805 lines
257 KiB
Plaintext
805 lines
257 KiB
Plaintext
|
[LM-EVAL] start Sun Aug 9 23:20:39 UTC 2026 token=hf_oUMhDnr...
|
|||
|
|
Downloading builder script: 0.00B [00:00, ?B/s]
Downloading builder script: 5.67kB [00:00, 7.22MB/s]
|
|||
|
|
2026-08-09:23:20:43,827 INFO [__main__.py:251] Verbosity set to INFO
|
|||
|
|
2026-08-09:23:20:46,667 INFO [__main__.py:335] Selected Tasks: ['mmlu']
|
|||
|
|
2026-08-09:23:20:46,667 INFO [__main__.py:336] Loading selected tasks...
|
|||
|
|
2026-08-09:23:20:46,669 INFO [evaluator.py:131] Setting random seed to 0 | Setting numpy seed to 1234 | Setting torch manual seed to 1234
|
|||
|
|
2026-08-09:23:20:46,728 INFO [huggingface.py:162] Using device 'cuda:0'
|
|||
|
|
Downloading readme: 0%| | 0.00/42.6k [00:00<?, ?B/s]
Downloading readme: 100%|██████████| 42.6k/42.6k [00:00<00:00, 333kB/s]
Downloading readme: 100%|██████████| 42.6k/42.6k [00:00<00:00, 330kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/28.1k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 28.1k/28.1k [00:00<00:00, 66.2kB/s]
Downloading data: 100%|██████████| 28.1k/28.1k [00:00<00:00, 66.0kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/6.26k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 6.26k/6.26k [00:00<00:00, 33.2kB/s]
Downloading data: 100%|██████████| 6.26k/6.26k [00:00<00:00, 33.1kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/6.82k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 6.82k/6.82k [00:00<00:00, 32.7kB/s]
Downloading data: 100%|██████████| 6.82k/6.82k [00:00<00:00, 32.6kB/s]
|
|||
|
|
Generating test split: 0%| | 0/100 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 100/100 [00:00<00:00, 15228.20 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/11 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 11/11 [00:00<00:00, 2814.63 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1427.31 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/27.3k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 27.3k/27.3k [00:00<00:00, 143kB/s]
Downloading data: 100%|██████████| 27.3k/27.3k [00:00<00:00, 143kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/5.29k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 5.29k/5.29k [00:00<00:00, 30.1kB/s]
Downloading data: 100%|██████████| 5.29k/5.29k [00:00<00:00, 29.2kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/6.55k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 6.55k/6.55k [00:00<00:00, 32.7kB/s]
Downloading data: 100%|██████████| 6.55k/6.55k [00:00<00:00, 32.6kB/s]
|
|||
|
|
Generating test split: 0%| | 0/100 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 100/100 [00:00<00:00, 21351.58 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/9 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 9/9 [00:00<00:00, 2602.28 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1433.85 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/33.0k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 33.0k/33.0k [00:00<00:00, 169kB/s]
Downloading data: 100%|██████████| 33.0k/33.0k [00:00<00:00, 169kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/7.97k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 7.97k/7.97k [00:00<00:00, 45.9kB/s]
Downloading data: 100%|██████████| 7.97k/7.97k [00:00<00:00, 45.7kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.58k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.58k/4.58k [00:00<00:00, 20.3kB/s]
Downloading data: 100%|██████████| 4.58k/4.58k [00:00<00:00, 20.3kB/s]
|
|||
|
|
Generating test split: 0%| | 0/151 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 151/151 [00:00<00:00, 31551.83 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/17 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 17/17 [00:00<00:00, 4680.53 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1443.23 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/20.1k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 20.1k/20.1k [00:00<00:00, 114kB/s]
Downloading data: 100%|██████████| 20.1k/20.1k [00:00<00:00, 113kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/5.29k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 5.29k/5.29k [00:00<00:00, 26.6kB/s]
Downloading data: 100%|██████████| 5.29k/5.29k [00:00<00:00, 26.5kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/3.51k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 3.51k/3.51k [00:00<00:00, 18.8kB/s]
Downloading data: 100%|██████████| 3.51k/3.51k [00:00<00:00, 18.7kB/s]
|
|||
|
|
Generating test split: 0%| | 0/135 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 135/135 [00:00<00:00, 29283.77 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/14 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 14/14 [00:00<00:00, 3889.27 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1418.72 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/62.7k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 62.7k/62.7k [00:00<00:00, 188kB/s]
Downloading data: 100%|██████████| 62.7k/62.7k [00:00<00:00, 188kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/10.6k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 10.6k/10.6k [00:00<00:00, 68.4kB/s]
Downloading data: 100%|██████████| 10.6k/10.6k [00:00<00:00, 68.1kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.95k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.95k/4.95k [00:00<00:00, 32.1kB/s]
Downloading data: 100%|██████████| 4.95k/4.95k [00:00<00:00, 31.9kB/s]
|
|||
|
|
Generating test split: 0%| | 0/310 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 310/310 [00:00<00:00, 57362.43 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/32 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 32/32 [00:00<00:00, 8539.65 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1407.48 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/58.0k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 58.0k/58.0k [00:00<00:00, 228kB/s]
Downloading data: 100%|██████████| 58.0k/58.0k [00:00<00:00, 227kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/10.9k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 10.9k/10.9k [00:00<00:00, 63.2kB/s]
Downloading data: 100%|██████████| 10.9k/10.9k [00:00<00:00, 62.9kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/6.08k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 6.08k/6.08k [00:00<00:00, 30.0kB/s]
Downloading data: 100%|██████████| 6.08k/6.08k [00:00<00:00, 29.9kB/s]
|
|||
|
|
Generating test split: 0%| | 0/216 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 216/216 [00:00<00:00, 40888.64 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/23 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 23/23 [00:00<00:00, 6212.58 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1404.56 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/41.1k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 41.1k/41.1k [00:00<00:00, 162kB/s]
Downloading data: 100%|██████████| 41.1k/41.1k [00:00<00:00, 161kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/9.39k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 9.39k/9.39k [00:00<00:00, 49.1kB/s]
Downloading data: 100%|██████████| 9.39k/9.39k [00:00<00:00, 48.9kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.56k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.56k/4.56k [00:00<00:00, 30.6kB/s]
Downloading data: 100%|██████████| 4.56k/4.56k [00:00<00:00, 30.5kB/s]
|
|||
|
|
Generating test split: 0%| | 0/378 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 378/378 [00:00<00:00, 93874.53 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/41 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 41/41 [00:00<00:00, 13748.52 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1773.19 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/17.9k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 17.9k/17.9k [00:00<00:00, 78.6kB/s]
Downloading data: 100%|██████████| 17.9k/17.9k [00:00<00:00, 78.3kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.88k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.88k/4.88k [00:00<00:00, 28.9kB/s]
Downloading data: 100%|██████████| 4.88k/4.88k [00:00<00:00, 28.8kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.05k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.05k/4.05k [00:00<00:00, 23.7kB/s]
Downloading data: 100%|██████████| 4.05k/4.05k [00:00<00:00, 23.6kB/s]
|
|||
|
|
Generating test split: 0%| | 0/100 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 100/100 [00:00<00:00, 23777.23 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/8 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 8/8 [00:00<00:00, 2276.27 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1492.42 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/17.6k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 17.6k/17.6k [00:00<00:00, 62.1kB/s]
Downloading data: 100%|██████████| 17.6k/17.6k [00:00<00:00, 61.9kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/5.09k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 5.09k/5.09k [00:00<00:00, 25.8kB/s]
Downloading data: 100%|██████████| 5.09k/5.09k [00:00<00:00, 25.7kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.09k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.09k/4.09k [00:00<00:00, 23.3kB/s]
Downloading data: 100%|██████████| 4.09k/4.09k [00:00<00:00, 23.3kB/s]
|
|||
|
|
Generating test split: 0%| | 0/145 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 145/145 [00:00<00:00, 65741.44 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/16 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 16/16 [00:00<00:00, 9931.75 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 3300.00 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/19.2k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 19.2k/19.2k [00:00<00:00, 125kB/s]
Downloading data: 100%|██████████| 19.2k/19.2k [00:00<00:00, 124kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/6.68k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 6.68k/6.68k [00:00<00:00, 38.0kB/s]
Downloading data: 100%|██████████| 6.68k/6.68k [00:00<00:00, 37.9kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.33k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.33k/4.33k [00:00<00:00, 19.1kB/s]
Downloading data: 100%|██████████| 4.33k/4.33k [00:00<00:00, 19.0kB/s]
|
|||
|
|
Generating test split: 0%| | 0/100 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 100/100 [00:00<00:00, 22889.67 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/11 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 11/11 [00:00<00:00, 2586.46 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1152.66 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/16.6k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 16.6k/16.6k [00:00<00:00, 97.9kB/s]
Downloading data: 100%|██████████| 16.6k/16.6k [00:00<00:00, 97.4kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/5.01k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 5.01k/5.01k [00:00<00:00, 23.7kB/s]
Downloading data: 100%|██████████| 5.01k/5.01k [00:00<00:00, 23.7kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/5.17k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 5.17k/5.17k [00:00<00:00, 24.9kB/s]
Downloading data: 100%|██████████| 5.17k/5.17k [00:00<00:00, 24.8kB/s]
|
|||
|
|
Generating test split: 0%| | 0/100 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 100/100 [00:00<00:00, 22764.20 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/11 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 11/11 [00:00<00:00, 2935.32 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1380.43 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/18.6k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 18.6k/18.6k [00:00<00:00, 86.1kB/s]
Downloading data: 100%|██████████| 18.6k/18.6k [00:00<00:00, 85.8kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/6.40k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 6.40k/6.40k [00:00<00:00, 43.2kB/s]
Downloading data: 100%|██████████| 6.40k/6.40k [00:00<00:00, 42.9kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.52k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.52k/4.52k [00:00<00:00, 27.0kB/s]
Downloading data: 100%|██████████| 4.52k/4.52k [00:00<00:00, 27.0kB/s]
|
|||
|
|
Generating test split: 0%| | 0/102 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 102/102 [00:00<00:00, 23325.83 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/11 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 11/11 [00:00<00:00, 3032.16 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1461.12 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/19.7k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 19.7k/19.7k [00:00<00:00, 99.7kB/s]
Downloading data: 100%|██████████| 19.7k/19.7k [00:00<00:00, 99.3kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/6.18k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 6.18k/6.18k [00:00<00:00, 39.7kB/s]
Downloading data: 100%|██████████| 6.18k/6.18k [00:00<00:00, 39.5kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/5.26k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 5.26k/5.26k [00:00<00:00, 33.9kB/s]
Downloading data: 100%|██████████| 5.26k/5.26k [00:00<00:00, 33.7kB/s]
|
|||
|
|
Generating test split: 0%| | 0/112 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 112/112 [00:00<00:00, 26169.13 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/11 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 11/11 [00:00<00:00, 3088.59 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1453.33 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/31.9k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 31.9k/31.9k [00:00<00:00, 114kB/s]
Downloading data: 100%|██████████| 31.9k/31.9k [00:00<00:00, 113kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/6.91k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 6.91k/6.91k [00:00<00:00, 40.8kB/s]
Downloading data: 100%|██████████| 6.91k/6.91k [00:00<00:00, 40.6kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.28k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.28k/4.28k [00:00<00:00, 24.0kB/s]
Downloading data: 100%|██████████| 4.28k/4.28k [00:00<00:00, 23.9kB/s]
|
|||
|
|
Generating test split: 0%| | 0/144 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 144/144 [00:00<00:00, 29423.67 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/16 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 16/16 [00:00<00:00, 4335.20 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1447.31 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/9.97k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 9.97k/9.97k [00:00<00:00, 53.9kB/s]
Downloading data: 100%|██████████| 9.97k/9.97k [00:00<00:00, 53.6kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/3.74k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 3.74k/3.74k [00:00<00:00, 23.7kB/s]
Downloading data: 100%|██████████| 3.74k/3.74k [00:00<00:00, 23.6kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/3.46k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 3.46k/3.46k [00:00<00:00, 17.4kB/s]
Downloading data: 100%|██████████| 3.46k/3.46k [00:00<00:00, 17.3kB/s]
|
|||
|
|
Generating test split: 0%| | 0/100 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 100/100 [00:00<00:00, 23953.76 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/11 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 11/11 [00:00<00:00, 3229.32 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1531.10 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/25.0k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 25.0k/25.0k [00:00<00:00, 80.5kB/s]
Downloading data: 100%|██████████| 25.0k/25.0k [00:00<00:00, 80.3kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/5.99k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 5.99k/5.99k [00:00<00:00, 32.3kB/s]
Downloading data: 100%|██████████| 5.99k/5.99k [00:00<00:00, 32.1kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/3.97k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 3.97k/3.97k [00:00<00:00, 22.3kB/s]
Downloading data: 100%|██████████| 3.97k/3.97k [00:00<00:00, 22.1kB/s]
|
|||
|
|
Generating test split: 0%| | 0/235 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 235/235 [00:00<00:00, 40091.98 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/26 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 26/26 [00:00<00:00, 5559.05 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1437.59 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/28.3k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 28.3k/28.3k [00:00<00:00, 184kB/s]
Downloading data: 100%|██████████| 28.3k/28.3k [00:00<00:00, 183kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/6.06k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 6.06k/6.06k [00:00<00:00, 37.0kB/s]
Downloading data: 100%|██████████| 6.06k/6.06k [00:00<00:00, 36.8kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.95k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.95k/4.95k [00:00<00:00, 30.8kB/s]
Downloading data: 100%|██████████| 4.95k/4.95k [00:00<00:00, 30.7kB/s]
|
|||
|
|
Generating test split: 0%| | 0/152 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 152/152 [00:00<00:00, 33073.99 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/16 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 16/16 [00:00<00:00, 4049.53 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1471.38 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/33.3k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 33.3k/33.3k [00:00<00:00, 205kB/s]
Downloading data: 100%|██████████| 33.3k/33.3k [00:00<00:00, 204kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/8.32k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 8.32k/8.32k [00:00<00:00, 47.9kB/s]
Downloading data: 100%|██████████| 8.32k/8.32k [00:00<00:00, 47.7kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.17k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.17k/4.17k [00:00<00:00, 22.2kB/s]
Downloading data: 100%|██████████| 4.17k/4.17k [00:00<00:00, 22.1kB/s]
|
|||
|
|
Generating test split: 0%| | 0/203 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 203/203 [00:00<00:00, 43529.84 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/22 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 22/22 [00:00<00:00, 6237.73 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1426.25 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/33.7k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 33.7k/33.7k [00:00<00:00, 141kB/s]
Downloading data: 100%|██████████| 33.7k/33.7k [00:00<00:00, 141kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/7.00k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 7.00k/7.00k [00:00<00:00, 45.9kB/s]
Downloading data: 100%|██████████| 7.00k/7.00k [00:00<00:00, 45.7kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.51k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.51k/4.51k [00:00<00:00, 25.9kB/s]
Downloading data: 100%|██████████| 4.51k/4.51k [00:00<00:00, 25.8kB/s]
|
|||
|
|
Generating test split: 0%| | 0/270 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 270/270 [00:00<00:00, 58942.49 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/29 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 29/29 [00:00<00:00, 8303.28 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1511.35 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/21.6k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 21.6k/21.6k [00:00<00:00, 117kB/s]
Downloading data: 100%|██████████| 21.6k/21.6k [00:00<00:00, 117kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/5.10k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 5.10k/5.10k [00:00<00:00, 24.9kB/s]
Downloading data: 100%|██████████| 5.10k/5.10k [00:00<00:00, 24.8kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.97k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.97k/4.97k [00:00<00:00, 25.0kB/s]
Downloading data: 100%|██████████| 4.97k/4.97k [00:00<00:00, 23.2kB/s]
|
|||
|
|
Generating test split: 0%| | 0/100 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 100/100 [00:00<00:00, 16317.07 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/11 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 11/11 [00:00<00:00, 2295.28 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1094.20 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/31.3k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 31.3k/31.3k [00:00<00:00, 207kB/s]
Downloading data: 100%|██████████| 31.3k/31.3k [00:00<00:00, 33.1kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/6.29k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 6.29k/6.29k [00:00<00:00, 28.8kB/s]
Downloading data: 100%|██████████| 6.29k/6.29k [00:00<00:00, 28.7kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/3.68k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 3.68k/3.68k [00:00<00:00, 24.1kB/s]
Downloading data: 100%|██████████| 3.68k/3.68k [00:00<00:00, 9.95kB/s]
|
|||
|
|
Generating test split: 0%| | 0/223 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 223/223 [00:00<00:00, 29976.60 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/23 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 23/23 [00:00<00:00, 4815.98 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1464.80 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/125k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 125k/125k [00:00<00:00, 579kB/s]
Downloading data: 100%|██████████| 125k/125k [00:00<00:00, 576kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/19.9k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 19.9k/19.9k [00:00<00:00, 50.6kB/s]
Downloading data: 100%|██████████| 19.9k/19.9k [00:00<00:00, 50.5kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/8.45k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 8.45k/8.45k [00:00<00:00, 45.5kB/s]
Downloading data: 100%|██████████| 8.45k/8.45k [00:00<00:00, 45.4kB/s]
|
|||
|
|
Generating test split: 0%| | 0/272 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 272/272 [00:00<00:00, 38032.16 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/31 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 31/31 [00:00<00:00, 8119.36 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1512.99 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/98.6k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 98.6k/98.6k [00:00<00:00, 354kB/s]
Downloading data: 100%|██████████| 98.6k/98.6k [00:00<00:00, 352kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/13.2k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 13.2k/13.2k [00:00<00:00, 79.1kB/s]
Downloading data: 100%|██████████| 13.2k/13.2k [00:00<00:00, 78.7kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/3.38k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 3.38k/3.38k [00:00<00:00, 22.7kB/s]
Downloading data: 100%|██████████| 3.38k/3.38k [00:00<00:00, 22.6kB/s]
|
|||
|
|
Generating test split: 0%| | 0/783 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 783/783 [00:00<00:00, 133615.69 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/86 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 86/86 [00:00<00:00, 23439.48 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1474.48 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/11.5k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 11.5k/11.5k [00:00<00:00, 58.1kB/s]
Downloading data: 100%|██████████| 11.5k/11.5k [00:00<00:00, 57.9kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.20k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.20k/4.20k [00:00<00:00, 20.9kB/s]
Downloading data: 100%|██████████| 4.20k/4.20k [00:00<00:00, 20.9kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/3.58k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 3.58k/3.58k [00:00<00:00, 19.9kB/s]
Downloading data: 100%|██████████| 3.58k/3.58k [00:00<00:00, 19.8kB/s]
|
|||
|
|
Generating test split: 0%| | 0/100 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 100/100 [00:00<00:00, 23388.75 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/10 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 10/10 [00:00<00:00, 2950.20 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1453.73 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/16.4k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 16.4k/16.4k [00:00<00:00, 111kB/s]
Downloading data: 100%|██████████| 16.4k/16.4k [00:00<00:00, 110kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/5.64k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 5.64k/5.64k [00:00<00:00, 36.0kB/s]
Downloading data: 100%|██████████| 5.64k/5.64k [00:00<00:00, 35.8kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/3.77k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 3.77k/3.77k [00:00<00:00, 21.6kB/s]
Downloading data: 100%|██████████| 3.77k/3.77k [00:00<00:00, 21.5kB/s]
|
|||
|
|
Generating test split: 0%| | 0/100 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 100/100 [00:00<00:00, 23974.30 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/11 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 11/11 [00:00<00:00, 3158.36 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1507.33 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/55.0k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 55.0k/55.0k [00:00<00:00, 177kB/s]
Downloading data: 100%|██████████| 55.0k/55.0k [00:00<00:00, 177kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/9.03k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 9.03k/9.03k [00:00<00:00, 49.0kB/s]
Downloading data: 100%|██████████| 9.03k/9.03k [00:00<00:00, 48.8kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/5.00k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 5.00k/5.00k [00:00<00:00, 33.2kB/s]
Downloading data: 100%|██████████| 5.00k/5.00k [00:00<00:00, 33.0kB/s]
|
|||
|
|
Generating test split: 0%| | 0/306 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 306/306 [00:00<00:00, 61330.20 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/33 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 33/33 [00:00<00:00, 8907.40 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1145.17 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/37.3k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 37.3k/37.3k [00:00<00:00, 127kB/s]
Downloading data: 100%|██████████| 37.3k/37.3k [00:00<00:00, 126kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/8.21k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 8.21k/8.21k [00:00<00:00, 45.1kB/s]
Downloading data: 100%|██████████| 8.21k/8.21k [00:00<00:00, 44.8kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.29k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.29k/4.29k [00:00<00:00, 21.2kB/s]
Downloading data: 100%|██████████| 4.29k/4.29k [00:00<00:00, 21.1kB/s]
|
|||
|
|
Generating test split: 0%| | 0/234 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 234/234 [00:00<00:00, 83380.10 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/25 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 25/25 [00:00<00:00, 13910.53 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 3707.18 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/27.3k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 27.3k/27.3k [00:00<00:00, 151kB/s]
Downloading data: 100%|██████████| 27.3k/27.3k [00:00<00:00, 150kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/7.06k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 7.06k/7.06k [00:00<00:00, 44.9kB/s]
Downloading data: 100%|██████████| 7.06k/7.06k [00:00<00:00, 44.7kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/3.88k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 3.88k/3.88k [00:00<00:00, 20.0kB/s]
Downloading data: 100%|██████████| 3.88k/3.88k [00:00<00:00, 20.0kB/s]
|
|||
|
|
Generating test split: 0%| | 0/166 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 166/166 [00:00<00:00, 36297.28 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/18 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 18/18 [00:00<00:00, 4865.15 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1149.00 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/40.5k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 40.5k/40.5k [00:00<00:00, 92.6kB/s]
Downloading data: 100%|██████████| 40.5k/40.5k [00:00<00:00, 92.4kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/7.49k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 7.49k/7.49k [00:00<00:00, 45.3kB/s]
Downloading data: 100%|██████████| 7.49k/7.49k [00:00<00:00, 45.1kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/3.68k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 3.68k/3.68k [00:00<00:00, 12.0kB/s]
Downloading data: 100%|██████████| 3.68k/3.68k [00:00<00:00, 12.0kB/s]
|
|||
|
|
Generating test split: 0%| | 0/265 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 265/265 [00:00<00:00, 41591.47 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/29 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 29/29 [00:00<00:00, 5720.76 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1038.25 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/42.5k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 42.5k/42.5k [00:00<00:00, 128kB/s]
Downloading data: 100%|██████████| 42.5k/42.5k [00:00<00:00, 127kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/9.00k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 9.00k/9.00k [00:00<00:00, 52.1kB/s]
Downloading data: 100%|██████████| 9.00k/9.00k [00:00<00:00, 51.9kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.85k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.85k/4.85k [00:00<00:00, 20.3kB/s]
Downloading data: 100%|██████████| 4.85k/4.85k [00:00<00:00, 20.2kB/s]
|
|||
|
|
Generating test split: 0%| | 0/173 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 173/173 [00:00<00:00, 35646.23 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/22 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 22/22 [00:00<00:00, 5842.02 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1511.79 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/69.5k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 69.5k/69.5k [00:00<00:00, 310kB/s]
Downloading data: 100%|██████████| 69.5k/69.5k [00:00<00:00, 309kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/12.9k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 12.9k/12.9k [00:00<00:00, 68.5kB/s]
Downloading data: 100%|██████████| 12.9k/12.9k [00:00<00:00, 68.2kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.90k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.90k/4.90k [00:00<00:00, 24.9kB/s]
Downloading data: 100%|██████████| 4.90k/4.90k [00:00<00:00, 24.9kB/s]
|
|||
|
|
Generating test split: 0%| | 0/282 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 282/282 [00:00<00:00, 101693.21 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/31 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 31/31 [00:00<00:00, 24789.98 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 4920.58 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/14.7k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 14.7k/14.7k [00:00<00:00, 62.0kB/s]
Downloading data: 100%|██████████| 14.7k/14.7k [00:00<00:00, 61.8kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.51k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.51k/4.51k [00:00<00:00, 28.5kB/s]
Downloading data: 100%|██████████| 4.51k/4.51k [00:00<00:00, 28.4kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/3.62k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 3.62k/3.62k [00:00<00:00, 14.1kB/s]
Downloading data: 100%|██████████| 3.62k/3.62k [00:00<00:00, 14.1kB/s]
|
