train.log
Browse files
train.log
CHANGED
|
@@ -235,3 +235,21 @@
|
|
| 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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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
|
| 238 |
+
[13:20:27] step 3075/8000 | loss=1.8096 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1623600/0/0 q=0 p=0 | 485 pos/s | vram=35.72GB
|
| 239 |
+
[13:20:49] step 3100/8000 | loss=1.8034 | lr=2.00e-03,3.00e-05 | clip=4/25 | mix s/d/b=1636800/0/0 q=0 p=0 | 485 pos/s | vram=35.72GB
|
| 240 |
+
[13:20:57] val/lichess_opening hard_ce=1.4582 soft_ce=1.4582 soft_temp_ce=1.4582 teacher_entropy=0.0000 teacher_kl=1.4582 wdl_ce=1.0367 value_rows=8192.0000
|
| 241 |
+
[13:21:19] step 3125/8000 | loss=1.7859 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1650000/0/0 q=0 p=0 | 485 pos/s | vram=35.72GB
|
| 242 |
+
[13:21:42] step 3150/8000 | loss=1.8136 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=1663200/0/0 q=0 p=0 | 486 pos/s | vram=35.72GB
|
| 243 |
+
[13:21:42] ckpt latest.pt (live weights) steps=3150 status=mid
|
| 244 |
+
[13:22:05] step 3175/8000 | loss=1.7987 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1676400/0/0 q=0 p=0 | 486 pos/s | vram=35.72GB
|
| 245 |
+
[13:22:27] step 3200/8000 | loss=1.7957 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1689600/0/0 q=0 p=0 | 487 pos/s | vram=35.72GB
|
| 246 |
+
[13:22:35] val/lichess_opening hard_ce=1.4645 soft_ce=1.4645 soft_temp_ce=1.4645 teacher_entropy=0.0000 teacher_kl=1.4645 wdl_ce=1.0359 value_rows=8192.0000
|
| 247 |
+
[13:22:58] step 3225/8000 | loss=1.7882 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1702800/0/0 q=0 p=0 | 486 pos/s | vram=35.72GB
|
| 248 |
+
[13:23:20] step 3250/8000 | loss=1.7820 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=1716000/0/0 q=0 p=0 | 487 pos/s | vram=35.72GB
|
| 249 |
+
[13:23:42] step 3275/8000 | loss=1.7642 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1729200/0/0 q=0 p=0 | 488 pos/s | vram=35.72GB
|
| 250 |
+
[13:24:04] step 3300/8000 | loss=1.7713 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=1742400/0/0 q=0 p=0 | 488 pos/s | vram=35.72GB
|
| 251 |
+
[13:24:05] ckpt step_003300.pt + latest.pt (live) steps=3300 status=mid kind=full
|
| 252 |
+
[13:24:14] val/lichess_opening hard_ce=1.4583 soft_ce=1.4583 soft_temp_ce=1.4583 teacher_entropy=0.0000 teacher_kl=1.4583 wdl_ce=1.0351 value_rows=8192.0000
|
| 253 |
+
[13:24:36] step 3325/8000 | loss=1.8060 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1755600/0/0 q=0 p=0 | 488 pos/s | vram=35.72GB
|
| 254 |
+
[13:24:58] step 3350/8000 | loss=1.7849 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1768800/0/0 q=0 p=0 | 488 pos/s | vram=35.72GB
|
| 255 |
+
[13:25:21] step 3375/8000 | loss=1.7986 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1782000/0/0 q=0 p=0 | 489 pos/s | vram=35.72GB
|