Exp-4 / train_log.log
CyanMonkey's picture
Upload logs
129a42f verified
Raw
History Blame Contribute Delete
65.1 kB
2026-07-03 12:55:05,033 | T4/P100 (Tesla T4 sm_75): Flash unavailable, using chunked attn
2026-07-03 12:55:05,280 | HTTP Request: GET https://huggingface.co/api/agent-harnesses "HTTP/1.1 200 OK"
2026-07-03 12:55:05,364 | HTTP Request: GET https://huggingface.co/api/whoami-v2 "HTTP/1.1 200 OK"
2026-07-03 12:55:05,443 | HTTP Request: HEAD https://huggingface.co/GODELEV/TOK-4K/resolve/main/config.json "HTTP/1.1 404 Not Found"
2026-07-03 12:55:05,514 | HTTP Request: HEAD https://huggingface.co/GODELEV/TOK-4K/resolve/main/config.json "HTTP/1.1 404 Not Found"
2026-07-03 12:55:05,582 | HTTP Request: HEAD https://huggingface.co/GODELEV/TOK-4K/resolve/main/tokenizer_config.json "HTTP/1.1 307 Temporary Redirect"
2026-07-03 12:55:05,601 | HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/GODELEV/TOK-4K/0a93937fbb072e0b839a0ae1902127e0d22b872f/tokenizer_config.json "HTTP/1.1 200 OK"
2026-07-03 12:55:05,621 | HTTP Request: GET https://huggingface.co/api/resolve-cache/models/GODELEV/TOK-4K/0a93937fbb072e0b839a0ae1902127e0d22b872f/tokenizer_config.json "HTTP/1.1 200 OK"
2026-07-03 12:55:05,727 | HTTP Request: GET https://huggingface.co/api/models/GODELEV/TOK-4K/tree/main/additional_chat_templates?recursive=false&expand=false "HTTP/1.1 404 Not Found"
2026-07-03 12:55:05,799 | HTTP Request: GET https://huggingface.co/api/models/GODELEV/TOK-4K/tree/main?recursive=true&expand=false "HTTP/1.1 200 OK"
2026-07-03 12:55:05,868 | HTTP Request: HEAD https://huggingface.co/GODELEV/TOK-4K/resolve/main/tokenizer.json "HTTP/1.1 307 Temporary Redirect"
2026-07-03 12:55:05,886 | HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/GODELEV/TOK-4K/0a93937fbb072e0b839a0ae1902127e0d22b872f/tokenizer.json "HTTP/1.1 200 OK"
2026-07-03 12:55:05,908 | HTTP Request: GET https://huggingface.co/api/resolve-cache/models/GODELEV/TOK-4K/0a93937fbb072e0b839a0ae1902127e0d22b872f/tokenizer.json "HTTP/1.1 200 OK"
2026-07-03 12:55:05,993 | HTTP Request: HEAD https://huggingface.co/GODELEV/TOK-4K/resolve/main/tokenizer.model "HTTP/1.1 404 Not Found"
2026-07-03 12:55:06,075 | HTTP Request: HEAD https://huggingface.co/GODELEV/TOK-4K/resolve/main/added_tokens.json "HTTP/1.1 404 Not Found"
2026-07-03 12:55:06,147 | HTTP Request: HEAD https://huggingface.co/GODELEV/TOK-4K/resolve/main/special_tokens_map.json "HTTP/1.1 307 Temporary Redirect"
2026-07-03 12:55:06,167 | HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/GODELEV/TOK-4K/0a93937fbb072e0b839a0ae1902127e0d22b872f/special_tokens_map.json "HTTP/1.1 200 OK"
2026-07-03 12:55:06,187 | HTTP Request: GET https://huggingface.co/api/resolve-cache/models/GODELEV/TOK-4K/0a93937fbb072e0b839a0ae1902127e0d22b872f/special_tokens_map.json "HTTP/1.1 200 OK"
2026-07-03 12:55:06,318 | HTTP Request: HEAD https://huggingface.co/GODELEV/TOK-4K/resolve/main/chat_template.jinja "HTTP/1.1 404 Not Found"
2026-07-03 12:55:06,418 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/main/README.md "HTTP/1.1 404 Not Found"
2026-07-03 12:55:06,648 | HTTP Request: GET https://huggingface.co/api/datasets/CyanMonkey/D3-4-lite "HTTP/1.1 200 OK"
2026-07-03 12:55:06,716 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/D3-4-lite.py "HTTP/1.1 404 Not Found"
2026-07-03 12:55:06,823 | HTTP Request: HEAD https://s3.amazonaws.com/datasets.huggingface.co/datasets/datasets/CyanMonkey/D3-4-lite/CyanMonkey/D3-4-lite.py "HTTP/1.1 404 Not Found"
2026-07-03 12:55:06,893 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/README.md "HTTP/1.1 404 Not Found"
2026-07-03 12:55:06,963 | HTTP Request: GET https://huggingface.co/api/datasets/CyanMonkey/D3-4-lite/revision/891bad98d6e4a7d0af41c4b6a6af01574dfceea6 "HTTP/1.1 200 OK"
2026-07-03 12:55:07,035 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/.huggingface.yaml "HTTP/1.1 404 Not Found"
2026-07-03 12:55:07,179 | HTTP Request: GET https://datasets-server.huggingface.co/info?dataset=CyanMonkey/D3-4-lite "HTTP/1.1 200 OK"
2026-07-03 12:55:07,278 | HTTP Request: GET https://huggingface.co/api/datasets/CyanMonkey/D3-4-lite/tree/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data?recursive=true&expand=false "HTTP/1.1 200 OK"
2026-07-03 12:55:07,358 | HTTP Request: GET https://huggingface.co/api/datasets/CyanMonkey/D3-4-lite/tree/891bad98d6e4a7d0af41c4b6a6af01574dfceea6?recursive=false&expand=false "HTTP/1.1 200 OK"
2026-07-03 12:55:07,461 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/dataset_infos.json "HTTP/1.1 404 Not Found"
2026-07-03 12:55:07,565 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00000-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:55:09,953 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00001-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:55:12,195 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00002-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:55:14,251 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00003-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:55:18,204 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00004-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:55:24,699 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00005-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:55:26,854 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00006-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:55:29,061 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00007-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:55:34,785 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00008-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:55:37,077 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00009-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:55:44,386 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00010-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:55:46,498 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00011-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:55:48,714 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00012-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:55:54,021 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00013-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:55:57,198 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00014-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:56:00,847 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00015-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:56:02,927 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00016-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:56:06,231 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00017-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:56:10,309 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00018-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:56:12,249 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00019-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:56:14,460 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00020-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:56:19,294 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00021-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:56:22,601 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00022-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:56:25,294 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00023-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:56:29,535 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00024-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:56:32,993 