|||
|
|
Generating test split: 0%| | 0/103 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 103/103 [00:00<00:00, 23392.53 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/11 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 11/11 [00:00<00:00, 2595.49 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1474.58 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/38.8k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 38.8k/38.8k [00:00<00:00, 247kB/s]
Downloading data: 100%|██████████| 38.8k/38.8k [00:00<00:00, 246kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/7.23k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 7.23k/7.23k [00:00<00:00, 49.0kB/s]
Downloading data: 100%|██████████| 7.23k/7.23k [00:00<00:00, 48.8kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/3.84k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 3.84k/3.84k [00:00<00:00, 20.3kB/s]
Downloading data: 100%|██████████| 3.84k/3.84k [00:00<00:00, 20.2kB/s]
|
|||
|
|
Generating test split: 0%| | 0/238 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 238/238 [00:00<00:00, 65475.82 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/26 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 26/26 [00:00<00:00, 10087.12 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 2152.47 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/28.2k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 28.2k/28.2k [00:00<00:00, 185kB/s]
Downloading data: 100%|██████████| 28.2k/28.2k [00:00<00:00, 184kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/6.17k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 6.17k/6.17k [00:00<00:00, 43.4kB/s]
Downloading data: 100%|██████████| 6.17k/6.17k [00:00<00:00, 43.1kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/3.94k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 3.94k/3.94k [00:00<00:00, 21.2kB/s]
Downloading data: 100%|██████████| 3.94k/3.94k [00:00<00:00, 21.1kB/s]
|
|||
|
|
Generating test split: 0%| | 0/198 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 198/198 [00:00<00:00, 45129.45 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/22 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 22/22 [00:00<00:00, 6079.50 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1430.62 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/43.9k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 43.9k/43.9k [00:00<00:00, 165kB/s]
Downloading data: 100%|██████████| 43.9k/43.9k [00:00<00:00, 165kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/8.36k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 8.36k/8.36k [00:00<00:00, 45.4kB/s]
Downloading data: 100%|██████████| 8.36k/8.36k [00:00<00:00, 45.2kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.21k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.21k/4.21k [00:00<00:00, 25.5kB/s]
Downloading data: 100%|██████████| 4.21k/4.21k [00:00<00:00, 25.4kB/s]
|
|||
|
|
Generating test split: 0%| | 0/201 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 201/201 [00:00<00:00, 43156.14 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/22 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 22/22 [00:00<00:00, 6164.39 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1484.92 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/20.6k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 20.6k/20.6k [00:00<00:00, 121kB/s]
Downloading data: 100%|██████████| 20.6k/20.6k [00:00<00:00, 120kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/6.46k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 6.46k/6.46k [00:00<00:00, 42.9kB/s]
Downloading data: 100%|██████████| 6.46k/6.46k [00:00<00:00, 42.7kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.44k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.44k/4.44k [00:00<00:00, 23.0kB/s]
Downloading data: 100%|██████████| 4.44k/4.44k [00:00<00:00, 22.9kB/s]
|
|||
|
|
Generating test split: 0%| | 0/110 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 110/110 [00:00<00:00, 25973.85 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/12 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 12/12 [00:00<00:00, 3513.55 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1450.41 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/24.5k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 24.5k/24.5k [00:00<00:00, 145kB/s]
Downloading data: 100%|██████████| 24.5k/24.5k [00:00<00:00, 144kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/7.03k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 7.03k/7.03k [00:00<00:00, 44.5kB/s]
Downloading data: 100%|██████████| 7.03k/7.03k [00:00<00:00, 44.2kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.55k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.55k/4.55k [00:00<00:00, 24.3kB/s]
Downloading data: 100%|██████████| 4.55k/4.55k [00:00<00:00, 24.2kB/s]
|
|||
|
|
Generating test split: 0%| | 0/114 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 114/114 [00:00<00:00, 26500.62 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/12 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 12/12 [00:00<00:00, 3362.62 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1185.70 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/23.2k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 23.2k/23.2k [00:00<00:00, 150kB/s]
Downloading data: 100%|██████████| 23.2k/23.2k [00:00<00:00, 149kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/5.27k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 5.27k/5.27k [00:00<00:00, 27.5kB/s]
Downloading data: 100%|██████████| 5.27k/5.27k [00:00<00:00, 27.4kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.09k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.09k/4.09k [00:00<00:00, 23.6kB/s]
Downloading data: 100%|██████████| 4.09k/4.09k [00:00<00:00, 23.4kB/s]
|
|||
|
|
Generating test split: 0%| | 0/131 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 131/131 [00:00<00:00, 30259.60 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/12 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 12/12 [00:00<00:00, 3249.09 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1476.97 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/40.2k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 40.2k/40.2k [00:00<00:00, 153kB/s]
Downloading data: 100%|██████████| 40.2k/40.2k [00:00<00:00, 152kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/8.28k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 8.28k/8.28k [00:00<00:00, 46.3kB/s]
Downloading data: 100%|██████████| 8.28k/8.28k [00:00<00:00, 46.0kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.48k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.48k/4.48k [00:00<00:00, 24.3kB/s]
Downloading data: 100%|██████████| 4.48k/4.48k [00:00<00:00, 24.2kB/s]
|
|||
|
|
Generating test split: 0%| | 0/193 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 193/193 [00:00<00:00, 38922.04 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/21 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 21/21 [00:00<00:00, 5407.69 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1403.90 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/19.5k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 19.5k/19.5k [00:00<00:00, 72.0kB/s]
Downloading data: 100%|██████████| 19.5k/19.5k [00:00<00:00, 71.7kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/5.28k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 5.28k/5.28k [00:00<00:00, 29.5kB/s]
Downloading data: 100%|██████████| 5.28k/5.28k [00:00<00:00, 29.4kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.23k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.23k/4.23k [00:00<00:00, 19.7kB/s]
Downloading data: 100%|██████████| 4.23k/4.23k [00:00<00:00, 19.6kB/s]
|
|||
|
|
Generating test split: 0%| | 0/100 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 100/100 [00:00<00:00, 23153.76 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/11 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 11/11 [00:00<00:00, 3009.42 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1420.55 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/54.8k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 54.8k/54.8k [00:00<00:00, 300kB/s]
Downloading data: 100%|██████████| 54.8k/54.8k [00:00<00:00, 299kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/9.90k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 9.90k/9.90k [00:00<00:00, 55.0kB/s]
Downloading data: 100%|██████████| 9.90k/9.90k [00:00<00:00, 54.8kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.05k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.05k/4.05k [00:00<00:00, 23.8kB/s]
Downloading data: 100%|██████████| 4.05k/4.05k [00:00<00:00, 23.7kB/s]
|
|||
|
|
Generating test split: 0%| | 0/390 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 390/390 [00:00<00:00, 71154.84 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/43 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 43/43 [00:00<00:00, 11381.74 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1467.57 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/114k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 114k/114k [00:00<00:00, 569kB/s]
Downloading data: 100%|██████████| 114k/114k [00:00<00:00, 566kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/18.7k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 18.7k/18.7k [00:00<00:00, 108kB/s]
Downloading data: 100%|██████████| 18.7k/18.7k [00:00<00:00, 107kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/7.50k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 7.50k/7.50k [00:00<00:00, 48.2kB/s]
Downloading data: 100%|██████████| 7.50k/7.50k [00:00<00:00, 48.0kB/s]
|
|||
|
|
Generating test split: 0%| | 0/245 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 245/245 [00:00<00:00, 34778.64 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/27 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 27/27 [00:00<00:00, 6653.32 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1449.21 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/92.8k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 92.8k/92.8k [00:00<00:00, 482kB/s]
Downloading data: 100%|██████████| 92.8k/92.8k [00:00<00:00, 479kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/15.2k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 15.2k/15.2k [00:00<00:00, 93.6kB/s]
Downloading data: 100%|██████████| 15.2k/15.2k [00:00<00:00, 93.2kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/5.19k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 5.19k/5.19k [00:00<00:00, 29.7kB/s]
Downloading data: 100%|██████████| 5.19k/5.19k [00:00<00:00, 29.6kB/s]
|
|||
|
|
Generating test split: 0%| | 0/545 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 545/545 [00:00<00:00, 103546.64 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/60 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 60/60 [00:00<00:00, 17010.83 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1536.49 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/133k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 133k/133k [00:00<00:00, 423kB/s]
Downloading data: 100%|██████████| 133k/133k [00:00<00:00, 422kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/22.1k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 22.1k/22.1k [00:00<00:00, 123kB/s]
Downloading data: 100%|██████████| 22.1k/22.1k [00:00<00:00, 122kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.70k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.70k/4.70k [00:00<00:00, 24.6kB/s]
Downloading data: 100%|██████████| 4.70k/4.70k [00:00<00:00, 24.5kB/s]
|
|||
|
|
Generating test split: 0%| | 0/612 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 612/612 [00:00<00:00, 89912.57 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/69 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 69/69 [00:00<00:00, 15196.75 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1459.50 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/60.9k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 60.9k/60.9k [00:00<00:00, 262kB/s]
Downloading data: 100%|██████████| 60.9k/60.9k [00:00<00:00, 261kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/10.7k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 10.7k/10.7k [00:00<00:00, 37.0kB/s]
Downloading data: 100%|██████████| 10.7k/10.7k [00:00<00:00, 36.9kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.42k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.42k/4.42k [00:00<00:00, 27.5kB/s]
Downloading data: 100%|██████████| 4.42k/4.42k [00:00<00:00, 27.4kB/s]
|
|||
|
|
Generating test split: 0%| | 0/346 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 346/346 [00:00<00:00, 68005.12 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/38 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 38/38 [00:00<00:00, 10576.92 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1367.92 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/48.6k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 48.6k/48.6k [00:00<00:00, 196kB/s]
Downloading data: 100%|██████████| 48.6k/48.6k [00:00<00:00, 196kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/9.16k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 9.16k/9.16k [00:00<00:00, 47.8kB/s]
Downloading data: 100%|██████████| 9.16k/9.16k [00:00<00:00, 47.6kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.21k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.21k/4.21k [00:00<00:00, 21.6kB/s]
Downloading data: 100%|██████████| 4.21k/4.21k [00:00<00:00, 21.5kB/s]
|
|||
|
|
Generating test split: 0%| | 0/311 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 311/311 [00:00<00:00, 125257.21 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/34 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 34/34 [00:00<00:00, 20664.59 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 3443.60 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/155k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 155k/155k [00:00<00:00, 492kB/s]
Downloading data: 100%|██████████| 155k/155k [00:00<00:00, 491kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/27.3k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 27.3k/27.3k [00:00<00:00, 144kB/s]
Downloading data: 100%|██████████| 27.3k/27.3k [00:00<00:00, 143kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/17.8k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 17.8k/17.8k [00:00<00:00, 89.9kB/s]
Downloading data: 100%|██████████| 17.8k/17.8k [00:00<00:00, 89.5kB/s]
|
|||
|
|
Generating test split: 0%| | 0/204 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 204/204 [00:00<00:00, 24456.58 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/22 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 22/22 [00:00<00:00, 4582.80 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1051.68 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/142k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 142k/142k [00:00<00:00, 436kB/s]
Downloading data: 100%|██████████| 142k/142k [00:00<00:00, 434kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/31.6k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 31.6k/31.6k [00:00<00:00, 182kB/s]
Downloading data: 100%|██████████| 31.6k/31.6k [00:00<00:00, 181kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/22.2k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 22.2k/22.2k [00:00<00:00, 122kB/s]
Downloading data: 100%|██████████| 22.2k/22.2k [00:00<00:00, 122kB/s]
|
|||
|
|
Generating test split: 0%| | 0/165 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 165/165 [00:00<00:00, 32232.32 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/18 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 18/18 [00:00<00:00, 5022.12 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1510.05 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/21.5k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 21.5k/21.5k [00:00<00:00, 141kB/s]
Downloading data: 100%|██████████| 21.5k/21.5k [00:00<00:00, 140kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/6.57k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 6.57k/6.57k [00:00<00:00, 43.0kB/s]
Downloading data: 100%|██████████| 6.57k/6.57k [00:00<00:00, 42.8kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.82k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.82k/4.82k [00:00<00:00, 27.2kB/s]
Downloading data: 100%|██████████| 4.82k/4.82k [00:00<00:00, 27.1kB/s]
|
|||
|
|
Generating test split: 0%| | 0/126 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 126/126 [00:00<00:00, 27542.33 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/14 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 14/14 [00:00<00:00, 4034.65 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1424.60 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/54.3k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 54.3k/54.3k [00:00<00:00, 179kB/s]
Downloading data: 100%|██████████| 54.3k/54.3k [00:00<00:00, 179kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/9.90k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 9.90k/9.90k [00:00<00:00, 45.0kB/s]
Downloading data: 100%|██████████| 9.90k/9.90k [00:00<00:00, 44.9kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.62k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.62k/4.62k [00:00<00:00, 24.4kB/s]
Downloading data: 100%|██████████| 4.62k/4.62k [00:00<00:00, 24.3kB/s]
|
|||
|
|
Generating test split: 0%| | 0/324 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 324/324 [00:00<00:00, 65971.87 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/35 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 35/35 [00:00<00:00, 9628.17 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1419.20 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/23.0k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 23.0k/23.0k [00:00<00:00, 116kB/s]
Downloading data: 100%|██████████| 23.0k/23.0k [00:00<00:00, 116kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/6.53k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 6.53k/6.53k [00:00<00:00, 33.4kB/s]
Downloading data: 100%|██████████| 6.53k/6.53k [00:00<00:00, 33.2kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.13k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.13k/4.13k [00:00<00:00, 22.2kB/s]
Downloading data: 100%|██████████| 4.13k/4.13k [00:00<00:00, 22.1kB/s]
|
|||
|
|
Generating test split: 0%| | 0/163 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 163/163 [00:00<00:00, 37434.79 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/18 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 18/18 [00:00<00:00, 5239.97 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1525.20 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/18.9k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 18.9k/18.9k [00:00<00:00, 95.4kB/s]
Downloading data: 100%|██████████| 18.9k/18.9k [00:00<00:00, 95.0kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.95k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.95k/4.95k [00:00<00:00, 31.5kB/s]
Downloading data: 100%|██████████| 4.95k/4.95k [00:00<00:00, 31.3kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/3.31k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 3.31k/3.31k [00:00<00:00, 21.5kB/s]
Downloading data: 100%|██████████| 3.31k/3.31k [00:00<00:00, 21.4kB/s]
|
|||
|
|
Generating test split: 0%| | 0/171 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 171/171 [00:00<00:00, 38413.90 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/19 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 19/19 [00:00<00:00, 5325.57 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1429.75 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/202k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 202k/202k [00:00<00:00, 658kB/s]
Downloading data: 100%|██████████| 202k/202k [00:00<00:00, 656kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/38.5k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 38.5k/38.5k [00:00<00:00, 228kB/s]
Downloading data: 100%|██████████| 38.5k/38.5k [00:00<00:00, 227kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/10.3k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 10.3k/10.3k [00:00<00:00, 51.8kB/s]
Downloading data: 100%|██████████| 10.3k/10.3k [00:00<00:00, 51.6kB/s]
|
|||
|
|
Generating test split: 0%| | 0/237 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 237/237 [00:00<00:00, 29773.57 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/26 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 26/26 [00:00<00:00, 6390.38 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1454.13 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/1.04M [00:00<?, ?B/s]
Downloading data: 100%|██████████| 1.04M/1.04M [00:00<00:00, 2.16MB/s]
Downloading data: 100%|██████████| 1.04M/1.04M [00:00<00:00, 2.14MB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/116k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 116k/116k [00:00<00:00, 291kB/s]
Downloading data: 100%|██████████| 116k/116k [00:00<00:00, 290kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/15.1k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 15.1k/15.1k [00:00<00:00, 80.7kB/s]
Downloading data: 100%|██████████| 15.1k/15.1k [00:00<00:00, 80.3kB/s]
|
|||
|
|
Generating test split: 0%| | 0/1534 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 1534/1534 [00:00<00:00, 64297.54 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/170 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 170/170 [00:00<00:00, 31582.22 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1430.82 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/23.3k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 23.3k/23.3k [00:00<00:00, 151kB/s]
Downloading data: 100%|██████████| 23.3k/23.3k [00:00<00:00, 150kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/6.22k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 6.22k/6.22k [00:00<00:00, 36.5kB/s]
Downloading data: 100%|██████████| 6.22k/6.22k [00:00<00:00, 36.3kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.06k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.06k/4.06k [00:00<00:00, 23.7kB/s]
Downloading data: 100%|██████████| 4.06k/4.06k [00:00<00:00, 23.6kB/s]
|
|||
|
|
Generating test split: 0%| | 0/108 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 108/108 [00:00<00:00, 24343.55 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/11 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 11/11 [00:00<00:00, 2509.10 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1404.37 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/89.8k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 89.8k/89.8k [00:00<00:00, 270kB/s]
Downloading data: 100%|██████████| 89.8k/89.8k [00:00<00:00, 269kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/14.9k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 14.9k/14.9k [00:00<00:00, 82.9kB/s]
Downloading data: 100%|██████████| 14.9k/14.9k [00:00<00:00, 82.5kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/5.15k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 5.15k/5.15k [00:00<00:00, 32.6kB/s]
Downloading data: 100%|██████████| 5.15k/5.15k [00:00<00:00, 32.5kB/s]
|
|||
|
|
Generating test split: 0%| | 0/895 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 895/895 [00:00<00:00, 124942.66 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/100 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 100/100 [00:00<00:00, 22618.12 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1493.59 examples/s]
|
|||
|
|
Downloading data: 0%| | 0.00/29.5k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 29.5k/29.5k [00:00<00:00, 130kB/s]
Downloading data: 100%|██████████| 29.5k/29.5k [00:00<00:00, 130kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/7.13k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 7.13k/7.13k [00:00<00:00, 42.8kB/s]
Downloading data: 100%|██████████| 7.13k/7.13k [00:00<00:00, 42.5kB/s]
|
|||
|
|
Downloading data: 0%| | 0.00/4.97k [00:00<?, ?B/s]
Downloading data: 100%|██████████| 4.97k/4.97k [00:00<00:00, 15.7kB/s]
Downloading data: 100%|██████████| 4.97k/4.97k [00:00<00:00, 15.7kB/s]
|
|||
|
|
Generating test split: 0%| | 0/121 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 121/121 [00:00<00:00, 28924.59 examples/s]
|
|||
|
|
Generating validation split: 0%| | 0/13 [00:00<?, ? examples/s]
Generating validation split: 100%|██████████| 13/13 [00:00<00:00, 3605.50 examples/s]
|
|||
|
|
Generating dev split: 0%| | 0/5 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 5/5 [00:00<00:00, 1468.08 examples/s]
|
|||
|
|
2026-08-09:23:23:23,100 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_international_law from None to 5
|
|||
|
|
2026-08-09:23:23:23,101 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_moral_scenarios from None to 5
|
|||
|
|
2026-08-09:23:23:23,101 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_jurisprudence from None to 5
|
|||
|
|
2026-08-09:23:23:23,101 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_professional_law from None to 5
|
|||
|
|
2026-08-09:23:23:23,101 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_high_school_world_history from None to 5
|
|||
|
|
2026-08-09:23:23:23,101 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_world_religions from None to 5
|
|||
|
|
2026-08-09:23:23:23,101 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_logical_fallacies from None to 5
|
|||
|
|
2026-08-09:23:23:23,101 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_prehistory from None to 5
|
|||
|
|
2026-08-09:23:23:23,101 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_formal_logic from None to 5
|
|||
|
|
2026-08-09:23:23:23,101 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_high_school_european_history from None to 5
|
|||
|
|
2026-08-09:23:23:23,101 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_high_school_us_history from None to 5
|
|||
|
|
2026-08-09:23:23:23,101 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_philosophy from None to 5
|
|||
|
|
2026-08-09:23:23:23,102 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_moral_disputes from None to 5
|
|||
|
|
2026-08-09:23:23:23,102 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_professional_psychology from None to 5
|
|||
|
|
2026-08-09:23:23:23,102 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_high_school_psychology from None to 5
|
|||
|
|
2026-08-09:23:23:23,102 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_security_studies from None to 5
|
|||
|
|
2026-08-09:23:23:23,102 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_high_school_macroeconomics from None to 5
|
|||
|
|
2026-08-09:23:23:23,102 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_us_foreign_policy from None to 5
|
|||
|
|
2026-08-09:23:23:23,102 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_high_school_government_and_politics from None to 5
|
|||
|
|
2026-08-09:23:23:23,102 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_human_sexuality from None to 5
|
|||
|
|
2026-08-09:23:23:23,102 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_econometrics from None to 5
|
|||
|
|
2026-08-09:23:23:23,102 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_public_relations from None to 5
|
|||
|
|
2026-08-09:23:23:23,102 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_sociology from None to 5
|
|||
|
|
2026-08-09:23:23:23,102 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_high_school_geography from None to 5
|
|||
|
|
2026-08-09:23:23:23,102 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_high_school_microeconomics from None to 5
|
|||
|
|
2026-08-09:23:23:23,103 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_management from None to 5
|
|||
|
|
2026-08-09:23:23:23,103 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_professional_accounting from None to 5
|
|||
|
|
2026-08-09:23:23:23,103 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_college_medicine from None to 5
|
|||
|
|
2026-08-09:23:23:23,103 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_clinical_knowledge from None to 5
|
|||
|
|
2026-08-09:23:23:23,103 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_virology from None to 5
|
|||
|
|
2026-08-09:23:23:23,103 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_marketing from None to 5
|
|||
|
|
2026-08-09:23:23:23,103 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_nutrition from None to 5
|
|||
|
|
2026-08-09:23:23:23,103 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_medical_genetics from None to 5
|
|||
|
|
2026-08-09:23:23:23,103 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_global_facts from None to 5
|
|||
|
|
2026-08-09:23:23:23,103 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_miscellaneous from None to 5
|
|||
|
|
2026-08-09:23:23:23,103 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_professional_medicine from None to 5
|
|||
|
|
2026-08-09:23:23:23,103 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_human_aging from None to 5
|
|||
|
|
2026-08-09:23:23:23,103 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_business_ethics from None to 5
|
|||
|
|
2026-08-09:23:23:23,103 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_high_school_mathematics from None to 5
|
|||
|
|
2026-08-09:23:23:23,103 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_high_school_chemistry from None to 5
|
|||
|
|
2026-08-09:23:23:23,103 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_astronomy from None to 5
|
|||
|
|
2026-08-09:23:23:23,104 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_conceptual_physics from None to 5
|
|||
|
|
2026-08-09:23:23:23,104 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_abstract_algebra from None to 5
|
|||
|
|
2026-08-09:23:23:23,104 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_college_biology from None to 5
|
|||
|
|
2026-08-09:23:23:23,104 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_machine_learning from None to 5
|
|||
|
|
2026-08-09:23:23:23,104 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_college_physics from None to 5
|
|||
|
|
2026-08-09:23:23:23,104 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_college_mathematics from None to 5
|
|||
|
|
2026-08-09:23:23:23,104 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_computer_security from None to 5
|
|||
|
|
2026-08-09:23:23:23,104 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_electrical_engineering from None to 5
|
|||
|
|
2026-08-09:23:23:23,104 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_college_chemistry from None to 5
|
|||
|
|
2026-08-09:23:23:23,104 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_elementary_mathematics from None to 5
|
|||
|
|
2026-08-09:23:23:23,104 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_high_school_statistics from None to 5
|
|||
|
|
2026-08-09:23:23:23,104 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_high_school_biology from None to 5
|
|||
|
|
2026-08-09:23:23:23,104 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_anatomy from None to 5
|
|||
|
|
2026-08-09:23:23:23,105 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_high_school_physics from None to 5
|
|||
|
|
2026-08-09:23:23:23,105 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_high_school_computer_science from None to 5
|
|||
|
|
2026-08-09:23:23:23,105 WARNING [evaluator.py:222] Overwriting default num_fewshot of mmlu_college_computer_science from None to 5
|
|||
|
|
2026-08-09:23:23:23,109 INFO [task.py:395] Building contexts for mmlu_international_law on rank 0...
