logger/trajectory.log

data: {"data":"===== Job started at 2026-04-25 19:57:38 =====","timestamp":"2026-04-25T19:57:38Z"}

data: {"data":"Downloading setuptools (1.0MiB)","timestamp":"2026-04-25T19:57:52.294Z"}

data: {"data":"Downloading pillow (6.8MiB)","timestamp":"2026-04-25T19:57:52.295Z"}

data: {"data":"Downloading nvidia-nvshmem-cu13 (57.6MiB)","timestamp":"2026-04-25T19:57:52.295Z"}

data: {"data":"Downloading nvidia-cusolver (191.6MiB)","timestamp":"2026-04-25T19:57:52.295Z"}

data: {"data":"Downloading hf-xet (4.0MiB)","timestamp":"2026-04-25T19:57:52.295Z"}

data: {"data":"Downloading nvidia-cusparse (139.2MiB)","timestamp":"2026-04-25T19:57:52.295Z"}

data: {"data":"Downloading pandas (10.4MiB)","timestamp":"2026-04-25T19:57:52.295Z"}

data: {"data":"Downloading nvidia-cuda-nvrtc (86.0MiB)","timestamp":"2026-04-25T19:57:52.296Z"}

data: {"data":"Downloading nvidia-nvjitlink (38.8MiB)","timestamp":"2026-04-25T19:57:52.296Z"}

data: {"data":"Downloading uvloop (4.2MiB)","timestamp":"2026-04-25T19:57:52.296Z"}

data: {"data":"Downloading nvidia-nccl-cu13 (187.4MiB)","timestamp":"2026-04-25T19:57:52.296Z"}

data: {"data":"Downloading nvidia-cuda-runtime (2.1MiB)","timestamp":"2026-04-25T19:57:52.297Z"}

data: {"data":"Downloading networkx (2.0MiB)","timestamp":"2026-04-25T19:57:52.297Z"}

data: {"data":"Downloading nvidia-cublas (403.5MiB)","timestamp":"2026-04-25T19:57:52.297Z"}

data: {"data":"Downloading aiohttp (1.7MiB)","timestamp":"2026-04-25T19:57:52.297Z"}

data: {"data":"Downloading nvidia-curand (56.8MiB)","timestamp":"2026-04-25T19:57:52.298Z"}

data: {"data":"Downloading nvidia-cuda-cupti (10.2MiB)","timestamp":"2026-04-25T19:57:52.298Z"}

data: {"data":"Downloading tokenizers (3.1MiB)","timestamp":"2026-04-25T19:57:52.298Z"}

data: {"data":"Downloading sympy (6.0MiB)","timestamp":"2026-04-25T19:57:52.298Z"}

data: {"data":"Downloading pygments (1.2MiB)","timestamp":"2026-04-25T19:57:52.299Z"}

data: {"data":"Downloading triton (179.5MiB)","timestamp":"2026-04-25T19:57:52.299Z"}

data: {"data":"Downloading trackio (1.6MiB)","timestamp":"2026-04-25T19:57:52.300Z"}

data: {"data":"Downloading nvidia-cufile (1.2MiB)","timestamp":"2026-04-25T19:57:52.300Z"}

data: {"data":"Downloading pyarrow (46.6MiB)","timestamp":"2026-04-25T19:57:52.300Z"}

data: {"data":"Downloading nvidia-cusparselt-cu13 (162.0MiB)","timestamp":"2026-04-25T19:57:52.300Z"}

data: {"data":"Downloading nvidia-cufft (204.2MiB)","timestamp":"2026-04-25T19:57:52.300Z"}

data: {"data":"Downloading transformers (9.9MiB)","timestamp":"2026-04-25T19:57:52.301Z"}

data: {"data":"Downloading torch (506.1MiB)","timestamp":"2026-04-25T19:57:52.301Z"}

data: {"data":"Downloading numpy (15.9MiB)","timestamp":"2026-04-25T19:57:52.301Z"}

data: {"data":"Downloading cuda-bindings (6.0MiB)","timestamp":"2026-04-25T19:57:52.301Z"}

data: {"data":"Downloading nvidia-cudnn-cu13 (349.1MiB)","timestamp":"2026-04-25T19:57:52.302Z"}

data: {"data":" Downloaded nvidia-cufile","timestamp":"2026-04-25T19:57:52.891Z"}

data: {"data":" Downloaded aiohttp","timestamp":"2026-04-25T19:57:53.092Z"}

data: {"data":" Downloaded trackio","timestamp":"2026-04-25T19:57:53.136Z"}

data: {"data":" Downloaded nvidia-cuda-runtime","timestamp":"2026-04-25T19:57:53.198Z"}

data: {"data":" Downloaded pygments","timestamp":"2026-04-25T19:57:53.324Z"}

data: {"data":" Downloaded tokenizers","timestamp":"2026-04-25T19:57:53.415Z"}

data: {"data":" Downloaded setuptools","timestamp":"2026-04-25T19:57:53.520Z"}

data: {"data":" Downloaded hf-xet","timestamp":"2026-04-25T19:57:53.612Z"}

data: {"data":" Downloaded networkx","timestamp":"2026-04-25T19:57:53.688Z"}

data: {"data":" Downloaded uvloop","timestamp":"2026-04-25T19:57:53.702Z"}

data: {"data":" Downloaded cuda-bindings","timestamp":"2026-04-25T19:57:54.130Z"}

data: {"data":" Downloaded pillow","timestamp":"2026-04-25T19:57:54.215Z"}

data: {"data":" Downloaded sympy","timestamp":"2026-04-25T19:57:54.570Z"}

data: {"data":" Downloaded nvidia-cuda-cupti","timestamp":"2026-04-25T19:57:54.733Z"}

data: {"data":" Downloaded numpy","timestamp":"2026-04-25T19:57:55.479Z"}

data: {"data":" Downloaded pandas","timestamp":"2026-04-25T19:57:56.503Z"}

data: {"data":" Downloaded transformers","timestamp":"2026-04-25T19:57:56.800Z"}

data: {"data":" Downloaded nvidia-nvjitlink","timestamp":"2026-04-25T19:57:57.075Z"}

data: {"data":" Downloaded nvidia-curand","timestamp":"2026-04-25T19:57:58.175Z"}

data: {"data":" Downloaded nvidia-nvshmem-cu13","timestamp":"2026-04-25T19:57:58.232Z"}

data: {"data":" Downloaded pyarrow","timestamp":"2026-04-25T19:57:58.535Z"}

data: {"data":" Downloaded nvidia-cuda-nvrtc","timestamp":"2026-04-25T19:57:59.905Z"}

data: {"data":" Downloaded nvidia-cusparse","timestamp":"2026-04-25T19:58:02.015Z"}

data: {"data":" Downloaded nvidia-cusparselt-cu13","timestamp":"2026-04-25T19:58:02.624Z"}

data: {"data":" Downloaded nvidia-nccl-cu13","timestamp":"2026-04-25T19:58:03.213Z"}

data: {"data":" Downloaded nvidia-cusolver","timestamp":"2026-04-25T19:58:03.282Z"}

data: {"data":" Downloaded triton","timestamp":"2026-04-25T19:58:03.328Z"}

data: {"data":" Downloaded nvidia-cufft","timestamp":"2026-04-25T19:58:03.404Z"}

data: {"data":" Downloaded nvidia-cudnn-cu13","timestamp":"2026-04-25T19:58:04.451Z"}

data: {"data":" Downloaded nvidia-cublas","timestamp":"2026-04-25T19:58:04.630Z"}

data: {"data":" Downloaded torch","timestamp":"2026-04-25T19:58:23.747Z"}

data: {"data":"Installed 90 packages in 436ms","timestamp":"2026-04-25T19:58:24.184Z"}

data: {"data":"","timestamp":"2026-04-25T19:58:43.478Z"}

data: {"data":"\rconfig.json:   0%|          | 0.00/663 [00:00<?, ?B/s]\u001b[A\rconfig.json: 100%|██████████| 663/663 [00:00<00:00, 3.33MB/s]","timestamp":"2026-04-25T19:58:43.478Z"}

data: {"data":"","timestamp":"2026-04-25T19:58:43.579Z"}

data: {"data":"\rmodel.safetensors.index.json:   0%|          | 0.00/27.8k [00:00<?, ?B/s]\u001b[A\rmodel.safetensors.index.json: 100%|██████████| 27.8k/27.8k [00:00<00:00, 84.4MB/s]","timestamp":"2026-04-25T19:58:43.580Z"}

data: {"data":"","timestamp":"2026-04-25T19:58:43.600Z"}

data: {"data":"\rDownloading (incomplete total...): 0.00B [00:00, ?B/s]\u001b[A","timestamp":"2026-04-25T19:58:43.603Z"}

data: {"data":"\rFetching 4 files:   0%|          | 0/4 [00:00<?, ?it/s]\u001b[A","timestamp":"2026-04-25T19:58:43.628Z"}

data: {"data":"\rDownloading (incomplete total...):   0%|          | 0.00/3.95G [00:00<?, ?B/s]\u001b[A","timestamp":"2026-04-25T19:58:43.629Z"}

data: {"data":"\rDownloading (incomplete total...):   0%|          | 0.00/7.81G [00:00<?, ?B/s]\u001b[A","timestamp":"2026-04-25T19:58:43.632Z"}

data: {"data":"\rDownloading (incomplete total...):   0%|          | 0.00/11.7G [00:00<?, ?B/s]\u001b[A","timestamp":"2026-04-25T19:58:43.647Z"}

data: {"data":"\rDownloading (incomplete total...):   0%|          | 0.00/15.2G [00:00<?, ?B/s]\u001b[A","timestamp":"2026-04-25T19:58:44.605Z"}

data: {"data":"\rDownloading (incomplete total...):   0%|          | 0.00/15.2G [00:01<?, ?B/s]\u001b[A","timestamp":"2026-04-25T19:58:44.605Z"}

data: {"data":"\rDownloading (incomplete total...):   0%|          | 0.00/15.2G [00:01<?, ?B/s]\u001b[A","timestamp":"2026-04-25T19:58:45.605Z"}

data: {"data":"\rDownloading (incomplete total...):   6%|▌         | 916M/15.2G [00:02<00:15, 916MB/s]\u001b[A","timestamp":"2026-04-25T19:58:45.605Z"}

data: {"data":"\rDownloading (incomplete total...):   6%|▌         | 916M/15.2G [00:02<00:15, 916MB/s]\u001b[A","timestamp":"2026-04-25T19:58:46.648Z"}

data: {"data":"\rDownloading (incomplete total...):  19%|█▉        | 2.87G/15.2G [00:03<00:09, 1.36GB/s]\u001b[A","timestamp":"2026-04-25T19:58:47.813Z"}

data: {"data":"\rDownloading (incomplete total...):  34%|███▍      | 5.19G/15.2G [00:04<00:05, 1.81GB/s]\u001b[A","timestamp":"2026-04-25T19:58:47.813Z"}

data: {"data":"\rDownloading (incomplete total...):  34%|███▍      | 5.19G/15.2G [00:04<00:05, 1.81GB/s]\u001b[A","timestamp":"2026-04-25T19:58:47.813Z"}

data: {"data":"\rDownloading (incomplete total...):  34%|███▍      | 5.19G/15.2G [00:04<00:05, 1.81GB/s]\u001b[A","timestamp":"2026-04-25T19:58:48.814Z"}

data: {"data":"\rDownloading (incomplete total...):  56%|█████▌    | 8.46G/15.2G [00:05<00:03, 2.25GB/s]\u001b[A","timestamp":"2026-04-25T19:58:48.814Z"}

data: {"data":"\rDownloading (incomplete total...):  56%|█████▌    | 8.53G/15.2G [00:05<00:02, 2.57GB/s]\u001b[A","timestamp":"2026-04-25T19:58:49.824Z"}

data: {"data":"\rDownloading (incomplete total...):  74%|███████▎  | 11.2G/15.2G [00:06<00:01, 2.59GB/s]\u001b[A","timestamp":"2026-04-25T19:58:50.807Z"}

data: {"data":"\rFetching 4 files:  25%|██▌       | 1/4 [00:07<00:21,  7.20s/it]\u001b[A\rFetching 4 files: 100%|██████████| 4/4 [00:07<00:00,  1.80s/it]","timestamp":"2026-04-25T19:58:50.807Z"}

data: {"data":"","timestamp":"2026-04-25T19:58:50.808Z"}

data: {"data":"\rDownload complete: 100%|██████████| 15.2G/15.2G [00:07<00:00, 2.59GB/s]                \u001b[A\rDownload complete: 100%|██████████| 15.2G/15.2G [00:07<00:00, 2.10GB/s]","timestamp":"2026-04-25T19:58:50.840Z"}

data: {"data":"","timestamp":"2026-04-25T19:58:51.651Z"}

data: {"data":"\rLoading weights:   0%|          | 0/339 [00:00<?, ?it/s]\u001b[A","timestamp":"2026-04-25T19:58:52.759Z"}

data: {"data":"\rLoading weights:  15%|█▌        | 52/339 [00:01<00:06, 46.94it/s]\u001b[A","timestamp":"2026-04-25T19:58:53.854Z"}

data: {"data":"\rLoading weights:  29%|██▉       | 99/339 [00:02<00:05, 44.68it/s]\u001b[A","timestamp":"2026-04-25T19:58:54.953Z"}

data: {"data":"\rLoading weights:  42%|████▏     | 144/339 [00:03<00:04, 42.95it/s]\u001b[A","timestamp":"2026-04-25T19:58:55.968Z"}

data: {"data":"\rLoading weights:  58%|█████▊    | 196/339 [00:04<00:03, 46.17it/s]\u001b[A","timestamp":"2026-04-25T19:58:56.959Z"}

data: {"data":"\rLoading weights:  72%|███████▏  | 245/339 [00:05<00:01, 47.14it/s]\u001b[A","timestamp":"2026-04-25T19:58:58.049Z"}

data: {"data":"\rLoading weights:  86%|████████▋ | 293/339 [00:06<00:00, 46.05it/s]\u001b[A\rLoading weights: 100%|██████████| 339/339 [00:07<00:00, 47.02it/s]","timestamp":"2026-04-25T19:58:58.861Z"}

data: {"data":"","timestamp":"2026-04-25T19:58:58.981Z"}

data: {"data":"\rgeneration_config.json:   0%|          | 0.00/243 [00:00<?, ?B/s]\u001b[A\rgeneration_config.json: 100%|██████████| 243/243 [00:00<00:00, 1.86MB/s]","timestamp":"2026-04-25T19:58:58.982Z"}

data: {"data":"","timestamp":"2026-04-25T19:58:59.019Z"}

data: {"data":"\rREADME.md:   0%|          | 0.00/748 [00:00<?, ?B/s]\u001b[A\rREADME.md: 100%|██████████| 748/748 [00:00<00:00, 6.16MB/s]","timestamp":"2026-04-25T19:58:59.019Z"}

