[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 1.86.0 for beta-1.87-1 [INFO] running `Command { std: "git" "clone" "/workspace/cache/git-repos/https%3A%2F%2Fgithub.com%2Fmaxjeffos%2Frust-neural-network-experiments" "/workspace/builds/worker-5-tc1/source", kill_on_drop: false }` [INFO] [stderr] Cloning into '/workspace/builds/worker-5-tc1/source'... [INFO] [stderr] done. [INFO] validating manifest of git repo https://github.com/maxjeffos/rust-neural-network-experiments on toolchain 1.86.0 [INFO] running `Command { std: CARGO_HOME="/workspace/cargo-home" RUSTUP_HOME="/workspace/rustup-home" "/workspace/cargo-home/bin/cargo" "+1.86.0" "metadata" "--manifest-path" "Cargo.toml" "--no-deps", kill_on_drop: false }` [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-5-tc1/source/Cargo.toml [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" "+1.86.0" "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] 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 time-test v0.2.2 [INFO] [stderr] Downloaded mnist v0.5.0 [INFO] [stderr] Downloaded autodiff v0.4.0 [INFO] [stderr] Downloaded crossbeam-epoch v0.9.6 [INFO] running `Command { std: "docker" "create" "-v" "/var/lib/crater-agent-workspace/builds/worker-5-tc1/target:/opt/rustwide/target:rw,Z" "-v" "/var/lib/crater-agent-workspace/builds/worker-5-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:b0b074c097205a61b89e8ad263052f976b2b332c4dc5f02aef1fe52501660d6e" "/opt/rustwide/cargo-home/bin/cargo" "+1.86.0" "metadata" "--no-deps" "--format-version=1", kill_on_drop: false }` [INFO] [stdout] e72f335e9f793deed98bc4d088e9a1cb0f6d650faa34c6ee7d004a16535a3a40 [INFO] running `Command { std: "docker" "start" "-a" "e72f335e9f793deed98bc4d088e9a1cb0f6d650faa34c6ee7d004a16535a3a40", kill_on_drop: false }` [INFO] running `Command { std: "docker" "inspect" "e72f335e9f793deed98bc4d088e9a1cb0f6d650faa34c6ee7d004a16535a3a40", kill_on_drop: false }` [INFO] running `Command { std: "docker" "rm" "-f" "e72f335e9f793deed98bc4d088e9a1cb0f6d650faa34c6ee7d004a16535a3a40", kill_on_drop: false }` [INFO] [stdout] e72f335e9f793deed98bc4d088e9a1cb0f6d650faa34c6ee7d004a16535a3a40 [INFO] running `Command { std: "docker" "create" "-v" "/var/lib/crater-agent-workspace/builds/worker-5-tc1/target:/opt/rustwide/target:rw,Z" "-v" "/var/lib/crater-agent-workspace/builds/worker-5-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=warn" "-e" "RUSTDOCFLAGS=--cap-lints=warn" "-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:b0b074c097205a61b89e8ad263052f976b2b332c4dc5f02aef1fe52501660d6e" "/opt/rustwide/cargo-home/bin/cargo" "+1.86.0" "build" "--frozen" "--message-format=json", kill_on_drop: false }` [INFO] [stdout] b2fe64d90b485bb6e97c2d4cd8f8e0f0506a4c64abbd421ff1415ac6a9f576e6 [INFO] running `Command { std: "docker" "start" "-a" "b2fe64d90b485bb6e97c2d4cd8f8e0f0506a4c64abbd421ff1415ac6a9f576e6", 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] 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 libc v0.2.112 [INFO] [stderr] Compiling libm v0.2.1 [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 ppv-lite86 v0.2.16 [INFO] [stderr] Compiling rayon-core v1.9.1 [INFO] [stderr] Compiling rayon v1.5.1 [INFO] [stderr] Compiling proc-macro2 v1.0.36 [INFO] [stderr] Compiling either v1.6.1 [INFO] [stderr] Compiling num-integer v0.1.44 [INFO] [stderr] Compiling unicode-xid v0.2.2 [INFO] [stderr] Compiling serde v1.0.136 [INFO] [stderr] Compiling rawpointer v0.2.1 [INFO] [stderr] Compiling syn v1.0.85 [INFO] [stderr] Compiling matrixmultiply v0.3.2 [INFO] [stderr] Compiling serde_derive v1.0.136 [INFO] [stderr] Compiling byteorder v1.4.3 [INFO] [stderr] Compiling serde_json v1.0.78 [INFO] [stderr] Compiling mnist v0.5.0 [INFO] [stderr] Compiling itoa v1.0.1 [INFO] [stderr] Compiling ryu v1.0.9 [INFO] [stderr] Compiling anyhow v1.0.82 [INFO] [stderr] Compiling crossbeam-channel v0.5.2 [INFO] [stderr] Compiling crossbeam-deque v0.8.1 [INFO] [stderr] Compiling quote v1.0.14 [INFO] [stderr] Compiling getrandom v0.2.4 [INFO] [stderr] Compiling num_cpus v1.13.1 [INFO] [stderr] Compiling rand_core v0.6.3 [INFO] [stderr] Compiling rand_chacha v0.3.1 [INFO] [stderr] Compiling rand v0.8.4 [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) -> FT { [INFO] [stdout] | ^^^^^^^^^^ [INFO] [stdout] | [INFO] [stdout] = note: `#[warn(dead_code)]` 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: elided lifetime has a name [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] | -- lifetime `'a` declared here ^^^^^^^^ this elided lifetime gets resolved as `'a` [INFO] [stdout] | [INFO] [stdout] = note: `#[warn(elided_named_lifetimes)]` 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)]` 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 { [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> { [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 test4-multivariable-regression v0.1.0 (/opt/rustwide/workdir/test4-multivariable-regression) [INFO] [stderr] Compiling test5-playing-with-matrix-ideas v0.1.0 (/opt/rustwide/workdir/test5-playing-with-matrix-ideas) [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)]` 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 test2-mlp-classifier v0.1.0 (/opt/rustwide/workdir/test2-mlp-classifier) [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)]` 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: 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)]` 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)]` 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)]` 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, output_size: usize) -> Self { [INFO] [stdout] | ^^^ [INFO] [stdout] [INFO] [stdout] [INFO] [stderr] Compiling metrics v0.1.0 (/opt/rustwide/workdir/metrics) [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] [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)]` 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)]` 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)]` 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)]` 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: 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)]` 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)]` 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 `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)]` 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: 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)]` 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] [stderr] Finished `dev` profile [unoptimized + debuginfo] target(s) in 18.87s [INFO] running `Command { std: "docker" "inspect" "b2fe64d90b485bb6e97c2d4cd8f8e0f0506a4c64abbd421ff1415ac6a9f576e6", kill_on_drop: false }` [INFO] running `Command { std: "docker" "rm" "-f" "b2fe64d90b485bb6e97c2d4cd8f8e0f0506a4c64abbd421ff1415ac6a9f576e6", kill_on_drop: false }` [INFO] [stdout] b2fe64d90b485bb6e97c2d4cd8f8e0f0506a4c64abbd421ff1415ac6a9f576e6 [INFO] running `Command { std: "docker" "create" "-v" "/var/lib/crater-agent-workspace/builds/worker-5-tc1/target:/opt/rustwide/target:rw,Z" "-v" "/var/lib/crater-agent-workspace/builds/worker-5-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=warn" "-e" "RUSTDOCFLAGS=--cap-lints=warn" "-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:b0b074c097205a61b89e8ad263052f976b2b332c4dc5f02aef1fe52501660d6e" "/opt/rustwide/cargo-home/bin/cargo" "+1.86.0" "test" "--frozen" "--no-run" "--message-format=json", kill_on_drop: false }` [INFO] [stdout] 6c743a48bcf0eb76f70d1b35d1a6e546be7d2020d8618dc7c3eddb5e8b4f00aa [INFO] running `Command { std: "docker" "start" "-a" "6c743a48bcf0eb76f70d1b35d1a6e546be7d2020d8618dc7c3eddb5e8b4f00aa", 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] 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 float-cmp v0.9.0 [INFO] [stderr] Compiling time v0.1.43 [INFO] [stdout] warning: elided lifetime has a name [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] | -- lifetime `'a` declared here ^^^^^^^^ this elided lifetime gets resolved as `'a` [INFO] [stdout] | [INFO] [stdout] = note: `#[warn(elided_named_lifetimes)]` 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)]` 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 { [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> { [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 test1-autodiff v0.1.0 (/opt/rustwide/workdir/test1-autodiff) [INFO] [stderr] Compiling test5-playing-with-matrix-ideas v0.1.0 (/opt/rustwide/workdir/test5-playing-with-matrix-ideas) [INFO] [stderr] Compiling common v0.1.0 (/opt/rustwide/workdir/common) [INFO] [stderr] Compiling mnist-data v0.1.0 (/opt/rustwide/workdir/mnist-data) [INFO] [stderr] Compiling test2-mlp-classifier v0.1.0 (/opt/rustwide/workdir/test2-mlp-classifier) [INFO] [stderr] Compiling metrics v0.1.0 (/opt/rustwide/workdir/metrics) [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)]` 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)]` 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)]` 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)]` 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)]` 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)]` 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: 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)]` 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: 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)]` 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)]` 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)]` 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, output_size: usize) -> Self { [INFO] [stdout] | ^^^ [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) -> FT { [INFO] [stdout] | ^^^^^^^^^^ [INFO] [stdout] | [INFO] [stdout] = note: `#[warn(dead_code)]` on by default [INFO] [stdout] [INFO] [stdout] [INFO] [stderr] Compiling test4-multivariable-regression v0.1.0 (/opt/rustwide/workdir/test4-multivariable-regression) [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: elided lifetime has a name [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] | -- lifetime `'a` declared here ^^^^^^^^ this elided lifetime gets resolved as `'a` [INFO] [stdout] | [INFO] [stdout] = note: `#[warn(elided_named_lifetimes)]` on by default [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)]` 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)]` 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: 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)]` 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: 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)]` 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)]` on by default [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)]` 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)]` on by default [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)]` on by default [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)]` 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)]` 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: `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)]` 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: 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)]` 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] [stderr] Finished `test` profile [unoptimized + debuginfo] target(s) in 5.67s [INFO] running `Command { std: "docker" "inspect" "6c743a48bcf0eb76f70d1b35d1a6e546be7d2020d8618dc7c3eddb5e8b4f00aa", kill_on_drop: false }` [INFO] running `Command { std: "docker" "rm" "-f" "6c743a48bcf0eb76f70d1b35d1a6e546be7d2020d8618dc7c3eddb5e8b4f00aa", kill_on_drop: false }` [INFO] [stdout] 6c743a48bcf0eb76f70d1b35d1a6e546be7d2020d8618dc7c3eddb5e8b4f00aa [INFO] running `Command { std: "docker" "create" "-v" "/var/lib/crater-agent-workspace/builds/worker-5-tc1/target:/opt/rustwide/target:rw,Z" "-v" "/var/lib/crater-agent-workspace/builds/worker-5-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=warn" "-e" "RUSTDOCFLAGS=--cap-lints=warn" "-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:b0b074c097205a61b89e8ad263052f976b2b332c4dc5f02aef1fe52501660d6e" "/opt/rustwide/cargo-home/bin/cargo" "+1.86.0" "test" "--frozen", kill_on_drop: false }` [INFO] [stdout] 7332ef7f233596604b05e2d73703d11a6f4bfc2efef7892887d9305d34c619a2 [INFO] running `Command { std: "docker" "start" "-a" "7332ef7f233596604b05e2d73703d11a6f4bfc2efef7892887d9305d34c619a2", 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] 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: elided lifetime has a name [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] | -- lifetime `'a` declared here ^^^^^^^^ this elided lifetime gets resolved as `'a` [INFO] [stderr] | [INFO] [stderr] = note: `#[warn(elided_named_lifetimes)]` on by default [INFO] [stderr] [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)]` 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 { [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> { [INFO] [stderr] | ^^^^^^^^^^^^^^^^^^ [INFO] [stderr] [INFO] [stderr] warning: `common` (lib) generated 4 warnings [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) -> FT { [INFO] [stderr] | ^^^^^^^^^^ [INFO] [stderr] | [INFO] [stderr] = note: `#[warn(dead_code)]` on by default [INFO] [stderr] [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)]` 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: `test1-autodiff` (bin "test1-autodiff" test) generated 1 warning [INFO] [stderr] warning: `test4-multivariable-regression` (bin "test4-multivariable-regression" test) generated 2 warnings [INFO] [stderr] warning: `common` (lib test) generated 2 warnings (2 duplicates) [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)]` 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)]` 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)]` 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)]` 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, output_size: usize) -> Self { [INFO] [stderr] | ^^^ [INFO] [stderr] [INFO] [stderr] warning: `test2-mlp-classifier` (bin "test2-mlp-classifier" test) generated 7 warnings [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)]` 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)]` 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)]` 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: 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)]` 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)]` 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)]` 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: 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)]` 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)]` 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)]` 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)]` 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: `test7-nn-mnist-classifier` (lib) generated 6 warnings [INFO] [stderr] warning: `test6-nn` (lib) generated 8 warnings [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 1 suggestion) [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)]` 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: 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)]` 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: `test6-nn` (bin "test6-nn" test) generated 1 warning [INFO] [stderr] warning: `test7-nn-mnist-classifier` (bin "test7-nn-mnist-classifier" test) generated 1 warning [INFO] [stderr] Finished `test` profile [unoptimized + debuginfo] target(s) in 0.26s [INFO] [stderr] Running unittests src/lib.rs (/opt/rustwide/target/debug/deps/common-8617b89baab6da3d) [INFO] [stdout] [INFO] [stdout] running 104 tests [INFO] [stdout] test linalg::column_vector_tests::add_works ... ok [INFO] [stdout] test linalg::column_vector_tests::add_mut_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::div_scalar_mut_works ... ok [INFO] [stdout] test linalg::column_vector_tests::dot_product_works ... ok [INFO] [stdout] test linalg::column_vector_tests::elementwise_divide_works ... ok [INFO] [stdout] test linalg::column_vector_tests::elementwise_divide_in_place_works ... 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_in_place_works ... ok [INFO] [stdout] test linalg::column_vector_tests::hadamard_product_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::multiply_by_scalar_works ... ok [INFO] [stdout] test linalg::column_vector_tests::new_zero_vector_works ... ok [INFO] [stdout] test linalg::column_vector_tests::hadamard_product_chaining_works ... ok [INFO] [stdout] test linalg::column_vector_tests::subtract_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_do_double_iterate_over_column_vectors ... 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::test_outer_product ... ok [INFO] [stdout] test linalg::column_vector_tests::test_vec_length ... ok [INFO] [stdout] test linalg::column_vector_tests::transpose_works ... ok [INFO] [stdout] test linalg::column_vector_tests::test_elementwise_square_root_in_place ... ok [INFO] [stdout] test linalg::column_vector_tests::transpose_into_row_vector_matrix_works ... 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::column_vector_tests::div_scalar_works ... ok [INFO] [stdout] test linalg::rows_matrix_builder_tests::test_row_matrix_builder_with_non_chaining ... ok [INFO] [stdout] test linalg::column_vector_tests::test_mult_scalar_mut ... ok [INFO] [stdout] test linalg::column_vector_tests::mult_by_matrix_works ... 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::add_mut_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::add_in_place_par_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_hadamard_product_in_place ... ok [INFO] [stdout] test linalg::tests::test_matrix_vector_multiplication ... ok [INFO] [stdout] test linalg::tests::test_elementwise_divide ... ok [INFO] [stdout] test linalg::tests::push_column_works ... ok [INFO] [stdout] test linalg::tests::test_elementwise_square_root_in_place ... ok [INFO] [stdout] test linalg::tests::test_extract_column ... ok [INFO] [stdout] test linalg::tests::test_elementwise_divide_product_in_place ... 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_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::test_div_scalar_mut ... 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::tests::add_in_place_works ... ok [INFO] [stdout] test linalg::tests::transpose_works_for_column_vector ... ok [INFO] [stdout] test linalg::tests::test_multiply_by_scalar ... ok [INFO] [stdout] test old_matrix::columns_matrix_builder_tests::test_columns_matrix_builder_with_chaining ... ok [INFO] [stdout] test old_matrix::rows_matrix_builder_tests::test_rows_matrix_builder_with_chaining ... ok [INFO] [stdout] test linalg::tests::test_matrix_vector_multiplication_with_column_vector_type ... ok [INFO] [stdout] test linalg::tests::test_from_columns ... ok [INFO] [stdout] test linalg::tests::test_mult_scalar_mut ... ok [INFO] [stdout] test old_matrix::tests::can_add_rows_and_get_values_at_specified_indexes ... ok [INFO] [stdout] test old_matrix::tests::multiply_works ... ok [INFO] [stdout] test old_matrix::tests::minus_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_in_place ... ok [INFO] [stdout] test old_matrix::tests::test_matrix_vector_multiplication ... ok [INFO] [stdout] test old_matrix::tests::test_multiply_by_scalar_in_place ... ok [INFO] [stdout] test old_matrix::tests::transpose_of_column_vector_mult_by_column_vector_works ... ok [INFO] [stdout] test old_matrix::tests::test_vec_length ... ok [INFO] [stdout] test old_matrix::tests::transpose_works ... ok [INFO] [stdout] test softmax::tests::test_softmax_derivative_diagonal ... ok [INFO] [stdout] test old_matrix::tests::test_hadamard_product ... ok [INFO] [stdout] test softmax::tests::test_softmax_derivative_matrix_size ... ok [INFO] [stdout] test softmax::tests::test_softmax_derivative_off_diagonal ... ok [INFO] [stdout] test softmax::tests::test_softmax_sum_to_one ... ok [INFO] [stdout] test softmax::tests::test_softmax_derivative_uniform_input ... ok [INFO] [stdout] test tests::dot_product_works ... ok [INFO] [stdout] test old_matrix::tests::new_identity_matrix_works ... ok [INFO] [stdout] test old_matrix::tests::transpose_works_for_column_vector ... ok [INFO] [stdout] test softmax::tests::test_softmax_numerical_stability ... ok [INFO] [stdout] test point::tests::it_works ... ok [INFO] [stdout] test old_matrix::tests::test_multiply_by_scalar ... ok [INFO] [stdout] test softmax::tests::test_softmax_output_range ... ok [INFO] [stdout] test tests::dot_returns_err_if_dimentions_are_zero ... ok [INFO] [stdout] test linalg::rows_matrix_builder_tests::test_rows_matrix_builder_with_chaining ... ok [INFO] [stdout] test linalg::tests::test_div_scalar ... ok [INFO] [stdout] test linalg::tests::test_extract_column_vector_as_matrix ... ok [INFO] [stdout] [INFO] [stdout] test result: ok. 104 passed; 0 failed; 0 ignored; 0 measured; 0 filtered out; finished in 0.04s [INFO] [stdout] [INFO] [stderr] Running unittests src/lib.rs (/opt/rustwide/target/debug/deps/metrics-0795c6b9f7be979a) [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-28233ebe6705e418) [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-a6b55f1c573a942e) [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-ce3c8b976e384173) [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-61a6867f971584ef) [INFO] [stdout] [INFO] [stderr] Running unittests src/main.rs (/opt/rustwide/target/debug/deps/test4_multivariable_regression-b293d1843842d65f) [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] [stdout] [INFO] [stdout] running 7 tests [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::compute_partial_derivatives_v_works ... 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 0.01s [INFO] [stdout] [INFO] [stderr] Running unittests src/main.rs (/opt/rustwide/target/debug/deps/test5_playing_with_matrix_ideas-2b2b1bb085dbc0ec) [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-7a1531b7a9affa30) [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_derivative ... ok [INFO] [stdout] test activation::activator::sigmoid::tests::activate_derivative_works ... ok [INFO] [stdout] test activation::activator::tests::activate_derivative_vector_works ... ok [INFO] [stdout] test activation::activator::sigmoid::tests::activate_works ... ok [INFO] [stdout] test activation::activator::tests::activate_vector_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::jelu::tests::test_activate ... ok [INFO] [stdout] test activation::jelu::tests::test_activate_derivative ... ok [INFO] [stdout] test activation::leaky_relu::tests::activate_prime_works ... 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::activator::elu::tests::activate_works ... ok [INFO] [stdout] test activation::activator::relu::tests::activate_works ... ok [INFO] [stdout] test activation::relu::tests::activate_works ... ok [INFO] [stdout] test activation::sigmoid::tests::activate_works ... ok [INFO] [stdout] test activation::sigmoid::tests::activate_derivative_works ... ok [INFO] [stdout] test activation::activator::relu::tests::activate_prime_works ... ok [INFO] [stdout] test activation::activator::jelu::tests::test_activate ... 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::divide_scalar_works ... ok [INFO] [stdout] test big_theta::tests::test_add_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_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_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 cost::tests::test_quadratic_cost_fn_dimension_mismatch ... ok [INFO] [stdout] test tests::feed_forward_works_simple_three_layer_using_feed_forward_capturing ... 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 tests::feed_forward_works_simple_three_layer ... ok [INFO] [stdout] test big_theta::tests::test_elementwise_mult_in_place_place_works ... ok [INFO] [stdout] test tests::feed_forward_works_simple_two_layer ... 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_cost_single_tr_ex_multiple_output_neurons ... 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 builder::test_nn_builder::cannot_add_output_layer_before_input_layer - should panic ... 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::panics_on_hidden_layer_with_invalid_weight_or_bias_dimensions ... 