Files
frankenstallm/source/eval/outputs/3b_benchmark_results.txt
ModelHub XC d4abdb70fa 初始化项目,由ModelHub XC社区提供模型
Model: pathcosmos/frankenstallm
Source: Original Platform
2026-07-14 04:21:16 +08:00

394 lines
136 KiB
Plaintext
Raw Permalink Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

2026-03-05:01:45:40 INFO [_cli.run:376] Selected Tasks: ['belebele_kor_Hang', 'global_mmlu_full_ko']
2026-03-05:01:45:40 INFO [evaluator:211] Setting random seed to 0 | Setting numpy seed to 1234 | Setting torch manual seed to 1234 | Setting fewshot manual seed to 1234
2026-03-05:01:45:40 INFO [evaluator:236] Initializing hf model, with arguments: {'pretrained': '/PROJECT/0325120031_A/ghong/taketimes/llm-bang/eval/outputs/hf_3b_base', 'dtype': 'bfloat16'}
2026-03-05:01:45:42 INFO [models.huggingface:161] Using device 'cuda:2'
2026-03-05:01:45:43 INFO [models.huggingface:423] Model parallel was set to False, max memory was not set, and device map was set to {'': 'cuda:2'}
Loading weights: 0%| | 0/171 [00:00<?, ?it/s]
Loading weights: 1%| | 1/171 [00:00<00:00, 11037.64it/s, Materializing param=lm_head.weight]
Loading weights: 1%| | 1/171 [00:00<00:00, 6967.28it/s, Materializing param=lm_head.weight]
Loading weights: 1%| | 2/171 [00:00<01:14, 2.28it/s, Materializing param=lm_head.weight]
Loading weights: 1%| | 2/171 [00:00<01:14, 2.28it/s, Materializing param=model.embed_tokens.weight]
Loading weights: 1%| | 2/171 [00:00<01:14, 2.28it/s, Materializing param=model.embed_tokens.weight]
Loading weights: 2%|▏ | 3/171 [00:00<01:13, 2.28it/s, Materializing param=model.layers.0.input_layernorm.weight]
Loading weights: 2%|▏ | 3/171 [00:00<01:13, 2.28it/s, Materializing param=model.layers.0.input_layernorm.weight]
Loading weights: 2%|▏ | 4/171 [00:00<01:13, 2.28it/s, Materializing param=model.layers.0.mlp.down_proj.weight]
Loading weights: 2%|▏ | 4/171 [00:00<01:13, 2.28it/s, Materializing param=model.layers.0.mlp.down_proj.weight]
Loading weights: 3%|▎ | 5/171 [00:00<01:12, 2.28it/s, Materializing param=model.layers.0.mlp.gate_proj.weight]
Loading weights: 3%|▎ | 5/171 [00:00<01:12, 2.28it/s, Materializing param=model.layers.0.mlp.gate_proj.weight]
Loading weights: 4%|▎ | 6/171 [00:00<01:12, 2.28it/s, Materializing param=model.layers.0.mlp.up_proj.weight]
Loading weights: 4%|▎ | 6/171 [00:00<01:12, 2.28it/s, Materializing param=model.layers.0.mlp.up_proj.weight]
Loading weights: 4%|▍ | 7/171 [00:00<01:11, 2.28it/s, Materializing param=model.layers.0.post_attention_layernorm.weight]
Loading weights: 4%|▍ | 7/171 [00:00<01:11, 2.28it/s, Materializing param=model.layers.0.post_attention_layernorm.weight]
Loading weights: 5%|▍ | 8/171 [00:00<01:11, 2.28it/s, Materializing param=model.layers.0.self_attn.o_proj.weight]
Loading weights: 5%|▍ | 8/171 [00:00<01:11, 2.28it/s, Materializing param=model.layers.0.self_attn.o_proj.weight]
Loading weights: 5%|▌ | 9/171 [00:00<01:11, 2.28it/s, Materializing param=model.layers.1.input_layernorm.weight]
Loading weights: 5%|▌ | 9/171 [00:00<01:11, 2.28it/s, Materializing param=model.layers.1.input_layernorm.weight]
Loading weights: 6%|▌ | 10/171 [00:00<01:10, 2.28it/s, Materializing param=model.layers.1.mlp.down_proj.weight]
Loading weights: 6%|▌ | 10/171 [00:00<01:10, 2.28it/s, Materializing param=model.layers.1.mlp.down_proj.weight]
Loading weights: 6%|▋ | 11/171 [00:00<01:10, 2.28it/s, Materializing param=model.layers.1.mlp.gate_proj.weight]
Loading weights: 6%|▋ | 11/171 [00:00<01:10, 2.28it/s, Materializing param=model.layers.1.mlp.gate_proj.weight]
Loading weights: 7%|▋ | 12/171 [00:00<01:09, 2.28it/s, Materializing param=model.layers.1.mlp.up_proj.weight]
Loading weights: 7%|▋ | 12/171 [00:00<01:09, 2.28it/s, Materializing param=model.layers.1.mlp.up_proj.weight]
Loading weights: 8%|▊ | 13/171 [00:00<01:09, 2.28it/s, Materializing param=model.layers.1.post_attention_layernorm.weight]
Loading weights: 8%|▊ | 13/171 [00:00<01:09, 2.28it/s, Materializing param=model.layers.1.post_attention_layernorm.weight]
Loading weights: 8%|▊ | 14/171 [00:00<01:08, 2.28it/s, Materializing param=model.layers.1.self_attn.o_proj.weight]
Loading weights: 8%|▊ | 14/171 [00:00<01:08, 2.28it/s, Materializing param=model.layers.1.self_attn.o_proj.weight]
Loading weights: 9%|▉ | 15/171 [00:01<00:08, 19.46it/s, Materializing param=model.layers.1.self_attn.o_proj.weight]
Loading weights: 9%|▉ | 15/171 [00:01<00:08, 19.46it/s, Materializing param=model.layers.2.input_layernorm.weight]
Loading weights: 9%|▉ | 15/171 [00:01<00:08, 19.46it/s, Materializing param=model.layers.2.input_layernorm.weight]
Loading weights: 9%|▉ | 16/171 [00:01<00:07, 19.46it/s, Materializing param=model.layers.2.mlp.down_proj.weight]