|
|||
|
|
0%| | 0/121 [00:00<?, ?it/s]
7%|▋ | 8/121 [00:00<00:01, 76.34it/s]
16%|█▌ | 19/121 [00:00<00:01, 92.08it/s]
25%|██▍ | 30/121 [00:00<00:00, 97.71it/s]
34%|███▍ | 41/121 [00:00<00:00, 100.76it/s]
43%|████▎ | 52/121 [00:00<00:00, 102.68it/s]
52%|█████▏ | 63/121 [00:00<00:00, 103.81it/s]
61%|██████ | 74/121 [00:00<00:00, 104.38it/s]
70%|███████ | 85/121 [00:00<00:00, 104.72it/s]
79%|███████▉ | 96/121 [00:00<00:00, 104.62it/s]
88%|████████▊ | 107/121 [00:01<00:00, 104.86it/s]
98%|█████████▊| 118/121 [00:01<00:00, 104.82it/s]
100%|██████████| 121/121 [00:01<00:00, 102.47it/s]
|
|||
|
|
2026-08-09:23:23:24,300 INFO [task.py:395] Building contexts for mmlu_moral_scenarios on rank 0...
|
|||
|
|
0%| | 0/895 [00:00<?, ?it/s]
1%| | 11/895 [00:00<00:08, 105.72it/s]
2%|▏ | 22/895 [00:00<00:08, 105.67it/s]
4%|▎ | 33/895 [00:00<00:08, 105.93it/s]
5%|▍ | 44/895 [00:00<00:08, 106.05it/s]
6%|▌ | 55/895 [00:00<00:07, 106.15it/s]
7%|▋ | 66/895 [00:00<00:07, 106.34it/s]
9%|▊ | 77/895 [00:00<00:07, 105.89it/s]
10%|▉ | 88/895 [00:00<00:07, 105.88it/s]
11%|█ | 99/895 [00:00<00:07, 105.94it/s]
12%|█▏ | 110/895 [00:01<00:07, 105.77it/s]
14%|█▎ | 121/895 [00:01<00:07, 105.83it/s]
15%|█▍ | 132/895 [00:01<00:07, 105.95it/s]
16%|█▌ | 143/895 [00:01<00:07, 106.06it/s]
17%|█▋ | 154/895 [00:01<00:06, 106.20it/s]
18%|█▊ | 165/895 [00:01<00:06, 106.21it/s]
20%|█▉ | 176/895 [00:01<00:06, 106.11it/s]
21%|██ | 187/895 [00:01<00:06, 106.13it/s]
22%|██▏ | 198/895 [00:01<00:06, 105.54it/s]
23%|██▎ | 209/895 [00:01<00:06, 105.44it/s]
25%|██▍ | 220/895 [00:02<00:06, 105.52it/s]
26%|██▌ | 231/895 [00:02<00:06, 105.79it/s]
27%|██▋ | 242/895 [00:02<00:06, 105.94it/s]
28%|██▊ | 253/895 [00:02<00:06, 105.79it/s]
29%|██▉ | 264/895 [00:02<00:05, 106.09it/s]
31%|███ | 275/895 [00:02<00:05, 106.26it/s]
32%|███▏ | 286/895 [00:02<00:05, 106.44it/s]
33%|███▎ | 297/895 [00:02<00:05, 106.23it/s]
34%|███▍ | 308/895 [00:02<00:05, 106.06it/s]
36%|███▌ | 319/895 [00:03<00:05, 105.12it/s]
37%|███▋ | 330/895 [00:03<00:05, 105.39it/s]
38%|███▊ | 341/895 [00:03<00:05, 105.41it/s]
39%|███▉ | 352/895 [00:03<00:05, 98.45it/s]
41%|████ | 363/895 [00:03<00:05, 100.80it/s]
42%|████▏ | 374/895 [00:03<00:05, 102.37it/s]
43%|████▎ | 385/895 [00:03<00:04, 103.48it/s]
44%|████▍ | 396/895 [00:03<00:04, 104.31it/s]
45%|████▌ | 407/895 [00:03<00:04, 104.78it/s]
47%|████▋ | 418/895 [00:03<00:04, 105.26it/s]
48%|████▊ | 429/895 [00:04<00:04, 105.78it/s]
49%|████▉ | 440/895 [00:04<00:04, 106.07it/s]
50%|█████ | 451/895 [00:04<00:04, 106.42it/s]
52%|█████▏ | 462/895 [00:04<00:04, 106.61it/s]
53%|█████▎ | 473/895 [00:04<00:03, 106.61it/s]
54%|█████▍ | 484/895 [00:04<00:03, 106.67it/s]
55%|█████▌ | 495/895 [00:04<00:03, 106.66it/s]
57%|█████▋ | 506/895 [00:04<00:03, 106.58it/s]
58%|█████▊ | 517/895 [00:04<00:03, 106.66it/s]
59%|█████▉ | 528/895 [00:05<00:03, 106.35it/s]
60%|██████ | 539/895 [00:05<00:03, 106.52it/s]
61%|██████▏ | 550/895 [00:05<00:03, 106.58it/s]
63%|██████▎ | 561/895 [00:05<00:03, 106.74it/s]
64%|██████▍ | 572/895 [00:05<00:03, 106.89it/s]
65%|██████▌ | 583/895 [00:05<00:02, 107.26it/s]
66%|██████▋ | 594/895 [00:05<00:02, 107.38it/s]
68%|██████▊ | 605/895 [00:05<00:02, 107.09it/s]
69%|██████▉ | 616/895 [00:05<00:02, 107.04it/s]
70%|███████ | 627/895 [00:05<00:02, 107.11it/s]
71%|███████▏ | 638/895 [00:06<00:02, 106.84it/s]
73%|███████▎ | 649/895 [00:06<00:02, 106.72it/s]
74%|███████▎ | 660/895 [00:06<00:02, 106.80it/s]
75%|███████▍ | 671/895 [00:06<00:02, 106.81it/s]
76%|███████▌ | 682/895 [00:06<00:01, 106.72it/s]
77%|███████▋ | 693/895 [00:06<00:01, 106.17it/s]
79%|███████▊ | 704/895 [00:06<00:01, 106.09it/s]
80%|███████▉ | 715/895 [00:06<00:01, 105.81it/s]
81%|████████ | 726/895 [00:06<00:01, 105.84it/s]
82%|████████▏ | 737/895 [00:06<00:01, 105.69it/s]
84%|████████▎ | 7
|
|||
|
|
2026-08-09:23:23:32,778 INFO [task.py:395] Building contexts for mmlu_jurisprudence on rank 0...
|
|||
|
|
0%| | 0/108 [00:00<?, ?it/s]
10%|█ | 11/108 [00:00<00:00, 106.07it/s]
20%|██ | 22/108 [00:00<00:00, 106.07it/s]
31%|███ | 33/108 [00:00<00:00, 105.95it/s]
41%|████ | 44/108 [00:00<00:00, 105.89it/s]
51%|█████ | 55/108 [00:00<00:00, 105.68it/s]
61%|██████ | 66/108 [00:00<00:00, 105.92it/s]
71%|███████▏ | 77/108 [00:00<00:00, 105.90it/s]
81%|████████▏ | 88/108 [00:00<00:00, 106.31it/s]
92%|█████████▏| 99/108 [00:00<00:00, 106.41it/s]
100%|██████████| 108/108 [00:01<00:00, 106.16it/s]
|
|||
|
|
2026-08-09:23:23:33,799 INFO [task.py:395] Building contexts for mmlu_professional_law on rank 0...
|
|||
|
|
0%| | 0/1534 [00:00<?, ?it/s]
1%| | 11/1534 [00:00<00:14, 105.69it/s]
1%|▏ | 22/1534 [00:00<00:14, 104.95it/s]
2%|▏ | 33/1534 [00:00<00:14, 104.88it/s]
3%|▎ | 44/1534 [00:00<00:14, 104.68it/s]
4%|▎ | 55/1534 [00:00<00:14, 104.66it/s]
4%|▍ | 66/1534 [00:00<00:14, 104.43it/s]
5%|▌ | 77/1534 [00:00<00:13, 104.49it/s]
6%|▌ | 88/1534 [00:00<00:13, 104.82it/s]
6%|▋ | 99/1534 [00:00<00:13, 105.10it/s]
7%|▋ | 110/1534 [00:01<00:13, 105.18it/s]
8%|▊ | 121/1534 [00:01<00:13, 105.41it/s]
9%|▊ | 132/1534 [00:01<00:13, 105.42it/s]
9%|▉ | 143/1534 [00:01<00:13, 105.50it/s]
10%|█ | 154/1534 [00:01<00:13, 105.17it/s]
11%|█ | 165/1534 [00:01<00:13, 105.21it/s]
11%|█▏ | 176/1534 [00:01<00:12, 105.11it/s]
12%|█▏ | 187/1534 [00:01<00:12, 104.96it/s]
13%|█▎ | 198/1534 [00:01<00:12, 105.09it/s]
14%|█▎ | 209/1534 [00:01<00:12, 105.27it/s]
14%|█▍ | 220/1534 [00:02<00:12, 105.46it/s]
15%|█▌ | 231/1534 [00:02<00:12, 105.34it/s]
16%|█▌ | 242/1534 [00:02<00:12, 105.22it/s]
16%|█▋ | 253/1534 [00:02<00:12, 105.25it/s]
17%|█▋ | 264/1534 [00:02<00:12, 105.02it/s]
18%|█▊ | 275/1534 [00:02<00:11, 105.02it/s]
19%|█▊ | 286/1534 [00:02<00:11, 104.88it/s]
19%|█▉ | 297/1534 [00:02<00:11, 104.86it/s]
20%|██ | 308/1534 [00:02<00:11, 105.02it/s]
21%|██ | 319/1534 [00:03<00:11, 104.90it/s]
22%|██▏ | 330/1534 [00:03<00:11, 104.92it/s]
22%|██▏ | 341/1534 [00:03<00:11, 104.74it/s]
23%|██▎ | 352/1534 [00:03<00:11, 104.71it/s]
24%|██▎ | 363/1534 [00:03<00:11, 104.46it/s]
24%|██▍ | 374/1534 [00:03<00:11, 104.62it/s]
25%|██▌ | 385/1534 [00:03<00:10, 104.60it/s]
26%|██▌ | 396/1534 [00:03<00:10, 104.62it/s]
27%|██▋ | 407/1534 [00:03<00:10, 104.63it/s]
27%|██▋ | 418/1534 [00:03<00:10, 104.84it/s]
28%|██▊ | 429/1534 [00:04<00:10, 105.03it/s]
29%|██▊ | 440/1534 [00:04<00:10, 105.13it/s]
29%|██▉ | 451/1534 [00:04<00:10, 105.02it/s]
30%|███ | 462/1534 [00:04<00:10, 104.89it/s]
31%|███ | 473/1534 [00:04<00:10, 104.67it/s]
32%|███▏ | 484/1534 [00:04<00:10, 104.57it/s]
32%|███▏ | 495/1534 [00:04<00:09, 104.93it/s]
33%|███▎ | 506/1534 [00:04<00:09, 105.00it/s]
34%|███▎ | 517/1534 [00:04<00:09, 105.01it/s]
34%|███▍ | 528/1534 [00:05<00:09, 105.14it/s]
35%|███▌ | 539/1534 [00:05<00:09, 105.24it/s]
36%|███▌ | 550/1534 [00:05<00:09, 105.31it/s]
37%|███▋ | 561/1534 [00:05<00:09, 105.43it/s]
37%|███▋ | 572/1534 [00:05<00:09, 105.42it/s]
38%|███▊ | 583/1534 [00:05<00:09, 105.60it/s]
39%|███▊ | 594/1534 [00:05<00:08, 105.61it/s]
39%|███▉ | 605/1534 [00:05<00:08, 105.64it/s]
40%|████ | 616/1534 [00:05<00:08, 105.52it/s]
41%|████ | 627/1534 [00:05<00:08, 105.35it/s]
42%|████▏ | 638/1534 [00:06<00:08, 105.25it/s]
42%|████▏ | 649/1534 [00:06<00:08, 105.20it/s]
43%|████▎ | 660/1534 [00:06<00:08, 105.09it/s]
44%|████▎ | 671/1534 [00:06<00:08, 104.99it/s]
44%|████▍ | 682/1534 [00:06<00:08, 105.04it/s]
45%|████▌ | 693/1534 [00:06<00:08, 105.00it/s]
46%|████▌ | 704/1534 [00:06<00:07, 104.91it/s]
47%|████▋ | 715/1534 [00:06<00:07, 104.94it/s]
47%|████▋ | 726/1534 [00:06<00:07, 104.94it/s]
48%|████▊ | 737/1534 [00:07<00:07, 104.94it/s]
49%|████▉ | 748/1534 [00:07<00:07, 105.01it/s]
49%|████▉ | 759/1534 [00:07<00:07, 104.89it/s]
50%|█████ | 770/1534 [00:07<00:07, 104.81it/s]
51%|██<E29688>
|
|||
|
|
2026-08-09:23:23:48,429 INFO [task.py:395] Building contexts for mmlu_high_school_world_history on rank 0...
|
|||
|
|
0%| | 0/237 [00:00<?, ?it/s]
5%|▍ | 11/237 [00:00<00:02, 105.72it/s]
9%|▉ | 22/237 [00:00<00:02, 105.94it/s]
14%|█▍ | 33/237 [00:00<00:01, 105.78it/s]
19%|█▊ | 44/237 [00:00<00:01, 106.05it/s]
23%|██▎ | 55/237 [00:00<00:01, 106.24it/s]
28%|██▊ | 66/237 [00:00<00:01, 105.98it/s]
32%|███▏ | 77/237 [00:00<00:01, 105.66it/s]
37%|███▋ | 88/237 [00:00<00:01, 105.42it/s]
42%|████▏ | 99/237 [00:00<00:01, 105.32it/s]
46%|████▋ | 110/237 [00:01<00:01, 105.17it/s]
51%|█████ | 121/237 [00:01<00:01, 105.07it/s]
56%|█████▌ | 132/237 [00:01<00:01, 104.98it/s]
60%|██████ | 143/237 [00:01<00:00, 104.99it/s]
65%|██████▍ | 154/237 [00:01<00:00, 104.82it/s]
70%|██████▉ | 165/237 [00:01<00:00, 104.78it/s]
74%|███████▍ | 176/237 [00:01<00:00, 104.60it/s]
79%|███████▉ | 187/237 [00:01<00:00, 104.52it/s]
84%|████████▎ | 198/237 [00:01<00:00, 104.46it/s]
88%|████████▊ | 209/237 [00:01<00:00, 104.48it/s]
93%|█████████▎| 220/237 [00:02<00:00, 104.68it/s]
97%|█████████▋| 231/237 [00:02<00:00, 105.08it/s]
100%|██████████| 237/237 [00:02<00:00, 105.15it/s]
|
|||
|
|
2026-08-09:23:23:50,689 INFO [task.py:395] Building contexts for mmlu_world_religions on rank 0...
|
|||
|
|
0%| | 0/171 [00:00<?, ?it/s]
6%|▋ | 11/171 [00:00<00:01, 105.36it/s]
13%|█▎ | 22/171 [00:00<00:01, 105.26it/s]
19%|█▉ | 33/171 [00:00<00:01, 105.39it/s]
26%|██▌ | 44/171 [00:00<00:01, 104.93it/s]
32%|███▏ | 55/171 [00:00<00:01, 104.76it/s]
39%|███▊ | 66/171 [00:00<00:01, 104.38it/s]
45%|████▌ | 77/171 [00:00<00:00, 104.39it/s]
51%|█████▏ | 88/171 [00:00<00:00, 104.50it/s]
58%|█████▊ | 99/171 [00:00<00:00, 104.85it/s]
64%|██████▍ | 110/171 [00:01<00:00, 105.19it/s]
71%|███████ | 121/171 [00:01<00:00, 105.36it/s]
77%|███████▋ | 132/171 [00:01<00:00, 105.57it/s]
84%|████████▎ | 143/171 [00:01<00:00, 105.60it/s]
90%|█████████ | 154/171 [00:01<00:00, 105.45it/s]
96%|█████████▋| 165/171 [00:01<00:00, 105.20it/s]
100%|██████████| 171/171 [00:01<00:00, 105.08it/s]
|
|||
|
|
2026-08-09:23:23:52,322 INFO [task.py:395] Building contexts for mmlu_logical_fallacies on rank 0...
|
|||
|
|
0%| | 0/163 [00:00<?, ?it/s]
7%|▋ | 11/163 [00:00<00:01, 106.28it/s]
13%|█▎ | 22/163 [00:00<00:01, 106.24it/s]
20%|██ | 33/163 [00:00<00:01, 106.91it/s]
27%|██▋ | 44/163 [00:00<00:01, 106.92it/s]
34%|███▎ | 55/163 [00:00<00:01, 107.26it/s]
40%|████ | 66/163 [00:00<00:00, 107.40it/s]
47%|████▋ | 77/163 [00:00<00:00, 107.31it/s]
54%|█████▍ | 88/163 [00:00<00:00, 106.89it/s]
61%|██████ | 99/163 [00:00<00:00, 106.74it/s]
67%|██████▋ | 110/163 [00:01<00:00, 106.81it/s]
74%|███████▍ | 121/163 [00:01<00:00, 107.06it/s]
81%|████████ | 132/163 [00:01<00:00, 107.22it/s]
88%|████████▊ | 143/163 [00:01<00:00, 107.37it/s]
94%|█████████▍| 154/163 [00:01<00:00, 107.58it/s]
100%|██████████| 163/163 [00:01<00:00, 107.21it/s]
|
|||
|
|
2026-08-09:23:23:53,846 INFO [task.py:395] Building contexts for mmlu_prehistory on rank 0...