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00025-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:56:35,254 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00026-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:56:37,659 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00027-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:56:41,660 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00028-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:56:46,206 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00029-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:56:48,574 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00030-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:56:52,381 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00031-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:56:54,355 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00032-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:56:59,837 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00033-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:57:02,467 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00034-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:57:04,565 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00035-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:57:08,501 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00036-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:57:11,551 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00037-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:57:12,741 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/train-00038-of-00039.arrow "HTTP/1.1 302 Found"
2026-07-03 12:57:17,011 | HTTP Request: HEAD https://huggingface.co/datasets/CyanMonkey/D3-4-lite/resolve/891bad98d6e4a7d0af41c4b6a6af01574dfceea6/data/val-00000-of-00001.arrow "HTTP/1.1 302 Found"
2026-07-03 13:02:18,946 | Data loaded train=15,253,790 val=200,000 steps_per_epoch=14,897 total_epochs=1.00
2026-07-03 13:02:21,562 | Model 3.000M params | float32 | amp=torch.float16 | compiled=True | attn=chunked
2026-07-03 13:02:21,794 | HTTP Request: HEAD https://huggingface.co/CyanMonkey/Exp-4/resolve/main/resume/latest_step.txt "HTTP/1.1 307 Temporary Redirect"
2026-07-03 13:02:21,911 | HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/CyanMonkey/Exp-4/3af264666e98fd05bae7641611c2fc302a5ee529/resume%2Flatest_step.txt "HTTP/1.1 200 OK"
2026-07-03 13:02:22,043 | HTTP Request: GET https://huggingface.co/api/resolve-cache/models/CyanMonkey/Exp-4/3af264666e98fd05bae7641611c2fc302a5ee529/resume%2Flatest_step.txt "HTTP/1.1 200 OK"
2026-07-03 13:02:22,134 | HTTP Request: HEAD https://huggingface.co/CyanMonkey/Exp-4/resolve/main/resume/ckpt.pt "HTTP/1.1 302 Found"
2026-07-03 13:02:24,695 | Resumed step=9600 tokens=10056499200 samples=9830400
2026-07-03 13:04:55,008 | step= 9620 | epoch=0.65 | loss=2.2095 | ppl=9.11 | lr=1.10e-04 | grad=1.115 | tok/s=168,929 | ETA=9:05:23 | VRAM=0.6GB | RAM=12%
2026-07-03 13:06:55,084 | step= 9640 | epoch=0.65 | loss=2.1912 | ppl=8.95 | lr=1.10e-04 | grad=1.237 | tok/s=175,027 | ETA=8:44:23 | VRAM=0.6GB | RAM=13%
2026-07-03 13:08:55,162 | step= 9660 | epoch=0.65 | loss=2.1764 | ppl=8.81 | lr=1.09e-04 | grad=1.261 | tok/s=174,884 | ETA=8:42:49 | VRAM=0.6GB | RAM=13%
2026-07-03 13:10:55,510 | step= 9680 | epoch=0.65 | loss=2.2098 | ppl=9.11 | lr=1.08e-04 | grad=1.380 | tok/s=173,232 | ETA=8:45:47 | VRAM=0.6GB | RAM=13%
2026-07-03 13:12:56,277 | step= 9700 | epoch=0.65 | loss=2.1793 | ppl=8.84 | lr=1.08e-04 | grad=1.153 | tok/s=172,445 | ETA=8:46:10 | VRAM=0.6GB | RAM=13%
2026-07-03 13:14:57,266 | step= 9720 | epoch=0.65 | loss=2.1421 | ppl=8.52 | lr=1.07e-04 | grad=1.340 | tok/s=173,007 | ETA=8:42:26 | VRAM=0.6GB | RAM=12%
2026-07-03 13:16:58,045 | step= 9740 | epoch=0.65 | loss=2.1337 | ppl=8.45 | lr=1.07e-04 | grad=1.164 | tok/s=173,263 | ETA=8:39:39 | VRAM=0.6GB | RAM=13%
2026-07-03 13:18:59,044 | step= 9760 | epoch=0.66 | loss=2.1513 | ppl=8.60 | lr=1.06e-04 | grad=1.219 | tok/s=172,706 | ETA=8:39:18 | VRAM=0.6GB | RAM=13%
2026-07-03 13:20:59,846 | step= 9780 | epoch=0.66 | loss=2.1867 | ppl=8.91 | lr=1.06e-04 | grad=1.292 | tok/s=174,212 | ETA=8:32:48 | VRAM=0.6GB | RAM=12%
2026-07-03 13:23:00,279 | step= 9800 | epoch=0.66 | loss=2.1370 | ppl=8.47 | lr=1.05e-04 | grad=1.289 | tok/s=174,102 | ETA=8:31:08 | VRAM=0.6GB | RAM=12%
2026-07-03 13:25:00,817 | step= 9820 | epoch=0.66 | loss=2.1358 | ppl=8.46 | lr=1.05e-04 | grad=0.952 | tok/s=174,262 | ETA=8:28:39 | VRAM=0.6GB | RAM=13%
2026-07-03 13:27:01,017 | step= 9840 | epoch=0.66 | loss=2.1616 | ppl=8.68 | lr=1.04e-04 | grad=1.362 | tok/s=174,270 | ETA=8:26:38 | VRAM=0.6GB | RAM=13%
2026-07-03 13:29:01,616 | step= 9860 | epoch=0.66 | loss=2.1477 | ppl=8.57 | lr=1.04e-04 | grad=1.086 | tok/s=173,724 | ETA=8:26:12 | VRAM=0.6GB | RAM=12%
2026-07-03 13:31:02,017 | step= 9880 | epoch=0.66 | loss=2.1636 | ppl=8.70 | lr=1.03e-04 | grad=1.003 | tok/s=173,957 | ETA=8:23:31 | VRAM=0.6GB | RAM=12%
2026-07-03 13:33:02,369 | step= 9900 | epoch=0.66 | loss=2.1565 | ppl=8.64 | lr=1.03e-04 | grad=1.148 | tok/s=174,580 | ETA=8:19:44 | VRAM=0.6GB | RAM=12%
2026-07-03 13:35:02,595 | step= 9920 | epoch=0.67 | loss=2.1251 | ppl=8.37 | lr=1.02e-04 | grad=1.173 | tok/s=174,216 | ETA=8:18:46 | VRAM=0.6GB | RAM=12%
2026-07-03 13:37:02,984 | step= 9940 | epoch=0.67 | loss=2.1418 | ppl=8.51 | lr=1.02e-04 | grad=1.141 | tok/s=174,365 | ETA=8:16:20 | VRAM=0.6GB | RAM=13%
2026-07-03 13:39:03,230 | step= 9960 | epoch=0.67 | loss=2.1673 | ppl=8.73 | lr=1.01e-04 | grad=1.339 | tok/s=174,560 | ETA=8:13:47 | VRAM=0.6GB | RAM=12%
2026-07-03 13:41:03,184 | step= 9980 | epoch=0.67 | loss=2.1930 | ppl=8.96 | lr=1.01e-04 | grad=1.550 | tok/s=174,625 | ETA=8:11:36 | VRAM=0.6GB | RAM=12%
2026-07-03 13:43:03,183 | step= 10000 | epoch=0.67 | loss=2.2613 | ppl=9.60 | lr=1.00e-04 | grad=1.675 | tok/s=173,669 | ETA=8:12:18 | VRAM=0.6GB | RAM=12%
2026-07-03 13:50:29,258 | VAL step=10000 epoch=0.67 loss=2.3259 ppl=10.24 ★ BEST
2026-07-03 13:50:29,333 | Checkpoint saved: step 10000
2026-07-03 13:50:29,367 | Saved safetensors: 47 tensors
2026-07-03 13:50:29,603 | HTTP Request: POST https://huggingface.co/api/repos/create "HTTP/1.1 409 Conflict"
2026-07-03 13:50:29,667 | HTTP Request: POST https://huggingface.co/api/validate-yaml "HTTP/1.1 200 OK"
2026-07-03 13:50:29,760 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-4/preupload/main "HTTP/1.1 200 OK"
2026-07-03 13:50:32,710 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-4/commit/main "HTTP/1.1 200 OK"
2026-07-03 13:50:32,716 | Hub push step=10000
2026-07-03 13:52:33,731 | step= 10020 | epoch=0.67 | loss=2.2578 | ppl=9.56 | lr=9.95e-05 | grad=1.502 | tok/s=172,280 | ETA=8:14:14 | VRAM=0.6GB | RAM=14%
2026-07-03 13:54:33,920 | step= 10040 | epoch=0.67 | loss=2.1723 | ppl=8.78 | lr=9.90e-05 | grad=1.821 | tok/s=175,035 | ETA=8:04:28 | VRAM=0.6GB | RAM=14%
2026-07-03 13:56:33,949 | step= 10060 | epoch=0.68 | loss=2.2123 | ppl=9.14 | lr=9.85e-05 | grad=1.576 | tok/s=173,554 | ETA=8:06:35 | VRAM=0.6GB | RAM=14%
2026-07-03 13:58:34,563 | step= 10080 | epoch=0.68 | loss=2.2109 | ppl=9.12 | lr=9.80e-05 | grad=1.252 | tok/s=173,446 | ETA=8:04:52 | VRAM=0.6GB | RAM=14%
2026-07-03 14:00:35,339 | step= 10100 | epoch=0.68 | loss=2.2305 | ppl=9.30 | lr=9.75e-05 | grad=1.143 | tok/s=173,660 | ETA=8:02:16 | VRAM=0.6GB | RAM=14%
2026-07-03 14:02:35,775 | step= 10120 | epoch=0.68 | loss=2.1348 | ppl=8.46 | lr=9.70e-05 | grad=1.356 | tok/s=173,875 | ETA=7:59:40 | VRAM=0.6GB | RAM=14%
2026-07-03 14:04:36,609 | step= 10140 | epoch=0.68 | loss=2.1465 | ppl=8.55 | lr=9.65e-05 | grad=1.280 | tok/s=172,537 | ETA=8:01:21 | VRAM=0.6GB | RAM=14%
