train.log

train.log

@@ -312,3 +312,14 @@
 [13:41:33] step 4375/8000 | loss=1.7857 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2310000/0/0 q=0 p=0 | 500 pos/s | vram=35.72GB
 [13:41:55] step 4400/8000 | loss=1.7754 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2323200/0/0 q=0 p=0 | 501 pos/s | vram=35.72GB
 [13:42:04] val/lichess_opening hard_ce=1.4428 soft_ce=1.4428 soft_temp_ce=1.4428 teacher_entropy=0.0000 teacher_kl=1.4428 wdl_ce=1.0377 value_rows=8192.0000
+[13:42:26] step 4425/8000 | loss=1.7847 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2336400/0/0 q=0 p=0 | 500 pos/s | vram=35.72GB
+[13:42:48] step 4450/8000 | loss=1.7747 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2349600/0/0 q=0 p=0 | 501 pos/s | vram=35.72GB
+[13:43:10] step 4475/8000 | loss=1.7989 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2362800/0/0 q=0 p=0 | 501 pos/s | vram=35.72GB
+[13:43:32] step 4500/8000 | loss=1.7656 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2376000/0/0 q=0 p=0 | 502 pos/s | vram=35.72GB
+[13:43:33] ckpt step_004500.pt + latest.pt (live) steps=4500 status=mid kind=full
+[13:43:42] val/lichess_opening hard_ce=1.4411 soft_ce=1.4411 soft_temp_ce=1.4411 teacher_entropy=0.0000 teacher_kl=1.4411 wdl_ce=1.0357 value_rows=8192.0000
+[13:44:04] step 4525/8000 | loss=1.7766 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2389200/0/0 q=0 p=0 | 501 pos/s | vram=35.72GB
+[13:44:25] step 4550/8000 | loss=1.7961 | lr=2.00e-03,3.00e-05 | clip=4/25 | mix s/d/b=2402400/0/0 q=0 p=0 | 502 pos/s | vram=35.72GB
+[13:44:47] step 4575/8000 | loss=1.7720 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2415600/0/0 q=0 p=0 | 502 pos/s | vram=35.72GB
+[13:45:09] step 4600/8000 | loss=1.7706 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2428800/0/0 q=0 p=0 | 503 pos/s | vram=35.72GB
+[13:45:18] val/lichess_opening hard_ce=1.4448 soft_ce=1.4448 soft_temp_ce=1.4448 teacher_entropy=0.0000 teacher_kl=1.4448 wdl_ce=1.0374 value_rows=8192.0000