Download train.log from avewright/middlegame-model: direct link, hf CLI and curl.
- Browser
- Download file 61.4 kB
-
https://huggingface.co/avewright/middlegame-model/resolve/main/train.log
- Command line
-
hf download hf://avewright/middlegame-model/train.log
-
curl -L -o train.log https://huggingface.co/avewright/middlegame-model/resolve/main/train.log
61.4 kB
| [14:56:29] trial=exp278_lichess_middlegame_stream arch=squares64 device=cuda vocab=1968 | |
| [14:56:29] train bs=528 accum=1 grad_ckpt=False compile=True elo_every=0 save_every=150 | |
| [14:56:29] model=Squares64RecurrentConfig(encoder_dim=256, hidden_dim=736, num_heads=8, ffn_ratio=4, dropout=0.05, use_swiglu=True, use_qk_norm=True, zero_init_out_proj=True, gradient_checkpointing=False, prefix_layers=4, recurrent_layers=7, recurrent_unrolls=3, suffix_layers=4, policy_head_dim=384, value_hidden=384, n_value_classes=3, use_history=False, use_threat_head=False) | |
| [14:56:30] params=98.97M | |
| [14:56:31] WEIGHTS-ONLY WARM START /root/transform/outputs/exp278_lichess_middlegame_stream/init.pt from eval/SWA snapshot (optimizer/RNG re-initialized; step reset to 0) | |
| [14:56:31] optimizer=PolarNorMuon (97.7M) + AdamW aux (1.3M) compile_polar=True | |
| [14:56:31] force_lr muon=0.002 adam=3e-05 | |
| [14:56:32] torch.compile enabled (mode=default); will fall back if inductor fails | |
| [14:56:32] external eval lichess_middlegame n=8,192 /root/transform/outputs/exp278_lichess_middlegame_stream/lichess_eval.pt | |
| [14:57:06] soft train=45,000,000 val=0 blocked=0 targets empty=0 unnorm=0 external_eval | |
| [14:58:34] batch probe ok bs=528 peak_vram=35.32GB compile=True | |
| [14:58:34] average_recurrent_grads() divides bank .grad by unroll count. That does NOT divide optimizer updates by the same amount: Polar-NorMuon is scale-invariant after orthogonalization, and RMS-Adam (m/sqrt(v)) is also approximately scale-invariant for a stationary grad. What does scale is SGD-style updates and the pre-clip global grad norm (so clipping fires less often after averaging). Use explicit param-group LRs if different update sizes are intended. | |
| [14:58:34] exposure deep/shallow odds=0.0x (mix=0.0 deep_n=0 shallow_n=45000000) | |
| [14:58:41] step 1/8000 | loss=2.1707 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=528/0/0 q=0 p=0 | 76 pos/s | vram=35.33GB | |
| [14:59:02] step 25/8000 | loss=1.9697 | lr=2.00e-03,3.00e-05 | clip=16/25 | mix s/d/b=13200/0/0 q=0 p=0 | 475 pos/s | vram=35.73GB | |
| [14:59:23] step 50/8000 | loss=1.9362 | lr=2.00e-03,3.00e-05 | clip=5/25 | mix s/d/b=26400/0/0 q=0 p=0 | 534 pos/s | vram=35.73GB | |
| [14:59:45] step 75/8000 | loss=1.9086 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=39600/0/0 q=0 p=0 | 556 pos/s | vram=35.73GB | |
| [15:00:07] step 100/8000 | loss=1.9178 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=52800/0/0 q=0 p=0 | 564 pos/s | vram=35.73GB | |
| [15:00:17] val/lichess_middlegame hard_ce=1.6958 soft_ce=1.6958 soft_temp_ce=1.6958 teacher_entropy=0.0000 teacher_kl=1.6958 wdl_ce=0.8440 value_rows=8192.0000 | |
| [15:00:39] step 125/8000 | loss=1.9028 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=66000/0/0 q=0 p=0 | 529 pos/s | vram=35.73GB | |
| [15:01:00] step 150/8000 | loss=1.8971 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=79200/0/0 q=0 p=0 | 540 pos/s | vram=35.73GB | |
| [15:01:01] ckpt latest.pt (live weights) steps=150 status=mid | |
| [15:01:23] step 175/8000 | loss=1.9170 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=92400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:01:45] step 200/8000 | loss=1.9122 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=105600/0/0 q=0 p=0 | 553 pos/s | vram=35.73GB | |
| [15:01:53] val/lichess_middlegame hard_ce=1.6867 soft_ce=1.6867 soft_temp_ce=1.6867 teacher_entropy=0.0000 teacher_kl=1.6867 wdl_ce=0.8398 value_rows=8192.0000 | |
| [15:02:15] step 225/8000 | loss=1.9260 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=118800/0/0 q=0 p=0 | 536 pos/s | vram=35.73GB | |
| [15:02:37] step 250/8000 | loss=1.9122 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=132000/0/0 q=0 p=0 | 543 pos/s | vram=35.73GB | |
| [15:02:59] step 275/8000 | loss=1.9149 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=145200/0/0 q=0 p=0 | 548 pos/s | vram=35.73GB | |
| [15:03:21] step 300/8000 | loss=1.8985 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=158400/0/0 q=0 p=0 | 552 pos/s | vram=35.73GB | |
| [15:03:22] ckpt step_000300.pt + latest.pt (live) steps=300 status=mid kind=full | |
| [15:03:30] val/lichess_middlegame hard_ce=1.6880 soft_ce=1.6880 soft_temp_ce=1.6880 teacher_entropy=0.0000 teacher_kl=1.6880 wdl_ce=0.8379 value_rows=8192.0000 | |
| [15:03:52] step 325/8000 | loss=1.8774 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=171600/0/0 q=0 p=0 | 539 pos/s | vram=35.73GB | |
| [15:04:14] step 350/8000 | loss=1.8823 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=184800/0/0 q=0 p=0 | 543 pos/s | vram=35.73GB | |
| [15:04:36] step 375/8000 | loss=1.9007 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=198000/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [15:04:58] step 400/8000 | loss=1.8805 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=211200/0/0 q=0 p=0 | 550 pos/s | vram=35.73GB | |
| [15:05:06] val/lichess_middlegame hard_ce=1.6814 soft_ce=1.6814 soft_temp_ce=1.6814 teacher_entropy=0.0000 teacher_kl=1.6814 wdl_ce=0.8366 value_rows=8192.0000 | |
| [15:05:29] step 425/8000 | loss=1.8911 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=224400/0/0 q=0 p=0 | 541 pos/s | vram=35.73GB | |
| [15:05:50] step 450/8000 | loss=1.9055 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=237600/0/0 q=0 p=0 | 544 pos/s | vram=35.73GB | |
| [15:05:51] ckpt latest.pt (live weights) steps=450 status=mid | |
| [15:06:13] step 475/8000 | loss=1.8900 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=250800/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [15:06:34] step 500/8000 | loss=1.8776 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=264000/0/0 q=0 p=0 | 549 pos/s | vram=35.73GB | |
| [15:06:43] val/lichess_middlegame hard_ce=1.6740 soft_ce=1.6740 soft_temp_ce=1.6740 teacher_entropy=0.0000 teacher_kl=1.6740 wdl_ce=0.8361 value_rows=8192.0000 | |
| [15:07:05] step 525/8000 | loss=1.9158 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=277200/0/0 q=0 p=0 | 542 pos/s | vram=35.73GB | |
| [15:07:27] step 550/8000 | loss=1.8693 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=290400/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:07:48] step 575/8000 | loss=1.8868 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=303600/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [15:08:10] step 600/8000 | loss=1.8922 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=316800/0/0 q=0 p=0 | 550 pos/s | vram=35.73GB | |
| [15:08:11] ckpt step_000600.pt + latest.pt (live) steps=600 status=mid kind=full | |
| [15:08:20] val/lichess_middlegame hard_ce=1.6760 soft_ce=1.6760 soft_temp_ce=1.6760 teacher_entropy=0.0000 teacher_kl=1.6760 wdl_ce=0.8355 value_rows=8192.0000 | |
| [15:08:42] step 625/8000 | loss=1.9033 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=330000/0/0 q=0 p=0 | 543 pos/s | vram=35.73GB | |
| [15:09:04] step 650/8000 | loss=1.8706 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=343200/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:09:26] step 675/8000 | loss=1.8909 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=356400/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [15:09:47] step 700/8000 | loss=1.8843 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=369600/0/0 q=0 p=0 | 549 pos/s | vram=35.73GB | |