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::simple_jelu_test ... ok [INFO] [stdout] test tests::simple_leaky_relu_test ... ok [INFO] [stdout] test tests::simple_test_to_get_elu_sorted_out ... FAILED [INFO] [stdout] test tests::test_nn_using_more_hidden_layers_with_more_neurons ... ok [INFO] [stdout] test tests::test_nn_using_constructor_for_random_initial_weights_and_biases ... ok [INFO] [stdout] test tests::test_nn has been running for over 60 seconds [INFO] [stdout] test tests::test_nn ... ok [INFO] [stdout] [INFO] [stdout] failures: [INFO] [stdout] [INFO] [stdout] ---- tests::simple_test_to_get_elu_sorted_out 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: 0.25047036495462704 [INFO] [stdout] finished ff for all training points - epoch 0 [INFO] [stdout] ed: 0.000000002190662373215151 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533874 0.658029 │ [INFO] [stdout] │ -1.702373 -1.202225 │ [INFO] [stdout] │ -1.020093 0.622078 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023135 │ [INFO] [stdout] │ 1.759468 │ [INFO] [stdout] │ -0.526977 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 1 [INFO] [stdout] ed: 0.0000000020068193174957394 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533837 0.657992 │ [INFO] [stdout] │ -1.703547 -1.203399 │ [INFO] [stdout] │ -1.020312 0.621859 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023151 │ [INFO] [stdout] │ 1.760055 │ [INFO] [stdout] │ -0.526867 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 2 [INFO] [stdout] ed: 0.0000000018513908675084328 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533803 0.657958 │ [INFO] [stdout] │ -1.704627 -1.204479 │ [INFO] [stdout] │ -1.020512 0.621658 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023166 │ [INFO] [stdout] │ 1.760595 │ [INFO] [stdout] │ -0.526767 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 3 [INFO] [stdout] ed: 0.0000000017187944472728808 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533772 0.657927 │ [INFO] [stdout] │ -1.705627 -1.205479 │ [INFO] [stdout] │ -1.020697 0.621474 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023179 │ [INFO] [stdout] │ 1.761095 │ [INFO] [stdout] │ -0.526675 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 4 [INFO] [stdout] ed: 0.0000000016044264540770406 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533742 0.657897 │ [INFO] [stdout] │ -1.706559 -1.206411 │ [INFO] [stdout] │ -1.020868 0.621302 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023191 │ [INFO] [stdout] │ 1.761561 │ [INFO] [stdout] │ -0.526589 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 5 [INFO] [stdout] ed: 0.0000000015041193452798615 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533715 0.657870 │ [INFO] [stdout] │ -1.707432 -1.207284 │ [INFO] [stdout] │ -1.021028 0.621143 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023202 │ [INFO] [stdout] │ 1.761998 │ [INFO] [stdout] │ -0.526509 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 6 [INFO] [stdout] ed: 0.000000001416403151684843 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533689 0.657844 │ [INFO] [stdout] │ -1.708252 -1.208104 │ [INFO] [stdout] │ -1.021178 0.620993 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023213 │ [INFO] [stdout] │ 1.762408 │ [INFO] [stdout] │ -0.526435 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 7 [INFO] [stdout] ed: 0.0000000013380601352372033 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533664 0.657819 │ [INFO] [stdout] │ -1.709027 -1.208879 │ [INFO] [stdout] │ -1.021318 0.620852 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023222 │ [INFO] [stdout] │ 1.762795 │ [INFO] [stdout] │ -0.526364 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 8 [INFO] [stdout] ed: 0.0000000012686976324678112 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533641 0.657796 │ [INFO] [stdout] │ -1.709760 -1.209612 │ [INFO] [stdout] │ -1.021451 0.620720 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023231 │ [INFO] [stdout] │ 1.763161 │ [INFO] [stdout] │ -0.526298 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 9 [INFO] [stdout] ed: 0.0000000012054398772456552 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533619 0.657774 │ [INFO] [stdout] │ -1.710456 -1.210308 │ [INFO] [stdout] │ -1.021577 0.620594 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023240 │ [INFO] [stdout] │ 1.763509 │ [INFO] [stdout] │ -0.526235 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 10 [INFO] [stdout] ed: 0.0000000011482047901276423 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533598 0.657753 │ [INFO] [stdout] │ -1.711118 -1.210970 │ [INFO] [stdout] │ -1.021696 0.620475 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023248 │ [INFO] [stdout] │ 1.763841 │ [INFO] [stdout] │ -0.526176 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 11 [INFO] [stdout] ed: 0.0000000010968790661004396 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533577 0.657732 │ [INFO] [stdout] │ -1.711751 -1.211603 │ [INFO] [stdout] │ -1.021809 0.620361 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023255 │ [INFO] [stdout] │ 1.764157 │ [INFO] [stdout] │ -0.526119 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 12 [INFO] [stdout] ed: 0.0000000010492351706765626 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533558 0.657713 │ [INFO] [stdout] │ -1.712356 -1.212208 │ [INFO] [stdout] │ -1.021918 0.620253 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023262 │ [INFO] [stdout] │ 1.764459 │ [INFO] [stdout] │ -0.526065 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 13 [INFO] [stdout] ed: 0.000000001006086922175918 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533539 0.657694 │ [INFO] [stdout] │ -1.712935 -1.212787 │ [INFO] [stdout] │ -1.022021 0.620150 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023269 │ [INFO] [stdout] │ 1.764749 │ [INFO] [stdout] │ -0.526013 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 14 [INFO] [stdout] ed: 0.000000000966465772294671 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533521 0.657676 │ [INFO] [stdout] │ -1.713492 -1.213344 │ [INFO] [stdout] │ -1.022120 0.620051 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023276 │ [INFO] [stdout] │ 1.765027 │ [INFO] [stdout] │ -0.525964 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 15 [INFO] [stdout] ed: 0.0000000009296320422127595 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533504 0.657659 │ [INFO] [stdout] │ -1.714027 -1.213879 │ [INFO] [stdout] │ -1.022215 0.619955 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023282 │ [INFO] [stdout] │ 1.765295 │ [INFO] [stdout] │ -0.525916 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 16 [INFO] [stdout] ed: 0.000000000895554020868371 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533487 0.657642 │ [INFO] [stdout] │ -1.714543 -1.214395 │ [INFO] [stdout] │ -1.022307 0.619864 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023287 │ [INFO] [stdout] │ 1.765553 │ [INFO] [stdout] │ -0.525871 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 17 [INFO] [stdout] ed: 0.00000000086426161819535 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533471 0.657626 │ [INFO] [stdout] │ -1.715040 -1.214892 │ [INFO] [stdout] │ -1.022395 0.619776 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023293 │ [INFO] [stdout] │ 1.765801 │ [INFO] [stdout] │ -0.525827 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 18 [INFO] [stdout] ed: 0.0000000008348412573911899 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533455 0.657610 │ [INFO] [stdout] │ -1.715520 -1.215372 │ [INFO] [stdout] │ -1.022479 0.619691 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023298 │ [INFO] [stdout] │ 1.766041 │ [INFO] [stdout] │ -0.525785 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 19 [INFO] [stdout] ed: 0.0000000008071614885152114 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533439 0.657594 │ [INFO] [stdout] │ -1.715984 -1.215836 │ [INFO] [stdout] │ -1.022561 0.619610 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023303 │ [INFO] [stdout] │ 1.766273 │ [INFO] [stdout] │ -0.525744 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 20 [INFO] [stdout] ed: 0.0000000007813202344557437 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533424 0.657579 │ [INFO] [stdout] │ -1.716433 -1.216285 │ [INFO] [stdout] │ -1.022640 0.619531 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023308 │ [INFO] [stdout] │ 1.766498 │ [INFO] [stdout] │ -0.525704 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 21 [INFO] [stdout] ed: 0.000000000757338666698597 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533410 0.657565 │ [INFO] [stdout] │ -1.716869 -1.216721 │ [INFO] [stdout] │ -1.022717 0.619454 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023312 │ [INFO] [stdout] │ 1.766716 │ [INFO] [stdout] │ -0.525666 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 22 [INFO] [stdout] ed: 0.0000000007348122974598643 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533396 0.657551 │ [INFO] [stdout] │ -1.717291 -1.217143 │ [INFO] [stdout] │ -1.022791 0.619380 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023316 │ [INFO] [stdout] │ 1.766927 │ [INFO] [stdout] │ -0.525629 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 23 [INFO] [stdout] ed: 0.0000000007135606598833152 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533382 0.657537 │ [INFO] [stdout] │ -1.717701 -1.217553 │ [INFO] [stdout] │ -1.022862 0.619308 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023320 │ [INFO] [stdout] │ 1.767132 │ [INFO] [stdout] │ -0.525593 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 24 [INFO] [stdout] ed: 0.0000000006933881633181132 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533368 0.657523 │ [INFO] [stdout] │ -1.718100 -1.217952 │ [INFO] [stdout] │ -1.022932 0.619239 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023324 │ [INFO] [stdout] │ 1.767331 │ [INFO] [stdout] │ -0.525559 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 25 [INFO] [stdout] ed: 0.0000000006738585240807345 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533355 0.657510 │ [INFO] [stdout] │ -1.718487 -1.218339 │ [INFO] [stdout] │ -1.022999 0.619171 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023328 │ [INFO] [stdout] │ 1.767525 │ [INFO] [stdout] │ -0.525525 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 26 [INFO] [stdout] ed: 0.0000000006566845488085143 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533342 0.657497 │ [INFO] [stdout] │ -1.718864 -1.218716 │ [INFO] [stdout] │ -1.023065 0.619106 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023332 │ [INFO] [stdout] │ 1.767713 │ [INFO] [stdout] │ -0.525492 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 27 [INFO] [stdout] ed: 0.0000000006387880442594312 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533329 0.657484 │ [INFO] [stdout] │ -1.719232 -1.219084 │ [INFO] [stdout] │ -1.023129 0.619042 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023335 │ [INFO] [stdout] │ 1.767897 │ [INFO] [stdout] │ -0.525460 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 28 [INFO] [stdout] ed: 0.0000000006224869113581148 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533317 0.657472 │ [INFO] [stdout] │ -1.719590 -1.219442 │ [INFO] [stdout] │ -1.023191 0.618980 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023339 │ [INFO] [stdout] │ 1.768076 │ [INFO] [stdout] │ -0.525429 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 29 [INFO] [stdout] ed: 0.0000000006074582597379487 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533305 0.657460 │ [INFO] [stdout] │ -1.719939 -1.219791 │ [INFO] [stdout] │ -1.023252 0.618919 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023342 │ [INFO] [stdout] │ 1.768250 │ [INFO] [stdout] │ -0.525399 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 30 [INFO] [stdout] ed: 0.0000000005932250877267104 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533293 0.657448 │ [INFO] [stdout] │ -1.720279 -1.220132 │ [INFO] [stdout] │ -1.023311 0.618860 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023345 │ [INFO] [stdout] │ 1.768421 │ [INFO] [stdout] │ -0.525370 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 31 [INFO] [stdout] ed: 0.000000000578705912904221 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533281 0.657436 │ [INFO] [stdout] │ -1.720612 -1.220464 │ [INFO] [stdout] │ -1.023368 0.618803 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023348 │ [INFO] [stdout] │ 1.768587 │ [INFO] [stdout] │ -0.525341 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 32 [INFO] [stdout] ed: 0.000000000565553866968695 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533270 0.657425 │ [INFO] [stdout] │ -1.720937 -1.220789 │ [INFO] [stdout] │ -1.023424 0.618746 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023351 │ [INFO] [stdout] │ 1.768750 │ [INFO] [stdout] │ -0.525313 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 33 [INFO] [stdout] ed: 0.0000000005530345853695396 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533258 0.657413 │ [INFO] [stdout] │ -1.721255 -1.221107 │ [INFO] [stdout] │ -1.023479 0.618692 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023354 │ [INFO] [stdout] │ 1.768909 │ [INFO] [stdout] │ -0.525286 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 34 [INFO] [stdout] ed: 0.0000000005408679924409539 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533247 0.657402 │ [INFO] [stdout] │ -1.721566 -1.221418 │ [INFO] [stdout] │ -1.023533 0.618638 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023356 │ [INFO] [stdout] │ 1.769064 │ [INFO] [stdout] │ -0.525259 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 35 [INFO] [stdout] ed: 0.0000000005290254748227561 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533236 0.657391 │ [INFO] [stdout] │ -1.721870 -1.221722 │ [INFO] [stdout] │ -1.023585 0.618586 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023359 │ [INFO] [stdout] │ 1.769216 │ [INFO] [stdout] │ -0.525233 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 36 [INFO] [stdout] ed: 0.0000000005180750534999955 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533225 0.657380 │ [INFO] [stdout] │ -1.722168 -1.222020 │ [INFO] [stdout] │ -1.023636 0.618534 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023361 │ [INFO] [stdout] │ 1.769365 │ [INFO] [stdout] │ -0.525207 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 37 [INFO] [stdout] ed: 0.0000000005071574851822354 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533215 0.657370 │ [INFO] [stdout] │ -1.722460 -1.222312 │ [INFO] [stdout] │ -1.023686 0.618484 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023364 │ [INFO] [stdout] │ 1.769511 │ [INFO] [stdout] │ -0.525182 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 38 [INFO] [stdout] ed: 0.0000000004971151520815742 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533204 0.657359 │ [INFO] [stdout] │ -1.722746 -1.222598 │ [INFO] [stdout] │ -1.023735 0.618435 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023366 │ [INFO] [stdout] │ 1.769654 │ [INFO] [stdout] │ -0.525158 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 39 [INFO] [stdout] ed: 0.000000000487454960663474 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533194 0.657349 │ [INFO] [stdout] │ -1.723026 -1.222878 │ [INFO] [stdout] │ -1.023783 0.618387 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023368 │ [INFO] [stdout] │ 1.769794 │ [INFO] [stdout] │ -0.525134 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 40 [INFO] [stdout] ed: 0.0000000004781680989351747 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533184 0.657339 │ [INFO] [stdout] │ -1.723301 -1.223153 │ [INFO] [stdout] │ -1.023830 0.618340 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023370 │ [INFO] [stdout] │ 1.769931 │ [INFO] [stdout] │ -0.525110 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 41 [INFO] [stdout] ed: 0.0000000004682745978053432 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533174 0.657329 │ [INFO] [stdout] │ -1.723570 -1.223423 │ [INFO] [stdout] │ -1.023877 0.618294 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023372 │ [INFO] [stdout] │ 1.770066 │ [INFO] [stdout] │ -0.525087 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 42 [INFO] [stdout] ed: 0.000000000460439551008371 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533164 0.657319 │ [INFO] [stdout] │ -1.723835 -1.223687 │ [INFO] [stdout] │ -1.023922 0.618249 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023374 │ [INFO] [stdout] │ 1.770198 │ [INFO] [stdout] │ -0.525065 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 43 [INFO] [stdout] ed: 0.000000000451630575647319 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533154 0.657309 │ [INFO] [stdout] │ -1.724095 -1.223947 │ [INFO] [stdout] │ -1.023966 0.618205 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023376 │ [INFO] [stdout] │ 1.770328 │ [INFO] [stdout] │ -0.525043 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 44 [INFO] [stdout] ed: 0.0000000004432749061074961 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533145 0.657300 │ [INFO] [stdout] │ -1.724350 -1.224202 │ [INFO] [stdout] │ -1.024010 0.618161 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023378 │ [INFO] [stdout] │ 1.770456 │ [INFO] [stdout] │ -0.525021 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 45 [INFO] [stdout] ed: 0.0000000004357017708779938 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533135 0.657290 │ [INFO] [stdout] │ -1.724601 -1.224453 │ [INFO] [stdout] │ -1.024052 0.618118 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023380 │ [INFO] [stdout] │ 1.770581 │ [INFO] [stdout] │ -0.525000 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 46 [INFO] [stdout] ed: 0.0000000004280470138199043 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533126 0.657281 │ [INFO] [stdout] │ -1.724847 -1.224699 │ [INFO] [stdout] │ -1.024094 0.618077 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023382 │ [INFO] [stdout] │ 1.770704 │ [INFO] [stdout] │ -0.524979 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 47 [INFO] [stdout] ed: 0.0000000004204827005699677 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533117 0.657272 │ [INFO] [stdout] │ -1.725089 -1.224941 │ [INFO] [stdout] │ -1.024135 0.618035 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023383 │ [INFO] [stdout] │ 1.770825 │ [INFO] [stdout] │ -0.524958 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 48 [INFO] [stdout] ed: 0.00000000041383443418271284 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533107 0.657262 │ [INFO] [stdout] │ -1.725327 -1.225179 │ [INFO] [stdout] │ -1.024176 0.617995 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023385 │ [INFO] [stdout] │ 1.770944 │ [INFO] [stdout] │ -0.524938 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 49 [INFO] [stdout] ed: 0.0000000004068567362028432 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533098 0.657253 │ [INFO] [stdout] │ -1.725562 -1.225414 │ [INFO] [stdout] │ -1.024216 0.617955 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023386 │ [INFO] [stdout] │ 1.771061 │ [INFO] [stdout] │ -0.524918 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 50 [INFO] [stdout] ed: 0.00000000040054071699567153 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533089 0.657244 │ [INFO] [stdout] │ -1.725792 -1.225644 │ [INFO] [stdout] │ -1.024255 0.617916 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023388 │ [INFO] [stdout] │ 1.771177 │ [INFO] [stdout] │ -0.524899 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 51 [INFO] [stdout] ed: 0.00000000039412488202456 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533080 0.657235 │ [INFO] [stdout] │ -1.726019 -1.225871 │ [INFO] [stdout] │ -1.024293 0.617878 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023389 │ [INFO] [stdout] │ 1.771290 │ [INFO] [stdout] │ -0.524880 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 52 [INFO] [stdout] ed: 0.00000000038767372684076076 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533072 0.657227 │ [INFO] [stdout] │ -1.726242 -1.226094 │ [INFO] [stdout] │ -1.024331 0.617840 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023391 │ [INFO] [stdout] │ 1.771402 │ [INFO] [stdout] │ -0.524861 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 53 [INFO] [stdout] ed: 0.0000000003820246586938974 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533063 0.657218 │ [INFO] [stdout] │ -1.726462 -1.226314 │ [INFO] [stdout] │ -1.024368 0.617803 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023392 │ [INFO] [stdout] │ 1.771512 │ [INFO] [stdout] │ -0.524842 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 54 [INFO] [stdout] ed: 0.0000000003763513930999847 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533054 0.657209 │ [INFO] [stdout] │ -1.726679 -1.226531 │ [INFO] [stdout] │ -1.024405 0.617766 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023393 │ [INFO] [stdout] │ 1.771620 │ [INFO] [stdout] │ -0.524824 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 55 [INFO] [stdout] ed: 0.00000000037024066703702963 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533046 0.657201 │ [INFO] [stdout] │ -1.726892 -1.226744 │ [INFO] [stdout] │ -1.024441 0.617730 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023394 │ [INFO] [stdout] │ 1.771726 │ [INFO] [stdout] │ -0.524806 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 56 [INFO] [stdout] ed: 0.00000000036488207729183083 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533037 0.657192 │ [INFO] [stdout] │ -1.727102 -1.226954 │ [INFO] [stdout] │ -1.024476 0.617694 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023396 │ [INFO] [stdout] │ 1.771831 │ [INFO] [stdout] │ -0.524788 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 57 [INFO] [stdout] ed: 0.00000000035950500365795024 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533029 0.657184 │ [INFO] [stdout] │ -1.727309 -1.227161 │ [INFO] [stdout] │ -1.024511 0.617659 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023397 │ [INFO] [stdout] │ 1.771935 │ [INFO] [stdout] │ -0.524771 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 58 [INFO] [stdout] ed: 0.00000000035440581390874863 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533021 0.657176 │ [INFO] [stdout] │ -1.727513 -1.227365 │ [INFO] [stdout] │ -1.024546 0.617625 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023398 │ [INFO] [stdout] │ 1.772037 │ [INFO] [stdout] │ -0.524754 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 59 [INFO] [stdout] ed: 0.00000000034931898248877377 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533013 0.657168 │ [INFO] [stdout] │ -1.727715 -1.227567 │ [INFO] [stdout] │ -1.024580 0.617591 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023399 │ [INFO] [stdout] │ 1.772138 │ [INFO] [stdout] │ -0.524737 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 60 [INFO] [stdout] ed: 0.000000000344024203514461 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.533004 0.657159 │ [INFO] [stdout] │ -1.727913 -1.227765 │ [INFO] [stdout] │ -1.024613 0.617558 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023400 │ [INFO] [stdout] │ 1.772237 │ [INFO] [stdout] │ -0.524720 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 61 [INFO] [stdout] ed: 0.0000000003396468750231329 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532996 0.657151 │ [INFO] [stdout] │ -1.728109 -1.227961 │ [INFO] [stdout] │ -1.024646 0.617525 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023401 │ [INFO] [stdout] │ 1.772335 │ [INFO] [stdout] │ -0.524704 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 62 [INFO] [stdout] ed: 0.000000000335133183417769 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532988 0.657143 │ [INFO] [stdout] │ -1.728302 -1.228154 │ [INFO] [stdout] │ -1.024678 0.617492 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023402 │ [INFO] [stdout] │ 1.772431 │ [INFO] [stdout] │ -0.524688 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 63 [INFO] [stdout] ed: 0.00000000033072234389392037 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532980 0.657135 │ [INFO] [stdout] │ -1.728493 -1.228345 │ [INFO] [stdout] │ -1.024710 0.617460 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023403 │ [INFO] [stdout] │ 1.772527 │ [INFO] [stdout] │ -0.524672 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 64 [INFO] [stdout] ed: 0.0000000003262197323340885 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532972 0.657127 │ [INFO] [stdout] │ -1.728681 -1.228533 │ [INFO] [stdout] │ -1.024742 0.617429 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023404 │ [INFO] [stdout] │ 1.772621 │ [INFO] [stdout] │ -0.524656 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 65 [INFO] [stdout] ed: 0.00000000032181868464952064 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532965 0.657120 │ [INFO] [stdout] │ -1.728867 -1.228719 │ [INFO] [stdout] │ -1.024773 0.617397 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023404 │ [INFO] [stdout] │ 1.772714 │ [INFO] [stdout] │ -0.524641 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 66 [INFO] [stdout] ed: 0.00000000031789795054203654 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532957 0.657112 │ [INFO] [stdout] │ -1.729050 -1.228902 │ [INFO] [stdout] │ -1.024804 0.617367 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023405 │ [INFO] [stdout] │ 1.772805 │ [INFO] [stdout] │ -0.524625 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 67 [INFO] [stdout] ed: 0.00000000031377628428466984 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532949 0.657104 │ [INFO] [stdout] │ -1.729231 -1.229083 │ [INFO] [stdout] │ -1.024834 0.617336 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023406 │ [INFO] [stdout] │ 1.772896 │ [INFO] [stdout] │ -0.524610 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 68 [INFO] [stdout] ed: 0.0000000003103884705291738 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532942 0.657097 │ [INFO] [stdout] │ -1.729410 -1.229262 │ [INFO] [stdout] │ -1.024864 0.617306 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023407 │ [INFO] [stdout] │ 1.772985 │ [INFO] [stdout] │ -0.524595 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 69 [INFO] [stdout] ed: 0.0000000003058697130345477 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532934 0.657089 │ [INFO] [stdout] │ -1.729587 -1.229439 │ [INFO] [stdout] │ -1.024894 0.617277 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023407 │ [INFO] [stdout] │ 1.773073 │ [INFO] [stdout] │ -0.524581 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 70 [INFO] [stdout] ed: 0.0000000003022823540171161 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532926 0.657081 │ [INFO] [stdout] │ -1.729761 -1.229613 │ [INFO] [stdout] │ -1.024923 0.617248 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023408 │ [INFO] [stdout] │ 1.773161 │ [INFO] [stdout] │ -0.524566 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 71 [INFO] [stdout] ed: 0.00000000029880487910793846 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532919 0.657074 │ [INFO] [stdout] │ -1.729933 -1.229785 │ [INFO] [stdout] │ -1.024952 0.617219 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023409 │ [INFO] [stdout] │ 1.773247 │ [INFO] [stdout] │ -0.524552 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 72 [INFO] [stdout] ed: 0.00000000029498143205312474 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532911 0.657066 │ [INFO] [stdout] │ -1.730104 -1.229956 │ [INFO] [stdout] │ -1.024980 0.617190 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023409 │ [INFO] [stdout] │ 1.773332 │ [INFO] [stdout] │ -0.524538 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 73 [INFO] [stdout] ed: 0.00000000029152752627473786 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532904 0.657059 │ [INFO] [stdout] │ -1.730272 -1.230124 │ [INFO] [stdout] │ -1.025008 0.617162 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023410 │ [INFO] [stdout] │ 1.773416 │ [INFO] [stdout] │ -0.524524 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 74 [INFO] [stdout] ed: 0.00000000028793161541912064 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532897 0.657052 │ [INFO] [stdout] │ -1.730439 -1.230291 │ [INFO] [stdout] │ -1.025036 0.617135 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023410 │ [INFO] [stdout] │ 1.773499 │ [INFO] [stdout] │ -0.524510 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 75 [INFO] [stdout] ed: 0.0000000002847164733370756 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532889 0.657044 │ [INFO] [stdout] │ -1.730603 -1.230455 │ [INFO] [stdout] │ -1.025064 0.617107 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023411 │ [INFO] [stdout] │ 1.773581 │ [INFO] [stdout] │ -0.524496 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 76 [INFO] [stdout] ed: 0.00000000028162211056745334 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532882 0.657037 │ [INFO] [stdout] │ -1.730766 -1.230618 │ [INFO] [stdout] │ -1.025091 0.617080 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023411 │ [INFO] [stdout] │ 1.773663 │ [INFO] [stdout] │ -0.524483 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 77 [INFO] [stdout] ed: 0.0000000002783987385593675 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532875 0.657030 │ [INFO] [stdout] │ -1.730927 -1.230779 │ [INFO] [stdout] │ -1.025118 0.617053 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023412 │ [INFO] [stdout] │ 1.773743 │ [INFO] [stdout] │ -0.524469 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 78 [INFO] [stdout] ed: 0.0000000002752278814945064 