Loading weights: 9%|▉ | 16/171 [00:01<00:07, 19.46it/s, Materializing param=model.layers.2.mlp.down_proj.weight]
Loading weights: 10%|▉ | 17/171 [00:01<00:07, 19.46it/s, Materializing param=model.layers.2.mlp.gate_proj.weight]
Loading weights: 10%|▉ | 17/171 [00:01<00:07, 19.46it/s, Materializing param=model.layers.2.mlp.gate_proj.weight]
Loading weights: 11%|█ | 18/171 [00:01<00:07, 19.46it/s, Materializing param=model.layers.2.mlp.up_proj.weight]
Loading weights: 11%|█ | 18/171 [00:01<00:07, 19.46it/s, Materializing param=model.layers.2.mlp.up_proj.weight]
Loading weights: 11%|█ | 19/171 [00:01<00:07, 19.46it/s, Materializing param=model.layers.2.post_attention_layernorm.weight]
Loading weights: 11%|█ | 19/171 [00:01<00:07, 19.46it/s, Materializing param=model.layers.2.post_attention_layernorm.weight]
Loading weights: 12%|█▏ | 20/171 [00:01<00:07, 19.46it/s, Materializing param=model.layers.2.self_attn.o_proj.weight]
Loading weights: 12%|█▏ | 20/171 [00:01<00:07, 19.46it/s, Materializing param=model.layers.2.self_attn.o_proj.weight]
Loading weights: 12%|█▏ | 21/171 [00:01<00:07, 19.46it/s, Materializing param=model.layers.3.input_layernorm.weight]
Loading weights: 12%|█▏ | 21/171 [00:01<00:07, 19.46it/s, Materializing param=model.layers.3.input_layernorm.weight]
Loading weights: 13%|█▎ | 22/171 [00:01<00:07, 19.46it/s, Materializing param=model.layers.3.mlp.down_proj.weight]
Loading weights: 13%|█▎ | 22/171 [00:01<00:07, 19.46it/s, Materializing param=model.layers.3.mlp.down_proj.weight]
Loading weights: 13%|█▎ | 23/171 [00:01<00:05, 27.36it/s, Materializing param=model.layers.3.mlp.down_proj.weight]
Loading weights: 13%|█▎ | 23/171 [00:01<00:05, 27.36it/s, Materializing param=model.layers.3.mlp.gate_proj.weight]
Loading weights: 13%|█▎ | 23/171 [00:01<00:05, 27.36it/s, Materializing param=model.layers.3.mlp.gate_proj.weight]
Loading weights: 14%|█▍ | 24/171 [00:01<00:05, 27.36it/s, Materializing param=model.layers.3.mlp.up_proj.weight]
Loading weights: 14%|█▍ | 24/171 [00:01<00:05, 27.36it/s, Materializing param=model.layers.3.mlp.up_proj.weight]
Loading weights: 15%|█▍ | 25/171 [00:01<00:05, 27.36it/s, Materializing param=model.layers.3.post_attention_layernorm.weight]
Loading weights: 15%|█▍ | 25/171 [00:01<00:05, 27.36it/s, Materializing param=model.layers.3.post_attention_layernorm.weight]
Loading weights: 15%|█▌ | 26/171 [00:01<00:05, 27.36it/s, Materializing param=model.layers.3.self_attn.o_proj.weight]
Loading weights: 15%|█▌ | 26/171 [00:01<00:05, 27.36it/s, Materializing param=model.layers.3.self_attn.o_proj.weight]
Loading weights: 16%|█▌ | 27/171 [00:01<00:05, 27.36it/s, Materializing param=model.layers.4.input_layernorm.weight]
Loading weights: 16%|█▌ | 27/171 [00:01<00:05, 27.36it/s, Materializing param=model.layers.4.input_layernorm.weight]
Loading weights: 16%|█▋ | 28/171 [00:01<00:05, 27.36it/s, Materializing param=model.layers.4.mlp.down_proj.weight]
Loading weights: 16%|█▋ | 28/171 [00:01<00:05, 27.36it/s, Materializing param=model.layers.4.mlp.down_proj.weight]
Loading weights: 17%|█▋ | 29/171 [00:01<00:04, 32.77it/s, Materializing param=model.layers.4.mlp.down_proj.weight]
Loading weights: 17%|█▋ | 29/171 [00:01<00:04, 32.77it/s, Materializing param=model.layers.4.mlp.gate_proj.weight]
Loading weights: 17%|█▋ | 29/171 [00:01<00:04, 32.77it/s, Materializing param=model.layers.4.mlp.gate_proj.weight]
Loading weights: 18%|█▊ | 30/171 [00:01<00:04, 32.77it/s, Materializing param=model.layers.4.mlp.up_proj.weight]
Loading weights: 18%|█▊ | 30/171 [00:01<00:04, 32.77it/s, Materializing param=model.layers.4.mlp.up_proj.weight]
Loading weights: 18%|█▊ | 31/171 [00:01<00:04, 32.77it/s, Materializing param=model.layers.4.post_attention_layernorm.weight]
Loading weights: 18%|█▊ | 31/171 [00:01<00:04, 32.77it/s, Materializing param=model.layers.4.post_attention_layernorm.weight]
Loading weights: 19%|█▊ | 32/171 [00:01<00:04, 32.77it/s, Materializing param=model.layers.4.self_attn.o_proj.weight]
Loading weights: 19%|█▊ | 32/171 [00:01<00:04, 32.77it/s, Materializing param=model.layers.4.self_attn.o_proj.weight]
Loading weights: 19%|█▉ | 33/171 [00:01<00:04, 32.77it/s, Materializing param=model.layers.5.input_layernorm.weight]
Loading weights: 19%|█▉ | 33/171 [00:01<00:04, 32.77it/s, Materializing param=model.layers.5.input_layernorm.weight]
Loading weights: 20%|█▉ | 34/171 [00:01<00:04, 32.77it/s, Materializing param=model.layers.5.mlp.down_proj.weight]
Loading weights: 20%|█▉ | 34/171 [00:01<00:04, 32.77it/s, Materializing param=model.layers.5.mlp.down_proj.weight]
Loading weights: 20%|██ | 35/171 [00:01<00:03, 35.32it/s, Materializing param=model.layers.5.mlp.down_proj.weight]
Loading weights: 20%|██ | 35/171 [00:01<00:03, 35.32it/s, Materializing param=model.layers.5.mlp.gate_proj.weight]
