 555: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 555: 0.24993047738991056
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 556
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 556: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 556: 0.2499300410128699
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 557
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 557: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 557: 0.24992960076863296
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 558
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 558: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 558: 0.2499291566014718
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 559
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 559: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 559: 0.24992870845461432
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 560
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 560: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 560: 0.24992825627021964
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 561
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 561: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 561: 0.2499277999893535
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 562
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 562: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 562: 0.24992733955196114
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 563
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 563: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 563: 0.2499268748968413
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 564
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 564: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 564: 0.2499264059616185
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 565
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 565: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 565: 0.2499259326827144
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 566
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 566: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 566: 0.24992545499531907
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 567
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 567: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 567: 0.2499249728333603
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 568
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 568: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 568: 0.24992448612947368
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 569
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 569: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 569: 0.24992399481496963
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 570
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 570: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 570: 0.24992349881980158
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 571
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 571: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 571: 0.24992299807253165
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 572
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 572: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 572: 0.2499224925002963
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 573
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 573: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 573: 0.24992198202877045
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 574
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 574: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 574: 0.24992146658213038
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 575
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 575: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 575: 0.24992094608301585
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 576
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 576: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 576: 0.24992042045249155
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 577
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 577: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 577: 0.24991988961000572
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 578
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 578: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 578: 0.2499193534733494
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 579
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 579: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 579: 0.24991881195861354
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 580
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 580: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 580: 0.2499182649801442
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 581
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 581: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 581: 0.2499177124504973
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 582
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 582: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 582: 0.24991715428039232
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 583
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 583: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 583: 0.2499165903786628
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 584
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 584: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 584: 0.2499160206522067
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 585
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 585: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 585: 0.24991544500593482
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 586
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 586: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 586: 0.24991486334271779
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 587
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 587: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 587: 0.2499142755633307
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 588
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 588: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 588: 0.24991368156639635
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 589
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 589: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 589: 0.24991308124832715
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 590
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 590: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 590: 0.24991247450326362
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 591
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 591: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 591: 0.24991186122301318
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 592
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 592: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 592: 0.24991124129698425
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 593
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 593: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 593: 0.24991061461212044
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 594
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 594: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 594: 0.249909981052831
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 595
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 595: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 595: 0.24990934050092015
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 596
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 596: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 596: 0.24990869283551248
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 597
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 597: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 597: 0.24990803793297775
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 598
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 598: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 598: 0.24990737566685114
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 599
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 599: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 599: 0.24990670590775252
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 600
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 600: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 600: 0.24990602852330146
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 601
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 601: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 601: 0.24990534337803033
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 602
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 602: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 602: 0.24990465033329365
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 603
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 603: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 603: 0.2499039492471748
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 604
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 604: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 604: 0.2499032399743893
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 605
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 605: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 605: 0.24990252236618415
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 606
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 606: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 606: 0.24990179627023426
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 607
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 607: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 607: 0.24990106153053424
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 608
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 608: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 608: 0.24990031798728807
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 609
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 609: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 609: 0.24989956547679223
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 610
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 610: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 610: 0.24989880383131663
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 611
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 611: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 611: 0.24989803287897988
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 612
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 612: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 612: 0.24989725244362115
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 613
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 613: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 613: 0.24989646234466528
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 614
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 614: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 614: 0.2498956623969854
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 615
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 615: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 615: 0.2498948524107579
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 616
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 616: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 616: 0.24989403219131384
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 617
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 617: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 617: 0.2498932015389829
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 618
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 618: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 618: 0.24989236024893308
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 619
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 619: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 619: 0.24989150811100255
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 620
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 620: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 620: 0.24989064490952634
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 621
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 621: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 621: 0.2498897704231553
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 622
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 622: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 622: 0.2498888844246682
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 623
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 623: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 623: 0.24988798668077594
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 624
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 624: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 624: 0.2498870769519191
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 625
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 625: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 625: 0.24988615499205596
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 626
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 626: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 626: 0.24988522054844245
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 627
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 627: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 627: 0.24988427336140356
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 628
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 628: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 628: 0.2498833131640946
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 629
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 629: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 629: 0.2498823396822527
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 630
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 630: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 630: 0.24988135263393868
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 631
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 631: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 631: 0.24988035172926706
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 632
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 632: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 632: 0.2498793366701252
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 633
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 633: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 633: 0.24987830714988077
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 634
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 634: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 634: 0.24987726285307552
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 635
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 635: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 635: 0.24987620345510755
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 636
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 636: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 636: 0.2498751286218981
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 637
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 637: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 637: 0.2498740380095447
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 638
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 638: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 638: 0.24987293126395863
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 639
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 639: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 639: 0.249871808020487
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 640
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 640: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 640: 0.249870667903516
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 641
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 641: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 641: 0.24986951052605919
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 642
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 642: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 642: 0.2498683354893239
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 643
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 643: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 643: 0.24986714238226077
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 644
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 644: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 644: 0.2498659307810896
[INFO] [stdout] 
[INFO] [stdout] starting mini batch from 0 to 20
[INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms
[INFO] [stdout] finished ff for all training points - epoch 645
[INFO] [stdout] computing gradients...
[INFO] [stdout] t_compute_gradients epoch 645: t_compute_gradients: 0 ms
[INFO] [stdout] cost across training set after epoch 645: 0.24986470024880564
[WARN] too many lines in the log, truncating it
