train.log

train.log

@@ -228,3 +228,14 @@
 [15:59:49] step 3800/8000 | loss=1.8397 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2006400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB
 [15:59:58] val/lichess_middlegame hard_ce=1.6413 soft_ce=1.6413 soft_temp_ce=1.6413 teacher_entropy=0.0000 teacher_kl=1.6413 wdl_ce=0.8294 value_rows=8192.0000
 [16:00:20] step 3825/8000 | loss=1.8440 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2019600/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB
+[16:00:42] step 3850/8000 | loss=1.8478 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2032800/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB
+[16:01:04] step 3875/8000 | loss=1.8433 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=2046000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB
+[16:01:26] step 3900/8000 | loss=1.8287 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2059200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB
+[16:01:27] ckpt step_003900.pt + latest.pt (live) steps=3900 status=mid kind=full
+[16:01:36] val/lichess_middlegame hard_ce=1.6334 soft_ce=1.6334 soft_temp_ce=1.6334 teacher_entropy=0.0000 teacher_kl=1.6334 wdl_ce=0.8336 value_rows=8192.0000
+[16:01:58] step 3925/8000 | loss=1.8329 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2072400/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB
+[16:02:20] step 3950/8000 | loss=1.8250 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=2085600/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB
+[16:02:42] step 3975/8000 | loss=1.8426 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=2098800/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB
+[16:03:03] step 4000/8000 | loss=1.8351 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2112000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB
+[16:03:12] val/lichess_middlegame hard_ce=1.6370 soft_ce=1.6370 soft_temp_ce=1.6370 teacher_entropy=0.0000 teacher_kl=1.6370 wdl_ce=0.8291 value_rows=8192.0000
+[16:03:34] step 4025/8000 | loss=1.8450 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2125200/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB