| 2026-06-21 04:59:30,776 | T4/P100 (Tesla T4 sm_75): Flash unavailable, using chunked attn |
| 2026-06-21 04:59:31,010 | HTTP Request: GET https://huggingface.co/api/agent-harnesses "HTTP/1.1 200 OK" |
| 2026-06-21 04:59:31,074 | HTTP Request: GET https://huggingface.co/api/whoami-v2 "HTTP/1.1 200 OK" |
| 2026-06-21 04:59:31,141 | HTTP Request: HEAD https://huggingface.co/GODELEV/TOK-8K/resolve/main/config.json "HTTP/1.1 404 Not Found" |
| 2026-06-21 04:59:31,208 | HTTP Request: HEAD https://huggingface.co/GODELEV/TOK-8K/resolve/main/config.json "HTTP/1.1 404 Not Found" |
| 2026-06-21 04:59:31,277 | HTTP Request: HEAD https://huggingface.co/GODELEV/TOK-8K/resolve/main/tokenizer_config.json "HTTP/1.1 307 Temporary Redirect" |
| 2026-06-21 04:59:31,294 | HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/GODELEV/TOK-8K/c2e8c2d4f1641e1f0292f732e5f1875b6b9aa5dc/tokenizer_config.json "HTTP/1.1 200 OK" |
| 2026-06-21 04:59:31,313 | HTTP Request: GET https://huggingface.co/api/resolve-cache/models/GODELEV/TOK-8K/c2e8c2d4f1641e1f0292f732e5f1875b6b9aa5dc/tokenizer_config.json "HTTP/1.1 200 OK" |
| 2026-06-21 04:59:31,402 | HTTP Request: GET https://huggingface.co/api/models/GODELEV/TOK-8K/tree/main/additional_chat_templates?recursive=false&expand=false "HTTP/1.1 404 Not Found" |
| 2026-06-21 04:59:31,481 | HTTP Request: GET https://huggingface.co/api/models/GODELEV/TOK-8K/tree/main?recursive=true&expand=false "HTTP/1.1 200 OK" |
| 2026-06-21 04:59:31,544 | HTTP Request: HEAD https://huggingface.co/GODELEV/TOK-8K/resolve/main/tokenizer.json "HTTP/1.1 307 Temporary Redirect" |
| 2026-06-21 04:59:31,562 | HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/GODELEV/TOK-8K/c2e8c2d4f1641e1f0292f732e5f1875b6b9aa5dc/tokenizer.json "HTTP/1.1 200 OK" |
| 2026-06-21 04:59:31,580 | HTTP Request: GET https://huggingface.co/api/resolve-cache/models/GODELEV/TOK-8K/c2e8c2d4f1641e1f0292f732e5f1875b6b9aa5dc/tokenizer.json "HTTP/1.1 200 OK" |
| 2026-06-21 04:59:31,689 | HTTP Request: HEAD https://huggingface.co/GODELEV/TOK-8K/resolve/main/tokenizer.model "HTTP/1.1 404 Not Found" |
| 2026-06-21 04:59:31,770 | HTTP Request: HEAD https://huggingface.co/GODELEV/TOK-8K/resolve/main/added_tokens.json "HTTP/1.1 404 Not Found" |
| 2026-06-21 04:59:31,838 | HTTP Request: HEAD https://huggingface.co/GODELEV/TOK-8K/resolve/main/special_tokens_map.json "HTTP/1.1 307 Temporary Redirect" |
| 2026-06-21 04:59:31,855 | HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/GODELEV/TOK-8K/c2e8c2d4f1641e1f0292f732e5f1875b6b9aa5dc/special_tokens_map.json "HTTP/1.1 200 OK" |
| 2026-06-21 04:59:31,874 | HTTP Request: GET https://huggingface.co/api/resolve-cache/models/GODELEV/TOK-8K/c2e8c2d4f1641e1f0292f732e5f1875b6b9aa5dc/special_tokens_map.json "HTTP/1.1 200 OK" |
| 2026-06-21 04:59:31,956 | HTTP Request: HEAD https://huggingface.co/GODELEV/TOK-8K/resolve/main/chat_template.jinja "HTTP/1.1 404 Not Found" |