data: {"data":"","timestamp":"2026-04-25T19:58:59.236Z"}

data: {"data":"\rdata/train-00000-of-00001.parquet:   0%|          | 0.00/30.6M [00:00<?, ?B/s]\u001b[A\rdata/train-00000-of-00001.parquet: 100%|██████████| 30.6M/30.6M [00:00<00:00, 146MB/s]","timestamp":"2026-04-25T19:58:59.446Z"}

data: {"data":"","timestamp":"2026-04-25T19:58:59.460Z"}

data: {"data":"\rdata/validation-00000-of-00001.parquet:   0%|          | 0.00/648k [00:00<?, ?B/s]\u001b[A\rdata/validation-00000-of-00001.parquet: 100%|██████████| 648k/648k [00:00<00:00, 3.09MB/s]","timestamp":"2026-04-25T19:58:59.670Z"}

data: {"data":"","timestamp":"2026-04-25T19:58:59.671Z"}

data: {"data":"\rGenerating train split:   0%|          | 0/1335 [00:00<?, ? examples/s]\u001b[A\rGenerating train split: 100%|██████████| 1335/1335 [00:00<00:00, 19246.80 examples/s]","timestamp":"2026-04-25T19:58:59.741Z"}

data: {"data":"","timestamp":"2026-04-25T19:58:59.741Z"}

data: {"data":"\rGenerating validation split:   0%|          | 0/28 [00:00<?, ? examples/s]\u001b[A\rGenerating validation split: 100%|██████████| 28/28 [00:00<00:00, 8099.90 examples/s]","timestamp":"2026-04-25T19:58:59.745Z"}

data: {"data":"","timestamp":"2026-04-25T19:58:59.834Z"}

data: {"data":"\rtokenizer_config.json:   0%|          | 0.00/7.30k [00:00<?, ?B/s]\u001b[A\rtokenizer_config.json: 100%|██████████| 7.30k/7.30k [00:00<00:00, 43.5MB/s]","timestamp":"2026-04-25T19:58:59.835Z"}

data: {"data":"","timestamp":"2026-04-25T19:58:59.958Z"}

data: {"data":"\rvocab.json:   0%|          | 0.00/2.78M [00:00<?, ?B/s]\u001b[A\rvocab.json: 100%|██████████| 2.78M/2.78M [00:00<00:00, 52.1MB/s]","timestamp":"2026-04-25T19:59:00.011Z"}

data: {"data":"","timestamp":"2026-04-25T19:59:00.050Z"}

data: {"data":"\rmerges.txt:   0%|          | 0.00/1.67M [00:00<?, ?B/s]\u001b[A\rmerges.txt: 100%|██████████| 1.67M/1.67M [00:00<00:00, 26.5MB/s]","timestamp":"2026-04-25T19:59:00.113Z"}

data: {"data":"","timestamp":"2026-04-25T19:59:00.143Z"}

data: {"data":"\rtokenizer.json:   0%|          | 0.00/7.03M [00:00<?, ?B/s]\u001b[A\rtokenizer.json: 100%|██████████| 7.03M/7.03M [00:00<00:00, 48.2MB/s]","timestamp":"2026-04-25T19:59:00.289Z"}

data: {"data":"","timestamp":"2026-04-25T19:59:02.610Z"}

data: {"data":"\rTokenizing train dataset:   0%|          | 0/1335 [00:00<?, ? examples/s]\u001b[A","timestamp":"2026-04-25T19:59:03.622Z"}

data: {"data":"\rTokenizing train dataset:   7%|▋         | 97/1335 [00:01<00:12, 95.94 examples/s]\u001b[A","timestamp":"2026-04-25T19:59:04.691Z"}

data: {"data":"\rTokenizing train dataset:  14%|█▍        | 193/1335 [00:02<00:12, 92.21 examples/s]\u001b[A","timestamp":"2026-04-25T19:59:05.736Z"}

data: {"data":"\rTokenizing train dataset:  22%|██▏       | 295/1335 [00:03<00:10, 94.69 examples/s]\u001b[A","timestamp":"2026-04-25T19:59:06.882Z"}

data: {"data":"\rTokenizing train dataset:  29%|██▉       | 393/1335 [00:04<00:10, 90.85 examples/s]\u001b[A","timestamp":"2026-04-25T19:59:07.936Z"}

data: {"data":"\rTokenizing train dataset:  37%|███▋      | 488/1335 [00:05<00:09, 90.61 examples/s]\u001b[A","timestamp":"2026-04-25T19:59:09.052Z"}

data: {"data":"\rTokenizing train dataset:  44%|████▎     | 583/1335 [00:06<00:08, 88.70 examples/s]\u001b[A","timestamp":"2026-04-25T19:59:10.097Z"}

data: {"data":"\rTokenizing train dataset:  51%|█████     | 677/1335 [00:07<00:07, 89.09 examples/s]\u001b[A","timestamp":"2026-04-25T19:59:11.200Z"}

data: {"data":"\rTokenizing train dataset:  58%|█████▊    | 768/1335 [00:08<00:06, 86.97 examples/s]\u001b[A","timestamp":"2026-04-25T19:59:12.277Z"}

data: {"data":"\rTokenizing train dataset:  64%|██████▍   | 859/1335 [00:09<00:05, 86.20 examples/s]\u001b[A","timestamp":"2026-04-25T19:59:13.350Z"}

data: {"data":"\rTokenizing train dataset:  71%|███████   | 950/1335 [00:10<00:04, 85.87 examples/s]\u001b[A","timestamp":"2026-04-25T19:59:16.265Z"}

data: {"data":"\rTokenizing train dataset:  78%|███████▊  | 1038/1335 [00:13<00:05, 55.53 examples/s]\u001b[A","timestamp":"2026-04-25T19:59:17.300Z"}

data: {"data":"\rTokenizing train dataset:  84%|████████▎ | 1116/1335 [00:14<00:03, 59.82 examples/s]\u001b[A","timestamp":"2026-04-25T19:59:18.349Z"}

data: {"data":"\rTokenizing train dataset:  90%|█████████ | 1204/1335 [00:15<00:01, 65.55 examples/s]\u001b[A","timestamp":"2026-04-25T19:59:19.385Z"}

data: {"data":"\rTokenizing train dataset:  96%|█████████▌| 1280/1335 [00:16<00:00, 67.52 examples/s]\u001b[A\rTokenizing train dataset: 100%|██████████| 1335/1335 [00:17<00:00, 75.99 examples/s]","timestamp":"2026-04-25T19:59:20.178Z"}

data: {"data":"[transformers] The tokenizer has new PAD/BOS/EOS tokens that differ from the model config and generation config. The model config and generation config were aligned accordingly, being updated with the tokenizer's values. Updated tokens: {'bos_token_id': None, 'pad_token_id': 151643}.","timestamp":"2026-04-25T19:59:40.471Z"}

data: {"data":"","timestamp":"2026-04-25T19:59:40.744Z"}

data: {"data":"\r  0%|          | 0/501 [00:00<?, ?it/s]\u001b[A","timestamp":"2026-04-25T19:59:43.620Z"}

data: {"data":"\r  0%|          | 1/501 [00:02<23:57,  2.88s/it]\u001b[A","timestamp":"2026-04-25T19:59:45.658Z"}

data: {"data":"\r  0%|          | 2/501 [00:04<19:49,  2.38s/it]\u001b[A","timestamp":"2026-04-25T19:59:47.698Z"}

data: {"data":"\r  1%|          | 3/501 [00:06<18:28,  2.23s/it]\u001b[A","timestamp":"2026-04-25T19:59:49.742Z"}

data: {"data":"\r  1%|          | 4/501 [00:08<17:50,  2.15s/it]\u001b[A","timestamp":"2026-04-25T19:59:51.788Z"}

data: {"data":"\r  1%|          | 5/501 [00:11<17:29,  2.12s/it]\u001b[A","timestamp":"2026-04-25T19:59:53.829Z"}

data: {"data":"\r  1%|          | 6/501 [00:13<17:14,  2.09s/it]\u001b[A","timestamp":"2026-04-25T19:59:56.084Z"}

data: {"data":"\r  1%|▏         | 7/501 [00:15<17:39,  2.14s/it]\u001b[A","timestamp":"2026-04-25T19:59:58.138Z"}

data: {"data":"\r  2%|▏         | 8/501 [00:17<17:22,  2.12s/it]\u001b[A","timestamp":"2026-04-25T20:00:00.181Z"}

data: {"data":"\r  2%|▏         | 9/501 [00:19<17:09,  2.09s/it]\u001b[A","timestamp":"2026-04-25T20:00:02.423Z"}

data: {"data":"\r  2%|▏         | 10/501 [00:21<17:30,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:00:02.423Z"}

data: {"data":"\r                                                \r\u001b[A","timestamp":"2026-04-25T20:00:02.423Z"}

data: {"data":"{'loss': '2.016', 'grad_norm': '0.934', 'learning_rate': '1.964e-05', 'entropy': '1.002', 'num_tokens': '8.094e+04', 'mean_token_accuracy': '0.6603', 'epoch': '0.05988'}","timestamp":"2026-04-25T20:00:02.423Z"}

data: {"data":"\r  2%|▏         | 10/501 [00:21<17:30,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:00:04.669Z"}

data: {"data":"\r  2%|▏         | 11/501 [00:23<17:44,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:00:06.720Z"}

data: {"data":"\r  2%|▏         | 12/501 [00:25<17:24,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:00:08.769Z"}

data: {"data":"\r  3%|▎         | 13/501 [00:28<17:09,  2.11s/it]\u001b[A","timestamp":"2026-04-25T20:00:11.025Z"}

data: {"data":"\r  3%|▎         | 14/501 [00:30<17:28,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:00:13.075Z"}

data: {"data":"\r  3%|▎         | 15/501 [00:32<17:11,  2.12s/it]\u001b[A","timestamp":"2026-04-25T20:00:15.325Z"}

data: {"data":"\r  3%|▎         | 16/501 [00:34<17:27,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:00:17.373Z"}

data: {"data":"\r  3%|▎         | 17/501 [00:36<17:09,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:00:19.627Z"}

data: {"data":"\r  4%|▎         | 18/501 [00:38<17:25,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:00:21.672Z"}

data: {"data":"\r  4%|▍         | 19/501 [00:40<17:06,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:00:23.930Z"}

data: {"data":"\r  4%|▍         | 20/501 [00:43<17:22,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:00:23.930Z"}

data: {"data":"\r                                                \r\u001b[A","timestamp":"2026-04-25T20:00:23.930Z"}

data: {"data":"{'loss': '1.94', 'grad_norm': '0.9047', 'learning_rate': '1.924e-05', 'entropy': '1.054', 'num_tokens': '1.611e+05', 'mean_token_accuracy': '0.6627', 'epoch': '0.1198'}","timestamp":"2026-04-25T20:00:23.930Z"}

data: {"data":"\r  4%|▍         | 20/501 [00:43<17:22,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:00:25.983Z"}

data: {"data":"\r  4%|▍         | 21/501 [00:45<17:03,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:00:28.035Z"}

data: {"data":"\r  4%|▍         | 22/501 [00:47<16:50,  2.11s/it]\u001b[A","timestamp":"2026-04-25T20:00:30.282Z"}

data: {"data":"\r  5%|▍         | 23/501 [00:49<17:07,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:00:32.541Z"}

data: {"data":"\r  5%|▍         | 24/501 [00:51<17:21,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:00:34.797Z"}

data: {"data":"\r  5%|▍         | 25/501 [00:54<17:29,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:00:37.050Z"}

data: {"data":"\r  5%|▌         | 26/501 [00:56<17:34,  2.22s/it]\u001b[A","timestamp":"2026-04-25T20:00:39.306Z"}

data: {"data":"\r  5%|▌         | 27/501 [00:58<17:37,  2.23s/it]\u001b[A","timestamp":"2026-04-25T20:00:41.564Z"}

data: {"data":"\r  6%|▌         | 28/501 [01:00<17:38,  2.24s/it]\u001b[A","timestamp":"2026-04-25T20:00:43.615Z"}

data: {"data":"\r  6%|▌         | 29/501 [01:02<17:10,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:00:45.873Z"}

data: {"data":"\r  6%|▌         | 30/501 [01:05<17:18,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:00:45.873Z"}

data: {"data":"\r                                                \r\u001b[A","timestamp":"2026-04-25T20:00:45.873Z"}

data: {"data":"{'loss': '1.85', 'grad_norm': '0.7995', 'learning_rate': '1.884e-05', 'entropy': '1.125', 'num_tokens': '2.41e+05', 'mean_token_accuracy': '0.6653', 'epoch': '0.1796'}","timestamp":"2026-04-25T20:00:45.873Z"}

data: {"data":"\r  6%|▌         | 30/501 [01:05<17:18,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:00:48.129Z"}

data: {"data":"\r  6%|▌         | 31/501 [01:07<17:23,  2.22s/it]\u001b[A","timestamp":"2026-04-25T20:00:50.388Z"}

data: {"data":"\r  6%|▋         | 32/501 [01:09<17:26,  2.23s/it]\u001b[A","timestamp":"2026-04-25T20:00:52.450Z"}

data: {"data":"\r  7%|▋         | 33/501 [01:11<17:00,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:00:54.504Z"}

data: {"data":"\r  7%|▋         | 34/501 [01:13<16:40,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:00:56.559Z"}

data: {"data":"\r  7%|▋         | 35/501 [01:15<16:26,  2.12s/it]\u001b[A","timestamp":"2026-04-25T20:00:58.823Z"}

data: {"data":"\r  7%|▋         | 36/501 [01:18<16:44,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:01:01.086Z"}

data: {"data":"\r  7%|▋         | 37/501 [01:20<16:56,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:01:03.357Z"}

data: {"data":"\r  8%|▊         | 38/501 [01:22<17:05,  2.22s/it]\u001b[A","timestamp":"2026-04-25T20:01:05.412Z"}

data: {"data":"\r  8%|▊         | 39/501 [01:24<16:41,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:01:07.670Z"}

data: {"data":"{'loss': '1.787', 'grad_norm': '0.5725', 'learning_rate': '1.844e-05', 'entropy': '1.236', 'num_tokens': '3.214e+05', 'mean_token_accuracy': '0.6671', 'epoch': '0.2395'}","timestamp":"2026-04-25T20:01:07.670Z"}

data: {"data":"\r  8%|▊         | 40/501 [01:26<16:51,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:01:07.670Z"}

data: {"data":"\r                                                \r\u001b[A","timestamp":"2026-04-25T20:01:07.670Z"}

data: {"data":"\r  8%|▊         | 40/501 [01:26<16:51,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:01:09.931Z"}

data: {"data":"\r  8%|▊         | 41/501 [01:29<16:58,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:01:12.203Z"}

data: {"data":"\r  8%|▊         | 42/501 [01:31<17:04,  2.23s/it]\u001b[A","timestamp":"2026-04-25T20:01:14.477Z"}

