train.log
Browse files
train.log
CHANGED
|
@@ -131,3 +131,14 @@
|
|
| 131 |
[12:49:44] val/lichess_opening hard_ce=1.4953 soft_ce=1.4953 soft_temp_ce=1.4953 teacher_entropy=0.0000 teacher_kl=1.4953 wdl_ce=1.0386 value_rows=8192.0000
|
| 132 |
[12:50:06] step 1225/8000 | loss=1.8407 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=646800/0/0 q=0 p=0 | 423 pos/s | vram=35.72GB
|
| 133 |
[12:50:23] soft inbox +560,000 train_n=25,205,305 shards=shard_000312,shard_000313,shard_000314,shard_000315,shard_000316,shard_000317,shard_000318
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 131 |
[12:49:44] val/lichess_opening hard_ce=1.4953 soft_ce=1.4953 soft_temp_ce=1.4953 teacher_entropy=0.0000 teacher_kl=1.4953 wdl_ce=1.0386 value_rows=8192.0000
|
| 132 |
[12:50:06] step 1225/8000 | loss=1.8407 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=646800/0/0 q=0 p=0 | 423 pos/s | vram=35.72GB
|
| 133 |
[12:50:23] soft inbox +560,000 train_n=25,205,305 shards=shard_000312,shard_000313,shard_000314,shard_000315,shard_000316,shard_000317,shard_000318
|
| 134 |
+
[12:50:46] step 1250/8000 | loss=1.8180 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=660000/0/0 q=0 p=0 | 421 pos/s | vram=35.72GB
|
| 135 |
+
[12:50:57] soft inbox +559,999 train_n=25,765,304 shards=shard_000319,shard_000320,shard_000321,shard_000322,shard_000323,shard_000324,shard_000325
|
| 136 |
+
[12:51:20] step 1275/8000 | loss=1.8345 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=673200/0/0 q=0 p=0 | 420 pos/s | vram=35.72GB
|
| 137 |
+
[12:51:42] step 1300/8000 | loss=1.8392 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=686400/0/0 q=0 p=0 | 422 pos/s | vram=35.72GB
|
| 138 |
+
[12:51:51] val/lichess_opening hard_ce=1.4945 soft_ce=1.4945 soft_temp_ce=1.4945 teacher_entropy=0.0000 teacher_kl=1.4945 wdl_ce=1.0374 value_rows=8192.0000
|
| 139 |
+
[12:52:13] step 1325/8000 | loss=1.8255 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=699600/0/0 q=0 p=0 | 422 pos/s | vram=35.72GB
|
| 140 |
+
[12:52:35] step 1350/8000 | loss=1.8139 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=712800/0/0 q=0 p=0 | 425 pos/s | vram=35.72GB
|
| 141 |
+
[12:52:35] ckpt latest.pt (live weights) steps=1350 status=mid
|
| 142 |
+
[12:52:57] step 1375/8000 | loss=1.8056 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=726000/0/0 q=0 p=0 | 427 pos/s | vram=35.72GB
|
| 143 |
+
[12:53:19] step 1400/8000 | loss=1.8114 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=739200/0/0 q=0 p=0 | 429 pos/s | vram=35.72GB
|
| 144 |
+
[12:53:27] val/lichess_opening hard_ce=1.4921 soft_ce=1.4921 soft_temp_ce=1.4921 teacher_entropy=0.0000 teacher_kl=1.4921 wdl_ce=1.0371 value_rows=8192.0000
|