| 2026-06-21 04:59:32,093 | HTTP Request: HEAD https://huggingface.co/datasets/GODELEV/D1-8-Lite/resolve/main/README.md "HTTP/1.1 404 Not Found" |
| 2026-06-21 04:59:32,180 | HTTP Request: GET https://huggingface.co/api/datasets/GODELEV/D1-8-Lite "HTTP/1.1 200 OK" |
| 2026-06-21 04:59:32,247 | HTTP Request: HEAD https://huggingface.co/datasets/GODELEV/D1-8-Lite/resolve/f12e00e7ed44fcf09dd0bedf10392c8440d74699/D1-8-Lite.py "HTTP/1.1 404 Not Found" |
| 2026-06-21 04:59:32,359 | HTTP Request: HEAD https://s3.amazonaws.com/datasets.huggingface.co/datasets/datasets/GODELEV/D1-8-Lite/GODELEV/D1-8-Lite.py "HTTP/1.1 404 Not Found" |
| 2026-06-21 04:59:32,424 | HTTP Request: HEAD https://huggingface.co/datasets/GODELEV/D1-8-Lite/resolve/f12e00e7ed44fcf09dd0bedf10392c8440d74699/README.md "HTTP/1.1 404 Not Found" |
| 2026-06-21 04:59:32,490 | HTTP Request: GET https://huggingface.co/api/datasets/GODELEV/D1-8-Lite/revision/f12e00e7ed44fcf09dd0bedf10392c8440d74699 "HTTP/1.1 200 OK" |
| 2026-06-21 04:59:32,562 | HTTP Request: HEAD https://huggingface.co/datasets/GODELEV/D1-8-Lite/resolve/f12e00e7ed44fcf09dd0bedf10392c8440d74699/.huggingface.yaml "HTTP/1.1 404 Not Found" |
| 2026-06-21 04:59:32,689 | HTTP Request: GET https://datasets-server.huggingface.co/info?dataset=GODELEV/D1-8-Lite "HTTP/1.1 200 OK" |
| 2026-06-21 04:59:32,796 | HTTP Request: GET https://huggingface.co/api/datasets/GODELEV/D1-8-Lite/tree/f12e00e7ed44fcf09dd0bedf10392c8440d74699/data?recursive=true&expand=false "HTTP/1.1 200 OK" |
| 2026-06-21 04:59:32,910 | HTTP Request: GET https://huggingface.co/api/datasets/GODELEV/D1-8-Lite/tree/f12e00e7ed44fcf09dd0bedf10392c8440d74699?recursive=false&expand=false "HTTP/1.1 200 OK" |
| 2026-06-21 04:59:33,007 | HTTP Request: HEAD https://huggingface.co/datasets/GODELEV/D1-8-Lite/resolve/f12e00e7ed44fcf09dd0bedf10392c8440d74699/dataset_infos.json "HTTP/1.1 404 Not Found" |
| 2026-06-21 04:59:33,126 | HTTP Request: HEAD https://huggingface.co/datasets/GODELEV/D1-8-Lite/resolve/f12e00e7ed44fcf09dd0bedf10392c8440d74699/data/train-00000-of-00015.parquet "HTTP/1.1 302 Found" |
| 2026-06-21 04:59:36,854 | HTTP Request: HEAD https://huggingface.co/datasets/GODELEV/D1-8-Lite/resolve/f12e00e7ed44fcf09dd0bedf10392c8440d74699/data/train-00001-of-00015.parquet "HTTP/1.1 302 Found" |
| 2026-06-21 04:59:40,818 | HTTP Request: HEAD https://huggingface.co/datasets/GODELEV/D1-8-Lite/resolve/f12e00e7ed44fcf09dd0bedf10392c8440d74699/data/train-00002-of-00015.parquet "HTTP/1.1 302 Found" |
| 2026-06-21 04:59:43,033 | HTTP Request: HEAD https://huggingface.co/datasets/GODELEV/D1-8-Lite/resolve/f12e00e7ed44fcf09dd0bedf10392c8440d74699/data/train-00003-of-00015.parquet "HTTP/1.1 302 Found" |
| 2026-06-21 04:59:47,356 | HTTP Request: HEAD https://huggingface.co/datasets/GODELEV/D1-8-Lite/resolve/f12e00e7ed44fcf09dd0bedf10392c8440d74699/data/train-00004-of-00015.parquet "HTTP/1.1 302 Found" |