2026-07-03 14:06:37,670 | step= 10160 | epoch=0.68 | loss=2.1907 | ppl=8.94 | lr=9.59e-05 | grad=1.798 | tok/s=174,045 | ETA=7:55:11 | VRAM=0.6GB | RAM=14%
2026-07-03 14:08:37,457 | step= 10180 | epoch=0.68 | loss=2.2353 | ppl=9.35 | lr=9.54e-05 | grad=1.645 | tok/s=174,540 | ETA=7:51:50 | VRAM=0.6GB | RAM=14%
2026-07-03 14:10:37,418 | step= 10200 | epoch=0.68 | loss=2.1890 | ppl=8.93 | lr=9.49e-05 | grad=1.190 | tok/s=174,769 | ETA=7:49:13 | VRAM=0.6GB | RAM=14%
2026-07-03 14:12:37,428 | step= 10220 | epoch=0.69 | loss=1.9968 | ppl=7.37 | lr=9.44e-05 | grad=1.796 | tok/s=174,023 | ETA=7:49:13 | VRAM=0.6GB | RAM=14%
2026-07-03 14:14:37,509 | step= 10240 | epoch=0.69 | loss=2.2097 | ppl=9.11 | lr=9.39e-05 | grad=1.135 | tok/s=174,503 | ETA=7:45:56 | VRAM=0.6GB | RAM=14%
2026-07-03 14:16:37,707 | step= 10260 | epoch=0.69 | loss=2.1612 | ppl=8.68 | lr=9.34e-05 | grad=0.920 | tok/s=173,405 | ETA=7:46:52 | VRAM=0.6GB | RAM=14%
2026-07-03 14:18:38,248 | step= 10280 | epoch=0.69 | loss=2.1381 | ppl=8.48 | lr=9.29e-05 | grad=2.035 | tok/s=173,818 | ETA=7:43:45 | VRAM=0.6GB | RAM=14%
2026-07-03 14:20:38,814 | step= 10300 | epoch=0.69 | loss=2.0973 | ppl=8.14 | lr=9.24e-05 | grad=1.621 | tok/s=173,877 | ETA=7:41:35 | VRAM=0.6GB | RAM=14%
2026-07-03 14:22:39,251 | step= 10320 | epoch=0.69 | loss=2.1178 | ppl=8.31 | lr=9.19e-05 | grad=1.922 | tok/s=174,520 | ETA=7:37:53 | VRAM=0.6GB | RAM=14%
2026-07-03 14:24:39,006 | step= 10340 | epoch=0.69 | loss=2.1368 | ppl=8.47 | lr=9.14e-05 | grad=1.798 | tok/s=174,797 | ETA=7:35:09 | VRAM=0.6GB | RAM=14%
2026-07-03 14:26:39,418 | step= 10360 | epoch=0.70 | loss=2.1060 | ppl=8.22 | lr=9.10e-05 | grad=1.533 | tok/s=174,487 | ETA=7:33:58 | VRAM=0.6GB | RAM=14%
2026-07-03 14:28:39,526 | step= 10380 | epoch=0.70 | loss=2.2001 | ppl=9.03 | lr=9.05e-05 | grad=1.232 | tok/s=174,562 | ETA=7:31:46 | VRAM=0.6GB | RAM=14%
2026-07-03 14:30:39,679 | step= 10400 | epoch=0.70 | loss=1.6673 | ppl=5.30 | lr=9.00e-05 | grad=1.184 | tok/s=174,303 | ETA=7:30:26 | VRAM=0.6GB | RAM=14%
2026-07-03 14:37:49,003 | VAL step=10400 epoch=0.70 loss=2.5011 ppl=12.20
2026-07-03 14:37:49,078 | Checkpoint saved: step 10400
2026-07-03 14:37:49,103 | Saved safetensors: 47 tensors
2026-07-03 14:37:49,386 | HTTP Request: POST https://huggingface.co/api/repos/create "HTTP/1.1 409 Conflict"
2026-07-03 14:37:49,447 | HTTP Request: POST https://huggingface.co/api/validate-yaml "HTTP/1.1 200 OK"
2026-07-03 14:37:49,539 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-4/preupload/main "HTTP/1.1 200 OK"
2026-07-03 14:37:52,558 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-4/commit/main "HTTP/1.1 200 OK"
2026-07-03 14:37:52,562 | Hub push step=10400
2026-07-03 14:39:52,894 | step= 10420 | epoch=0.70 | loss=1.5109 | ppl=4.53 | lr=8.95e-05 | grad=1.033 | tok/s=173,447 | ETA=7:30:39 | VRAM=0.6GB | RAM=14%
2026-07-03 14:41:53,142 | step= 10440 | epoch=0.70 | loss=1.4253 | ppl=4.16 | lr=8.90e-05 | grad=0.987 | tok/s=173,949 | ETA=7:27:20 | VRAM=0.6GB | RAM=14%
2026-07-03 14:43:53,478 | step= 10460 | epoch=0.70 | loss=1.3748 | ppl=3.95 | lr=8.85e-05 | grad=1.254 | tok/s=174,018 | ETA=7:25:09 | VRAM=0.6GB | RAM=14%
2026-07-03 14:45:53,240 | step= 10480 | epoch=0.70 | loss=1.4464 | ppl=4.25 | lr=8.80e-05 | grad=1.475 | tok/s=175,174 | ETA=7:20:14 | VRAM=0.6GB | RAM=14%
2026-07-03 14:47:52,576 | step= 10500 | epoch=0.70 | loss=1.3180 | ppl=3.74 | lr=8.75e-05 | grad=1.081 | tok/s=175,068 | ETA=7:18:30 | VRAM=0.6GB | RAM=14%
2026-07-03 14:49:52,443 | step= 10520 | epoch=0.71 | loss=1.3000 | ppl=3.67 | lr=8.71e-05 | grad=1.311 | tok/s=174,940 | ETA=7:16:49 | VRAM=0.6GB | RAM=14%
2026-07-03 14:51:52,337 | step= 10540 | epoch=0.71 | loss=1.2857 | ppl=3.62 | lr=8.66e-05 | grad=1.001 | tok/s=174,832 | ETA=7:15:06 | VRAM=0.6GB | RAM=14%
2026-07-03 14:53:52,303 | step= 10560 | epoch=0.71 | loss=1.2751 | ppl=3.58 | lr=8.61e-05 | grad=0.797 | tok/s=174,153 | ETA=7:14:47 | VRAM=0.6GB | RAM=14%
2026-07-03 14:55:52,340 | step= 10580 | epoch=0.71 | loss=1.2527 | ppl=3.50 | lr=8.56e-05 | grad=0.953 | tok/s=174,510 | ETA=7:11:54 | VRAM=0.6GB | RAM=14%
2026-07-03 14:57:52,144 | step= 10600 | epoch=0.71 | loss=1.2465 | ppl=3.48 | lr=8.51e-05 | grad=1.495 | tok/s=175,082 | ETA=7:08:29 | VRAM=0.6GB | RAM=14%
2026-07-03 14:59:51,998 | step= 10620 | epoch=0.71 | loss=1.2611 | ppl=3.53 | lr=8.47e-05 | grad=1.284 | tok/s=175,009 | ETA=7:06:40 | VRAM=0.6GB | RAM=14%
2026-07-03 15:01:51,584 | step= 10640 | epoch=0.71 | loss=1.2218 | ppl=3.39 | lr=8.42e-05 | grad=0.791 | tok/s=175,258 | ETA=7:04:04 | VRAM=0.6GB | RAM=14%
2026-07-03 15:03:51,332 | step= 10660 | epoch=0.72 | loss=1.2232 | ppl=3.40 | lr=8.37e-05 | grad=0.958 | tok/s=175,028 | ETA=7:02:38 | VRAM=0.6GB | RAM=14%
2026-07-03 15:05:50,974 | step= 10680 | epoch=0.72 | loss=1.2021 | ppl=3.33 | lr=8.33e-05 | grad=0.859 | tok/s=175,407 | ETA=6:59:44 | VRAM=0.6GB | RAM=14%
2026-07-03 15:07:50,488 | step= 10700 | epoch=0.72 | loss=1.2294 | ppl=3.42 | lr=8.28e-05 | grad=0.987 | tok/s=175,097 | ETA=6:58:29 | VRAM=0.6GB | RAM=14%
2026-07-03 15:09:50,313 | step= 10720 | epoch=0.72 | loss=1.1838 | ppl=3.27 | lr=8.23e-05 | grad=1.025 | tok/s=174,673 | ETA=6:57:30 | VRAM=0.6GB | RAM=14%
2026-07-03 15:11:50,404 | step= 10740 | epoch=0.72 | loss=1.2120 | ppl=3.36 | lr=8.19e-05 | grad=1.178 | tok/s=174,185 | ETA=6:56:40 | VRAM=0.6GB | RAM=14%
2026-07-03 15:13:50,698 | step= 10760 | epoch=0.72 | loss=1.1785 | ppl=3.25 | lr=8.14e-05 | grad=1.065 | tok/s=173,853 | ETA=6:55:27 | VRAM=0.6GB | RAM=14%
2026-07-03 15:15:51,213 | step= 10780 | epoch=0.72 | loss=1.1943 | ppl=3.30 | lr=8.09e-05 | grad=1.070 | tok/s=173,525 | ETA=6:54:13 | VRAM=0.6GB | RAM=14%
2026-07-03 15:17:51,062 | step= 10800 | epoch=0.72 | loss=1.1934 | ppl=3.30 | lr=8.05e-05 | grad=1.427 | tok/s=174,656 | ETA=6:49:32 | VRAM=0.6GB | RAM=14%
2026-07-03 15:24:59,197 | VAL step=10800 epoch=0.72 loss=2.7339 ppl=15.39
2026-07-03 15:24:59,278 | Checkpoint saved: step 10800
2026-07-03 15:24:59,305 | Saved safetensors: 47 tensors
2026-07-03 15:24:59,537 | HTTP Request: POST https://huggingface.co/api/repos/create "HTTP/1.1 409 Conflict"
2026-07-03 15:24:59,609 | HTTP Request: POST https://huggingface.co/api/validate-yaml "HTTP/1.1 200 OK"
2026-07-03 15:24:59,721 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-4/preupload/main "HTTP/1.1 200 OK"
2026-07-03 15:25:02,782 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-4/commit/main "HTTP/1.1 200 OK"
2026-07-03 15:25:02,786 | Hub push step=10800
2026-07-03 15:27:02,341 | step= 10820 | epoch=0.73 | loss=1.2291 | ppl=3.42 | lr=8.00e-05 | grad=1.636 | tok/s=175,849 | ETA=6:44:47 | VRAM=0.6GB | RAM=14%
2026-07-03 15:29:01,639 | step= 10840 | epoch=0.73 | loss=1.1608 | ppl=3.19 | lr=7.96e-05 | grad=1.074 | tok/s=175,377 | ETA=6:43:53 | VRAM=0.6GB | RAM=14%
2026-07-03 15:31:01,170 | step= 10860 | epoch=0.73 | loss=1.2112 | ppl=3.36 | lr=7.91e-05 | grad=0.943 | tok/s=174,998 | ETA=6:42:45 | VRAM=0.6GB | RAM=14%
2026-07-03 15:33:00,704 | step= 10880 | epoch=0.73 | loss=1.1824 | ppl=3.26 | lr=7.86e-05 | grad=0.885 | tok/s=175,114 | ETA=6:40:30 | VRAM=0.6GB | RAM=14%
2026-07-03 15:35:00,063 | step= 10900 | epoch=0.73 | loss=1.1668 | ppl=3.21 | lr=7.82e-05 | grad=1.156 | tok/s=174,889 | ETA=6:39:01 | VRAM=0.6GB | RAM=14%
2026-07-03 15:36:59,687 | step= 10920 | epoch=0.73 | loss=1.1637 | ppl=3.20 | lr=7.77e-05 | grad=0.942 | tok/s=174,996 | ETA=6:36:46 | VRAM=0.6GB | RAM=14%
2026-07-03 15:38:59,413 | step= 10940 | epoch=0.73 | loss=1.1408 | ppl=3.13 | lr=7.73e-05 | grad=1.150 | tok/s=174,744 | ETA=6:35:21 | VRAM=0.6GB | RAM=14%