|
|||
|
|
0%| | 0/324 [00:00<?, ?it/s]
3%|▎ | 11/324 [00:00<00:02, 107.26it/s]
7%|▋ | 22/324 [00:00<00:02, 107.07it/s]
10%|█ | 33/324 [00:00<00:02, 106.62it/s]
14%|█▎ | 44/324 [00:00<00:02, 106.24it/s]
17%|█▋ | 55/324 [00:00<00:02, 106.14it/s]
20%|██ | 66/324 [00:00<00:02, 106.06it/s]
24%|██▍ | 77/324 [00:00<00:02, 106.09it/s]
27%|██▋ | 88/324 [00:00<00:02, 106.17it/s]
31%|███ | 99/324 [00:00<00:02, 106.05it/s]
34%|███▍ | 110/324 [00:01<00:02, 106.29it/s]
37%|███▋ | 121/324 [00:01<00:01, 106.56it/s]
41%|████ | 132/324 [00:01<00:01, 106.37it/s]
44%|████▍ | 143/324 [00:01<00:01, 106.08it/s]
48%|████▊ | 154/324 [00:01<00:01, 106.02it/s]
51%|█████ | 165/324 [00:01<00:01, 105.98it/s]
54%|█████▍ | 176/324 [00:01<00:01, 105.79it/s]
58%|█████▊ | 187/324 [00:01<00:01, 106.03it/s]
61%|██████ | 198/324 [00:01<00:01, 106.19it/s]
65%|██████▍ | 209/324 [00:01<00:01, 106.42it/s]
68%|██████▊ | 220/324 [00:02<00:00, 106.41it/s]
71%|███████▏ | 231/324 [00:02<00:00, 106.28it/s]
75%|███████▍ | 242/324 [00:02<00:00, 106.27it/s]
78%|███████▊ | 253/324 [00:02<00:00, 106.33it/s]
81%|████████▏ | 264/324 [00:02<00:00, 106.16it/s]
85%|████████▍ | 275/324 [00:02<00:00, 106.25it/s]
88%|████████▊ | 286/324 [00:02<00:00, 106.38it/s]
92%|█████████▏| 297/324 [00:02<00:00, 106.77it/s]
95%|█████████▌| 308/324 [00:02<00:00, 106.99it/s]
98%|█████████▊| 319/324 [00:02<00:00, 107.10it/s]
100%|██████████| 324/324 [00:03<00:00, 106.40it/s]
|
|||
|
|
2026-08-09:23:23:56,900 INFO [task.py:395] Building contexts for mmlu_formal_logic on rank 0...
|
|||
|
|
0%| | 0/126 [00:00<?, ?it/s]
9%|▊ | 11/126 [00:00<00:01, 107.72it/s]
17%|█▋ | 22/126 [00:00<00:00, 107.06it/s]
26%|██▌ | 33/126 [00:00<00:00, 106.77it/s]
35%|███▍ | 44/126 [00:00<00:00, 106.24it/s]
44%|████▎ | 55/126 [00:00<00:00, 106.06it/s]
52%|█████▏ | 66/126 [00:00<00:00, 106.09it/s]
61%|██████ | 77/126 [00:00<00:00, 106.35it/s]
70%|██████▉ | 88/126 [00:00<00:00, 106.54it/s]
79%|███████▊ | 99/126 [00:00<00:00, 106.77it/s]
87%|████████▋ | 110/126 [00:01<00:00, 106.95it/s]
96%|█████████▌| 121/126 [00:01<00:00, 107.04it/s]
100%|██████████| 126/126 [00:01<00:00, 106.67it/s]
|
|||
|
|
2026-08-09:23:23:58,085 INFO [task.py:395] Building contexts for mmlu_high_school_european_history on rank 0...
|
|||
|
|
0%| | 0/165 [00:00<?, ?it/s]
7%|▋ | 11/165 [00:00<00:01, 105.59it/s]
13%|█▎ | 22/165 [00:00<00:01, 105.08it/s]
20%|██ | 33/165 [00:00<00:01, 105.24it/s]
27%|██▋ | 44/165 [00:00<00:01, 105.53it/s]
33%|███▎ | 55/165 [00:00<00:01, 105.89it/s]
40%|████ | 66/165 [00:00<00:00, 106.14it/s]
47%|████▋ | 77/165 [00:00<00:00, 106.46it/s]
53%|█████▎ | 88/165 [00:00<00:00, 106.64it/s]
60%|██████ | 99/165 [00:00<00:00, 106.53it/s]
67%|██████▋ | 110/165 [00:01<00:00, 106.63it/s]
73%|███████▎ | 121/165 [00:01<00:00, 106.72it/s]
80%|████████ | 132/165 [00:01<00:00, 106.44it/s]
87%|████████▋ | 143/165 [00:01<00:00, 106.47it/s]
93%|█████████▎| 154/165 [00:01<00:00, 106.48it/s]
100%|██████████| 165/165 [00:01<00:00, 106.55it/s]
100%|██████████| 165/165 [00:01<00:00, 106.30it/s]
|
|||
|
|
2026-08-09:23:23:59,642 INFO [task.py:395] Building contexts for mmlu_high_school_us_history on rank 0...
|
|||
|
|
0%| | 0/204 [00:00<?, ?it/s]
5%|▌ | 11/204 [00:00<00:01, 107.27it/s]
11%|█ | 22/204 [00:00<00:01, 106.93it/s]
16%|█▌ | 33/204 [00:00<00:01, 106.89it/s]
22%|██▏ | 44/204 [00:00<00:01, 106.94it/s]
27%|██▋ | 55/204 [00:00<00:01, 106.99it/s]
32%|███▏ | 66/204 [00:00<00:01, 106.89it/s]
38%|███▊ | 77/204 [00:00<00:01, 107.10it/s]
43%|████▎ | 88/204 [00:00<00:01, 107.13it/s]
49%|████▊ | 99/204 [00:00<00:00, 107.02it/s]
54%|█████▍ | 110/204 [00:01<00:00, 107.11it/s]
59%|█████▉ | 121/204 [00:01<00:00, 107.28it/s]
65%|██████▍ | 132/204 [00:01<00:00, 107.44it/s]
70%|███████ | 143/204 [00:01<00:00, 107.35it/s]
75%|███████▌ | 154/204 [00:01<00:00, 107.25it/s]
81%|████████ | 165/204 [00:01<00:00, 107.32it/s]
86%|████████▋ | 176/204 [00:01<00:00, 107.48it/s]
92%|█████████▏| 187/204 [00:01<00:00, 107.50it/s]
97%|█████████▋| 198/204 [00:01<00:00, 107.60it/s]
100%|██████████| 204/204 [00:01<00:00, 107.29it/s]
|
|||
|
|
2026-08-09:23:24:01,549 INFO [task.py:395] Building contexts for mmlu_philosophy on rank 0...
|
|||
|
|
0%| | 0/311 [00:00<?, ?it/s]
4%|▎ | 11/311 [00:00<00:02, 107.36it/s]
7%|▋ | 22/311 [00:00<00:02, 106.98it/s]
11%|█ | 33/311 [00:00<00:02, 107.01it/s]
14%|█▍ | 44/311 [00:00<00:02, 107.11it/s]
18%|█▊ | 55/311 [00:00<00:02, 107.19it/s]
21%|██ | 66/311 [00:00<00:02, 107.25it/s]
25%|██▍ | 77/311 [00:00<00:02, 107.27it/s]
28%|██▊ | 88/311 [00:00<00:02, 107.33it/s]
32%|███▏ | 99/311 [00:00<00:01, 107.27it/s]
35%|███▌ | 110/311 [00:01<00:01, 107.31it/s]
39%|███▉ | 121/311 [00:01<00:01, 107.37it/s]
42%|████▏ | 132/311 [00:01<00:01, 107.42it/s]
46%|████▌ | 143/311 [00:01<00:01, 107.31it/s]
50%|████▉ | 154/311 [00:01<00:01, 107.22it/s]
53%|█████▎ | 165/311 [00:01<00:01, 107.32it/s]
57%|█████▋ | 176/311 [00:01<00:01, 107.14it/s]
60%|██████ | 187/311 [00:01<00:01, 106.97it/s]
64%|██████▎ | 198/311 [00:01<00:01, 106.79it/s]
67%|██████▋ | 209/311 [00:01<00:00, 106.86it/s]
71%|███████ | 220/311 [00:02<00:00, 107.03it/s]
74%|███████▍ | 231/311 [00:02<00:00, 106.96it/s]
78%|███████▊ | 242/311 [00:02<00:00, 106.99it/s]
81%|████████▏ | 253/311 [00:02<00:00, 107.15it/s]
85%|████████▍ | 264/311 [00:02<00:00, 107.25it/s]
88%|████████▊ | 275/311 [00:02<00:00, 107.28it/s]
92%|█████████▏| 286/311 [00:02<00:00, 107.38it/s]
95%|█████████▌| 297/311 [00:02<00:00, 107.31it/s]
99%|█████████▉| 308/311 [00:02<00:00, 107.34it/s]
100%|██████████| 311/311 [00:02<00:00, 107.19it/s]
|
|||
|
|
2026-08-09:23:24:04,459 INFO [task.py:395] Building contexts for mmlu_moral_disputes on rank 0...
|
|||
|
|
0%| | 0/346 [00:00<?, ?it/s]
3%|▎ | 11/346 [00:00<00:03, 107.25it/s]
6%|▋ | 22/346 [00:00<00:03, 106.89it/s]
10%|▉ | 33/346 [00:00<00:02, 106.77it/s]
13%|█▎ | 44/346 [00:00<00:02, 106.81it/s]
16%|█▌ | 55/346 [00:00<00:02, 106.94it/s]
19%|█▉ | 66/346 [00:00<00:02, 107.08it/s]
22%|██▏ | 77/346 [00:00<00:02, 106.92it/s]
25%|██▌ | 88/346 [00:00<00:02, 106.74it/s]
29%|██▊ | 99/346 [00:00<00:02, 106.69it/s]
32%|███▏ | 110/346 [00:01<00:02, 106.51it/s]
35%|███▍ | 121/346 [00:01<00:02, 106.42it/s]
38%|███▊ | 132/346 [00:01<00:02, 106.37it/s]
41%|████▏ | 143/346 [00:01<00:01, 106.47it/s]
45%|████▍ | 154/346 [00:01<00:01, 106.55it/s]
48%|████▊ | 165/346 [00:01<00:01, 106.62it/s]
51%|█████ | 176/346 [00:01<00:01, 106.69it/s]
54%|█████▍ | 187/346 [00:01<00:01, 106.68it/s]
57%|█████▋ | 198/346 [00:01<00:01, 106.75it/s]
60%|██████ | 209/346 [00:01<00:01, 106.77it/s]
64%|██████▎ | 220/346 [00:02<00:01, 106.68it/s]
67%|██████▋ | 231/346 [00:02<00:01, 106.87it/s]
70%|██████▉ | 242/346 [00:02<00:00, 106.97it/s]
73%|███████▎ | 253/346 [00:02<00:00, 106.98it/s]
76%|███████▋ | 264/346 [00:02<00:00, 106.94it/s]
79%|███████▉ | 275/346 [00:02<00:00, 107.16it/s]
83%|████████▎ | 286/346 [00:02<00:00, 107.17it/s]
86%|████████▌ | 297/346 [00:02<00:00, 107.12it/s]
89%|████████▉ | 308/346 [00:02<00:00, 106.96it/s]
92%|█████████▏| 319/346 [00:02<00:00, 106.91it/s]
95%|█████████▌| 330/346 [00:03<00:00, 106.95it/s]
99%|█████████▊| 341/346 [00:03<00:00, 106.70it/s]
100%|██████████| 346/346 [00:03<00:00, 106.78it/s]
|
|||
|
|
2026-08-09:23:24:07,708 INFO [task.py:395] Building contexts for mmlu_professional_psychology on rank 0...
|
|||
|
|
0%| | 0/612 [00:00<?, ?it/s]
2%|▏ | 11/612 [00:00<00:05, 106.98it/s]
4%|▎ | 22/612 [00:00<00:05, 107.06it/s]
5%|▌ | 33/612 [00:00<00:05, 107.14it/s]
7%|▋ | 44/612 [00:00<00:05, 107.29it/s]
9%|▉ | 55/612 [00:00<00:05, 107.12it/s]
11%|█ | 66/612 [00:00<00:05, 107.03it/s]
13%|█▎ | 77/612 [00:00<00:05, 106.92it/s]
14%|█▍ | 88/612 [00:00<00:04, 107.04it/s]
16%|█▌ | 99/612 [00:00<00:04, 107.12it/s]
18%|█▊ | 110/612 [00:01<00:04, 107.02it/s]
20%|█▉ | 121/612 [00:01<00:04, 107.21it/s]
22%|██▏ | 132/612 [00:01<00:04, 107.34it/s]
23%|██▎ | 143/612 [00:01<00:04, 107.22it/s]
25%|██▌ | 154/612 [00:01<00:04, 107.20it/s]
27%|██▋ | 165/612 [00:01<00:04, 107.23it/s]
29%|██▉ | 176/612 [00:01<00:04, 107.18it/s]
31%|███ | 187/612 [00:01<00:03, 107.13it/s]
32%|███▏ | 198/612 [00:01<00:03, 106.90it/s]
34%|███▍ | 209/612 [00:01<00:03, 106.92it/s]
36%|███▌ | 220/612 [00:02<00:03, 106.97it/s]
38%|███▊ | 231/612 [00:02<00:03, 107.01it/s]
40%|███▉ | 242/612 [00:02<00:03, 107.15it/s]
41%|████▏ | 253/612 [00:02<00:03, 107.05it/s]
43%|████▎ | 264/612 [00:02<00:03, 107.02it/s]
45%|████▍ | 275/612 [00:02<00:03, 106.95it/s]
47%|████▋ | 286/612 [00:02<00:03, 106.78it/s]
49%|████▊ | 297/612 [00:02<00:02, 106.88it/s]
50%|█████ | 308/612 [00:02<00:02, 106.99it/s]
52%|█████▏ | 319/612 [00:02<00:02, 106.96it/s]
54%|█████▍ | 330/612 [00:03<00:02, 106.94it/s]
56%|█████▌ | 341/612 [00:03<00:02, 107.10it/s]
58%|█████▊ | 352/612 [00:03<00:02, 106.99it/s]
59%|█████▉ | 363/612 [00:03<00:02, 107.11it/s]
61%|██████ | 374/612 [00:03<00:02, 107.07it/s]
63%|██████▎ | 385/612 [00:03<00:02, 107.10it/s]
65%|██████▍ | 396/612 [00:03<00:02, 107.30it/s]
67%|██████▋ | 407/612 [00:03<00:01, 107.24it/s]
68%|██████▊ | 418/612 [00:03<00:01, 107.16it/s]
70%|███████ | 429/612 [00:04<00:01, 107.33it/s]
72%|███████▏ | 440/612 [00:04<00:01, 107.40it/s]
74%|███████▎ | 451/612 [00:04<00:01, 107.51it/s]
75%|███████▌ | 462/612 [00:04<00:01, 107.57it/s]
77%|███████▋ | 473/612 [00:04<00:01, 107.64it/s]
79%|███████▉ | 484/612 [00:04<00:01, 107.72it/s]
81%|████████ | 495/612 [00:04<00:01, 107.66it/s]
83%|████████▎ | 506/612 [00:04<00:00, 107.70it/s]
84%|████████▍ | 517/612 [00:04<00:00, 107.82it/s]
86%|████████▋ | 528/612 [00:04<00:00, 107.75it/s]
88%|████████▊ | 539/612 [00:05<00:00, 107.67it/s]
90%|████████▉ | 550/612 [00:05<00:00, 107.79it/s]
92%|█████████▏| 561/612 [00:05<00:00, 107.87it/s]
93%|█████████▎| 572/612 [00:05<00:00, 107.72it/s]
95%|█████████▌| 583/612 [00:05<00:00, 107.45it/s]
97%|█████████▋| 594/612 [00:05<00:00, 107.41it/s]
99%|█████████▉| 605/612 [00:05<00:00, 107.30it/s]
100%|██████████| 612/612 [00:05<00:00, 107.25it/s]
|
|||
|
|
2026-08-09:23:24:13,430 INFO [task.py:395] Building contexts for mmlu_high_school_psychology on rank 0...
|
|||
|
|
0%| | 0/545 [00:00<?, ?it/s]
2%|▏ | 11/545 [00:00<00:04, 107.91it/s]
4%|▍ | 22/545 [00:00<00:04, 108.09it/s]
6%|▌ | 33/545 [00:00<00:04, 108.16it/s]
8%|▊ | 44/545 [00:00<00:04, 108.31it/s]
10%|█ | 55/545 [00:00<00:04, 108.47it/s]
12%|█▏ | 66/545 [00:00<00:04, 108.50it/s]
14%|█▍ | 77/545 [00:00<00:04, 108.55it/s]
16%|█▌ | 88/545 [00:00<00:04, 108.41it/s]
18%|█▊ | 99/545 [00:00<00:04, 108.46it/s]
20%|██ | 110/545 [00:01<00:04, 108.44it/s]
22%|██▏ | 121/545 [00:01<00:03, 108.58it/s]
24%|██▍ | 132/545 [00:01<00:03, 108.69it/s]
26%|██▌ | 143/545 [00:01<00:03, 108.60it/s]
28%|██▊ | 154/545 [00:01<00:03, 108.59it/s]
30%|███ | 165/545 [00:01<00:03, 108.53it/s]
32%|███▏ | 176/545 [00:01<00:03, 108.57it/s]
34%|███▍ | 187/545 [00:01<00:03, 108.48it/s]
36%|███▋ | 198/545 [00:01<00:03, 108.34it/s]
38%|███▊ | 209/545 [00:01<00:03, 108.41it/s]
40%|████ | 220/545 [00:02<00:02, 108.46it/s]
42%|████▏ | 231/545 [00:02<00:02, 108.33it/s]
44%|████▍ | 242/545 [00:02<00:02, 108.16it/s]
46%|████▋ | 253/545 [00:02<00:02, 108.26it/s]
48%|████▊ | 264/545 [00:02<00:02, 108.37it/s]
50%|█████ | 275/545 [00:02<00:02, 108.42it/s]
52%|█████▏ | 286/545 [00:02<00:02, 108.37it/s]
54%|█████▍ | 297/545 [00:02<00:02, 108.25it/s]
57%|█████▋ | 308/545 [00:02<00:02, 108.18it/s]
59%|█████▊ | 319/545 [00:02<00:02, 108.01it/s]
61%|██████ | 330/545 [00:03<00:01, 107.93it/s]
63%|██████▎ | 341/545 [00:03<00:01, 108.11it/s]
65%|██████▍ | 352/545 [00:03<00:01, 108.12it/s]
67%|██████▋ | 363/545 [00:03<00:01, 108.21it/s]
69%|██████▊ | 374/545 [00:03<00:01, 108.34it/s]
71%|███████ | 385/545 [00:03<00:01, 108.39it/s]
73%|███████▎ | 396/545 [00:03<00:01, 108.33it/s]
75%|███████▍ | 407/545 [00:03<00:01, 108.02it/s]
77%|███████▋ | 418/545 [00:03<00:01, 107.72it/s]
79%|███████▊ | 429/545 [00:03<00:01, 107.62it/s]
81%|████████ | 440/545 [00:04<00:00, 107.51it/s]
83%|████████▎ | 451/545 [00:04<00:00, 107.38it/s]
85%|████████▍ | 462/545 [00:04<00:00, 107.15it/s]
87%|████████▋ | 473/545 [00:04<00:00, 107.00it/s]
89%|████████▉ | 484/545 [00:04<00:00, 106.92it/s]
91%|█████████ | 495/545 [00:04<00:00, 106.90it/s]
93%|█████████▎| 506/545 [00:04<00:00, 106.79it/s]
95%|█████████▍| 517/545 [00:04<00:00, 106.77it/s]
97%|█████████▋| 528/545 [00:04<00:00, 106.95it/s]
99%|█████████▉| 539/545 [00:04<00:00, 106.70it/s]
100%|██████████| 545/545 [00:05<00:00, 107.94it/s]
|
|||
|
|
2026-08-09:23:24:18,493 INFO [task.py:395] Building contexts for mmlu_security_studies on rank 0...
|
|||
|
|
0%| | 0/245 [00:00<?, ?it/s]
4%|▍ | 11/245 [00:00<00:02, 106.96it/s]
9%|▉ | 22/245 [00:00<00:02, 106.73it/s]
13%|█▎ | 33/245 [00:00<00:01, 106.85it/s]
18%|█▊ | 44/245 [00:00<00:01, 106.85it/s]
22%|██▏ | 55/245 [00:00<00:01, 106.77it/s]
27%|██▋ | 66/245 [00:00<00:01, 106.63it/s]
31%|███▏ | 77/245 [00:00<00:01, 106.41it/s]
36%|███▌ | 88/245 [00:00<00:01, 106.47it/s]
40%|████ | 99/245 [00:00<00:01, 106.77it/s]
45%|████▍ | 110/245 [00:01<00:01, 106.65it/s]
49%|████▉ | 121/245 [00:01<00:01, 106.64it/s]
54%|█████▍ | 132/245 [00:01<00:01, 106.65it/s]
58%|█████▊ | 143/245 [00:01<00:00, 106.74it/s]
63%|██████▎ | 154/245 [00:01<00:00, 106.90it/s]
67%|██████▋ | 165/245 [00:01<00:00, 106.83it/s]
72%|███████▏ | 176/245 [00:01<00:00, 106.90it/s]
76%|███████▋ | 187/245 [00:01<00:00, 106.85it/s]
81%|████████ | 198/245 [00:01<00:00, 106.69it/s]
85%|████████▌ | 209/245 [00:01<00:00, 106.77it/s]
90%|████████▉ | 220/245 [00:02<00:00, 106.80it/s]
94%|█████████▍| 231/245 [00:02<00:00, 106.91it/s]
99%|█████████▉| 242/245 [00:02<00:00, 106.99it/s]
100%|██████████| 245/245 [00:02<00:00, 106.78it/s]
|
|||
|
|
2026-08-09:23:24:20,794 INFO [task.py:395] Building contexts for mmlu_high_school_macroeconomics on rank 0...