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532868 0.657023 │ [INFO] [stdout] │ -1.731086 -1.230938 │ [INFO] [stdout] │ -1.025144 0.617027 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023412 │ [INFO] [stdout] │ 1.773823 │ [INFO] [stdout] │ -0.524456 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 79 [INFO] [stdout] ed: 0.000000000272236124430879 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532861 0.657016 │ [INFO] [stdout] │ -1.731243 -1.231095 │ [INFO] [stdout] │ -1.025170 0.617000 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023413 │ [INFO] [stdout] │ 1.773901 │ [INFO] [stdout] │ -0.524443 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 80 [INFO] [stdout] ed: 0.00000000026928935225726573 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532854 0.657009 │ [INFO] [stdout] │ -1.731399 -1.231251 │ [INFO] [stdout] │ -1.025196 0.616975 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023413 │ [INFO] [stdout] │ 1.773979 │ [INFO] [stdout] │ -0.524430 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 81 [INFO] [stdout] ed: 0.0000000002661091048740633 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532847 0.657002 │ [INFO] [stdout] │ -1.731553 -1.231405 │ [INFO] [stdout] │ -1.025222 0.616949 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023413 │ [INFO] [stdout] │ 1.774056 │ [INFO] [stdout] │ -0.524417 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 82 [INFO] [stdout] ed: 0.0000000002635068313713509 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532840 0.656995 │ [INFO] [stdout] │ -1.731705 -1.231557 │ [INFO] [stdout] │ -1.025247 0.616924 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023414 │ [INFO] [stdout] │ 1.774132 │ [INFO] [stdout] │ -0.524405 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 83 [INFO] [stdout] ed: 0.0000000002613126780273038 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532833 0.656988 │ [INFO] [stdout] │ -1.731856 -1.231708 │ [INFO] [stdout] │ -1.025272 0.616899 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023414 │ [INFO] [stdout] │ 1.774208 │ [INFO] [stdout] │ -0.524392 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 84 [INFO] [stdout] ed: 0.0000000002577950307512297 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532826 0.656981 │ [INFO] [stdout] │ -1.732005 -1.231857 │ [INFO] [stdout] │ -1.025297 0.616874 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023414 │ [INFO] [stdout] │ 1.774282 │ [INFO] [stdout] │ -0.524380 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 85 [INFO] [stdout] ed: 0.0000000002552074729490268 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532819 0.656974 │ [INFO] [stdout] │ -1.732153 -1.232005 │ [INFO] [stdout] │ -1.025321 0.616849 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023415 │ [INFO] [stdout] │ 1.774356 │ [INFO] [stdout] │ -0.524368 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 86 [INFO] [stdout] ed: 0.0000000002527226128672309 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532812 0.656967 │ [INFO] [stdout] │ -1.732299 -1.232151 │ [INFO] [stdout] │ -1.025346 0.616825 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023415 │ [INFO] [stdout] │ 1.774429 │ [INFO] [stdout] │ -0.524356 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 87 [INFO] [stdout] ed: 0.00000000025054103157028564 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532805 0.656960 │ [INFO] [stdout] │ -1.732443 -1.232295 │ [INFO] [stdout] │ -1.025370 0.616801 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023415 │ [INFO] [stdout] │ 1.774501 │ [INFO] [stdout] │ -0.524344 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 88 [INFO] [stdout] ed: 0.0000000002473593341009333 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532798 0.656953 │ [INFO] [stdout] │ -1.732587 -1.232439 │ [INFO] [stdout] │ -1.025393 0.616777 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023415 │ [INFO] [stdout] │ 1.774573 │ [INFO] [stdout] │ -0.524332 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 89 [INFO] [stdout] ed: 0.00000000024531258917410075 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532792 0.656947 │ [INFO] [stdout] │ -1.732729 -1.232581 │ [INFO] [stdout] │ -1.025417 0.616754 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023415 │ [INFO] [stdout] │ 1.774644 │ [INFO] [stdout] │ -0.524320 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 90 [INFO] [stdout] ed: 0.00000000024272465542313744 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532785 0.656940 │ [INFO] [stdout] │ -1.732869 -1.232721 │ [INFO] [stdout] │ -1.025440 0.616731 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023416 │ [INFO] [stdout] │ 1.774714 │ [INFO] [stdout] │ -0.524309 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 91 [INFO] [stdout] ed: 0.00000000024078512168291274 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532778 0.656933 │ [INFO] [stdout] │ -1.733008 -1.232860 │ [INFO] [stdout] │ -1.025463 0.616707 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023416 │ [INFO] [stdout] │ 1.774784 │ [INFO] [stdout] │ -0.524297 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 92 [INFO] [stdout] ed: 0.000000000237985780124592 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532772 0.656927 │ [INFO] [stdout] │ -1.733146 -1.232998 │ [INFO] [stdout] │ -1.025486 0.616685 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023416 │ [INFO] [stdout] │ 1.774853 │ [INFO] [stdout] │ -0.524286 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 93 [INFO] [stdout] ed: 0.00000000023592236288924817 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532765 0.656920 │ [INFO] [stdout] │ -1.733283 -1.233135 │ [INFO] [stdout] │ -1.025509 0.616662 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023416 │ [INFO] [stdout] │ 1.774921 │ [INFO] [stdout] │ -0.524275 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 94 [INFO] [stdout] ed: 0.00000000023341342346941656 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532758 0.656913 │ [INFO] [stdout] │ -1.733418 -1.233270 │ [INFO] [stdout] │ -1.025531 0.616640 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023416 │ [INFO] [stdout] │ 1.774988 │ [INFO] [stdout] │ -0.524264 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 95 [INFO] [stdout] ed: 0.00000000023128158093612088 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532752 0.656907 │ [INFO] [stdout] │ -1.733552 -1.233404 │ [INFO] [stdout] │ -1.025553 0.616618 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023416 │ [INFO] [stdout] │ 1.775055 │ [INFO] [stdout] │ -0.524253 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 96 [INFO] [stdout] ed: 0.00000000022902924491446521 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532745 0.656900 │ [INFO] [stdout] │ -1.733685 -1.233537 │ [INFO] [stdout] │ -1.025575 0.616596 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023416 │ [INFO] [stdout] │ 1.775122 │ [INFO] [stdout] │ -0.524242 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 97 [INFO] [stdout] ed: 0.00000000022686525652982784 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532739 0.656894 │ [INFO] [stdout] │ -1.733816 -1.233668 │ [INFO] [stdout] │ -1.025597 0.616574 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023416 │ [INFO] [stdout] │ 1.775187 │ [INFO] [stdout] │ -0.524231 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 98 [INFO] [stdout] ed: 0.00000000022535363082530412 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532732 0.656887 │ [INFO] [stdout] │ -1.733947 -1.233799 │ [INFO] [stdout] │ -1.025618 0.616552 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023416 │ [INFO] [stdout] │ 1.775253 │ [INFO] [stdout] │ -0.524220 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 99 [INFO] [stdout] ed: 0.00000000022337628035840527 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532726 0.656881 │ [INFO] [stdout] │ -1.734076 -1.233928 │ [INFO] [stdout] │ -1.025640 0.616531 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023416 │ [INFO] [stdout] │ 1.775317 │ [INFO] [stdout] │ -0.524210 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 100 [INFO] [stdout] ed: 0.00000000022131973238209397 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532719 0.656874 │ [INFO] [stdout] │ -1.734204 -1.234056 │ [INFO] [stdout] │ -1.025661 0.616510 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023416 │ [INFO] [stdout] │ 1.775381 │ [INFO] [stdout] │ -0.524199 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 101 [INFO] [stdout] ed: 0.00000000021922757537268814 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532713 0.656868 │ [INFO] [stdout] │ -1.734331 -1.234183 │ [INFO] [stdout] │ -1.025682 0.616489 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023416 │ [INFO] [stdout] │ 1.775445 │ [INFO] [stdout] │ -0.524189 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 102 [INFO] [stdout] ed: 0.00000000021732701091392266 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532707 0.656862 │ [INFO] [stdout] │ -1.734457 -1.234309 │ [INFO] [stdout] │ -1.025702 0.616468 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023416 │ [INFO] [stdout] │ 1.775508 │ [INFO] [stdout] │ -0.524179 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 103 [INFO] [stdout] ed: 0.0000000002155647114683182 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532700 0.656855 │ [INFO] [stdout] │ -1.734581 -1.234434 │ [INFO] [stdout] │ -1.025723 0.616448 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023416 │ [INFO] [stdout] │ 1.775570 │ [INFO] [stdout] │ -0.524168 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 104 [INFO] [stdout] ed: 0.0000000002132288103381082 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532694 0.656849 │ [INFO] [stdout] │ -1.734705 -1.234557 │ [INFO] [stdout] │ -1.025743 0.616427 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023416 │ [INFO] [stdout] │ 1.775632 │ [INFO] [stdout] │ -0.524158 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 105 [INFO] [stdout] ed: 0.000000000211559133647758 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532688 0.656843 │ [INFO] [stdout] │ -1.734828 -1.234680 │ [INFO] [stdout] │ -1.025764 0.616407 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023416 │ [INFO] [stdout] │ 1.775693 │ [INFO] [stdout] │ -0.524148 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 106 [INFO] [stdout] ed: 0.00000000021010022680132118 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532681 0.656836 │ [INFO] [stdout] │ -1.734950 -1.234802 │ [INFO] [stdout] │ -1.025784 0.616387 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023416 │ [INFO] [stdout] │ 1.775754 │ [INFO] [stdout] │ -0.524138 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 107 [INFO] [stdout] ed: 0.00000000020825632460692859 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532675 0.656830 │ [INFO] [stdout] │ -1.735070 -1.234922 │ [INFO] [stdout] │ -1.025803 0.616367 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023415 │ [INFO] [stdout] │ 1.775814 │ [INFO] [stdout] │ -0.524129 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 108 [INFO] [stdout] ed: 0.0000000002060715148907271 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532669 0.656824 │ [INFO] [stdout] │ -1.735190 -1.235042 │ [INFO] [stdout] │ -1.025823 0.616348 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023415 │ [INFO] [stdout] │ 1.775874 │ [INFO] [stdout] │ -0.524119 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 109 [INFO] [stdout] ed: 0.0000000002049113572387944 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532663 0.656818 │ [INFO] [stdout] │ -1.735308 -1.235160 │ [INFO] [stdout] │ -1.025843 0.616328 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023415 │ [INFO] [stdout] │ 1.775933 │ [INFO] [stdout] │ -0.524109 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 110 [INFO] [stdout] ed: 0.00000000020309404511651405 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532657 0.656812 │ [INFO] [stdout] │ -1.735426 -1.235278 │ [INFO] [stdout] │ -1.025862 0.616309 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023415 │ [INFO] [stdout] │ 1.775992 │ [INFO] [stdout] │ -0.524099 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 111 [INFO] [stdout] ed: 0.00000000020100331646703331 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532650 0.656805 │ [INFO] [stdout] │ -1.735543 -1.235395 │ [INFO] [stdout] │ -1.025881 0.616290 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023415 │ [INFO] [stdout] │ 1.776050 │ [INFO] [stdout] │ -0.524090 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 112 [INFO] [stdout] ed: 0.00000000019947400875622428 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532644 0.656799 │ [INFO] [stdout] │ -1.735659 -1.235511 │ [INFO] [stdout] │ -1.025900 0.616271 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023415 │ [INFO] [stdout] │ 1.776108 │ [INFO] [stdout] │ -0.524081 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 113 [INFO] [stdout] ed: 0.00000000019775468544775144 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532638 0.656793 │ [INFO] [stdout] │ -1.735774 -1.235626 │ [INFO] [stdout] │ -1.025919 0.616252 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023414 │ [INFO] [stdout] │ 1.776166 │ [INFO] [stdout] │ -0.524071 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 114 [INFO] [stdout] ed: 0.0000000001964928596230599 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532632 0.656787 │ [INFO] [stdout] │ -1.735888 -1.235740 │ [INFO] [stdout] │ -1.025938 0.616233 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023414 │ [INFO] [stdout] │ 1.776223 │ [INFO] [stdout] │ -0.524062 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 115 [INFO] [stdout] ed: 0.0000000001947300890943027 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532626 0.656781 │ [INFO] [stdout] │ -1.736001 -1.235853 │ [INFO] [stdout] │ -1.025956 0.616215 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023414 │ [INFO] [stdout] │ 1.776279 │ [INFO] [stdout] │ -0.524053 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 116 [INFO] [stdout] ed: 0.0000000001931332169316272 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532620 0.656775 │ [INFO] [stdout] │ -1.736113 -1.235965 │ [INFO] [stdout] │ -1.025975 0.616196 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023414 │ [INFO] [stdout] │ 1.776335 │ [INFO] [stdout] │ -0.524044 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 117 [INFO] [stdout] ed: 0.00000000019162986094395397 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532614 0.656769 │ [INFO] [stdout] │ -1.736224 -1.236076 │ [INFO] [stdout] │ -1.025993 0.616178 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023413 │ [INFO] [stdout] │ 1.776391 │ [INFO] [stdout] │ -0.524035 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 118 [INFO] [stdout] ed: 0.00000000018999805605079169 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532608 0.656763 │ [INFO] [stdout] │ -1.736335 -1.236187 │ [INFO] [stdout] │ -1.026011 0.616160 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023413 │ [INFO] [stdout] │ 1.776446 │ [INFO] [stdout] │ -0.524026 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 119 [INFO] [stdout] ed: 0.00000000018897874061046692 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532602 0.656757 │ [INFO] [stdout] │ -1.736445 -1.236297 │ [INFO] [stdout] │ -1.026029 0.616142 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023413 │ [INFO] [stdout] │ 1.776501 │ [INFO] [stdout] │ -0.524017 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 120 [INFO] [stdout] ed: 0.0000000001875559310257944 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532596 0.656751 │ [INFO] [stdout] │ -1.736553 -1.236405 │ [INFO] [stdout] │ -1.026047 0.616124 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023412 │ [INFO] [stdout] │ 1.776555 │ [INFO] [stdout] │ -0.524008 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 121 [INFO] [stdout] ed: 0.000000000185809158781664 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532590 0.656745 │ [INFO] [stdout] │ -1.736661 -1.236514 │ [INFO] [stdout] │ -1.026064 0.616106 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023412 │ [INFO] [stdout] │ 1.776609 │ [INFO] [stdout] │ -0.523999 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 122 [INFO] [stdout] ed: 0.00000000018467987974223138 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532584 0.656739 │ [INFO] [stdout] │ -1.736769 -1.236621 │ [INFO] [stdout] │ -1.026082 0.616089 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023412 │ [INFO] [stdout] │ 1.776663 │ [INFO] [stdout] │ -0.523990 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 123 [INFO] [stdout] ed: 0.0000000001832119808624165 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532578 0.656733 │ [INFO] [stdout] │ -1.736875 -1.236727 │ [INFO] [stdout] │ -1.026099 0.616071 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023411 │ [INFO] [stdout] │ 1.776716 │ [INFO] [stdout] │ -0.523982 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 124 [INFO] [stdout] ed: 0.00000000018203510890946132 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532572 0.656727 │ [INFO] [stdout] │ -1.736981 -1.236833 │ [INFO] [stdout] │ -1.026117 0.616054 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023411 │ [INFO] [stdout] │ 1.776769 │ [INFO] [stdout] │ -0.523973 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 125 [INFO] [stdout] ed: 0.0000000001807100790879787 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532566 0.656721 │ [INFO] [stdout] │ -1.737086 -1.236938 │ [INFO] [stdout] │ -1.026134 0.616037 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023411 │ [INFO] [stdout] │ 1.776822 │ [INFO] [stdout] │ -0.523965 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 126 [INFO] [stdout] ed: 0.00000000017945929490094676 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532560 0.656715 │ [INFO] [stdout] │ -1.737190 -1.237042 │ [INFO] [stdout] │ -1.026151 0.616020 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023410 │ [INFO] [stdout] │ 1.776874 │ [INFO] [stdout] │ -0.523956 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 127 [INFO] [stdout] ed: 0.00000000017796449849432877 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532554 0.656709 │ [INFO] [stdout] │ -1.737294 -1.237146 │ [INFO] [stdout] │ -1.026168 0.616003 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023410 │ [INFO] [stdout] │ 1.776925 │ [INFO] [stdout] │ -0.523948 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 128 [INFO] [stdout] ed: 0.00000000017676864807625873 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532549 0.656704 │ [INFO] [stdout] │ -1.737396 -1.237248 │ [INFO] [stdout] │ -1.026185 0.615986 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023409 │ [INFO] [stdout] │ 1.776977 │ [INFO] [stdout] │ -0.523939 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 129 [INFO] [stdout] ed: 0.00000000017544627047050613 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532543 0.656698 │ [INFO] [stdout] │ -1.737498 -1.237350 │ [INFO] [stdout] │ -1.026201 0.615970 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023409 │ [INFO] [stdout] │ 1.777028 │ [INFO] [stdout] │ -0.523931 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 130 [INFO] [stdout] ed: 0.00000000017433875600903133 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532537 0.656692 │ [INFO] [stdout] │ -1.737600 -1.237452 │ [INFO] [stdout] │ -1.026218 0.615953 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023409 │ [INFO] [stdout] │ 1.777078 │ [INFO] [stdout] │ -0.523923 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 131 [INFO] [stdout] ed: 0.0000000001734933324113619 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532531 0.656686 │ [INFO] [stdout] │ -1.737700 -1.237552 │ [INFO] [stdout] │ -1.026234 0.615937 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023408 │ [INFO] [stdout] │ 1.777129 │ [INFO] [stdout] │ -0.523915 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 132 [INFO] [stdout] ed: 0.00000000017180209321425154 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532525 0.656680 │ [INFO] [stdout] │ -1.737800 -1.237652 │ [INFO] [stdout] │ -1.026250 0.615920 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023408 │ [INFO] [stdout] │ 1.777179 │ [INFO] [stdout] │ -0.523907 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 133 [INFO] [stdout] ed: 0.00000000017059538259423807 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532520 0.656675 │ [INFO] [stdout] │ -1.737899 -1.237751 │ [INFO] [stdout] │ -1.026267 0.615904 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023407 │ [INFO] [stdout] │ 1.777228 │ [INFO] [stdout] │ -0.523899 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 134 [INFO] [stdout] ed: 0.0000000001693491110717181 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532514 0.656669 │ [INFO] [stdout] │ -1.737998 -1.237850 │ [INFO] [stdout] │ -1.026283 0.615888 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023407 │ [INFO] [stdout] │ 1.777277 │ [INFO] [stdout] │ -0.523891 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 135 [INFO] [stdout] ed: 0.00000000016829616201819608 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532508 0.656663 │ [INFO] [stdout] │ -1.738096 -1.237948 │ [INFO] [stdout] │ -1.026299 0.615872 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023406 │ [INFO] [stdout] │ 1.777326 │ [INFO] [stdout] │ -0.523883 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 136 [INFO] [stdout] ed: 0.00000000016722088505361462 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532502 0.656657 │ [INFO] [stdout] │ -1.738193 -1.238045 │ [INFO] [stdout] │ -1.026315 0.615856 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023406 │ [INFO] [stdout] │ 1.777375 │ [INFO] [stdout] │ -0.523875 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 137 [INFO] [stdout] ed: 0.00000000016621120646997825 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532497 0.656652 │ [INFO] [stdout] │ -1.738290 -1.238142 │ [INFO] [stdout] │ -1.026330 0.615840 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023405 │ [INFO] [stdout] │ 1.777423 │ [INFO] [stdout] │ -0.523867 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 138 [INFO] [stdout] ed: 0.00000000016523656852850081 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532491 0.656646 │ [INFO] [stdout] │ -1.738386 -1.238238 │ [INFO] [stdout] │ -1.026346 0.615825 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023405 │ [INFO] [stdout] │ 1.777471 │ [INFO] [stdout] │ -0.523860 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 139 [INFO] [stdout] ed: 0.00000000016408982282156213 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532485 0.656640 │ [INFO] [stdout] │ -1.738481 -1.238333 │ [INFO] [stdout] │ -1.026361 0.615809 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023404 │ [INFO] [stdout] │ 1.777519 │ [INFO] [stdout] │ -0.523852 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 140 [INFO] [stdout] ed: 0.00000000016292393857965137 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532480 0.656635 │ [INFO] [stdout] │ -1.738576 -1.238428 │ [INFO] [stdout] │ -1.026377 0.615794 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023404 │ [INFO] [stdout] │ 1.777566 │ [INFO] [stdout] │ -0.523844 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 141 [INFO] [stdout] ed: 0.0000000001618383551032295 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532474 0.656629 │ [INFO] [stdout] │ -1.738670 -1.238522 │ [INFO] [stdout] │ -1.026392 0.615779 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023403 │ [INFO] [stdout] │ 1.777613 │ [INFO] [stdout] │ -0.523837 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 142 [INFO] [stdout] ed: 0.00000000016060619934524405 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532468 0.656623 │ [INFO] [stdout] │ -1.738763 -1.238615 │ [INFO] [stdout] │ -1.026407 0.615763 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023403 │ [INFO] [stdout] │ 1.777660 │ [INFO] [stdout] │ -0.523829 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 143 [INFO] [stdout] ed: 0.00000000015972095148639192 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532463 0.656618 │ [INFO] [stdout] │ -1.738856 -1.238708 │ [INFO] [stdout] │ -1.026422 0.615748 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023402 │ [INFO] [stdout] │ 1.777706 │ [INFO] [stdout] │ -0.523822 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 144 [INFO] [stdout] ed: 0.00000000015905395364201118 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532457 0.656612 │ [INFO] [stdout] │ -1.738948 -1.238800 │ [INFO] [stdout] │ -1.026438 0.615733 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023402 │ [INFO] [stdout] │ 1.777752 │ [INFO] [stdout] │ -0.523814 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 145 [INFO] [stdout] ed: 0.00000000015791092654413102 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532451 0.656606 │ [INFO] [stdout] │ -1.739040 -1.238892 │ [INFO] [stdout] │ -1.026452 0.615718 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023401 │ [INFO] [stdout] │ 1.777798 │ [INFO] [stdout] │ -0.523807 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 146 [INFO] [stdout] ed: 0.00000000015660405355599988 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532446 0.656601 │ [INFO] [stdout] │ -1.739131 -1.238983 │ [INFO] [stdout] │ -1.026467 0.615704 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023400 │ [INFO] [stdout] │ 1.777844 │ [INFO] [stdout] │ -0.523799 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 147 [INFO] [stdout] ed: 0.00000000015586165348151133 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532440 0.656595 │ [INFO] [stdout] │ -1.739222 -1.239074 │ [INFO] [stdout] │ -1.026482 0.615689 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023400 │ [INFO] [stdout] │ 1.777889 │ [INFO] [stdout] │ -0.523792 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 148 [INFO] [stdout] ed: 0.00000000015476039404358678 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532435 0.656590 │ [INFO] [stdout] │ -1.739312 -1.239164 │ [INFO] [stdout] │ -1.026497 0.615674 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023399 │ [INFO] [stdout] │ 1.777934 │ [INFO] [stdout] │ -0.523785 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 149 [INFO] [stdout] ed: 0.00000000015324213659786989 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532429 0.656584 │ [INFO] [stdout] │ -1.739401 -1.239254 │ [INFO] [stdout] │ -1.026511 0.615660 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023399 │ [INFO] [stdout] │ 1.777979 │ [INFO] [stdout] │ -0.523778 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 150 [INFO] [stdout] ed: 0.00000000015326140111356918 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532424 0.656579 │ [INFO] [stdout] │ -1.739490 -1.239342 │ [INFO] [stdout] │ -1.026526 0.615645 