train.log
Browse files
train.log
CHANGED
|
@@ -293,3 +293,22 @@
|
|
| 293 |
[13:36:19] step 4050/8000 | loss=1.7761 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2138400/0/0 q=0 p=0 | 497 pos/s | vram=35.72GB
|
| 294 |
[13:36:20] ckpt latest.pt (live weights) steps=4050 status=mid
|
| 295 |
[13:36:42] step 4075/8000 | loss=1.7829 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=2151600/0/0 q=0 p=0 | 497 pos/s | vram=35.72GB
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 293 |
[13:36:19] step 4050/8000 | loss=1.7761 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2138400/0/0 q=0 p=0 | 497 pos/s | vram=35.72GB
|
| 294 |
[13:36:20] ckpt latest.pt (live weights) steps=4050 status=mid
|
| 295 |
[13:36:42] step 4075/8000 | loss=1.7829 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=2151600/0/0 q=0 p=0 | 497 pos/s | vram=35.72GB
|
| 296 |
+
[13:37:04] step 4100/8000 | loss=1.7856 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2164800/0/0 q=0 p=0 | 498 pos/s | vram=35.72GB
|
| 297 |
+
[13:37:13] val/lichess_opening hard_ce=1.4424 soft_ce=1.4424 soft_temp_ce=1.4424 teacher_entropy=0.0000 teacher_kl=1.4424 wdl_ce=1.0365 value_rows=8192.0000
|
| 298 |
+
[13:37:34] step 4125/8000 | loss=1.7784 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2178000/0/0 q=0 p=0 | 498 pos/s | vram=35.72GB
|
| 299 |
+
[13:37:56] step 4150/8000 | loss=1.7789 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2191200/0/0 q=0 p=0 | 498 pos/s | vram=35.72GB
|
| 300 |
+
[13:38:18] step 4175/8000 | loss=1.7948 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2204400/0/0 q=0 p=0 | 499 pos/s | vram=35.72GB
|
| 301 |
+
[13:38:40] step 4200/8000 | loss=1.7830 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2217600/0/0 q=0 p=0 | 499 pos/s | vram=35.72GB
|
| 302 |
+
[13:38:41] ckpt step_004200.pt + latest.pt (live) steps=4200 status=mid kind=full
|
| 303 |
+
[13:38:50] val/lichess_opening hard_ce=1.4478 soft_ce=1.4478 soft_temp_ce=1.4478 teacher_entropy=0.0000 teacher_kl=1.4478 wdl_ce=1.0391 value_rows=8192.0000
|
| 304 |
+
[13:39:12] step 4225/8000 | loss=1.7733 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=2230800/0/0 q=0 p=0 | 499 pos/s | vram=35.72GB
|
| 305 |
+
[13:39:34] step 4250/8000 | loss=1.7692 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2244000/0/0 q=0 p=0 | 499 pos/s | vram=35.72GB
|
| 306 |
+
[13:39:56] step 4275/8000 | loss=1.7878 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2257200/0/0 q=0 p=0 | 499 pos/s | vram=35.72GB
|
| 307 |
+
[13:40:18] step 4300/8000 | loss=1.7847 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=2270400/0/0 q=0 p=0 | 500 pos/s | vram=35.72GB
|
| 308 |
+
[13:40:27] val/lichess_opening hard_ce=1.4463 soft_ce=1.4463 soft_temp_ce=1.4463 teacher_entropy=0.0000 teacher_kl=1.4463 wdl_ce=1.0355 value_rows=8192.0000
|
| 309 |
+
[13:40:49] step 4325/8000 | loss=1.7852 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2283600/0/0 q=0 p=0 | 499 pos/s | vram=35.72GB
|
| 310 |
+
[13:41:11] step 4350/8000 | loss=1.7755 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2296800/0/0 q=0 p=0 | 500 pos/s | vram=35.72GB
|
| 311 |
+
[13:41:11] ckpt latest.pt (live weights) steps=4350 status=mid
|
| 312 |
+
[13:41:33] step 4375/8000 | loss=1.7857 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2310000/0/0 q=0 p=0 | 500 pos/s | vram=35.72GB
|
| 313 |
+
[13:41:55] step 4400/8000 | loss=1.7754 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2323200/0/0 q=0 p=0 | 501 pos/s | vram=35.72GB
|
| 314 |
+
[13:42:04] val/lichess_opening hard_ce=1.4428 soft_ce=1.4428 soft_temp_ce=1.4428 teacher_entropy=0.0000 teacher_kl=1.4428 wdl_ce=1.0377 value_rows=8192.0000
|