train.log

train.log

@@ -132,3 +132,14 @@
 [15:32:22] ckpt step_002100.pt + latest.pt (live) steps=2100 status=mid kind=full
 [15:32:31] val/lichess_middlegame hard_ce=1.6515 soft_ce=1.6515 soft_temp_ce=1.6515 teacher_entropy=0.0000 teacher_kl=1.6515 wdl_ce=0.8331 value_rows=8192.0000
 [15:32:53] step 2125/8000 | loss=1.8812 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1122000/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB
+[15:33:14] step 2150/8000 | loss=1.8692 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1135200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB
+[15:33:36] step 2175/8000 | loss=1.8651 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1148400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB
+[15:33:58] step 2200/8000 | loss=1.8637 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1161600/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB
+[15:34:07] val/lichess_middlegame hard_ce=1.6533 soft_ce=1.6533 soft_temp_ce=1.6533 teacher_entropy=0.0000 teacher_kl=1.6533 wdl_ce=0.8298 value_rows=8192.0000
+[15:34:29] step 2225/8000 | loss=1.8722 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1174800/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB
+[15:34:51] step 2250/8000 | loss=1.8799 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1188000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB
+[15:34:51] ckpt latest.pt (live weights) steps=2250 status=mid
+[15:35:13] step 2275/8000 | loss=1.8718 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1201200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB
+[15:35:35] step 2300/8000 | loss=1.8785 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=1214400/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB
+[15:35:44] val/lichess_middlegame hard_ce=1.6502 soft_ce=1.6502 soft_temp_ce=1.6502 teacher_entropy=0.0000 teacher_kl=1.6502 wdl_ce=0.8360 value_rows=8192.0000
+[15:36:05] step 2325/8000 | loss=1.8382 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1227600/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB