fbfhbfbfbv / day50 /eval128.log
td-builder's picture
Duplicate from td-builder/RSI
77f690c
Raw History Blame Contribute Delete
8.07 kB
[pair] 80 eval problems | BASE=/workspace/RSI/newbase ADAPTER=/workspace/RSI/outputs/af/teach_adapter_128
[transformers] `torch_dtype` is deprecated! Use `dtype` instead!
Loading weights: 0%| | 0/771 [00:00<?, ?it/s] Loading weights: 0%| | 1/771 [00:00<04:25, 2.90it/s] Loading weights: 0%| | 2/771 [00:00<04:22, 2.93it/s] Loading weights: 1%| | 4/771 [00:00<02:10, 5.90it/s] Loading weights: 1%| | 9/771 [00:00<00:50, 15.06it/s] Loading weights: 2%|▏ | 17/771 [00:01<00:26, 28.57it/s] Loading weights: 4%|β–Ž | 28/771 [00:01<00:16, 45.16it/s] Loading weights: 4%|▍ | 34/771 [00:01<00:15, 47.14it/s] Loading weights: 5%|β–Œ | 41/771 [00:01<00:14, 50.91it/s] Loading weights: 7%|β–‹ | 52/771 [00:01<00:11, 62.00it/s] Loading weights: 8%|β–Š | 59/771 [00:01<00:11, 61.99it/s] Loading weights: 9%|β–Š | 66/771 [00:01<00:12, 55.19it/s] Loading weights: 10%|β–‰ | 77/771 [00:01<00:10, 64.65it/s] Loading weights: 11%|β–ˆβ– | 88/771 [00:02<00:09, 71.02it/s] Loading weights: 12%|β–ˆβ– | 96/771 [00:02<00:09, 69.21it/s] Loading weights: 13%|β–ˆβ–Ž | 104/771 [00:02<00:10, 62.15it/s] Loading weights: 15%|β–ˆβ– | 113/771 [00:02<00:10, 63.72it/s] Loading weights: 16%|β–ˆβ–Œ | 124/771 [00:02<00:09, 68.80it/s] Loading weights: 17%|β–ˆβ–‹ | 131/771 [00:02<00:09, 67.85it/s] Loading weights: 18%|β–ˆβ–Š | 138/771 [00:02<00:10, 58.80it/s] Loading weights: 19%|β–ˆβ–‰ | 149/771 [00:03<00:09, 65.66it/s] Loading weights: 21%|β–ˆβ–ˆ | 160/771 [00:03<00:08, 70.88it/s] Loading weights: 22%|β–ˆβ–ˆβ– | 168/771 [00:03<00:08, 68.25it/s] Loading weights: 23%|β–ˆβ–ˆβ–Ž | 175/771 [00:03<00:09, 59.82it/s] Loading weights: 24%|β–ˆβ–ˆβ– | 185/771 [00:03<00:09, 64.44it/s] Loading weights: 25%|β–ˆβ–ˆβ–Œ | 196/771 [00:03<00:08, 70.03it/s] Loading weights: 26%|β–ˆβ–ˆβ–‹ | 204/771 [00:03<00:08, 69.28it/s] Loading weights: 27%|β–ˆβ–ˆβ–‹ | 212/771 [00:03<00:08, 64.02it/s] Loading weights: 29%|β–ˆβ–ˆβ–Š | 221/771 [00:04<00:08, 66.63it/s] Loading weights: 30%|β–ˆβ–ˆβ–ˆ | 232/771 [00:04<00:07, 73.03it/s] Loading weights: 31%|β–ˆβ–ˆβ–ˆ | 240/771 [00:04<00:07, 71.34it/s] Loading weights: 32%|β–ˆβ–ˆβ–ˆβ– | 248/771 [00:04<00:08, 64.98it/s] Loading weights: 33%|β–ˆβ–ˆβ–ˆβ–Ž | 257/771 [00:04<00:07, 67.76it/s] Loading weights: 35%|β–ˆβ–ˆβ–ˆβ– | 268/771 [00:04<00:06, 74.23it/s] Loading weights: 36%|β–ˆβ–ˆβ–ˆβ–Œ | 276/771 [00:04<00:06, 72.51it/s] Loading weights: 37%|β–ˆβ–ˆβ–ˆβ–‹ | 284/771 [00:04<00:07, 66.54it/s] Loading weights: 38%|β–ˆβ–ˆβ–ˆβ–Š | 293/771 [00:05<00:06, 68.69it/s] Loading weights: 39%|β–ˆβ–ˆβ–ˆβ–‰ | 304/771 [00:05<00:06, 75.11it/s] Loading weights: 40%|β–ˆβ–ˆβ–ˆβ–ˆ | 312/771 [00:05<00:06, 73.01it/s] Loading weights: 42%|β–ˆβ–ˆβ–ˆβ–ˆβ– | 320/771 [00:05<00:06, 66.84it/s] Loading weights: 43%|β–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 329/771 [00:05<00:06, 69.10it/s] Loading weights: 44%|β–ˆβ–ˆβ–ˆβ–ˆβ– | 340/771 [00:05<00:05, 76.28it/s] Loading weights: 45%|β–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 348/771 [00:05<00:05, 74.97it/s] Loading weights: 46%|β–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 356/771 [00:05<00:05, 69.19it/s] Loading weights: 47%|β–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 365/771 [00:06<00:05, 72.08it/s] Loading weights: 49%|β–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 376/771 [00:06<00:05, 78.68it/s] Loading weights: 50%|β–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 384/771 [00:06<00:05, 76.66it/s] Loading weights: 51%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 392/771 [00:06<00:05, 70.17it/s] Loading weights: 52%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 401/771 [00:06<00:05, 72.62it/s] Loading weights: 53%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 412/771 [00:06<00:04, 79.07it/s] Loading weights: 54%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 420/771 [00:06<00:04, 77.39it/s] Loading weights: 56%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 428/771 [00:06<00:04, 71.55it/s] Loading weights: 57%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 437/771 [00:07<00:04, 72.16it/s] Loading weights: 58%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 448/771 [00:07<00:04, 77.80it/s] Loading weights: 59%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 456/771 [00:07<00:04, 72.22it/s] Loading weights: 60%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 464/771 [00:07<00:04, 65.20it/s] Loading weights: 61%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 