data: {"data":"\r  9%|▊         | 43/501 [01:33<17:07,  2.24s/it]\u001b[A","timestamp":"2026-04-25T20:01:16.751Z"}

data: {"data":"\r  9%|▉         | 44/501 [01:36<17:09,  2.25s/it]\u001b[A","timestamp":"2026-04-25T20:01:18.815Z"}

data: {"data":"\r  9%|▉         | 45/501 [01:38<16:41,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:01:21.087Z"}

data: {"data":"\r  9%|▉         | 46/501 [01:40<16:49,  2.22s/it]\u001b[A","timestamp":"2026-04-25T20:01:23.143Z"}

data: {"data":"\r  9%|▉         | 47/501 [01:42<16:25,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:01:25.408Z"}

data: {"data":"\r 10%|▉         | 48/501 [01:44<16:36,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:01:27.467Z"}

data: {"data":"\r 10%|▉         | 49/501 [01:46<16:14,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:01:29.532Z"}

data: {"data":"\r 10%|▉         | 50/501 [01:48<16:00,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:01:29.533Z"}

data: {"data":"\r                                                \r\u001b[A","timestamp":"2026-04-25T20:01:29.533Z"}

data: {"data":"{'loss': '1.71', 'grad_norm': '0.4529', 'learning_rate': '1.804e-05', 'entropy': '1.288', 'num_tokens': '4.017e+05', 'mean_token_accuracy': '0.6737', 'epoch': '0.2994'}","timestamp":"2026-04-25T20:01:29.533Z"}

data: {"data":"\r 10%|▉         | 50/501 [01:48<16:00,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:01:31.594Z"}

data: {"data":"\r 10%|█         | 51/501 [01:50<15:49,  2.11s/it]\u001b[A","timestamp":"2026-04-25T20:01:33.856Z"}

data: {"data":"\r 10%|█         | 52/501 [01:53<16:07,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:01:35.923Z"}

data: {"data":"\r 11%|█         | 53/501 [01:55<15:53,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:01:38.180Z"}

data: {"data":"\r 11%|█         | 54/501 [01:57<16:08,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:01:40.440Z"}

data: {"data":"\r 11%|█         | 55/501 [01:59<16:18,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:01:42.519Z"}

data: {"data":"\r 11%|█         | 56/501 [02:01<16:01,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:01:44.584Z"}

data: {"data":"\r 11%|█▏        | 57/501 [02:03<15:46,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:01:46.852Z"}

data: {"data":"\r 12%|█▏        | 58/501 [02:06<16:02,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:01:48.922Z"}

data: {"data":"\r 12%|█▏        | 59/501 [02:08<15:46,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:01:50.980Z"}

data: {"data":"\r 12%|█▏        | 60/501 [02:10<15:33,  2.12s/it]\u001b[A","timestamp":"2026-04-25T20:01:50.981Z"}

data: {"data":"\r                                                \r\u001b[A","timestamp":"2026-04-25T20:01:50.981Z"}

data: {"data":"{'loss': '1.671', 'grad_norm': '0.4426', 'learning_rate': '1.764e-05', 'entropy': '1.369', 'num_tokens': '4.81e+05', 'mean_token_accuracy': '0.6733', 'epoch': '0.3593'}","timestamp":"2026-04-25T20:01:50.981Z"}

data: {"data":"\r 12%|█▏        | 60/501 [02:10<15:33,  2.12s/it]\u001b[A","timestamp":"2026-04-25T20:01:53.242Z"}

data: {"data":"\r 12%|█▏        | 61/501 [02:12<15:50,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:01:55.296Z"}

data: {"data":"\r 12%|█▏        | 62/501 [02:14<15:34,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:01:57.563Z"}

data: {"data":"\r 13%|█▎        | 63/501 [02:16<15:50,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:01:59.836Z"}

data: {"data":"\r 13%|█▎        | 64/501 [02:19<16:01,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:02:02.104Z"}

data: {"data":"\r 13%|█▎        | 65/501 [02:21<16:08,  2.22s/it]\u001b[A","timestamp":"2026-04-25T20:02:04.167Z"}

data: {"data":"\r 13%|█▎        | 66/501 [02:23<15:45,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:02:06.225Z"}

data: {"data":"\r 13%|█▎        | 67/501 [02:25<15:28,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:02:08.503Z"}

data: {"data":"\r 14%|█▎        | 68/501 [02:27<15:44,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:02:10.563Z"}

data: {"data":"\r 14%|█▍        | 69/501 [02:29<15:26,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:02:12.626Z"}

data: {"data":"\r 14%|█▍        | 70/501 [02:31<15:13,  2.12s/it]\u001b[A","timestamp":"2026-04-25T20:02:12.626Z"}

data: {"data":"\r                                                \r\u001b[A","timestamp":"2026-04-25T20:02:12.626Z"}

data: {"data":"{'loss': '1.621', 'grad_norm': '0.4408', 'learning_rate': '1.725e-05', 'entropy': '1.402', 'num_tokens': '5.606e+05', 'mean_token_accuracy': '0.6754', 'epoch': '0.4192'}","timestamp":"2026-04-25T20:02:12.626Z"}

data: {"data":"\r 14%|█▍        | 70/501 [02:31<15:13,  2.12s/it]\u001b[A","timestamp":"2026-04-25T20:02:14.889Z"}

data: {"data":"\r 14%|█▍        | 71/501 [02:34<15:30,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:02:17.158Z"}

data: {"data":"\r 14%|█▍        | 72/501 [02:36<15:41,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:02:19.431Z"}

data: {"data":"\r 15%|█▍        | 73/501 [02:38<15:49,  2.22s/it]\u001b[A","timestamp":"2026-04-25T20:02:21.495Z"}

data: {"data":"\r 15%|█▍        | 74/501 [02:40<15:27,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:02:23.556Z"}

data: {"data":"\r 15%|█▍        | 75/501 [02:42<15:11,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:02:25.825Z"}

data: {"data":"\r 15%|█▌        | 76/501 [02:45<15:25,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:02:28.100Z"}

data: {"data":"\r 15%|█▌        | 77/501 [02:47<15:35,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:02:30.362Z"}

data: {"data":"\r 16%|█▌        | 78/501 [02:49<15:40,  2.22s/it]\u001b[A","timestamp":"2026-04-25T20:02:32.629Z"}

data: {"data":"\r 16%|█▌        | 79/501 [02:51<15:43,  2.24s/it]\u001b[A","timestamp":"2026-04-25T20:02:34.697Z"}

data: {"data":"\r 16%|█▌        | 80/501 [02:53<15:20,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:02:34.698Z"}

data: {"data":"{'loss': '1.576', 'grad_norm': '0.3904', 'learning_rate': '1.685e-05', 'entropy': '1.434', 'num_tokens': '6.407e+05', 'mean_token_accuracy': '0.6783', 'epoch': '0.479'}","timestamp":"2026-04-25T20:02:34.698Z"}

data: {"data":"\r                                                \r\u001b[A","timestamp":"2026-04-25T20:02:34.698Z"}

data: {"data":"\r 16%|█▌        | 80/501 [02:53<15:20,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:02:36.960Z"}

data: {"data":"\r 16%|█▌        | 81/501 [02:56<15:27,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:02:39.222Z"}

data: {"data":"\r 16%|█▋        | 82/501 [02:58<15:32,  2.23s/it]\u001b[A","timestamp":"2026-04-25T20:02:41.484Z"}

data: {"data":"\r 17%|█▋        | 83/501 [03:00<15:34,  2.24s/it]\u001b[A","timestamp":"2026-04-25T20:02:43.748Z"}

data: {"data":"\r 17%|█▋        | 84/501 [03:03<15:35,  2.24s/it]\u001b[A","timestamp":"2026-04-25T20:02:45.803Z"}

data: {"data":"\r 17%|█▋        | 85/501 [03:05<15:10,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:02:48.061Z"}

data: {"data":"\r 17%|█▋        | 86/501 [03:07<15:16,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:02:50.120Z"}

data: {"data":"\r 17%|█▋        | 87/501 [03:09<14:55,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:02:52.397Z"}

data: {"data":"\r 18%|█▊        | 88/501 [03:11<15:07,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:02:54.452Z"}

data: {"data":"\r 18%|█▊        | 89/501 [03:13<14:47,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:02:56.713Z"}

data: {"data":"\r 18%|█▊        | 90/501 [03:15<14:58,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:02:56.714Z"}

data: {"data":"{'loss': '1.54', 'grad_norm': '0.4359', 'learning_rate': '1.645e-05', 'entropy': '1.451', 'num_tokens': '7.193e+05', 'mean_token_accuracy': '0.6835', 'epoch': '0.5389'}","timestamp":"2026-04-25T20:02:56.714Z"}

data: {"data":"\r                                                \r\u001b[A","timestamp":"2026-04-25T20:02:56.714Z"}

data: {"data":"\r 18%|█▊        | 90/501 [03:15<14:58,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:02:58.987Z"}

data: {"data":"\r 18%|█▊        | 91/501 [03:18<15:07,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:03:01.050Z"}

data: {"data":"\r 18%|█▊        | 92/501 [03:20<14:46,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:03:03.118Z"}

data: {"data":"\r 19%|█▊        | 93/501 [03:22<14:32,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:03:05.189Z"}

data: {"data":"\r 19%|█▉        | 94/501 [03:24<14:22,  2.12s/it]\u001b[A","timestamp":"2026-04-25T20:03:07.261Z"}

data: {"data":"\r 19%|█▉        | 95/501 [03:26<14:14,  2.10s/it]\u001b[A","timestamp":"2026-04-25T20:03:09.323Z"}

data: {"data":"\r 19%|█▉        | 96/501 [03:28<14:07,  2.09s/it]\u001b[A","timestamp":"2026-04-25T20:03:11.383Z"}

data: {"data":"\r 19%|█▉        | 97/501 [03:30<14:01,  2.08s/it]\u001b[A","timestamp":"2026-04-25T20:03:13.648Z"}

data: {"data":"\r 20%|█▉        | 98/501 [03:32<14:21,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:03:15.707Z"}

data: {"data":"\r 20%|█▉        | 99/501 [03:34<14:09,  2.11s/it]\u001b[A","timestamp":"2026-04-25T20:03:17.779Z"}

data: {"data":"\r 20%|█▉        | 100/501 [03:37<14:02,  2.10s/it]\u001b[A","timestamp":"2026-04-25T20:03:17.779Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:03:17.779Z"}

data: {"data":"{'loss': '1.461', 'grad_norm': '0.4393', 'learning_rate': '1.605e-05', 'entropy': '1.456', 'num_tokens': '7.998e+05', 'mean_token_accuracy': '0.6981', 'epoch': '0.5988'}","timestamp":"2026-04-25T20:03:17.779Z"}

data: {"data":"\r 20%|█▉        | 100/501 [03:37<14:02,  2.10s/it]\u001b[A","timestamp":"2026-04-25T20:03:19.846Z"}

data: {"data":"\r 20%|██        | 101/501 [03:39<13:56,  2.09s/it]\u001b[A","timestamp":"2026-04-25T20:03:22.109Z"}

data: {"data":"\r 20%|██        | 102/501 [03:41<14:14,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:03:24.372Z"}

data: {"data":"\r 21%|██        | 103/501 [03:43<14:27,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:03:26.434Z"}

data: {"data":"\r 21%|██        | 104/501 [03:45<14:11,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:03:28.693Z"}

data: {"data":"\r 21%|██        | 105/501 [03:47<14:22,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:03:30.957Z"}

data: {"data":"\r 21%|██        | 106/501 [03:50<14:30,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:03:33.012Z"}

data: {"data":"\r 21%|██▏       | 107/501 [03:52<14:10,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:03:35.291Z"}

data: {"data":"\r 22%|██▏       | 108/501 [03:54<14:22,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:03:37.354Z"}

data: {"data":"\r 22%|██▏       | 109/501 [03:56<14:04,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:03:39.421Z"}

data: {"data":"\r 22%|██▏       | 110/501 [03:58<13:52,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:03:39.421Z"}

data: {"data":"{'loss': '1.413', 'grad_norm': '0.503', 'learning_rate': '1.565e-05', 'entropy': '1.44', 'num_tokens': '8.798e+05', 'mean_token_accuracy': '0.7075', 'epoch': '0.6587'}","timestamp":"2026-04-25T20:03:39.421Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:03:39.421Z"}

data: {"data":"\r 22%|██▏       | 110/501 [03:58<13:52,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:03:41.689Z"}

data: {"data":"\r 22%|██▏       | 111/501 [04:00<14:06,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:03:43.958Z"}

data: {"data":"\r 22%|██▏       | 112/501 [04:03<14:15,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:03:46.023Z"}

data: {"data":"\r 23%|██▎       | 113/501 [04:05<13:57,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:03:48.092Z"}

data: {"data":"\r 23%|██▎       | 114/501 [04:07<13:45,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:03:50.366Z"}

data: {"data":"\r 23%|██▎       | 115/501 [04:09<13:59,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:03:52.638Z"}

data: {"data":"\r 23%|██▎       | 116/501 [04:11<14:08,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:03:54.907Z"}

data: {"data":"\r 23%|██▎       | 117/501 [04:14<14:13,  2.22s/it]\u001b[A","timestamp":"2026-04-25T20:03:57.174Z"}

data: {"data":"\r 24%|██▎       | 118/501 [04:16<14:16,  2.24s/it]\u001b[A","timestamp":"2026-04-25T20:03:59.238Z"}

data: {"data":"\r 24%|██▍       | 119/501 [04:18<13:54,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:04:01.295Z"}

data: {"data":"\r 24%|██▍       | 120/501 [04:20<13:37,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:04:01.296Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:04:01.296Z"}

data: {"data":"{'loss': '1.351', 'grad_norm': '0.6165', 'learning_rate': '1.525e-05', 'entropy': '1.411', 'num_tokens': '9.6e+05', 'mean_token_accuracy': '0.7185', 'epoch': '0.7186'}","timestamp":"2026-04-25T20:04:01.296Z"}

data: {"data":"\r 24%|██▍       | 120/501 [04:20<13:37,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:04:03.562Z"}

data: {"data":"\r 24%|██▍       | 121/501 [04:22<13:49,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:04:05.626Z"}

data: {"data":"\r 24%|██▍       | 122/501 [04:24<13:33,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:04:07.697Z"}

data: {"data":"\r 25%|██▍       | 123/501 [04:26<13:23,  2.12s/it]\u001b[A","timestamp":"2026-04-25T20:04:09.964Z"}

data: {"data":"\r 25%|██▍       | 124/501 [04:29<13:37,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:04:12.232Z"}

data: {"data":"\r 25%|██▍       | 125/501 [04:31<13:46,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:04:14.500Z"}

data: {"data":"\r 25%|██▌       | 126/501 [04:33<13:51,  2.22s/it]\u001b[A","timestamp":"2026-04-25T20:04:16.773Z"}