| 2026-06-21 04:59:50,356 | HTTP Request: HEAD https://huggingface.co/datasets/GODELEV/D1-8-Lite/resolve/f12e00e7ed44fcf09dd0bedf10392c8440d74699/data/train-00005-of-00015.parquet "HTTP/1.1 302 Found" |
| 2026-06-21 04:59:52,523 | HTTP Request: HEAD https://huggingface.co/datasets/GODELEV/D1-8-Lite/resolve/f12e00e7ed44fcf09dd0bedf10392c8440d74699/data/train-00006-of-00015.parquet "HTTP/1.1 302 Found" |
| 2026-06-21 04:59:56,560 | HTTP Request: HEAD https://huggingface.co/datasets/GODELEV/D1-8-Lite/resolve/f12e00e7ed44fcf09dd0bedf10392c8440d74699/data/train-00007-of-00015.parquet "HTTP/1.1 302 Found" |
| 2026-06-21 05:00:00,867 | HTTP Request: HEAD https://huggingface.co/datasets/GODELEV/D1-8-Lite/resolve/f12e00e7ed44fcf09dd0bedf10392c8440d74699/data/train-00008-of-00015.parquet "HTTP/1.1 302 Found" |
| 2026-06-21 05:00:03,060 | HTTP Request: HEAD https://huggingface.co/datasets/GODELEV/D1-8-Lite/resolve/f12e00e7ed44fcf09dd0bedf10392c8440d74699/data/train-00009-of-00015.parquet "HTTP/1.1 302 Found" |
| 2026-06-21 05:00:04,861 | HTTP Request: HEAD https://huggingface.co/datasets/GODELEV/D1-8-Lite/resolve/f12e00e7ed44fcf09dd0bedf10392c8440d74699/data/train-00010-of-00015.parquet "HTTP/1.1 302 Found" |
| 2026-06-21 05:00:09,614 | HTTP Request: HEAD https://huggingface.co/datasets/GODELEV/D1-8-Lite/resolve/f12e00e7ed44fcf09dd0bedf10392c8440d74699/data/train-00011-of-00015.parquet "HTTP/1.1 302 Found" |
| 2026-06-21 05:00:12,382 | HTTP Request: HEAD https://huggingface.co/datasets/GODELEV/D1-8-Lite/resolve/f12e00e7ed44fcf09dd0bedf10392c8440d74699/data/train-00012-of-00015.parquet "HTTP/1.1 302 Found" |
| 2026-06-21 05:00:14,593 | HTTP Request: HEAD https://huggingface.co/datasets/GODELEV/D1-8-Lite/resolve/f12e00e7ed44fcf09dd0bedf10392c8440d74699/data/train-00013-of-00015.parquet "HTTP/1.1 302 Found" |
| 2026-06-21 05:00:21,150 | HTTP Request: HEAD https://huggingface.co/datasets/GODELEV/D1-8-Lite/resolve/f12e00e7ed44fcf09dd0bedf10392c8440d74699/data/train-00014-of-00015.parquet "HTTP/1.1 302 Found" |
| 2026-06-21 05:00:23,380 | HTTP Request: HEAD https://huggingface.co/datasets/GODELEV/D1-8-Lite/resolve/f12e00e7ed44fcf09dd0bedf10392c8440d74699/data/val-00000-of-00001.parquet "HTTP/1.1 302 Found" |
| 2026-06-21 05:02:37,389 | Data loaded train=5,901,696 val=200,000 steps_per_epoch=5,764 total_epochs=1.00 |
| 2026-06-21 05:02:40,503 | Model 9.853M params | float32 | amp=torch.float16 | compiled=True | attn=chunked |
| 2026-06-21 05:02:40,739 | HTTP Request: HEAD https://huggingface.co/CyanMonkey/Exp-3/resolve/main/resume/latest_step.txt "HTTP/1.1 307 Temporary Redirect" |
| 2026-06-21 05:02:40,850 | HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/CyanMonkey/Exp-3/a78b3e0c380bf750df2e81e90e774c99bbd334bd/resume%2Flatest_step.txt "HTTP/1.1 200 OK" |
| 2026-06-21 05:02:40,967 | HTTP Request: GET https://huggingface.co/api/resolve-cache/models/CyanMonkey/Exp-3/a78b3e0c380bf750df2e81e90e774c99bbd334bd/resume%2Flatest_step.txt "HTTP/1.1 200 OK" |