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023398 │ [INFO] [stdout] │ 1.778023 │ [INFO] [stdout] │ -0.523771 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 151 [INFO] [stdout] ed: 0.00000000015176005723151723 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532418 0.656573 │ [INFO] [stdout] │ -1.739579 -1.239431 │ [INFO] [stdout] │ -1.026540 0.615631 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023397 │ [INFO] [stdout] │ 1.778067 │ [INFO] [stdout] │ -0.523764 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 152 [INFO] [stdout] ed: 0.00000000015086765269453554 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532412 0.656567 │ [INFO] [stdout] │ -1.739667 -1.239519 │ [INFO] [stdout] │ -1.026554 0.615617 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023397 │ [INFO] [stdout] │ 1.778111 │ [INFO] [stdout] │ -0.523756 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 153 [INFO] [stdout] ed: 0.00000000014976927658636097 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532407 0.656562 │ [INFO] [stdout] │ -1.739754 -1.239606 │ [INFO] [stdout] │ -1.026568 0.615602 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023396 │ [INFO] [stdout] │ 1.778155 │ [INFO] [stdout] │ -0.523749 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 154 [INFO] [stdout] ed: 0.0000000001490687087466223 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532401 0.656556 │ [INFO] [stdout] │ -1.739841 -1.239693 │ [INFO] [stdout] │ -1.026582 0.615588 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023395 │ [INFO] [stdout] │ 1.778198 │ [INFO] [stdout] │ -0.523742 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 155 [INFO] [stdout] ed: 0.00000000014839826130654814 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532396 0.656551 │ [INFO] [stdout] │ -1.739927 -1.239779 │ [INFO] [stdout] │ -1.026596 0.615574 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023395 │ [INFO] [stdout] │ 1.778241 │ [INFO] [stdout] │ -0.523736 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 156 [INFO] [stdout] ed: 0.0000000001471925412919705 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532390 0.656545 │ [INFO] [stdout] │ -1.740013 -1.239865 │ [INFO] [stdout] │ -1.026610 0.615560 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023394 │ [INFO] [stdout] │ 1.778284 │ [INFO] [stdout] │ -0.523729 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 157 [INFO] [stdout] ed: 0.00000000014644632003832366 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532385 0.656540 │ [INFO] [stdout] │ -1.740098 -1.239950 │ [INFO] [stdout] │ -1.026624 0.615547 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023393 │ [INFO] [stdout] │ 1.778327 │ [INFO] [stdout] │ -0.523722 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 158 [INFO] [stdout] ed: 0.00000000014552778727052932 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532379 0.656534 │ [INFO] [stdout] │ -1.740183 -1.240035 │ [INFO] [stdout] │ -1.026638 0.615533 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023393 │ [INFO] [stdout] │ 1.778369 │ [INFO] [stdout] │ -0.523715 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 159 [INFO] [stdout] ed: 0.00000000014521856053252033 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532374 0.656529 │ [INFO] [stdout] │ -1.740267 -1.240119 │ [INFO] [stdout] │ -1.026652 0.615519 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023392 │ [INFO] [stdout] │ 1.778411 │ [INFO] [stdout] │ -0.523708 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 160 [INFO] [stdout] ed: 0.00000000014352571684084 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532369 0.656524 │ [INFO] [stdout] │ -1.740351 -1.240203 │ [INFO] [stdout] │ -1.026665 0.615506 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023391 │ [INFO] [stdout] │ 1.778453 │ [INFO] [stdout] │ -0.523702 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 161 [INFO] [stdout] ed: 0.0000000001431727108283333 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532363 0.656518 │ [INFO] [stdout] │ -1.740435 -1.240287 │ [INFO] [stdout] │ -1.026679 0.615492 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023391 │ [INFO] [stdout] │ 1.778495 │ [INFO] [stdout] │ -0.523695 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 162 [INFO] [stdout] ed: 0.00000000014218923175540396 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532358 0.656513 │ [INFO] [stdout] │ -1.740517 -1.240370 │ [INFO] [stdout] │ -1.026692 0.615479 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023390 │ [INFO] [stdout] │ 1.778536 │ [INFO] [stdout] │ -0.523688 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 163 [INFO] [stdout] ed: 0.0000000001415104026716306 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532352 0.656507 │ [INFO] [stdout] │ -1.740600 -1.240452 │ [INFO] [stdout] │ -1.026705 0.615465 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023389 │ [INFO] [stdout] │ 1.778578 │ [INFO] [stdout] │ -0.523682 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 164 [INFO] [stdout] ed: 0.00000000014056761457001545 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532347 0.656502 │ [INFO] [stdout] │ -1.740682 -1.240534 │ [INFO] [stdout] │ -1.026719 0.615452 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023389 │ [INFO] [stdout] │ 1.778619 │ [INFO] [stdout] │ -0.523675 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 165 [INFO] [stdout] ed: 0.00000000013981703425514132 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532342 0.656497 │ [INFO] [stdout] │ -1.740763 -1.240615 │ [INFO] [stdout] │ -1.026732 0.615439 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023388 │ [INFO] [stdout] │ 1.778659 │ [INFO] [stdout] │ -0.523669 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 166 [INFO] [stdout] ed: 0.00000000013872092004243866 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532336 0.656491 │ [INFO] [stdout] │ -1.740844 -1.240696 │ [INFO] [stdout] │ -1.026745 0.615426 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023387 │ [INFO] [stdout] │ 1.778700 │ [INFO] [stdout] │ -0.523662 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 167 [INFO] [stdout] ed: 0.00000000013819996789197156 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532331 0.656486 │ [INFO] [stdout] │ -1.740925 -1.240777 │ [INFO] [stdout] │ -1.026758 0.615413 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023386 │ [INFO] [stdout] │ 1.778740 │ [INFO] [stdout] │ -0.523656 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 168 [INFO] [stdout] ed: 0.00000000013760419863328705 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532325 0.656480 │ [INFO] [stdout] │ -1.741005 -1.240857 │ [INFO] [stdout] │ -1.026771 0.615400 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023386 │ [INFO] [stdout] │ 1.778780 │ [INFO] [stdout] │ -0.523649 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 169 [INFO] [stdout] ed: 0.0000000001362525694787307 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532320 0.656475 │ [INFO] [stdout] │ -1.741085 -1.240937 │ [INFO] [stdout] │ -1.026784 0.615387 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023385 │ [INFO] [stdout] │ 1.778820 │ [INFO] [stdout] │ -0.523643 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 170 [INFO] [stdout] ed: 0.00000000013581889844480161 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532315 0.656470 │ [INFO] [stdout] │ -1.741164 -1.241016 │ [INFO] [stdout] │ -1.026797 0.615374 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023384 │ [INFO] [stdout] │ 1.778860 │ [INFO] [stdout] │ -0.523637 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 171 [INFO] [stdout] ed: 0.0000000001351284570962055 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532309 0.656464 │ [INFO] [stdout] │ -1.741243 -1.241095 │ [INFO] [stdout] │ -1.026809 0.615361 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023383 │ [INFO] [stdout] │ 1.778899 │ [INFO] [stdout] │ -0.523630 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 172 [INFO] [stdout] ed: 0.000000000134452431069573 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532304 0.656459 │ [INFO] [stdout] │ -1.741321 -1.241174 │ [INFO] [stdout] │ -1.026822 0.615349 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023382 │ [INFO] [stdout] │ 1.778938 │ [INFO] [stdout] │ -0.523624 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 173 [INFO] [stdout] ed: 0.00000000013360092639872583 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532299 0.656454 │ [INFO] [stdout] │ -1.741399 -1.241252 │ [INFO] [stdout] │ -1.026835 0.615336 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023382 │ [INFO] [stdout] │ 1.778977 │ [INFO] [stdout] │ -0.523618 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 174 [INFO] [stdout] ed: 0.00000000013294656125907924 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532293 0.656448 │ [INFO] [stdout] │ -1.741477 -1.241329 │ [INFO] [stdout] │ -1.026847 0.615324 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023381 │ [INFO] [stdout] │ 1.779016 │ [INFO] [stdout] │ -0.523612 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 175 [INFO] [stdout] ed: 0.00000000013223776983504118 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532288 0.656443 │ [INFO] [stdout] │ -1.741554 -1.241406 │ [INFO] [stdout] │ -1.026860 0.615311 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023380 │ [INFO] [stdout] │ 1.779054 │ [INFO] [stdout] │ -0.523605 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 176 [INFO] [stdout] ed: 0.00000000013173117417400598 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532283 0.656438 │ [INFO] [stdout] │ -1.741631 -1.241483 │ [INFO] [stdout] │ -1.026872 0.615299 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023379 │ [INFO] [stdout] │ 1.779093 │ [INFO] [stdout] │ -0.523599 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 177 [INFO] [stdout] ed: 0.0000000001306036502579085 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532277 0.656432 │ [INFO] [stdout] │ -1.741707 -1.241560 │ [INFO] [stdout] │ -1.026884 0.615286 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023378 │ [INFO] [stdout] │ 1.779131 │ [INFO] [stdout] │ -0.523593 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 178 [INFO] [stdout] ed: 0.00000000013028036451095214 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532272 0.656427 │ [INFO] [stdout] │ -1.741783 -1.241636 │ [INFO] [stdout] │ -1.026897 0.615274 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023378 │ [INFO] [stdout] │ 1.779169 │ [INFO] [stdout] │ -0.523587 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 179 [INFO] [stdout] ed: 0.0000000001293244208281964 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532267 0.656422 │ [INFO] [stdout] │ -1.741859 -1.241711 │ [INFO] [stdout] │ -1.026909 0.615262 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023377 │ [INFO] [stdout] │ 1.779207 │ [INFO] [stdout] │ -0.523581 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 180 [INFO] [stdout] ed: 0.00000000012869771400560908 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532262 0.656417 │ [INFO] [stdout] │ -1.741934 -1.241786 │ [INFO] [stdout] │ -1.026921 0.615250 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023376 │ [INFO] [stdout] │ 1.779244 │ [INFO] [stdout] │ -0.523575 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 181 [INFO] [stdout] ed: 0.00000000012844406390502678 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532256 0.656411 │ [INFO] [stdout] │ -1.742009 -1.241861 │ [INFO] [stdout] │ -1.026933 0.615238 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023375 │ [INFO] [stdout] │ 1.779282 │ [INFO] [stdout] │ -0.523569 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 182 [INFO] [stdout] ed: 0.00000000012775313572042645 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532251 0.656406 │ [INFO] [stdout] │ -1.742084 -1.241936 │ [INFO] [stdout] │ -1.026945 0.615226 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023374 │ [INFO] [stdout] │ 1.779319 │ [INFO] [stdout] │ -0.523563 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 183 [INFO] [stdout] ed: 0.00000000012697428159413257 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532246 0.656401 │ [INFO] [stdout] │ -1.742158 -1.242010 │ [INFO] [stdout] │ -1.026957 0.615214 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023373 │ [INFO] [stdout] │ 1.779356 │ [INFO] [stdout] │ -0.523557 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 184 [INFO] [stdout] ed: 0.00000000012618584056457257 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532241 0.656396 │ [INFO] [stdout] │ -1.742231 -1.242083 │ [INFO] [stdout] │ -1.026969 0.615202 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023373 │ [INFO] [stdout] │ 1.779393 │ [INFO] [stdout] │ -0.523552 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 185 [INFO] [stdout] ed: 0.0000000001252406269283514 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532235 0.656390 │ [INFO] [stdout] │ -1.742305 -1.242157 │ [INFO] [stdout] │ -1.026981 0.615190 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023372 │ [INFO] [stdout] │ 1.779429 │ [INFO] [stdout] │ -0.523546 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 186 [INFO] [stdout] ed: 0.00000000012512791055489946 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532230 0.656385 │ [INFO] [stdout] │ -1.742378 -1.242230 │ [INFO] [stdout] │ -1.026992 0.615178 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023371 │ [INFO] [stdout] │ 1.779466 │ [INFO] [stdout] │ -0.523540 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 187 [INFO] [stdout] ed: 0.00000000012427093791574983 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532225 0.656380 │ [INFO] [stdout] │ -1.742450 -1.242302 │ [INFO] [stdout] │ -1.027004 0.615167 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023370 │ [INFO] [stdout] │ 1.779502 │ [INFO] [stdout] │ -0.523534 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 188 [INFO] [stdout] ed: 0.0000000001237469489137792 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532220 0.656375 │ [INFO] [stdout] │ -1.742522 -1.242375 │ [INFO] [stdout] │ -1.027016 0.615155 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023369 │ [INFO] [stdout] │ 1.779538 │ [INFO] [stdout] │ -0.523528 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 189 [INFO] [stdout] ed: 0.0000000001232715434069537 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532214 0.656369 │ [INFO] [stdout] │ -1.742594 -1.242446 │ [INFO] [stdout] │ -1.027027 0.615143 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023368 │ [INFO] [stdout] │ 1.779574 │ [INFO] [stdout] │ -0.523523 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 190 [INFO] [stdout] ed: 0.00000000012249365153943912 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532209 0.656364 │ [INFO] [stdout] │ -1.742666 -1.242518 │ [INFO] [stdout] │ -1.027039 0.615132 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023367 │ [INFO] [stdout] │ 1.779610 │ [INFO] [stdout] │ -0.523517 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 191 [INFO] [stdout] ed: 0.00000000012226803849830192 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532204 0.656359 │ [INFO] [stdout] │ -1.742737 -1.242589 │ [INFO] [stdout] │ -1.027050 0.615120 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023367 │ [INFO] [stdout] │ 1.779645 │ [INFO] [stdout] │ -0.523511 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 192 [INFO] [stdout] ed: 0.0000000001207785322091744 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532199 0.656354 │ [INFO] [stdout] │ -1.742808 -1.242660 │ [INFO] [stdout] │ -1.027062 0.615109 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023366 │ [INFO] [stdout] │ 1.779681 │ [INFO] [stdout] │ -0.523506 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 193 [INFO] [stdout] ed: 0.00000000012010907732342802 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532194 0.656349 │ [INFO] [stdout] │ -1.742878 -1.242730 │ [INFO] [stdout] │ -1.027073 0.615098 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023365 │ [INFO] [stdout] │ 1.779716 │ [INFO] [stdout] │ -0.523500 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 194 [INFO] [stdout] ed: 0.0000000001201617298935714 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532188 0.656343 │ [INFO] [stdout] │ -1.742949 -1.242801 │ [INFO] [stdout] │ -1.027084 0.615086 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023364 │ [INFO] [stdout] │ 1.779751 │ [INFO] [stdout] │ -0.523495 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 195 [INFO] [stdout] ed: 0.00000000011942664343510644 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532183 0.656338 │ [INFO] [stdout] │ -1.743018 -1.242870 │ [INFO] [stdout] │ -1.027096 0.615075 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023363 │ [INFO] [stdout] │ 1.779786 │ [INFO] [stdout] │ -0.523489 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 196 [INFO] [stdout] ed: 0.00000000011894750715923734 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532178 0.656333 │ [INFO] [stdout] │ -1.743088 -1.242940 │ [INFO] [stdout] │ -1.027107 0.615064 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023362 │ [INFO] [stdout] │ 1.779821 │ [INFO] [stdout] │ -0.523484 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 197 [INFO] [stdout] ed: 0.00000000011854343046536394 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532173 0.656328 │ [INFO] [stdout] │ -1.743157 -1.243009 │ [INFO] [stdout] │ -1.027118 0.615053 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023361 │ [INFO] [stdout] │ 1.779855 │ [INFO] [stdout] │ -0.523478 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 198 [INFO] [stdout] ed: 0.00000000011737892852104705 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532168 0.656323 │ [INFO] [stdout] │ -1.743226 -1.243078 │ [INFO] [stdout] │ -1.027129 0.615042 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023360 │ [INFO] [stdout] │ 1.779890 │ [INFO] [stdout] │ -0.523473 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 199 [INFO] [stdout] ed: 0.0000000001170965275434183 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532163 0.656318 │ [INFO] [stdout] │ -1.743295 -1.243147 │ [INFO] [stdout] │ -1.027140 0.615031 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023359 │ [INFO] [stdout] │ 1.779924 │ [INFO] [stdout] │ -0.523467 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 200 [INFO] [stdout] ed: 0.00000000011658094186997425 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532158 0.656312 │ [INFO] [stdout] │ -1.743363 -1.243215 │ [INFO] [stdout] │ -1.027151 0.615020 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023358 │ [INFO] [stdout] │ 1.779958 │ [INFO] [stdout] │ -0.523462 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 201 [INFO] [stdout] ed: 0.0000000001165212133028155 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532152 0.656307 │ [INFO] [stdout] │ -1.743431 -1.243283 │ [INFO] [stdout] │ -1.027162 0.615009 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023357 │ [INFO] [stdout] │ 1.779992 │ [INFO] [stdout] │ -0.523456 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 202 [INFO] [stdout] ed: 0.00000000011600295167147874 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532147 0.656302 │ [INFO] [stdout] │ -1.743498 -1.243350 │ [INFO] [stdout] │ -1.027173 0.614998 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023356 │ [INFO] [stdout] │ 1.780026 │ [INFO] [stdout] │ -0.523451 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 203 [INFO] [stdout] ed: 0.00000000011513980447773927 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532142 0.656297 │ [INFO] [stdout] │ -1.743565 -1.243418 │ [INFO] [stdout] │ -1.027184 0.614987 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023355 │ [INFO] [stdout] │ 1.780059 │ [INFO] [stdout] │ -0.523446 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 204 [INFO] [stdout] ed: 0.00000000011433305230524808 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532137 0.656292 │ [INFO] [stdout] │ -1.743632 -1.243484 │ [INFO] [stdout] │ -1.027194 0.614976 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023354 │ [INFO] [stdout] │ 1.780093 │ [INFO] [stdout] │ -0.523440 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 205 [INFO] [stdout] ed: 0.00000000011383893366626458 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532132 0.656287 │ [INFO] [stdout] │ -1.743699 -1.243551 │ [INFO] [stdout] │ -1.027205 0.614966 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023353 │ [INFO] [stdout] │ 1.780126 │ [INFO] [stdout] │ -0.523435 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 206 [INFO] [stdout] ed: 0.00000000011318752609132532 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532127 0.656282 │ [INFO] [stdout] │ -1.743765 -1.243617 │ [INFO] [stdout] │ -1.027216 0.614955 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023352 │ [INFO] [stdout] │ 1.780159 │ [INFO] [stdout] │ -0.523430 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 207 [INFO] [stdout] ed: 0.00000000011260361778457272 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532122 0.656277 │ [INFO] [stdout] │ -1.743832 -1.243684 │ [INFO] [stdout] │ -1.027226 0.614944 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023351 │ [INFO] [stdout] │ 1.780192 │ [INFO] [stdout] │ -0.523425 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 208 [INFO] [stdout] ed: 0.00000000011247031870202002 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532117 0.656272 │ [INFO] [stdout] │ -1.743897 -1.243749 │ [INFO] [stdout] │ -1.027237 0.614934 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023350 │ [INFO] [stdout] │ 1.780225 │ [INFO] [stdout] │ -0.523419 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 209 [INFO] [stdout] ed: 0.00000000011212167817591443 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532111 0.656266 │ [INFO] [stdout] │ -1.743963 -1.243815 │ [INFO] [stdout] │ -1.027247 0.614923 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023350 │ [INFO] [stdout] │ 1.780258 │ [INFO] [stdout] │ -0.523414 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 210 [INFO] [stdout] ed: 0.00000000011120156718680642 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532106 0.656261 │ [INFO] [stdout] │ -1.744028 -1.243880 │ [INFO] [stdout] │ -1.027258 0.614913 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023349 │ [INFO] [stdout] │ 1.780290 │ [INFO] [stdout] │ -0.523409 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 211 [INFO] [stdout] ed: 0.00000000011036078653453424 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532101 0.656256 │ [INFO] [stdout] │ -1.744093 -1.243945 │ [INFO] [stdout] │ -1.027268 0.614903 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023348 │ [INFO] [stdout] │ 1.780323 │ [INFO] [stdout] │ -0.523404 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 212 [INFO] [stdout] ed: 0.00000000011053667194804408 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532096 0.656251 │ [INFO] [stdout] │ -1.744157 -1.244009 │ [INFO] [stdout] │ -1.027279 0.614892 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023347 │ [INFO] [stdout] │ 1.780355 │ [INFO] [stdout] │ -0.523399 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 213 [INFO] [stdout] ed: 0.00000000011011574974577214 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532091 0.656246 │ [INFO] [stdout] │ -1.744222 -1.244074 │ [INFO] [stdout] │ -1.027289 0.614882 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023346 │ [INFO] [stdout] │ 1.780387 │ [INFO] [stdout] │ -0.523394 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 214 [INFO] [stdout] ed: 0.00000000010954455418321105 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532086 0.656241 │ [INFO] [stdout] │ -1.744286 -1.244138 │ [INFO] [stdout] │ -1.027299 0.614872 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023345 │ [INFO] [stdout] │ 1.780419 │ [INFO] [stdout] │ -0.523389 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 215 [INFO] [stdout] ed: 0.00000000010915005746386565 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532081 0.656236 │ [INFO] [stdout] │ -1.744350 -1.244202 │ [INFO] [stdout] │ -1.027309 0.614861 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023343 │ [INFO] [stdout] │ 1.780451 │ [INFO] [stdout] │ -0.523384 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 216 [INFO] [stdout] ed: 0.00000000010837798857738919 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532076 0.656231 │ [INFO] [stdout] │ -1.744413 -1.244265 │ [INFO] [stdout] │ -1.027320 0.614851 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023342 │ [INFO] [stdout] │ 1.780483 │ [INFO] [stdout] │ -0.523379 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 217 [INFO] [stdout] ed: 0.00000000010752874604569893 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532071 0.656226 │ [INFO] [stdout] │ -1.744476 -1.244328 │ [INFO] [stdout] │ -1.027330 0.614841 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023341 │ [INFO] [stdout] │ 1.780514 │ [INFO] [stdout] │ -0.523374 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 218 [INFO] [stdout] ed: 0.00000000010719968705652868 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532066 0.656221 │ [INFO] [stdout] │ -1.744539 -1.244391 │ [INFO] [stdout] │ -1.027340 0.614831 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023340 │ [INFO] [stdout] │ 1.780546 │ [INFO] [stdout] │ -0.523369 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 219 [INFO] [stdout] ed: 0.00000000010704180774405788 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532061 0.656216 │ [INFO] [stdout] │ -1.744602 -1.244454 │ [INFO] [stdout] │ -1.027350 0.614821 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023339 │ [INFO] [stdout] │ 1.780577 │ [INFO] [stdout] │ -0.523364 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 220 [INFO] [stdout] ed: 0.00000000010659920535362739 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532056 0.656211 │ [INFO] [stdout] │ -1.744664 -1.244516 │ [INFO] [stdout] │ -1.027360 0.614811 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023338 │ [INFO] [stdout] │ 1.780608 │ [INFO] [stdout] │ -0.523359 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 221 [INFO] [stdout] ed: 0.0000000001059203517375229 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532051 0.656206 │ [INFO] [stdout] │ -1.744726 -1.244578 │ [INFO] [stdout] │ -1.027370 0.614801 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023337 │ [INFO] [stdout] │ 1.780639 │ [INFO] [stdout] │ -0.523354 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 222 [INFO] [stdout] ed: 0.00000000010567312111820855 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532046 0.656201 │ [INFO] [stdout] │ -1.744788 -1.244640 │ [INFO] [stdout] │ -1.027380 0.614791 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023336 │ [INFO] [stdout] │ 1.780670 │ [INFO] [stdout] │ -0.523349 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 