473/771 [00:07<00:04, 67.69it/s] Loading weights: 63%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 484/771 [00:07<00:04, 70.81it/s] Loading weights: 64%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 492/771 [00:07<00:04, 69.55it/s] Loading weights: 65%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 499/771 [00:08<00:04, 57.93it/s] Loading weights: 66%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 509/771 [00:08<00:04, 59.47it/s] Loading weights: 67%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 520/771 [00:08<00:03, 64.02it/s] Loading weights: 68%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 527/771 [00:08<00:03, 61.47it/s] Loading weights: 69%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 534/771 [00:08<00:04, 55.58it/s] Loading weights: 71%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 545/771 [00:08<00:03, 64.25it/s] Loading weights: 72%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 552/771 [00:08<00:03, 64.06it/s] Loading weights: 73%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 559/771 [00:09<00:03, 58.20it/s] Loading weights: 74%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 569/771 [00:09<00:03, 59.93it/s] Loading weights: 75%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 580/771 [00:09<00:02, 64.89it/s] Loading weights: 76%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 587/771 [00:09<00:02, 61.71it/s] Loading weights: 77%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 594/771 [00:09<00:03, 51.28it/s] Loading weights: 78%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 605/771 [00:09<00:02, 56.88it/s] Loading weights: 80%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 616/771 [00:09<00:02, 60.47it/s] Loading weights: 81%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 623/771 [00:10<00:02, 57.38it/s] Loading weights: 82%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 629/771 [00:10<00:02, 53.33it/s] Loading weights: 83%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 640/771 [00:10<00:02, 60.13it/s] Loading weights: 84%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 647/771 [00:10<00:02, 55.59it/s] Loading weights: 85%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 653/771 [00:10<00:02, 51.68it/s] Loading weights: 86%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 664/771 [00:10<00:01, 57.02it/s] Loading weights: 87%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 670/771 [00:10<00:01, 52.60it/s] Loading weights: 88%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 677/771 [00:11<00:01, 51.59it/s] Loading weights: 89%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 688/771 [00:11<00:01, 57.33it/s] Loading weights: 90%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 694/771 [00:11<00:01, 52.42it/s] Loading weights: 91%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 701/771 [00:11<00:01, 51.08it/s] Loading weights: 92%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–| 712/771 [00:11<00:01, 53.94it/s] Loading weights: 93%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž| 718/771 [00:11<00:01, 50.60it/s] Loading weights: 94%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–| 725/771 [00:12<00:00, 50.28it/s] Loading weights: 95%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ| 736/771 [00:12<00:00, 55.64it/s] Loading weights: 96%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ| 742/771 [00:12<00:00, 51.28it/s] Loading weights: 97%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹| 749/771 [00:12<00:00, 49.50it/s] Loading weights: 98%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š| 758/771 [00:12<00:00, 58.28it/s] Loading weights: 99%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰| 765/771 [00:12<00:00, 49.05it/s] Loading weights: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 771/771 [00:12<00:00, 59.98it/s]
[pair] loaded 4bit HF base + PEFT adapter OK
=== BASE arm (adapter DISABLED) ===
[pair] 8/80
[pair] 16/80
[pair] 24/80
[pair] 32/80
[pair] 40/80
[pair] 48/80
[pair] 56/80
[pair] 64/80
[pair] 72/80
[pair] 80/80
HOLDOUT[base] = 7/80 mean_partial=0.2718
=== TEACH arm (adapter ENABLED) ===
[pair] 8/80
[pair] 16/80
[pair] 24/80
[pair] 32/80
[pair] 40/80
[pair] 48/80
[pair] 56/80
[pair] 64/80
[pair] 72/80
[pair] 80/80
HOLDOUT[teach] = 6/80 mean_partial=0.3971
TEACHER VERDICT: DEAD | base=7/80 teach=6/80 D=-1 gained=3 lost=4 McNemar_z=-0.38 | partial base_mp=0.2718 teach_mp=0.3971 Dmp=+0.1253 improved=42 worsened=16 sign_z=3.41 | backend=hf-4bit SAME both arms
PAIR_DONE