data: {"data":"\r 25%|██▌       | 127/501 [04:36<13:55,  2.23s/it]\u001b[A","timestamp":"2026-04-25T20:04:19.045Z"}

data: {"data":"\r 26%|██▌       | 128/501 [04:38<13:57,  2.25s/it]\u001b[A","timestamp":"2026-04-25T20:04:21.317Z"}

data: {"data":"\r 26%|██▌       | 129/501 [04:40<13:58,  2.25s/it]\u001b[A","timestamp":"2026-04-25T20:04:23.387Z"}

data: {"data":"\r 26%|██▌       | 130/501 [04:42<13:35,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:04:23.387Z"}

data: {"data":"{'loss': '1.286', 'grad_norm': '0.6028', 'learning_rate': '1.485e-05', 'entropy': '1.34', 'num_tokens': '1.039e+06', 'mean_token_accuracy': '0.7231', 'epoch': '0.7784'}","timestamp":"2026-04-25T20:04:23.387Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:04:23.387Z"}

data: {"data":"\r 26%|██▌       | 130/501 [04:42<13:35,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:04:25.442Z"}

data: {"data":"\r 26%|██▌       | 131/501 [04:44<13:17,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:04:27.707Z"}

data: {"data":"\r 26%|██▋       | 132/501 [04:46<13:27,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:04:29.979Z"}

data: {"data":"\r 27%|██▋       | 133/501 [04:49<13:34,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:04:32.049Z"}

data: {"data":"\r 27%|██▋       | 134/501 [04:51<13:16,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:04:34.120Z"}

data: {"data":"\r 27%|██▋       | 135/501 [04:53<13:03,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:04:36.398Z"}

data: {"data":"\r 27%|██▋       | 136/501 [04:55<13:16,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:04:38.468Z"}

data: {"data":"\r 27%|██▋       | 137/501 [04:57<13:01,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:04:40.536Z"}

data: {"data":"\r 28%|██▊       | 138/501 [04:59<12:51,  2.12s/it]\u001b[A","timestamp":"2026-04-25T20:04:42.589Z"}

data: {"data":"\r 28%|██▊       | 139/501 [05:01<12:41,  2.10s/it]\u001b[A","timestamp":"2026-04-25T20:04:44.855Z"}

data: {"data":"\r 28%|██▊       | 140/501 [05:04<12:56,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:04:44.855Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:04:44.855Z"}

data: {"data":"{'loss': '1.206', 'grad_norm': '0.7572', 'learning_rate': '1.445e-05', 'entropy': '1.26', 'num_tokens': '1.119e+06', 'mean_token_accuracy': '0.73', 'epoch': '0.8383'}","timestamp":"2026-04-25T20:04:44.855Z"}

data: {"data":"\r 28%|██▊       | 140/501 [05:04<12:56,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:04:47.115Z"}

data: {"data":"\r 28%|██▊       | 141/501 [05:06<13:06,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:04:49.390Z"}

data: {"data":"\r 28%|██▊       | 142/501 [05:08<13:13,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:04:51.457Z"}

data: {"data":"\r 29%|██▊       | 143/501 [05:10<12:56,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:04:53.519Z"}

data: {"data":"\r 29%|██▊       | 144/501 [05:12<12:42,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:04:55.795Z"}

data: {"data":"\r 29%|██▉       | 145/501 [05:15<12:55,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:04:58.075Z"}

data: {"data":"\r 29%|██▉       | 146/501 [05:17<13:04,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:05:00.131Z"}

data: {"data":"\r 29%|██▉       | 147/501 [05:19<12:45,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:05:02.195Z"}

data: {"data":"\r 30%|██▉       | 148/501 [05:21<12:33,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:05:04.255Z"}

data: {"data":"\r 30%|██▉       | 149/501 [05:23<12:23,  2.11s/it]\u001b[A","timestamp":"2026-04-25T20:05:06.322Z"}

data: {"data":"\r 30%|██▉       | 150/501 [05:25<12:16,  2.10s/it]\u001b[A","timestamp":"2026-04-25T20:05:06.323Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:05:06.323Z"}

data: {"data":"{'loss': '1.088', 'grad_norm': '0.724', 'learning_rate': '1.405e-05', 'entropy': '1.175', 'num_tokens': '1.199e+06', 'mean_token_accuracy': '0.7461', 'epoch': '0.8982'}","timestamp":"2026-04-25T20:05:06.323Z"}

data: {"data":"\r 30%|██▉       | 150/501 [05:25<12:16,  2.10s/it]\u001b[A","timestamp":"2026-04-25T20:05:08.387Z"}

data: {"data":"\r 30%|███       | 151/501 [05:27<12:10,  2.09s/it]\u001b[A","timestamp":"2026-04-25T20:05:10.652Z"}

data: {"data":"\r 30%|███       | 152/501 [05:29<12:27,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:05:12.709Z"}

data: {"data":"\r 31%|███       | 153/501 [05:31<12:16,  2.12s/it]\u001b[A","timestamp":"2026-04-25T20:05:14.968Z"}

data: {"data":"\r 31%|███       | 154/501 [05:34<12:29,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:05:17.031Z"}

data: {"data":"\r 31%|███       | 155/501 [05:36<12:17,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:05:19.300Z"}

data: {"data":"\r 31%|███       | 156/501 [05:38<12:29,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:05:21.360Z"}

data: {"data":"\r 31%|███▏      | 157/501 [05:40<12:15,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:05:23.413Z"}

data: {"data":"\r 32%|███▏      | 158/501 [05:42<12:04,  2.11s/it]\u001b[A","timestamp":"2026-04-25T20:05:25.681Z"}

data: {"data":"\r 32%|███▏      | 159/501 [05:44<12:18,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:05:27.941Z"}

data: {"data":"\r 32%|███▏      | 160/501 [05:47<12:26,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:05:27.941Z"}

data: {"data":"{'loss': '0.9598', 'grad_norm': '1.037', 'learning_rate': '1.365e-05', 'entropy': '1.044', 'num_tokens': '1.28e+06', 'mean_token_accuracy': '0.7734', 'epoch': '0.9581'}","timestamp":"2026-04-25T20:05:27.941Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:05:27.941Z"}

data: {"data":"\r 32%|███▏      | 160/501 [05:47<12:26,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:05:30.214Z"}

data: {"data":"\r 32%|███▏      | 161/501 [05:49<12:32,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:05:32.279Z"}

data: {"data":"\r 32%|███▏      | 162/501 [05:51<12:15,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:05:34.338Z"}

data: {"data":"\r 33%|███▎      | 163/501 [05:53<12:02,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:05:36.602Z"}

data: {"data":"\r 33%|███▎      | 164/501 [05:55<12:12,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:05:38.869Z"}

data: {"data":"\r 33%|███▎      | 165/501 [05:58<12:20,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:05:40.927Z"}

data: {"data":"\r 33%|███▎      | 166/501 [06:00<12:03,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:05:42.727Z"}

data: {"data":"\r 33%|███▎      | 167/501 [06:01<11:25,  2.05s/it]\u001b[A","timestamp":"2026-04-25T20:05:44.815Z"}

data: {"data":"\r 34%|███▎      | 168/501 [06:04<11:26,  2.06s/it]\u001b[A","timestamp":"2026-04-25T20:05:46.873Z"}

data: {"data":"\r 34%|███▎      | 169/501 [06:06<11:24,  2.06s/it]\u001b[A","timestamp":"2026-04-25T20:05:49.144Z"}

data: {"data":"\r 34%|███▍      | 170/501 [06:08<11:43,  2.12s/it]\u001b[A","timestamp":"2026-04-25T20:05:49.144Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:05:49.144Z"}

data: {"data":"{'loss': '0.8251', 'grad_norm': '0.9347', 'learning_rate': '1.325e-05', 'entropy': '0.9091', 'num_tokens': '1.36e+06', 'mean_token_accuracy': '0.8098', 'epoch': '1.018'}","timestamp":"2026-04-25T20:05:49.144Z"}

data: {"data":"\r 34%|███▍      | 170/501 [06:08<11:43,  2.12s/it]\u001b[A","timestamp":"2026-04-25T20:05:51.415Z"}

data: {"data":"\r 34%|███▍      | 171/501 [06:10<11:55,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:05:53.475Z"}

data: {"data":"\r 34%|███▍      | 172/501 [06:12<11:42,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:05:55.743Z"}

data: {"data":"\r 35%|███▍      | 173/501 [06:14<11:53,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:05:57.804Z"}

data: {"data":"\r 35%|███▍      | 174/501 [06:17<11:40,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:06:00.071Z"}

data: {"data":"\r 35%|███▍      | 175/501 [06:19<11:50,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:06:02.328Z"}

data: {"data":"\r 35%|███▌      | 176/501 [06:21<11:55,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:06:04.597Z"}

data: {"data":"\r 35%|███▌      | 177/501 [06:23<12:00,  2.22s/it]\u001b[A","timestamp":"2026-04-25T20:06:06.657Z"}

data: {"data":"\r 36%|███▌      | 178/501 [06:25<11:42,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:06:08.922Z"}

data: {"data":"\r 36%|███▌      | 179/501 [06:28<11:48,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:06:10.981Z"}

data: {"data":"{'loss': '0.7125', 'grad_norm': '0.9415', 'learning_rate': '1.285e-05', 'entropy': '0.7939', 'num_tokens': '1.44e+06', 'mean_token_accuracy': '0.8415', 'epoch': '1.078'}","timestamp":"2026-04-25T20:06:10.981Z"}

data: {"data":"\r 36%|███▌      | 180/501 [06:30<11:32,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:06:10.981Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:06:10.981Z"}

data: {"data":"\r 36%|███▌      | 180/501 [06:30<11:32,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:06:13.250Z"}

data: {"data":"\r 36%|███▌      | 181/501 [06:32<11:41,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:06:15.316Z"}

data: {"data":"\r 36%|███▋      | 182/501 [06:34<11:27,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:06:17.371Z"}

data: {"data":"\r 37%|███▋      | 183/501 [06:36<11:15,  2.12s/it]\u001b[A","timestamp":"2026-04-25T20:06:19.636Z"}

data: {"data":"\r 37%|███▋      | 184/501 [06:38<11:26,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:06:21.901Z"}

data: {"data":"\r 37%|███▋      | 185/501 [06:41<11:33,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:06:23.962Z"}

data: {"data":"\r 37%|███▋      | 186/501 [06:43<11:18,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:06:26.335Z"}

data: {"data":"\r 37%|███▋      | 187/501 [06:45<11:37,  2.22s/it]\u001b[A","timestamp":"2026-04-25T20:06:28.598Z"}

data: {"data":"\r 38%|███▊      | 188/501 [06:47<11:39,  2.23s/it]\u001b[A","timestamp":"2026-04-25T20:06:30.862Z"}

data: {"data":"\r 38%|███▊      | 189/501 [06:50<11:39,  2.24s/it]\u001b[A","timestamp":"2026-04-25T20:06:33.129Z"}

data: {"data":"\r 38%|███▊      | 190/501 [06:52<11:39,  2.25s/it]\u001b[A","timestamp":"2026-04-25T20:06:33.129Z"}

data: {"data":"{'loss': '0.5916', 'grad_norm': '0.7555', 'learning_rate': '1.246e-05', 'entropy': '0.6653', 'num_tokens': '1.52e+06', 'mean_token_accuracy': '0.8737', 'epoch': '1.138'}","timestamp":"2026-04-25T20:06:33.129Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:06:33.129Z"}

data: {"data":"\r 38%|███▊      | 190/501 [06:52<11:39,  2.25s/it]\u001b[A","timestamp":"2026-04-25T20:06:35.184Z"}

data: {"data":"\r 38%|███▊      | 191/501 [06:54<11:19,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:06:37.443Z"}

data: {"data":"\r 38%|███▊      | 192/501 [06:56<11:23,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:06:39.713Z"}

data: {"data":"\r 39%|███▊      | 193/501 [06:58<11:26,  2.23s/it]\u001b[A","timestamp":"2026-04-25T20:06:41.770Z"}

data: {"data":"\r 39%|███▊      | 194/501 [07:01<11:08,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:06:44.029Z"}

data: {"data":"\r 39%|███▉      | 195/501 [07:03<11:13,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:06:46.280Z"}

data: {"data":"\r 39%|███▉      | 196/501 [07:05<11:16,  2.22s/it]\u001b[A","timestamp":"2026-04-25T20:06:48.545Z"}

data: {"data":"\r 39%|███▉      | 197/501 [07:07<11:18,  2.23s/it]\u001b[A","timestamp":"2026-04-25T20:06:50.614Z"}

data: {"data":"\r 40%|███▉      | 198/501 [07:09<11:01,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:06:52.679Z"}

data: {"data":"\r 40%|███▉      | 199/501 [07:11<10:48,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:06:54.741Z"}

data: {"data":"\r 40%|███▉      | 200/501 [07:13<10:38,  2.12s/it]\u001b[A","timestamp":"2026-04-25T20:06:54.741Z"}

data: {"data":"{'loss': '0.5276', 'grad_norm': '0.7433', 'learning_rate': '1.206e-05', 'entropy': '0.5887', 'num_tokens': '1.6e+06', 'mean_token_accuracy': '0.888', 'epoch': '1.198'}","timestamp":"2026-04-25T20:06:54.741Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:06:54.741Z"}

data: {"data":"\r 40%|███▉      | 200/501 [07:13<10:38,  2.12s/it]\u001b[A","timestamp":"2026-04-25T20:06:57.007Z"}

data: {"data":"\r 40%|████      | 201/501 [07:16<10:49,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:06:59.284Z"}

data: {"data":"\r 40%|████      | 202/501 [07:18<10:57,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:07:01.346Z"}

data: {"data":"\r 41%|████      | 203/501 [07:20<10:43,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:07:03.403Z"}

data: {"data":"\r 41%|████      | 204/501 [07:22<10:31,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:07:05.675Z"}

data: {"data":"\r 41%|████      | 205/501 [07:24<10:42,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:07:07.742Z"}

data: {"data":"\r 41%|████      | 206/501 [07:26<10:31,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:07:10.007Z"}

data: {"data":"\r 41%|████▏     | 207/501 [07:29<10:40,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:07:12.274Z"}

data: {"data":"\r 42%|████▏     | 208/501 [07:31<10:45,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:07:14.333Z"}

data: {"data":"\r 42%|████▏     | 209/501 [07:33<10:30,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:07:16.600Z"}

data: {"data":"\r 42%|████▏     | 210/501 [07:35<10:38,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:07:16.600Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:07:16.600Z"}

data: {"data":"{'loss': '0.4512', 'grad_norm': '0.6285', 'learning_rate': '1.166e-05', 'entropy': '0.508', 'num_tokens': '1.68e+06', 'mean_token_accuracy': '0.904', 'epoch': '1.257'}","timestamp":"2026-04-25T20:07:16.600Z"}

