train.log
Browse files
train.log
CHANGED
|
@@ -253,3 +253,14 @@
|
|
| 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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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
|
| 256 |
+
[13:25:44] step 3400/8000 | loss=1.7901 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1795200/0/0 q=0 p=0 | 490 pos/s | vram=35.72GB
|
| 257 |
+
[13:25:53] val/lichess_opening hard_ce=1.4548 soft_ce=1.4548 soft_temp_ce=1.4548 teacher_entropy=0.0000 teacher_kl=1.4548 wdl_ce=1.0352 value_rows=8192.0000
|
| 258 |
+
[13:26:15] step 3425/8000 | loss=1.7821 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1808400/0/0 q=0 p=0 | 489 pos/s | vram=35.72GB
|
| 259 |
+
[13:26:37] step 3450/8000 | loss=1.8052 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=1821600/0/0 q=0 p=0 | 490 pos/s | vram=35.72GB
|
| 260 |
+
[13:26:38] ckpt latest.pt (live weights) steps=3450 status=mid
|
| 261 |
+
[13:27:00] step 3475/8000 | loss=1.7864 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1834800/0/0 q=0 p=0 | 490 pos/s | vram=35.72GB
|
| 262 |
+
[13:27:22] step 3500/8000 | loss=1.8019 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1848000/0/0 q=0 p=0 | 491 pos/s | vram=35.72GB
|
| 263 |
+
[13:27:30] val/lichess_opening hard_ce=1.4505 soft_ce=1.4505 soft_temp_ce=1.4505 teacher_entropy=0.0000 teacher_kl=1.4505 wdl_ce=1.0352 value_rows=8192.0000
|
| 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
|