2026-07-03 15:40:59,281 | step= 10960 | epoch=0.74 | loss=1.1510 | ppl=3.16 | lr=7.69e-05 | grad=1.030 | tok/s=175,185 | ETA=6:32:22 | VRAM=0.6GB | RAM=14%
2026-07-03 15:42:58,856 | step= 10980 | epoch=0.74 | loss=1.1387 | ppl=3.12 | lr=7.64e-05 | grad=0.785 | tok/s=175,073 | ETA=6:30:37 | VRAM=0.6GB | RAM=14%
2026-07-03 15:44:58,332 | step= 11000 | epoch=0.74 | loss=1.1455 | ppl=3.14 | lr=7.60e-05 | grad=0.805 | tok/s=175,149 | ETA=6:28:27 | VRAM=0.6GB | RAM=14%
2026-07-03 15:46:57,631 | step= 11020 | epoch=0.74 | loss=1.1202 | ppl=3.07 | lr=7.55e-05 | grad=0.981 | tok/s=175,346 | ETA=6:26:01 | VRAM=0.6GB | RAM=14%
2026-07-03 15:48:57,065 | step= 11040 | epoch=0.74 | loss=1.0924 | ppl=2.98 | lr=7.51e-05 | grad=1.058 | tok/s=175,594 | ETA=6:23:29 | VRAM=0.6GB | RAM=14%
2026-07-03 15:50:56,453 | step= 11060 | epoch=0.74 | loss=1.1046 | ppl=3.02 | lr=7.46e-05 | grad=0.821 | tok/s=175,583 | ETA=6:21:32 | VRAM=0.6GB | RAM=14%
2026-07-03 15:52:55,925 | step= 11080 | epoch=0.74 | loss=1.1077 | ppl=3.03 | lr=7.42e-05 | grad=0.816 | tok/s=174,621 | ETA=6:21:38 | VRAM=0.6GB | RAM=14%
2026-07-03 15:54:55,691 | step= 11100 | epoch=0.75 | loss=1.1364 | ppl=3.12 | lr=7.38e-05 | grad=1.047 | tok/s=175,987 | ETA=6:16:41 | VRAM=0.6GB | RAM=14%
2026-07-03 15:56:55,003 | step= 11120 | epoch=0.75 | loss=1.1183 | ppl=3.06 | lr=7.33e-05 | grad=0.855 | tok/s=176,491 | ETA=6:13:38 | VRAM=0.6GB | RAM=14%
2026-07-03 15:58:54,220 | step= 11140 | epoch=0.75 | loss=1.1210 | ppl=3.07 | lr=7.29e-05 | grad=0.909 | tok/s=175,790 | ETA=6:13:08 | VRAM=0.6GB | RAM=14%
2026-07-03 16:00:54,010 | step= 11160 | epoch=0.75 | loss=1.2112 | ppl=3.36 | lr=7.25e-05 | grad=1.133 | tok/s=174,346 | ETA=6:14:13 | VRAM=0.6GB | RAM=14%
2026-07-03 16:02:53,878 | step= 11180 | epoch=0.75 | loss=2.5069 | ppl=12.27 | lr=7.20e-05 | grad=2.031 | tok/s=175,201 | ETA=6:10:24 | VRAM=0.6GB | RAM=14%
2026-07-03 16:04:53,582 | step= 11200 | epoch=0.75 | loss=2.3412 | ppl=10.39 | lr=7.16e-05 | grad=1.326 | tok/s=174,902 | ETA=6:09:02 | VRAM=0.6GB | RAM=14%
2026-07-03 16:12:02,272 | VAL step=11200 epoch=0.75 loss=2.5917 ppl=13.35
2026-07-03 16:12:02,351 | Checkpoint saved: step 11200
2026-07-03 16:12:02,376 | Saved safetensors: 47 tensors
2026-07-03 16:12:02,610 | HTTP Request: POST https://huggingface.co/api/repos/create "HTTP/1.1 409 Conflict"
2026-07-03 16:12:02,679 | HTTP Request: POST https://huggingface.co/api/validate-yaml "HTTP/1.1 200 OK"
2026-07-03 16:12:02,779 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-4/preupload/main "HTTP/1.1 200 OK"
2026-07-03 16:12:07,027 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-4/commit/main "HTTP/1.1 200 OK"
2026-07-03 16:12:07,031 | Hub push step=11200
2026-07-03 16:14:07,521 | step= 11220 | epoch=0.75 | loss=2.2615 | ppl=9.60 | lr=7.12e-05 | grad=1.251 | tok/s=174,062 | ETA=6:08:49 | VRAM=0.6GB | RAM=14%
2026-07-03 16:16:07,783 | step= 11240 | epoch=0.75 | loss=2.2960 | ppl=9.93 | lr=7.08e-05 | grad=1.378 | tok/s=172,773 | ETA=6:09:33 | VRAM=0.6GB | RAM=14%
2026-07-03 16:18:08,112 | step= 11260 | epoch=0.76 | loss=2.3001 | ppl=9.98 | lr=7.04e-05 | grad=1.342 | tok/s=174,859 | ETA=6:03:08 | VRAM=0.6GB | RAM=14%
2026-07-03 16:20:07,883 | step= 11280 | epoch=0.76 | loss=2.2854 | ppl=9.83 | lr=6.99e-05 | grad=1.266 | tok/s=174,258 | ETA=6:02:23 | VRAM=0.6GB | RAM=14%
2026-07-03 16:22:08,433 | step= 11300 | epoch=0.76 | loss=2.2610 | ppl=9.59 | lr=6.95e-05 | grad=1.454 | tok/s=173,381 | ETA=6:02:12 | VRAM=0.6GB | RAM=14%
2026-07-03 16:24:08,520 | step= 11320 | epoch=0.76 | loss=2.2003 | ppl=9.03 | lr=6.91e-05 | grad=1.492 | tok/s=175,266 | ETA=5:56:19 | VRAM=0.6GB | RAM=14%
2026-07-03 16:26:08,128 | step= 11340 | epoch=0.76 | loss=2.2372 | ppl=9.37 | lr=6.87e-05 | grad=0.907 | tok/s=175,270 | ETA=5:54:19 | VRAM=0.6GB | RAM=14%
2026-07-03 16:28:08,393 | step= 11360 | epoch=0.76 | loss=2.1766 | ppl=8.82 | lr=6.83e-05 | grad=2.006 | tok/s=172,314 | ETA=5:58:22 | VRAM=0.6GB | RAM=14%
2026-07-03 16:30:08,557 | step= 11380 | epoch=0.76 | loss=1.8754 | ppl=6.52 | lr=6.79e-05 | grad=1.387 | tok/s=175,186 | ETA=5:50:30 | VRAM=0.6GB | RAM=14%
2026-07-03 16:32:07,986 | step= 11400 | epoch=0.77 | loss=2.1864 | ppl=8.90 | lr=6.75e-05 | grad=1.109 | tok/s=175,427 | ETA=5:48:02 | VRAM=0.6GB | RAM=14%
2026-07-03 16:34:07,815 | step= 11420 | epoch=0.77 | loss=2.1467 | ppl=8.56 | lr=6.70e-05 | grad=1.125 | tok/s=173,952 | ETA=5:48:58 | VRAM=0.6GB | RAM=14%
2026-07-03 16:36:07,815 | step= 11440 | epoch=0.77 | loss=2.1747 | ppl=8.80 | lr=6.66e-05 | grad=1.092 | tok/s=175,479 | ETA=5:43:57 | VRAM=0.6GB | RAM=14%
2026-07-03 16:38:07,478 | step= 11460 | epoch=0.77 | loss=2.2271 | ppl=9.27 | lr=6.62e-05 | grad=1.516 | tok/s=175,017 | ETA=5:42:51 | VRAM=0.6GB | RAM=14%
2026-07-03 16:40:07,518 | step= 11480 | epoch=0.77 | loss=2.1813 | ppl=8.86 | lr=6.58e-05 | grad=1.717 | tok/s=174,467 | ETA=5:41:56 | VRAM=0.6GB | RAM=14%
2026-07-03 16:42:08,013 | step= 11500 | epoch=0.77 | loss=2.2304 | ppl=9.30 | lr=6.54e-05 | grad=1.570 | tok/s=174,552 | ETA=5:39:46 | VRAM=0.6GB | RAM=14%
2026-07-03 16:44:07,723 | step= 11520 | epoch=0.77 | loss=2.1956 | ppl=8.99 | lr=6.50e-05 | grad=1.671 | tok/s=174,716 | ETA=5:37:27 | VRAM=0.6GB | RAM=14%
2026-07-03 16:46:07,652 | step= 11540 | epoch=0.77 | loss=2.1781 | ppl=8.83 | lr=6.46e-05 | grad=1.077 | tok/s=173,842 | ETA=5:37:08 | VRAM=0.6GB | RAM=14%
2026-07-03 16:48:08,129 | step= 11560 | epoch=0.78 | loss=2.4455 | ppl=11.54 | lr=6.43e-05 | grad=1.510 | tok/s=174,693 | ETA=5:33:30 | VRAM=0.6GB | RAM=14%
2026-07-03 16:50:07,873 | step= 11580 | epoch=0.78 | loss=2.3459 | ppl=10.44 | lr=6.39e-05 | grad=0.812 | tok/s=175,395 | ETA=5:30:10 | VRAM=0.6GB | RAM=14%
2026-07-03 16:52:07,638 | step= 11600 | epoch=0.78 | loss=2.2836 | ppl=9.81 | lr=6.35e-05 | grad=0.923 | tok/s=174,088 | ETA=5:30:39 | VRAM=0.6GB | RAM=14%
2026-07-03 16:59:15,903 | VAL step=11600 epoch=0.78 loss=2.3416 ppl=10.40
2026-07-03 16:59:15,978 | Checkpoint saved: step 11600
2026-07-03 16:59:16,003 | Saved safetensors: 47 tensors
2026-07-03 16:59:16,277 | HTTP Request: POST https://huggingface.co/api/repos/create "HTTP/1.1 409 Conflict"
2026-07-03 16:59:16,339 | HTTP Request: POST https://huggingface.co/api/validate-yaml "HTTP/1.1 200 OK"
2026-07-03 16:59:16,444 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-4/preupload/main "HTTP/1.1 200 OK"
2026-07-03 16:59:19,479 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-4/commit/main "HTTP/1.1 200 OK"
2026-07-03 16:59:19,483 | Hub push step=11600
2026-07-03 17:01:20,741 | step= 11620 | epoch=0.78 | loss=2.3296 | ppl=10.27 | lr=6.31e-05 | grad=1.266 | tok/s=174,552 | ETA=5:27:46 | VRAM=0.6GB | RAM=15%
2026-07-03 17:03:21,279 | step= 11640 | epoch=0.78 | loss=2.2923 | ppl=9.90 | lr=6.27e-05 | grad=0.864 | tok/s=173,094 | ETA=5:28:31 | VRAM=0.6GB | RAM=15%
2026-07-03 17:05:21,168 | step= 11660 | epoch=0.78 | loss=2.2551 | ppl=9.54 | lr=6.23e-05 | grad=1.631 | tok/s=175,786 | ETA=5:21:30 | VRAM=0.6GB | RAM=14%
2026-07-03 17:07:21,627 | step= 11680 | epoch=0.78 | loss=2.3463 | ppl=10.45 | lr=6.19e-05 | grad=1.027 | tok/s=173,410 | ETA=5:23:53 | VRAM=0.6GB | RAM=14%
2026-07-03 17:09:22,691 | step= 11700 | epoch=0.79 | loss=2.3212 | ppl=10.19 | lr=6.16e-05 | grad=0.927 | tok/s=171,723 | ETA=5:25:02 | VRAM=0.6GB | RAM=15%
2026-07-03 17:11:22,791 | step= 11720 | epoch=0.79 | loss=2.2227 | ppl=9.23 | lr=6.12e-05 | grad=0.896 | tok/s=174,861 | ETA=5:17:12 | VRAM=0.6GB | RAM=15%
2026-07-03 17:13:22,496 | step= 11740 | epoch=0.79 | loss=2.3125 | ppl=10.10 | lr=6.08e-05 | grad=1.154 | tok/s=174,843 | ETA=5:15:14 | VRAM=0.6GB | RAM=14%
2026-07-03 17:15:23,246 | step= 11760 | epoch=0.79 | loss=2.3083 | ppl=10.06 | lr=6.04e-05 | grad=1.083 | tok/s=174,313 | ETA=5:14:12 | VRAM=0.6GB | RAM=14%