data: {"data":"\r 42%|████▏     | 210/501 [07:35<10:38,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:07:18.662Z"}

data: {"data":"\r 42%|████▏     | 211/501 [07:37<10:24,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:07:20.917Z"}

data: {"data":"\r 42%|████▏     | 212/501 [07:40<10:31,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:07:23.193Z"}

data: {"data":"\r 43%|████▎     | 213/501 [07:42<10:36,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:07:25.459Z"}

data: {"data":"\r 43%|████▎     | 214/501 [07:44<10:39,  2.23s/it]\u001b[A","timestamp":"2026-04-25T20:07:27.720Z"}

data: {"data":"\r 43%|████▎     | 215/501 [07:46<10:39,  2.24s/it]\u001b[A","timestamp":"2026-04-25T20:07:29.989Z"}

data: {"data":"\r 43%|████▎     | 216/501 [07:49<10:40,  2.25s/it]\u001b[A","timestamp":"2026-04-25T20:07:32.049Z"}

data: {"data":"\r 43%|████▎     | 217/501 [07:51<10:22,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:07:34.115Z"}

data: {"data":"\r 44%|████▎     | 218/501 [07:53<10:09,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:07:36.166Z"}

data: {"data":"\r 44%|████▎     | 219/501 [07:55<09:58,  2.12s/it]\u001b[A","timestamp":"2026-04-25T20:07:38.429Z"}

data: {"data":"\r 44%|████▍     | 220/501 [07:57<10:08,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:07:38.429Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:07:38.429Z"}

data: {"data":"{'loss': '0.4343', 'grad_norm': '0.5901', 'learning_rate': '1.126e-05', 'entropy': '0.4829', 'num_tokens': '1.76e+06', 'mean_token_accuracy': '0.9058', 'epoch': '1.317'}","timestamp":"2026-04-25T20:07:38.429Z"}

data: {"data":"\r 44%|████▍     | 220/501 [07:57<10:08,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:07:40.684Z"}

data: {"data":"\r 44%|████▍     | 221/501 [07:59<10:13,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:07:42.743Z"}

data: {"data":"\r 44%|████▍     | 222/501 [08:01<10:00,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:07:45.007Z"}

data: {"data":"\r 45%|████▍     | 223/501 [08:04<10:07,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:07:47.278Z"}

data: {"data":"\r 45%|████▍     | 224/501 [08:06<10:12,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:07:49.536Z"}

data: {"data":"\r 45%|████▍     | 225/501 [08:08<10:14,  2.23s/it]\u001b[A","timestamp":"2026-04-25T20:07:51.806Z"}

data: {"data":"\r 45%|████▌     | 226/501 [08:11<10:15,  2.24s/it]\u001b[A","timestamp":"2026-04-25T20:07:53.866Z"}

data: {"data":"\r 45%|████▌     | 227/501 [08:13<09:58,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:07:55.932Z"}

data: {"data":"\r 46%|████▌     | 228/501 [08:15<09:46,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:07:58.198Z"}

data: {"data":"\r 46%|████▌     | 229/501 [08:17<09:54,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:08:00.463Z"}

data: {"data":"\r 46%|████▌     | 230/501 [08:19<09:58,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:08:00.464Z"}

data: {"data":"{'loss': '0.3473', 'grad_norm': '0.4776', 'learning_rate': '1.086e-05', 'entropy': '0.4007', 'num_tokens': '1.84e+06', 'mean_token_accuracy': '0.9269', 'epoch': '1.377'}","timestamp":"2026-04-25T20:08:00.464Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:08:00.464Z"}

data: {"data":"\r 46%|████▌     | 230/501 [08:19<09:58,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:08:02.723Z"}

data: {"data":"\r 46%|████▌     | 231/501 [08:21<10:00,  2.22s/it]\u001b[A","timestamp":"2026-04-25T20:08:04.998Z"}

data: {"data":"\r 46%|████▋     | 232/501 [08:24<10:02,  2.24s/it]\u001b[A","timestamp":"2026-04-25T20:08:07.058Z"}

data: {"data":"\r 47%|████▋     | 233/501 [08:26<09:45,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:08:09.120Z"}

data: {"data":"\r 47%|████▋     | 234/501 [08:28<09:33,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:08:11.181Z"}

data: {"data":"\r 47%|████▋     | 235/501 [08:30<09:24,  2.12s/it]\u001b[A","timestamp":"2026-04-25T20:08:13.447Z"}

data: {"data":"\r 47%|████▋     | 236/501 [08:32<09:33,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:08:15.514Z"}

data: {"data":"\r 47%|████▋     | 237/501 [08:34<09:23,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:08:17.774Z"}

data: {"data":"\r 48%|████▊     | 238/501 [08:37<09:31,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:08:20.046Z"}

data: {"data":"\r 48%|████▊     | 239/501 [08:39<09:37,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:08:22.101Z"}

data: {"data":"\r 48%|████▊     | 240/501 [08:41<09:23,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:08:22.101Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:08:22.101Z"}

data: {"data":"{'loss': '0.3489', 'grad_norm': '0.4805', 'learning_rate': '1.046e-05', 'entropy': '0.3968', 'num_tokens': '1.919e+06', 'mean_token_accuracy': '0.9259', 'epoch': '1.437'}","timestamp":"2026-04-25T20:08:22.102Z"}

data: {"data":"\r 48%|████▊     | 240/501 [08:41<09:23,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:08:24.356Z"}

data: {"data":"\r 48%|████▊     | 241/501 [08:43<09:28,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:08:26.624Z"}

data: {"data":"\r 48%|████▊     | 242/501 [08:45<09:32,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:08:28.685Z"}

data: {"data":"\r 49%|████▊     | 243/501 [08:47<09:18,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:08:30.745Z"}

data: {"data":"\r 49%|████▊     | 244/501 [08:50<09:08,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:08:32.802Z"}

data: {"data":"\r 49%|████▉     | 245/501 [08:52<09:00,  2.11s/it]\u001b[A","timestamp":"2026-04-25T20:08:35.061Z"}

data: {"data":"\r 49%|████▉     | 246/501 [08:54<09:09,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:08:37.321Z"}

data: {"data":"\r 49%|████▉     | 247/501 [08:56<09:15,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:08:39.591Z"}

data: {"data":"\r 50%|████▉     | 248/501 [08:58<09:19,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:08:41.656Z"}

data: {"data":"\r 50%|████▉     | 249/501 [09:00<09:06,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:08:43.719Z"}

data: {"data":"\r 50%|████▉     | 250/501 [09:02<08:56,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:08:43.719Z"}

data: {"data":"{'loss': '0.3167', 'grad_norm': '0.4296', 'learning_rate': '1.006e-05', 'entropy': '0.3645', 'num_tokens': '1.999e+06', 'mean_token_accuracy': '0.9326', 'epoch': '1.497'}","timestamp":"2026-04-25T20:08:43.719Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:08:43.719Z"}

data: {"data":"\r 50%|████▉     | 250/501 [09:02<08:56,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:08:45.770Z"}

data: {"data":"\r 50%|█████     | 251/501 [09:05<08:47,  2.11s/it]\u001b[A","timestamp":"2026-04-25T20:08:48.044Z"}

data: {"data":"\r 50%|█████     | 252/501 [09:07<08:57,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:08:50.111Z"}

data: {"data":"\r 50%|█████     | 253/501 [09:09<08:48,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:08:52.384Z"}

data: {"data":"\r 51%|█████     | 254/501 [09:11<08:57,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:08:54.450Z"}

data: {"data":"\r 51%|█████     | 255/501 [09:13<08:46,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:08:56.519Z"}

data: {"data":"\r 51%|█████     | 256/501 [09:15<08:39,  2.12s/it]\u001b[A","timestamp":"2026-04-25T20:08:58.584Z"}

data: {"data":"\r 51%|█████▏    | 257/501 [09:17<08:33,  2.10s/it]\u001b[A","timestamp":"2026-04-25T20:09:00.854Z"}

data: {"data":"\r 51%|█████▏    | 258/501 [09:20<08:43,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:09:02.913Z"}

data: {"data":"\r 52%|█████▏    | 259/501 [09:22<08:34,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:09:05.170Z"}

data: {"data":"{'loss': '0.2932', 'grad_norm': '0.8133', 'learning_rate': '9.661e-06', 'entropy': '0.3425', 'num_tokens': '2.08e+06', 'mean_token_accuracy': '0.9361', 'epoch': '1.557'}","timestamp":"2026-04-25T20:09:05.171Z"}

data: {"data":"\r 52%|█████▏    | 260/501 [09:24<08:41,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:09:05.171Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:09:05.171Z"}

data: {"data":"\r 52%|█████▏    | 260/501 [09:24<08:41,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:09:07.436Z"}

data: {"data":"\r 52%|█████▏    | 261/501 [09:26<08:46,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:09:09.491Z"}

data: {"data":"\r 52%|█████▏    | 262/501 [09:28<08:34,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:09:11.765Z"}

data: {"data":"\r 52%|█████▏    | 263/501 [09:31<08:41,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:09:13.825Z"}

data: {"data":"\r 53%|█████▎    | 264/501 [09:33<08:29,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:09:16.095Z"}

data: {"data":"\r 53%|█████▎    | 265/501 [09:35<08:36,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:09:18.156Z"}

data: {"data":"\r 53%|█████▎    | 266/501 [09:37<08:24,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:09:20.417Z"}

data: {"data":"\r 53%|█████▎    | 267/501 [09:39<08:30,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:09:22.473Z"}

data: {"data":"\r 53%|█████▎    | 268/501 [09:41<08:19,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:09:24.535Z"}

data: {"data":"\r 54%|█████▎    | 269/501 [09:43<08:11,  2.12s/it]\u001b[A","timestamp":"2026-04-25T20:09:26.588Z"}

data: {"data":"\r 54%|█████▍    | 270/501 [09:45<08:05,  2.10s/it]\u001b[A","timestamp":"2026-04-25T20:09:26.588Z"}

data: {"data":"{'loss': '0.3099', 'grad_norm': '0.3904', 'learning_rate': '9.261e-06', 'entropy': '0.3643', 'num_tokens': '2.16e+06', 'mean_token_accuracy': '0.9327', 'epoch': '1.617'}","timestamp":"2026-04-25T20:09:26.588Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:09:26.588Z"}

data: {"data":"\r 54%|█████▍    | 270/501 [09:45<08:05,  2.10s/it]\u001b[A","timestamp":"2026-04-25T20:09:28.860Z"}

data: {"data":"\r 54%|█████▍    | 271/501 [09:48<08:14,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:09:30.912Z"}

data: {"data":"\r 54%|█████▍    | 272/501 [09:50<08:05,  2.12s/it]\u001b[A","timestamp":"2026-04-25T20:09:33.179Z"}

data: {"data":"\r 54%|█████▍    | 273/501 [09:52<08:13,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:09:35.239Z"}

data: {"data":"\r 55%|█████▍    | 274/501 [09:54<08:04,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:09:37.302Z"}

data: {"data":"\r 55%|█████▍    | 275/501 [09:56<07:57,  2.11s/it]\u001b[A","timestamp":"2026-04-25T20:09:39.361Z"}

data: {"data":"\r 55%|█████▌    | 276/501 [09:58<07:51,  2.10s/it]\u001b[A","timestamp":"2026-04-25T20:09:41.627Z"}

data: {"data":"\r 55%|█████▌    | 277/501 [10:00<08:01,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:09:43.885Z"}

data: {"data":"\r 55%|█████▌    | 278/501 [10:03<08:06,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:09:46.141Z"}

data: {"data":"\r 56%|█████▌    | 279/501 [10:05<08:09,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:09:48.203Z"}

data: {"data":"\r 56%|█████▌    | 280/501 [10:07<07:57,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:09:48.203Z"}

data: {"data":"{'loss': '0.2672', 'grad_norm': '0.5745', 'learning_rate': '8.862e-06', 'entropy': '0.3198', 'num_tokens': '2.24e+06', 'mean_token_accuracy': '0.9451', 'epoch': '1.677'}","timestamp":"2026-04-25T20:09:48.203Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:09:48.204Z"}

data: {"data":"\r 56%|█████▌    | 280/501 [10:07<07:57,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:09:50.264Z"}

data: {"data":"\r 56%|█████▌    | 281/501 [10:09<07:48,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:09:52.528Z"}

data: {"data":"\r 56%|█████▋    | 282/501 [10:11<07:55,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:09:54.584Z"}

data: {"data":"\r 56%|█████▋    | 283/501 [10:13<07:45,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:09:56.838Z"}

data: {"data":"\r 57%|█████▋    | 284/501 [10:16<07:51,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:09:59.095Z"}

data: {"data":"\r 57%|█████▋    | 285/501 [10:18<07:54,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:10:01.140Z"}

data: {"data":"\r 57%|█████▋    | 286/501 [10:20<07:42,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:10:03.399Z"}

data: {"data":"\r 57%|█████▋    | 287/501 [10:22<07:47,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:10:05.663Z"}

data: {"data":"\r 57%|█████▋    | 288/501 [10:24<07:50,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:10:07.725Z"}

data: {"data":"\r 58%|█████▊    | 289/501 [10:26<07:38,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:10:09.782Z"}

data: {"data":"\r 58%|█████▊    | 290/501 [10:29<07:29,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:10:09.783Z"}

data: {"data":"{'loss': '0.2567', 'grad_norm': '0.3679', 'learning_rate': '8.463e-06', 'entropy': '0.3086', 'num_tokens': '2.32e+06', 'mean_token_accuracy': '0.9474', 'epoch': '1.737'}","timestamp":"2026-04-25T20:10:09.783Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:10:09.783Z"}

data: {"data":"\r 58%|█████▊    | 290/501 [10:29<07:29,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:10:11.849Z"}

data: {"data":"\r 58%|█████▊    | 291/501 [10:31<07:23,  2.11s/it]\u001b[A","timestamp":"2026-04-25T20:10:13.903Z"}

data: {"data":"\r 58%|█████▊    | 292/501 [10:33<07:17,  2.09s/it]\u001b[A","timestamp":"2026-04-25T20:10:16.173Z"}

data: {"data":"\r 58%|█████▊    | 293/501 [10:35<07:26,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:10:18.227Z"}

data: {"data":"\r 59%|█████▊    | 294/501 [10:37<07:18,  2.12s/it]\u001b[A","timestamp":"2026-04-25T20:10:20.491Z"}

data: {"data":"\r 59%|█████▉    | 295/501 [10:39<07:25,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:10:22.558Z"}

data: {"data":"\r 59%|█████▉    | 296/501 [10:41<07:17,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:10:24.625Z"}

data: {"data":"\r 59%|█████▉    | 297/501 [10:43<07:11,  2.11s/it]\u001b[A","timestamp":"2026-04-25T20:10:26.684Z"}

data: {"data":"\r 59%|█████▉    | 298/501 [10:45<07:05,  2.10s/it]\u001b[A","timestamp":"2026-04-25T20:10:28.948Z"}

