train.log

train.log

@@ -357,3 +357,15 @@
 [13:54:32] step 5175/8000 | loss=1.7650 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2732400/0/0 q=0 p=0 | 506 pos/s | vram=35.72GB
 [13:54:54] step 5200/8000 | loss=1.7655 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2745600/0/0 q=0 p=0 | 507 pos/s | vram=35.72GB
 [13:55:03] val/lichess_opening hard_ce=1.4293 soft_ce=1.4293 soft_temp_ce=1.4293 teacher_entropy=0.0000 teacher_kl=1.4293 wdl_ce=1.0344 value_rows=8192.0000
+[13:55:25] step 5225/8000 | loss=1.7754 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2758800/0/0 q=0 p=0 | 506 pos/s | vram=35.72GB
+[13:55:47] step 5250/8000 | loss=1.7754 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2772000/0/0 q=0 p=0 | 507 pos/s | vram=35.72GB
+[13:55:47] ckpt latest.pt (live weights) steps=5250 status=mid
+[13:56:09] step 5275/8000 | loss=1.7664 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2785200/0/0 q=0 p=0 | 507 pos/s | vram=35.72GB
+[13:56:32] step 5300/8000 | loss=1.7667 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2798400/0/0 q=0 p=0 | 507 pos/s | vram=35.72GB
+[13:56:41] val/lichess_opening hard_ce=1.4347 soft_ce=1.4347 soft_temp_ce=1.4347 teacher_entropy=0.0000 teacher_kl=1.4347 wdl_ce=1.0357 value_rows=8192.0000
+[13:57:03] step 5325/8000 | loss=1.7602 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2811600/0/0 q=0 p=0 | 507 pos/s | vram=35.72GB
+[13:57:24] step 5350/8000 | loss=1.7499 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2824800/0/0 q=0 p=0 | 507 pos/s | vram=35.72GB
+[13:57:46] step 5375/8000 | loss=1.7480 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2838000/0/0 q=0 p=0 | 508 pos/s | vram=35.72GB
+[13:58:08] step 5400/8000 | loss=1.7684 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2851200/0/0 q=0 p=0 | 508 pos/s | vram=35.72GB
+[13:58:09] ckpt step_005400.pt + latest.pt (live) steps=5400 status=mid kind=full
+[13:58:18] val/lichess_opening hard_ce=1.4278 soft_ce=1.4278 soft_temp_ce=1.4278 teacher_entropy=0.0000 teacher_kl=1.4278 wdl_ce=1.0349 value_rows=8192.0000