1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
|
#!/usr/bin/env python3
"""Phase A training loop: local CPU, PyTorch, over the cached CSR
tensors build_training_tensors.py produces. Goal is pipeline/
framework validation (per NNUE.md) -- prove the data loader, model,
loss, and checkpointing work end-to-end and get fast local iteration
when something breaks, not to produce the best possible net. The
real, larger Phase B run moves to a rented GPU against more data.
CSR batching: each position is a variable-length "bag" of feature
indices (3-32 of them). To build a batch for nn.EmbeddingBag without
padding, gather the relevant CSR row-slices for a batch of position
indices, concatenate them, and recompute offsets -- see
_gather_batch() below.
Usage:
python3 nnue_train.py \
--train-dir runs/sd10_twic_2M/tensors_train \
--holdout-dir runs/sd10_twic_2M/tensors_holdout \
--outdir runs/sd10_twic_2M/nnue_ckpt \
--epochs 20 --batch-size 8192 --threads 8
"""
import argparse
import json
import time
from pathlib import Path
import numpy as np
import torch
import torch.nn as nn
from nnue_model import NnueNet, DEFAULT_K
class CsrTensors:
"""mmap-backed CSR feature tensors for one split (train or
holdout), as written by build_training_tensors.py."""
def __init__(self, tensor_dir):
tensor_dir = Path(tensor_dir)
self.white_idx = np.load(tensor_dir / "white_idx.npy", mmap_mode="r")
self.white_off = np.load(tensor_dir / "white_off.npy")
self.black_idx = np.load(tensor_dir / "black_idx.npy", mmap_mode="r")
self.black_off = np.load(tensor_dir / "black_off.npy")
self.stm = np.load(tensor_dir / "stm.npy")
self.target = np.load(tensor_dir / "target.npy")
self.n = len(self.target)
assert len(self.white_off) == self.n + 1
assert len(self.black_off) == self.n + 1
assert len(self.stm) == self.n
def __len__(self):
return self.n
def _gather_batch(idx_arr, off_arr, row_ids):
"""Build (flat_idx, batch_offsets) for an nn.EmbeddingBag call
covering exactly the bags named by row_ids (a 1D array of row
indices into off_arr). row_ids need not be sorted or contiguous."""
pieces = []
batch_off = np.empty(len(row_ids), dtype=np.int64)
cursor = 0
for i, r in enumerate(row_ids):
start, end = off_arr[r], off_arr[r + 1]
pieces.append(idx_arr[start:end])
batch_off[i] = cursor
cursor += end - start
flat = np.concatenate(pieces) if pieces else np.empty(0, dtype=np.int32)
return flat, batch_off
def iterate_batches(data: CsrTensors, batch_size, shuffle, rng):
order = rng.permutation(data.n) if shuffle else np.arange(data.n)
for start in range(0, data.n, batch_size):
rows = order[start:start + batch_size]
rows_sorted = np.sort(rows) # sequential mmap reads, not required but friendlier
w_idx, w_off = _gather_batch(data.white_idx, data.white_off, rows_sorted)
b_idx, b_off = _gather_batch(data.black_idx, data.black_off, rows_sorted)
stm = data.stm[rows_sorted]
target = data.target[rows_sorted]
yield (
torch.from_numpy(w_idx.astype(np.int64, copy=False)),
torch.from_numpy(w_off),
torch.from_numpy(b_idx.astype(np.int64, copy=False)),
torch.from_numpy(b_off),
torch.from_numpy(stm.astype(np.int64, copy=False)),
torch.from_numpy(target.copy()),
)
def evaluate(model, data, batch_size, k):
model.eval()
total_loss = 0.0
total_n = 0
rng = np.random.default_rng(0)
with torch.no_grad():
for w_idx, w_off, b_idx, b_off, stm, target in iterate_batches(
data, batch_size, shuffle=False, rng=rng):
pred = model.win_probability(w_idx, w_off, b_idx, b_off, stm, k=k)
loss = nn.functional.mse_loss(pred, target, reduction="sum")
total_loss += loss.item()
total_n += len(target)
model.train()
return total_loss / max(total_n, 1)
def main():
ap = argparse.ArgumentParser(description=__doc__)
ap.add_argument("--train-dir", required=True)
ap.add_argument("--holdout-dir", required=True)
ap.add_argument("--outdir", required=True)
ap.add_argument("--epochs", type=int, default=20)
ap.add_argument("--batch-size", type=int, default=8192)
ap.add_argument("--lr", type=float, default=1e-3)
ap.add_argument("--k", type=float, default=DEFAULT_K)
ap.add_argument("--threads", type=int, default=8,
help="torch CPU thread count -- kept modest by default "
"since this is a shared multi-user box")
ap.add_argument("--eval-every-steps", type=int, default=2000)
ap.add_argument("--resume", default=None,
help="checkpoint .pt to resume from")
ap.add_argument("--seed", type=int, default=0)
args = ap.parse_args()
torch.set_num_threads(args.threads)
torch.manual_seed(args.seed)
outdir = Path(args.outdir)
outdir.mkdir(parents=True, exist_ok=True)
log_path = outdir / "train_log.jsonl"
print("Loading tensors ...")
