diff options
Diffstat (limited to 'src/train.rs')
| -rw-r--r-- | src/train.rs | 64 |
1 files changed, 34 insertions, 30 deletions
diff --git a/src/train.rs b/src/train.rs index 1e68080..35f8fdd 100644 --- a/src/train.rs +++ b/src/train.rs @@ -1,4 +1,6 @@ -use std::{collections::VecDeque, fs, path::{Path, PathBuf}, sync::atomic::{AtomicUsize, Ordering}, time::{Duration, Instant}}; +use std::{collections::VecDeque, fs, path::{Path, PathBuf}, time::{Duration, Instant}}; + +use rayon::prelude::*; use crate::{board::{repetitions, GameBoard, Move, Outcome, Turn, REPETITION_DRAW, SYMMETRIES}, claude_player::ClaudePlayer, network::{Adam, Network, Rng, Sample}, neural_player::NeuralPlayer, player::{MinimaxPlayer, Player}}; @@ -29,8 +31,11 @@ pub struct Config pub epochs: usize, pub batch_size: usize, pub learning_rate: f32, - /// Games against `ClaudePlayer`, and against the previous generation, after each generation (half as each side). + /// Games against `ClaudePlayer`, and against the generation that last played these matches (half as each side). pub match_games: usize, + /// Play those matches only on generations whose number is a multiple of this, so generation + /// N plays generation N - `match_every`. + pub match_every: usize, } impl Default for Config @@ -54,6 +59,7 @@ impl Default for Config batch_size: 256, learning_rate: 1e-3, match_games: 100, + match_every: 10, } } } @@ -128,27 +134,7 @@ fn td_targets(plies: &[Ply], outcome: Outcome, lambda: f32) -> Vec<f32> /// Runs `f(0..n)` across all cores, returning the results in order. fn parallel<T: Send>(n: usize, f: impl Fn(usize) -> T + Sync) -> Vec<T> { - let threads = std::thread::available_parallelism().map_or(1, |n| n.get()).min(n.max(1)); - let next = AtomicUsize::new(0); - let mut results: Vec<(usize, T)> = std::thread::scope(|s| - { - let handles: Vec<_> = (0..threads).map(|_| s.spawn(|| - { - let mut done = Vec::new(); - loop - { - let i = next.fetch_add(1, Ordering::Relaxed); - if i >= n - { - return done; - } - done.push((i, f(i))); - } - })).collect(); - handles.into_iter().flat_map(|h| h.join().expect("worker thread panicked")).collect() - }); - results.sort_by_key(|(i, _)| *i); - results.into_iter().map(|(_, r)| r).collect() + (0..n).into_par_iter().map(&f).collect() } /// A player that searches exactly `depth` plies. @@ -270,13 +256,15 @@ pub fn run(cfg: &Config) -> std::io::Result<()> } None => Network::random(0x5EED), }; + // The opponent for the first matches, if the generation they should be against isn't saved + let initial = net.clone(); let mut adam = Adam::new(cfg.learning_rate); // For each generation, its positions from tiger-win, sheep-win and drawn games let mut buffer: VecDeque<[Vec<Sample>; 3]> = VecDeque::new(); let mut rng = Rng::new(first as u64); println!("Self-play results, then the mean error on positions from tiger-win (T) and sheep-win (S) games, before and after training"); - println!("{:>4} {:>7} {:>6} {:>6} {:>6} {:>8} {:>8} {:>8} {:>8} {:>7} {:>9} {:>7}", - "gen", "trained", "tigers", "sheep", "draws", "T before", "S before", "T after", "S after", "vs prev", "vs Claude", "time s"); + println!("{:>4} {:>7} {:>6} {:>6} {:>6} {:>8} {:>8} {:>8} {:>8} {:>7} {:>9} {:>7} {:>7}", + "gen", "trained", "tigers", "sheep", "draws", "T before", "S before", "T after", "S after", "vs prev", "vs Claude", "train s", "time s"); for generation in first..first + cfg.generations { let start = Instant::now(); @@ -290,10 +278,11 @@ pub fn run(cfg: &Config) -> std::io::Result<()> buffer.pop_front(); } + // Training: the losses before and after, and every epoch + let train_start = Instant::now(); let pools: [Vec<Sample>; 3] = [0, 1, 2].map(|k| buffer.iter().flat_map(|g| &g[k]).copied().collect()); let losses = |net: &Network| (net.loss(&pools[0]), net.loss(&pools[1])); let before = losses(&net); - let previous = net.clone(); let mut trained = 0; for _ in 0..cfg.epochs { @@ -314,13 +303,28 @@ pub fn run(cfg: &Config) -> std::io::Result<()> } } let after = losses(&net); + let train_time = train_start.elapsed(); - let vs_prev = match_score(&net, || neural(&previous, cfg.depth), cfg, seed_base ^ 0xA); - let vs_claude = match_score(&net, || claude(cfg.depth), cfg, seed_base ^ 0xB); + // The matches are slow and only measure progress, so they are only played now and then + let every = cfg.match_every.max(1); + let (vs_prev, vs_claude) = if generation.is_multiple_of(every) + { + // Against the generation that last played them, read back from its file, so a rerun + // that carries on from the out dir still finds it + let last = cfg.out_dir.join(format!("gen-{:03}.bin", generation - every)); + let previous = Network::load(&last).unwrap_or_else(|_| initial.clone()); + let percent = |score: f32| format!("{:.0}%", score * 100.0); + (percent(match_score(&net, || neural(&previous, cfg.depth), cfg, seed_base ^ 0xA)), + percent(match_score(&net, || claude(cfg.depth), cfg, seed_base ^ 0xB))) + } + else + { + ("-".to_string(), "-".to_string()) + }; net.save(&cfg.out_dir.join(format!("gen-{generation:03}.bin")))?; net.save(&cfg.out_dir.join("latest.bin"))?; - println!("{generation:>4} {trained:>7} {tigers:>6} {sheep:>6} {draws:>6} {:>8.4} {:>8.4} {:>8.4} {:>8.4} {:>6.0}% {:>8.0}% {:>7.1}", - before.0, before.1, after.0, after.1, vs_prev * 100.0, vs_claude * 100.0, start.elapsed().as_secs_f64()); + println!("{generation:>4} {trained:>7} {tigers:>6} {sheep:>6} {draws:>6} {:>8.4} {:>8.4} {:>8.4} {:>8.4} {vs_prev:>7} {vs_claude:>9} {:>7.2} {:>7.1}", + before.0, before.1, after.0, after.1, train_time.as_secs_f64(), start.elapsed().as_secs_f64()); } Ok(()) } |