2026-07-03 17:17:22,962 | step= 11780 | epoch=0.79 | loss=2.3095 | ppl=10.07 | lr=6.01e-05 | grad=1.231 | tok/s=175,140 | ETA=5:10:43 | VRAM=0.6GB | RAM=15%
2026-07-03 17:19:23,759 | step= 11800 | epoch=0.79 | loss=2.3137 | ppl=10.11 | lr=5.97e-05 | grad=0.833 | tok/s=173,844 | ETA=5:11:01 | VRAM=0.6GB | RAM=15%
2026-07-03 17:21:24,073 | step= 11820 | epoch=0.79 | loss=2.2965 | ppl=9.94 | lr=5.93e-05 | grad=0.949 | tok/s=174,431 | ETA=5:07:59 | VRAM=0.6GB | RAM=15%
2026-07-03 17:23:24,093 | step= 11840 | epoch=0.79 | loss=2.2698 | ppl=9.68 | lr=5.90e-05 | grad=0.994 | tok/s=174,422 | ETA=5:05:59 | VRAM=0.6GB | RAM=15%
2026-07-03 17:25:23,940 | step= 11860 | epoch=0.80 | loss=2.2433 | ppl=9.42 | lr=5.86e-05 | grad=0.911 | tok/s=175,057 | ETA=5:02:53 | VRAM=0.6GB | RAM=15%
2026-07-03 17:27:23,681 | step= 11880 | epoch=0.80 | loss=2.2865 | ppl=9.84 | lr=5.82e-05 | grad=1.174 | tok/s=175,160 | ETA=5:00:43 | VRAM=0.6GB | RAM=15%
2026-07-03 17:29:23,429 | step= 11900 | epoch=0.80 | loss=2.2788 | ppl=9.76 | lr=5.79e-05 | grad=1.047 | tok/s=174,759 | ETA=4:59:24 | VRAM=0.6GB | RAM=15%
2026-07-03 17:31:23,529 | step= 11920 | epoch=0.80 | loss=2.2323 | ppl=9.32 | lr=5.75e-05 | grad=1.279 | tok/s=173,048 | ETA=5:00:21 | VRAM=0.6GB | RAM=15%
2026-07-03 17:33:24,192 | step= 11940 | epoch=0.80 | loss=2.3019 | ppl=9.99 | lr=5.72e-05 | grad=1.162 | tok/s=175,051 | ETA=4:54:55 | VRAM=0.6GB | RAM=15%
2026-07-03 17:35:24,522 | step= 11960 | epoch=0.80 | loss=2.2696 | ppl=9.68 | lr=5.68e-05 | grad=0.884 | tok/s=173,151 | ETA=4:56:08 | VRAM=0.6GB | RAM=15%
2026-07-03 17:37:24,682 | step= 11980 | epoch=0.80 | loss=2.2216 | ppl=9.22 | lr=5.65e-05 | grad=1.269 | tok/s=174,934 | ETA=4:51:07 | VRAM=0.6GB | RAM=15%
2026-07-03 17:39:24,443 | step= 12000 | epoch=0.81 | loss=2.2868 | ppl=9.84 | lr=5.61e-05 | grad=0.851 | tok/s=175,004 | ETA=4:49:01 | VRAM=0.6GB | RAM=15%
2026-07-03 17:46:31,789 | VAL step=12000 epoch=0.81 loss=2.2704 ppl=9.68 ★ BEST
2026-07-03 17:46:31,859 | Checkpoint saved: step 12000
2026-07-03 17:46:31,885 | Saved safetensors: 47 tensors
2026-07-03 17:46:32,116 | HTTP Request: POST https://huggingface.co/api/repos/create "HTTP/1.1 409 Conflict"
2026-07-03 17:46:32,178 | HTTP Request: POST https://huggingface.co/api/validate-yaml "HTTP/1.1 200 OK"
2026-07-03 17:46:32,315 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-4/preupload/main "HTTP/1.1 200 OK"
2026-07-03 17:46:36,295 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-4/commit/main "HTTP/1.1 200 OK"
2026-07-03 17:46:36,299 | Hub push step=12000
2026-07-03 17:48:36,930 | step= 12020 | epoch=0.81 | loss=2.2716 | ppl=9.70 | lr=5.58e-05 | grad=0.950 | tok/s=173,389 | ETA=4:49:41 | VRAM=0.6GB | RAM=15%
2026-07-03 17:50:36,848 | step= 12040 | epoch=0.81 | loss=2.2200 | ppl=9.21 | lr=5.54e-05 | grad=0.895 | tok/s=172,607 | ETA=4:48:59 | VRAM=0.6GB | RAM=15%
2026-07-03 17:52:37,761 | step= 12060 | epoch=0.81 | loss=2.3029 | ppl=10.00 | lr=5.51e-05 | grad=1.436 | tok/s=174,101 | ETA=4:44:29 | VRAM=0.6GB | RAM=15%
2026-07-03 17:54:37,507 | step= 12080 | epoch=0.81 | loss=2.2549 | ppl=9.53 | lr=5.47e-05 | grad=1.083 | tok/s=175,725 | ETA=4:39:53 | VRAM=0.6GB | RAM=15%
2026-07-03 17:56:37,747 | step= 12100 | epoch=0.81 | loss=2.2079 | ppl=9.10 | lr=5.44e-05 | grad=1.252 | tok/s=172,587 | ETA=4:42:57 | VRAM=0.6GB | RAM=15%
2026-07-03 17:58:38,225 | step= 12120 | epoch=0.81 | loss=2.2815 | ppl=9.79 | lr=5.41e-05 | grad=1.198 | tok/s=174,426 | ETA=4:37:57 | VRAM=0.6GB | RAM=15%
2026-07-03 18:00:38,217 | step= 12140 | epoch=0.81 | loss=2.2446 | ppl=9.44 | lr=5.37e-05 | grad=1.033 | tok/s=174,345 | ETA=4:36:05 | VRAM=0.6GB | RAM=15%
2026-07-03 18:02:37,995 | step= 12160 | epoch=0.82 | loss=2.2175 | ppl=9.18 | lr=5.34e-05 | grad=1.241 | tok/s=174,304 | ETA=4:34:09 | VRAM=0.6GB | RAM=15%
2026-07-03 18:04:37,899 | step= 12180 | epoch=0.82 | loss=2.2873 | ppl=9.85 | lr=5.31e-05 | grad=1.596 | tok/s=173,887 | ETA=4:32:48 | VRAM=0.6GB | RAM=15%
2026-07-03 18:06:39,242 | step= 12200 | epoch=0.82 | loss=2.2659 | ppl=9.64 | lr=5.27e-05 | grad=0.826 | tok/s=173,501 | ETA=4:31:23 | VRAM=0.6GB | RAM=15%
2026-07-03 18:08:39,526 | step= 12220 | epoch=0.82 | loss=2.2518 | ppl=9.51 | lr=5.24e-05 | grad=0.999 | tok/s=175,148 | ETA=4:26:51 | VRAM=0.6GB | RAM=15%
2026-07-03 18:10:39,358 | step= 12240 | epoch=0.82 | loss=2.2721 | ppl=9.70 | lr=5.21e-05 | grad=1.050 | tok/s=174,822 | ETA=4:25:21 | VRAM=0.6GB | RAM=15%
2026-07-03 18:12:40,037 | step= 12260 | epoch=0.82 | loss=2.2727 | ppl=9.71 | lr=5.18e-05 | grad=0.957 | tok/s=172,167 | ETA=4:27:24 | VRAM=0.6GB | RAM=15%
2026-07-03 18:14:41,222 | step= 12280 | epoch=0.82 | loss=2.2561 | ppl=9.55 | lr=5.14e-05 | grad=0.880 | tok/s=174,724 | ETA=4:21:30 | VRAM=0.6GB | RAM=15%
2026-07-03 18:16:41,033 | step= 12300 | epoch=0.83 | loss=2.2040 | ppl=9.06 | lr=5.11e-05 | grad=1.566 | tok/s=174,592 | ETA=4:19:41 | VRAM=0.6GB | RAM=15%
2026-07-03 18:18:42,116 | step= 12320 | epoch=0.83 | loss=2.2760 | ppl=9.74 | lr=5.08e-05 | grad=0.977 | tok/s=172,452 | ETA=4:20:53 | VRAM=0.6GB | RAM=15%
2026-07-03 18:20:42,372 | step= 12340 | epoch=0.83 | loss=2.2559 | ppl=9.54 | lr=5.05e-05 | grad=0.866 | tok/s=174,870 | ETA=4:15:17 | VRAM=0.6GB | RAM=15%
2026-07-03 18:22:42,212 | step= 12360 | epoch=0.83 | loss=2.2266 | ppl=9.27 | lr=5.02e-05 | grad=0.955 | tok/s=174,880 | ETA=4:13:16 | VRAM=0.6GB | RAM=15%
2026-07-03 18:24:42,001 | step= 12380 | epoch=0.83 | loss=2.3221 | ppl=10.20 | lr=4.99e-05 | grad=1.097 | tok/s=174,894 | ETA=4:11:15 | VRAM=0.6GB | RAM=15%
2026-07-03 18:26:41,811 | step= 12400 | epoch=0.83 | loss=2.2311 | ppl=9.31 | lr=4.96e-05 | grad=1.125 | tok/s=174,934 | ETA=4:09:12 | VRAM=0.6GB | RAM=15%
2026-07-03 18:33:50,204 | VAL step=12400 epoch=0.83 loss=2.2555 ppl=9.54 ★ BEST
2026-07-03 18:33:50,276 | Checkpoint saved: step 12400
2026-07-03 18:33:50,303 | Saved safetensors: 47 tensors
2026-07-03 18:33:50,557 | HTTP Request: POST https://huggingface.co/api/repos/create "HTTP/1.1 409 Conflict"
2026-07-03 18:33:50,619 | HTTP Request: POST https://huggingface.co/api/validate-yaml "HTTP/1.1 200 OK"
2026-07-03 18:33:50,719 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-4/preupload/main "HTTP/1.1 200 OK"
2026-07-03 18:33:55,268 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-4/commit/main "HTTP/1.1 200 OK"
2026-07-03 18:33:55,274 | Hub push step=12400
2026-07-03 18:35:55,972 | step= 12420 | epoch=0.83 | loss=2.2632 | ppl=9.61 | lr=4.93e-05 | grad=0.880 | tok/s=172,817 | ETA=4:10:14 | VRAM=0.6GB | RAM=15%
2026-07-03 18:37:56,142 | step= 12440 | epoch=0.84 | loss=2.1828 | ppl=8.87 | lr=4.90e-05 | grad=1.088 | tok/s=175,062 | ETA=4:05:02 | VRAM=0.6GB | RAM=15%
2026-07-03 18:39:55,923 | step= 12460 | epoch=0.84 | loss=2.2566 | ppl=9.55 | lr=4.87e-05 | grad=1.143 | tok/s=175,208 | ETA=4:02:50 | VRAM=0.6GB | RAM=15%
2026-07-03 18:41:55,685 | step= 12480 | epoch=0.84 | loss=2.2492 | ppl=9.48 | lr=4.84e-05 | grad=1.245 | tok/s=174,917 | ETA=4:01:15 | VRAM=0.6GB | RAM=15%
2026-07-03 18:43:55,846 | step= 12500 | epoch=0.84 | loss=2.1936 | ppl=8.97 | lr=4.81e-05 | grad=0.900 | tok/s=173,109 | ETA=4:01:45 | VRAM=0.6GB | RAM=15%
2026-07-03 18:45:56,846 | step= 12520 | epoch=0.84 | loss=2.3339 | ppl=10.32 | lr=4.78e-05 | grad=1.043 | tok/s=174,670 | ETA=3:57:35 | VRAM=0.6GB | RAM=15%
2026-07-03 18:47:56,606 | step= 12540 | epoch=0.84 | loss=2.2616 | ppl=9.60 | lr=4.75e-05 | grad=1.171 | tok/s=174,993 | ETA=3:55:09 | VRAM=0.6GB | RAM=15%
2026-07-03 18:49:56,829 | step= 12560 | epoch=0.84 | loss=2.2274 | ppl=9.28 | lr=4.72e-05 | grad=1.057 | tok/s=173,057 | ETA=3:55:46 | VRAM=0.6GB | RAM=15%
2026-07-03 18:51:57,299 | step= 12580 | epoch=0.84 | loss=2.2559 | ppl=9.54 | lr=4.69e-05 | grad=0.977 | tok/s=175,083 | ETA=3:51:03 | VRAM=0.6GB | RAM=15%
