train.log

train.log

@@ -199,3 +199,14 @@
 [15:51:43] step 3300/8000 | loss=1.8729 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1742400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB
 [15:51:44] ckpt step_003300.pt + latest.pt (live) steps=3300 status=mid kind=full
 [15:51:53] val/lichess_middlegame hard_ce=1.6471 soft_ce=1.6471 soft_temp_ce=1.6471 teacher_entropy=0.0000 teacher_kl=1.6471 wdl_ce=0.8300 value_rows=8192.0000
+[15:52:16] step 3325/8000 | loss=1.8442 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1755600/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB
+[15:52:38] step 3350/8000 | loss=1.8542 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1768800/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB
+[15:53:00] step 3375/8000 | loss=1.8315 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=1782000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB
+[15:53:22] step 3400/8000 | loss=1.8258 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1795200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB
+[15:53:30] val/lichess_middlegame hard_ce=1.6421 soft_ce=1.6421 soft_temp_ce=1.6421 teacher_entropy=0.0000 teacher_kl=1.6421 wdl_ce=0.8305 value_rows=8192.0000
+[15:53:52] step 3425/8000 | loss=1.8627 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1808400/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB
+[15:54:14] step 3450/8000 | loss=1.8357 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1821600/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB
+[15:54:15] ckpt latest.pt (live weights) steps=3450 status=mid
+[15:54:37] step 3475/8000 | loss=1.8530 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1834800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB
+[15:54:59] step 3500/8000 | loss=1.8508 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1848000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB
+[15:55:08] val/lichess_middlegame hard_ce=1.6444 soft_ce=1.6444 soft_temp_ce=1.6444 teacher_entropy=0.0000 teacher_kl=1.6444 wdl_ce=0.8323 value_rows=8192.0000