Loading weights: 20%|██ | 35/171 [00:01<00:03, 35.32it/s, Materializing param=model.layers.5.mlp.gate_proj.weight]
Loading weights: 21%|██ | 36/171 [00:01<00:03, 35.32it/s, Materializing param=model.layers.5.mlp.up_proj.weight]
Loading weights: 21%|██ | 36/171 [00:01<00:03, 35.32it/s, Materializing param=model.layers.5.mlp.up_proj.weight]
Loading weights: 22%|██▏ | 37/171 [00:01<00:03, 35.32it/s, Materializing param=model.layers.5.post_attention_layernorm.weight]
Loading weights: 22%|██▏ | 37/171 [00:01<00:03, 35.32it/s, Materializing param=model.layers.5.post_attention_layernorm.weight]
Loading weights: 22%|██▏ | 38/171 [00:01<00:03, 35.32it/s, Materializing param=model.layers.5.self_attn.o_proj.weight]
Loading weights: 22%|██▏ | 38/171 [00:01<00:03, 35.32it/s, Materializing param=model.layers.5.self_attn.o_proj.weight]
Loading weights: 23%|██▎ | 39/171 [00:01<00:03, 35.32it/s, Materializing param=model.layers.6.input_layernorm.weight]
Loading weights: 23%|██▎ | 39/171 [00:01<00:03, 35.32it/s, Materializing param=model.layers.6.input_layernorm.weight]
Loading weights: 23%|██▎ | 40/171 [00:01<00:03, 35.32it/s, Materializing param=model.layers.6.mlp.down_proj.weight]
Loading weights: 23%|██▎ | 40/171 [00:01<00:03, 35.32it/s, Materializing param=model.layers.6.mlp.down_proj.weight]
Loading weights: 24%|██▍ | 41/171 [00:01<00:03, 35.32it/s, Materializing param=model.layers.6.mlp.gate_proj.weight]
Loading weights: 24%|██▍ | 41/171 [00:01<00:03, 35.32it/s, Materializing param=model.layers.6.mlp.gate_proj.weight]
Loading weights: 25%|██▍ | 42/171 [00:01<00:03, 42.36it/s, Materializing param=model.layers.6.mlp.gate_proj.weight]
Loading weights: 25%|██▍ | 42/171 [00:01<00:03, 42.36it/s, Materializing param=model.layers.6.mlp.up_proj.weight]
Loading weights: 25%|██▍ | 42/171 [00:01<00:03, 42.36it/s, Materializing param=model.layers.6.mlp.up_proj.weight]
Loading weights: 25%|██▌ | 43/171 [00:01<00:03, 42.36it/s, Materializing param=model.layers.6.post_attention_layernorm.weight]
Loading weights: 25%|██▌ | 43/171 [00:01<00:03, 42.36it/s, Materializing param=model.layers.6.post_attention_layernorm.weight]
Loading weights: 26%|██▌ | 44/171 [00:01<00:02, 42.36it/s, Materializing param=model.layers.6.self_attn.o_proj.weight]
Loading weights: 26%|██▌ | 44/171 [00:01<00:02, 42.36it/s, Materializing param=model.layers.6.self_attn.o_proj.weight]
Loading weights: 26%|██▋ | 45/171 [00:01<00:02, 42.36it/s, Materializing param=model.layers.7.input_layernorm.weight]
Loading weights: 26%|██▋ | 45/171 [00:01<00:02, 42.36it/s, Materializing param=model.layers.7.input_layernorm.weight]
Loading weights: 27%|██▋ | 46/171 [00:01<00:02, 42.36it/s, Materializing param=model.layers.7.mlp.down_proj.weight]
Loading weights: 27%|██▋ | 46/171 [00:01<00:02, 42.36it/s, Materializing param=model.layers.7.mlp.down_proj.weight]
Loading weights: 27%|██▋ | 47/171 [00:01<00:02, 42.36it/s, Materializing param=model.layers.7.mlp.gate_proj.weight]
Loading weights: 27%|██▋ | 47/171 [00:01<00:02, 42.36it/s, Materializing param=model.layers.7.mlp.gate_proj.weight]
Loading weights: 28%|██▊ | 48/171 [00:01<00:02, 42.36it/s, Materializing param=model.layers.7.mlp.up_proj.weight]
Loading weights: 28%|██▊ | 48/171 [00:01<00:02, 42.36it/s, Materializing param=model.layers.7.mlp.up_proj.weight]
Loading weights: 29%|██▊ | 49/171 [00:01<00:02, 45.35it/s, Materializing param=model.layers.7.mlp.up_proj.weight]
Loading weights: 29%|██▊ | 49/171 [00:01<00:02, 45.35it/s, Materializing param=model.layers.7.post_attention_layernorm.weight]
Loading weights: 29%|██▊ | 49/171 [00:01<00:02, 45.35it/s, Materializing param=model.layers.7.post_attention_layernorm.weight]
Loading weights: 29%|██▉ | 50/171 [00:01<00:02, 45.35it/s, Materializing param=model.layers.7.self_attn.o_proj.weight]
Loading weights: 29%|██▉ | 50/171 [00:01<00:02, 45.35it/s, Materializing param=model.layers.7.self_attn.o_proj.weight]
Loading weights: 30%|██▉ | 51/171 [00:01<00:02, 45.35it/s, Materializing param=model.layers.8.input_layernorm.weight]
Loading weights: 30%|██▉ | 51/171 [00:01<00:02, 45.35it/s, Materializing param=model.layers.8.input_layernorm.weight]
Loading weights: 30%|███ | 52/171 [00:01<00:02, 45.35it/s, Materializing param=model.layers.8.mlp.down_proj.weight]
Loading weights: 30%|███ | 52/171 [00:01<00:02, 45.35it/s, Materializing param=model.layers.8.mlp.down_proj.weight]
Loading weights: 31%|███ | 53/171 [00:01<00:02, 45.35it/s, Materializing param=model.layers.8.mlp.gate_proj.weight]
Loading weights: 31%|███ | 53/171 [00:01<00:02, 45.35it/s, Materializing param=model.layers.8.mlp.gate_proj.weight]
Loading weights: 32%|███▏ | 54/171 [00:01<00:02, 45.35it/s, Materializing param=model.layers.8.mlp.up_proj.weight]