2026-07-03 18:53:57,184 | step= 12600 | epoch=0.85 | loss=2.2973 | ppl=9.95 | lr=4.66e-05 | grad=1.160 | tok/s=174,688 | ETA=3:49:34 | VRAM=0.6GB | RAM=15%
2026-07-03 18:55:58,362 | step= 12620 | epoch=0.85 | loss=2.2428 | ppl=9.42 | lr=4.63e-05 | grad=1.176 | tok/s=173,494 | ETA=3:49:08 | VRAM=0.6GB | RAM=15%
2026-07-03 18:57:58,320 | step= 12640 | epoch=0.85 | loss=2.2624 | ppl=9.61 | lr=4.61e-05 | grad=0.839 | tok/s=174,754 | ETA=3:45:29 | VRAM=0.6GB | RAM=15%
2026-07-03 18:59:58,346 | step= 12660 | epoch=0.85 | loss=2.2809 | ppl=9.79 | lr=4.58e-05 | grad=0.800 | tok/s=174,577 | ETA=3:43:43 | VRAM=0.6GB | RAM=15%
2026-07-03 19:01:58,239 | step= 12680 | epoch=0.85 | loss=2.2267 | ppl=9.27 | lr=4.55e-05 | grad=1.178 | tok/s=174,807 | ETA=3:41:25 | VRAM=0.6GB | RAM=15%
2026-07-03 19:03:58,129 | step= 12700 | epoch=0.85 | loss=2.2631 | ppl=9.61 | lr=4.52e-05 | grad=0.944 | tok/s=174,788 | ETA=3:39:27 | VRAM=0.6GB | RAM=15%
2026-07-03 19:05:57,955 | step= 12720 | epoch=0.85 | loss=2.2616 | ppl=9.60 | lr=4.50e-05 | grad=1.048 | tok/s=174,621 | ETA=3:37:39 | VRAM=0.6GB | RAM=15%
2026-07-03 19:07:57,828 | step= 12740 | epoch=0.86 | loss=2.2765 | ppl=9.74 | lr=4.47e-05 | grad=0.853 | tok/s=174,241 | ETA=3:36:08 | VRAM=0.6GB | RAM=15%
2026-07-03 19:09:58,761 | step= 12760 | epoch=0.86 | loss=2.3042 | ppl=10.02 | lr=4.44e-05 | grad=0.975 | tok/s=174,707 | ETA=3:33:33 | VRAM=0.6GB | RAM=15%
2026-07-03 19:11:58,467 | step= 12780 | epoch=0.86 | loss=2.2465 | ppl=9.45 | lr=4.42e-05 | grad=0.875 | tok/s=174,913 | ETA=3:31:18 | VRAM=0.6GB | RAM=15%
2026-07-03 19:13:58,488 | step= 12800 | epoch=0.86 | loss=2.2629 | ppl=9.61 | lr=4.39e-05 | grad=0.935 | tok/s=172,891 | ETA=3:31:45 | VRAM=0.6GB | RAM=15%
2026-07-03 19:21:06,646 | VAL step=12800 epoch=0.86 loss=2.2479 ppl=9.47 ★ BEST
2026-07-03 19:21:06,722 | Checkpoint saved: step 12800
2026-07-03 19:21:06,745 | Saved safetensors: 47 tensors
2026-07-03 19:21:06,979 | HTTP Request: POST https://huggingface.co/api/repos/create "HTTP/1.1 409 Conflict"
2026-07-03 19:21:07,042 | HTTP Request: POST https://huggingface.co/api/validate-yaml "HTTP/1.1 200 OK"
2026-07-03 19:21:07,310 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-4/preupload/main "HTTP/1.1 200 OK"
2026-07-03 19:21:10,424 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-4/commit/main "HTTP/1.1 200 OK"
2026-07-03 19:21:10,428 | Hub push step=12800
2026-07-03 19:23:11,436 | step= 12820 | epoch=0.86 | loss=2.2677 | ppl=9.66 | lr=4.36e-05 | grad=0.992 | tok/s=171,103 | ETA=3:31:56 | VRAM=0.6GB | RAM=15%
2026-07-03 19:25:13,003 | step= 12840 | epoch=0.86 | loss=2.2547 | ppl=9.53 | lr=4.34e-05 | grad=1.092 | tok/s=173,173 | ETA=3:27:23 | VRAM=0.6GB | RAM=15%
2026-07-03 19:27:13,006 | step= 12860 | epoch=0.86 | loss=2.2360 | ppl=9.36 | lr=4.31e-05 | grad=0.977 | tok/s=174,637 | ETA=3:23:38 | VRAM=0.6GB | RAM=15%
2026-07-03 19:29:12,857 | step= 12880 | epoch=0.86 | loss=2.3005 | ppl=9.98 | lr=4.29e-05 | grad=1.038 | tok/s=174,401 | ETA=3:21:55 | VRAM=0.6GB | RAM=15%
2026-07-03 19:31:12,807 | step= 12900 | epoch=0.87 | loss=2.2513 | ppl=9.50 | lr=4.26e-05 | grad=0.841 | tok/s=174,775 | ETA=3:19:29 | VRAM=0.6GB | RAM=15%
2026-07-03 19:33:12,668 | step= 12920 | epoch=0.87 | loss=2.2374 | ppl=9.37 | lr=4.24e-05 | grad=0.832 | tok/s=174,908 | ETA=3:17:20 | VRAM=0.6GB | RAM=15%
2026-07-03 19:35:12,637 | step= 12940 | epoch=0.87 | loss=2.2802 | ppl=9.78 | lr=4.21e-05 | grad=0.995 | tok/s=174,014 | ETA=3:16:20 | VRAM=0.6GB | RAM=15%
2026-07-03 19:37:13,075 | step= 12960 | epoch=0.87 | loss=2.2904 | ppl=9.88 | lr=4.19e-05 | grad=1.053 | tok/s=174,030 | ETA=3:14:19 | VRAM=0.6GB | RAM=15%
2026-07-03 19:39:13,428 | step= 12980 | epoch=0.87 | loss=2.2159 | ppl=9.17 | lr=4.17e-05 | grad=0.849 | tok/s=174,256 | ETA=3:12:04 | VRAM=0.6GB | RAM=15%
2026-07-03 19:41:13,932 | step= 13000 | epoch=0.87 | loss=2.2685 | ppl=9.66 | lr=4.14e-05 | grad=1.032 | tok/s=173,436 | ETA=3:10:57 | VRAM=0.6GB | RAM=15%
2026-07-03 19:43:14,186 | step= 13020 | epoch=0.87 | loss=2.2806 | ppl=9.78 | lr=4.12e-05 | grad=0.975 | tok/s=173,943 | ETA=3:08:23 | VRAM=0.6GB | RAM=15%
2026-07-03 19:45:15,147 | step= 13040 | epoch=0.88 | loss=2.2558 | ppl=9.54 | lr=4.09e-05 | grad=0.910 | tok/s=172,567 | ETA=3:07:52 | VRAM=0.6GB | RAM=15%
2026-07-03 19:47:16,433 | step= 13060 | epoch=0.88 | loss=2.2967 | ppl=9.94 | lr=4.07e-05 | grad=0.892 | tok/s=173,192 | ETA=3:05:11 | VRAM=0.6GB | RAM=15%
2026-07-03 19:49:17,345 | step= 13080 | epoch=0.88 | loss=2.2581 | ppl=9.56 | lr=4.05e-05 | grad=1.008 | tok/s=173,606 | ETA=3:02:43 | VRAM=0.6GB | RAM=15%
2026-07-03 19:51:18,188 | step= 13100 | epoch=0.88 | loss=2.2357 | ppl=9.35 | lr=4.03e-05 | grad=1.089 | tok/s=174,309 | ETA=2:59:59 | VRAM=0.6GB | RAM=15%
2026-07-03 19:53:17,985 | step= 13120 | epoch=0.88 | loss=2.2643 | ppl=9.62 | lr=4.00e-05 | grad=2.202 | tok/s=175,063 | ETA=2:57:13 | VRAM=0.6GB | RAM=15%
2026-07-03 19:55:17,731 | step= 13140 | epoch=0.88 | loss=2.2446 | ppl=9.44 | lr=3.98e-05 | grad=1.211 | tok/s=174,937 | ETA=2:55:21 | VRAM=0.6GB | RAM=15%
2026-07-03 19:57:17,488 | step= 13160 | epoch=0.88 | loss=2.2791 | ppl=9.77 | lr=3.96e-05 | grad=1.392 | tok/s=174,907 | ETA=2:53:23 | VRAM=0.6GB | RAM=15%
2026-07-03 19:59:17,500 | step= 13180 | epoch=0.88 | loss=2.2475 | ppl=9.46 | lr=3.94e-05 | grad=1.140 | tok/s=173,933 | ETA=2:52:21 | VRAM=0.6GB | RAM=15%
2026-07-03 20:01:17,468 | step= 13200 | epoch=0.89 | loss=2.1775 | ppl=8.82 | lr=3.92e-05 | grad=1.654 | tok/s=174,870 | ETA=2:49:25 | VRAM=0.6GB | RAM=15%
2026-07-03 20:08:24,746 | VAL step=13200 epoch=0.89 loss=2.3171 ppl=10.15
2026-07-03 20:08:24,820 | Checkpoint saved: step 13200
2026-07-03 20:08:24,846 | Saved safetensors: 47 tensors
2026-07-03 20:08:25,095 | HTTP Request: POST https://huggingface.co/api/repos/create "HTTP/1.1 409 Conflict"
2026-07-03 20:08:25,158 | HTTP Request: POST https://huggingface.co/api/validate-yaml "HTTP/1.1 200 OK"
2026-07-03 20:08:25,256 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-4/preupload/main "HTTP/1.1 200 OK"
2026-07-03 20:08:28,032 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-4/commit/main "HTTP/1.1 200 OK"
2026-07-03 20:08:28,036 | Hub push step=13200
2026-07-03 20:10:28,576 | step= 13220 | epoch=0.89 | loss=2.2276 | ppl=9.28 | lr=3.89e-05 | grad=1.065 | tok/s=173,043 | ETA=2:49:12 | VRAM=0.6GB | RAM=15%
2026-07-03 20:12:29,886 | step= 13240 | epoch=0.89 | loss=2.1931 | ppl=8.96 | lr=3.87e-05 | grad=1.024 | tok/s=173,929 | ETA=2:46:19 | VRAM=0.6GB | RAM=15%
2026-07-03 20:14:30,091 | step= 13260 | epoch=0.89 | loss=2.2019 | ppl=9.04 | lr=3.85e-05 | grad=1.247 | tok/s=174,497 | ETA=2:43:47 | VRAM=0.6GB | RAM=15%
2026-07-03 20:16:29,913 | step= 13280 | epoch=0.89 | loss=2.1968 | ppl=9.00 | lr=3.83e-05 | grad=0.982 | tok/s=174,664 | ETA=2:41:37 | VRAM=0.6GB | RAM=15%
2026-07-03 20:18:29,663 | step= 13300 | epoch=0.89 | loss=2.1195 | ppl=8.33 | lr=3.81e-05 | grad=1.198 | tok/s=174,766 | ETA=2:39:32 | VRAM=0.6GB | RAM=15%
2026-07-03 20:20:29,453 | step= 13320 | epoch=0.89 | loss=2.1772 | ppl=8.82 | lr=3.79e-05 | grad=1.353 | tok/s=175,071 | ETA=2:37:16 | VRAM=0.6GB | RAM=15%
2026-07-03 20:22:29,203 | step= 13340 | epoch=0.90 | loss=2.1396 | ppl=8.50 | lr=3.77e-05 | grad=1.094 | tok/s=175,004 | ETA=2:35:19 | VRAM=0.6GB | RAM=15%
2026-07-03 20:24:28,909 | step= 13360 | epoch=0.90 | loss=2.1154 | ppl=8.29 | lr=3.75e-05 | grad=1.161 | tok/s=175,347 | ETA=2:33:02 | VRAM=0.6GB | RAM=15%
2026-07-03 20:26:28,574 | step= 13380 | epoch=0.90 | loss=2.1647 | ppl=8.71 | lr=3.73e-05 | grad=1.130 | tok/s=175,201 | ETA=2:31:10 | VRAM=0.6GB | RAM=15%