223 [INFO] [stdout] ed: 0.00000000010517358718479877 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532041 0.656196 │ [INFO] [stdout] │ -1.744850 -1.244702 │ [INFO] [stdout] │ -1.027390 0.614781 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023335 │ [INFO] [stdout] │ 1.780701 │ [INFO] [stdout] │ -0.523344 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 224 [INFO] [stdout] ed: 0.00000000010495544316450632 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532036 0.656191 │ [INFO] [stdout] │ -1.744911 -1.244763 │ [INFO] [stdout] │ -1.027399 0.614771 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023334 │ [INFO] [stdout] │ 1.780732 │ [INFO] [stdout] │ -0.523339 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 225 [INFO] [stdout] ed: 0.00000000010383367468012697 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532031 0.656186 │ [INFO] [stdout] │ -1.744972 -1.244824 │ [INFO] [stdout] │ -1.027409 0.614762 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023333 │ [INFO] [stdout] │ 1.780762 │ [INFO] [stdout] │ -0.523335 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 226 [INFO] [stdout] ed: 0.00000000010385494264347576 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532026 0.656181 │ [INFO] [stdout] │ -1.745033 -1.244885 │ [INFO] [stdout] │ -1.027419 0.614752 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023332 │ [INFO] [stdout] │ 1.780792 │ [INFO] [stdout] │ -0.523330 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 227 [INFO] [stdout] ed: 0.00000000010375700808175022 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532021 0.656176 │ [INFO] [stdout] │ -1.745094 -1.244946 │ [INFO] [stdout] │ -1.027429 0.614742 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023331 │ [INFO] [stdout] │ 1.780823 │ [INFO] [stdout] │ -0.523325 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 228 [INFO] [stdout] ed: 0.00000000010285266234198286 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532016 0.656171 │ [INFO] [stdout] │ -1.745154 -1.245006 │ [INFO] [stdout] │ -1.027438 0.614732 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023330 │ [INFO] [stdout] │ 1.780853 │ [INFO] [stdout] │ -0.523320 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 229 [INFO] [stdout] ed: 0.0000000001027773800908545 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532011 0.656166 │ [INFO] [stdout] │ -1.745214 -1.245066 │ [INFO] [stdout] │ -1.027448 0.614723 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023329 │ [INFO] [stdout] │ 1.780883 │ [INFO] [stdout] │ -0.523316 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 230 [INFO] [stdout] ed: 0.00000000010225279508830012 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532006 0.656161 │ [INFO] [stdout] │ -1.745274 -1.245126 │ [INFO] [stdout] │ -1.027457 0.614713 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023328 │ [INFO] [stdout] │ 1.780913 │ [INFO] [stdout] │ -0.523311 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 231 [INFO] [stdout] ed: 0.00000000010182563287528534 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.532001 0.656156 │ [INFO] [stdout] │ -1.745334 -1.245186 │ [INFO] [stdout] │ -1.027467 0.614704 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023327 │ [INFO] [stdout] │ 1.780943 │ [INFO] [stdout] │ -0.523306 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 232 [INFO] [stdout] ed: 0.00000000010116257129617815 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.531996 0.656151 │ [INFO] [stdout] │ -1.745393 -1.245245 │ [INFO] [stdout] │ -1.027476 0.614694 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023326 │ [INFO] [stdout] │ 1.780972 │ [INFO] [stdout] │ -0.523302 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 233 [INFO] [stdout] ed: 0.00000000010158347708582855 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.531991 0.656146 │ [INFO] [stdout] │ -1.745452 -1.245304 │ [INFO] [stdout] │ -1.027486 0.614685 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023324 │ [INFO] [stdout] │ 1.781002 │ [INFO] [stdout] │ -0.523297 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 234 [INFO] [stdout] ed: 0.00000000010047699616804982 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.531986 0.656141 │ [INFO] [stdout] │ -1.745511 -1.245363 │ [INFO] [stdout] │ -1.027495 0.614675 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023323 │ [INFO] [stdout] │ 1.781031 │ [INFO] [stdout] │ -0.523292 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 235 [INFO] [stdout] ed: 0.00000000010011104970598638 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.531981 0.656136 │ [INFO] [stdout] │ -1.745570 -1.245422 │ [INFO] [stdout] │ -1.027505 0.614666 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023322 │ [INFO] [stdout] │ 1.781060 │ [INFO] [stdout] │ -0.523288 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 236 [INFO] [stdout] ed: 0.00000000009972431418789142 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.531976 0.656131 │ [INFO] [stdout] │ -1.745628 -1.245480 │ [INFO] [stdout] │ -1.027514 0.614657 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023321 │ [INFO] [stdout] │ 1.781090 │ [INFO] [stdout] │ -0.523283 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 237 [INFO] [stdout] ed: 0.00000000009877659196098453 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.531971 0.656126 │ [INFO] [stdout] │ -1.745686 -1.245539 │ [INFO] [stdout] │ -1.027523 0.614647 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023320 │ [INFO] [stdout] │ 1.781119 │ [INFO] [stdout] │ -0.523279 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 238 [INFO] [stdout] ed: 0.00000000009901805057577598 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.531966 0.656121 │ [INFO] [stdout] │ -1.745744 -1.245596 │ [INFO] [stdout] │ -1.027533 0.614638 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023319 │ [INFO] [stdout] │ 1.781148 │ [INFO] [stdout] │ -0.523274 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 239 [INFO] [stdout] ed: 0.0000000000980390786597558 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.531961 0.656116 │ [INFO] [stdout] │ -1.745802 -1.245654 │ [INFO] [stdout] │ -1.027542 0.614629 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023318 │ [INFO] [stdout] │ 1.781177 │ [INFO] [stdout] │ -0.523269 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 240 [INFO] [stdout] ed: 0.00000000009808984841642161 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.531956 0.656111 │ [INFO] [stdout] │ -1.745860 -1.245712 │ [INFO] [stdout] │ -1.027551 0.614620 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023317 │ [INFO] [stdout] │ 1.781205 │ [INFO] [stdout] │ -0.523265 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 241 [INFO] [stdout] ed: 0.00000000009782354093840082 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.531951 0.656106 │ [INFO] [stdout] │ -1.745917 -1.245769 │ [INFO] [stdout] │ -1.027560 0.614611 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023316 │ [INFO] [stdout] │ 1.781234 │ [INFO] [stdout] │ -0.523260 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 242 [INFO] [stdout] ed: 0.0000000000972985928253194 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.531946 0.656101 │ [INFO] [stdout] │ -1.745974 -1.245826 │ [INFO] [stdout] │ -1.027569 0.614601 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023315 │ [INFO] [stdout] │ 1.781262 │ [INFO] [stdout] │ -0.523256 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 243 [INFO] [stdout] ed: 0.00000000009666203922822112 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.531941 0.656096 │ [INFO] [stdout] │ -1.746031 -1.245883 │ [INFO] [stdout] │ -1.027578 0.614592 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023313 │ [INFO] [stdout] │ 1.781291 │ [INFO] [stdout] │ -0.523251 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 244 [INFO] [stdout] ed: 0.00000000009615810838874704 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.531936 0.656091 │ [INFO] [stdout] │ -1.746088 -1.245940 │ [INFO] [stdout] │ -1.027587 0.614583 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023312 │ [INFO] [stdout] │ 1.781319 │ [INFO] [stdout] │ -0.523247 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 245 [INFO] [stdout] ed: 0.00000000009612377424826157 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.531931 0.656086 │ [INFO] [stdout] │ -1.746144 -1.245996 │ [INFO] [stdout] │ -1.027596 0.614574 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023311 │ [INFO] [stdout] │ 1.781347 │ [INFO] [stdout] │ -0.523243 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 246 [INFO] [stdout] ed: 0.00000000009598884562988604 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.531926 0.656081 │ [INFO] [stdout] │ -1.746200 -1.246052 │ [INFO] [stdout] │ -1.027605 0.614565 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023310 │ [INFO] [stdout] │ 1.781375 │ [INFO] [stdout] │ -0.523238 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 247 [INFO] [stdout] ed: 0.00000000009560885465713972 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.531921 0.656076 │ [INFO] [stdout] │ -1.746256 -1.246108 │ [INFO] [stdout] │ -1.027614 0.614556 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023309 │ [INFO] [stdout] │ 1.781403 │ [INFO] [stdout] │ -0.523234 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 248 [INFO] [stdout] ed: 0.00000000009454423423677358 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.531916 0.656071 │ [INFO] [stdout] │ -1.746312 -1.246164 │ [INFO] [stdout] │ -1.027623 0.614547 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023308 │ [INFO] [stdout] │ 1.781431 │ [INFO] [stdout] │ -0.523229 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] finished ff for all training points - epoch 249 [INFO] [stdout] ed: 0.00000000009480413405006479 [INFO] [stdout] weights in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.531912 0.656067 │ [INFO] [stdout] │ -1.746367 -1.246220 │ [INFO] [stdout] │ -1.027632 0.614539 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] biases in layer 1: [INFO] [stdout] ╭ ╮ [INFO] [stdout] │ 2.023307 │ [INFO] [stdout] │ 1.781459 │ [INFO] [stdout] │ -0.523225 │ [INFO] [stdout] ╰ ╯ [INFO] [stdout] [INFO] [stdout] stopping after 250 epocs [INFO] [stdout] [INFO] [stdout] cost across entire training set after 250 epocs: 0.25001456946348344 [INFO] [stdout] computing initial cross accross entire training dataset... [INFO] [stdout] initial cost across entire training set: 0.25001456946348344 [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: 0 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: 0.2500145063220251 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 8 ms [INFO] [stdout] cost across training set after epoch 1: 0.2500144436687518 [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 2 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 2: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 2: 0.2500143814980265 [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 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: 0.2500143198042984 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 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: 0.2500142585821013 [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 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: 0.25001419782605216 [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 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: 0.25001413753084906 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 7: 0.25001407769127015 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 8 ms [INFO] [stdout] cost across training set after epoch 8: 0.250014018302172 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 7 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: 1 ms [INFO] [stdout] cost across training set after epoch 9: 0.25001395935848797 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.250013900855227 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 3 ms [INFO] [stdout] cost across training set after epoch 11: 0.250013842787472 [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 12 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 12: t_compute_gradients: 0 ms [INFO] [stdout] cost across training set after epoch 12: 0.250013785150379 [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 13 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 13: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 13: 0.2500137279391749 [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 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: 0.2500136711491572 [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 15 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 15: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 15: 0.2500136147756917 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 2 ms [INFO] [stdout] cost across training set after epoch 16: 0.2500135588142121 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500135032602183 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 4 ms [INFO] [stdout] cost across training set after epoch 18: 0.25001344810927545 [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 19 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 19: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 19: 0.2500133933570124 [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 20 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 20: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 20: 0.25001333899912115 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 8 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: 1 ms [INFO] [stdout] cost across training set after epoch 21: 0.25001328503135506 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 4 ms [INFO] [stdout] cost across training set after epoch 22: 0.25001323144952836 [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 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: 0.25001317824951463 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0 ms [INFO] [stdout] cost across training set after epoch 24: 0.250013125427246 [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 25 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 25: t_compute_gradients: 3 ms [INFO] [stdout] cost across training set after epoch 25: 0.2500130729787119 [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: 0 ms [INFO] [stdout] cost across training set after epoch 26: 0.25001302089995847 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 0 ms [INFO] [stdout] cost across training set after epoch 27: 0.2500129691870869 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500129178362531 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 14 ms [INFO] [stdout] cost across training set after epoch 29: 0.2500128668436666 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 0.25001281620558913 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 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: 0.25001276591833455 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 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: 0.2500127159782673 [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 33 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 33: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 33: 0.25001266638180175 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 11 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: 0 ms [INFO] [stdout] cost across training set after epoch 34: 0.2500126171254013 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 8 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: 4 ms [INFO] [stdout] cost across training set after epoch 35: 0.25001256820557793 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500125196188906 [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 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: 0.25001247136194504 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 4 ms [INFO] [stdout] cost across training set after epoch 38: 0.25001242343139296 [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 39 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 39: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 39: 0.25001237582393104 [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 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: 0.25001232853630023 [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 41 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 41: t_compute_gradients: 5 ms [INFO] [stdout] cost across training set after epoch 41: 0.2500122815652851 [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 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: 0.250012234907713 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 1 ms [INFO] [stdout] cost across training set after epoch 43: 0.2500121885604536 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 3 ms [INFO] [stdout] cost across training set after epoch 44: 0.2500121425204177 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 3 ms [INFO] [stdout] cost across training set after epoch 45: 0.2500120967845572 [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 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: 0.25001205134986393 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 0.2500120062133691 [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 48 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 48: t_compute_gradients: 5 ms [INFO] [stdout] cost across training set after epoch 48: 0.25001196137214277 [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 49 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 49: t_compute_gradients: 4 ms [INFO] [stdout] cost across training set after epoch 49: 0.2500119168232932 [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 50 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 50: t_compute_gradients: 0 ms [INFO] [stdout] cost across training set after epoch 50: 0.25001187256396623 [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 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: 0.25001182859134435 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 11 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: 1 ms [INFO] [stdout] cost across training set after epoch 52: 0.25001178490264675 [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 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: 0.2500117414951283 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 2 ms [INFO] [stdout] cost across training set after epoch 54: 0.25001169836607867 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0 ms [INFO] [stdout] cost across training set after epoch 55: 0.25001165551282284 [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 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: 0.25001161293271934 [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 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: 0.2500115706231604 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 3 ms [INFO] [stdout] cost across training set after epoch 58: 0.2500115285815713 [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 59 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 59: t_compute_gradients: 15 ms [INFO] [stdout] cost across training set after epoch 59: 0.2500114868054096 [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 60 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 60: t_compute_gradients: 2 ms [INFO] [stdout] cost across training set after epoch 60: 0.2500114452921651 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 0.25001140403935895 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 62: 0.2500113630445433 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 8 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: 0 ms [INFO] [stdout] cost across training set after epoch 63: 0.2500113223053008 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 64: 0.25001128181924426 [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 65 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 65: t_compute_gradients: 0 ms [INFO] [stdout] cost across training set after epoch 65: 0.2500112415840158 [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 66 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 66: t_compute_gradients: 2 ms [INFO] [stdout] cost across training set after epoch 66: 0.2500112015972867 [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 67 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 67: t_compute_gradients: 2 ms [INFO] [stdout] cost across training set after epoch 67: 0.25001116185675704 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 9 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: 6 ms [INFO] [stdout] cost across training set after epoch 68: 0.2500111223601551 [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 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: 0.250011083105237 [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 70 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 70: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 70: 0.2500110440897859 [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 71 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 71: t_compute_gradients: 2 ms [INFO] [stdout] cost across training set after epoch 71: 0.2500110053116124 [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 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: 0.2500109667685533 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 1 ms [INFO] [stdout] cost across training set after epoch 73: 0.2500109284584716 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500108903792563 [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 75 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 75: t_compute_gradients: 2 ms [INFO] [stdout] cost across training set after epoch 75: 0.2500108525288213 [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: 2 ms [INFO] [stdout] cost across training set after epoch 76: 0.2500108149051061 [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 77 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 77: t_compute_gradients: 3 ms [INFO] [stdout] cost across training set after epoch 77: 0.25001077750607414 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 5 ms [INFO] [stdout] cost across training set after epoch 78: 0.2500107403297137 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 3 ms [INFO] [stdout] cost across training set after epoch 79: 0.2500107033740365 [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 80 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 80: t_compute_gradients: 0 ms [INFO] [stdout] cost across training set after epoch 80: 0.2500106666370781 [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 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: 0.25001063011689706 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 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: 0.25001059381157503 [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 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: 0.2500105577192159 [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 84 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 84: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 84: 0.25001052183794575 [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 85 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 85: t_compute_gradients: 5 ms [INFO] [stdout] cost across training set after epoch 85: 0.25001048616591287 [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 86 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 86: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 86: 0.25001045070128675 [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 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: 0.2500104154422582 [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 88 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 88: t_compute_gradients: 7 ms [INFO] [stdout] cost across training set after epoch 88: 0.2500103803870391 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 0.2500103455338616 [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 90 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 90: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 90: 0.25001031088097864 [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 91 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 91: t_compute_gradients: 3 ms [INFO] [stdout] cost across training set after epoch 91: 0.25001027642666285 [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 92 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 92: t_compute_gradients: 2 ms [INFO] [stdout] cost across training set after epoch 92: 0.25001024216920675 [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 93 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 93: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 93: 0.25001020810692237 [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 94 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 94: t_compute_gradients: 4 ms [INFO] [stdout] cost across training set after epoch 94: 0.25001017423814087 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 13 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: 14 ms [INFO] [stdout] cost across training set after epoch 95: 0.2500101405612124 [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: 2 ms [INFO] [stdout] cost across training set after epoch 96: 0.25001010707450555 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 3 ms [INFO] [stdout] cost across training set after epoch 97: 0.25001007377640766 [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 98 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 98: t_compute_gradients: 3 ms [INFO] [stdout] cost across training set after epoch 98: 0.2500100406653239 [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 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: 0.2500100077396774 [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 100 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 100: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 100: 0.25000997499790906 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 1 ms [INFO] [stdout] cost across training set after epoch 101: 0.2500099424384771 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 3 ms [INFO] [stdout] cost across training set after epoch 102: 0.2500099100598566 [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 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: 0.25000987786054013 [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 104 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 104: t_compute_gradients: 0 ms [INFO] [stdout] cost across training set after epoch 104: 0.2500098458390364 [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 105 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 105: t_compute_gradients: 2 ms [INFO] [stdout] cost