Loading weights: 32%|███▏ | 54/171 [00:01<00:02, 45.35it/s, Materializing param=model.layers.8.mlp.up_proj.weight]
Loading weights: 32%|███▏ | 55/171 [00:01<00:02, 46.46it/s, Materializing param=model.layers.8.mlp.up_proj.weight]
Loading weights: 32%|███▏ | 55/171 [00:01<00:02, 46.46it/s, Materializing param=model.layers.8.post_attention_layernorm.weight]
Loading weights: 32%|███▏ | 55/171 [00:01<00:02, 46.46it/s, Materializing param=model.layers.8.post_attention_layernorm.weight]
Loading weights: 33%|███▎ | 56/171 [00:01<00:02, 46.46it/s, Materializing param=model.layers.8.self_attn.o_proj.weight]
Loading weights: 33%|███▎ | 56/171 [00:01<00:02, 46.46it/s, Materializing param=model.layers.8.self_attn.o_proj.weight]
Loading weights: 33%|███▎ | 57/171 [00:01<00:02, 46.46it/s, Materializing param=model.layers.9.input_layernorm.weight]
Loading weights: 33%|███▎ | 57/171 [00:01<00:02, 46.46it/s, Materializing param=model.layers.9.input_layernorm.weight]
Loading weights: 34%|███▍ | 58/171 [00:01<00:02, 46.46it/s, Materializing param=model.layers.9.mlp.down_proj.weight]
Loading weights: 34%|███▍ | 58/171 [00:01<00:02, 46.46it/s, Materializing param=model.layers.9.mlp.down_proj.weight]
Loading weights: 35%|███▍ | 59/171 [00:01<00:02, 46.46it/s, Materializing param=model.layers.9.mlp.gate_proj.weight]
Loading weights: 35%|███▍ | 59/171 [00:01<00:02, 46.46it/s, Materializing param=model.layers.9.mlp.gate_proj.weight]
Loading weights: 35%|███▌ | 60/171 [00:01<00:02, 46.46it/s, Materializing param=model.layers.9.mlp.up_proj.weight]
Loading weights: 35%|███▌ | 60/171 [00:01<00:02, 46.46it/s, Materializing param=model.layers.9.mlp.up_proj.weight]
Loading weights: 36%|███▌ | 61/171 [00:01<00:02, 46.46it/s, Materializing param=model.layers.9.post_attention_layernorm.weight]
Loading weights: 36%|███▌ | 61/171 [00:01<00:02, 46.46it/s, Materializing param=model.layers.9.post_attention_layernorm.weight]
Loading weights: 36%|███▋ | 62/171 [00:01<00:02, 46.46it/s, Materializing param=model.layers.9.self_attn.o_proj.weight]
Loading weights: 36%|███▋ | 62/171 [00:01<00:02, 46.46it/s, Materializing param=model.layers.9.self_attn.o_proj.weight]
Loading weights: 37%|███▋ | 63/171 [00:01<00:02, 46.46it/s, Materializing param=model.layers.10.input_layernorm.weight]
Loading weights: 37%|███▋ | 63/171 [00:01<00:02, 46.46it/s, Materializing param=model.layers.10.input_layernorm.weight]
Loading weights: 37%|███▋ | 64/171 [00:01<00:02, 46.46it/s, Materializing param=model.layers.10.mlp.down_proj.weight]
Loading weights: 37%|███▋ | 64/171 [00:01<00:02, 46.46it/s, Materializing param=model.layers.10.mlp.down_proj.weight]
Loading weights: 38%|███▊ | 65/171 [00:01<00:02, 47.43it/s, Materializing param=model.layers.10.mlp.down_proj.weight]
Loading weights: 38%|███▊ | 65/171 [00:01<00:02, 47.43it/s, Materializing param=model.layers.10.mlp.gate_proj.weight]
Loading weights: 38%|███▊ | 65/171 [00:01<00:02, 47.43it/s, Materializing param=model.layers.10.mlp.gate_proj.weight]
Loading weights: 39%|███▊ | 66/171 [00:01<00:02, 47.43it/s, Materializing param=model.layers.10.mlp.up_proj.weight]
Loading weights: 39%|███▊ | 66/171 [00:01<00:02, 47.43it/s, Materializing param=model.layers.10.mlp.up_proj.weight]
Loading weights: 39%|███▉ | 67/171 [00:01<00:02, 47.43it/s, Materializing param=model.layers.10.post_attention_layernorm.weight]
Loading weights: 39%|███▉ | 67/171 [00:01<00:02, 47.43it/s, Materializing param=model.layers.10.post_attention_layernorm.weight]
Loading weights: 40%|███▉ | 68/171 [00:01<00:02, 47.43it/s, Materializing param=model.layers.10.self_attn.o_proj.weight]
Loading weights: 40%|███▉ | 68/171 [00:01<00:02, 47.43it/s, Materializing param=model.layers.10.self_attn.o_proj.weight]
Loading weights: 40%|████ | 69/171 [00:01<00:02, 47.43it/s, Materializing param=model.layers.11.input_layernorm.weight]
Loading weights: 40%|████ | 69/171 [00:01<00:02, 47.43it/s, Materializing param=model.layers.11.input_layernorm.weight]
Loading weights: 41%|████ | 70/171 [00:01<00:02, 47.43it/s, Materializing param=model.layers.11.mlp.down_proj.weight]
Loading weights: 41%|████ | 70/171 [00:01<00:02, 47.43it/s, Materializing param=model.layers.11.mlp.down_proj.weight]
Loading weights: 42%|████▏ | 71/171 [00:02<00:02, 47.43it/s, Materializing param=model.layers.11.mlp.gate_proj.weight]
Loading weights: 42%|████▏ | 71/171 [00:02<00:02, 47.43it/s, Materializing param=model.layers.11.mlp.gate_proj.weight]
Loading weights: 42%|████▏ | 72/171 [00:02<00:02, 47.43it/s, Materializing param=model.layers.11.mlp.up_proj.weight]
Loading weights: 42%|████▏ | 72/171 [00:02<00:02, 47.43it/s, Materializing param=model.layers.11.mlp.up_proj.weight]
Loading weights: 43%|████▎ | 73/171 [00:02<00:01, 51.37it/s, Materializing param=model.layers.11.mlp.up_proj.weight]