data: {"data":"\r 60%|█████▉    | 299/501 [10:48<07:13,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:10:31.007Z"}

data: {"data":"{'loss': '0.2163', 'grad_norm': '0.4672', 'learning_rate': '8.064e-06', 'entropy': '0.2649', 'num_tokens': '2.401e+06', 'mean_token_accuracy': '0.9553', 'epoch': '1.796'}","timestamp":"2026-04-25T20:10:31.007Z"}

data: {"data":"\r 60%|█████▉    | 300/501 [10:50<07:06,  2.12s/it]\u001b[A","timestamp":"2026-04-25T20:10:31.007Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:10:31.008Z"}

data: {"data":"\r 60%|█████▉    | 300/501 [10:50<07:06,  2.12s/it]\u001b[A","timestamp":"2026-04-25T20:10:33.063Z"}

data: {"data":"\r 60%|██████    | 301/501 [10:52<07:00,  2.10s/it]\u001b[A","timestamp":"2026-04-25T20:10:35.334Z"}

data: {"data":"\r 60%|██████    | 302/501 [10:54<07:08,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:10:37.601Z"}

data: {"data":"\r 60%|██████    | 303/501 [10:56<07:12,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:10:39.658Z"}

data: {"data":"\r 61%|██████    | 304/501 [10:58<07:03,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:10:41.922Z"}

data: {"data":"\r 61%|██████    | 305/501 [11:01<07:07,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:10:44.191Z"}

data: {"data":"\r 61%|██████    | 306/501 [11:03<07:10,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:10:46.254Z"}

data: {"data":"\r 61%|██████▏   | 307/501 [11:05<07:00,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:10:48.314Z"}

data: {"data":"\r 61%|██████▏   | 308/501 [11:07<06:51,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:10:50.583Z"}

data: {"data":"\r 62%|██████▏   | 309/501 [11:09<06:57,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:10:52.646Z"}

data: {"data":"\r 62%|██████▏   | 310/501 [11:11<06:48,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:10:52.647Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:10:52.647Z"}

data: {"data":"{'loss': '0.2175', 'grad_norm': '0.5738', 'learning_rate': '7.665e-06', 'entropy': '0.2677', 'num_tokens': '2.481e+06', 'mean_token_accuracy': '0.9549', 'epoch': '1.856'}","timestamp":"2026-04-25T20:10:52.647Z"}

data: {"data":"\r 62%|██████▏   | 310/501 [11:11<06:48,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:10:54.914Z"}

data: {"data":"\r 62%|██████▏   | 311/501 [11:14<06:53,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:10:56.981Z"}

data: {"data":"\r 62%|██████▏   | 312/501 [11:16<06:45,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:10:59.246Z"}

data: {"data":"\r 62%|██████▏   | 313/501 [11:18<06:50,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:11:01.508Z"}

data: {"data":"\r 63%|██████▎   | 314/501 [11:20<06:52,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:11:03.574Z"}

data: {"data":"\r 63%|██████▎   | 315/501 [11:22<06:42,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:11:05.642Z"}

data: {"data":"\r 63%|██████▎   | 316/501 [11:24<06:34,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:11:07.706Z"}

data: {"data":"\r 63%|██████▎   | 317/501 [11:26<06:28,  2.11s/it]\u001b[A","timestamp":"2026-04-25T20:11:09.772Z"}

data: {"data":"\r 63%|██████▎   | 318/501 [11:29<06:24,  2.10s/it]\u001b[A","timestamp":"2026-04-25T20:11:11.842Z"}

data: {"data":"\r 64%|██████▎   | 319/501 [11:31<06:20,  2.09s/it]\u001b[A","timestamp":"2026-04-25T20:11:14.100Z"}

data: {"data":"\r 64%|██████▍   | 320/501 [11:33<06:27,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:11:14.100Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:11:14.100Z"}

data: {"data":"{'loss': '0.2033', 'grad_norm': '0.4641', 'learning_rate': '7.265e-06', 'entropy': '0.2481', 'num_tokens': '2.562e+06', 'mean_token_accuracy': '0.9584', 'epoch': '1.916'}","timestamp":"2026-04-25T20:11:14.100Z"}

data: {"data":"\r 64%|██████▍   | 320/501 [11:33<06:27,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:11:16.364Z"}

data: {"data":"\r 64%|██████▍   | 321/501 [11:35<06:31,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:11:18.421Z"}

data: {"data":"\r 64%|██████▍   | 322/501 [11:37<06:23,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:11:20.687Z"}

data: {"data":"\r 64%|██████▍   | 323/501 [11:39<06:27,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:11:22.942Z"}

data: {"data":"\r 65%|██████▍   | 324/501 [11:42<06:29,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:11:25.207Z"}

data: {"data":"\r 65%|██████▍   | 325/501 [11:44<06:30,  2.22s/it]\u001b[A","timestamp":"2026-04-25T20:11:27.468Z"}

data: {"data":"\r 65%|██████▌   | 326/501 [11:46<06:30,  2.23s/it]\u001b[A","timestamp":"2026-04-25T20:11:29.533Z"}

data: {"data":"\r 65%|██████▌   | 327/501 [11:48<06:19,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:11:31.811Z"}

data: {"data":"\r 65%|██████▌   | 328/501 [11:51<06:22,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:11:33.871Z"}

data: {"data":"\r 66%|██████▌   | 329/501 [11:53<06:12,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:11:35.936Z"}

data: {"data":"\r 66%|██████▌   | 330/501 [11:55<06:05,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:11:35.936Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:11:35.936Z"}

data: {"data":"{'loss': '0.223', 'grad_norm': '0.5205', 'learning_rate': '6.866e-06', 'entropy': '0.2656', 'num_tokens': '2.642e+06', 'mean_token_accuracy': '0.9551', 'epoch': '1.976'}","timestamp":"2026-04-25T20:11:35.936Z"}

data: {"data":"\r 66%|██████▌   | 330/501 [11:55<06:05,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:11:38.198Z"}

data: {"data":"\r 66%|██████▌   | 331/501 [11:57<06:09,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:11:40.458Z"}

data: {"data":"\r 66%|██████▋   | 332/501 [11:59<06:11,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:11:42.708Z"}

data: {"data":"\r 66%|██████▋   | 333/501 [12:01<06:12,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:11:44.681Z"}

data: {"data":"\r 67%|██████▋   | 334/501 [12:03<05:57,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:11:46.960Z"}

data: {"data":"\r 67%|██████▋   | 335/501 [12:06<06:02,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:11:49.010Z"}

data: {"data":"\r 67%|██████▋   | 336/501 [12:08<05:53,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:11:51.268Z"}

data: {"data":"\r 67%|██████▋   | 337/501 [12:10<05:57,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:11:53.325Z"}

data: {"data":"\r 67%|██████▋   | 338/501 [12:12<05:49,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:11:55.599Z"}

data: {"data":"\r 68%|██████▊   | 339/501 [12:14<05:53,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:11:57.657Z"}

data: {"data":"\r 68%|██████▊   | 340/501 [12:16<05:45,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:11:57.657Z"}

data: {"data":"{'loss': '0.2279', 'grad_norm': '0.4992', 'learning_rate': '6.467e-06', 'entropy': '0.2709', 'num_tokens': '2.72e+06', 'mean_token_accuracy': '0.9543', 'epoch': '2.036'}","timestamp":"2026-04-25T20:11:57.657Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:11:57.657Z"}

data: {"data":"\r 68%|██████▊   | 340/501 [12:16<05:45,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:11:59.914Z"}

data: {"data":"\r 68%|██████▊   | 341/501 [12:19<05:48,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:12:02.173Z"}

data: {"data":"\r 68%|██████▊   | 342/501 [12:21<05:50,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:12:04.441Z"}

data: {"data":"\r 68%|██████▊   | 343/501 [12:23<05:51,  2.22s/it]\u001b[A","timestamp":"2026-04-25T20:12:06.503Z"}

data: {"data":"\r 69%|██████▊   | 344/501 [12:25<05:41,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:12:08.561Z"}

data: {"data":"\r 69%|██████▉   | 345/501 [12:27<05:33,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:12:10.621Z"}

data: {"data":"\r 69%|██████▉   | 346/501 [12:29<05:27,  2.12s/it]\u001b[A","timestamp":"2026-04-25T20:12:12.885Z"}

data: {"data":"\r 69%|██████▉   | 347/501 [12:32<05:32,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:12:14.945Z"}

data: {"data":"\r 69%|██████▉   | 348/501 [12:34<05:25,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:12:17.203Z"}

data: {"data":"\r 70%|██████▉   | 349/501 [12:36<05:29,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:12:19.469Z"}

data: {"data":"\r 70%|██████▉   | 350/501 [12:38<05:31,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:12:19.469Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:12:19.469Z"}

data: {"data":"{'loss': '0.1949', 'grad_norm': '0.6589', 'learning_rate': '6.068e-06', 'entropy': '0.2418', 'num_tokens': '2.8e+06', 'mean_token_accuracy': '0.9595', 'epoch': '2.096'}","timestamp":"2026-04-25T20:12:19.469Z"}

data: {"data":"\r 70%|██████▉   | 350/501 [12:38<05:31,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:12:21.724Z"}

data: {"data":"\r 70%|███████   | 351/501 [12:40<05:32,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:12:23.990Z"}

data: {"data":"\r 70%|███████   | 352/501 [12:43<05:32,  2.23s/it]\u001b[A","timestamp":"2026-04-25T20:12:26.059Z"}

data: {"data":"\r 70%|███████   | 353/501 [12:45<05:22,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:12:28.116Z"}

data: {"data":"\r 71%|███████   | 354/501 [12:47<05:15,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:12:30.391Z"}

data: {"data":"\r 71%|███████   | 355/501 [12:49<05:18,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:12:32.447Z"}

data: {"data":"\r 71%|███████   | 356/501 [12:51<05:11,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:12:34.705Z"}

data: {"data":"\r 71%|███████▏  | 357/501 [12:53<05:13,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:12:36.972Z"}

data: {"data":"\r 71%|███████▏  | 358/501 [12:56<05:15,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:12:39.027Z"}

data: {"data":"\r 72%|███████▏  | 359/501 [12:58<05:06,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:12:41.092Z"}

data: {"data":"\r 72%|███████▏  | 360/501 [13:00<05:00,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:12:41.093Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:12:41.093Z"}

data: {"data":"{'loss': '0.1919', 'grad_norm': '0.5246', 'learning_rate': '5.669e-06', 'entropy': '0.2304', 'num_tokens': '2.879e+06', 'mean_token_accuracy': '0.9598', 'epoch': '2.156'}","timestamp":"2026-04-25T20:12:41.093Z"}

data: {"data":"\r 72%|███████▏  | 360/501 [13:00<05:00,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:12:43.152Z"}

data: {"data":"\r 72%|███████▏  | 361/501 [13:02<04:55,  2.11s/it]\u001b[A","timestamp":"2026-04-25T20:12:45.217Z"}

data: {"data":"\r 72%|███████▏  | 362/501 [13:04<04:51,  2.10s/it]\u001b[A","timestamp":"2026-04-25T20:12:47.268Z"}

data: {"data":"\r 72%|███████▏  | 363/501 [13:06<04:47,  2.08s/it]\u001b[A","timestamp":"2026-04-25T20:12:49.533Z"}

data: {"data":"\r 73%|███████▎  | 364/501 [13:08<04:52,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:12:51.598Z"}

data: {"data":"\r 73%|███████▎  | 365/501 [13:10<04:47,  2.12s/it]\u001b[A","timestamp":"2026-04-25T20:12:53.660Z"}

data: {"data":"\r 73%|███████▎  | 366/501 [13:12<04:43,  2.10s/it]\u001b[A","timestamp":"2026-04-25T20:12:55.920Z"}

data: {"data":"\r 73%|███████▎  | 367/501 [13:15<04:47,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:12:58.186Z"}

data: {"data":"\r 73%|███████▎  | 368/501 [13:17<04:50,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:13:00.445Z"}

data: {"data":"\r 74%|███████▎  | 369/501 [13:19<04:51,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:13:02.708Z"}

data: {"data":"\r 74%|███████▍  | 370/501 [13:21<04:51,  2.22s/it]\u001b[A","timestamp":"2026-04-25T20:13:02.708Z"}

data: {"data":"{'loss': '0.1926', 'grad_norm': '0.4952', 'learning_rate': '5.269e-06', 'entropy': '0.2281', 'num_tokens': '2.959e+06', 'mean_token_accuracy': '0.9603', 'epoch': '2.216'}","timestamp":"2026-04-25T20:13:02.708Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:13:02.708Z"}

data: {"data":"\r 74%|███████▍  | 370/501 [13:21<04:51,  2.22s/it]\u001b[A","timestamp":"2026-04-25T20:13:04.764Z"}

data: {"data":"\r 74%|███████▍  | 371/501 [13:24<04:42,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:13:07.033Z"}

data: {"data":"\r 74%|███████▍  | 372/501 [13:26<04:44,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:13:09.099Z"}

data: {"data":"\r 74%|███████▍  | 373/501 [13:28<04:36,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:13:11.151Z"}

data: {"data":"\r 75%|███████▍  | 374/501 [13:30<04:30,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:13:13.417Z"}

data: {"data":"\r 75%|███████▍  | 375/501 [13:32<04:33,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:13:15.478Z"}

data: {"data":"\r 75%|███████▌  | 376/501 [13:34<04:27,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:13:17.756Z"}

data: {"data":"\r 75%|███████▌  | 377/501 [13:37<04:30,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:13:19.822Z"}

data: {"data":"\r 75%|███████▌  | 378/501 [13:39<04:23,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:13:21.898Z"}

data: {"data":"\r 76%|███████▌  | 379/501 [13:41<04:19,  2.12s/it]\u001b[A","timestamp":"2026-04-25T20:13:23.964Z"}

data: {"data":"\r 76%|███████▌  | 380/501 [13:43<04:14,  2.11s/it]\u001b[A","timestamp":"2026-04-25T20:13:23.965Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:13:23.965Z"}

data: {"data":"{'loss': '0.179', 'grad_norm': '0.4726', 'learning_rate': '4.87e-06', 'entropy': '0.2133', 'num_tokens': '3.039e+06', 'mean_token_accuracy': '0.9628', 'epoch': '2.275'}","timestamp":"2026-04-25T20:13:23.965Z"}

data: {"data":"\r 76%|███████▌  | 380/501 [13:43<04:14,  2.11s/it]\u001b[A","timestamp":"2026-04-25T20:13:26.030Z"}

data: {"data":"\r 76%|███████▌  | 381/501 [13:45<04:11,  2.09s/it]\u001b[A","timestamp":"2026-04-25T20:13:28.097Z"}

data: {"data":"\r 76%|███████▌  | 382/501 [13:47<04:08,  2.09s/it]\u001b[A","timestamp":"2026-04-25T20:13:30.158Z"}