| 2026-06-21 05:02:41,056 | HTTP Request: HEAD https://huggingface.co/CyanMonkey/Exp-3/resolve/main/resume/ckpt.pt "HTTP/1.1 302 Found" |
| 2026-06-21 05:02:44,672 | Resumed step=4400 tokens=4609228800 samples=4505600 |
| 2026-06-21 05:08:55,875 | step= 4420 | epoch=0.77 | loss=2.4509 | ppl=11.60 | lr=6.83e-05 | grad=0.701 | tok/s=69,874 | ETA=5:35:49 | VRAM=0.7GB | RAM=18% |
| 2026-06-21 05:13:54,557 | step= 4440 | epoch=0.77 | loss=2.4030 | ppl=11.06 | lr=6.72e-05 | grad=0.760 | tok/s=70,266 | ETA=5:28:58 | VRAM=0.7GB | RAM=18% |
| 2026-06-21 05:18:52,771 | step= 4460 | epoch=0.77 | loss=2.4228 | ppl=11.28 | lr=6.61e-05 | grad=0.620 | tok/s=70,267 | ETA=5:24:00 | VRAM=0.7GB | RAM=18% |
| 2026-06-21 05:23:51,031 | step= 4480 | epoch=0.78 | loss=2.3738 | ppl=10.74 | lr=6.51e-05 | grad=0.626 | tok/s=70,255 | ETA=5:19:05 | VRAM=0.7GB | RAM=18% |
| 2026-06-21 05:28:49,287 | step= 4500 | epoch=0.78 | loss=2.3390 | ppl=10.37 | lr=6.40e-05 | grad=0.578 | tok/s=70,338 | ETA=5:13:44 | VRAM=0.7GB | RAM=18% |
| 2026-06-21 05:33:48,086 | step= 4520 | epoch=0.78 | loss=2.3736 | ppl=10.74 | lr=6.30e-05 | grad=0.656 | tok/s=70,180 | ETA=5:09:28 | VRAM=0.7GB | RAM=18% |
| 2026-06-21 05:38:46,468 | step= 4540 | epoch=0.79 | loss=2.3175 | ppl=10.15 | lr=6.20e-05 | grad=0.631 | tok/s=70,129 | ETA=5:04:43 | VRAM=0.7GB | RAM=18% |
| 2026-06-21 05:43:45,267 | step= 4560 | epoch=0.79 | loss=2.3865 | ppl=10.87 | lr=6.10e-05 | grad=0.704 | tok/s=70,062 | ETA=5:00:01 | VRAM=0.7GB | RAM=18% |
| 2026-06-21 05:48:44,247 | step= 4580 | epoch=0.79 | loss=2.3261 | ppl=10.24 | lr=6.00e-05 | grad=0.611 | tok/s=69,954 | ETA=4:55:30 | VRAM=0.7GB | RAM=18% |
| 2026-06-21 05:53:43,360 | step= 4600 | epoch=0.80 | loss=2.3882 | ppl=10.89 | lr=5.91e-05 | grad=0.646 | tok/s=69,958 | ETA=4:50:29 | VRAM=0.7GB | RAM=18% |
| 2026-06-21 05:58:42,493 | step= 4620 | epoch=0.80 | loss=2.3308 | ppl=10.29 | lr=5.81e-05 | grad=0.619 | tok/s=70,082 | ETA=4:44:59 | VRAM=0.7GB | RAM=18% |
| 2026-06-21 06:03:41,556 | step= 4640 | epoch=0.80 | loss=2.3956 | ppl=10.97 | lr=5.72e-05 | grad=0.544 | tok/s=69,970 | ETA=4:40:27 | VRAM=0.7GB | RAM=18% |
| 2026-06-21 06:08:41,006 | step= 4660 | epoch=0.81 | loss=2.3158 | ppl=10.13 | lr=5.62e-05 | grad=0.540 | tok/s=69,894 | ETA=4:35:46 | VRAM=0.7GB | RAM=18% |
| 2026-06-21 06:13:39,905 | step= 4680 | epoch=0.81 | loss=2.4054 | ppl=11.08 | lr=5.53e-05 | grad=0.723 | tok/s=70,336 | ETA=4:29:04 | VRAM=0.7GB | RAM=18% |
| 2026-06-21 06:18:38,192 | step= 4700 | epoch=0.82 | loss=2.3174 | ppl=10.15 | lr=5.44e-05 | grad=0.529 | tok/s=70,013 | ETA=4:25:19 | VRAM=0.7GB | RAM=18% |
| 2026-06-21 06:23:37,753 | step= 4720 | epoch=0.82 | loss=2.3958 | ppl=10.98 | lr=5.36e-05 | grad=0.859 | tok/s=69,999 | ETA=4:20:23 | VRAM=0.7GB | RAM=18% |
| 2026-06-21 06:28:37,262 | step= 4740 | epoch=0.82 | loss=2.2913 | ppl=9.89 | lr=5.27e-05 | grad=0.640 | tok/s=69,954 | ETA=4:15:34 | VRAM=0.7GB | RAM=18% |
| 2026-06-21 06:33:36,861 | step= 4760 | epoch=0.83 | loss=2.3658 | ppl=10.65 | lr=5.18e-05 | grad=0.682 | tok/s=69,983 | ETA=4:10:28 | VRAM=0.7GB | RAM=18% |