| [15:09:56] val/lichess_middlegame hard_ce=1.6694 soft_ce=1.6694 soft_temp_ce=1.6694 teacher_entropy=0.0000 teacher_kl=1.6694 wdl_ce=0.8352 value_rows=8192.0000 | |
| [15:10:18] step 725/8000 | loss=1.8778 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=382800/0/0 q=0 p=0 | 543 pos/s | vram=35.73GB | |
| [15:10:41] step 750/8000 | loss=1.8883 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=396000/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:10:41] ckpt latest.pt (live weights) steps=750 status=mid | |
| [15:11:03] step 775/8000 | loss=1.8988 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=409200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:11:25] step 800/8000 | loss=1.8825 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=422400/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [15:11:34] val/lichess_middlegame hard_ce=1.6675 soft_ce=1.6675 soft_temp_ce=1.6675 teacher_entropy=0.0000 teacher_kl=1.6675 wdl_ce=0.8363 value_rows=8192.0000 | |
| [15:11:56] step 825/8000 | loss=1.8710 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=435600/0/0 q=0 p=0 | 543 pos/s | vram=35.73GB | |
| [15:12:18] step 850/8000 | loss=1.8988 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=448800/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:12:40] step 875/8000 | loss=1.8934 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=462000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:13:01] step 900/8000 | loss=1.8826 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=475200/0/0 q=0 p=0 | 548 pos/s | vram=35.73GB | |
| [15:13:02] ckpt step_000900.pt + latest.pt (live) steps=900 status=mid kind=full | |
| [15:13:11] val/lichess_middlegame hard_ce=1.6665 soft_ce=1.6665 soft_temp_ce=1.6665 teacher_entropy=0.0000 teacher_kl=1.6665 wdl_ce=0.8333 value_rows=8192.0000 | |
| [15:13:33] step 925/8000 | loss=1.8848 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=488400/0/0 q=0 p=0 | 543 pos/s | vram=35.73GB | |
| [15:13:55] step 950/8000 | loss=1.8847 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=501600/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:14:17] step 975/8000 | loss=1.8632 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=514800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:14:38] step 1000/8000 | loss=1.8857 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=528000/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [15:14:47] val/lichess_middlegame hard_ce=1.6637 soft_ce=1.6637 soft_temp_ce=1.6637 teacher_entropy=0.0000 teacher_kl=1.6637 wdl_ce=0.8341 value_rows=8192.0000 | |
| [15:15:09] step 1025/8000 | loss=1.8718 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=541200/0/0 q=0 p=0 | 544 pos/s | vram=35.73GB | |
| [15:15:31] step 1050/8000 | loss=1.8783 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=554400/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:15:31] ckpt latest.pt (live weights) steps=1050 status=mid | |
| [15:15:54] step 1075/8000 | loss=1.8910 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=567600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:16:15] step 1100/8000 | loss=1.8772 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=580800/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [15:16:24] val/lichess_middlegame hard_ce=1.6636 soft_ce=1.6636 soft_temp_ce=1.6636 teacher_entropy=0.0000 teacher_kl=1.6636 wdl_ce=0.8337 value_rows=8192.0000 | |
| [15:16:46] step 1125/8000 | loss=1.8673 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=594000/0/0 q=0 p=0 | 544 pos/s | vram=35.73GB | |
| [15:17:08] step 1150/8000 | loss=1.8935 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=607200/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:17:30] step 1175/8000 | loss=1.8880 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=620400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:17:52] step 1200/8000 | loss=1.8769 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=633600/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [15:17:52] ckpt step_001200.pt + latest.pt (live) steps=1200 status=mid kind=full | |
| [15:18:01] val/lichess_middlegame hard_ce=1.6622 soft_ce=1.6622 soft_temp_ce=1.6622 teacher_entropy=0.0000 teacher_kl=1.6622 wdl_ce=0.8380 value_rows=8192.0000 | |
| [15:18:23] step 1225/8000 | loss=1.8759 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=646800/0/0 q=0 p=0 | 544 pos/s | vram=35.73GB | |
| [15:18:45] step 1250/8000 | loss=1.8803 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=660000/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:19:07] step 1275/8000 | loss=1.8841 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=673200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:19:29] step 1300/8000 | loss=1.8857 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=686400/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [15:19:37] val/lichess_middlegame hard_ce=1.6569 soft_ce=1.6569 soft_temp_ce=1.6569 teacher_entropy=0.0000 teacher_kl=1.6569 wdl_ce=0.8365 value_rows=8192.0000 | |
| [15:19:59] step 1325/8000 | loss=1.8777 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=699600/0/0 q=0 p=0 | 544 pos/s | vram=35.73GB | |
| [15:20:21] step 1350/8000 | loss=1.8713 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=712800/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:20:22] ckpt latest.pt (live weights) steps=1350 status=mid | |
| [15:20:44] step 1375/8000 | loss=1.8691 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=726000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:21:06] step 1400/8000 | loss=1.8910 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=739200/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [15:21:14] val/lichess_middlegame hard_ce=1.6578 soft_ce=1.6578 soft_temp_ce=1.6578 teacher_entropy=0.0000 teacher_kl=1.6578 wdl_ce=0.8358 value_rows=8192.0000 | |
| [15:21:36] step 1425/8000 | loss=1.8570 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=752400/0/0 q=0 p=0 | 544 pos/s | vram=35.73GB | |
| [15:21:58] step 1450/8000 | loss=1.8780 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=765600/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:22:20] step 1475/8000 | loss=1.8817 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=778800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:22:42] step 1500/8000 | loss=1.8721 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=792000/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [15:22:43] ckpt step_001500.pt + latest.pt (live) steps=1500 status=mid kind=full | |
| [15:22:51] val/lichess_middlegame hard_ce=1.6601 soft_ce=1.6601 soft_temp_ce=1.6601 teacher_entropy=0.0000 teacher_kl=1.6601 wdl_ce=0.8335 value_rows=8192.0000 | |
| [15:23:13] step 1525/8000 | loss=1.8742 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=805200/0/0 q=0 p=0 | 544 pos/s | vram=35.73GB | |
| [15:23:35] step 1550/8000 | loss=1.8627 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=818400/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:23:57] step 1575/8000 | loss=1.8671 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=831600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:24:19] step 1600/8000 | loss=1.8789 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=844800/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [15:24:27] val/lichess_middlegame hard_ce=1.6589 soft_ce=1.6589 soft_temp_ce=1.6589 teacher_entropy=0.0000 teacher_kl=1.6589 wdl_ce=0.8333 value_rows=8192.0000 | |
| [15:24:49] step 1625/8000 | loss=1.8730 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=858000/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:25:11] step 1650/8000 | loss=1.8806 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=871200/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:25:11] ckpt latest.pt (live weights) steps=1650 status=mid | |
