train.log
Browse files
train.log
CHANGED
|
@@ -450,3 +450,21 @@
|
|
| 450 |
[14:20:59] val/lichess_opening hard_ce=1.4106 soft_ce=1.4106 soft_temp_ce=1.4106 teacher_entropy=0.0000 teacher_kl=1.4106 wdl_ce=1.0339 value_rows=8192.0000
|
| 451 |
[14:21:21] step 6825/8000 | loss=1.7487 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3603600/0/0 q=0 p=0 | 514 pos/s | vram=35.72GB
|
| 452 |
[14:21:43] step 6850/8000 | loss=1.7582 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3616800/0/0 q=0 p=0 | 515 pos/s | vram=35.72GB
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 450 |
[14:20:59] val/lichess_opening hard_ce=1.4106 soft_ce=1.4106 soft_temp_ce=1.4106 teacher_entropy=0.0000 teacher_kl=1.4106 wdl_ce=1.0339 value_rows=8192.0000
|
| 451 |
[14:21:21] step 6825/8000 | loss=1.7487 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3603600/0/0 q=0 p=0 | 514 pos/s | vram=35.72GB
|
| 452 |
[14:21:43] step 6850/8000 | loss=1.7582 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3616800/0/0 q=0 p=0 | 515 pos/s | vram=35.72GB
|
| 453 |
+
[14:22:05] step 6875/8000 | loss=1.7540 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3630000/0/0 q=0 p=0 | 515 pos/s | vram=35.72GB
|
| 454 |
+
[14:22:27] step 6900/8000 | loss=1.7415 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3643200/0/0 q=0 p=0 | 515 pos/s | vram=35.72GB
|
| 455 |
+
[14:22:28] ckpt step_006900.pt + latest.pt (live) steps=6900 status=mid kind=full
|
| 456 |
+
[14:22:37] val/lichess_opening hard_ce=1.4189 soft_ce=1.4189 soft_temp_ce=1.4189 teacher_entropy=0.0000 teacher_kl=1.4189 wdl_ce=1.0341 value_rows=8192.0000
|
| 457 |
+
[14:22:59] step 6925/8000 | loss=1.7624 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3656400/0/0 q=0 p=0 | 515 pos/s | vram=35.72GB
|
| 458 |
+
[14:23:22] step 6950/8000 | loss=1.7436 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3669600/0/0 q=0 p=0 | 515 pos/s | vram=35.72GB
|
| 459 |
+
[14:23:44] step 6975/8000 | loss=1.7382 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=3682800/0/0 q=0 p=0 | 515 pos/s | vram=35.72GB
|
| 460 |
+
[14:24:05] step 7000/8000 | loss=1.7473 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3696000/0/0 q=0 p=0 | 516 pos/s | vram=35.72GB
|
| 461 |
+
[14:24:14] val/lichess_opening hard_ce=1.4145 soft_ce=1.4145 soft_temp_ce=1.4145 teacher_entropy=0.0000 teacher_kl=1.4145 wdl_ce=1.0337 value_rows=8192.0000
|
| 462 |
+
[14:24:36] step 7025/8000 | loss=1.7552 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3709200/0/0 q=0 p=0 | 515 pos/s | vram=35.72GB
|
| 463 |
+
[14:24:58] step 7050/8000 | loss=1.7439 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3722400/0/0 q=0 p=0 | 515 pos/s | vram=35.72GB
|
| 464 |
+
[14:24:59] ckpt latest.pt (live weights) steps=7050 status=mid
|
| 465 |
+
[14:25:20] step 7075/8000 | loss=1.7450 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3735600/0/0 q=0 p=0 | 516 pos/s | vram=35.72GB
|
| 466 |
+
[14:25:42] step 7100/8000 | loss=1.7615 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3748800/0/0 q=0 p=0 | 516 pos/s | vram=35.72GB
|
| 467 |
+
[14:25:51] val/lichess_opening hard_ce=1.4111 soft_ce=1.4111 soft_temp_ce=1.4111 teacher_entropy=0.0000 teacher_kl=1.4111 wdl_ce=1.0360 value_rows=8192.0000
|
| 468 |
+
[14:26:13] step 7125/8000 | loss=1.7525 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3762000/0/0 q=0 p=0 | 516 pos/s | vram=35.72GB
|
| 469 |
+
[14:26:35] step 7150/8000 | loss=1.7465 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3775200/0/0 q=0 p=0 | 516 pos/s | vram=35.72GB
|
| 470 |
+
[14:26:57] step 7175/8000 | loss=1.7664 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3788400/0/0 q=0 p=0 | 516 pos/s | vram=35.72GB
|