| 2026-06-21 06:38:36,008 | step= 4780 | epoch=0.83 | loss=2.3585 | ppl=10.58 | lr=5.10e-05 | grad=0.555 | tok/s=69,955 | ETA=4:05:34 | VRAM=0.7GB | RAM=18% |
| 2026-06-21 06:43:34,949 | step= 4800 | epoch=0.83 | loss=2.3004 | ppl=9.98 | lr=5.02e-05 | grad=1.200 | tok/s=70,165 | ETA=3:59:52 | VRAM=0.7GB | RAM=18% |
| 2026-06-21 07:00:59,419 | VAL step=4800 epoch=0.83 loss=2.4049 ppl=11.08 ★ BEST |
| 2026-06-21 07:00:59,592 | Checkpoint saved: step 4800 |
| 2026-06-21 07:00:59,666 | Saved safetensors: 101 tensors |
| 2026-06-21 07:00:59,988 | HTTP Request: POST https://huggingface.co/api/repos/create "HTTP/1.1 409 Conflict" |
| 2026-06-21 07:01:00,054 | HTTP Request: POST https://huggingface.co/api/validate-yaml "HTTP/1.1 200 OK" |
| 2026-06-21 07:01:00,141 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-3/preupload/main "HTTP/1.1 200 OK" |
| 2026-06-21 07:01:12,147 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-3/commit/main "HTTP/1.1 200 OK" |
| 2026-06-21 07:01:12,151 | Hub push step=4800 |
| 2026-06-21 07:06:11,610 | step= 4820 | epoch=0.84 | loss=2.2441 | ppl=9.43 | lr=4.94e-05 | grad=0.761 | tok/s=70,208 | ETA=3:54:45 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 07:11:10,714 | step= 4840 | epoch=0.84 | loss=2.1300 | ppl=8.42 | lr=4.86e-05 | grad=0.730 | tok/s=70,044 | ETA=3:50:18 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 07:16:09,956 | step= 4860 | epoch=0.84 | loss=2.1810 | ppl=8.85 | lr=4.78e-05 | grad=0.822 | tok/s=70,063 | ETA=3:45:16 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 07:21:08,660 | step= 4880 | epoch=0.85 | loss=2.1566 | ppl=8.64 | lr=4.70e-05 | grad=0.725 | tok/s=70,299 | ETA=3:39:32 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 07:26:06,622 | step= 4900 | epoch=0.85 | loss=2.0882 | ppl=8.07 | lr=4.63e-05 | grad=0.722 | tok/s=70,355 | ETA=3:34:24 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 07:31:05,060 | step= 4920 | epoch=0.85 | loss=2.0157 | ppl=7.51 | lr=4.56e-05 | grad=0.850 | tok/s=70,152 | ETA=3:30:03 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 07:36:03,905 | step= 4940 | epoch=0.86 | loss=2.0546 | ppl=7.80 | lr=4.49e-05 | grad=0.850 | tok/s=70,073 | ETA=3:25:18 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 07:41:01,817 | step= 4960 | epoch=0.86 | loss=2.1003 | ppl=8.17 | lr=4.42e-05 | grad=0.804 | tok/s=70,284 | ETA=3:19:43 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 07:46:00,292 | step= 4980 | epoch=0.86 | loss=2.1087 | ppl=8.24 | lr=4.35e-05 | grad=0.941 | tok/s=70,355 | ETA=3:14:33 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 07:50:58,198 | step= 5000 | epoch=0.87 | loss=2.0873 | ppl=8.06 | lr=4.28e-05 | grad=0.701 | tok/s=70,316 | ETA=3:09:41 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 07:55:56,734 | step= 5020 | epoch=0.87 | loss=2.2094 | ppl=9.11 | lr=4.22e-05 | grad=0.779 | tok/s=70,159 | ETA=3:05:08 