| [15:25:33] step 1675/8000 | loss=1.8586 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=884400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:25:55] step 1700/8000 | loss=1.8709 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=897600/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [15:26:04] val/lichess_middlegame hard_ce=1.6577 soft_ce=1.6577 soft_temp_ce=1.6577 teacher_entropy=0.0000 teacher_kl=1.6577 wdl_ce=0.8340 value_rows=8192.0000 | |
| [15:26:26] step 1725/8000 | loss=1.8746 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=910800/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:26:48] step 1750/8000 | loss=1.8782 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=924000/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:27:10] step 1775/8000 | loss=1.8580 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=937200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:27:31] step 1800/8000 | loss=1.8764 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=950400/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [15:27:32] ckpt step_001800.pt + latest.pt (live) steps=1800 status=mid kind=full | |
| [15:27:41] val/lichess_middlegame hard_ce=1.6541 soft_ce=1.6541 soft_temp_ce=1.6541 teacher_entropy=0.0000 teacher_kl=1.6541 wdl_ce=0.8338 value_rows=8192.0000 | |
| [15:28:03] step 1825/8000 | loss=1.8567 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=963600/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:28:25] step 1850/8000 | loss=1.8609 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=976800/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:28:46] step 1875/8000 | loss=1.8644 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=990000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:29:08] step 1900/8000 | loss=1.8720 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=1003200/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [15:29:17] val/lichess_middlegame hard_ce=1.6559 soft_ce=1.6559 soft_temp_ce=1.6559 teacher_entropy=0.0000 teacher_kl=1.6559 wdl_ce=0.8337 value_rows=8192.0000 | |
| [15:29:39] step 1925/8000 | loss=1.8569 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=1016400/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:30:01] step 1950/8000 | loss=1.8801 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1029600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:30:01] ckpt latest.pt (live weights) steps=1950 status=mid | |
| [15:30:23] step 1975/8000 | loss=1.8623 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1042800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:30:45] step 2000/8000 | loss=1.8738 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1056000/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [15:30:54] val/lichess_middlegame hard_ce=1.6538 soft_ce=1.6538 soft_temp_ce=1.6538 teacher_entropy=0.0000 teacher_kl=1.6538 wdl_ce=0.8327 value_rows=8192.0000 | |
| [15:31:16] step 2025/8000 | loss=1.8641 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1069200/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:31:38] step 2050/8000 | loss=1.8646 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1082400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:31:59] step 2075/8000 | loss=1.8611 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1095600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:32:21] step 2100/8000 | loss=1.8810 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=1108800/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [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 | |
| [15:36:27] step 2350/8000 | loss=1.8613 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=1240800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:36:49] step 2375/8000 | loss=1.8766 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1254000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:37:11] step 2400/8000 | loss=1.8605 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1267200/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [15:37:12] ckpt step_002400.pt + latest.pt (live) steps=2400 status=mid kind=full | |
| [15:37:21] val/lichess_middlegame hard_ce=1.6483 soft_ce=1.6483 soft_temp_ce=1.6483 teacher_entropy=0.0000 teacher_kl=1.6483 wdl_ce=0.8303 value_rows=8192.0000 | |
| [15:37:43] step 2425/8000 | loss=1.8580 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1280400/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:38:05] step 2450/8000 | loss=1.8610 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1293600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:38:27] step 2475/8000 | loss=1.8449 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1306800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:38:49] step 2500/8000 | loss=1.8605 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1320000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:38:58] val/lichess_middlegame hard_ce=1.6460 soft_ce=1.6460 soft_temp_ce=1.6460 teacher_entropy=0.0000 teacher_kl=1.6460 wdl_ce=0.8340 value_rows=8192.0000 | |
| [15:39:20] step 2525/8000 | loss=1.8573 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1333200/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:39:42] step 2550/8000 | loss=1.8469 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1346400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:39:42] ckpt latest.pt (live weights) steps=2550 status=mid | |
| [15:40:04] step 2575/8000 | loss=1.8534 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1359600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:40:26] step 2600/8000 | loss=1.8579 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1372800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:40:35] val/lichess_middlegame hard_ce=1.6463 soft_ce=1.6463 soft_temp_ce=1.6463 teacher_entropy=0.0000 teacher_kl=1.6463 wdl_ce=0.8310 value_rows=8192.0000 | |
| [15:40:57] step 2625/8000 | loss=1.8499 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1386000/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:41:19] step 2650/8000 | loss=1.8610 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1399200/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:41:41] step 2675/8000 | loss=1.8743 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=1412400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:42:03] step 2700/8000 | loss=1.8666 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1425600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:42:04] ckpt step_002700.pt + latest.pt (live) steps=2700 status=mid kind=full | |
| [15:42:13] val/lichess_middlegame hard_ce=1.6420 soft_ce=1.6420 soft_temp_ce=1.6420 teacher_entropy=0.0000 teacher_kl=1.6420 wdl_ce=0.8299 value_rows=8192.0000 | |
| [15:42:34] step 2725/8000 | loss=1.8650 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1438800/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:42:56] step 2750/8000 | loss=1.8697 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1452000/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:43:18] step 2775/8000 | loss=1.8324 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1465200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:43:39] step 2800/8000 | loss=1.8405 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1478400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:43:48] val/lichess_middlegame hard_ce=1.6386 soft_ce=1.6386 soft_temp_ce=1.6386 teacher_entropy=0.0000 teacher_kl=1.6386 wdl_ce=0.8312 value_rows=8192.0000 | |