|
|||
|
|
0%| | 0/390 [00:00<?, ?it/s]
3%|▎ | 11/390 [00:00<00:03, 108.41it/s]
6%|▌ | 22/390 [00:00<00:03, 107.91it/s]
8%|▊ | 33/390 [00:00<00:03, 107.68it/s]
11%|█▏ | 44/390 [00:00<00:03, 107.61it/s]
14%|█▍ | 55/390 [00:00<00:03, 107.46it/s]
17%|█▋ | 66/390 [00:00<00:03, 107.46it/s]
20%|█▉ | 77/390 [00:00<00:02, 107.47it/s]
23%|██▎ | 88/390 [00:00<00:02, 107.47it/s]
25%|██▌ | 99/390 [00:00<00:02, 107.75it/s]
28%|██▊ | 110/390 [00:01<00:02, 107.76it/s]
31%|███ | 121/390 [00:01<00:02, 107.73it/s]
34%|███▍ | 132/390 [00:01<00:02, 107.92it/s]
37%|███▋ | 143/390 [00:01<00:02, 107.98it/s]
39%|███▉ | 154/390 [00:01<00:02, 107.91it/s]
42%|████▏ | 165/390 [00:01<00:02, 107.88it/s]
45%|████▌ | 176/390 [00:01<00:01, 107.86it/s]
48%|████▊ | 187/390 [00:01<00:01, 107.75it/s]
51%|█████ | 198/390 [00:01<00:01, 107.69it/s]
54%|█████▎ | 209/390 [00:01<00:01, 107.65it/s]
56%|█████▋ | 220/390 [00:02<00:01, 107.71it/s]
59%|█████▉ | 231/390 [00:02<00:01, 107.73it/s]
62%|██████▏ | 242/390 [00:02<00:01, 107.71it/s]
65%|██████▍ | 253/390 [00:02<00:01, 107.72it/s]
68%|██████▊ | 264/390 [00:02<00:01, 107.65it/s]
71%|███████ | 275/390 [00:02<00:01, 107.64it/s]
73%|███████▎ | 286/390 [00:02<00:00, 107.88it/s]
76%|███████▌ | 297/390 [00:02<00:00, 107.90it/s]
79%|███████▉ | 308/390 [00:02<00:00, 108.08it/s]
82%|████████▏ | 319/390 [00:02<00:00, 108.17it/s]
85%|████████▍ | 330/390 [00:03<00:00, 108.26it/s]
87%|████████▋ | 341/390 [00:03<00:00, 108.42it/s]
90%|█████████ | 352/390 [00:03<00:00, 108.55it/s]
93%|█████████▎| 363/390 [00:03<00:00, 108.61it/s]
96%|█████████▌| 374/390 [00:03<00:00, 108.38it/s]
99%|█████████▊| 385/390 [00:03<00:00, 108.27it/s]
100%|██████████| 390/390 [00:03<00:00, 107.91it/s]
|
|||
|
|
2026-08-09:23:24:24,418 INFO [task.py:395] Building contexts for mmlu_us_foreign_policy on rank 0...
|
|||
|
|
0%| | 0/100 [00:00<?, ?it/s]
11%|█ | 11/100 [00:00<00:00, 108.94it/s]
22%|██▏ | 22/100 [00:00<00:00, 108.94it/s]
33%|███▎ | 33/100 [00:00<00:00, 109.03it/s]
44%|████▍ | 44/100 [00:00<00:00, 108.76it/s]
55%|█████▌ | 55/100 [00:00<00:00, 108.53it/s]
66%|██████▌ | 66/100 [00:00<00:00, 108.21it/s]
77%|███████▋ | 77/100 [00:00<00:00, 108.07it/s]
88%|████████▊ | 88/100 [00:00<00:00, 108.08it/s]
99%|█████████▉| 99/100 [00:00<00:00, 107.68it/s]
100%|██████████| 100/100 [00:00<00:00, 108.18it/s]
|
|||
|
|
2026-08-09:23:24:25,346 INFO [task.py:395] Building contexts for mmlu_high_school_government_and_politics on rank 0...
|
|||
|
|
0%| | 0/193 [00:00<?, ?it/s]
6%|▌ | 11/193 [00:00<00:01, 107.66it/s]
11%|█▏ | 22/193 [00:00<00:01, 107.71it/s]
17%|█▋ | 33/193 [00:00<00:01, 107.68it/s]
23%|██▎ | 44/193 [00:00<00:01, 107.63it/s]
28%|██▊ | 55/193 [00:00<00:01, 107.48it/s]
34%|███▍ | 66/193 [00:00<00:01, 107.66it/s]
40%|███▉ | 77/193 [00:00<00:01, 107.56it/s]
46%|████▌ | 88/193 [00:00<00:00, 107.55it/s]
51%|█████▏ | 99/193 [00:00<00:00, 107.40it/s]
57%|█████▋ | 110/193 [00:01<00:00, 107.42it/s]
63%|██████▎ | 121/193 [00:01<00:00, 107.62it/s]
68%|██████▊ | 132/193 [00:01<00:00, 107.56it/s]
74%|███████▍ | 143/193 [00:01<00:00, 107.45it/s]
80%|███████▉ | 154/193 [00:01<00:00, 107.49it/s]
85%|████████▌ | 165/193 [00:01<00:00, 107.47it/s]
91%|█████████ | 176/193 [00:01<00:00, 107.41it/s]
97%|█████████▋| 187/193 [00:01<00:00, 107.30it/s]
100%|██████████| 193/193 [00:01<00:00, 107.47it/s]
|
|||
|
|
2026-08-09:23:24:27,147 INFO [task.py:395] Building contexts for mmlu_human_sexuality on rank 0...
|
|||
|
|
0%| | 0/131 [00:00<?, ?it/s]
8%|▊ | 11/131 [00:00<00:01, 107.41it/s]
17%|█▋ | 22/131 [00:00<00:01, 107.02it/s]
25%|██▌ | 33/131 [00:00<00:00, 107.15it/s]
34%|███▎ | 44/131 [00:00<00:00, 107.66it/s]
42%|████▏ | 55/131 [00:00<00:00, 107.70it/s]
50%|█████ | 66/131 [00:00<00:00, 107.68it/s]
59%|█████▉ | 77/131 [00:00<00:00, 107.87it/s]
67%|██████▋ | 88/131 [00:00<00:00, 107.94it/s]
76%|███████▌ | 99/131 [00:00<00:00, 107.93it/s]
84%|████████▍ | 110/131 [00:01<00:00, 107.99it/s]
92%|█████████▏| 121/131 [00:01<00:00, 107.91it/s]
100%|██████████| 131/131 [00:01<00:00, 107.76it/s]
|
|||
|
|
2026-08-09:23:24:28,366 INFO [task.py:395] Building contexts for mmlu_econometrics on rank 0...
|
|||
|
|
0%| | 0/114 [00:00<?, ?it/s]
10%|▉ | 11/114 [00:00<00:00, 107.85it/s]
19%|█▉ | 22/114 [00:00<00:00, 107.94it/s]
29%|██▉ | 33/114 [00:00<00:00, 108.19it/s]
39%|███▊ | 44/114 [00:00<00:00, 108.25it/s]
48%|████▊ | 55/114 [00:00<00:00, 108.00it/s]
58%|█████▊ | 66/114 [00:00<00:00, 107.94it/s]
68%|██████▊ | 77/114 [00:00<00:00, 107.49it/s]
77%|███████▋ | 88/114 [00:00<00:00, 107.45it/s]
87%|████████▋ | 99/114 [00:00<00:00, 107.27it/s]
96%|█████████▋| 110/114 [00:01<00:00, 107.39it/s]
100%|██████████| 114/114 [00:01<00:00, 107.65it/s]
|
|||
|
|
2026-08-09:23:24:29,429 INFO [task.py:395] Building contexts for mmlu_public_relations on rank 0...
|
|||
|
|
0%| | 0/110 [00:00<?, ?it/s]
10%|█ | 11/110 [00:00<00:00, 106.94it/s]
20%|██ | 22/110 [00:00<00:00, 106.86it/s]
30%|███ | 33/110 [00:00<00:00, 107.01it/s]
40%|████ | 44/110 [00:00<00:00, 107.28it/s]
50%|█████ | 55/110 [00:00<00:00, 107.50it/s]
60%|██████ | 66/110 [00:00<00:00, 107.42it/s]
70%|███████ | 77/110 [00:00<00:00, 107.48it/s]
80%|████████ | 88/110 [00:00<00:00, 107.44it/s]
90%|█████████ | 99/110 [00:00<00:00, 107.25it/s]
100%|██████████| 110/110 [00:01<00:00, 107.16it/s]
100%|██████████| 110/110 [00:01<00:00, 107.24it/s]
|
|||
|
|
2026-08-09:23:24:30,458 INFO [task.py:395] Building contexts for mmlu_sociology on rank 0...
|
|||
|
|
0%| | 0/201 [00:00<?, ?it/s]
5%|▌ | 11/201 [00:00<00:01, 106.67it/s]
11%|█ | 22/201 [00:00<00:01, 106.91it/s]
16%|█▋ | 33/201 [00:00<00:01, 106.96it/s]
22%|██▏ | 44/201 [00:00<00:01, 106.79it/s]
27%|██▋ | 55/201 [00:00<00:01, 106.77it/s]
33%|███▎ | 66/201 [00:00<00:01, 106.62it/s]
38%|███▊ | 77/201 [00:00<00:01, 106.76it/s]
44%|████▍ | 88/201 [00:00<00:01, 106.91it/s]
49%|████▉ | 99/201 [00:00<00:00, 107.07it/s]
55%|█████▍ | 110/201 [00:01<00:00, 107.12it/s]
60%|██████ | 121/201 [00:01<00:00, 107.29it/s]
66%|██████▌ | 132/201 [00:01<00:00, 107.49it/s]
71%|███████ | 143/201 [00:01<00:00, 107.69it/s]
77%|███████▋ | 154/201 [00:01<00:00, 107.77it/s]
82%|████████▏ | 165/201 [00:01<00:00, 107.82it/s]
88%|████████▊ | 176/201 [00:01<00:00, 107.73it/s]
93%|█████████▎| 187/201 [00:01<00:00, 107.72it/s]
99%|█████████▊| 198/201 [00:01<00:00, 107.67it/s]
100%|██████████| 201/201 [00:01<00:00, 107.32it/s]
|
|||
|
|
2026-08-09:23:24:32,336 INFO [task.py:395] Building contexts for mmlu_high_school_geography on rank 0...
|
|||
|
|
0%| | 0/198 [00:00<?, ?it/s]
6%|▌ | 11/198 [00:00<00:01, 107.09it/s]
11%|█ | 22/198 [00:00<00:01, 106.95it/s]
17%|█▋ | 33/198 [00:00<00:01, 107.06it/s]
22%|██▏ | 44/198 [00:00<00:01, 106.98it/s]
28%|██▊ | 55/198 [00:00<00:01, 107.06it/s]
33%|███▎ | 66/198 [00:00<00:01, 106.86it/s]
39%|███▉ | 77/198 [00:00<00:01, 106.63it/s]
44%|████▍ | 88/198 [00:00<00:01, 106.73it/s]
50%|█████ | 99/198 [00:00<00:00, 106.57it/s]
56%|█████▌ | 110/198 [00:01<00:00, 106.71it/s]
61%|██████ | 121/198 [00:01<00:00, 106.94it/s]
67%|██████▋ | 132/198 [00:01<00:00, 107.08it/s]
72%|███████▏ | 143/198 [00:01<00:00, 107.16it/s]
78%|███████▊ | 154/198 [00:01<00:00, 107.34it/s]
83%|████████▎ | 165/198 [00:01<00:00, 107.22it/s]
89%|████████▉ | 176/198 [00:01<00:00, 107.30it/s]
94%|█████████▍| 187/198 [00:01<00:00, 107.13it/s]
100%|██████████| 198/198 [00:01<00:00, 106.88it/s]
100%|██████████| 198/198 [00:01<00:00, 106.96it/s]
|
|||
|
|
2026-08-09:23:24:34,193 INFO [task.py:395] Building contexts for mmlu_high_school_microeconomics on rank 0...
|
|||
|
|
0%| | 0/238 [00:00<?, ?it/s]
5%|▍ | 11/238 [00:00<00:02, 106.37it/s]
9%|▉ | 22/238 [00:00<00:02, 106.71it/s]
14%|█▍ | 33/238 [00:00<00:01, 106.86it/s]
18%|█▊ | 44/238 [00:00<00:01, 106.79it/s]
23%|██▎ | 55/238 [00:00<00:01, 106.97it/s]
28%|██▊ | 66/238 [00:00<00:01, 107.04it/s]
32%|███▏ | 77/238 [00:00<00:01, 107.07it/s]
37%|███▋ | 88/238 [00:00<00:01, 107.01it/s]
42%|████▏ | 99/238 [00:00<00:01, 107.24it/s]
46%|████▌ | 110/238 [00:01<00:01, 107.37it/s]
51%|█████ | 121/238 [00:01<00:01, 107.36it/s]
55%|█████▌ | 132/238 [00:01<00:00, 107.27it/s]
60%|██████ | 143/238 [00:01<00:00, 107.42it/s]
65%|██████▍ | 154/238 [00:01<00:00, 107.49it/s]
69%|██████▉ | 165/238 [00:01<00:00, 107.55it/s]
74%|███████▍ | 176/238 [00:01<00:00, 107.54it/s]
79%|███████▊ | 187/238 [00:01<00:00, 107.72it/s]
83%|████████▎ | 198/238 [00:01<00:00, 107.76it/s]
88%|████████▊ | 209/238 [00:01<00:00, 107.86it/s]
92%|█████████▏| 220/238 [00:02<00:00, 107.94it/s]
97%|█████████▋| 231/238 [00:02<00:00, 108.00it/s]
100%|██████████| 238/238 [00:02<00:00, 107.45it/s]
|
|||
|
|
2026-08-09:23:24:36,414 INFO [task.py:395] Building contexts for mmlu_management on rank 0...
|
|||
|
|
0%| | 0/103 [00:00<?, ?it/s]
11%|█ | 11/103 [00:00<00:00, 107.71it/s]
21%|██▏ | 22/103 [00:00<00:00, 108.13it/s]
32%|███▏ | 33/103 [00:00<00:00, 108.20it/s]
43%|████▎ | 44/103 [00:00<00:00, 108.25it/s]
53%|█████▎ | 55/103 [00:00<00:00, 108.12it/s]
64%|██████▍ | 66/103 [00:00<00:00, 108.04it/s]
75%|███████▍ | 77/103 [00:00<00:00, 107.85it/s]
85%|████████▌ | 88/103 [00:00<00:00, 107.79it/s]
96%|█████████▌| 99/103 [00:00<00:00, 107.34it/s]
100%|██████████| 103/103 [00:00<00:00, 107.72it/s]
|
|||
|
|
2026-08-09:23:24:37,373 INFO [task.py:395] Building contexts for mmlu_professional_accounting on rank 0...
|
|||
|
|
0%| | 0/282 [00:00<?, ?it/s]
4%|▍ | 11/282 [00:00<00:02, 106.91it/s]
8%|▊ | 22/282 [00:00<00:02, 107.23it/s]
12%|█▏ | 33/282 [00:00<00:02, 107.48it/s]
16%|█▌ | 44/282 [00:00<00:02, 107.72it/s]
20%|█▉ | 55/282 [00:00<00:02, 107.70it/s]
23%|██▎ | 66/282 [00:00<00:02, 107.75it/s]
27%|██▋ | 77/282 [00:00<00:01, 107.70it/s]
31%|███ | 88/282 [00:00<00:01, 107.59it/s]
35%|███▌ | 99/282 [00:00<00:01, 107.47it/s]
39%|███▉ | 110/282 [00:01<00:01, 107.58it/s]
43%|████▎ | 121/282 [00:01<00:01, 107.61it/s]
47%|████▋ | 132/282 [00:01<00:01, 107.62it/s]
51%|█████ | 143/282 [00:01<00:01, 107.65it/s]
55%|█████▍ | 154/282 [00:01<00:01, 107.71it/s]
59%|█████▊ | 165/282 [00:01<00:01, 107.68it/s]
62%|██████▏ | 176/282 [00:01<00:00, 107.67it/s]
66%|██████▋ | 187/282 [00:01<00:00, 107.81it/s]
70%|███████ | 198/282 [00:01<00:00, 107.95it/s]
74%|███████▍ | 209/282 [00:01<00:00, 107.88it/s]
78%|███████▊ | 220/282 [00:02<00:00, 107.87it/s]
82%|████████▏ | 231/282 [00:02<00:00, 108.00it/s]
86%|████████▌ | 242/282 [00:02<00:00, 107.94it/s]
90%|████████▉ | 253/282 [00:02<00:00, 107.86it/s]
94%|█████████▎| 264/282 [00:02<00:00, 107.73it/s]
98%|█████████▊| 275/282 [00:02<00:00, 107.87it/s]
100%|██████████| 282/282 [00:02<00:00, 107.72it/s]
|
|||
|
|
2026-08-09:23:24:39,998 INFO [task.py:395] Building contexts for mmlu_college_medicine on rank 0...
|
|||
|
|
0%| | 0/173 [00:00<?, ?it/s]
6%|▋ | 11/173 [00:00<00:01, 106.68it/s]
13%|█▎ | 22/173 [00:00<00:01, 106.98it/s]
19%|█▉ | 33/173 [00:00<00:01, 107.21it/s]
25%|██▌ | 44/173 [00:00<00:01, 107.34it/s]
32%|███▏ | 55/173 [00:00<00:01, 107.08it/s]
38%|███▊ | 66/173 [00:00<00:00, 107.11it/s]
45%|████▍ | 77/173 [00:00<00:00, 107.18it/s]
51%|█████ | 88/173 [00:00<00:00, 107.08it/s]
57%|█████▋ | 99/173 [00:00<00:00, 107.06it/s]
64%|██████▎ | 110/173 [00:01<00:00, 106.96it/s]
70%|██████▉ | 121/173 [00:01<00:00, 106.87it/s]
76%|███████▋ | 132/173 [00:01<00:00, 106.72it/s]
83%|████████▎ | 143/173 [00:01<00:00, 106.73it/s]
89%|████████▉ | 154/173 [00:01<00:00, 106.82it/s]
95%|█████████▌| 165/173 [00:01<00:00, 106.80it/s]
100%|██████████| 173/173 [00:01<00:00, 106.94it/s]
|
|||
|
|
2026-08-09:23:24:41,621 INFO [task.py:395] Building contexts for mmlu_clinical_knowledge on rank 0...
|
|||
|
|
0%| | 0/265 [00:00<?, ?it/s]
4%|▍ | 11/265 [00:00<00:02, 106.90it/s]
8%|▊ | 22/265 [00:00<00:02, 107.21it/s]
12%|█▏ | 33/265 [00:00<00:02, 107.26it/s]
17%|█▋ | 44/265 [00:00<00:02, 107.38it/s]
21%|██ | 55/265 [00:00<00:01, 107.32it/s]
25%|██▍ | 66/265 [00:00<00:01, 107.25it/s]
29%|██▉ | 77/265 [00:00<00:01, 107.11it/s]
33%|███▎ | 88/265 [00:00<00:01, 107.05it/s]
37%|███▋ | 99/265 [00:00<00:01, 107.12it/s]
42%|████▏ | 110/265 [00:01<00:01, 107.01it/s]
46%|████▌ | 121/265 [00:01<00:01, 107.00it/s]
50%|████▉ | 132/265 [00:01<00:01, 107.09it/s]
54%|█████▍ | 143/265 [00:01<00:01, 107.16it/s]
58%|█████▊ | 154/265 [00:01<00:01, 107.13it/s]
62%|██████▏ | 165/265 [00:01<00:00, 107.03it/s]
66%|██████▋ | 176/265 [00:01<00:00, 107.00it/s]
71%|███████ | 187/265 [00:01<00:00, 107.13it/s]
75%|███████▍ | 198/265 [00:01<00:00, 107.17it/s]
79%|███████▉ | 209/265 [00:01<00:00, 107.23it/s]
83%|████████▎ | 220/265 [00:02<00:00, 107.39it/s]
87%|████████▋ | 231/265 [00:02<00:00, 107.54it/s]
91%|█████████▏| 242/265 [00:02<00:00, 107.73it/s]
95%|█████████▌| 253/265 [00:02<00:00, 107.82it/s]
100%|█████████▉| 264/265 [00:02<00:00, 107.59it/s]
100%|██████████| 265/265 [00:02<00:00, 107.27it/s]
|
|||
|
|
2026-08-09:23:24:44,098 INFO [task.py:395] Building contexts for mmlu_virology on rank 0...
|
|||
|
|
0%| | 0/166 [00:00<?, ?it/s]
7%|▋ | 11/166 [00:00<00:01, 107.62it/s]
13%|█▎ | 22/166 [00:00<00:01, 107.79it/s]
20%|█▉ | 33/166 [00:00<00:01, 107.72it/s]
27%|██▋ | 44/166 [00:00<00:01, 107.60it/s]
33%|███▎ | 55/166 [00:00<00:01, 107.45it/s]
40%|███▉ | 66/166 [00:00<00:00, 107.30it/s]
46%|████▋ | 77/166 [00:00<00:00, 107.42it/s]
53%|█████▎ | 88/166 [00:00<00:00, 107.19it/s]
60%|█████▉ | 99/166 [00:00<00:00, 106.95it/s]
66%|██████▋ | 110/166 [00:01<00:00, 106.93it/s]
73%|███████▎ | 121/166 [00:01<00:00, 106.92it/s]
80%|███████▉ | 132/166 [00:01<00:00, 106.75it/s]
86%|████████▌ | 143/166 [00:01<00:00, 106.72it/s]
93%|█████████▎| 154/166 [00:01<00:00, 106.66it/s]
99%|█████████▉| 165/166 [00:01<00:00, 106.77it/s]
100%|██████████| 166/166 [00:01<00:00, 107.04it/s]
|
|||
|
|
2026-08-09:23:24:45,654 INFO [task.py:395] Building contexts for mmlu_marketing on rank 0...