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 08:00:55,791 | step= 5040 | epoch=0.87 | loss=2.1538 | ppl=8.62 | lr=4.15e-05 | grad=0.697 | tok/s=70,059 | ETA=3:00:25 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 08:05:54,308 | step= 5060 | epoch=0.88 | loss=2.1098 | ppl=8.25 | lr=4.09e-05 | grad=0.815 | tok/s=70,298 | ETA=2:54:50 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 08:10:52,373 | step= 5080 | epoch=0.88 | loss=2.1579 | ppl=8.65 | lr=4.03e-05 | grad=0.674 | tok/s=70,371 | ETA=2:49:42 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 08:15:50,526 | step= 5100 | epoch=0.88 | loss=2.0848 | ppl=8.04 | lr=3.97e-05 | grad=0.679 | tok/s=70,255 | ETA=2:45:00 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 08:20:48,928 | step= 5120 | epoch=0.89 | loss=2.0596 | ppl=7.84 | lr=3.91e-05 | grad=0.874 | tok/s=70,258 | ETA=2:40:02 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 08:25:47,256 | step= 5140 | epoch=0.89 | loss=2.1028 | ppl=8.19 | lr=3.86e-05 | grad=0.842 | tok/s=70,156 | ETA=2:35:17 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 08:30:45,502 | step= 5160 | epoch=0.90 | loss=2.0672 | ppl=7.90 | lr=3.81e-05 | grad=0.816 | tok/s=70,230 | ETA=2:30:09 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 08:35:43,620 | step= 5180 | epoch=0.90 | loss=2.1192 | ppl=8.32 | lr=3.75e-05 | grad=1.057 | tok/s=70,364 | ETA=2:24:54 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 08:40:42,338 | step= 5200 | epoch=0.90 | loss=2.4389 | ppl=11.46 | lr=3.70e-05 | grad=0.610 | tok/s=70,079 | ETA=2:20:30 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 08:57:33,185 | VAL step=5200 epoch=0.90 loss=2.4004 ppl=11.03 ★ BEST |
| 2026-06-21 08:57:33,357 | Checkpoint saved: step 5200 |
| 2026-06-21 08:57:33,431 | Saved safetensors: 101 tensors |
| 2026-06-21 08:57:33,844 | HTTP Request: POST https://huggingface.co/api/repos/create "HTTP/1.1 409 Conflict" |
| 2026-06-21 08:57:33,902 | HTTP Request: POST https://huggingface.co/api/validate-yaml "HTTP/1.1 200 OK" |
| 2026-06-21 08:57:33,990 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-3/preupload/main "HTTP/1.1 200 OK" |
| 2026-06-21 08:57:38,622 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-3/commit/main "HTTP/1.1 200 OK" |
| 2026-06-21 08:57:38,627 | Hub push step=5200 |
| 2026-06-21 09:02:37,707 | step= 5220 | epoch=0.91 | loss=2.4057 | ppl=11.09 | lr=3.66e-05 | grad=0.632 | tok/s=70,296 | ETA=2:15:06 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 09:07:36,323 | step= 5240 | epoch=0.91 | loss=2.4515 | ppl=11.61 | lr=3.61e-05 | grad=0.692 | tok/s=70,161 | ETA=2:10:23 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 09:12:35,603 | step= 5260 | epoch=0.91 | loss=2.3649 | ppl=10.64 | lr=3.56e-05 | grad=0.655 | tok/s=70,178 | ETA=2:05:23 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 09:17:34,773 | step= 5280 | epoch=0.92 | loss=2.3754 | ppl=10.76 | lr=3.52e-05 | grad=0.613 | tok/s=70,229 | ETA=2:00:19 