| [15:44:10] step 2825/8000 | loss=1.8729 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1491600/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:44:32] step 2850/8000 | loss=1.8509 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1504800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:44:32] ckpt latest.pt (live weights) steps=2850 status=mid | |
| [15:44:54] step 2875/8000 | loss=1.8552 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1518000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:45:16] step 2900/8000 | loss=1.8386 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1531200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:45:24] val/lichess_middlegame hard_ce=1.6439 soft_ce=1.6439 soft_temp_ce=1.6439 teacher_entropy=0.0000 teacher_kl=1.6439 wdl_ce=0.8326 value_rows=8192.0000 | |
| [15:45:47] step 2925/8000 | loss=1.8410 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1544400/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:46:09] step 2950/8000 | loss=1.8598 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1557600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:46:30] step 2975/8000 | loss=1.8748 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1570800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:46:52] step 3000/8000 | loss=1.8680 | lr=2.00e-03,3.00e-05 | clip=4/25 | mix s/d/b=1584000/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [15:46:53] ckpt step_003000.pt + latest.pt (live) steps=3000 status=mid kind=full | |
| [15:47:02] val/lichess_middlegame hard_ce=1.6396 soft_ce=1.6396 soft_temp_ce=1.6396 teacher_entropy=0.0000 teacher_kl=1.6396 wdl_ce=0.8340 value_rows=8192.0000 | |
| [15:47:24] step 3025/8000 | loss=1.8549 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=1597200/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:47:46] step 3050/8000 | loss=1.8344 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=1610400/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:48:08] step 3075/8000 | loss=1.8446 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1623600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:48:30] step 3100/8000 | loss=1.8561 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1636800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:48:39] val/lichess_middlegame hard_ce=1.6417 soft_ce=1.6417 soft_temp_ce=1.6417 teacher_entropy=0.0000 teacher_kl=1.6417 wdl_ce=0.8329 value_rows=8192.0000 | |
| [15:49:00] step 3125/8000 | loss=1.8369 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=1650000/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:49:22] step 3150/8000 | loss=1.8542 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1663200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:49:23] ckpt latest.pt (live weights) steps=3150 status=mid | |
| [15:49:45] step 3175/8000 | loss=1.8421 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1676400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:50:06] step 3200/8000 | loss=1.8524 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1689600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:50:15] val/lichess_middlegame hard_ce=1.6446 soft_ce=1.6446 soft_temp_ce=1.6446 teacher_entropy=0.0000 teacher_kl=1.6446 wdl_ce=0.8313 value_rows=8192.0000 | |
| [15:50:37] step 3225/8000 | loss=1.8375 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1702800/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:50:59] step 3250/8000 | loss=1.8498 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1716000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:51:21] step 3275/8000 | loss=1.8605 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1729200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [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 | |
| [15:55:30] step 3525/8000 | loss=1.8343 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=1861200/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:55:52] step 3550/8000 | loss=1.8459 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1874400/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:56:13] step 3575/8000 | loss=1.8487 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1887600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:56:35] step 3600/8000 | loss=1.8456 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1900800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:56:36] ckpt step_003600.pt + latest.pt (live) steps=3600 status=mid kind=full | |
| [15:56:45] val/lichess_middlegame hard_ce=1.6375 soft_ce=1.6375 soft_temp_ce=1.6375 teacher_entropy=0.0000 teacher_kl=1.6375 wdl_ce=0.8297 value_rows=8192.0000 | |
| [15:57:07] step 3625/8000 | loss=1.8289 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=1914000/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:57:29] step 3650/8000 | loss=1.8390 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1927200/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:57:50] step 3675/8000 | loss=1.8574 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1940400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:58:12] step 3700/8000 | loss=1.8400 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1953600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [15:58:21] val/lichess_middlegame hard_ce=1.6358 soft_ce=1.6358 soft_temp_ce=1.6358 teacher_entropy=0.0000 teacher_kl=1.6358 wdl_ce=0.8283 value_rows=8192.0000 | |
| [15:58:43] step 3725/8000 | loss=1.8526 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1966800/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:59:05] step 3750/8000 | loss=1.8447 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1980000/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [15:59:05] ckpt latest.pt (live weights) steps=3750 status=mid | |
| [15:59:27] step 3775/8000 | loss=1.8197 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=1993200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [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 | |
| [16:03:56] step 4050/8000 | loss=1.8734 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2138400/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [16:03:56] ckpt latest.pt (live weights) steps=4050 status=mid | |
| [16:04:18] step 4075/8000 | loss=1.8572 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2151600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:04:40] step 4100/8000 | loss=1.8589 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2164800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:04:48] val/lichess_middlegame hard_ce=1.6365 soft_ce=1.6365 soft_temp_ce=1.6365 teacher_entropy=0.0000 teacher_kl=1.6365 wdl_ce=0.8288 value_rows=8192.0000 | |
| [16:05:10] step 4125/8000 | loss=1.8361 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2178000/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [16:05:32] step 4150/8000 | loss=1.8244 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=2191200/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [16:05:54] step 4175/8000 | loss=1.8583 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2204400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:06:15] step 4200/8000 | loss=1.8567 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2217600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:06:16] ckpt step_004200.pt + latest.pt (live) steps=4200 status=mid kind=full | |
| [16:06:25] val/lichess_middlegame hard_ce=1.6322 soft_ce=1.6322 soft_temp_ce=1.6322 teacher_entropy=0.0000 teacher_kl=1.6322 wdl_ce=0.8297 value_rows=8192.0000 | |