across training set after epoch 105: 0.2500098139938708 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 11 ms [INFO] [stdout] cost across training set after epoch 106: 0.25000978232358495 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 0.25000975082673643 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 0.25000971950189854 [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 109 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 109: t_compute_gradients: 2 ms [INFO] [stdout] cost across training set after epoch 109: 0.2500096883476603 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 1 ms [INFO] [stdout] cost across training set after epoch 110: 0.25000965736262576 [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 111 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 111: t_compute_gradients: 6 ms [INFO] [stdout] cost across training set after epoch 111: 0.25000962654541464 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 3 ms [INFO] [stdout] cost across training set after epoch 112: 0.2500095958946611 [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 113 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 113: t_compute_gradients: 3 ms [INFO] [stdout] cost across training set after epoch 113: 0.2500095654090143 [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 114 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 114: t_compute_gradients: 5 ms [INFO] [stdout] cost across training set after epoch 114: 0.2500095350871378 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 8 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: 2 ms [INFO] [stdout] cost across training set after epoch 115: 0.2500095049277098 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 0.2500094749294222 [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 117 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 117: t_compute_gradients: 0 ms [INFO] [stdout] cost across training set after epoch 117: 0.2500094450909813 [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 118 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 118: t_compute_gradients: 7 ms [INFO] [stdout] cost across training set after epoch 118: 0.2500094154111069 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 10 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: 1 ms [INFO] [stdout] cost across training set after epoch 119: 0.25000938588853233 [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 120 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 120: t_compute_gradients: 5 ms [INFO] [stdout] cost across training set after epoch 120: 0.25000935652200473 [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 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: 0.2500093273102842 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 8 ms [INFO] [stdout] cost across training set after epoch 122: 0.2500092982521439 [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 123 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 123: t_compute_gradients: 3 ms [INFO] [stdout] cost across training set after epoch 123: 0.2500092693463699 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 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: 0.2500092405917611 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 7 ms [INFO] [stdout] cost across training set after epoch 125: 0.25000921198712883 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 1 ms [INFO] [stdout] cost across training set after epoch 126: 0.2500091835312971 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 7 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: 2 ms [INFO] [stdout] cost across training set after epoch 127: 0.2500091552231015 [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 128 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 128: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 128: 0.25000912706139056 [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 129 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 129: t_compute_gradients: 6 ms [INFO] [stdout] cost across training set after epoch 129: 0.2500090990450241 [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 130 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 130: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 130: 0.25000907117287396 [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 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: 0.2500090434438235 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 4 ms [INFO] [stdout] cost across training set after epoch 132: 0.2500090158567677 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 12 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: 0 ms [INFO] [stdout] cost across training set after epoch 133: 0.25000898841061264 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 16 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: 7 ms [INFO] [stdout] cost across training set after epoch 134: 0.25000896110427584 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 8 ms [INFO] [stdout] cost across training set after epoch 135: 0.25000893393668555 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 5 ms [INFO] [stdout] cost across training set after epoch 136: 0.2500089069067812 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500088800135128 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 8 ms [INFO] [stdout] cost across training set after epoch 138: 0.250008853255841 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 139: 0.25000882663273705 [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 140 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 140: t_compute_gradients: 3 ms [INFO] [stdout] cost across training set after epoch 140: 0.2500088001431824 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500087737861688 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0 ms [INFO] [stdout] cost across training set after epoch 142: 0.25000874756069824 [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 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: 0.25000872146578235 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 12 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: 12 ms [INFO] [stdout] cost across training set after epoch 144: 0.25000869550044286 [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 145 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 145: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 145: 0.25000866966371116 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 5 ms [INFO] [stdout] cost across training set after epoch 146: 0.25000864395462835 [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 147 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 147: t_compute_gradients: 3 ms [INFO] [stdout] cost across training set after epoch 147: 0.25000861837224475 [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 148 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 148: t_compute_gradients: 2 ms [INFO] [stdout] cost across training set after epoch 148: 0.2500085929156204 [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: 1 ms [INFO] [stdout] cost across training set after epoch 149: 0.2500085675838243 [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: 5 ms [INFO] [stdout] cost across training set after epoch 150: 0.2500085423759346 [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 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: 0.2500085172910388 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 0.2500084923282329 [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 153 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 153: t_compute_gradients: 8 ms [INFO] [stdout] cost across training set after epoch 153: 0.25000846748662214 [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 154 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 154: t_compute_gradients: 0 ms [INFO] [stdout] cost across training set after epoch 154: 0.25000844276532 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500084181634489 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 7 ms [INFO] [stdout] cost across training set after epoch 156: 0.2500083936801397 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000836931453146 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 1 ms [INFO] [stdout] cost across training set after epoch 158: 0.2500083450657718 [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 159 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 159: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 159: 0.25000832093301634 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 5 ms [INFO] [stdout] cost across training set after epoch 160: 0.2500082969154289 [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 161 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 161: t_compute_gradients: 8 ms [INFO] [stdout] cost across training set after epoch 161: 0.2500082730121812 [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 162 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 162: t_compute_gradients: 7 ms [INFO] [stdout] cost across training set after epoch 162: 0.250008249222453 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500082255454316 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 2 ms [INFO] [stdout] cost across training set after epoch 164: 0.2500082019803124 [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 165 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 165: t_compute_gradients: 0 ms [INFO] [stdout] cost across training set after epoch 165: 0.2500081785262982 [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 166 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 166: t_compute_gradients: 4 ms [INFO] [stdout] cost across training set after epoch 166: 0.2500081551825993 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 5 ms [INFO] [stdout] cost across training set after epoch 167: 0.2500081319484334 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 1 ms [INFO] [stdout] cost across training set after epoch 168: 0.25000810882302593 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 2 ms [INFO] [stdout] cost across training set after epoch 169: 0.250008085805609 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000806289542254 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 171: 0.2500080400917131 [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 172 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 172: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 172: 0.25000801739373446 [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 173 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 173: t_compute_gradients: 2 ms [INFO] [stdout] cost across training set after epoch 173: 0.2500079948007473 [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 174 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 174: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 174: 0.25000797231201927 [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 175 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 175: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 175: 0.2500079499268245 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000792764444413 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 1 ms [INFO] [stdout] cost across training set after epoch 177: 0.25000790546416585 [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 178 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 178: t_compute_gradients: 5 ms [INFO] [stdout] cost across training set after epoch 178: 0.2500078833852838 [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 179 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 179: t_compute_gradients: 4 ms [INFO] [stdout] cost across training set after epoch 179: 0.25000786140709846 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 1 ms [INFO] [stdout] cost across training set after epoch 180: 0.25000783952891725 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000781775005343 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 12 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: 2 ms [INFO] [stdout] cost across training set after epoch 182: 0.2500077960698265 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 9 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: 4 ms [INFO] [stdout] cost across training set after epoch 183: 0.25000777448756245 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 8 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: 1 ms [INFO] [stdout] cost across training set after epoch 184: 0.25000775300259337 [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 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: 0.2500077316142569 [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 186 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 186: t_compute_gradients: 4 ms [INFO] [stdout] cost across training set after epoch 186: 0.25000771032189717 [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 187 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 187: t_compute_gradients: 11 ms [INFO] [stdout] cost across training set after epoch 187: 0.2500076891248642 [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 188 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 188: t_compute_gradients: 6 ms [INFO] [stdout] cost across training set after epoch 188: 0.2500076680225136 [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 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: 0.25000764701420675 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 1 ms [INFO] [stdout] cost across training set after epoch 190: 0.25000762609931104 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 1 ms [INFO] [stdout] cost across training set after epoch 191: 0.2500076052771993 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 8 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: 5 ms [INFO] [stdout] cost across training set after epoch 192: 0.2500075845472499 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 0.25000756390884693 [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 194 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 194: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 194: 0.25000754336137965 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 0.250007522904243 [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 196 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 196: t_compute_gradients: 5 ms [INFO] [stdout] cost across training set after epoch 196: 0.25000750253683723 [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 197 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 197: t_compute_gradients: 6 ms [INFO] [stdout] cost across training set after epoch 197: 0.2500074822585677 [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 198 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 198: t_compute_gradients: 5 ms [INFO] [stdout] cost across training set after epoch 198: 0.25000746206884517 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 20 ms [INFO] [stdout] cost across training set after epoch 199: 0.25000744196708546 [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 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: 0.2500074219527096 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 201: 0.2500074020251436 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 7 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: 9 ms [INFO] [stdout] cost across training set after epoch 202: 0.25000738218381846 [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 203 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 203: t_compute_gradients: 4 ms [INFO] [stdout] cost across training set after epoch 203: 0.2500073624281701 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 9 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: 5 ms [INFO] [stdout] cost across training set after epoch 204: 0.25000734275763964 [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 205 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 205: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 205: 0.25000732317167257 [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 206 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 206: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 206: 0.25000730366971946 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 9 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: 7 ms [INFO] [stdout] cost across training set after epoch 207: 0.25000728425123564 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 208: 0.2500072649156809 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 9 ms [INFO] [stdout] cost across training set after epoch 209: 0.25000724566252003 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0 ms [INFO] [stdout] cost across training set after epoch 210: 0.250007226491222 [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 211 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 211: t_compute_gradients: 8 ms [INFO] [stdout] cost across training set after epoch 211: 0.2500072074012604 [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 212 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 212: t_compute_gradients: 7 ms [INFO] [stdout] cost across training set after epoch 212: 0.25000718839211367 [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 213 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 213: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 213: 0.25000716946326434 [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 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: 0.2500071506141995 [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 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: 0.25000713184441026 [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 216 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 216: t_compute_gradients: 8 ms [INFO] [stdout] cost across training set after epoch 216: 0.25000711315339263 [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 217 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 217: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 217: 0.25000709454064635 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 3 ms [INFO] [stdout] cost across training set after epoch 218: 0.2500070760056755 [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 219 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 219: t_compute_gradients: 6 ms [INFO] [stdout] cost across training set after epoch 219: 0.2500070575479886 [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 220 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 220: t_compute_gradients: 5 ms [INFO] [stdout] cost across training set after epoch 220: 0.25000703916709793 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 11 ms [INFO] [stdout] cost across training set after epoch 221: 0.25000702086252014 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 2 ms [INFO] [stdout] cost across training set after epoch 222: 0.2500070026337756 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 1 ms [INFO] [stdout] cost across training set after epoch 223: 0.25000698448038905 [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 224 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 224: t_compute_gradients: 8 ms [INFO] [stdout] cost across training set after epoch 224: 0.2500069664018888 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 225: 0.25000694839780746 [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 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: 0.25000693046768124 [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 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: 0.2500069126110502 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 3 ms [INFO] [stdout] cost across training set after epoch 228: 0.2500068948274584 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 2 ms [INFO] [stdout] cost across training set after epoch 229: 0.2500068771164534 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 1 ms [INFO] [stdout] cost across training set after epoch 230: 0.2500068594775867 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 21 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: 2 ms [INFO] [stdout] cost across training set after epoch 231: 0.25000684191041334 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0 ms [INFO] [stdout] cost across training set after epoch 232: 0.25000682441449207 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 2 ms [INFO] [stdout] cost across training set after epoch 233: 0.25000680698938516 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 13 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: 0.25000678963465844 [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 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: 0.25000677234988145 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 10 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: 0.250006755134627 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 8 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: 8 ms [INFO] [stdout] cost across training set after epoch 237: 0.2500067379884715 [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: 0.2500067209109948 [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 239 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 239: t_compute_gradients: 2 ms [INFO] [stdout] cost across training set after epoch 239: 0.25000670390178 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 240: 0.2500066869604138 [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 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: 0.2500066700864859 [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 242 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 242: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 242: 0.25000665327958954 [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 243 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 243: t_compute_gradients: 0 ms [INFO] [stdout] cost across training set after epoch 243: 0.2500066365393212 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0 ms [INFO] [stdout] cost across training set after epoch 244: 0.2500066198652804 [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 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: 0.2500066032570699 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0 ms [INFO] [stdout] cost across training set after epoch 246: 0.25000658671429604 [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 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: 0.2500065702365676 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 7 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: 0.2500065538234969 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 7 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: 7 ms [INFO] [stdout] cost across training set after epoch 249: 0.25000653747469925 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0 ms [INFO] [stdout] cost across training set after epoch 250: 0.25000652118979294 [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 251 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 251: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 251: 0.2500065049683994 [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 252 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 252: t_compute_gradients: 4 ms [INFO] [stdout] cost across training set after epoch 252: 0.25000648881014287 [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 253 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 253: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 253: 0.2500064727146506 [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 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: 0.2500064566815527 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 255: 0.2500064407104824 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 4 ms [INFO] [stdout] cost across training set after epoch 256: 0.25000642480107554 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 257: 0.250006408952971 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 258: 0.25000639316581014 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 259: 0.25000637743923754 [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 260 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 260: t_compute_gradients: 4 ms [INFO] [stdout] cost across training set after epoch 260: 0.25000636177290003 [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 261 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 261: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 261: 0.2500063461664478 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000633061953326 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 263: 0.2500063151318115 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 10 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: 2 ms [INFO] [stdout] cost across training set after epoch 264: 0.25000629970294047 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 6 ms [INFO] [stdout] cost across training set after epoch 265: 0.2500062843325807 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 0.2500062690203953 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500062537660498 [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 268 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 268: t_compute_gradients: 2 ms [INFO] [stdout] cost across training set after epoch 268: 0.2500062385692125 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 2 ms [INFO] [stdout] cost across training set after epoch 269: 0.2500062234295541 [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 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: 0.25000620834674786 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 7 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: 3 ms [INFO] [stdout] cost across training set after epoch 271: 0.25000619332046947 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500061783503972 [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 273 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 273: t_compute_gradients: 2 ms [INFO] [stdout] cost across training set after epoch 273: 0.25000616343621146 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 4 ms [INFO] [stdout] cost across training set after epoch 274: 0.25000614857759557 [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 275 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 275: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 275: 0.25000613377423453 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 1 ms [INFO] [stdout] cost across training set after epoch 276: 0.25000611902581643 [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 277 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 277: t_compute_gradients: 3 ms [INFO] [stdout] cost across training set after epoch 277: 0.2500061043320311 [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 278 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 278: t_compute_gradients: 7 ms [INFO] [stdout] cost across training set after epoch 278: 0.25000608969257127 [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 279 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 279: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 279: 0.25000607510713135 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 0.25000606057540853 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 0.25000604609710203 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 7 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: 0 ms [INFO] [stdout] cost across training set after epoch 282: 0.2500060316719132 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 283: 0.250006017299546 [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 284 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 284: t_compute_gradients: 2 ms [INFO] [stdout] cost across training set after epoch 284: 0.2500060029797061 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 3 ms [INFO] [stdout] cost across training set after epoch 285: 0.2500059887121015 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 2 ms [INFO] [stdout] cost across training set after epoch 286: 0.2500059744964427 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 2 ms [INFO] [stdout] cost across training set after epoch 287: 0.25000596033244177 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500059462198133 [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 289 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 289: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 289: 0.2500059321582739 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 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: 5 ms [INFO] [stdout] cost across training set after epoch 290: 0.2500059181475421 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 1 ms [INFO] [stdout] cost across training set after epoch 291: 0.2500059041873386 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 292: 0.2500058902773862 [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 293 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 293: t_compute_gradients: 3 ms [INFO] [stdout] cost across training set after epoch 293: 0.2500058764174095 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0 ms [INFO] [stdout] cost across training set after epoch 294: 0.25000586260713537 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 2 ms [INFO] [stdout] cost across training set after epoch 295: 0.2500058488462925 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0 ms [INFO] [stdout] cost across training set after epoch 296: 0.2500058351346116 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 2 ms [INFO] [stdout] cost across training set after epoch 297: 0.2500058214718252 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0 ms [INFO] [stdout] cost across training set after epoch 298: 0.25000580785766807 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0 ms [INFO] [stdout] cost across training set after epoch 299: 0.2500057942918765 [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 300 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 300: t_compute_gradients: 0 ms [INFO] [stdout] cost across training set after epoch 300: 0.250005780774189 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 5 ms [INFO] [stdout] cost across training set after epoch 301: 0.25000576730434565 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000575388208873 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 1 ms [INFO] [stdout] cost across training set after epoch 303: 0.2500057405071622 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000572717931174 [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 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: 0.2500057138982849 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500057006638312 [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 307 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 307: t_compute_gradients: 7 ms [INFO] [stdout] cost across training set after epoch 307: 0.2500056874757018 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500056743336495 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 2 ms [INFO] [stdout] cost across training set after epoch 309: 0.2500056612374292 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 8 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: 1 ms [INFO] [stdout] cost across training set after epoch 310: 0.25000564818679716 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 9 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: 1 ms [INFO] [stdout] cost across training set after epoch 311: 0.2500056351815116 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 2 ms [INFO] [stdout] cost across training set after epoch 312: 0.25000562222133227 [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 313 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 313: t_compute_gradients: 2 ms [INFO] [stdout] cost across training set after epoch 313: 0.2500056093060207 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 314: 0.2500055964353402 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 5 ms [INFO] [stdout] cost across training set after epoch 315: 0.2500055836090555 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 2 ms [INFO] [stdout] cost across training set after epoch 316: 0.25000557082693303 [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 317 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 317: t_compute_gradients: 0 ms [INFO] [stdout] cost across training set after epoch 317: 0.2500055580887412 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 318: 0.25000554539424946 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 0.25000553274322945 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 6 ms [INFO] [stdout] cost across training set after epoch 320: 0.2500055201354538 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 321: 0.25000550757069717 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000549504873554 [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 323 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 323: t_compute_gradients: 2 ms [INFO] [stdout] cost across training set after epoch 323: 0.2500054825693467 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0 ms [INFO] [stdout] cost across training set after epoch 324: 0.2500054701323096 [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 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: 0.250005457737405 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 2 ms [INFO] [stdout] cost across training set after epoch 326: 0.25000544538441505 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500054330731234 [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 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: 0.2500054208033152 [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 329 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 329: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 329: 0.25000540857477715 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 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: 0 ms [INFO] [stdout] cost across training set after epoch 330: 0.25000539638729713 [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 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: 0.25000538424066493 [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 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: 0.2500053721346712 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 1 ms [INFO] [stdout] cost across training set after epoch 333: 0.25000536006910856 [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 334 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 334: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 334: 0.25000534804377067 [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 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: 0.25000533605845277 [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 336 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 336: t_compute_gradients: 5 ms [INFO] [stdout] cost across training set after epoch 336: 0.2500053241129511 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 5 ms [INFO] [stdout] cost across training set after epoch 337: 0.25000531220706407 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 2 ms [INFO] [stdout] cost across training set after epoch 338: 0.25000530034059065 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500052885133316 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000527672508877 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 2 ms [INFO] [stdout] cost across training set after epoch 341: 0.25000526497566555 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 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: 1 ms [INFO] [stdout] cost across training set after epoch 342: 0.25000525326486656 [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 343 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 343: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 343: 0.2500052415924977 [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 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: 0.2500052299583662 [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 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: 0.25000521836228057 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000520680405053 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000519528348714 [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 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: 0.2500051838004026 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 349: 0.2500051723546105 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 5 ms [INFO] [stdout] cost across training set after epoch 350: 0.2500051609459256 [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 351 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 351: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 351: 0.250005149574164 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 4 ms [INFO] [stdout] cost across training set after epoch 352: 0.25000513823914267 [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 353 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 353: t_compute_gradients: 5 ms [INFO] [stdout] cost across training set after epoch 353: 0.2500051269406801 [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 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: 0.2500051156785958 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0 ms [INFO] [stdout] cost across training set after epoch 355: 0.2500051044527106 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 7 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: 1 ms [INFO] [stdout] cost across training set after epoch 356: 0.2500050932628464 [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 357 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 357: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 357: 0.25000508210882627 [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 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: 0.2500050709904746 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 4 ms [INFO] [stdout] cost across training set after epoch 359: 0.2500050599076165 [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 360 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 360: t_compute_gradients: 2 ms [INFO] [stdout] cost across training set after epoch 360: 0.2500050488600787 [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 361 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 361: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 361: 0.25000503784768885 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 362: 0.2500050268702756 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 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: 1 ms [INFO] [stdout] cost across training set after epoch 363: 0.25000501592766877 [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 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: 0.2500050050196996 [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 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: 0.2500049941461998 [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 366 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 366: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 366: 0.2500049833070027 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500049725019426 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 2 ms [INFO] [stdout] cost across training set after epoch 368: 0.2500049617308546 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.250004950993575 [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 370 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 370: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 370: 0.25000494028994125 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0 ms [INFO] [stdout] cost across training set after epoch 371: 0.25000492961979176 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 1 ms [INFO] [stdout] cost across training set after epoch 372: 0.25000491898296595 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 2 ms [INFO] [stdout] cost across training set after epoch 373: 0.25000490837930434 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 374: 0.25000489780864826 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000488727084025 [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 376 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 376: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 376: 0.2500048767657238 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000486629314345 [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 378 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 378: t_compute_gradients: 3 ms [INFO] [stdout] cost across training set after epoch 378: 0.2500048558529444 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 2 ms [INFO] [stdout] cost across training set after epoch 379: 0.2500048454449733 [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 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: 0.25000483506907745 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 1 ms [INFO] [stdout] cost across training set after epoch 381: 0.25000482472510516 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500048144129059 [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 383 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 383: t_compute_gradients: 3 ms [INFO] [stdout] cost across training set after epoch 383: 0.2500048041323296 [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 384 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 384: t_compute_gradients: 4 ms [INFO] [stdout] cost across training set after epoch 384: 0.25000479388322766 [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 385 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 385: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 385: 0.25000478366545215 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 1 ms [INFO] [stdout] cost across training set after epoch 386: 0.250004773478856 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 14 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: 1 ms [INFO] [stdout] cost across training set after epoch 387: 0.25000476332329324 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 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: 0.2500047531986187 [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 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: 0.2500047431046881 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 8 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: 0.25000473304135806 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 391: 0.2500047230084862 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500047130059308 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0 ms [INFO] [stdout] cost across training set after epoch 393: 0.25000470303355127 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 14 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: 1 ms [INFO] [stdout] cost across training set after epoch 394: 0.25000469309120754 [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 395 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 395: t_compute_gradients: 4 ms [INFO] [stdout] cost across training set after epoch 395: 0.25000468317876084 [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 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: 0.2500046732960729 [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 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: 0.25000466344300654 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500046536194252 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 399: 0.2500046438251933 [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 400 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 400: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 400: 0.250004634060176 [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 401 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 401: t_compute_gradients: 2 ms [INFO] [stdout] cost across training set after epoch 401: 0.2500046243242393 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 2 ms [INFO] [stdout] cost across training set after epoch 402: 0.25000461461725015 [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 403 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 403: t_compute_gradients: 0 ms [INFO] [stdout] cost across training set after epoch 403: 0.25000460493907617 [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 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: 0.25000459528958574 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 1 ms [INFO] [stdout] cost across training set after epoch 405: 0.2500045856686481 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 4 ms [INFO] [stdout] cost across training set after epoch 406: 0.2500045760761334 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 8 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: 0.2500045665119123 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 0.2500045569758566 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 409: 0.2500045474678386 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 4 ms [INFO] [stdout] cost across training set after epoch 410: 0.2500045379877314 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500045285354089 [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 412 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 412: t_compute_gradients: 9 ms [INFO] [stdout] cost across training set after epoch 412: 0.2500045191107457 [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 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: 0.2500045097136173 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 7 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: 0.25000450034389987 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 3 ms [INFO] [stdout] cost across training set after epoch 415: 0.25000449100147026 [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 416 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 416: t_compute_gradients: 6 ms [INFO] [stdout] cost across training set after epoch 416: 0.25000448168620604 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500044723979856 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 418: 0.25000446313668806 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0 ms [INFO] [stdout] cost across training set after epoch 419: 0.25000445390219317 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500044446943814 [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 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: 0.25000443551313395 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000442635833275 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 1 ms [INFO] [stdout] cost across training set after epoch 423: 0.2500044172298605 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000440812760033 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 4 ms [INFO] [stdout] cost across training set after epoch 425: 0.2500043990514364 [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 426 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 426: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 426: 0.2500043900012531 [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 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: 0.2500043809769361 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000437197837116 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500043630054451 [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 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: 0.2500043540580451 [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 431 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 431: t_compute_gradients: 0 ms [INFO] [stdout] cost across training set after epoch 431: 0.25000434513605935 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0 ms [INFO] [stdout] cost across training set after epoch 432: 0.2500043362393764 [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 433 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 433: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 433: 0.25000432736788547 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0 ms [INFO] [stdout] cost across training set after epoch 434: 0.2500043185214766 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500043097000403 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0 ms [INFO] [stdout] cost across training set after epoch 436: 0.25000430090346776 [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 437 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 437: t_compute_gradients: 3 ms [INFO] [stdout] cost across training set after epoch 437: 0.2500042921316508 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 6 ms [INFO] [stdout] cost across training set after epoch 438: 0.250004283384482 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 439: 0.2500042746618543 [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 440 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 440: t_compute_gradients: 2 ms [INFO] [stdout] cost across training set after epoch 440: 0.25000426596366154 [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 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: 0.25000425728979775 [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 442 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 442: t_compute_gradients: 2 ms [INFO] [stdout] cost across training set after epoch 442: 0.2500042486401581 [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 443 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 443: t_compute_gradients: 2 ms [INFO] [stdout] cost across training set after epoch 443: 0.25000424001463795 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 1 ms [INFO] [stdout] cost across training set after epoch 444: 0.25000423141313355 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 7 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: 1 ms [INFO] [stdout] cost across training set after epoch 445: 0.25000422283554136 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 0 ms [INFO] [stdout] cost across training set after epoch 446: 0.25000421428175895 [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 447 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 447: t_compute_gradients: 0 ms [INFO] [stdout] cost across training set after epoch 447: 0.2500042057516839 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 9 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: 0.25000419724521494 [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 449 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 449: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 449: 0.25000418876225095 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 3 ms [INFO] [stdout] cost across training set after epoch 450: 0.25000418030269145 [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 451 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 451: t_compute_gradients: 3 ms [INFO] [stdout] cost across training set after epoch 451: 0.25000417186643686 [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 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: 0.25000416345338766 [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 453 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 453: t_compute_gradients: 5 ms [INFO] [stdout] cost across training set after epoch 453: 0.25000415506344525 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0 ms [INFO] [stdout] cost across training set after epoch 454: 0.2500041466965116 [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 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: 0.25000413835248886 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 13 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: 0.2500041300312802 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 2 ms [INFO] [stdout] cost across training set after epoch 457: 0.25000412173278896 [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 458 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 458: t_compute_gradients: 2 ms [INFO] [stdout] cost across training set after epoch 458: 0.2500041134569193 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 2 ms [INFO] [stdout] cost across training set after epoch 459: 0.2500041052035758 [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 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: 0.2500040969726634 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 461: 0.250004088764088 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 7 ms [INFO] [stdout] cost across training set after epoch 462: 0.25000408057775547 [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 463 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 463: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 463: 0.2500040724135727 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 0.25000406427144684 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 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: 5 ms [INFO] [stdout] cost across training set after epoch 465: 0.2500040561512856 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 2 ms [INFO] [stdout] cost across training set after epoch 466: 0.25000404805299725 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 467: 0.25000403997649057 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000403192167464 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 469: 0.25000402388845927 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 13 ms [INFO] [stdout] cost across training set after