Loading weights: 43%|████▎ | 73/171 [00:02<00:01, 51.37it/s, Materializing param=model.layers.11.post_attention_layernorm.weight]
Loading weights: 43%|████▎ | 73/171 [00:02<00:01, 51.37it/s, Materializing param=model.layers.11.post_attention_layernorm.weight]
Loading weights: 43%|████▎ | 74/171 [00:02<00:01, 51.37it/s, Materializing param=model.layers.11.self_attn.o_proj.weight]
Loading weights: 43%|████▎ | 74/171 [00:02<00:01, 51.37it/s, Materializing param=model.layers.11.self_attn.o_proj.weight]
Loading weights: 44%|████▍ | 75/171 [00:02<00:01, 51.37it/s, Materializing param=model.layers.12.input_layernorm.weight]
Loading weights: 44%|████▍ | 75/171 [00:02<00:01, 51.37it/s, Materializing param=model.layers.12.input_layernorm.weight]
Loading weights: 44%|████▍ | 76/171 [00:02<00:01, 51.37it/s, Materializing param=model.layers.12.mlp.down_proj.weight]
Loading weights: 44%|████▍ | 76/171 [00:02<00:01, 51.37it/s, Materializing param=model.layers.12.mlp.down_proj.weight]
Loading weights: 45%|████▌ | 77/171 [00:02<00:01, 51.37it/s, Materializing param=model.layers.12.mlp.gate_proj.weight]
Loading weights: 45%|████▌ | 77/171 [00:02<00:01, 51.37it/s, Materializing param=model.layers.12.mlp.gate_proj.weight]
Loading weights: 46%|████▌ | 78/171 [00:02<00:01, 51.37it/s, Materializing param=model.layers.12.mlp.up_proj.weight]
Loading weights: 46%|████▌ | 78/171 [00:02<00:01, 51.37it/s, Materializing param=model.layers.12.mlp.up_proj.weight]
Loading weights: 46%|████▌ | 79/171 [00:02<00:01, 51.37it/s, Materializing param=model.layers.12.post_attention_layernorm.weight]
Loading weights: 46%|████▌ | 79/171 [00:02<00:01, 51.37it/s, Materializing param=model.layers.12.post_attention_layernorm.weight]
Loading weights: 47%|████▋ | 80/171 [00:02<00:01, 51.37it/s, Materializing param=model.layers.12.self_attn.o_proj.weight]
Loading weights: 47%|████▋ | 80/171 [00:02<00:01, 51.37it/s, Materializing param=model.layers.12.self_attn.o_proj.weight]
Loading weights: 47%|████▋ | 81/171 [00:02<00:01, 51.37it/s, Materializing param=model.layers.13.input_layernorm.weight]
Loading weights: 47%|████▋ | 81/171 [00:02<00:01, 51.37it/s, Materializing param=model.layers.13.input_layernorm.weight]
Loading weights: 48%|████▊ | 82/171 [00:02<00:01, 51.37it/s, Materializing param=model.layers.13.mlp.down_proj.weight]
Loading weights: 48%|████▊ | 82/171 [00:02<00:01, 51.37it/s, Materializing param=model.layers.13.mlp.down_proj.weight]
Loading weights: 49%|████▊ | 83/171 [00:02<00:01, 53.60it/s, Materializing param=model.layers.13.mlp.down_proj.weight]
Loading weights: 49%|████▊ | 83/171 [00:02<00:01, 53.60it/s, Materializing param=model.layers.13.mlp.gate_proj.weight]
Loading weights: 49%|████▊ | 83/171 [00:02<00:01, 53.60it/s, Materializing param=model.layers.13.mlp.gate_proj.weight]
Loading weights: 49%|████▉ | 84/171 [00:02<00:01, 53.60it/s, Materializing param=model.layers.13.mlp.up_proj.weight]
Loading weights: 49%|████▉ | 84/171 [00:02<00:01, 53.60it/s, Materializing param=model.layers.13.mlp.up_proj.weight]
Loading weights: 50%|████▉ | 85/171 [00:02<00:01, 53.60it/s, Materializing param=model.layers.13.post_attention_layernorm.weight]
Loading weights: 50%|████▉ | 85/171 [00:02<00:01, 53.60it/s, Materializing param=model.layers.13.post_attention_layernorm.weight]
Loading weights: 50%|█████ | 86/171 [00:02<00:01, 53.60it/s, Materializing param=model.layers.13.self_attn.o_proj.weight]
Loading weights: 50%|█████ | 86/171 [00:02<00:01, 53.60it/s, Materializing param=model.layers.13.self_attn.o_proj.weight]
Loading weights: 51%|█████ | 87/171 [00:02<00:01, 53.60it/s, Materializing param=model.layers.14.input_layernorm.weight]
Loading weights: 51%|█████ | 87/171 [00:02<00:01, 53.60it/s, Materializing param=model.layers.14.input_layernorm.weight]
Loading weights: 51%|█████▏ | 88/171 [00:02<00:01, 53.60it/s, Materializing param=model.layers.14.mlp.down_proj.weight]
Loading weights: 51%|█████▏ | 88/171 [00:02<00:01, 53.60it/s, Materializing param=model.layers.14.mlp.down_proj.weight]
Loading weights: 52%|█████▏ | 89/171 [00:02<00:01, 54.33it/s, Materializing param=model.layers.14.mlp.down_proj.weight]
Loading weights: 52%|█████▏ | 89/171 [00:02<00:01, 54.33it/s, Materializing param=model.layers.14.mlp.gate_proj.weight]
Loading weights: 52%|█████▏ | 89/171 [00:02<00:01, 54.33it/s, Materializing param=model.layers.14.mlp.gate_proj.weight]
Loading weights: 53%|█████▎ | 90/171 [00:02<00:01, 54.33it/s, Materializing param=model.layers.14.mlp.up_proj.weight]
Loading weights: 53%|█████▎ | 90/171 [00:02<00:01, 54.33it/s, Materializing param=model.layers.14.mlp.up_proj.weight]
Loading weights: 53%|█████▎ | 91/171 [00:02<00:01, 54.33it/s, Materializing param=model.layers.14.post_attention_layernorm.weight]