| [16:06:47] step 4225/8000 | loss=1.8335 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2230800/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [16:07:09] step 4250/8000 | loss=1.8639 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=2244000/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [16:07:30] step 4275/8000 | loss=1.8515 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2257200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:07:52] step 4300/8000 | loss=1.8325 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2270400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:08:01] val/lichess_middlegame hard_ce=1.6345 soft_ce=1.6345 soft_temp_ce=1.6345 teacher_entropy=0.0000 teacher_kl=1.6345 wdl_ce=0.8299 value_rows=8192.0000 | |
| [16:08:23] step 4325/8000 | loss=1.8261 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2283600/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [16:08:45] step 4350/8000 | loss=1.8384 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=2296800/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [16:08:45] ckpt latest.pt (live weights) steps=4350 status=mid | |
| [16:09:07] step 4375/8000 | loss=1.8480 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2310000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:09:29] step 4400/8000 | loss=1.8481 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2323200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:09:37] val/lichess_middlegame hard_ce=1.6352 soft_ce=1.6352 soft_temp_ce=1.6352 teacher_entropy=0.0000 teacher_kl=1.6352 wdl_ce=0.8292 value_rows=8192.0000 | |
| [16:09:59] step 4425/8000 | loss=1.8501 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2336400/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [16:10:21] step 4450/8000 | loss=1.8260 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2349600/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [16:10:43] step 4475/8000 | loss=1.8535 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2362800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:11:05] step 4500/8000 | loss=1.8364 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2376000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:11:05] ckpt step_004500.pt + latest.pt (live) steps=4500 status=mid kind=full | |
| [16:11:14] val/lichess_middlegame hard_ce=1.6346 soft_ce=1.6346 soft_temp_ce=1.6346 teacher_entropy=0.0000 teacher_kl=1.6346 wdl_ce=0.8283 value_rows=8192.0000 | |
| [16:11:36] step 4525/8000 | loss=1.8518 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=2389200/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [16:11:58] step 4550/8000 | loss=1.8474 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=2402400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:12:19] step 4575/8000 | loss=1.8281 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2415600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:12:41] step 4600/8000 | loss=1.8258 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2428800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:12:50] val/lichess_middlegame hard_ce=1.6312 soft_ce=1.6312 soft_temp_ce=1.6312 teacher_entropy=0.0000 teacher_kl=1.6312 wdl_ce=0.8299 value_rows=8192.0000 | |
| [16:13:12] step 4625/8000 | loss=1.8493 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=2442000/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [16:13:33] step 4650/8000 | loss=1.8273 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=2455200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:13:34] ckpt latest.pt (live weights) steps=4650 status=mid | |
| [16:13:56] step 4675/8000 | loss=1.8347 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2468400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:14:17] step 4700/8000 | loss=1.8258 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=2481600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:14:26] val/lichess_middlegame hard_ce=1.6367 soft_ce=1.6367 soft_temp_ce=1.6367 teacher_entropy=0.0000 teacher_kl=1.6367 wdl_ce=0.8293 value_rows=8192.0000 | |
| [16:14:48] step 4725/8000 | loss=1.8210 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2494800/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [16:15:10] step 4750/8000 | loss=1.8439 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=2508000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:15:32] step 4775/8000 | loss=1.8299 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2521200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:15:53] step 4800/8000 | loss=1.8377 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=2534400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:15:54] ckpt step_004800.pt + latest.pt (live) steps=4800 status=mid kind=full | |
| [16:16:03] val/lichess_middlegame hard_ce=1.6291 soft_ce=1.6291 soft_temp_ce=1.6291 teacher_entropy=0.0000 teacher_kl=1.6291 wdl_ce=0.8298 value_rows=8192.0000 | |
| [16:16:25] step 4825/8000 | loss=1.8390 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2547600/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [16:16:46] step 4850/8000 | loss=1.8376 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=2560800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:17:08] step 4875/8000 | loss=1.8389 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=2574000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:17:30] step 4900/8000 | loss=1.8300 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2587200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:17:39] val/lichess_middlegame hard_ce=1.6338 soft_ce=1.6338 soft_temp_ce=1.6338 teacher_entropy=0.0000 teacher_kl=1.6338 wdl_ce=0.8263 value_rows=8192.0000 | |
| [16:18:00] step 4925/8000 | loss=1.8426 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=2600400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:18:22] step 4950/8000 | loss=1.8262 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2613600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:18:23] ckpt latest.pt (live weights) steps=4950 status=mid | |
| [16:18:45] step 4975/8000 | loss=1.8143 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2626800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:19:07] step 5000/8000 | loss=1.8492 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=2640000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:19:16] val/lichess_middlegame hard_ce=1.6293 soft_ce=1.6293 soft_temp_ce=1.6293 teacher_entropy=0.0000 teacher_kl=1.6293 wdl_ce=0.8298 value_rows=8192.0000 | |
| [16:19:38] step 5025/8000 | loss=1.8439 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2653200/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [16:20:01] step 5050/8000 | loss=1.8302 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=2666400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:20:23] step 5075/8000 | loss=1.8332 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2679600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:20:45] step 5100/8000 | loss=1.8250 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2692800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:20:45] ckpt step_005100.pt + latest.pt (live) steps=5100 status=mid kind=full | |
| [16:20:54] val/lichess_middlegame hard_ce=1.6333 soft_ce=1.6333 soft_temp_ce=1.6333 teacher_entropy=0.0000 teacher_kl=1.6333 wdl_ce=0.8254 value_rows=8192.0000 | |
| [16:21:16] step 5125/8000 | loss=1.8273 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2706000/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [16:21:38] step 5150/8000 | loss=1.8338 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2719200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:22:00] step 5175/8000 | loss=1.8147 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2732400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:22:21] step 5200/8000 | loss=1.8505 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2745600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:22:30] val/lichess_middlegame hard_ce=1.6243 soft_ce=1.6243 soft_temp_ce=1.6243 teacher_entropy=0.0000 teacher_kl=1.6243 wdl_ce=0.8271 value_rows=8192.0000 | |
