train.log
Browse files
train.log
CHANGED
|
@@ -51,3 +51,18 @@
|
|
| 51 |
[12:31:53] step 400/8000 | loss=1.8309 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=211200/0/0 q=0 p=0 | 484 pos/s | vram=35.72GB
|
| 52 |
[12:31:59] soft inbox +480,000 train_n=9,445,105 shards=shard_000113,shard_000114,shard_000115,shard_000116,shard_000117,shard_000118
|
| 53 |
[12:32:08] val/lichess_opening hard_ce=1.5139 soft_ce=1.5139 soft_temp_ce=1.5139 teacher_entropy=0.0000 teacher_kl=1.5139 wdl_ce=1.0394 value_rows=8192.0000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
[12:31:53] step 400/8000 | loss=1.8309 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=211200/0/0 q=0 p=0 | 484 pos/s | vram=35.72GB
|
| 52 |
[12:31:59] soft inbox +480,000 train_n=9,445,105 shards=shard_000113,shard_000114,shard_000115,shard_000116,shard_000117,shard_000118
|
| 53 |
[12:32:08] val/lichess_opening hard_ce=1.5139 soft_ce=1.5139 soft_temp_ce=1.5139 teacher_entropy=0.0000 teacher_kl=1.5139 wdl_ce=1.0394 value_rows=8192.0000
|
| 54 |
+
[12:32:30] step 425/8000 | loss=1.8258 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=224400/0/0 q=0 p=0 | 474 pos/s | vram=35.72GB
|
| 55 |
+
[12:32:35] soft inbox +549,232 train_n=9,994,337 shards=shard_000119,shard_000120,shard_000121,shard_000122,shard_000123,shard_000124,shard_000125
|
| 56 |
+
[12:32:57] step 450/8000 | loss=1.8129 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=237600/0/0 q=0 p=0 | 475 pos/s | vram=35.72GB
|
| 57 |
+
[12:33:01] soft inbox +400,000 train_n=10,394,337 shards=shard_000126,shard_000127,shard_000128,shard_000129,shard_000130
|
| 58 |
+
[12:33:01] ckpt latest.pt (live weights) steps=450 status=mid
|
| 59 |
+
[12:33:23] step 475/8000 | loss=1.8014 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=250800/0/0 q=0 p=0 | 477 pos/s | vram=35.72GB
|
| 60 |
+
[12:33:27] soft inbox +480,000 train_n=10,874,337 shards=shard_000131,shard_000132,shard_000133,shard_000134,shard_000135,shard_000136
|
| 61 |
+
[12:33:49] step 500/8000 | loss=1.8187 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=264000/0/0 q=0 p=0 | 478 pos/s | vram=35.72GB
|
| 62 |
+
[12:33:54] soft inbox +400,000 train_n=11,274,337 shards=shard_000137,shard_000138,shard_000139,shard_000140,shard_000141
|
| 63 |
+
[12:34:03] val/lichess_opening hard_ce=1.5141 soft_ce=1.5141 soft_temp_ce=1.5141 teacher_entropy=0.0000 teacher_kl=1.5141 wdl_ce=1.0395 value_rows=8192.0000
|
| 64 |
+
[12:34:25] step 525/8000 | loss=1.8187 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=277200/0/0 q=0 p=0 | 471 pos/s | vram=35.72GB
|
| 65 |
+
[12:34:33] soft inbox +560,000 train_n=11,834,337 shards=shard_000142,shard_000143,shard_000144,shard_000145,shard_000146,shard_000147,shard_000148
|
| 66 |
+
[12:34:55] step 550/8000 | loss=1.8243 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=290400/0/0 q=0 p=0 | 470 pos/s | vram=35.72GB
|
| 67 |
+
[12:35:02] soft inbox +480,000 train_n=12,314,337 shards=shard_000149,shard_000150,shard_000151,shard_000152,shard_000153,shard_000154
|
| 68 |
+
[12:35:24] step 575/8000 | loss=1.8222 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=303600/0/0 q=0 p=0 | 469 pos/s | vram=35.72GB
|