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 09:22:33,579 | step= 5300 | epoch=0.92 | loss=2.3710 | ppl=10.71 | lr=3.48e-05 | grad=0.626 | tok/s=70,345 | ETA=1:55:09 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 09:27:32,336 | step= 5320 | epoch=0.92 | loss=2.3813 | ppl=10.82 | lr=3.44e-05 | grad=0.628 | tok/s=69,986 | ETA=1:50:45 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 09:32:31,455 | step= 5340 | epoch=0.93 | loss=2.3760 | ppl=10.76 | lr=3.40e-05 | grad=0.665 | tok/s=69,974 | ETA=1:45:47 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 09:37:30,612 | step= 5360 | epoch=0.93 | loss=2.3663 | ppl=10.66 | lr=3.36e-05 | grad=0.737 | tok/s=69,947 | ETA=1:40:50 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 09:42:29,936 | step= 5380 | epoch=0.93 | loss=2.3950 | ppl=10.97 | lr=3.33e-05 | grad=0.569 | tok/s=70,147 | ETA=1:35:34 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 09:47:28,548 | step= 5400 | epoch=0.94 | loss=2.5930 | ppl=13.37 | lr=3.30e-05 | grad=1.203 | tok/s=70,371 | ETA=1:30:18 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 09:52:26,908 | step= 5420 | epoch=0.94 | loss=2.5466 | ppl=12.76 | lr=3.26e-05 | grad=0.469 | tok/s=69,953 | ETA=1:25:51 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 09:57:25,782 | step= 5440 | epoch=0.94 | loss=2.5106 | ppl=12.31 | lr=3.23e-05 | grad=0.506 | tok/s=69,931 | ETA=1:20:53 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 10:02:24,659 | step= 5460 | epoch=0.95 | loss=2.5141 | ppl=12.35 | lr=3.21e-05 | grad=0.460 | tok/s=70,216 | ETA=1:15:35 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 10:07:23,276 | step= 5480 | epoch=0.95 | loss=2.5031 | ppl=12.22 | lr=3.18e-05 | grad=0.452 | tok/s=70,086 | ETA=1:10:44 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 10:12:21,612 | step= 5500 | epoch=0.95 | loss=2.4946 | ppl=12.12 | lr=3.16e-05 | grad=0.558 | tok/s=70,269 | ETA=1:05:35 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 10:17:20,611 | step= 5520 | epoch=0.96 | loss=2.3794 | ppl=10.80 | lr=3.13e-05 | grad=0.690 | tok/s=70,247 | ETA=1:00:38 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 10:22:18,723 | step= 5540 | epoch=0.96 | loss=2.3631 | ppl=10.62 | lr=3.11e-05 | grad=0.626 | tok/s=70,102 | ETA=0:55:47 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 10:27:17,670 | step= 5560 | epoch=0.96 | loss=2.3722 | ppl=10.72 | lr=3.09e-05 | grad=0.556 | tok/s=70,310 | ETA=0:50:39 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 10:32:16,717 | step= 5580 | epoch=0.97 | loss=2.1053 | ppl=8.21 | lr=3.08e-05 | grad=1.470 | tok/s=70,154 | ETA=0:45:47 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 10:37:15,768 | step= 5600 | epoch=0.97 | loss=2.0113 | ppl=7.47 | lr=3.06e-05 | grad=0.546 | tok/s=70,071 | ETA=0:40:51 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 10:54:06,550 | VAL step=5600 epoch=0.97 loss=2.4695 ppl=11.82 |
| 2026-06-21 10:54:06,743 | Checkpoint saved: step 5600 |