2026-07-03 20:28:28,355 | step= 13400 | epoch=0.90 | loss=2.2497 | ppl=9.49 | lr=3.71e-05 | grad=1.190 | tok/s=174,270 | ETA=2:29:58 | VRAM=0.6GB | RAM=15%
2026-07-03 20:30:29,591 | step= 13420 | epoch=0.90 | loss=2.2163 | ppl=9.17 | lr=3.70e-05 | grad=1.398 | tok/s=172,743 | ETA=2:29:16 | VRAM=0.6GB | RAM=15%
2026-07-03 20:32:29,884 | step= 13440 | epoch=0.90 | loss=2.1960 | ppl=8.99 | lr=3.68e-05 | grad=1.784 | tok/s=174,939 | ETA=2:25:24 | VRAM=0.6GB | RAM=15%
2026-07-03 20:34:29,734 | step= 13460 | epoch=0.90 | loss=2.1757 | ppl=8.81 | lr=3.66e-05 | grad=1.463 | tok/s=174,827 | ETA=2:23:30 | VRAM=0.6GB | RAM=15%
2026-07-03 20:36:29,627 | step= 13480 | epoch=0.90 | loss=2.1492 | ppl=8.58 | lr=3.64e-05 | grad=1.430 | tok/s=174,319 | ETA=2:21:55 | VRAM=0.6GB | RAM=15%
2026-07-03 20:38:29,372 | step= 13500 | epoch=0.91 | loss=2.1137 | ppl=8.28 | lr=3.62e-05 | grad=1.681 | tok/s=174,959 | ETA=2:19:24 | VRAM=0.6GB | RAM=15%
2026-07-03 20:40:29,143 | step= 13520 | epoch=0.91 | loss=2.2400 | ppl=9.39 | lr=3.61e-05 | grad=1.571 | tok/s=174,779 | ETA=2:17:33 | VRAM=0.6GB | RAM=15%
2026-07-03 20:42:30,285 | step= 13540 | epoch=0.91 | loss=2.1875 | ppl=8.91 | lr=3.59e-05 | grad=0.935 | tok/s=174,112 | ETA=2:16:04 | VRAM=0.6GB | RAM=15%
2026-07-03 20:44:30,638 | step= 13560 | epoch=0.91 | loss=2.1638 | ppl=8.70 | lr=3.57e-05 | grad=0.971 | tok/s=174,529 | ETA=2:13:44 | VRAM=0.6GB | RAM=15%
2026-07-03 20:46:30,556 | step= 13580 | epoch=0.91 | loss=2.1978 | ppl=9.01 | lr=3.55e-05 | grad=0.915 | tok/s=174,870 | ETA=2:11:29 | VRAM=0.6GB | RAM=15%
2026-07-03 20:48:30,486 | step= 13600 | epoch=0.91 | loss=2.1972 | ppl=9.00 | lr=3.54e-05 | grad=0.848 | tok/s=174,332 | ETA=2:09:53 | VRAM=0.6GB | RAM=15%
2026-07-03 20:55:37,562 | VAL step=13600 epoch=0.91 loss=2.2627 ppl=9.61
2026-07-03 20:55:37,632 | Checkpoint saved: step 13600
2026-07-03 20:55:37,658 | Saved safetensors: 47 tensors
2026-07-03 20:55:37,891 | HTTP Request: POST https://huggingface.co/api/repos/create "HTTP/1.1 409 Conflict"
2026-07-03 20:55:37,968 | HTTP Request: POST https://huggingface.co/api/validate-yaml "HTTP/1.1 200 OK"
2026-07-03 20:55:38,433 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-4/preupload/main "HTTP/1.1 200 OK"
2026-07-03 20:55:41,667 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-4/commit/main "HTTP/1.1 200 OK"
2026-07-03 20:55:41,671 | Hub push step=13600
2026-07-03 20:57:42,396 | step= 13620 | epoch=0.91 | loss=2.2070 | ppl=9.09 | lr=3.52e-05 | grad=0.715 | tok/s=173,770 | ETA=2:08:18 | VRAM=0.6GB | RAM=15%
2026-07-03 20:59:42,372 | step= 13640 | epoch=0.92 | loss=2.1662 | ppl=8.73 | lr=3.51e-05 | grad=0.846 | tok/s=175,332 | ETA=2:05:10 | VRAM=0.6GB | RAM=15%
2026-07-03 21:01:42,205 | step= 13660 | epoch=0.92 | loss=2.1630 | ppl=8.70 | lr=3.49e-05 | grad=0.804 | tok/s=174,961 | ETA=2:03:26 | VRAM=0.6GB | RAM=15%
2026-07-03 21:03:43,106 | step= 13680 | epoch=0.92 | loss=2.1560 | ppl=8.64 | lr=3.47e-05 | grad=0.986 | tok/s=172,336 | ETA=2:03:17 | VRAM=0.6GB | RAM=15%
2026-07-03 21:05:43,447 | step= 13700 | epoch=0.92 | loss=2.0709 | ppl=7.93 | lr=3.46e-05 | grad=0.962 | tok/s=174,751 | ETA=1:59:35 | VRAM=0.6GB | RAM=15%
2026-07-03 21:07:43,436 | step= 13720 | epoch=0.92 | loss=2.1055 | ppl=8.21 | lr=3.44e-05 | grad=1.157 | tok/s=172,663 | ETA=1:59:00 | VRAM=0.6GB | RAM=15%
2026-07-03 21:09:44,796 | step= 13740 | epoch=0.92 | loss=2.2158 | ppl=9.17 | lr=3.43e-05 | grad=0.853 | tok/s=172,788 | ETA=1:56:54 | VRAM=0.6GB | RAM=15%
2026-07-03 21:11:45,089 | step= 13760 | epoch=0.92 | loss=2.1411 | ppl=8.51 | lr=3.41e-05 | grad=0.769 | tok/s=174,890 | ETA=1:53:30 | VRAM=0.6GB | RAM=15%
2026-07-03 21:13:45,050 | step= 13780 | epoch=0.93 | loss=2.1600 | ppl=8.67 | lr=3.40e-05 | grad=0.908 | tok/s=174,370 | ETA=1:51:50 | VRAM=0.6GB | RAM=15%
2026-07-03 21:15:44,927 | step= 13800 | epoch=0.93 | loss=2.2077 | ppl=9.09 | lr=3.39e-05 | grad=0.909 | tok/s=174,939 | ETA=1:49:28 | VRAM=0.6GB | RAM=15%
2026-07-03 21:17:45,119 | step= 13820 | epoch=0.93 | loss=2.1671 | ppl=8.73 | lr=3.37e-05 | grad=0.864 | tok/s=174,028 | ETA=1:48:02 | VRAM=0.6GB | RAM=15%
2026-07-03 21:19:45,341 | step= 13840 | epoch=0.93 | loss=2.0516 | ppl=7.78 | lr=3.36e-05 | grad=0.913 | tok/s=174,829 | ETA=1:45:33 | VRAM=0.6GB | RAM=15%
2026-07-03 21:21:45,401 | step= 13860 | epoch=0.93 | loss=2.1585 | ppl=8.66 | lr=3.34e-05 | grad=0.968 | tok/s=174,516 | ETA=1:43:44 | VRAM=0.6GB | RAM=15%
2026-07-03 21:23:45,691 | step= 13880 | epoch=0.93 | loss=2.2031 | ppl=9.05 | lr=3.33e-05 | grad=0.865 | tok/s=173,617 | ETA=1:42:16 | VRAM=0.6GB | RAM=15%
2026-07-03 21:25:45,912 | step= 13900 | epoch=0.93 | loss=2.2445 | ppl=9.44 | lr=3.32e-05 | grad=0.896 | tok/s=174,649 | ETA=1:39:40 | VRAM=0.6GB | RAM=15%
2026-07-03 21:27:46,017 | step= 13920 | epoch=0.93 | loss=2.2678 | ppl=9.66 | lr=3.31e-05 | grad=0.847 | tok/s=174,016 | ETA=1:38:01 | VRAM=0.6GB | RAM=15%
2026-07-03 21:29:45,961 | step= 13940 | epoch=0.94 | loss=2.2296 | ppl=9.30 | lr=3.29e-05 | grad=1.037 | tok/s=173,047 | ETA=1:36:33 | VRAM=0.6GB | RAM=15%
2026-07-03 21:31:46,938 | step= 13960 | epoch=0.94 | loss=2.2350 | ppl=9.35 | lr=3.28e-05 | grad=0.967 | tok/s=174,551 | ETA=1:33:43 | VRAM=0.6GB | RAM=15%
2026-07-03 21:33:47,153 | step= 13980 | epoch=0.94 | loss=2.3107 | ppl=10.08 | lr=3.27e-05 | grad=1.077 | tok/s=173,442 | ETA=1:32:18 | VRAM=0.6GB | RAM=15%
2026-07-03 21:35:47,407 | step= 14000 | epoch=0.94 | loss=2.2543 | ppl=9.53 | lr=3.26e-05 | grad=0.826 | tok/s=174,365 | ETA=1:29:49 | VRAM=0.6GB | RAM=15%
2026-07-03 21:42:54,379 | VAL step=14000 epoch=0.94 loss=2.2449 ppl=9.44 ★ BEST
2026-07-03 21:42:54,447 | Checkpoint saved: step 14000
2026-07-03 21:42:54,474 | Saved safetensors: 47 tensors
2026-07-03 21:42:54,715 | HTTP Request: POST https://huggingface.co/api/repos/create "HTTP/1.1 409 Conflict"
2026-07-03 21:42:54,777 | HTTP Request: POST https://huggingface.co/api/validate-yaml "HTTP/1.1 200 OK"
2026-07-03 21:42:54,867 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-4/preupload/main "HTTP/1.1 200 OK"
2026-07-03 21:42:58,316 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-4/commit/main "HTTP/1.1 200 OK"
2026-07-03 21:42:58,319 | Hub push step=14000
2026-07-03 21:44:59,152 | step= 14020 | epoch=0.94 | loss=2.2232 | ppl=9.24 | lr=3.25e-05 | grad=1.234 | tok/s=173,202 | ETA=1:28:24 | VRAM=0.6GB | RAM=15%
2026-07-03 21:46:59,318 | step= 14040 | epoch=0.94 | loss=2.2969 | ppl=9.94 | lr=3.24e-05 | grad=0.986 | tok/s=173,384 | ETA=1:26:17 | VRAM=0.6GB | RAM=15%
2026-07-03 21:49:00,179 | step= 14060 | epoch=0.94 | loss=2.2939 | ppl=9.91 | lr=3.23e-05 | grad=1.062 | tok/s=174,479 | ETA=1:23:45 | VRAM=0.6GB | RAM=15%
2026-07-03 21:51:00,232 | step= 14080 | epoch=0.95 | loss=2.2545 | ppl=9.53 | lr=3.21e-05 | grad=0.885 | tok/s=174,636 | ETA=1:21:40 | VRAM=0.6GB | RAM=15%
2026-07-03 21:53:00,276 | step= 14100 | epoch=0.95 | loss=2.2652 | ppl=9.63 | lr=3.20e-05 | grad=0.898 | tok/s=174,508 | ETA=1:19:44 | VRAM=0.6GB | RAM=15%
2026-07-03 21:55:00,377 | step= 14120 | epoch=0.95 | loss=2.2554 | ppl=9.54 | lr=3.19e-05 | grad=0.925 | tok/s=174,621 | ETA=1:17:41 | VRAM=0.6GB | RAM=15%
2026-07-03 21:57:00,479 | step= 14140 | epoch=0.95 | loss=2.2711 | ppl=9.69 | lr=3.18e-05 | grad=0.824 | tok/s=174,071 | ETA=1:15:55 | VRAM=0.6GB | RAM=15%
2026-07-03 21:59:00,677 | step= 14160 | epoch=0.95 | loss=2.2146 | ppl=9.16 | lr=3.17e-05 | grad=1.034 | tok/s=174,819 | ETA=1:13:36 | VRAM=0.6GB | RAM=15%
2026-07-03 22:01:00,915 | step= 14180 | epoch=0.95 | loss=2.2650 | ppl=9.63 | lr=3.17e-05 | grad=0.749 | tok/s=173,633 | ETA=1:12:05 | VRAM=0.6GB | RAM=15%
2026-07-03 22:03:01,300 | step= 14200 | epoch=0.95 | loss=2.2275 | ppl=9.28 | lr=3.16e-05 | grad=1.053 | tok/s=173,416 | ETA=1:10:10 | VRAM=0.6GB | RAM=15%