Loading weights: 53%|█████▎ | 91/171 [00:02<00:01, 54.33it/s, Materializing param=model.layers.14.post_attention_layernorm.weight]
Loading weights: 54%|█████▍ | 92/171 [00:02<00:01, 54.33it/s, Materializing param=model.layers.14.self_attn.o_proj.weight]
Loading weights: 54%|█████▍ | 92/171 [00:02<00:01, 54.33it/s, Materializing param=model.layers.14.self_attn.o_proj.weight]
Loading weights: 54%|█████▍ | 93/171 [00:02<00:01, 54.33it/s, Materializing param=model.layers.15.input_layernorm.weight]
Loading weights: 54%|█████▍ | 93/171 [00:02<00:01, 54.33it/s, Materializing param=model.layers.15.input_layernorm.weight]
Loading weights: 55%|█████▍ | 94/171 [00:02<00:01, 54.33it/s, Materializing param=model.layers.15.mlp.down_proj.weight]
Loading weights: 55%|█████▍ | 94/171 [00:02<00:01, 54.33it/s, Materializing param=model.layers.15.mlp.down_proj.weight]
Loading weights: 56%|█████▌ | 95/171 [00:02<00:01, 55.09it/s, Materializing param=model.layers.15.mlp.down_proj.weight]
Loading weights: 56%|█████▌ | 95/171 [00:02<00:01, 55.09it/s, Materializing param=model.layers.15.mlp.gate_proj.weight]
Loading weights: 56%|█████▌ | 95/171 [00:02<00:01, 55.09it/s, Materializing param=model.layers.15.mlp.gate_proj.weight]
Loading weights: 56%|█████▌ | 96/171 [00:02<00:01, 55.09it/s, Materializing param=model.layers.15.mlp.up_proj.weight]
Loading weights: 56%|█████▌ | 96/171 [00:02<00:01, 55.09it/s, Materializing param=model.layers.15.mlp.up_proj.weight]
Loading weights: 57%|█████▋ | 97/171 [00:02<00:01, 55.09it/s, Materializing param=model.layers.15.post_attention_layernorm.weight]
Loading weights: 57%|█████▋ | 97/171 [00:02<00:01, 55.09it/s, Materializing param=model.layers.15.post_attention_layernorm.weight]
Loading weights: 57%|█████▋ | 98/171 [00:02<00:01, 55.09it/s, Materializing param=model.layers.15.self_attn.o_proj.weight]
Loading weights: 57%|█████▋ | 98/171 [00:02<00:01, 55.09it/s, Materializing param=model.layers.15.self_attn.o_proj.weight]
Loading weights: 58%|█████▊ | 99/171 [00:02<00:01, 55.09it/s, Materializing param=model.layers.16.input_layernorm.weight]
Loading weights: 58%|█████▊ | 99/171 [00:02<00:01, 55.09it/s, Materializing param=model.layers.16.input_layernorm.weight]
Loading weights: 58%|█████▊ | 100/171 [00:02<00:01, 55.09it/s, Materializing param=model.layers.16.mlp.down_proj.weight]
Loading weights: 58%|█████▊ | 100/171 [00:02<00:01, 55.09it/s, Materializing param=model.layers.16.mlp.down_proj.weight]
Loading weights: 59%|█████▉ | 101/171 [00:02<00:01, 53.99it/s, Materializing param=model.layers.16.mlp.down_proj.weight]
Loading weights: 59%|█████▉ | 101/171 [00:02<00:01, 53.99it/s, Materializing param=model.layers.16.mlp.gate_proj.weight]
Loading weights: 59%|█████▉ | 101/171 [00:02<00:01, 53.99it/s, Materializing param=model.layers.16.mlp.gate_proj.weight]
Loading weights: 60%|█████▉ | 102/171 [00:02<00:01, 53.99it/s, Materializing param=model.layers.16.mlp.up_proj.weight]
Loading weights: 60%|█████▉ | 102/171 [00:02<00:01, 53.99it/s, Materializing param=model.layers.16.mlp.up_proj.weight]
Loading weights: 60%|██████ | 103/171 [00:02<00:01, 53.99it/s, Materializing param=model.layers.16.post_attention_layernorm.weight]
Loading weights: 60%|██████ | 103/171 [00:02<00:01, 53.99it/s, Materializing param=model.layers.16.post_attention_layernorm.weight]
Loading weights: 61%|██████ | 104/171 [00:02<00:01, 53.99it/s, Materializing param=model.layers.16.self_attn.o_proj.weight]
Loading weights: 61%|██████ | 104/171 [00:02<00:01, 53.99it/s, Materializing param=model.layers.16.self_attn.o_proj.weight]
Loading weights: 61%|██████▏ | 105/171 [00:02<00:01, 53.99it/s, Materializing param=model.layers.17.input_layernorm.weight]
Loading weights: 61%|██████▏ | 105/171 [00:02<00:01, 53.99it/s, Materializing param=model.layers.17.input_layernorm.weight]
Loading weights: 62%|██████▏ | 106/171 [00:02<00:01, 53.99it/s, Materializing param=model.layers.17.mlp.down_proj.weight]
Loading weights: 62%|██████▏ | 106/171 [00:02<00:01, 53.99it/s, Materializing param=model.layers.17.mlp.down_proj.weight]
Loading weights: 63%|██████▎ | 107/171 [00:02<00:01, 48.06it/s, Materializing param=model.layers.17.mlp.down_proj.weight]
Loading weights: 63%|██████▎ | 107/171 [00:02<00:01, 48.06it/s, Materializing param=model.layers.17.mlp.gate_proj.weight]
Loading weights: 63%|██████▎ | 107/171 [00:02<00:01, 48.06it/s, Materializing param=model.layers.17.mlp.gate_proj.weight]
Loading weights: 63%|██████▎ | 108/171 [00:02<00:01, 48.06it/s, Materializing param=model.layers.17.mlp.up_proj.weight]
Loading weights: 63%|██████▎ | 108/171 [00:02<00:01, 48.06it/s, Materializing param=model.layers.17.mlp.up_proj.weight]