| [16:22:52] step 5225/8000 | loss=1.8393 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2758800/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [16:23:14] step 5250/8000 | loss=1.8292 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2772000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:23:14] ckpt latest.pt (live weights) steps=5250 status=mid | |
| [16:23:36] step 5275/8000 | loss=1.8259 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=2785200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:23:58] step 5300/8000 | loss=1.8227 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2798400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:24:07] val/lichess_middlegame hard_ce=1.6277 soft_ce=1.6277 soft_temp_ce=1.6277 teacher_entropy=0.0000 teacher_kl=1.6277 wdl_ce=0.8246 value_rows=8192.0000 | |
| [16:24:28] step 5325/8000 | loss=1.8300 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=2811600/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [16:24:50] step 5350/8000 | loss=1.8299 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2824800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:25:12] step 5375/8000 | loss=1.8205 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2838000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:25:34] step 5400/8000 | loss=1.8281 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2851200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:25:35] ckpt step_005400.pt + latest.pt (live) steps=5400 status=mid kind=full | |
| [16:25:44] val/lichess_middlegame hard_ce=1.6262 soft_ce=1.6262 soft_temp_ce=1.6262 teacher_entropy=0.0000 teacher_kl=1.6262 wdl_ce=0.8286 value_rows=8192.0000 | |
| [16:26:05] step 5425/8000 | loss=1.8600 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2864400/0/0 q=0 p=0 | 545 pos/s | vram=35.73GB | |
| [16:26:27] step 5450/8000 | loss=1.8419 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=2877600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:26:49] step 5475/8000 | loss=1.8325 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2890800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:27:11] step 5500/8000 | loss=1.8037 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2904000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:27:20] val/lichess_middlegame hard_ce=1.6268 soft_ce=1.6268 soft_temp_ce=1.6268 teacher_entropy=0.0000 teacher_kl=1.6268 wdl_ce=0.8305 value_rows=8192.0000 | |
| [16:27:41] step 5525/8000 | loss=1.8364 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=2917200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:28:03] step 5550/8000 | loss=1.8063 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2930400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:28:04] ckpt latest.pt (live weights) steps=5550 status=mid | |
| [16:28:25] step 5575/8000 | loss=1.8305 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2943600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:28:47] step 5600/8000 | loss=1.8482 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=2956800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:28:56] val/lichess_middlegame hard_ce=1.6249 soft_ce=1.6249 soft_temp_ce=1.6249 teacher_entropy=0.0000 teacher_kl=1.6249 wdl_ce=0.8273 value_rows=8192.0000 | |
| [16:29:18] step 5625/8000 | loss=1.8089 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2970000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:29:40] step 5650/8000 | loss=1.8206 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2983200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:30:02] step 5675/8000 | loss=1.8187 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2996400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:30:24] step 5700/8000 | loss=1.8218 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3009600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:30:24] ckpt step_005700.pt + latest.pt (live) steps=5700 status=mid kind=full | |
| [16:30:33] val/lichess_middlegame hard_ce=1.6264 soft_ce=1.6264 soft_temp_ce=1.6264 teacher_entropy=0.0000 teacher_kl=1.6264 wdl_ce=0.8264 value_rows=8192.0000 | |
| [16:30:55] step 5725/8000 | loss=1.8291 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3022800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:31:17] step 5750/8000 | loss=1.8347 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=3036000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:31:39] step 5775/8000 | loss=1.8355 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3049200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:32:00] step 5800/8000 | loss=1.8137 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=3062400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:32:09] val/lichess_middlegame hard_ce=1.6281 soft_ce=1.6281 soft_temp_ce=1.6281 teacher_entropy=0.0000 teacher_kl=1.6281 wdl_ce=0.8261 value_rows=8192.0000 | |
| [16:32:31] step 5825/8000 | loss=1.8410 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3075600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:32:53] step 5850/8000 | loss=1.8237 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3088800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:32:53] ckpt latest.pt (live weights) steps=5850 status=mid | |
| [16:33:15] step 5875/8000 | loss=1.8255 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3102000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:33:37] step 5900/8000 | loss=1.8148 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3115200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:33:45] val/lichess_middlegame hard_ce=1.6233 soft_ce=1.6233 soft_temp_ce=1.6233 teacher_entropy=0.0000 teacher_kl=1.6233 wdl_ce=0.8266 value_rows=8192.0000 | |
| [16:34:07] step 5925/8000 | loss=1.8323 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3128400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:34:29] step 5950/8000 | loss=1.8280 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3141600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:34:51] step 5975/8000 | loss=1.8106 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3154800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:35:13] step 6000/8000 | loss=1.8148 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3168000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:35:14] ckpt step_006000.pt + latest.pt (live) steps=6000 status=mid kind=full | |
| [16:35:22] val/lichess_middlegame hard_ce=1.6236 soft_ce=1.6236 soft_temp_ce=1.6236 teacher_entropy=0.0000 teacher_kl=1.6236 wdl_ce=0.8269 value_rows=8192.0000 | |
| [16:35:44] step 6025/8000 | loss=1.8212 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3181200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:36:06] step 6050/8000 | loss=1.8295 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3194400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:36:28] step 6075/8000 | loss=1.8237 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3207600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:36:49] step 6100/8000 | loss=1.8313 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3220800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:36:58] val/lichess_middlegame hard_ce=1.6197 soft_ce=1.6197 soft_temp_ce=1.6197 teacher_entropy=0.0000 teacher_kl=1.6197 wdl_ce=0.8272 value_rows=8192.0000 | |
| [16:37:20] step 6125/8000 | loss=1.8176 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=3234000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:37:42] step 6150/8000 | loss=1.8269 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=3247200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:37:42] ckpt latest.pt (live weights) steps=6150 status=mid | |