|
|||
|
|
0%| | 0/234 [00:00<?, ?it/s]
5%|▍ | 11/234 [00:00<00:02, 107.08it/s]
9%|▉ | 22/234 [00:00<00:01, 107.29it/s]
14%|█▍ | 33/234 [00:00<00:01, 107.34it/s]
19%|█▉ | 44/234 [00:00<00:01, 107.24it/s]
24%|██▎ | 55/234 [00:00<00:01, 107.20it/s]
28%|██▊ | 66/234 [00:00<00:01, 107.03it/s]
33%|███▎ | 77/234 [00:00<00:01, 107.16it/s]
38%|███▊ | 88/234 [00:00<00:01, 107.12it/s]
42%|████▏ | 99/234 [00:00<00:01, 107.23it/s]
47%|████▋ | 110/234 [00:01<00:01, 107.27it/s]
52%|█████▏ | 121/234 [00:01<00:01, 107.64it/s]
56%|█████▋ | 132/234 [00:01<00:00, 107.76it/s]
61%|██████ | 143/234 [00:01<00:00, 107.81it/s]
66%|██████▌ | 154/234 [00:01<00:00, 107.88it/s]
71%|███████ | 165/234 [00:01<00:00, 107.96it/s]
75%|███████▌ | 176/234 [00:01<00:00, 107.71it/s]
80%|███████▉ | 187/234 [00:01<00:00, 107.87it/s]
85%|████████▍ | 198/234 [00:01<00:00, 107.72it/s]
89%|████████▉ | 209/234 [00:01<00:00, 107.83it/s]
94%|█████████▍| 220/234 [00:02<00:00, 107.67it/s]
99%|█████████▊| 231/234 [00:02<00:00, 107.64it/s]
100%|██████████| 234/234 [00:02<00:00, 107.55it/s]
|
|||
|
|
2026-08-09:23:24:47,836 INFO [task.py:395] Building contexts for mmlu_nutrition on rank 0...
|
|||
|
|
0%| | 0/306 [00:00<?, ?it/s]
4%|▎ | 11/306 [00:00<00:02, 107.98it/s]
7%|▋ | 22/306 [00:00<00:02, 107.56it/s]
11%|█ | 33/306 [00:00<00:02, 107.64it/s]
14%|█▍ | 44/306 [00:00<00:02, 107.64it/s]
18%|█▊ | 55/306 [00:00<00:02, 107.71it/s]
22%|██▏ | 66/306 [00:00<00:02, 107.59it/s]
25%|██▌ | 77/306 [00:00<00:02, 107.56it/s]
29%|██▉ | 88/306 [00:00<00:02, 107.56it/s]
32%|███▏ | 99/306 [00:01<00:02, 69.18it/s]
36%|███▌ | 110/306 [00:01<00:02, 77.18it/s]
40%|███▉ | 121/306 [00:01<00:02, 84.14it/s]
43%|████▎ | 132/306 [00:01<00:01, 89.83it/s]
47%|████▋ | 143/306 [00:01<00:01, 94.29it/s]
50%|█████ | 154/306 [00:01<00:01, 97.72it/s]
54%|█████▍ | 165/306 [00:01<00:01, 100.21it/s]
58%|█████▊ | 176/306 [00:01<00:01, 102.01it/s]
61%|██████ | 187/306 [00:01<00:01, 103.33it/s]
65%|██████▍ | 198/306 [00:02<00:01, 104.24it/s]
68%|██████▊ | 209/306 [00:02<00:00, 104.88it/s]
72%|███████▏ | 220/306 [00:02<00:00, 105.26it/s]
75%|███████▌ | 231/306 [00:02<00:00, 105.45it/s]
79%|███████▉ | 242/306 [00:02<00:00, 105.42it/s]
83%|████████▎ | 253/306 [00:02<00:00, 105.68it/s]
86%|████████▋ | 264/306 [00:02<00:00, 105.76it/s]
90%|████████▉ | 275/306 [00:02<00:00, 105.80it/s]
93%|█████████▎| 286/306 [00:02<00:00, 106.03it/s]
97%|█████████▋| 297/306 [00:02<00:00, 105.87it/s]
100%|██████████| 306/306 [00:03<00:00, 100.21it/s]
|
|||
|
|
2026-08-09:23:24:50,897 INFO [task.py:395] Building contexts for mmlu_medical_genetics on rank 0...
|
|||
|
|
0%| | 0/100 [00:00<?, ?it/s]
11%|█ | 11/100 [00:00<00:00, 106.27it/s]
22%|██▏ | 22/100 [00:00<00:00, 105.96it/s]
33%|███▎ | 33/100 [00:00<00:00, 106.25it/s]
44%|████▍ | 44/100 [00:00<00:00, 106.25it/s]
55%|█████▌ | 55/100 [00:00<00:00, 106.32it/s]
66%|██████▌ | 66/100 [00:00<00:00, 106.57it/s]
77%|███████▋ | 77/100 [00:00<00:00, 106.65it/s]
88%|████████▊ | 88/100 [00:00<00:00, 106.76it/s]
99%|█████████▉| 99/100 [00:00<00:00, 106.97it/s]
100%|██████████| 100/100 [00:00<00:00, 106.58it/s]
|
|||
|
|
2026-08-09:23:24:51,839 INFO [task.py:395] Building contexts for mmlu_global_facts on rank 0...
|
|||
|
|
0%| | 0/100 [00:00<?, ?it/s]
11%|█ | 11/100 [00:00<00:00, 107.81it/s]
22%|██▏ | 22/100 [00:00<00:00, 107.92it/s]
33%|███▎ | 33/100 [00:00<00:00, 108.16it/s]
44%|████▍ | 44/100 [00:00<00:00, 108.06it/s]
55%|█████▌ | 55/100 [00:00<00:00, 107.93it/s]
66%|██████▌ | 66/100 [00:00<00:00, 107.94it/s]
77%|███████▋ | 77/100 [00:00<00:00, 107.95it/s]
88%|████████▊ | 88/100 [00:00<00:00, 107.81it/s]
99%|█████████▉| 99/100 [00:00<00:00, 107.88it/s]
100%|██████████| 100/100 [00:00<00:00, 107.90it/s]
|
|||
|
|
2026-08-09:23:24:52,768 INFO [task.py:395] Building contexts for mmlu_miscellaneous on rank 0...
|
|||
|
|
0%| | 0/783 [00:00<?, ?it/s]
1%|▏ | 11/783 [00:00<00:07, 107.76it/s]
3%|▎ | 22/783 [00:00<00:07, 107.52it/s]
4%|▍ | 33/783 [00:00<00:06, 107.18it/s]
6%|▌ | 44/783 [00:00<00:06, 107.20it/s]
7%|▋ | 55/783 [00:00<00:06, 107.17it/s]
8%|▊ | 66/783 [00:00<00:06, 107.19it/s]
10%|▉ | 77/783 [00:00<00:06, 107.22it/s]
11%|█ | 88/783 [00:00<00:06, 107.32it/s]
13%|█▎ | 99/783 [00:00<00:06, 107.38it/s]
14%|█▍ | 110/783 [00:01<00:06, 107.37it/s]
15%|█▌ | 121/783 [00:01<00:06, 107.38it/s]
17%|█▋ | 132/783 [00:01<00:06, 107.23it/s]
18%|█▊ | 143/783 [00:01<00:05, 107.26it/s]
20%|█▉ | 154/783 [00:01<00:05, 107.29it/s]
21%|██ | 165/783 [00:01<00:05, 107.09it/s]
22%|██▏ | 176/783 [00:01<00:05, 107.16it/s]
24%|██▍ | 187/783 [00:01<00:05, 107.23it/s]
25%|██▌ | 198/783 [00:01<00:05, 107.24it/s]
27%|██▋ | 209/783 [00:01<00:05, 107.46it/s]
28%|██▊ | 220/783 [00:02<00:05, 107.54it/s]
30%|██▉ | 231/783 [00:02<00:05, 107.68it/s]
31%|███ | 242/783 [00:02<00:05, 107.59it/s]
32%|███▏ | 253/783 [00:02<00:04, 107.53it/s]
34%|███▎ | 264/783 [00:02<00:04, 107.57it/s]
35%|███▌ | 275/783 [00:02<00:04, 107.42it/s]
37%|███▋ | 286/783 [00:02<00:04, 107.26it/s]
38%|███▊ | 297/783 [00:02<00:04, 107.14it/s]
39%|███▉ | 308/783 [00:02<00:04, 107.24it/s]
41%|████ | 319/783 [00:02<00:04, 107.08it/s]
42%|████▏ | 330/783 [00:03<00:04, 107.15it/s]
44%|████▎ | 341/783 [00:03<00:04, 107.05it/s]
45%|████▍ | 352/783 [00:03<00:04, 106.82it/s]
46%|████▋ | 363/783 [00:03<00:03, 106.73it/s]
48%|████▊ | 374/783 [00:03<00:03, 106.51it/s]
49%|████▉ | 385/783 [00:03<00:03, 106.67it/s]
51%|█████ | 396/783 [00:03<00:03, 106.81it/s]
52%|█████▏ | 407/783 [00:03<00:03, 106.70it/s]
53%|█████▎ | 418/783 [00:03<00:03, 106.89it/s]
55%|█████▍ | 429/783 [00:04<00:03, 107.00it/s]
56%|█████▌ | 440/783 [00:04<00:03, 107.04it/s]
58%|█████▊ | 451/783 [00:04<00:03, 107.15it/s]
59%|█████▉ | 462/783 [00:04<00:03, 106.98it/s]
60%|██████ | 473/783 [00:04<00:02, 106.91it/s]
62%|██████▏ | 484/783 [00:04<00:02, 106.72it/s]
63%|██████▎ | 495/783 [00:04<00:02, 106.52it/s]
65%|██████▍ | 506/783 [00:04<00:02, 106.53it/s]
66%|██████▌ | 517/783 [00:04<00:02, 106.57it/s]
67%|██████▋ | 528/783 [00:04<00:02, 106.46it/s]
69%|██████▉ | 539/783 [00:05<00:02, 106.34it/s]
70%|███████ | 550/783 [00:05<00:02, 106.49it/s]
72%|███████▏ | 561/783 [00:05<00:02, 106.64it/s]
73%|███████▎ | 572/783 [00:05<00:01, 106.61it/s]
74%|███████▍ | 583/783 [00:05<00:01, 106.53it/s]
76%|███████▌ | 594/783 [00:05<00:01, 106.54it/s]
77%|███████▋ | 605/783 [00:05<00:01, 106.73it/s]
79%|███████▊ | 616/783 [00:05<00:01, 106.69it/s]
80%|████████ | 627/783 [00:05<00:01, 106.87it/s]
81%|████████▏ | 638/783 [00:05<00:01, 107.00it/s]
83%|████████▎ | 649/783 [00:06<00:01, 106.55it/s]
84%|████████▍ | 660/783 [00:06<00:01, 106.82it/s]
86%|████████▌ | 671/783 [00:06<00:01, 106.82it/s]
87%|████████▋ | 682/783 [00:06<00:00, 107.05it/s]
89%|████████▊ | 693/783 [00:06<00:00, 107.13it/s]
90%|████████▉ | 704/783 [00:06<00:00, 107.30it/s]
91%|█████████▏| 715/783 [00:06<00:00, 107.38it/s]
93%|█████████▎| 726/783 [00:06<00:00, 107.55it/s]
94%|██████<E29688><E29688>
|
|||
|
|
2026-08-09:23:25:00,099 INFO [task.py:395] Building contexts for mmlu_professional_medicine on rank 0...
|
|||
|
|
0%| | 0/272 [00:00<?, ?it/s]
4%|▍ | 11/272 [00:00<00:02, 107.03it/s]
8%|▊ | 22/272 [00:00<00:02, 106.93it/s]
12%|█▏ | 33/272 [00:00<00:02, 107.04it/s]
16%|█▌ | 44/272 [00:00<00:02, 107.09it/s]
20%|██ | 55/272 [00:00<00:02, 107.12it/s]
24%|██▍ | 66/272 [00:00<00:01, 106.85it/s]
28%|██▊ | 77/272 [00:00<00:01, 106.56it/s]
32%|███▏ | 88/272 [00:00<00:01, 106.44it/s]
36%|███▋ | 99/272 [00:00<00:01, 106.50it/s]
40%|████ | 110/272 [00:01<00:01, 106.61it/s]
44%|████▍ | 121/272 [00:01<00:01, 106.74it/s]
49%|████▊ | 132/272 [00:01<00:01, 106.67it/s]
53%|█████▎ | 143/272 [00:01<00:01, 106.85it/s]
57%|█████▋ | 154/272 [00:01<00:01, 106.97it/s]
61%|██████ | 165/272 [00:01<00:00, 107.03it/s]
65%|██████▍ | 176/272 [00:01<00:00, 106.93it/s]
69%|██████▉ | 187/272 [00:01<00:00, 107.03it/s]
73%|███████▎ | 198/272 [00:01<00:00, 106.96it/s]
77%|███████▋ | 209/272 [00:01<00:00, 106.82it/s]
81%|████████ | 220/272 [00:02<00:00, 106.81it/s]
85%|████████▍ | 231/272 [00:02<00:00, 106.67it/s]
89%|████████▉ | 242/272 [00:02<00:00, 106.72it/s]
93%|█████████▎| 253/272 [00:02<00:00, 106.76it/s]
97%|█████████▋| 264/272 [00:02<00:00, 106.80it/s]
100%|██████████| 272/272 [00:02<00:00, 106.83it/s]
|
|||
|
|
2026-08-09:23:25:02,652 INFO [task.py:395] Building contexts for mmlu_human_aging on rank 0...
|
|||
|
|
0%| | 0/223 [00:00<?, ?it/s]
5%|▍ | 11/223 [00:00<00:01, 107.26it/s]
10%|▉ | 22/223 [00:00<00:01, 107.48it/s]
15%|█▍ | 33/223 [00:00<00:01, 107.64it/s]
20%|█▉ | 44/223 [00:00<00:01, 107.45it/s]
25%|██▍ | 55/223 [00:00<00:01, 107.30it/s]
30%|██▉ | 66/223 [00:00<00:01, 107.18it/s]
35%|███▍ | 77/223 [00:00<00:01, 107.31it/s]
39%|███▉ | 88/223 [00:00<00:01, 107.41it/s]
44%|████▍ | 99/223 [00:00<00:01, 107.64it/s]
49%|████▉ | 110/223 [00:01<00:01, 107.73it/s]
54%|█████▍ | 121/223 [00:01<00:00, 107.91it/s]
59%|█████▉ | 132/223 [00:01<00:00, 107.99it/s]
64%|██████▍ | 143/223 [00:01<00:00, 108.02it/s]
69%|██████▉ | 154/223 [00:01<00:00, 107.97it/s]
74%|███████▍ | 165/223 [00:01<00:00, 107.99it/s]
79%|███████▉ | 176/223 [00:01<00:00, 107.85it/s]
84%|████████▍ | 187/223 [00:01<00:00, 107.89it/s]
89%|████████▉ | 198/223 [00:01<00:00, 107.79it/s]
94%|█████████▎| 209/223 [00:01<00:00, 107.77it/s]
99%|█████████▊| 220/223 [00:02<00:00, 107.70it/s]
100%|██████████| 223/223 [00:02<00:00, 107.68it/s]
|
|||
|
|
2026-08-09:23:25:04,729 INFO [task.py:395] Building contexts for mmlu_business_ethics on rank 0...
|
|||
|
|
0%| | 0/100 [00:00<?, ?it/s]
11%|█ | 11/100 [00:00<00:00, 107.19it/s]
22%|██▏ | 22/100 [00:00<00:00, 106.87it/s]
33%|███▎ | 33/100 [00:00<00:00, 106.88it/s]
44%|████▍ | 44/100 [00:00<00:00, 106.75it/s]
55%|█████▌ | 55/100 [00:00<00:00, 106.92it/s]
66%|██████▌ | 66/100 [00:00<00:00, 106.76it/s]
77%|███████▋ | 77/100 [00:00<00:00, 106.68it/s]
88%|████████▊ | 88/100 [00:00<00:00, 106.72it/s]
99%|█████████▉| 99/100 [00:00<00:00, 106.74it/s]
100%|██████████| 100/100 [00:00<00:00, 106.76it/s]
|
|||
|
|
2026-08-09:23:25:05,669 INFO [task.py:395] Building contexts for mmlu_high_school_mathematics on rank 0...
|
|||
|
|
0%| | 0/270 [00:00<?, ?it/s]
4%|▍ | 11/270 [00:00<00:02, 107.20it/s]
8%|▊ | 22/270 [00:00<00:02, 107.20it/s]
12%|█▏ | 33/270 [00:00<00:02, 107.34it/s]
16%|█▋ | 44/270 [00:00<00:02, 107.19it/s]
20%|██ | 55/270 [00:00<00:02, 107.18it/s]
24%|██▍ | 66/270 [00:00<00:01, 107.00it/s]
29%|██▊ | 77/270 [00:00<00:01, 106.97it/s]
33%|███▎ | 88/270 [00:00<00:01, 106.82it/s]
37%|███▋ | 99/270 [00:00<00:01, 106.89it/s]
41%|████ | 110/270 [00:01<00:01, 107.11it/s]
45%|████▍ | 121/270 [00:01<00:01, 107.25it/s]
49%|████▉ | 132/270 [00:01<00:01, 107.28it/s]
53%|█████▎ | 143/270 [00:01<00:01, 107.38it/s]
57%|█████▋ | 154/270 [00:01<00:01, 107.25it/s]
61%|██████ | 165/270 [00:01<00:00, 107.21it/s]
65%|██████▌ | 176/270 [00:01<00:00, 107.02it/s]
69%|██████▉ | 187/270 [00:01<00:00, 107.02it/s]
73%|███████▎ | 198/270 [00:01<00:00, 106.91it/s]
77%|███████▋ | 209/270 [00:01<00:00, 106.95it/s]
81%|████████▏ | 220/270 [00:02<00:00, 106.95it/s]
86%|████████▌ | 231/270 [00:02<00:00, 107.06it/s]
90%|████████▉ | 242/270 [00:02<00:00, 107.06it/s]
94%|█████████▎| 253/270 [00:02<00:00, 107.04it/s]
98%|█████████▊| 264/270 [00:02<00:00, 107.13it/s]
100%|██████████| 270/270 [00:02<00:00, 107.09it/s]
|
|||
|
|
2026-08-09:23:25:08,197 INFO [task.py:395] Building contexts for mmlu_high_school_chemistry on rank 0...
|
|||
|
|
0%| | 0/203 [00:00<?, ?it/s]
5%|▌ | 11/203 [00:00<00:01, 106.68it/s]
11%|█ | 22/203 [00:00<00:01, 107.06it/s]
16%|█▋ | 33/203 [00:00<00:01, 107.07it/s]
22%|██▏ | 44/203 [00:00<00:01, 106.81it/s]
27%|██▋ | 55/203 [00:00<00:01, 106.83it/s]
33%|███▎ | 66/203 [00:00<00:01, 106.89it/s]
38%|███▊ | 77/203 [00:00<00:01, 107.00it/s]
43%|████▎ | 88/203 [00:00<00:01, 107.09it/s]
49%|████▉ | 99/203 [00:00<00:00, 107.16it/s]
54%|█████▍ | 110/203 [00:01<00:00, 107.29it/s]
60%|█████▉ | 121/203 [00:01<00:00, 107.40it/s]
65%|██████▌ | 132/203 [00:01<00:00, 107.58it/s]
70%|███████ | 143/203 [00:01<00:00, 107.73it/s]
76%|███████▌ | 154/203 [00:01<00:00, 107.89it/s]
81%|████████▏ | 165/203 [00:01<00:00, 107.92it/s]
87%|████████▋ | 176/203 [00:01<00:00, 107.94it/s]
92%|█████████▏| 187/203 [00:01<00:00, 108.13it/s]
98%|█████████▊| 198/203 [00:01<00:00, 108.17it/s]
100%|██████████| 203/203 [00:01<00:00, 107.52it/s]
|
|||
|
|
2026-08-09:23:25:10,091 INFO [task.py:395] Building contexts for mmlu_astronomy on rank 0...
|
|||
|
|
0%| | 0/152 [00:00<?, ?it/s]
7%|▋ | 11/152 [00:00<00:01, 108.36it/s]
14%|█▍ | 22/152 [00:00<00:01, 108.20it/s]
22%|██▏ | 33/152 [00:00<00:01, 108.36it/s]
29%|██▉ | 44/152 [00:00<00:00, 108.43it/s]
36%|███▌ | 55/152 [00:00<00:00, 108.46it/s]
43%|████▎ | 66/152 [00:00<00:00, 108.46it/s]
51%|█████ | 77/152 [00:00<00:00, 108.41it/s]
58%|█████▊ | 88/152 [00:00<00:00, 108.18it/s]
65%|██████▌ | 99/152 [00:00<00:00, 108.23it/s]
72%|███████▏ | 110/152 [00:01<00:00, 108.15it/s]
80%|███████▉ | 121/152 [00:01<00:00, 108.31it/s]
87%|████████▋ | 132/152 [00:01<00:00, 108.30it/s]
94%|█████████▍| 143/152 [00:01<00:00, 108.34it/s]
100%|██████████| 152/152 [00:01<00:00, 108.37it/s]
|
|||
|
|
2026-08-09:23:25:11,498 INFO [task.py:395] Building contexts for mmlu_conceptual_physics on rank 0...
|
|||
|
|
0%| | 0/235 [00:00<?, ?it/s]
5%|▍ | 11/235 [00:00<00:02, 108.42it/s]
9%|▉ | 22/235 [00:00<00:01, 108.63it/s]
14%|█▍ | 33/235 [00:00<00:01, 108.66it/s]
19%|█▊ | 44/235 [00:00<00:01, 108.81it/s]
23%|██▎ | 55/235 [00:00<00:01, 108.84it/s]
28%|██▊ | 66/235 [00:00<00:01, 108.64it/s]
33%|███▎ | 77/235 [00:00<00:01, 108.51it/s]
37%|███▋ | 88/235 [00:00<00:01, 108.25it/s]
42%|████▏ | 99/235 [00:00<00:01, 108.23it/s]
47%|████▋ | 110/235 [00:01<00:01, 108.28it/s]
51%|█████▏ | 121/235 [00:01<00:01, 108.18it/s]
56%|█████▌ | 132/235 [00:01<00:00, 108.20it/s]
61%|██████ | 143/235 [00:01<00:00, 108.20it/s]
66%|██████▌ | 154/235 [00:01<00:00, 108.12it/s]
70%|███████ | 165/235 [00:01<00:00, 108.07it/s]
75%|███████▍ | 176/235 [00:01<00:00, 107.94it/s]
80%|███████▉ | 187/235 [00:01<00:00, 107.91it/s]
84%|████████▍ | 198/235 [00:01<00:00, 107.82it/s]
89%|████████▉ | 209/235 [00:01<00:00, 107.93it/s]
94%|█████████▎| 220/235 [00:02<00:00, 108.12it/s]
98%|█████████▊| 231/235 [00:02<00:00, 108.30it/s]
100%|██████████| 235/235 [00:02<00:00, 108.26it/s]
|
|||
|
|
2026-08-09:23:25:13,675 INFO [task.py:395] Building contexts for mmlu_abstract_algebra on rank 0...
