train.log
Browse files
train.log
CHANGED
|
@@ -153,3 +153,21 @@
|
|
| 153 |
[12:56:12] step 1575/8000 | loss=1.8137 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=831600/0/0 q=0 p=0 | 439 pos/s | vram=35.72GB
|
| 154 |
[12:56:33] step 1600/8000 | loss=1.8124 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=844800/0/0 q=0 p=0 | 441 pos/s | vram=35.72GB
|
| 155 |
[12:56:42] val/lichess_opening hard_ce=1.4850 soft_ce=1.4850 soft_temp_ce=1.4850 teacher_entropy=0.0000 teacher_kl=1.4850 wdl_ce=1.0377 value_rows=8192.0000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 153 |
[12:56:12] step 1575/8000 | loss=1.8137 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=831600/0/0 q=0 p=0 | 439 pos/s | vram=35.72GB
|
| 154 |
[12:56:33] step 1600/8000 | loss=1.8124 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=844800/0/0 q=0 p=0 | 441 pos/s | vram=35.72GB
|
| 155 |
[12:56:42] val/lichess_opening hard_ce=1.4850 soft_ce=1.4850 soft_temp_ce=1.4850 teacher_entropy=0.0000 teacher_kl=1.4850 wdl_ce=1.0377 value_rows=8192.0000
|
| 156 |
+
[12:57:04] step 1625/8000 | loss=1.8202 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=858000/0/0 q=0 p=0 | 441 pos/s | vram=35.72GB
|
| 157 |
+
[12:57:26] step 1650/8000 | loss=1.8358 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=871200/0/0 q=0 p=0 | 442 pos/s | vram=35.72GB
|
| 158 |
+
[12:57:27] ckpt latest.pt (live weights) steps=1650 status=mid
|
| 159 |
+
[12:57:49] step 1675/8000 | loss=1.8062 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=884400/0/0 q=0 p=0 | 444 pos/s | vram=35.72GB
|
| 160 |
+
[12:58:11] step 1700/8000 | loss=1.8121 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=897600/0/0 q=0 p=0 | 446 pos/s | vram=35.72GB
|
| 161 |
+
[12:58:20] val/lichess_opening hard_ce=1.4865 soft_ce=1.4865 soft_temp_ce=1.4865 teacher_entropy=0.0000 teacher_kl=1.4865 wdl_ce=1.0374 value_rows=8192.0000
|
| 162 |
+
[12:58:42] step 1725/8000 | loss=1.8273 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=910800/0/0 q=0 p=0 | 445 pos/s | vram=35.72GB
|
| 163 |
+
[12:59:04] step 1750/8000 | loss=1.8191 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=924000/0/0 q=0 p=0 | 447 pos/s | vram=35.72GB
|
| 164 |
+
[12:59:26] step 1775/8000 | loss=1.8235 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=937200/0/0 q=0 p=0 | 449 pos/s | vram=35.72GB
|
| 165 |
+
[12:59:48] step 1800/8000 | loss=1.8315 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=950400/0/0 q=0 p=0 | 450 pos/s | vram=35.72GB
|
| 166 |
+
[12:59:49] ckpt step_001800.pt + latest.pt (live) steps=1800 status=mid kind=full
|
| 167 |
+
[12:59:58] val/lichess_opening hard_ce=1.4759 soft_ce=1.4759 soft_temp_ce=1.4759 teacher_entropy=0.0000 teacher_kl=1.4759 wdl_ce=1.0371 value_rows=8192.0000
|
| 168 |
+
[13:00:20] step 1825/8000 | loss=1.8072 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=963600/0/0 q=0 p=0 | 450 pos/s | vram=35.72GB
|
| 169 |
+
[13:00:42] step 1850/8000 | loss=1.8028 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=976800/0/0 q=0 p=0 | 451 pos/s | vram=35.72GB
|
| 170 |
+
[13:01:04] step 1875/8000 | loss=1.7991 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=990000/0/0 q=0 p=0 | 453 pos/s | vram=35.72GB
|
| 171 |
+
[13:01:26] step 1900/8000 | loss=1.7955 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1003200/0/0 q=0 p=0 | 454 pos/s | vram=35.72GB
|
| 172 |
+
[13:01:35] val/lichess_opening hard_ce=1.4825 soft_ce=1.4825 soft_temp_ce=1.4825 teacher_entropy=0.0000 teacher_kl=1.4825 wdl_ce=1.0379 value_rows=8192.0000
|
| 173 |
+
[13:01:57] step 1925/8000 | loss=1.7875 | lr=2.00e-03,3.00e-05 | clip=5/25 | mix s/d/b=1016400/0/0 q=0 p=0 | 454 pos/s | vram=35.72GB
|