train.log
Browse files
train.log
CHANGED
|
@@ -216,3 +216,22 @@
|
|
| 216 |
[13:14:22] step 2700/8000 | loss=1.7898 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1425600/0/0 q=0 p=0 | 478 pos/s | vram=35.72GB
|
| 217 |
[13:14:23] ckpt step_002700.pt + latest.pt (live) steps=2700 status=mid kind=full
|
| 218 |
[13:14:31] val/lichess_opening hard_ce=1.4694 soft_ce=1.4694 soft_temp_ce=1.4694 teacher_entropy=0.0000 teacher_kl=1.4694 wdl_ce=1.0364 value_rows=8192.0000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 216 |
[13:14:22] step 2700/8000 | loss=1.7898 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1425600/0/0 q=0 p=0 | 478 pos/s | vram=35.72GB
|
| 217 |
[13:14:23] ckpt step_002700.pt + latest.pt (live) steps=2700 status=mid kind=full
|
| 218 |
[13:14:31] val/lichess_opening hard_ce=1.4694 soft_ce=1.4694 soft_temp_ce=1.4694 teacher_entropy=0.0000 teacher_kl=1.4694 wdl_ce=1.0364 value_rows=8192.0000
|
| 219 |
+
[13:14:53] step 2725/8000 | loss=1.7951 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1438800/0/0 q=0 p=0 | 477 pos/s | vram=35.72GB
|
| 220 |
+
[13:15:15] step 2750/8000 | loss=1.8133 | lr=2.00e-03,3.00e-05 | clip=4/25 | mix s/d/b=1452000/0/0 q=0 p=0 | 478 pos/s | vram=35.72GB
|
| 221 |
+
[13:15:37] step 2775/8000 | loss=1.7946 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1465200/0/0 q=0 p=0 | 479 pos/s | vram=35.72GB
|
| 222 |
+
[13:16:00] step 2800/8000 | loss=1.7891 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1478400/0/0 q=0 p=0 | 480 pos/s | vram=35.72GB
|
| 223 |
+
[13:16:08] val/lichess_opening hard_ce=1.4588 soft_ce=1.4588 soft_temp_ce=1.4588 teacher_entropy=0.0000 teacher_kl=1.4588 wdl_ce=1.0368 value_rows=8192.0000
|
| 224 |
+
[13:16:30] step 2825/8000 | loss=1.7912 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1491600/0/0 q=0 p=0 | 479 pos/s | vram=35.72GB
|
| 225 |
+
[13:16:52] step 2850/8000 | loss=1.7750 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1504800/0/0 q=0 p=0 | 480 pos/s | vram=35.72GB
|
| 226 |
+
[13:16:52] ckpt latest.pt (live weights) steps=2850 status=mid
|
| 227 |
+
[13:17:14] step 2875/8000 | loss=1.7927 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1518000/0/0 q=0 p=0 | 481 pos/s | vram=35.72GB
|
| 228 |
+
[13:17:36] step 2900/8000 | loss=1.8083 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1531200/0/0 q=0 p=0 | 482 pos/s | vram=35.72GB
|
| 229 |
+
[13:17:45] val/lichess_opening hard_ce=1.4610 soft_ce=1.4610 soft_temp_ce=1.4610 teacher_entropy=0.0000 teacher_kl=1.4610 wdl_ce=1.0380 value_rows=8192.0000
|
| 230 |
+
[13:18:06] step 2925/8000 | loss=1.7936 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=1544400/0/0 q=0 p=0 | 481 pos/s | vram=35.72GB
|
| 231 |
+
[13:18:28] step 2950/8000 | loss=1.7691 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1557600/0/0 q=0 p=0 | 482 pos/s | vram=35.72GB
|
| 232 |
+
[13:18:50] step 2975/8000 | loss=1.7828 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1570800/0/0 q=0 p=0 | 483 pos/s | vram=35.72GB
|
| 233 |
+
[13:19:12] step 3000/8000 | loss=1.7961 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1584000/0/0 q=0 p=0 | 484 pos/s | vram=35.72GB
|
| 234 |
+
[13:19:13] ckpt step_003000.pt + latest.pt (live) steps=3000 status=mid kind=full
|
| 235 |
+
[13:19:21] val/lichess_opening hard_ce=1.4613 soft_ce=1.4613 soft_temp_ce=1.4613 teacher_entropy=0.0000 teacher_kl=1.4613 wdl_ce=1.0367 value_rows=8192.0000
|
| 236 |
+
[13:19:43] step 3025/8000 | loss=1.8004 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1597200/0/0 q=0 p=0 | 483 pos/s | vram=35.72GB
|
| 237 |
+
[13:20:05] step 3050/8000 | loss=1.7827 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=1610400/0/0 q=0 p=0 | 484 pos/s | vram=35.72GB
|