| 2026-06-21 10:54:06,803 | Saved safetensors: 101 tensors |
| 2026-06-21 10:54:07,226 | HTTP Request: POST https://huggingface.co/api/repos/create "HTTP/1.1 409 Conflict" |
| 2026-06-21 10:54:07,287 | HTTP Request: POST https://huggingface.co/api/validate-yaml "HTTP/1.1 200 OK" |
| 2026-06-21 10:54:07,374 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-3/preupload/main "HTTP/1.1 200 OK" |
| 2026-06-21 10:54:11,886 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-3/commit/main "HTTP/1.1 200 OK" |
| 2026-06-21 10:54:11,891 | Hub push step=5600 |
| 2026-06-21 10:59:10,669 | step= 5620 | epoch=0.98 | loss=1.9671 | ppl=7.15 | lr=3.05e-05 | grad=0.476 | tok/s=70,324 | ETA=0:35:45 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 11:04:09,713 | step= 5640 | epoch=0.98 | loss=1.9579 | ppl=7.08 | lr=3.03e-05 | grad=0.536 | tok/s=70,032 | ETA=0:30:54 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 11:09:08,646 | step= 5660 | epoch=0.98 | loss=1.9574 | ppl=7.08 | lr=3.02e-05 | grad=0.506 | tok/s=70,149 | ETA=0:25:53 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 11:14:07,293 | step= 5680 | epoch=0.99 | loss=1.9455 | ppl=7.00 | lr=3.02e-05 | grad=0.491 | tok/s=70,082 | ETA=0:20:55 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 11:19:06,246 | step= 5700 | epoch=0.99 | loss=1.9177 | ppl=6.81 | lr=3.01e-05 | grad=0.511 | tok/s=70,203 | ETA=0:15:54 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 11:24:04,827 | step= 5720 | epoch=0.99 | loss=1.9238 | ppl=6.85 | lr=3.00e-05 | grad=0.522 | tok/s=70,349 | ETA=0:10:55 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 11:29:03,405 | step= 5740 | epoch=1.00 | loss=1.9215 | ppl=6.83 | lr=3.00e-05 | grad=0.512 | tok/s=69,910 | ETA=0:05:59 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 11:34:02,250 | step= 5760 | epoch=1.00 | loss=1.9236 | ppl=6.85 | lr=3.00e-05 | grad=0.596 | tok/s=70,326 | ETA=0:00:59 | VRAM=0.7GB | RAM=20% |
| 2026-06-21 11:51:52,887 | Final eval loss=2.5147 ppl=12.36 |
| 2026-06-21 11:51:53,082 | Checkpoint saved: step 5764 |
| 2026-06-21 11:51:53,143 | Saved safetensors: 101 tensors |
| 2026-06-21 11:51:53,511 | HTTP Request: POST https://huggingface.co/api/repos/create "HTTP/1.1 409 Conflict" |
| 2026-06-21 11:51:53,569 | HTTP Request: POST https://huggingface.co/api/validate-yaml "HTTP/1.1 200 OK" |
| 2026-06-21 11:51:53,654 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-3/preupload/main "HTTP/1.1 200 OK" |
| 2026-06-21 11:52:00,477 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-3/commit/main "HTTP/1.1 200 OK" |
| 2026-06-21 11:52:00,481 | Hub push step=5764 |
| 2026-06-21 11:52:00,561 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-3/preupload/main "HTTP/1.1 200 OK" |
| 2026-06-21 11:52:01,327 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-3/commit/main "HTTP/1.1 200 OK" |
| 2026-06-21 11:52:01,407 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-3/preupload/main "HTTP/1.1 200 OK" |
|
|