| [16:38:04] step 6175/8000 | loss=1.8163 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3260400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:38:26] step 6200/8000 | loss=1.8163 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3273600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:38:34] val/lichess_middlegame hard_ce=1.6175 soft_ce=1.6175 soft_temp_ce=1.6175 teacher_entropy=0.0000 teacher_kl=1.6175 wdl_ce=0.8253 value_rows=8192.0000 | |
| [16:38:56] step 6225/8000 | loss=1.8282 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=3286800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:39:18] step 6250/8000 | loss=1.7930 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3300000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:39:40] step 6275/8000 | loss=1.7990 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3313200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:40:01] step 6300/8000 | loss=1.8335 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=3326400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:40:02] ckpt step_006300.pt + latest.pt (live) steps=6300 status=mid kind=full | |
| [16:40:11] val/lichess_middlegame hard_ce=1.6117 soft_ce=1.6117 soft_temp_ce=1.6117 teacher_entropy=0.0000 teacher_kl=1.6117 wdl_ce=0.8249 value_rows=8192.0000 | |
| [16:40:33] step 6325/8000 | loss=1.8411 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3339600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:40:55] step 6350/8000 | loss=1.8262 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3352800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:41:16] step 6375/8000 | loss=1.8238 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3366000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:41:38] step 6400/8000 | loss=1.8276 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3379200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:41:47] val/lichess_middlegame hard_ce=1.6195 soft_ce=1.6195 soft_temp_ce=1.6195 teacher_entropy=0.0000 teacher_kl=1.6195 wdl_ce=0.8262 value_rows=8192.0000 | |
| [16:42:08] step 6425/8000 | loss=1.8324 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=3392400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:42:30] step 6450/8000 | loss=1.8147 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3405600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:42:31] ckpt latest.pt (live weights) steps=6450 status=mid | |
| [16:42:52] step 6475/8000 | loss=1.8208 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=3418800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:43:14] step 6500/8000 | loss=1.8249 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=3432000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:43:23] val/lichess_middlegame hard_ce=1.6179 soft_ce=1.6179 soft_temp_ce=1.6179 teacher_entropy=0.0000 teacher_kl=1.6179 wdl_ce=0.8244 value_rows=8192.0000 | |
| [16:43:45] step 6525/8000 | loss=1.8190 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3445200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:44:06] step 6550/8000 | loss=1.8044 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=3458400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:44:28] step 6575/8000 | loss=1.7972 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=3471600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:44:50] step 6600/8000 | loss=1.8143 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=3484800/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [16:44:51] ckpt step_006600.pt + latest.pt (live) steps=6600 status=mid kind=full | |
| [16:44:59] val/lichess_middlegame hard_ce=1.6190 soft_ce=1.6190 soft_temp_ce=1.6190 teacher_entropy=0.0000 teacher_kl=1.6190 wdl_ce=0.8282 value_rows=8192.0000 | |
| [16:45:21] step 6625/8000 | loss=1.8141 | lr=2.00e-03,3.00e-05 | clip=4/25 | mix s/d/b=3498000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:45:43] step 6650/8000 | loss=1.8182 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=3511200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:46:05] step 6675/8000 | loss=1.8105 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3524400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:46:26] step 6700/8000 | loss=1.8095 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3537600/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [16:46:35] val/lichess_middlegame hard_ce=1.6145 soft_ce=1.6145 soft_temp_ce=1.6145 teacher_entropy=0.0000 teacher_kl=1.6145 wdl_ce=0.8243 value_rows=8192.0000 | |
| [16:46:57] step 6725/8000 | loss=1.8215 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3550800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:47:19] step 6750/8000 | loss=1.8154 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=3564000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:47:19] ckpt latest.pt (live weights) steps=6750 status=mid | |
| [16:47:41] step 6775/8000 | loss=1.8198 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=3577200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:48:03] step 6800/8000 | loss=1.8346 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=3590400/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [16:48:11] val/lichess_middlegame hard_ce=1.6124 soft_ce=1.6124 soft_temp_ce=1.6124 teacher_entropy=0.0000 teacher_kl=1.6124 wdl_ce=0.8269 value_rows=8192.0000 | |
| [16:48:33] step 6825/8000 | loss=1.8082 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=3603600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:48:55] step 6850/8000 | loss=1.8001 | lr=2.00e-03,3.00e-05 | clip=4/25 | mix s/d/b=3616800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:49:17] step 6875/8000 | loss=1.8150 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=3630000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:49:39] step 6900/8000 | loss=1.8227 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3643200/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [16:49:39] ckpt step_006900.pt + latest.pt (live) steps=6900 status=mid kind=full | |
| [16:49:48] val/lichess_middlegame hard_ce=1.6116 soft_ce=1.6116 soft_temp_ce=1.6116 teacher_entropy=0.0000 teacher_kl=1.6116 wdl_ce=0.8233 value_rows=8192.0000 | |
| [16:50:10] step 6925/8000 | loss=1.8322 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3656400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:50:32] step 6950/8000 | loss=1.8302 | lr=2.00e-03,3.00e-05 | clip=4/25 | mix s/d/b=3669600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:50:53] step 6975/8000 | loss=1.8252 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3682800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:51:15] step 7000/8000 | loss=1.7971 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=3696000/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [16:51:24] val/lichess_middlegame hard_ce=1.6111 soft_ce=1.6111 soft_temp_ce=1.6111 teacher_entropy=0.0000 teacher_kl=1.6111 wdl_ce=0.8245 value_rows=8192.0000 | |
| [16:51:46] step 7025/8000 | loss=1.8155 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3709200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:52:07] step 7050/8000 | loss=1.8314 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=3722400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:52:08] ckpt latest.pt (live weights) steps=7050 status=mid | |
| [16:52:30] step 7075/8000 | loss=1.8187 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=3735600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:52:51] step 7100/8000 | loss=1.8000 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3748800/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [16:53:00] val/lichess_middlegame hard_ce=1.6097 soft_ce=1.6097 soft_temp_ce=1.6097 teacher_entropy=0.0000 teacher_kl=1.6097 wdl_ce=0.8261 value_rows=8192.0000 | |
