train.log
Browse files
train.log
CHANGED
|
@@ -264,3 +264,22 @@
|
|
| 264 |
[13:27:53] step 3525/8000 | loss=1.7866 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1861200/0/0 q=0 p=0 | 490 pos/s | vram=35.72GB
|
| 265 |
[13:28:14] step 3550/8000 | loss=1.7845 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1874400/0/0 q=0 p=0 | 491 pos/s | vram=35.72GB
|
| 266 |
[13:28:36] step 3575/8000 | loss=1.7818 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=1887600/0/0 q=0 p=0 | 492 pos/s | vram=35.72GB
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 264 |
[13:27:53] step 3525/8000 | loss=1.7866 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1861200/0/0 q=0 p=0 | 490 pos/s | vram=35.72GB
|
| 265 |
[13:28:14] step 3550/8000 | loss=1.7845 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1874400/0/0 q=0 p=0 | 491 pos/s | vram=35.72GB
|
| 266 |
[13:28:36] step 3575/8000 | loss=1.7818 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=1887600/0/0 q=0 p=0 | 492 pos/s | vram=35.72GB
|
| 267 |
+
[13:28:58] step 3600/8000 | loss=1.7874 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1900800/0/0 q=0 p=0 | 492 pos/s | vram=35.72GB
|
| 268 |
+
[13:28:59] ckpt step_003600.pt + latest.pt (live) steps=3600 status=mid kind=full
|
| 269 |
+
[13:29:08] val/lichess_opening hard_ce=1.4566 soft_ce=1.4566 soft_temp_ce=1.4566 teacher_entropy=0.0000 teacher_kl=1.4566 wdl_ce=1.0392 value_rows=8192.0000
|
| 270 |
+
[13:29:30] step 3625/8000 | loss=1.7970 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1914000/0/0 q=0 p=0 | 492 pos/s | vram=35.72GB
|
| 271 |
+
[13:29:52] step 3650/8000 | loss=1.7853 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1927200/0/0 q=0 p=0 | 492 pos/s | vram=35.72GB
|
| 272 |
+
[13:30:14] step 3675/8000 | loss=1.8039 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=1940400/0/0 q=0 p=0 | 493 pos/s | vram=35.72GB
|
| 273 |
+
[13:30:36] step 3700/8000 | loss=1.8013 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1953600/0/0 q=0 p=0 | 493 pos/s | vram=35.72GB
|
| 274 |
+
[13:30:45] val/lichess_opening hard_ce=1.4547 soft_ce=1.4547 soft_temp_ce=1.4547 teacher_entropy=0.0000 teacher_kl=1.4547 wdl_ce=1.0359 value_rows=8192.0000
|
| 275 |
+
[13:31:07] step 3725/8000 | loss=1.7716 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=1966800/0/0 q=0 p=0 | 493 pos/s | vram=35.72GB
|
| 276 |
+
[13:31:29] step 3750/8000 | loss=1.7964 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1980000/0/0 q=0 p=0 | 494 pos/s | vram=35.72GB
|
| 277 |
+
[13:31:29] ckpt latest.pt (live weights) steps=3750 status=mid
|
| 278 |
+
[13:31:51] step 3775/8000 | loss=1.7593 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1993200/0/0 q=0 p=0 | 494 pos/s | vram=35.72GB
|
| 279 |
+
[13:32:13] step 3800/8000 | loss=1.7902 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=2006400/0/0 q=0 p=0 | 495 pos/s | vram=35.72GB
|
| 280 |
+
[13:32:22] val/lichess_opening hard_ce=1.4431 soft_ce=1.4431 soft_temp_ce=1.4431 teacher_entropy=0.0000 teacher_kl=1.4431 wdl_ce=1.0360 value_rows=8192.0000
|
| 281 |
+
[13:32:44] step 3825/8000 | loss=1.7923 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2019600/0/0 q=0 p=0 | 494 pos/s | vram=35.72GB
|
| 282 |
+
[13:33:06] step 3850/8000 | loss=1.7947 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2032800/0/0 q=0 p=0 | 495 pos/s | vram=35.72GB
|
| 283 |
+
[13:33:27] step 3875/8000 | loss=1.7631 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2046000/0/0 q=0 p=0 | 495 pos/s | vram=35.72GB
|
| 284 |
+
[13:33:49] step 3900/8000 | loss=1.7928 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2059200/0/0 q=0 p=0 | 496 pos/s | vram=35.72GB
|
| 285 |
+
[13:33:50] ckpt step_003900.pt + latest.pt (live) steps=3900 status=mid kind=full
|