data: {"data":"\r 76%|███████▋  | 383/501 [13:49<04:05,  2.08s/it]\u001b[A","timestamp":"2026-04-25T20:13:32.212Z"}

data: {"data":"\r 77%|███████▋  | 384/501 [13:51<04:02,  2.07s/it]\u001b[A","timestamp":"2026-04-25T20:13:34.624Z"}

data: {"data":"\r 77%|███████▋  | 385/501 [13:53<04:12,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:13:36.679Z"}

data: {"data":"\r 77%|███████▋  | 386/501 [13:55<04:05,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:13:38.948Z"}

data: {"data":"\r 77%|███████▋  | 387/501 [13:58<04:08,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:13:41.211Z"}

data: {"data":"\r 77%|███████▋  | 388/501 [14:00<04:08,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:13:43.268Z"}

data: {"data":"\r 78%|███████▊  | 389/501 [14:02<04:01,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:13:45.527Z"}

data: {"data":"\r 78%|███████▊  | 390/501 [14:04<04:02,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:13:45.527Z"}

data: {"data":"{'loss': '0.1914', 'grad_norm': '0.6392', 'learning_rate': '4.471e-06', 'entropy': '0.2287', 'num_tokens': '3.12e+06', 'mean_token_accuracy': '0.9596', 'epoch': '2.335'}","timestamp":"2026-04-25T20:13:45.527Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:13:45.527Z"}

data: {"data":"\r 78%|███████▊  | 390/501 [14:04<04:02,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:13:47.797Z"}

data: {"data":"\r 78%|███████▊  | 391/501 [14:07<04:03,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:13:50.061Z"}

data: {"data":"\r 78%|███████▊  | 392/501 [14:09<04:02,  2.23s/it]\u001b[A","timestamp":"2026-04-25T20:13:52.328Z"}

data: {"data":"\r 78%|███████▊  | 393/501 [14:11<04:01,  2.24s/it]\u001b[A","timestamp":"2026-04-25T20:13:54.599Z"}

data: {"data":"\r 79%|███████▊  | 394/501 [14:13<04:00,  2.25s/it]\u001b[A","timestamp":"2026-04-25T20:13:56.663Z"}

data: {"data":"\r 79%|███████▉  | 395/501 [14:15<03:52,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:13:58.725Z"}

data: {"data":"\r 79%|███████▉  | 396/501 [14:17<03:46,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:14:00.793Z"}

data: {"data":"\r 79%|███████▉  | 397/501 [14:20<03:41,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:14:02.860Z"}

data: {"data":"\r 79%|███████▉  | 398/501 [14:22<03:37,  2.11s/it]\u001b[A","timestamp":"2026-04-25T20:14:04.926Z"}

data: {"data":"\r 80%|███████▉  | 399/501 [14:24<03:33,  2.10s/it]\u001b[A","timestamp":"2026-04-25T20:14:07.193Z"}

data: {"data":"\r 80%|███████▉  | 400/501 [14:26<03:36,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:14:07.193Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:14:07.193Z"}

data: {"data":"{'loss': '0.1782', 'grad_norm': '0.5421', 'learning_rate': '4.072e-06', 'entropy': '0.2141', 'num_tokens': '3.201e+06', 'mean_token_accuracy': '0.962', 'epoch': '2.395'}","timestamp":"2026-04-25T20:14:07.193Z"}

data: {"data":"\r 80%|███████▉  | 400/501 [14:26<03:36,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:14:09.459Z"}

data: {"data":"\r 80%|████████  | 401/501 [14:28<03:38,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:14:11.516Z"}

data: {"data":"\r 80%|████████  | 402/501 [14:30<03:32,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:14:13.787Z"}

data: {"data":"\r 80%|████████  | 403/501 [14:33<03:33,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:14:16.057Z"}

data: {"data":"\r 81%|████████  | 404/501 [14:35<03:34,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:14:18.110Z"}

data: {"data":"\r 81%|████████  | 405/501 [14:37<03:27,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:14:20.380Z"}

data: {"data":"\r 81%|████████  | 406/501 [14:39<03:28,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:14:22.451Z"}

data: {"data":"\r 81%|████████  | 407/501 [14:41<03:22,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:14:24.523Z"}

data: {"data":"\r 81%|████████▏ | 408/501 [14:43<03:18,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:14:26.591Z"}

data: {"data":"\r 82%|████████▏ | 409/501 [14:45<03:14,  2.11s/it]\u001b[A","timestamp":"2026-04-25T20:14:28.646Z"}

data: {"data":"\r 82%|████████▏ | 410/501 [14:47<03:10,  2.10s/it]\u001b[A","timestamp":"2026-04-25T20:14:28.647Z"}

data: {"data":"{'loss': '0.1689', 'grad_norm': '0.4012', 'learning_rate': '3.673e-06', 'entropy': '0.2013', 'num_tokens': '3.281e+06', 'mean_token_accuracy': '0.9647', 'epoch': '2.455'}","timestamp":"2026-04-25T20:14:28.647Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:14:28.647Z"}

data: {"data":"\r 82%|████████▏ | 410/501 [14:47<03:10,  2.10s/it]\u001b[A","timestamp":"2026-04-25T20:14:30.919Z"}

data: {"data":"\r 82%|████████▏ | 411/501 [14:50<03:13,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:14:33.189Z"}

data: {"data":"\r 82%|████████▏ | 412/501 [14:52<03:14,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:14:35.250Z"}

data: {"data":"\r 82%|████████▏ | 413/501 [14:54<03:09,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:14:37.517Z"}

data: {"data":"\r 83%|████████▎ | 414/501 [14:56<03:09,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:14:39.779Z"}

data: {"data":"\r 83%|████████▎ | 415/501 [14:59<03:09,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:14:42.040Z"}

data: {"data":"\r 83%|████████▎ | 416/501 [15:01<03:08,  2.22s/it]\u001b[A","timestamp":"2026-04-25T20:14:44.300Z"}

data: {"data":"\r 83%|████████▎ | 417/501 [15:03<03:07,  2.23s/it]\u001b[A","timestamp":"2026-04-25T20:14:46.572Z"}

data: {"data":"\r 83%|████████▎ | 418/501 [15:05<03:06,  2.25s/it]\u001b[A","timestamp":"2026-04-25T20:14:48.844Z"}

data: {"data":"\r 84%|████████▎ | 419/501 [15:08<03:04,  2.25s/it]\u001b[A","timestamp":"2026-04-25T20:14:51.112Z"}

data: {"data":"\r 84%|████████▍ | 420/501 [15:10<03:02,  2.26s/it]\u001b[A","timestamp":"2026-04-25T20:14:51.112Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:14:51.112Z"}

data: {"data":"{'loss': '0.184', 'grad_norm': '0.455', 'learning_rate': '3.273e-06', 'entropy': '0.2205', 'num_tokens': '3.36e+06', 'mean_token_accuracy': '0.9612', 'epoch': '2.515'}","timestamp":"2026-04-25T20:14:51.112Z"}

data: {"data":"\r 84%|████████▍ | 420/501 [15:10<03:02,  2.26s/it]\u001b[A","timestamp":"2026-04-25T20:14:53.368Z"}

data: {"data":"\r 84%|████████▍ | 421/501 [15:12<03:00,  2.26s/it]\u001b[A","timestamp":"2026-04-25T20:14:55.436Z"}

data: {"data":"\r 84%|████████▍ | 422/501 [15:14<02:53,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:14:57.501Z"}

data: {"data":"\r 84%|████████▍ | 423/501 [15:16<02:48,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:14:59.565Z"}

data: {"data":"\r 85%|████████▍ | 424/501 [15:18<02:44,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:15:01.636Z"}

data: {"data":"\r 85%|████████▍ | 425/501 [15:20<02:40,  2.11s/it]\u001b[A","timestamp":"2026-04-25T20:15:03.700Z"}

data: {"data":"\r 85%|████████▌ | 426/501 [15:22<02:37,  2.10s/it]\u001b[A","timestamp":"2026-04-25T20:15:05.967Z"}

data: {"data":"\r 85%|████████▌ | 427/501 [15:25<02:39,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:15:08.237Z"}

data: {"data":"\r 85%|████████▌ | 428/501 [15:27<02:39,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:15:10.290Z"}

data: {"data":"\r 86%|████████▌ | 429/501 [15:29<02:34,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:15:12.558Z"}

data: {"data":"\r 86%|████████▌ | 430/501 [15:31<02:34,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:15:12.558Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:15:12.558Z"}

data: {"data":"{'loss': '0.1483', 'grad_norm': '0.4924', 'learning_rate': '2.874e-06', 'entropy': '0.1837', 'num_tokens': '3.441e+06', 'mean_token_accuracy': '0.9692', 'epoch': '2.575'}","timestamp":"2026-04-25T20:15:12.558Z"}

data: {"data":"\r 86%|████████▌ | 430/501 [15:31<02:34,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:15:14.827Z"}

data: {"data":"\r 86%|████████▌ | 431/501 [15:34<02:34,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:15:16.884Z"}

data: {"data":"\r 86%|████████▌ | 432/501 [15:36<02:29,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:15:19.138Z"}

data: {"data":"\r 86%|████████▋ | 433/501 [15:38<02:28,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:15:21.403Z"}

data: {"data":"\r 87%|████████▋ | 434/501 [15:40<02:28,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:15:23.674Z"}

data: {"data":"\r 87%|████████▋ | 435/501 [15:42<02:27,  2.23s/it]\u001b[A","timestamp":"2026-04-25T20:15:25.932Z"}

data: {"data":"\r 87%|████████▋ | 436/501 [15:45<02:25,  2.24s/it]\u001b[A","timestamp":"2026-04-25T20:15:28.197Z"}

data: {"data":"\r 87%|████████▋ | 437/501 [15:47<02:23,  2.25s/it]\u001b[A","timestamp":"2026-04-25T20:15:30.452Z"}

data: {"data":"\r 87%|████████▋ | 438/501 [15:49<02:21,  2.25s/it]\u001b[A","timestamp":"2026-04-25T20:15:32.709Z"}

data: {"data":"\r 88%|████████▊ | 439/501 [15:51<02:19,  2.25s/it]\u001b[A","timestamp":"2026-04-25T20:15:34.767Z"}

data: {"data":"\r 88%|████████▊ | 440/501 [15:54<02:13,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:15:34.767Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:15:34.767Z"}

data: {"data":"{'loss': '0.1643', 'grad_norm': '0.7521', 'learning_rate': '2.475e-06', 'entropy': '0.1987', 'num_tokens': '3.52e+06', 'mean_token_accuracy': '0.9659', 'epoch': '2.635'}","timestamp":"2026-04-25T20:15:34.767Z"}

data: {"data":"\r 88%|████████▊ | 440/501 [15:54<02:13,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:15:37.030Z"}

data: {"data":"\r 88%|████████▊ | 441/501 [15:56<02:12,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:15:39.088Z"}

data: {"data":"\r 88%|████████▊ | 442/501 [15:58<02:07,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:15:41.356Z"}

data: {"data":"\r 88%|████████▊ | 443/501 [16:00<02:07,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:15:43.419Z"}

data: {"data":"\r 89%|████████▊ | 444/501 [16:02<02:02,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:15:45.481Z"}

data: {"data":"\r 89%|████████▉ | 445/501 [16:04<01:59,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:15:47.738Z"}

data: {"data":"\r 89%|████████▉ | 446/501 [16:06<01:59,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:15:50.005Z"}

data: {"data":"\r 89%|████████▉ | 447/501 [16:09<01:58,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:15:52.274Z"}

data: {"data":"\r 89%|████████▉ | 448/501 [16:11<01:57,  2.22s/it]\u001b[A","timestamp":"2026-04-25T20:15:54.334Z"}

data: {"data":"\r 90%|████████▉ | 449/501 [16:13<01:52,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:15:56.594Z"}

data: {"data":"\r 90%|████████▉ | 450/501 [16:15<01:52,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:15:56.594Z"}

data: {"data":"{'loss': '0.1631', 'grad_norm': '0.5542', 'learning_rate': '2.076e-06', 'entropy': '0.1994', 'num_tokens': '3.6e+06', 'mean_token_accuracy': '0.9651', 'epoch': '2.695'}","timestamp":"2026-04-25T20:15:56.594Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:15:56.594Z"}

data: {"data":"\r 90%|████████▉ | 450/501 [16:15<01:52,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:15:58.659Z"}

data: {"data":"\r 90%|█████████ | 451/501 [16:17<01:47,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:16:00.721Z"}

data: {"data":"\r 90%|█████████ | 452/501 [16:19<01:44,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:16:02.990Z"}

data: {"data":"\r 90%|█████████ | 453/501 [16:22<01:44,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:16:05.050Z"}

data: {"data":"\r 91%|█████████ | 454/501 [16:24<01:40,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:16:07.106Z"}

data: {"data":"\r 91%|█████████ | 455/501 [16:26<01:37,  2.11s/it]\u001b[A","timestamp":"2026-04-25T20:16:09.163Z"}

data: {"data":"\r 91%|█████████ | 456/501 [16:28<01:34,  2.10s/it]\u001b[A","timestamp":"2026-04-25T20:16:11.431Z"}

data: {"data":"\r 91%|█████████ | 457/501 [16:30<01:34,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:16:13.493Z"}

data: {"data":"\r 91%|█████████▏| 458/501 [16:32<01:31,  2.12s/it]\u001b[A","timestamp":"2026-04-25T20:16:15.904Z"}

data: {"data":"\r 92%|█████████▏| 459/501 [16:35<01:32,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:16:17.966Z"}

data: {"data":"\r 92%|█████████▏| 460/501 [16:37<01:28,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:16:17.967Z"}

data: {"data":"{'loss': '0.156', 'grad_norm': '0.4535', 'learning_rate': '1.677e-06', 'entropy': '0.1903', 'num_tokens': '3.681e+06', 'mean_token_accuracy': '0.9667', 'epoch': '2.754'}","timestamp":"2026-04-25T20:16:17.967Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:16:17.967Z"}

data: {"data":"\r 92%|█████████▏| 460/501 [16:37<01:28,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:16:20.238Z"}

data: {"data":"\r 92%|█████████▏| 461/501 [16:39<01:27,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:16:22.301Z"}

data: {"data":"\r 92%|█████████▏| 462/501 [16:41<01:24,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:16:24.567Z"}

data: {"data":"\r 92%|█████████▏| 463/501 [16:43<01:23,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:16:26.832Z"}

data: {"data":"\r 93%|█████████▎| 464/501 [16:46<01:21,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:16:29.094Z"}

data: {"data":"\r 93%|█████████▎| 465/501 [16:48<01:20,  2.23s/it]\u001b[A","timestamp":"2026-04-25T20:16:31.349Z"}

data: {"data":"\r 93%|█████████▎| 466/501 [16:50<01:18,  2.24s/it]\u001b[A","timestamp":"2026-04-25T20:16:33.405Z"}