| [16:53:22] step 7125/8000 | loss=1.8230 | lr=2.00e-03,3.00e-05 | clip=4/25 | mix s/d/b=3762000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:53:44] step 7150/8000 | loss=1.8191 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=3775200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:54:05] step 7175/8000 | loss=1.8117 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=3788400/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [16:54:27] step 7200/8000 | loss=1.8353 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3801600/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [16:54:28] ckpt step_007200.pt + latest.pt (live) steps=7200 status=mid kind=full | |
| [16:54:37] val/lichess_middlegame hard_ce=1.6048 soft_ce=1.6048 soft_temp_ce=1.6048 teacher_entropy=0.0000 teacher_kl=1.6048 wdl_ce=0.8232 value_rows=8192.0000 | |
| [16:54:59] step 7225/8000 | loss=1.8280 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=3814800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:55:21] step 7250/8000 | loss=1.8046 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3828000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:55:43] step 7275/8000 | loss=1.7930 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=3841200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:56:05] step 7300/8000 | loss=1.8203 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3854400/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [16:56:13] val/lichess_middlegame hard_ce=1.6071 soft_ce=1.6071 soft_temp_ce=1.6071 teacher_entropy=0.0000 teacher_kl=1.6071 wdl_ce=0.8238 value_rows=8192.0000 | |
| [16:56:35] step 7325/8000 | loss=1.7890 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3867600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:56:57] step 7350/8000 | loss=1.8235 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=3880800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:56:58] ckpt latest.pt (live weights) steps=7350 status=mid | |
| [16:57:19] step 7375/8000 | loss=1.8038 | lr=2.00e-03,3.00e-05 | clip=4/25 | mix s/d/b=3894000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:57:41] step 7400/8000 | loss=1.8178 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3907200/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [16:57:50] val/lichess_middlegame hard_ce=1.6080 soft_ce=1.6080 soft_temp_ce=1.6080 teacher_entropy=0.0000 teacher_kl=1.6080 wdl_ce=0.8239 value_rows=8192.0000 | |
| [16:58:12] step 7425/8000 | loss=1.8189 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=3920400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:58:33] step 7450/8000 | loss=1.8096 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=3933600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [16:58:55] step 7475/8000 | loss=1.8362 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=3946800/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [16:59:17] step 7500/8000 | loss=1.8384 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3960000/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [16:59:18] ckpt step_007500.pt + latest.pt (live) steps=7500 status=mid kind=full | |
| [16:59:27] val/lichess_middlegame hard_ce=1.6067 soft_ce=1.6067 soft_temp_ce=1.6067 teacher_entropy=0.0000 teacher_kl=1.6067 wdl_ce=0.8241 value_rows=8192.0000 | |
| [16:59:48] step 7525/8000 | loss=1.8072 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=3973200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [17:00:10] step 7550/8000 | loss=1.8360 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=3986400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [17:00:32] step 7575/8000 | loss=1.7944 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=3999600/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [17:00:54] step 7600/8000 | loss=1.8073 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=4012800/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [17:01:03] val/lichess_middlegame hard_ce=1.6090 soft_ce=1.6090 soft_temp_ce=1.6090 teacher_entropy=0.0000 teacher_kl=1.6090 wdl_ce=0.8236 value_rows=8192.0000 | |
| [17:01:24] step 7625/8000 | loss=1.8246 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=4026000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [17:01:46] step 7650/8000 | loss=1.8046 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=4039200/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [17:01:47] ckpt latest.pt (live weights) steps=7650 status=mid | |
| [17:02:08] step 7675/8000 | loss=1.8144 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=4052400/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [17:02:30] step 7700/8000 | loss=1.8193 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=4065600/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [17:02:39] val/lichess_middlegame hard_ce=1.6089 soft_ce=1.6089 soft_temp_ce=1.6089 teacher_entropy=0.0000 teacher_kl=1.6089 wdl_ce=0.8244 value_rows=8192.0000 | |
| [17:03:01] step 7725/8000 | loss=1.7926 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=4078800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [17:03:22] step 7750/8000 | loss=1.8179 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=4092000/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [17:03:44] step 7775/8000 | loss=1.8241 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=4105200/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [17:04:06] step 7800/8000 | loss=1.7913 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=4118400/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [17:04:07] ckpt step_007800.pt + latest.pt (live) steps=7800 status=mid kind=full | |
| [17:04:15] val/lichess_middlegame hard_ce=1.6088 soft_ce=1.6088 soft_temp_ce=1.6088 teacher_entropy=0.0000 teacher_kl=1.6088 wdl_ce=0.8242 value_rows=8192.0000 | |
| [17:04:37] step 7825/8000 | loss=1.8154 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=4131600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [17:04:59] step 7850/8000 | loss=1.8330 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=4144800/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [17:05:21] step 7875/8000 | loss=1.8230 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=4158000/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [17:05:43] step 7900/8000 | loss=1.7989 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=4171200/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [17:05:51] val/lichess_middlegame hard_ce=1.6058 soft_ce=1.6058 soft_temp_ce=1.6058 teacher_entropy=0.0000 teacher_kl=1.6058 wdl_ce=0.8312 value_rows=8192.0000 | |
| [17:06:13] step 7925/8000 | loss=1.8021 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=4184400/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [17:06:35] step 7950/8000 | loss=1.8280 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=4197600/0/0 q=0 p=0 | 546 pos/s | vram=35.73GB | |
| [17:06:35] ckpt latest.pt (live weights) steps=7950 status=mid | |
| [17:06:57] step 7975/8000 | loss=1.7964 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=4210800/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [17:07:19] step 8000/8000 | loss=1.7870 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=4224000/0/0 q=0 p=0 | 547 pos/s | vram=35.73GB | |
| [17:07:28] val/lichess_middlegame hard_ce=1.6071 soft_ce=1.6071 soft_temp_ce=1.6071 teacher_entropy=0.0000 teacher_kl=1.6071 wdl_ce=0.8252 value_rows=8192.0000 | |
| [17:07:28] timing wall=7734s active=6935s steps=8000 status=trained | |
| [17:07:28] done steps=8000 pos_s=546.2 params=98.97M status=trained kind=full | |