train_data = CsrTensors(args.train_dir)
holdout_data = CsrTensors(args.holdout_dir)
print(f" train: {len(train_data)} positions, holdout: {len(holdout_data)} positions")
model = NnueNet()
optimizer = torch.optim.Adam(model.parameters(), lr=args.lr)
start_epoch = 0
global_step = 0
if args.resume:
ckpt = torch.load(args.resume, map_location="cpu", weights_only=True)
model.load_state_dict(ckpt["model"])
optimizer.load_state_dict(ckpt["optimizer"])
start_epoch = ckpt["epoch"] + 1
global_step = ckpt.get("global_step", 0)
print(f"Resumed from {args.resume} at epoch {start_epoch}")
rng = np.random.default_rng(args.seed)
t_start = time.time()
with open(log_path, "a") as log_f:
for epoch in range(start_epoch, args.epochs):
epoch_loss = 0.0
epoch_n = 0
t_epoch = time.time()
for w_idx, w_off, b_idx, b_off, stm, target in iterate_batches(
train_data, args.batch_size, shuffle=True, rng=rng):
optimizer.zero_grad()
pred = model.win_probability(w_idx, w_off, b_idx, b_off, stm, k=args.k)
loss = nn.functional.mse_loss(pred, target)
loss.backward()
optimizer.step()
bs = len(target)
epoch_loss += loss.item() * bs
epoch_n += bs
global_step += 1
if global_step % args.eval_every_steps == 0:
holdout_mse = evaluate(model, holdout_data, args.batch_size, args.k)
elapsed = time.time() - t_start
rec = {
"step": global_step, "epoch": epoch,
"train_mse_running": epoch_loss / max(epoch_n, 1),
"holdout_mse": holdout_mse,
"elapsed_s": round(elapsed, 1),
"positions_seen": epoch_n + epoch * len(train_data),
}
print(f" step {global_step} epoch {epoch} "
f"train_mse={rec['train_mse_running']:.5f} "
f"holdout_mse={holdout_mse:.5f} "
f"elapsed={elapsed:.0f}s")
log_f.write(json.dumps(rec) + "\n")
log_f.flush()
holdout_mse = evaluate(model, holdout_data, args.batch_size, args.k)
epoch_elapsed = time.time() - t_epoch
print(f"Epoch {epoch} done: train_mse={epoch_loss / max(epoch_n, 1):.5f} "
f"holdout_mse={holdout_mse:.5f} ({epoch_elapsed:.0f}s)")
ckpt_path = outdir / f"ckpt_epoch{epoch:03d}.pt"
torch.save({
"model": model.state_dict(),
"optimizer": optimizer.state_dict(),
"epoch": epoch,
"global_step": global_step,
"holdout_mse": holdout_mse,
"args": vars(args),
}, ckpt_path)
print(f" wrote {ckpt_path}")
print(f"Training done in {time.time() - t_start:.0f}s")
if __name__ == "__main__":
main()
|