Loading weights: 64%|██████▎ | 109/171 [00:02<00:01, 48.06it/s, Materializing param=model.layers.17.post_attention_layernorm.weight]
Loading weights: 64%|██████▎ | 109/171 [00:02<00:01, 48.06it/s, Materializing param=model.layers.17.post_attention_layernorm.weight]
Loading weights: 64%|██████▍ | 110/171 [00:02<00:01, 48.06it/s, Materializing param=model.layers.17.self_attn.o_proj.weight]
Loading weights: 64%|██████▍ | 110/171 [00:02<00:01, 48.06it/s, Materializing param=model.layers.17.self_attn.o_proj.weight]
Loading weights: 65%|██████▍ | 111/171 [00:02<00:01, 48.06it/s, Materializing param=model.layers.18.input_layernorm.weight]
Loading weights: 65%|██████▍ | 111/171 [00:02<00:01, 48.06it/s, Materializing param=model.layers.18.input_layernorm.weight]
Loading weights: 65%|██████▌ | 112/171 [00:02<00:01, 48.06it/s, Materializing param=model.layers.18.mlp.down_proj.weight]
Loading weights: 65%|██████▌ | 112/171 [00:02<00:01, 48.06it/s, Materializing param=model.layers.18.mlp.down_proj.weight]
Loading weights: 66%|██████▌ | 113/171 [00:02<00:01, 48.06it/s, Materializing param=model.layers.18.mlp.gate_proj.weight]
Loading weights: 66%|██████▌ | 113/171 [00:02<00:01, 48.06it/s, Materializing param=model.layers.18.mlp.gate_proj.weight]
Loading weights: 67%|██████▋ | 114/171 [00:02<00:01, 52.74it/s, Materializing param=model.layers.18.mlp.gate_proj.weight]
Loading weights: 67%|██████▋ | 114/171 [00:02<00:01, 52.74it/s, Materializing param=model.layers.18.mlp.up_proj.weight]
Loading weights: 67%|██████▋ | 114/171 [00:02<00:01, 52.74it/s, Materializing param=model.layers.18.mlp.up_proj.weight]
Loading weights: 67%|██████▋ | 115/171 [00:02<00:01, 52.74it/s, Materializing param=model.layers.18.post_attention_layernorm.weight]
Loading weights: 67%|██████▋ | 115/171 [00:02<00:01, 52.74it/s, Materializing param=model.layers.18.post_attention_layernorm.weight]
Loading weights: 68%|██████▊ | 116/171 [00:02<00:01, 52.74it/s, Materializing param=model.layers.18.self_attn.o_proj.weight]
Loading weights: 68%|██████▊ | 116/171 [00:02<00:01, 52.74it/s, Materializing param=model.layers.18.self_attn.o_proj.weight]
Loading weights: 68%|██████▊ | 117/171 [00:02<00:01, 52.74it/s, Materializing param=model.layers.19.input_layernorm.weight]
Loading weights: 68%|██████▊ | 117/171 [00:02<00:01, 52.74it/s, Materializing param=model.layers.19.input_layernorm.weight]
Loading weights: 69%|██████▉ | 118/171 [00:02<00:01, 52.74it/s, Materializing param=model.layers.19.mlp.down_proj.weight]
Loading weights: 69%|██████▉ | 118/171 [00:02<00:01, 52.74it/s, Materializing param=model.layers.19.mlp.down_proj.weight]
Loading weights: 70%|██████▉ | 119/171 [00:02<00:00, 52.74it/s, Materializing param=model.layers.19.mlp.gate_proj.weight]
Loading weights: 70%|██████▉ | 119/171 [00:02<00:00, 52.74it/s, Materializing param=model.layers.19.mlp.gate_proj.weight]
Loading weights: 70%|███████ | 120/171 [00:02<00:00, 52.74it/s, Materializing param=model.layers.19.mlp.up_proj.weight]
Loading weights: 70%|███████ | 120/171 [00:02<00:00, 52.74it/s, Materializing param=model.layers.19.mlp.up_proj.weight]
Loading weights: 71%|███████ | 121/171 [00:02<00:00, 55.69it/s, Materializing param=model.layers.19.mlp.up_proj.weight]
Loading weights: 71%|███████ | 121/171 [00:02<00:00, 55.69it/s, Materializing param=model.layers.19.post_attention_layernorm.weight]
Loading weights: 71%|███████ | 121/171 [00:02<00:00, 55.69it/s, Materializing param=model.layers.19.post_attention_layernorm.weight]
Loading weights: 71%|███████▏ | 122/171 [00:02<00:00, 55.69it/s, Materializing param=model.layers.19.self_attn.o_proj.weight]
Loading weights: 71%|███████▏ | 122/171 [00:02<00:00, 55.69it/s, Materializing param=model.layers.19.self_attn.o_proj.weight]
Loading weights: 72%|███████▏ | 123/171 [00:02<00:00, 55.69it/s, Materializing param=model.layers.20.input_layernorm.weight]
Loading weights: 72%|███████▏ | 123/171 [00:02<00:00, 55.69it/s, Materializing param=model.layers.20.input_layernorm.weight]
Loading weights: 73%|███████▎ | 124/171 [00:02<00:00, 55.69it/s, Materializing param=model.layers.20.mlp.down_proj.weight]
Loading weights: 73%|███████▎ | 124/171 [00:02<00:00, 55.69it/s, Materializing param=model.layers.20.mlp.down_proj.weight]
Loading weights: 73%|███████▎ | 125/171 [00:03<00:00, 55.69it/s, Materializing param=model.layers.20.mlp.gate_proj.weight]
Loading weights: 73%|███████▎ | 125/171 [00:03<00:00, 55.69it/s, Materializing param=model.layers.20.mlp.gate_proj.weight]
Loading weights: 74%|███████▎ | 126/171 [00:03<00:00, 55.69it/s, Materializing param=model.layers.20.mlp.up_proj.weight]
Loading weights: 74%|███████▎ | 126/171 [00:03<00:00, 55.69it/s, Materializing param=model.layers.20.mlp.up_proj.weight]