|
|||
|
|
0%| | 0/100 [00:00<?, ?it/s]
11%|█ | 11/100 [00:00<00:00, 107.85it/s]
22%|██▏ | 22/100 [00:00<00:00, 107.73it/s]
33%|███▎ | 33/100 [00:00<00:00, 107.94it/s]
44%|████▍ | 44/100 [00:00<00:00, 107.77it/s]
55%|█████▌ | 55/100 [00:00<00:00, 107.49it/s]
66%|██████▌ | 66/100 [00:00<00:00, 107.37it/s]
77%|███████▋ | 77/100 [00:00<00:00, 107.41it/s]
88%|████████▊ | 88/100 [00:00<00:00, 107.30it/s]
99%|█████████▉| 99/100 [00:00<00:00, 107.16it/s]
100%|██████████| 100/100 [00:00<00:00, 107.41it/s]
|
|||
|
|
2026-08-09:23:25:14,609 INFO [task.py:395] Building contexts for mmlu_college_biology on rank 0...
|
|||
|
|
0%| | 0/144 [00:00<?, ?it/s]
8%|▊ | 11/144 [00:00<00:01, 108.13it/s]
15%|█▌ | 22/144 [00:00<00:01, 108.15it/s]
23%|██▎ | 33/144 [00:00<00:01, 107.92it/s]
31%|███ | 44/144 [00:00<00:00, 108.07it/s]
38%|███▊ | 55/144 [00:00<00:00, 108.13it/s]
46%|████▌ | 66/144 [00:00<00:00, 108.02it/s]
53%|█████▎ | 77/144 [00:00<00:00, 106.79it/s]
61%|██████ | 88/144 [00:00<00:00, 107.30it/s]
69%|██████▉ | 99/144 [00:00<00:00, 107.56it/s]
76%|███████▋ | 110/144 [00:01<00:00, 107.68it/s]
84%|████████▍ | 121/144 [00:01<00:00, 107.82it/s]
92%|█████████▏| 132/144 [00:01<00:00, 108.08it/s]
99%|█████████▉| 143/144 [00:01<00:00, 108.21it/s]
100%|██████████| 144/144 [00:01<00:00, 107.86it/s]
|
|||
|
|
2026-08-09:23:25:15,948 INFO [task.py:395] Building contexts for mmlu_machine_learning on rank 0...
|
|||
|
|
0%| | 0/112 [00:00<?, ?it/s]
10%|▉ | 11/112 [00:00<00:00, 107.82it/s]
20%|█▉ | 22/112 [00:00<00:00, 108.06it/s]
29%|██▉ | 33/112 [00:00<00:00, 108.16it/s]
39%|███▉ | 44/112 [00:00<00:00, 108.03it/s]
49%|████▉ | 55/112 [00:00<00:00, 107.83it/s]
59%|█████▉ | 66/112 [00:00<00:00, 107.71it/s]
69%|██████▉ | 77/112 [00:00<00:00, 107.27it/s]
79%|███████▊ | 88/112 [00:00<00:00, 107.26it/s]
88%|████████▊ | 99/112 [00:00<00:00, 107.12it/s]
98%|█████████▊| 110/112 [00:01<00:00, 106.98it/s]
100%|██████████| 112/112 [00:01<00:00, 107.39it/s]
|
|||
|
|
2026-08-09:23:25:16,994 INFO [task.py:395] Building contexts for mmlu_college_physics on rank 0...
|
|||
|
|
0%| | 0/102 [00:00<?, ?it/s]
11%|█ | 11/102 [00:00<00:00, 106.62it/s]
22%|██▏ | 22/102 [00:00<00:00, 107.00it/s]
32%|███▏ | 33/102 [00:00<00:00, 107.17it/s]
43%|████▎ | 44/102 [00:00<00:00, 107.06it/s]
54%|█████▍ | 55/102 [00:00<00:00, 107.23it/s]
65%|██████▍ | 66/102 [00:00<00:00, 107.28it/s]
75%|███████▌ | 77/102 [00:00<00:00, 107.27it/s]
86%|████████▋ | 88/102 [00:00<00:00, 107.21it/s]
97%|█████████▋| 99/102 [00:00<00:00, 107.30it/s]
100%|██████████| 102/102 [00:00<00:00, 107.17it/s]
|
|||
|
|
2026-08-09:23:25:17,949 INFO [task.py:395] Building contexts for mmlu_college_mathematics on rank 0...
|
|||
|
|
0%| | 0/100 [00:00<?, ?it/s]
11%|█ | 11/100 [00:00<00:00, 107.46it/s]
22%|██▏ | 22/100 [00:00<00:00, 107.23it/s]
33%|███▎ | 33/100 [00:00<00:00, 107.07it/s]
44%|████▍ | 44/100 [00:00<00:00, 107.16it/s]
55%|█████▌ | 55/100 [00:00<00:00, 107.15it/s]
66%|██████▌ | 66/100 [00:00<00:00, 107.17it/s]
77%|███████▋ | 77/100 [00:00<00:00, 107.20it/s]
88%|████████▊ | 88/100 [00:00<00:00, 107.21it/s]
99%|█████████▉| 99/100 [00:00<00:00, 107.14it/s]
100%|██████████| 100/100 [00:00<00:00, 107.16it/s]
|
|||
|
|
2026-08-09:23:25:18,885 INFO [task.py:395] Building contexts for mmlu_computer_security on rank 0...
|
|||
|
|
0%| | 0/100 [00:00<?, ?it/s]
11%|█ | 11/100 [00:00<00:00, 106.94it/s]
22%|██▏ | 22/100 [00:00<00:00, 107.02it/s]
33%|███▎ | 33/100 [00:00<00:00, 107.03it/s]
44%|████▍ | 44/100 [00:00<00:00, 107.30it/s]
55%|█████▌ | 55/100 [00:00<00:00, 107.24it/s]
66%|██████▌ | 66/100 [00:00<00:00, 107.27it/s]
77%|███████▋ | 77/100 [00:00<00:00, 107.37it/s]
88%|████████▊ | 88/100 [00:00<00:00, 107.56it/s]
99%|█████████▉| 99/100 [00:00<00:00, 107.66it/s]
100%|██████████| 100/100 [00:00<00:00, 107.37it/s]
|
|||
|
|
2026-08-09:23:25:19,819 INFO [task.py:395] Building contexts for mmlu_electrical_engineering on rank 0...
|
|||
|
|
0%| | 0/145 [00:00<?, ?it/s]
8%|▊ | 11/145 [00:00<00:01, 108.43it/s]
15%|█▌ | 22/145 [00:00<00:01, 108.51it/s]
23%|██▎ | 33/145 [00:00<00:01, 108.39it/s]
30%|███ | 44/145 [00:00<00:00, 108.24it/s]
38%|███▊ | 55/145 [00:00<00:00, 108.19it/s]
46%|████▌ | 66/145 [00:00<00:00, 108.03it/s]
53%|█████▎ | 77/145 [00:00<00:00, 107.99it/s]
61%|██████ | 88/145 [00:00<00:00, 107.87it/s]
68%|██████▊ | 99/145 [00:00<00:00, 107.85it/s]
76%|███████▌ | 110/145 [00:01<00:00, 107.73it/s]
83%|████████▎ | 121/145 [00:01<00:00, 107.62it/s]
91%|█████████ | 132/145 [00:01<00:00, 107.46it/s]
99%|█████████▊| 143/145 [00:01<00:00, 107.18it/s]
100%|██████████| 145/145 [00:01<00:00, 107.75it/s]
|
|||
|
|
2026-08-09:23:25:21,169 INFO [task.py:395] Building contexts for mmlu_college_chemistry on rank 0...
|
|||
|
|
0%| | 0/100 [00:00<?, ?it/s]
11%|█ | 11/100 [00:00<00:00, 105.91it/s]
22%|██▏ | 22/100 [00:00<00:00, 106.04it/s]
33%|███▎ | 33/100 [00:00<00:00, 105.96it/s]
44%|████▍ | 44/100 [00:00<00:00, 105.99it/s]
55%|█████▌ | 55/100 [00:00<00:00, 106.00it/s]
66%|██████▌ | 66/100 [00:00<00:00, 106.21it/s]
77%|███████▋ | 77/100 [00:00<00:00, 106.24it/s]
88%|████████▊ | 88/100 [00:00<00:00, 106.10it/s]
99%|█████████▉| 99/100 [00:00<00:00, 106.14it/s]
100%|██████████| 100/100 [00:00<00:00, 106.06it/s]
|
|||
|
|
2026-08-09:23:25:22,115 INFO [task.py:395] Building contexts for mmlu_elementary_mathematics on rank 0...
|
|||
|
|
0%| | 0/378 [00:00<?, ?it/s]
3%|▎ | 11/378 [00:00<00:03, 107.92it/s]
6%|▌ | 22/378 [00:00<00:03, 107.74it/s]
9%|▊ | 33/378 [00:00<00:03, 107.78it/s]
12%|█▏ | 44/378 [00:00<00:03, 107.84it/s]
15%|█▍ | 55/378 [00:00<00:02, 107.92it/s]
17%|█▋ | 66/378 [00:00<00:02, 107.77it/s]
20%|██ | 77/378 [00:00<00:02, 107.83it/s]
23%|██▎ | 88/378 [00:00<00:02, 107.93it/s]
26%|██▌ | 99/378 [00:00<00:02, 107.99it/s]
29%|██▉ | 110/378 [00:01<00:02, 107.80it/s]
32%|███▏ | 121/378 [00:01<00:02, 107.70it/s]
35%|███▍ | 132/378 [00:01<00:02, 107.53it/s]
38%|███▊ | 143/378 [00:01<00:02, 107.55it/s]
41%|████ | 154/378 [00:01<00:02, 107.69it/s]
44%|████▎ | 165/378 [00:01<00:01, 107.73it/s]
47%|████▋ | 176/378 [00:01<00:01, 107.80it/s]
49%|████▉ | 187/378 [00:01<00:01, 107.86it/s]
52%|█████▏ | 198/378 [00:01<00:01, 107.65it/s]
55%|█████▌ | 209/378 [00:01<00:01, 107.34it/s]
58%|█████▊ | 220/378 [00:02<00:01, 107.31it/s]
61%|██████ | 231/378 [00:02<00:01, 107.14it/s]
64%|██████▍ | 242/378 [00:02<00:01, 107.09it/s]
67%|██████▋ | 253/378 [00:02<00:01, 107.11it/s]
70%|██████▉ | 264/378 [00:02<00:01, 107.31it/s]
73%|███████▎ | 275/378 [00:02<00:00, 107.38it/s]
76%|███████▌ | 286/378 [00:02<00:00, 107.24it/s]
79%|███████▊ | 297/378 [00:02<00:00, 107.29it/s]
81%|████████▏ | 308/378 [00:02<00:00, 107.36it/s]
84%|████████▍ | 319/378 [00:02<00:00, 107.15it/s]
87%|████████▋ | 330/378 [00:03<00:00, 107.21it/s]
90%|█████████ | 341/378 [00:03<00:00, 107.06it/s]
93%|█████████▎| 352/378 [00:03<00:00, 107.13it/s]
96%|█████████▌| 363/378 [00:03<00:00, 107.14it/s]
99%|█████████▉| 374/378 [00:03<00:00, 107.27it/s]
100%|██████████| 378/378 [00:03<00:00, 107.47it/s]
|
|||
|
|
2026-08-09:23:25:25,642 INFO [task.py:395] Building contexts for mmlu_high_school_statistics on rank 0...
|
|||
|
|
0%| | 0/216 [00:00<?, ?it/s]
5%|▌ | 11/216 [00:00<00:01, 107.60it/s]
10%|█ | 22/216 [00:00<00:01, 107.47it/s]
15%|█▌ | 33/216 [00:00<00:01, 107.74it/s]
20%|██ | 44/216 [00:00<00:01, 107.72it/s]
25%|██▌ | 55/216 [00:00<00:01, 107.59it/s]
31%|███ | 66/216 [00:00<00:01, 107.51it/s]
36%|███▌ | 77/216 [00:00<00:01, 107.53it/s]
41%|████ | 88/216 [00:00<00:01, 107.53it/s]
46%|████▌ | 99/216 [00:00<00:01, 107.52it/s]
51%|█████ | 110/216 [00:01<00:00, 107.74it/s]
56%|█████▌ | 121/216 [00:01<00:00, 107.82it/s]
61%|██████ | 132/216 [00:01<00:00, 107.67it/s]
66%|██████▌ | 143/216 [00:01<00:00, 107.48it/s]
71%|███████▏ | 154/216 [00:01<00:00, 107.39it/s]
76%|███████▋ | 165/216 [00:01<00:00, 107.46it/s]
81%|████████▏ | 176/216 [00:01<00:00, 107.48it/s]
87%|████████▋ | 187/216 [00:01<00:00, 107.35it/s]
92%|█████████▏| 198/216 [00:01<00:00, 107.45it/s]
97%|█████████▋| 209/216 [00:01<00:00, 107.40it/s]
100%|██████████| 216/216 [00:02<00:00, 107.51it/s]
|
|||
|
|
2026-08-09:23:25:27,657 INFO [task.py:395] Building contexts for mmlu_high_school_biology on rank 0...
|
|||
|
|
0%| | 0/310 [00:00<?, ?it/s]
4%|▎ | 11/310 [00:00<00:02, 106.20it/s]
7%|▋ | 22/310 [00:00<00:02, 106.69it/s]
11%|█ | 33/310 [00:00<00:02, 106.70it/s]
14%|█▍ | 44/310 [00:00<00:02, 106.27it/s]
18%|█▊ | 55/310 [00:00<00:02, 106.29it/s]
21%|██▏ | 66/310 [00:00<00:02, 106.30it/s]
25%|██▍ | 77/310 [00:00<00:02, 106.29it/s]
28%|██▊ | 88/310 [00:00<00:02, 106.26it/s]
32%|███▏ | 99/310 [00:00<00:01, 106.35it/s]
35%|███▌ | 110/310 [00:01<00:01, 106.51it/s]
39%|███▉ | 121/310 [00:01<00:01, 106.54it/s]
43%|████▎ | 132/310 [00:01<00:01, 106.44it/s]
46%|████▌ | 143/310 [00:01<00:01, 106.29it/s]
50%|████▉ | 154/310 [00:01<00:01, 106.43it/s]
53%|█████▎ | 165/310 [00:01<00:01, 106.30it/s]
57%|█████▋ | 176/310 [00:01<00:01, 106.13it/s]
60%|██████ | 187/310 [00:01<00:01, 106.19it/s]
64%|██████▍ | 198/310 [00:01<00:01, 106.17it/s]
67%|██████▋ | 209/310 [00:01<00:00, 106.29it/s]
71%|███████ | 220/310 [00:02<00:00, 106.40it/s]
75%|███████▍ | 231/310 [00:02<00:00, 106.52it/s]
78%|███████▊ | 242/310 [00:02<00:00, 106.72it/s]
82%|████████▏ | 253/310 [00:02<00:00, 106.43it/s]
85%|████████▌ | 264/310 [00:02<00:00, 106.53it/s]
89%|████████▊ | 275/310 [00:02<00:00, 106.68it/s]
92%|█████████▏| 286/310 [00:02<00:00, 106.64it/s]
96%|█████████▌| 297/310 [00:02<00:00, 106.71it/s]
99%|█████████▉| 308/310 [00:02<00:00, 106.83it/s]
100%|██████████| 310/310 [00:02<00:00, 106.47it/s]
|
|||
|
|
2026-08-09:23:25:30,577 INFO [task.py:395] Building contexts for mmlu_anatomy on rank 0...
|
|||
|
|
0%| | 0/135 [00:00<?, ?it/s]
8%|▊ | 11/135 [00:00<00:01, 107.84it/s]
16%|█▋ | 22/135 [00:00<00:01, 108.19it/s]
24%|██▍ | 33/135 [00:00<00:00, 107.87it/s]
33%|███▎ | 44/135 [00:00<00:00, 108.20it/s]
41%|████ | 55/135 [00:00<00:00, 108.01it/s]
49%|████▉ | 66/135 [00:00<00:00, 107.92it/s]
57%|█████▋ | 77/135 [00:00<00:00, 107.66it/s]
65%|██████▌ | 88/135 [00:00<00:00, 107.79it/s]
73%|███████▎ | 99/135 [00:00<00:00, 107.85it/s]
81%|████████▏ | 110/135 [00:01<00:00, 108.00it/s]
90%|████████▉ | 121/135 [00:01<00:00, 107.99it/s]
98%|█████████▊| 132/135 [00:01<00:00, 108.13it/s]
100%|██████████| 135/135 [00:01<00:00, 107.98it/s]
|
|||
|
|
2026-08-09:23:25:31,831 INFO [task.py:395] Building contexts for mmlu_high_school_physics on rank 0...
|
|||
|
|
0%| | 0/151 [00:00<?, ?it/s]
7%|▋ | 11/151 [00:00<00:01, 107.63it/s]
15%|█▍ | 22/151 [00:00<00:01, 107.71it/s]
22%|██▏ | 33/151 [00:00<00:01, 107.41it/s]
29%|██▉ | 44/151 [00:00<00:00, 107.37it/s]
36%|███▋ | 55/151 [00:00<00:00, 107.38it/s]
44%|████▎ | 66/151 [00:00<00:00, 107.41it/s]
51%|█████ | 77/151 [00:00<00:00, 107.52it/s]
58%|█████▊ | 88/151 [00:00<00:00, 107.41it/s]
66%|██████▌ | 99/151 [00:00<00:00, 107.42it/s]
73%|███████▎ | 110/151 [00:01<00:00, 107.48it/s]
80%|████████ | 121/151 [00:01<00:00, 107.38it/s]
87%|████████▋ | 132/151 [00:01<00:00, 107.23it/s]
95%|█████████▍| 143/151 [00:01<00:00, 107.25it/s]
100%|██████████| 151/151 [00:01<00:00, 107.34it/s]
|
|||
|
|
2026-08-09:23:25:33,242 INFO [task.py:395] Building contexts for mmlu_high_school_computer_science on rank 0...
|
|||
|
|
0%| | 0/100 [00:00<?, ?it/s]
11%|█ | 11/100 [00:00<00:00, 106.55it/s]
22%|██▏ | 22/100 [00:00<00:00, 107.06it/s]
33%|███▎ | 33/100 [00:00<00:00, 107.35it/s]
44%|████▍ | 44/100 [00:00<00:00, 107.24it/s]
55%|█████▌ | 55/100 [00:00<00:00, 107.09it/s]
66%|██████▌ | 66/100 [00:00<00:00, 107.05it/s]
77%|███████▋ | 77/100 [00:00<00:00, 107.09it/s]
88%|████████▊ | 88/100 [00:00<00:00, 106.99it/s]
99%|█████████▉| 99/100 [00:00<00:00, 106.98it/s]
100%|██████████| 100/100 [00:00<00:00, 107.01it/s]
|
|||
|
|
2026-08-09:23:25:34,179 INFO [task.py:395] Building contexts for mmlu_college_computer_science on rank 0...