2026-07-03 22:05:01,696 | step= 14220 | epoch=0.95 | loss=2.2171 | ppl=9.18 | lr=3.15e-05 | grad=1.093 | tok/s=174,411 | ETA=1:07:46 | VRAM=0.6GB | RAM=15%
2026-07-03 22:07:01,757 | step= 14240 | epoch=0.96 | loss=2.2640 | ppl=9.62 | lr=3.14e-05 | grad=1.087 | tok/s=174,433 | ETA=1:05:45 | VRAM=0.6GB | RAM=15%
2026-07-03 22:09:01,847 | step= 14260 | epoch=0.96 | loss=2.2494 | ppl=9.48 | lr=3.13e-05 | grad=0.819 | tok/s=174,930 | ETA=1:03:34 | VRAM=0.6GB | RAM=15%
2026-07-03 22:11:02,107 | step= 14280 | epoch=0.96 | loss=2.2380 | ppl=9.37 | lr=3.12e-05 | grad=0.900 | tok/s=174,457 | ETA=1:01:44 | VRAM=0.6GB | RAM=15%
2026-07-03 22:13:02,013 | step= 14300 | epoch=0.96 | loss=2.2056 | ppl=9.08 | lr=3.11e-05 | grad=0.849 | tok/s=174,671 | ETA=0:59:40 | VRAM=0.6GB | RAM=15%
2026-07-03 22:15:01,968 | step= 14320 | epoch=0.96 | loss=2.2360 | ppl=9.36 | lr=3.11e-05 | grad=1.112 | tok/s=174,454 | ETA=0:57:44 | VRAM=0.6GB | RAM=15%
2026-07-03 22:17:01,932 | step= 14340 | epoch=0.96 | loss=2.2640 | ppl=9.62 | lr=3.10e-05 | grad=1.105 | tok/s=174,603 | ETA=0:55:41 | VRAM=0.6GB | RAM=15%
2026-07-03 22:19:01,978 | step= 14360 | epoch=0.96 | loss=2.2536 | ppl=9.52 | lr=3.09e-05 | grad=1.176 | tok/s=174,377 | ETA=0:53:45 | VRAM=0.6GB | RAM=15%
2026-07-03 22:21:02,148 | step= 14380 | epoch=0.97 | loss=2.2443 | ppl=9.43 | lr=3.09e-05 | grad=0.913 | tok/s=174,221 | ETA=0:51:48 | VRAM=0.6GB | RAM=15%
2026-07-03 22:23:02,487 | step= 14400 | epoch=0.97 | loss=2.2325 | ppl=9.32 | lr=3.08e-05 | grad=0.969 | tok/s=173,673 | ETA=0:49:57 | VRAM=0.6GB | RAM=15%
2026-07-03 22:30:10,603 | VAL step=14400 epoch=0.97 loss=2.2386 ppl=9.38 ★ BEST
2026-07-03 22:30:10,674 | Checkpoint saved: step 14400
2026-07-03 22:30:10,702 | Saved safetensors: 47 tensors
2026-07-03 22:30:10,951 | HTTP Request: POST https://huggingface.co/api/repos/create "HTTP/1.1 409 Conflict"
2026-07-03 22:30:11,014 | HTTP Request: POST https://huggingface.co/api/validate-yaml "HTTP/1.1 200 OK"
2026-07-03 22:30:11,140 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-4/preupload/main "HTTP/1.1 200 OK"
2026-07-03 22:30:14,202 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-4/commit/main "HTTP/1.1 200 OK"
2026-07-03 22:30:14,206 | Hub push step=14400
2026-07-03 22:32:15,182 | step= 14420 | epoch=0.97 | loss=2.2699 | ppl=9.68 | lr=3.07e-05 | grad=0.949 | tok/s=172,501 | ETA=0:48:16 | VRAM=0.6GB | RAM=15%
2026-07-03 22:34:16,132 | step= 14440 | epoch=0.97 | loss=2.2429 | ppl=9.42 | lr=3.07e-05 | grad=0.791 | tok/s=174,680 | ETA=0:45:40 | VRAM=0.6GB | RAM=15%
2026-07-03 22:36:16,077 | step= 14460 | epoch=0.97 | loss=2.1844 | ppl=8.88 | lr=3.06e-05 | grad=0.801 | tok/s=174,742 | ETA=0:43:39 | VRAM=0.6GB | RAM=15%
2026-07-03 22:38:16,104 | step= 14480 | epoch=0.97 | loss=2.2722 | ppl=9.70 | lr=3.06e-05 | grad=0.850 | tok/s=174,350 | ETA=0:41:45 | VRAM=0.6GB | RAM=15%
2026-07-03 22:40:16,639 | step= 14500 | epoch=0.97 | loss=2.2538 | ppl=9.52 | lr=3.05e-05 | grad=0.843 | tok/s=174,224 | ETA=0:39:47 | VRAM=0.6GB | RAM=15%
2026-07-03 22:42:17,255 | step= 14520 | epoch=0.97 | loss=2.1790 | ppl=8.84 | lr=3.05e-05 | grad=1.190 | tok/s=173,967 | ETA=0:37:50 | VRAM=0.6GB | RAM=15%
2026-07-03 22:44:17,754 | step= 14540 | epoch=0.98 | loss=2.2649 | ppl=9.63 | lr=3.04e-05 | grad=0.750 | tok/s=172,685 | ETA=0:36:05 | VRAM=0.6GB | RAM=15%
2026-07-03 22:46:18,298 | step= 14560 | epoch=0.98 | loss=2.2608 | ppl=9.59 | lr=3.04e-05 | grad=0.965 | tok/s=173,833 | ETA=0:33:50 | VRAM=0.6GB | RAM=15%
2026-07-03 22:48:18,694 | step= 14580 | epoch=0.98 | loss=2.1861 | ppl=8.90 | lr=3.03e-05 | grad=1.123 | tok/s=174,440 | ETA=0:31:43 | VRAM=0.6GB | RAM=15%
2026-07-03 22:50:19,026 | step= 14600 | epoch=0.98 | loss=2.2404 | ppl=9.40 | lr=3.03e-05 | grad=0.800 | tok/s=173,786 | ETA=0:29:50 | VRAM=0.6GB | RAM=15%
2026-07-03 22:52:19,352 | step= 14620 | epoch=0.98 | loss=2.2367 | ppl=9.36 | lr=3.02e-05 | grad=0.982 | tok/s=173,855 | ETA=0:27:49 | VRAM=0.6GB | RAM=15%
2026-07-03 22:54:19,696 | step= 14640 | epoch=0.98 | loss=2.2346 | ppl=9.34 | lr=3.02e-05 | grad=0.900 | tok/s=174,438 | ETA=0:25:43 | VRAM=0.6GB | RAM=15%
2026-07-03 22:56:20,335 | step= 14660 | epoch=0.98 | loss=2.1897 | ppl=8.93 | lr=3.02e-05 | grad=0.973 | tok/s=173,277 | ETA=0:23:52 | VRAM=0.6GB | RAM=15%
2026-07-03 22:58:21,056 | step= 14680 | epoch=0.99 | loss=2.2947 | ppl=9.92 | lr=3.02e-05 | grad=2.358 | tok/s=173,690 | ETA=0:21:48 | VRAM=0.6GB | RAM=15%
2026-07-03 23:00:21,974 | step= 14700 | epoch=0.99 | loss=2.2783 | ppl=9.76 | lr=3.01e-05 | grad=1.473 | tok/s=173,345 | ETA=0:19:50 | VRAM=0.6GB | RAM=15%
2026-07-03 23:02:22,640 | step= 14720 | epoch=0.99 | loss=2.2375 | ppl=9.37 | lr=3.01e-05 | grad=0.983 | tok/s=174,269 | ETA=0:17:43 | VRAM=0.6GB | RAM=15%
2026-07-03 23:04:23,056 | step= 14740 | epoch=0.99 | loss=2.1290 | ppl=8.41 | lr=3.01e-05 | grad=1.475 | tok/s=173,869 | ETA=0:15:45 | VRAM=0.6GB | RAM=15%
2026-07-03 23:06:23,430 | step= 14760 | epoch=0.99 | loss=2.1861 | ppl=8.90 | lr=3.01e-05 | grad=1.351 | tok/s=173,719 | ETA=0:13:46 | VRAM=0.6GB | RAM=15%
2026-07-03 23:08:23,552 | step= 14780 | epoch=0.99 | loss=2.1656 | ppl=8.72 | lr=3.00e-05 | grad=1.261 | tok/s=174,903 | ETA=0:11:40 | VRAM=0.6GB | RAM=15%
2026-07-03 23:10:23,485 | step= 14800 | epoch=0.99 | loss=2.1459 | ppl=8.55 | lr=3.00e-05 | grad=0.989 | tok/s=175,021 | ETA=0:09:40 | VRAM=0.6GB | RAM=15%
2026-07-03 23:17:32,106 | VAL step=14800 epoch=0.99 loss=2.3084 ppl=10.06
2026-07-03 23:17:32,175 | Checkpoint saved: step 14800
2026-07-03 23:17:32,199 | Saved safetensors: 47 tensors
2026-07-03 23:17:32,442 | HTTP Request: POST https://huggingface.co/api/repos/create "HTTP/1.1 409 Conflict"
2026-07-03 23:17:32,505 | HTTP Request: POST https://huggingface.co/api/validate-yaml "HTTP/1.1 200 OK"
2026-07-03 23:17:32,732 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-4/preupload/main "HTTP/1.1 200 OK"
2026-07-03 23:17:36,313 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-4/commit/main "HTTP/1.1 200 OK"
2026-07-03 23:17:36,317 | Hub push step=14800
2026-07-03 23:19:36,798 | step= 14820 | epoch=0.99 | loss=2.1415 | ppl=8.51 | lr=3.00e-05 | grad=1.092 | tok/s=173,867 | ETA=0:07:43 | VRAM=0.6GB | RAM=15%
2026-07-03 23:21:36,990 | step= 14840 | epoch=1.00 | loss=2.0656 | ppl=7.89 | lr=3.00e-05 | grad=1.763 | tok/s=173,214 | ETA=0:05:44 | VRAM=0.6GB | RAM=15%
2026-07-03 23:23:36,728 | step= 14860 | epoch=1.00 | loss=2.2239 | ppl=9.24 | lr=3.00e-05 | grad=1.127 | tok/s=174,985 | ETA=0:03:41 | VRAM=0.6GB | RAM=15%
2026-07-03 23:25:36,884 | step= 14880 | epoch=1.00 | loss=2.1761 | ppl=8.81 | lr=3.00e-05 | grad=1.017 | tok/s=174,866 | ETA=0:01:41 | VRAM=0.6GB | RAM=15%
2026-07-03 23:34:28,792 | Final eval loss=2.3172 ppl=10.15
2026-07-03 23:34:28,874 | Checkpoint saved: step 14897
2026-07-03 23:34:28,902 | Saved safetensors: 47 tensors
2026-07-03 23:34:29,141 | HTTP Request: POST https://huggingface.co/api/repos/create "HTTP/1.1 409 Conflict"
2026-07-03 23:34:29,203 | HTTP Request: POST https://huggingface.co/api/validate-yaml "HTTP/1.1 200 OK"
2026-07-03 23:34:29,301 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-4/preupload/main "HTTP/1.1 200 OK"
2026-07-03 23:34:32,203 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-4/commit/main "HTTP/1.1 200 OK"
2026-07-03 23:34:32,207 | Hub push step=14897
2026-07-03 23:34:32,301 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-4/preupload/main "HTTP/1.1 200 OK"
2026-07-03 23:34:32,979 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-4/commit/main "HTTP/1.1 200 OK"
2026-07-03 23:34:33,065 | HTTP Request: POST https://huggingface.co/api/models/CyanMonkey/Exp-4/preupload/main "HTTP/1.1 200 OK"