data: {"data":"\r 93%|█████████▎| 467/501 [16:52<01:14,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:16:35.672Z"}

data: {"data":"\r 93%|█████████▎| 468/501 [16:54<01:12,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:16:37.745Z"}

data: {"data":"\r 94%|█████████▎| 469/501 [16:57<01:09,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:16:39.814Z"}

data: {"data":"\r 94%|█████████▍| 470/501 [16:59<01:06,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:16:39.814Z"}

data: {"data":"{'loss': '0.1569', 'grad_norm': '0.4086', 'learning_rate': '1.277e-06', 'entropy': '0.1883', 'num_tokens': '3.76e+06', 'mean_token_accuracy': '0.9665', 'epoch': '2.814'}","timestamp":"2026-04-25T20:16:39.814Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:16:39.814Z"}

data: {"data":"\r 94%|█████████▍| 470/501 [16:59<01:06,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:16:42.073Z"}

data: {"data":"\r 94%|█████████▍| 471/501 [17:01<01:05,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:16:44.340Z"}

data: {"data":"\r 94%|█████████▍| 472/501 [17:03<01:03,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:16:46.398Z"}

data: {"data":"\r 94%|█████████▍| 473/501 [17:05<01:00,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:16:48.672Z"}

data: {"data":"\r 95%|█████████▍| 474/501 [17:07<00:59,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:16:50.938Z"}

data: {"data":"\r 95%|█████████▍| 475/501 [17:10<00:57,  2.22s/it]\u001b[A","timestamp":"2026-04-25T20:16:53.005Z"}

data: {"data":"\r 95%|█████████▌| 476/501 [17:12<00:54,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:16:55.276Z"}

data: {"data":"\r 95%|█████████▌| 477/501 [17:14<00:52,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:16:57.341Z"}

data: {"data":"\r 95%|█████████▌| 478/501 [17:16<00:49,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:16:59.414Z"}

data: {"data":"\r 96%|█████████▌| 479/501 [17:18<00:46,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:17:01.464Z"}

data: {"data":"\r 96%|█████████▌| 480/501 [17:20<00:44,  2.11s/it]\u001b[A","timestamp":"2026-04-25T20:17:01.464Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:17:01.464Z"}

data: {"data":"{'loss': '0.1574', 'grad_norm': '0.5595', 'learning_rate': '8.782e-07', 'entropy': '0.1872', 'num_tokens': '3.841e+06', 'mean_token_accuracy': '0.9665', 'epoch': '2.874'}","timestamp":"2026-04-25T20:17:01.464Z"}

data: {"data":"\r 96%|█████████▌| 480/501 [17:20<00:44,  2.11s/it]\u001b[A","timestamp":"2026-04-25T20:17:03.733Z"}

data: {"data":"\r 96%|█████████▌| 481/501 [17:22<00:43,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:17:06.002Z"}

data: {"data":"\r 96%|█████████▌| 482/501 [17:25<00:41,  2.19s/it]\u001b[A","timestamp":"2026-04-25T20:17:08.264Z"}

data: {"data":"\r 96%|█████████▋| 483/501 [17:27<00:39,  2.21s/it]\u001b[A","timestamp":"2026-04-25T20:17:10.321Z"}

data: {"data":"\r 97%|█████████▋| 484/501 [17:29<00:36,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:17:12.592Z"}

data: {"data":"\r 97%|█████████▋| 485/501 [17:31<00:35,  2.20s/it]\u001b[A","timestamp":"2026-04-25T20:17:14.861Z"}

data: {"data":"\r 97%|█████████▋| 486/501 [17:34<00:33,  2.22s/it]\u001b[A","timestamp":"2026-04-25T20:17:16.932Z"}

data: {"data":"\r 97%|█████████▋| 487/501 [17:36<00:30,  2.17s/it]\u001b[A","timestamp":"2026-04-25T20:17:18.993Z"}

data: {"data":"\r 97%|█████████▋| 488/501 [17:38<00:27,  2.14s/it]\u001b[A","timestamp":"2026-04-25T20:17:21.267Z"}

data: {"data":"\r 98%|█████████▊| 489/501 [17:40<00:26,  2.18s/it]\u001b[A","timestamp":"2026-04-25T20:17:23.334Z"}

data: {"data":"{'loss': '0.1478', 'grad_norm': '0.4566', 'learning_rate': '4.79e-07', 'entropy': '0.1755', 'num_tokens': '3.921e+06', 'mean_token_accuracy': '0.9688', 'epoch': '2.934'}","timestamp":"2026-04-25T20:17:23.334Z"}

data: {"data":"\r 98%|█████████▊| 490/501 [17:42<00:23,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:17:23.334Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:17:23.334Z"}

data: {"data":"\r 98%|█████████▊| 490/501 [17:42<00:23,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:17:25.392Z"}

data: {"data":"\r 98%|█████████▊| 491/501 [17:44<00:21,  2.12s/it]\u001b[A","timestamp":"2026-04-25T20:17:27.451Z"}

data: {"data":"\r 98%|█████████▊| 492/501 [17:46<00:18,  2.10s/it]\u001b[A","timestamp":"2026-04-25T20:17:29.519Z"}

data: {"data":"\r 98%|█████████▊| 493/501 [17:48<00:16,  2.09s/it]\u001b[A","timestamp":"2026-04-25T20:17:31.580Z"}

data: {"data":"\r 99%|█████████▊| 494/501 [17:50<00:14,  2.08s/it]\u001b[A","timestamp":"2026-04-25T20:17:33.642Z"}

data: {"data":"\r 99%|█████████▉| 495/501 [17:52<00:12,  2.08s/it]\u001b[A","timestamp":"2026-04-25T20:17:35.898Z"}

data: {"data":"\r 99%|█████████▉| 496/501 [17:55<00:10,  2.13s/it]\u001b[A","timestamp":"2026-04-25T20:17:37.954Z"}

data: {"data":"\r 99%|█████████▉| 497/501 [17:57<00:08,  2.11s/it]\u001b[A","timestamp":"2026-04-25T20:17:40.217Z"}

data: {"data":"\r 99%|█████████▉| 498/501 [17:59<00:06,  2.15s/it]\u001b[A","timestamp":"2026-04-25T20:17:42.270Z"}

data: {"data":"\r100%|█████████▉| 499/501 [18:01<00:04,  2.12s/it]\u001b[A","timestamp":"2026-04-25T20:17:44.525Z"}

data: {"data":"\r100%|█████████▉| 500/501 [18:03<00:02,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:17:44.526Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:17:44.526Z"}

data: {"data":"{'loss': '0.1538', 'grad_norm': '0.4972', 'learning_rate': '7.984e-08', 'entropy': '0.1857', 'num_tokens': '4.001e+06', 'mean_token_accuracy': '0.967', 'epoch': '2.994'}","timestamp":"2026-04-25T20:17:44.526Z"}

data: {"data":"\r100%|█████████▉| 500/501 [18:03<00:02,  2.16s/it]\u001b[A","timestamp":"2026-04-25T20:17:46.961Z"}

data: {"data":"\r100%|██████████| 501/501 [18:06<00:00,  2.24s/it]\u001b[A","timestamp":"2026-04-25T20:17:47.267Z"}

data: {"data":"{'train_runtime': '1087', 'train_samples_per_second': '3.686', 'train_steps_per_second': '0.461', 'train_loss': '0.6784', 'entropy': '0.1464', 'num_tokens': '4.008e+06', 'mean_token_accuracy': '0.9756', 'epoch': '3'}","timestamp":"2026-04-25T20:17:47.267Z"}

data: {"data":"\r                                                 \r\u001b[A","timestamp":"2026-04-25T20:17:47.267Z"}

data: {"data":"\r100%|██████████| 501/501 [18:06<00:00,  2.24s/it]\u001b[A\r100%|██████████| 501/501 [18:06<00:00,  2.17s/it]","timestamp":"2026-04-25T20:17:47.268Z"}

data: {"data":"✅ Training completed.","timestamp":"2026-04-25T20:17:48.789Z"}

data: {"data":"\rProcessing Files (0 / 0)      : |          |  0.00B /  0.00B            ","timestamp":"2026-04-25T20:17:49.231Z"}

data: {"data":"\rNew Data Upload               : |          |  0.00B /  0.00B            \u001b[A","timestamp":"2026-04-25T20:17:49.353Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:49.354Z"}

data: {"data":"\r  .../output/training_args.bin: 100%|██████████| 5.71kB / 5.71kB            \u001b[A\u001b[A","timestamp":"2026-04-25T20:17:49.354Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:49.354Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:49.354Z"}

data: {"data":"\r  /data/output/tokenizer.json : 100%|██████████| 11.4MB / 11.4MB            \u001b[A\u001b[A\u001b[A","timestamp":"2026-04-25T20:17:49.354Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:49.354Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:49.354Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:49.354Z"}

data: {"data":"\r  ...adapter_model.safetensors: 100%|██████████| 20.2MB / 20.2MB            \u001b[A\u001b[A\u001b[A\u001b[A","timestamp":"2026-04-25T20:17:49.354Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:49.354Z"}

data: {"data":"\r  .../output/training_args.bin: 100%|██████████| 5.71kB / 5.71kB            \u001b[A\u001b[A","timestamp":"2026-04-25T20:17:49.354Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:49.354Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:49.354Z"}

data: {"data":"\r  /data/output/tokenizer.json : 100%|██████████| 11.4MB / 11.4MB            \u001b[A\u001b[A\u001b[A","timestamp":"2026-04-25T20:17:49.354Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:49.354Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:49.354Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:49.354Z"}

data: {"data":"\r  ...adapter_model.safetensors: 100%|██████████| 20.2MB / 20.2MB            \u001b[A\u001b[A\u001b[A\u001b[A","timestamp":"2026-04-25T20:17:49.448Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:49.448Z"}

data: {"data":"\r  .../output/training_args.bin: 100%|██████████| 5.71kB / 5.71kB            \u001b[A\u001b[A","timestamp":"2026-04-25T20:17:49.448Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:49.448Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:49.448Z"}

data: {"data":"\r  /data/output/tokenizer.json : 100%|██████████| 11.4MB / 11.4MB            \u001b[A\u001b[A\u001b[A","timestamp":"2026-04-25T20:17:49.448Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:49.448Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:49.448Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:49.448Z"}

data: {"data":"\r  ...adapter_model.safetensors: 100%|██████████| 20.2MB / 20.2MB            \u001b[A\u001b[A\u001b[A\u001b[A\rProcessing Files (3 / 3)      : 100%|██████████| 31.6MB / 31.6MB,  0.00B/s  ","timestamp":"2026-04-25T20:17:49.448Z"}

data: {"data":"\rNew Data Upload               : |          |  0.00B /  0.00B,  0.00B/s  ","timestamp":"2026-04-25T20:17:49.448Z"}

data: {"data":"\r  .../output/training_args.bin: 100%|██████████| 5.71kB / 5.71kB            ","timestamp":"2026-04-25T20:17:49.448Z"}

data: {"data":"\r  /data/output/tokenizer.json : 100%|██████████| 11.4MB / 11.4MB            ","timestamp":"2026-04-25T20:17:49.449Z"}

data: {"data":"\r  ...adapter_model.safetensors: 100%|██████████| 20.2MB / 20.2MB            ","timestamp":"2026-04-25T20:17:49.449Z"}

data: {"data":"💾 Model saved to /data/output.","timestamp":"2026-04-25T20:17:49.781Z"}

data: {"data":"\rProcessing Files (0 / 0)      : |          |  0.00B /  0.00B            ","timestamp":"2026-04-25T20:17:50.124Z"}

data: {"data":"\rNew Data Upload               : |          |  0.00B /  0.00B            \u001b[A","timestamp":"2026-04-25T20:17:50.234Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:50.234Z"}

data: {"data":"\r  .../output/training_args.bin: 100%|██████████| 5.71kB / 5.71kB            \u001b[A\u001b[A","timestamp":"2026-04-25T20:17:50.234Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:50.234Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:50.234Z"}

data: {"data":"\r  /data/output/tokenizer.json : 100%|██████████| 11.4MB / 11.4MB            \u001b[A\u001b[A\u001b[A","timestamp":"2026-04-25T20:17:50.234Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:50.234Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:50.234Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:50.234Z"}

data: {"data":"\r  ...adapter_model.safetensors: 100%|██████████| 20.2MB / 20.2MB            \u001b[A\u001b[A\u001b[A\u001b[A","timestamp":"2026-04-25T20:17:50.234Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:50.234Z"}

data: {"data":"\r  .../output/training_args.bin: 100%|██████████| 5.71kB / 5.71kB            \u001b[A\u001b[A","timestamp":"2026-04-25T20:17:50.234Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:50.234Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:50.234Z"}

data: {"data":"\r  /data/output/tokenizer.json : 100%|██████████| 11.4MB / 11.4MB            \u001b[A\u001b[A\u001b[A","timestamp":"2026-04-25T20:17:50.234Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:50.234Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:50.234Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:50.234Z"}

data: {"data":"\r  ...adapter_model.safetensors: 100%|██████████| 20.2MB / 20.2MB            \u001b[A\u001b[A\u001b[A\u001b[A","timestamp":"2026-04-25T20:17:50.334Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:50.334Z"}

data: {"data":"\r  .../output/training_args.bin: 100%|██████████| 5.71kB / 5.71kB            \u001b[A\u001b[A","timestamp":"2026-04-25T20:17:50.334Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:50.334Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:50.334Z"}

data: {"data":"\r  /data/output/tokenizer.json : 100%|██████████| 11.4MB / 11.4MB            \u001b[A\u001b[A\u001b[A","timestamp":"2026-04-25T20:17:50.334Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:50.334Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:50.335Z"}

data: {"data":"","timestamp":"2026-04-25T20:17:50.335Z"}

data: {"data":"\r  ...adapter_model.safetensors: 100%|██████████| 20.2MB / 20.2MB            \u001b[A\u001b[A\u001b[A\u001b[A\rProcessing Files (3 / 3)      : 100%|██████████| 31.6MB / 31.6MB,  0.00B/s  ","timestamp":"2026-04-25T20:17:50.335Z"}

data: {"data":"\rNew Data Upload               : |          |  0.00B /  0.00B,  0.00B/s  ","timestamp":"2026-04-25T20:17:50.335Z"}

data: {"data":"\r  .../output/training_args.bin: 100%|██████████| 5.71kB / 5.71kB            ","timestamp":"2026-04-25T20:17:50.335Z"}

data: {"data":"\r  /data/output/tokenizer.json : 100%|██████████| 11.4MB / 11.4MB            ","timestamp":"2026-04-25T20:17:50.335Z"}

data: {"data":"\r  ...adapter_model.safetensors: 100%|██████████| 20.2MB / 20.2MB            ","timestamp":"2026-04-25T20:17:50.335Z"}

data: {"data":"🤗 Model pushed to the Hub in https://huggingface.co/Yaswanth-Bolla/qwen2.5-7b-sre-sft.","timestamp":"2026-04-25T20:17:50.641Z"}