|
|||
|
|
0%| | 0/100 [00:00<?, ?it/s]
11%|█ | 11/100 [00:00<00:00, 107.33it/s]
22%|██▏ | 22/100 [00:00<00:00, 107.67it/s]
33%|███▎ | 33/100 [00:00<00:00, 107.63it/s]
44%|████▍ | 44/100 [00:00<00:00, 107.51it/s]
55%|█████▌ | 55/100 [00:00<00:00, 107.67it/s]
66%|██████▌ | 66/100 [00:00<00:00, 107.78it/s]
77%|███████▋ | 77/100 [00:00<00:00, 107.80it/s]
88%|████████▊ | 88/100 [00:00<00:00, 107.98it/s]
99%|█████████▉| 99/100 [00:00<00:00, 107.89it/s]
100%|██████████| 100/100 [00:00<00:00, 107.76it/s]
|
|||
|
|
2026-08-09:23:25:35,110 INFO [evaluator.py:362] Running loglikelihood requests
|
|||
|
|
Token indices sequence length is longer than the specified maximum sequence length for this model (1682 > 1024). Running this sequence through the model will result in indexing errors
|
|||
|
|
Running loglikelihood requests: 0%| | 0/56168 [00:00<?, ?it/s]
Running loglikelihood requests: 0%| | 1/56168 [00:00<9:55:37, 1.57it/s]
Running loglikelihood requests: 0%| | 65/56168 [00:00<09:15, 100.95it/s]
Running loglikelihood requests: 0%| | 125/56168 [00:00<04:52, 191.89it/s]
Running loglikelihood requests: 0%| | 163/56168 [00:01<04:51, 192.24it/s]
Running loglikelihood requests: 0%| | 213/56168 [00:01<03:41, 252.95it/s]
Running loglikelihood requests: 0%| | 257/56168 [00:01<03:50, 242.65it/s]
Running loglikelihood requests: 1%| | 305/56168 [00:01<03:11, 291.42it/s]
Running loglikelihood requests: 1%| | 343/56168 [00:01<02:59, 310.23it/s]
Running loglikelihood requests: 1%| | 381/56168 [00:01<02:50, 327.13it/s]
Running loglikelihood requests: 1%| | 419/56168 [00:01<03:24, 272.87it/s]
Running loglikelihood requests: 1%| | 461/56168 [00:02<03:01, 306.42it/s]
Running loglikelihood requests: 1%| | 513/56168 [00:02<03:11, 290.09it/s]
Running loglikelihood requests: 1%| | 556/56168 [00:02<02:53, 320.98it/s]
Running loglikelihood requests: 1%| | 609/56168 [00:02<03:03, 302.65it/s]
Running loglikelihood requests: 1%| | 650/56168 [00:02<02:50, 326.07it/s]
Running loglikelihood requests: 1%|▏ | 705/56168 [00:02<02:59, 308.32it/s]
Running loglikelihood requests: 1%|▏ | 753/56168 [00:02<02:40, 345.46it/s]
Running loglikelihood requests: 1%|▏ | 801/56168 [00:03<03:00, 307.47it/s]
Running loglikelihood requests: 1%|▏ | 835/56168 [00:03<02:56, 314.12it/s]
Running loglikelihood requests: 2%|▏ | 889/56168 [00:03<02:30, 367.18it/s]
Running loglikelihood requests: 2%|▏ | 929/56168 [00:03<03:01, 304.41it/s]
Running loglikelihood requests: 2%|▏ | 965/56168 [00:03<02:54, 316.93it/s]
Running loglikelihood requests: 2%|▏ | 1000/56168 [00:03<02:50, 324.44it/s]
Running loglikelihood requests: 2%|▏ | 1035/56168 [00:03<02:47, 330.05it/s]
Running loglikelihood requests: 2%|▏ | 1070/56168 [00:03<02:44, 334.60it/s]
Running loglikelihood requests: 2%|▏ | 1105/56168 [00:04<02:42, 338.86it/s]
Running loglikelihood requests: 2%|▏ | 1153/56168 [00:04<03:04, 298.93it/s]
Running loglikelihood requests: 2%|▏ | 1213/56168 [00:04<02:27, 371.74it/s]
Running loglikelihood requests: 2%|▏ | 1254/56168 [00:04<02:58, 308.43it/s]
Running loglikelihood requests: 2%|▏ | 1310/56168 [00:04<02:29, 365.98it/s]
Running loglikelihood requests: 2%|▏ | 1351/56168 [00:04<02:58, 307.19it/s]
Running loglikelihood requests: 3%|▎ | 1409/56168 [00:04<03:00, 302.65it/s]
Running loglikelihood requests: 3%|▎ | 1453/56168 [00:05<02:45, 331.13it/s]
Running loglikelihood requests: 3%|▎ | 1490/56168 [00:05<02:41, 339.43it/s]
Running loglikelihood requests: 3%|▎ | 1537/56168 [00:05<03:01, 300.63it/s]
Running loglikelihood requests: 3%|▎ | 1570/56168 [00:05<02:58, 306.72it/s]
Running loglikelihood requests: 3%|▎ | 1607/56168 [00:05<02:49, 321.87it/s]
Running loglikelihood requests: 3%|▎ | 1657/56168 [00:05<02:28, 367.32it/s]
Running loglikelihood requests: 3%|▎ | 1697/56168 [00:05<03:00, 301.82it/s]
Running loglikelihood requests: 3%|▎ | 1731/56168 [00:05<02:55, 309.70it/s]
Running loglikelihood requests: 3%|▎ | 1765/56168 [00:06<02:51, 317.14it/s]
Running loglikelihood requests: 3%|▎ | 1799/56168 [00:06<02:48, 323.03it/s]
Running loglikelihood requests: 3%|▎ | 1857/56168 [00:06<02:54, 311.19it/s]
Running loglikelihood requests: 3%|▎ | 1902/56168 [00:06<02:37, 343.89it/s]
Running loglikelihood requests: 3%|▎ | 1953/56168 [00:06<02:53, 312.21it/s]
Running loglikelihood requests: 4%|▎ | 1987/56168 [00:06<02:50, 317.79it/s]
Running loglikelihood requ
|
|||
|
|
fatal: not a git repository (or any parent up to mount point /home)
|
|||
|
|
Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
|
|||
|
|
hf (pretrained=/home/zeus/microllm2/microllm2-checkpoints/final_merged,dtype=bfloat16,trust_remote_code=False), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: 8
|
|||
|
|
| Tasks |Version|Filter|n-shot|Metric|Value | |Stderr|
|
|||
|
|
|---------------------------------------|-------|------|-----:|------|-----:|---|-----:|
|
|||
|
|
|mmlu |N/A |none | 0|acc |0.2610|± |0.0037|
|
|||
|
|
| - humanities |N/A |none | 5|acc |0.2623|± |0.0064|
|
|||
|
|
| - formal_logic | 0|none | 5|acc |0.1667|± |0.0333|
|
|||
|
|
| - high_school_european_history | 0|none | 5|acc |0.2970|± |0.0357|
|
|||
|
|
| - high_school_us_history | 0|none | 5|acc |0.2745|± |0.0313|
|
|||
|
|
| - high_school_world_history | 0|none | 5|acc |0.2321|± |0.0275|
|
|||
|
|
| - international_law | 0|none | 5|acc |0.3554|± |0.0437|
|
|||
|
|
| - jurisprudence | 0|none | 5|acc |0.2870|± |0.0437|
|
|||
|
|
| - logical_fallacies | 0|none | 5|acc |0.2883|± |0.0356|
|
|||
|
|
| - moral_disputes | 0|none | 5|acc |0.2803|± |0.0242|
|
|||
|
|
| - moral_scenarios | 0|none | 5|acc |0.2525|± |0.0145|
|
|||
|
|
| - philosophy | 0|none | 5|acc |0.3248|± |0.0266|
|
|||
|
|
| - prehistory | 0|none | 5|acc |0.2500|± |0.0241|
|
|||
|
|
| - professional_law | 0|none | 5|acc |0.2471|± |0.0110|
|
|||
|
|
| - world_religions | 0|none | 5|acc |0.2807|± |0.0345|
|
|||
|
|
| - other |N/A |none | 5|acc |0.2671|± |0.0079|
|
|||
|
|
| - business_ethics | 0|none | 5|acc |0.2300|± |0.0423|
|
|||
|
|
| - clinical_knowledge | 0|none | 5|acc |0.2377|± |0.0262|
|
|||
|
|
| - college_medicine | 0|none | 5|acc |0.2543|± |0.0332|
|
|||
|
|
| - global_facts | 0|none | 5|acc |0.3100|± |0.0465|
|
|||
|
|
| - human_aging | 0|none | 5|acc |0.3049|± |0.0309|
|
|||
|
|
| - management | 0|none | 5|acc |0.2427|± |0.0425|
|
|||
|
|
| - marketing | 0|none | 5|acc |0.2778|± |0.0293|
|
|||
|
|
| - medical_genetics | 0|none | 5|acc |0.3300|± |0.0473|
|
|||
|
|
| - miscellaneous | 0|none | 5|acc |0.2771|± |0.0160|
|
|||
|
|
| - nutrition | 0|none | 5|acc |0.2451|± |0.0246|
|
|||
|
|
| - professional_accounting | 0|none | 5|acc |0.2695|± |0.0265|
|
|||
|
|
| - professional_medicine | 0|none | 5|acc |0.2169|± |0.0250|
|
|||
|
|
| - virology | 0|none | 5|acc |0.3072|± |0.0359|
|
|||
|
|
| - social_sciences |N/A |none | 5|acc |0.2343|± |0.0076|
|
|||
|
|
| - econometrics | 0|none | 5|acc |0.2456|± |0.0405|
|
|||
|
|
| - high_school_geography | 0|none | 5|acc |0.2525|± |0.0310|
|
|||
|
|
| - high_school_government_and_politics| 0|none | 5|acc |0.2228|± |0.0300|
|
|||
|
|
| - high_school_macroeconomics | 0|none | 5|acc |0.2462|± |0.0218|
|
|||
|
|
| - high_school_microeconomics | 0|none | 5|acc |0.2059|± |0.0263|
|
|||
|
|
| - high_school_psychology | 0|none | 5|acc |0.2404|± |0.0183|
|
|||
|
|
| - human_sexuality | 0|none | 5|acc |0.1908|± |0.0345|
|
|||
|
|
| - professional_psychology | 0|none | 5|acc |0.2647|± |0.0178|
|
|||
|
|
| - public_relations | 0|none | 5|acc |0.2909|± |0.0435|
|
|||
|
|
| - security_studies | 0|none | 5|acc |0.1673|± |0.0239|
|
|||
|
|
| - sociology | 0|none | 5|acc |0.2239|± |0.0295|
|
|||
|
|
| - us_foreign_policy | 0|none | 5|acc |0.1900|± |0.0394|
|
|||
|
|
| - stem |N/A |none | 5|acc |0.2791|± |0.0080|
|
|||
|
|
| - abstract_algebra | 0|none | 5|acc |0.2500|± |0.0435|
|
|||
|
|
| - anatomy | 0|none | 5|acc |0.3481|± |0.0412|
|
|||
|
|
| - astronomy | 0|none | 5|acc |0.3355|± |0.0384|
|
|||
|
|
| - college_biology | 0|none | 5|acc |0.2847|± |0.0377|
|
|||
|
|
| - college_chemistry | 0|none | 5|acc |0.1700|± |0.0378|
|
|||
|
|
| - college_computer_science | 0|none | 5|acc |0.3300|± |0.0473|
|
|||
|
|
| - college_mathematics | 0|none | 5|acc |0.3200|± |0.0469|
|
|||
|
|
| - college_physics | 0|none | 5|acc |0.2549|± |0.0434|
|
|||
|
|
| - computer_security | 0|none | 5|acc |0.3000|± |0.0461|
|
|||
|
|
| - conceptual_physics | 0|none | 5|acc |0.2170|± |0.0269|
|
|||
|
|
| - electrical_engineering | 0|none | 5|acc |0.2897|± |0.0378|
|
|||
|
|
| - elementary_mathematics | 0|none | 5|acc |0.2672|± |0.0228|
|
|||
|
|
| - high_school_biology | 0|none | 5|acc |0.2645|± |0.0251|
|
|||
|
|
| - high_school_chemistry | 0|none | 5|acc |0.2365|± |0.0299|
|
|||
|
|
| - high_school_computer_science | 0|none | 5|acc |0.3300|± |0.0473|
|
|||
|
|
| - high_school_mathematics | 0|none | 5|acc |0.2593|± |0.0267|
|
|||
|
|
| - high_school_physics | 0|none | 5|acc |0.2715|± |0.0363|
|
|||
|
|
| - high_school_statistics | 0|none | 5|acc |0.3519|± |0.0326|
|
|||
|
|
| - machine_learning | 0|none | 5|acc |0.3036|± |0.0436|
|
|||
|
|
|
|||
|
|
| Groups |Version|Filter|n-shot|Metric|Value | |Stderr|
|
|||
|
|
|------------------|-------|------|-----:|------|-----:|---|-----:|
|
|||
|
|
|mmlu |N/A |none | 0|acc |0.2610|± |0.0037|
|
|||
|
|
| - humanities |N/A |none | 5|acc |0.2623|± |0.0064|
|
|||
|
|
| - other |N/A |none | 5|acc |0.2671|± |0.0079|
|
|||
|
|
| - social_sciences|N/A |none | 5|acc |0.2343|± |0.0076|
|
|||
|
|
| - stem |N/A |none | 5|acc |0.2791|± |0.0080|
|
|||
|
|
|
|||
|
|
[LM-EVAL] exit 0 at Sun Aug 9 23:29:33 UTC 2026
|
|||
|
|
total 88K
|
|||
|
|
-rw-r--r-- 1 adelynmosley2369 adelynmosley2369 85K Aug 9 23:29 results.json
|
|||
|
|
{
|
|||
|
|
"results": {
|
|||
|
|
"mmlu": {
|
|||
|
|
"acc,none": 0.26100270616721266,
|
|||
|
|
"acc_stderr,none": 0.0037004678245414263,
|
|||
|
|
"alias": "mmlu"
|
|||
|
|
},
|
|||
|
|
"mmlu_humanities": {
|
|||
|
|
"alias": " - humanities",
|
|||
|
|
"acc,none": 0.2622741764080765,
|
|||
|
|
"acc_stderr,none": 0.006405056497034186
|
|||
|
|
},
|
|||
|
|
"mmlu_formal_logic": {
|
|||
|
|
"alias": " - formal_logic",
|
|||
|
|
"acc,none": 0.16666666666666666,
|
|||
|
|
"acc_stderr,none": 0.03333333333333333
|
|||
|
|
},
|
|||
|
|
"mmlu_high_school_european_history": {
|
|||
|
|
"alias": " - high_school_european_history",
|
|||
|
|
"acc,none": 0.296969696969697,
|
|||
|
|
"acc_stderr,none": 0.03567969772268046
|
|||
|
|
},
|
|||
|
|
"mmlu_high_school_us_history": {
|
|||
|
|
"alias": " - high_school_us_history",
|
|||
|
|
"acc,none": 0.27450980392156865,
|
|||
|
|
"acc_stderr,none": 0.03132179803083291
|
|||
|
|
},
|
|||
|
|
"mmlu_high_school_world_history": {
|
|||
|
|
"alias": " - high_school_world_history",
|
|||
|
|
"acc,none": 0.2320675105485232,
|
|||
|
|
"acc_stderr,none": 0.027479744550808465
|
|||
|
|
},
|
|||
|
|
"mmlu_international_law": {
|
|||
|
|
"alias": " - international_law",
|
|||
|
|
"acc,none": 0.35537190082644626,
|
|||
|
|
"acc_stderr,none": 0.043692363265739845
|
|||
|
|
},
|
|||
|
|
"mmlu_jurisprudence": {
|
|||
|
|
"alias": " - jurisprudence",
|
|||
|
|
"acc,none": 0.28703703703703703,
|
|||
|
|
"acc_stderr,none": 0.04373313040914761
|
|||
|
|
},
|
|||
|
|
"mmlu_logical_fallacies": {
|
|||
|
|
"alias": " - logical_fallacies",
|
|||
|
|
"acc,none": 0.2883435582822086,
|
|||
|
|
"acc_stderr,none": 0.03559039531617345
|
|||
|
|
},
|
|||
|
|
"mmlu_moral_disputes": {
|
|||
|
|
"alias": " - moral_disputes",
|
|||
|
|
"acc,none": 0.28034682080924855,
|
|||
|
|
"acc_stderr,none": 0.024182427496577626
|
|||
|
|
},
|
|||
|
|
"mmlu_moral_scenarios": {
|
|||
|
|
"alias": " - moral_scenarios",
|
|||
|
|
"acc,none": 0.25251396648044694,
|
|||
|
|
"acc_stderr,none": 0.014530330201468655
|
|||
|
|
},
|
|||
|
|
"mmlu_philosophy": {
|
|||
|
|
"alias": " - philosophy",
|
|||
|
|
"acc,none": 0.3247588424437299,
|
|||
|
|
"acc_stderr,none": 0.02659678228769707
|
|||
|
|
},
|
|||
|
|
"mmlu_prehistory": {
|
|||
|
|
"alias": " - prehistory",
|
|||
|
|
"acc,none": 0.25,
|
|||
|
|
"acc_stderr,none": 0.02409347123262133
|
|||
|
|
},
|
|||
|
|
"mmlu_professional_law": {
|
|||
|
|
"alias": " - professional_law",
|
|||
|
|
"acc,none": 0.2470664928292047,
|
|||
|
|
"acc_stderr,none": 0.011015752255279445
|
|||
|
|
},
|
|||
|
|
"mmlu_world_religions": {
|
|||
|
|
"alias": " - world_religions",
|
|||
|
|
"acc,none": 0.2807017543859649,
|
|||
|
|
"acc_stderr,none": 0.03446296217088429
|
|||
|
|
},
|
|||
|
|
"mmlu_other": {
|
|||
|
|
"alias": " - other",
|
|||
|
|
"acc,none": 0.2671387190215642,
|
|||
|
|
"acc_stderr,none": 0.007937843638596481
|
|||
|
|
},
|
|||
|
|
"mmlu_business_ethics": {
|
|||
|
|
"alias": " - business_ethics",
|
|||
|
|
"acc,none": 0.23,
|
|||
|
|
"acc_stderr,none": 0.04229525846816507
|
|||
|
|
},
|
|||
|
|
"mmlu_clinical_knowledge": {
|
|||
|
|
"alias": " - clinical_knowledge",
|
|||
|
|
"acc,none": 0.23773584905660378,
|
|||
|
|
"acc_stderr,none": 0.02619980880756196
|
|||
|
|
},
|
|||
|
|
"mmlu_college_medicine": {
|
|||
|
|
"alias": " - college_medicine",
|
|||
|
|
"acc,none": 0.2543352601156069,
|
|||
|
|
"acc_stderr,none": 0.03320556443085566
|
|||
|
|
},
|
|||
|
|
"mmlu_global_facts": {
|
|||
|
|
"alias": " - global_facts",
|
|||
|
|
"acc,none": 0.31,
|
|||
|
|
"acc_stderr,none": 0.04648231987117317
|
|||
|
|
},
|
|||
|
|
"mmlu_human_aging": {
|
|||
|
|
"alias": " - human_aging",
|
|||
|
|
"acc,none": 0.30493273542600896,
|
|||
|
|
"acc_stderr,none": 0.03089861088247754
|
|||
|
|
},
|
|||
|
|
"mmlu_management": {
|
|||
|
|
"alias": " - management",
|
|||
|
|
"acc,none": 0.24271844660194175,
|
|||
|
|
"acc_stderr,none": 0.04245022486384496
|
|||
|
|
},
|
|||
|
|
"mmlu_marketing": {
|
|||
|
|
"alias": " - marketing",
|
|||
|
|
"acc,none": 0.2777777777777778,
|
|||
|
|
"acc_stderr,none": 0.029343114798094483
|
|||
|
|
},
|
|||
|
|
"mmlu_medical_genetics": {
|
|||
|
|
"alias": " - medical_genetics",
|
|||
|
|
"acc,none": 0.33,
|
|||
|
|
"acc_stderr,none": 0.04725815626252609
|
|||
|
|
},
|
|||
|
|
"mmlu_miscellaneous": {
|
|||
|
|
"alias": " - miscellaneous",
|
|||
|
|
"acc,none": 0.2771392081736909,
|
|||
|
|
"acc_stderr,none": 0.01600563629412252
|
|||
|
|
},
|
|||
|
|
"mmlu_nutrition": {
|
|||
|
|
"alias": " - nutrition",
|
|||
|
|
"acc,none": 0.24509803921568626,
|
|||
|
|
"acc_stderr,none": 0.024630048979824716
|
|||
|
|
},
|
|||
|
|
"mmlu_professional_accounting": {
|
|||
|
|
"alias": " - professional_accounting",
|
|||
|
|
"acc,none": 0.2695035460992908,
|
|||
|
|
"acc_stderr,none": 0.02646903681859067
|
|||
|
|
},
|
|||
|
|
"mmlu_professional_medicine": {
|
|||
|
|
"alias": " - professional_medicine",
|
|||
|
|
"acc,none": 0.21691176470588236,
|
|||
|
|
"acc_stderr,none": 0.025035845227711254
|
|||
|
|
},
|
|||
|
|
"mmlu_virology": {
|
|||
|
|
"alias": " - virology",
|
|||
|
|
"acc,none": 0.3072289156626506,
|
|||
|
|
"acc_stderr,none": 0.03591566797824665
|
|||
|
|
},
|
|||
|
|
"mmlu_social_sciences": {
|
|||
|
|
"alias": " - social_sciences",
|
|||
|
|
"acc,none": 0.23431914202144946,
|
|||
|
|
"acc_stderr,none": 0.007631090779162625
|
|||
|
|
},
|
|||
|
|
"mmlu_econometrics": {
|
|||
|
|
"alias": " - econometrics",
|
|||
|
|
"acc,none": 0.24561403508771928,
|
|||
|
|
"acc_stderr,none": 0.040493392977481425
|
|||
|
|
},
|
|||
|
|
"mmlu_high_school_geography": {
|
|||
|
|
"alias": " - high_school_geography",
|
|||
|
|
"acc,none": 0.25252525252525254,
|
|||
|
|
"acc_stderr,none": 0.03095405547036587
|
|||
|
|
},
|
|||
|
|
"mmlu_high_school_government_and_politics": {
|
|||
|
|
"alias": " - high_school_government_and_politics",
|
|||
|
|
"acc,none": 0.22279792746113988,
|
|||
|
|
"acc_stderr,none": 0.030031147977641528
|
|||
|
|
},
|
|||
|
|
"mmlu_high_school_macroeconomics": {
|
|||
|
|
"alias": " - high_school_macroeconomics",
|
|||
|
|
"acc,none": 0.24615384615384617,
|
|||
|
|
"acc_stderr,none": 0.02184086699042312
|
|||
|
|
},
|
|||
|
|
"mmlu_high_school_microeconomics": {
|
|||
|
|
"alias": " - high_school_microeconomics",
|
|||
|
|
"acc,none": 0.20588235294117646,
|
|||
|
|
"acc_stderr,none": 0.026265024608275907
|
|||
|
|
},
|
|||
|
|
"mmlu_high_school_psychology": {
|
|||
|
|
"alias": " - high_school_psychology",
|
|||
|
|
"acc,none": 0.24036697247706423,
|
|||
|
|
"acc_stderr,none": 0.01832060732096402
|
|||
|
|
},
|
|||
|
|
"mmlu_human_sexuality": {
|
|||
|
|
"alias": " - human_sexuality",
|
|||
|
|
"acc,none": 0.19083969465648856,
|
|||
|
|
"acc_stderr,none": 0.03446513350752599
|
|||
|
|
},
|
|||
|
|
"mmlu_professional_psychology": {
|
|||
|
|
"alias": " - professional_psychology",
|
|||
|
|
"acc,none": 0.2647058823529412,
|
|||
|
|
"acc_stderr,none": 0.01784808957491327
|
|||
|
|
},
|
|||
|
|
"mmlu_public_relations": {
|
|||
|
|
"alias": " - public_relations",
|
|||
|
|
"acc,none": 0.2909090909090909,
|
|||
|
|
"acc_stderr,none": 0.04350271442923247
|
|||
|
|
},
|
|||
|
|
"mmlu_security_studies": {
|
|||
|
|
"alias": " - security_studies",
|
|||
|
|
"acc,none": 0.1673469387755102,
|
|||
|
|
'lm_eval_full.log' -> '/teamspace/studios/this_studio/microllm2/lm_eval_full.log'
|