epoch 470: 0.25000401587675486 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 1 ms [INFO] [stdout] cost across training set after epoch 471: 0.2500040078864719 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 2 ms [INFO] [stdout] cost across training set after epoch 472: 0.25000399991752187 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000399196981626 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 2 ms [INFO] [stdout] cost across training set after epoch 474: 0.2500039840432675 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.250003976137788 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 9 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: 0.2500039682532912 [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 477 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 477: t_compute_gradients: 5 ms [INFO] [stdout] cost across training set after epoch 477: 0.2500039603896905 [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 478 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 478: t_compute_gradients: 0 ms [INFO] [stdout] cost across training set after epoch 478: 0.25000395254690017 [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 479 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 479: t_compute_gradients: 2 ms [INFO] [stdout] cost across training set after epoch 479: 0.2500039447248346 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 7 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: 1 ms [INFO] [stdout] cost across training set after epoch 480: 0.250003936923409 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 6 ms [INFO] [stdout] cost across training set after epoch 481: 0.25000392914253877 [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 482 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 482: t_compute_gradients: 0 ms [INFO] [stdout] cost across training set after epoch 482: 0.25000392138214 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 2 ms [INFO] [stdout] cost across training set after epoch 483: 0.2500039136421289 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 4 ms [INFO] [stdout] cost across training set after epoch 484: 0.2500039059224225 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.250003898222938 [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 486 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 486: t_compute_gradients: 0 ms [INFO] [stdout] cost across training set after epoch 486: 0.2500038905435933 [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 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: 0.2500038828843064 [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 488 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 488: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 488: 0.2500038752449961 [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 489 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 489: t_compute_gradients: 2 ms [INFO] [stdout] cost across training set after epoch 489: 0.25000386762558147 [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 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: 0.25000386002598185 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 491: 0.25000385244611745 [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 492 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 492: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 492: 0.25000384488590843 [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 493 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 493: t_compute_gradients: 4 ms [INFO] [stdout] cost across training set after epoch 493: 0.2500038373452757 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 3 ms [INFO] [stdout] cost across training set after epoch 494: 0.25000382982414054 [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 495 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 495: t_compute_gradients: 4 ms [INFO] [stdout] cost across training set after epoch 495: 0.25000382232242435 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500038148400495 [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 497 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 497: t_compute_gradients: 6 ms [INFO] [stdout] cost across training set after epoch 497: 0.25000380737693817 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000379993301347 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 4 ms [INFO] [stdout] cost across training set after epoch 499: 0.2500037925081986 [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 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: 0.25000378510241716 [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 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: 0.2500037777155935 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 0.2500037703476519 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000376299851734 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000375566811517 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.250003748356371 [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 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: 0.2500037410632109 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 507: 0.25000373378856156 [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 508 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 508: t_compute_gradients: 6 ms [INFO] [stdout] cost across training set after epoch 508: 0.2500037265323495 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 7 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: 3 ms [INFO] [stdout] cost across training set after epoch 509: 0.25000371929450205 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 7 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: 2 ms [INFO] [stdout] cost across training set after epoch 510: 0.25000371207494704 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 4 ms [INFO] [stdout] cost across training set after epoch 511: 0.2500037048736123 [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 512 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 512: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 512: 0.2500036976904262 [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 513 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 513: t_compute_gradients: 0 ms [INFO] [stdout] cost across training set after epoch 513: 0.2500036905253175 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 1 ms [INFO] [stdout] cost across training set after epoch 514: 0.2500036833782153 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 515: 0.2500036762490491 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500036691377488 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000366204424446 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500036549684669 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500036479103468 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 6 ms [INFO] [stdout] cost across training set after epoch 520: 0.2500036408698155 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000363384680474 [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 522 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 522: t_compute_gradients: 4 ms [INFO] [stdout] cost across training set after epoch 522: 0.25000362684124655 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 3 ms [INFO] [stdout] cost across training set after epoch 523: 0.25000361985307307 [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 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: 0.2500036128822171 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 4 ms [INFO] [stdout] cost across training set after epoch 525: 0.2500036059286118 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 1 ms [INFO] [stdout] cost across training set after epoch 526: 0.2500035989921904 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 1 ms [INFO] [stdout] cost across training set after epoch 527: 0.2500035920728866 [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 528 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 528: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 528: 0.2500035851706345 [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 529 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 529: t_compute_gradients: 3 ms [INFO] [stdout] cost across training set after epoch 529: 0.2500035782853685 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 1 ms [INFO] [stdout] cost across training set after epoch 530: 0.25000357141702334 [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 531 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 531: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 531: 0.250003564565534 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 5 ms [INFO] [stdout] cost across training set after epoch 532: 0.25000355773083605 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 7 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: 1 ms [INFO] [stdout] cost across training set after epoch 533: 0.250003550912865 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 9 ms [INFO] [stdout] cost across training set after epoch 534: 0.25000354411155706 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 12 ms [INFO] [stdout] cost across training set after epoch 535: 0.2500035373268485 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 6 ms [INFO] [stdout] cost across training set after epoch 536: 0.2500035305586761 [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 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: 0.25000352380697666 [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 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: 0.2500035170716877 [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 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: 0.2500035103527468 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 6 ms [INFO] [stdout] cost across training set after epoch 540: 0.25000350365009194 [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 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: 0.2500034969636613 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 0.25000349029339364 [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 543 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 543: t_compute_gradients: 4 ms [INFO] [stdout] cost across training set after epoch 543: 0.25000348363922764 [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 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: 0.2500034770011027 [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 545 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 545: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 545: 0.2500034703789581 [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 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: 0.2500034637727337 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500034571823696 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 548: 0.25000345060780643 [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 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: 0.2500034440489845 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 1 ms [INFO] [stdout] cost across training set after epoch 550: 0.25000343750584497 [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 551 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 551: t_compute_gradients: 2 ms [INFO] [stdout] cost across training set after epoch 551: 0.2500034309783291 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 9 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: 1 ms [INFO] [stdout] cost across training set after epoch 552: 0.2500034244663786 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 13 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: 4 ms [INFO] [stdout] cost across training set after epoch 553: 0.250003417969935 [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 554 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 554: t_compute_gradients: 3 ms [INFO] [stdout] cost across training set after epoch 554: 0.25000341148894084 [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 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: 0.2500034050233383 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500033985730702 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500033921380794 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 1 ms [INFO] [stdout] cost across training set after epoch 558: 0.2500033857183094 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 5 ms [INFO] [stdout] cost across training set after epoch 559: 0.25000337931370353 [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 560 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 560: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 560: 0.25000337292420577 [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 561 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 561: t_compute_gradients: 2 ms [INFO] [stdout] cost across training set after epoch 561: 0.2500033665497602 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 8 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: 1 ms [INFO] [stdout] cost across training set after epoch 562: 0.2500033601903112 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 3 ms [INFO] [stdout] cost across training set after epoch 563: 0.25000335384580336 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500033475161817 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500033412013913 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 0.25000333490137766 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500033286160867 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 568: 0.25000332234546413 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 1 ms [INFO] [stdout] cost across training set after epoch 569: 0.2500033160894563 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 570: 0.25000330984800984 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 6 ms [INFO] [stdout] cost across training set after epoch 571: 0.25000330362107137 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 4 ms [INFO] [stdout] cost across training set after epoch 572: 0.250003297408588 [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 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: 0.2500032912105069 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 10 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: 1 ms [INFO] [stdout] cost across training set after epoch 574: 0.25000328502677577 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 2 ms [INFO] [stdout] cost across training set after epoch 575: 0.25000327885734225 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 576: 0.2500032727021545 [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 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: 0.2500032665611608 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000326043430965 [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 579 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 579: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 579: 0.2500032543215498 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 1 ms [INFO] [stdout] cost across training set after epoch 580: 0.2500032482228304 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 7 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: 1 ms [INFO] [stdout] cost across training set after epoch 581: 0.2500032421381006 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 0.25000323606730995 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 1 ms [INFO] [stdout] cost across training set after epoch 583: 0.2500032300104083 [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 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: 0.25000322396734553 [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 585 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 585: t_compute_gradients: 5 ms [INFO] [stdout] cost across training set after epoch 585: 0.25000321793807195 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 6 ms [INFO] [stdout] cost across training set after epoch 586: 0.25000321192253805 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500032059206945 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 0.2500031999324922 [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 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: 0.2500031939578824 [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 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: 0.25000318799681653 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000318204924615 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 5 ms [INFO] [stdout] cost across training set after epoch 592: 0.25000317611512307 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 1 ms [INFO] [stdout] cost across training set after epoch 593: 0.2500031701943995 [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 594 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 594: t_compute_gradients: 2 ms [INFO] [stdout] cost across training set after epoch 594: 0.2500031642870278 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 5 ms [INFO] [stdout] cost across training set after epoch 595: 0.2500031583929604 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 596: 0.25000315251215005 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500031466445497 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500031407901128 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 599: 0.25000313494879256 [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 600 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 600: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 600: 0.2500031291205427 [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 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: 0.250003123305317 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 7 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: 0.2500031175030697 [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 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: 0.2500031117137549 [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 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: 0.2500031059373272 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 5 ms [INFO] [stdout] cost across training set after epoch 605: 0.2500031001737413 [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 606 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 606: t_compute_gradients: 3 ms [INFO] [stdout] cost across training set after epoch 606: 0.25000309442295215 [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 607 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 607: t_compute_gradients: 5 ms [INFO] [stdout] cost across training set after epoch 607: 0.25000308868491483 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 4 ms [INFO] [stdout] cost across training set after epoch 608: 0.25000308295958473 [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 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: 0.2500030772469174 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000307154686857 [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 611 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 611: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 611: 0.2500030658593942 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500030601844504 [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 613 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 613: t_compute_gradients: 3 ms [INFO] [stdout] cost across training set after epoch 613: 0.2500030545219937 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000304887198044 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 7 ms [INFO] [stdout] cost across training set after epoch 615: 0.2500030432343676 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 616: 0.25000303760911197 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 0.2500030319961708 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500030263955014 [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 619 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 619: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 619: 0.2500030208070614 [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 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: 0.2500030152308085 [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 621 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 621: t_compute_gradients: 6 ms [INFO] [stdout] cost across training set after epoch 621: 0.25000300966670064 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 9 ms [INFO] [stdout] cost across training set after epoch 622: 0.25000300411469584 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000299857475256 [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 624 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 624: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 624: 0.2500029930468293 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 0.25000298753088473 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 0.25000298202687776 [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 627 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 627: t_compute_gradients: 4 ms [INFO] [stdout] cost across training set after epoch 627: 0.25000297653476744 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000297105451297 [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 629 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 629: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 629: 0.2500029655860739 [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 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: 0.25000296012940976 [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 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: 0.2500029546844804 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 632: 0.25000294925124594 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000294382966626 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000293841970195 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 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: 4 ms [INFO] [stdout] cost across training set after epoch 635: 0.2500029330213135 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 636: 0.2500029276344615 [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 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: 0.250002922259107 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 638: 0.2500029168952109 [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 639 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 639: t_compute_gradients: 4 ms [INFO] [stdout] cost across training set after epoch 639: 0.2500029115427345 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 640: 0.25000290620163923 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.2500029008718866 [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 642 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 642: t_compute_gradients: 2 ms [INFO] [stdout] cost across training set after epoch 642: 0.2500028955534383 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 0.25000289024625644 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [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: 1 ms [INFO] [stdout] cost across training set after epoch 644: 0.25000288495030293 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 5 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: 1 ms [INFO] [stdout] cost across training set after epoch 645: 0.2500028796655402 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms [INFO] [stdout] finished ff for all training points - epoch 646 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 646: t_compute_gradients: 0 ms [INFO] [stdout] cost across training set after epoch 646: 0.2500028743919306 [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 647 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 647: t_compute_gradients: 0 ms [INFO] [stdout] cost across training set after epoch 647: 0.25000286912943653 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms [INFO] [stdout] finished ff for all training points - epoch 648 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 648: t_compute_gradients: 0 ms [INFO] [stdout] cost across training set after epoch 648: 0.250002863878021 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms [INFO] [stdout] finished ff for all training points - epoch 649 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 649: t_compute_gradients: 0 ms [INFO] [stdout] cost across training set after epoch 649: 0.2500028586376467 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms [INFO] [stdout] finished ff for all training points - epoch 650 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 650: t_compute_gradients: 0 ms [INFO] [stdout] cost across training set after epoch 650: 0.250002853408277 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms [INFO] [stdout] finished ff for all training points - epoch 651 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 651: t_compute_gradients: 0 ms [INFO] [stdout] cost across training set after epoch 651: 0.25000284818987495 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms [INFO] [stdout] finished ff for all training points - epoch 652 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 652: t_compute_gradients: 0 ms [INFO] [stdout] cost across training set after epoch 652: 0.250002842982404 [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 653 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 653: t_compute_gradients: 0 ms [INFO] [stdout] cost across training set after epoch 653: 0.2500028377858277 [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 654 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 654: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 654: 0.2500028326001098 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 0 ms [INFO] [stdout] finished ff for all training points - epoch 655 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 655: t_compute_gradients: 0 ms [INFO] [stdout] cost across training set after epoch 655: 0.2500028274252141 [INFO] [stdout] [INFO] [stdout] starting mini batch from 0 to 20 [INFO] [stdout] t_mini_batch_ff (all data points): t_mini_batch_ff: 6 ms [INFO] [stdout] finished ff for all training points - epoch 656 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 656: t_compute_gradients: 1 ms [INFO] [stdout] cost across training set after epoch 656: 0.25000282226110493 [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 657 [INFO] [stdout] computing gradients... [INFO] [stdout] t_compute_gradients epoch 657: t_compute_gradients: 0 ms [INFO] [stdout] cost across training set after epoch 657: 0.25000281710774613 [INFO] [stdout] [WARN] too many lines in the log, truncating it