Loading weights: 74%|███████▍ | 127/171 [00:03<00:00, 55.69it/s, Materializing param=model.layers.20.post_attention_layernorm.weight]
Loading weights: 74%|███████▍ | 127/171 [00:03<00:00, 55.69it/s, Materializing param=model.layers.20.post_attention_layernorm.weight]
Loading weights: 75%|███████▍ | 128/171 [00:03<00:00, 55.69it/s, Materializing param=model.layers.20.self_attn.o_proj.weight]
Loading weights: 75%|███████▍ | 128/171 [00:03<00:00, 55.69it/s, Materializing param=model.layers.20.self_attn.o_proj.weight]
Loading weights: 75%|███████▌ | 129/171 [00:03<00:00, 55.69it/s, Materializing param=model.layers.21.input_layernorm.weight]
Loading weights: 75%|███████▌ | 129/171 [00:03<00:00, 55.69it/s, Materializing param=model.layers.21.input_layernorm.weight]
Loading weights: 76%|███████▌ | 130/171 [00:03<00:00, 55.69it/s, Materializing param=model.layers.21.mlp.down_proj.weight]
Loading weights: 76%|███████▌ | 130/171 [00:03<00:00, 55.69it/s, Materializing param=model.layers.21.mlp.down_proj.weight]
Loading weights: 77%|███████▋ | 131/171 [00:03<00:00, 52.17it/s, Materializing param=model.layers.21.mlp.down_proj.weight]
Loading weights: 77%|███████▋ | 131/171 [00:03<00:00, 52.17it/s, Materializing param=model.layers.21.mlp.gate_proj.weight]
Loading weights: 77%|███████▋ | 131/171 [00:03<00:00, 52.17it/s, Materializing param=model.layers.21.mlp.gate_proj.weight]
Loading weights: 77%|███████▋ | 132/171 [00:03<00:00, 52.17it/s, Materializing param=model.layers.21.mlp.up_proj.weight]
Loading weights: 77%|███████▋ | 132/171 [00:03<00:00, 52.17it/s, Materializing param=model.layers.21.mlp.up_proj.weight]
Loading weights: 78%|███████▊ | 133/171 [00:03<00:00, 52.17it/s, Materializing param=model.layers.21.post_attention_layernorm.weight]
Loading weights: 78%|███████▊ | 133/171 [00:03<00:00, 52.17it/s, Materializing param=model.layers.21.post_attention_layernorm.weight]
Loading weights: 78%|███████▊ | 134/171 [00:03<00:00, 52.17it/s, Materializing param=model.layers.21.self_attn.o_proj.weight]
Loading weights: 78%|███████▊ | 134/171 [00:03<00:00, 52.17it/s, Materializing param=model.layers.21.self_attn.o_proj.weight]
Loading weights: 79%|███████▉ | 135/171 [00:03<00:00, 52.17it/s, Materializing param=model.layers.22.input_layernorm.weight]
Loading weights: 79%|███████▉ | 135/171 [00:03<00:00, 52.17it/s, Materializing param=model.layers.22.input_layernorm.weight]
Loading weights: 80%|███████▉ | 136/171 [00:03<00:00, 52.17it/s, Materializing param=model.layers.22.mlp.down_proj.weight]
Loading weights: 80%|███████▉ | 136/171 [00:03<00:00, 52.17it/s, Materializing param=model.layers.22.mlp.down_proj.weight]
Loading weights: 80%|████████ | 137/171 [00:03<00:00, 52.17it/s, Materializing param=model.layers.22.mlp.gate_proj.weight]
Loading weights: 80%|████████ | 137/171 [00:03<00:00, 52.17it/s, Materializing param=model.layers.22.mlp.gate_proj.weight]
Loading weights: 81%|████████ | 138/171 [00:03<00:00, 55.54it/s, Materializing param=model.layers.22.mlp.gate_proj.weight]
Loading weights: 81%|████████ | 138/171 [00:03<00:00, 55.54it/s, Materializing param=model.layers.22.mlp.up_proj.weight]
Loading weights: 81%|████████ | 138/171 [00:03<00:00, 55.54it/s, Materializing param=model.layers.22.mlp.up_proj.weight]
Loading weights: 81%|████████▏ | 139/171 [00:03<00:00, 55.54it/s, Materializing param=model.layers.22.post_attention_layernorm.weight]
Loading weights: 81%|████████▏ | 139/171 [00:03<00:00, 55.54it/s, Materializing param=model.layers.22.post_attention_layernorm.weight]
Loading weights: 82%|████████▏ | 140/171 [00:03<00:00, 55.54it/s, Materializing param=model.layers.22.self_attn.o_proj.weight]
Loading weights: 82%|████████▏ | 140/171 [00:03<00:00, 55.54it/s, Materializing param=model.layers.22.self_attn.o_proj.weight]
Loading weights: 82%|████████▏ | 141/171 [00:03<00:00, 55.54it/s, Materializing param=model.layers.23.input_layernorm.weight]
Loading weights: 82%|████████▏ | 141/171 [00:03<00:00, 55.54it/s, Materializing param=model.layers.23.input_layernorm.weight]
Loading weights: 83%|████████▎ | 142/171 [00:03<00:00, 55.54it/s, Materializing param=model.layers.23.mlp.down_proj.weight]
Loading weights: 83%|████████▎ | 142/171 [00:03<00:00, 55.54it/s, Materializing param=model.layers.23.mlp.down_proj.weight]
Loading weights: 84%|████████▎ | 143/171 [00:03<00:00, 55.54it/s, Materializing param=model.layers.23.mlp.gate_proj.weight]
Loading weights: 84%|████████▎ | 143/171 [00:03<00:00, 55.54it/s, Materializing param=model.layers.23.mlp.gate_proj.weight]
Loading weights: 84%|████████▍ | 144/171 [00:03<00:00, 55.54it/s, Materializing param=model.layers.23.mlp.up_proj.weight]
Loading weights: 84%|████████▍ | 144/171 [00:03<00:00, 55.54it/s, Materializing param=model.layers.23.mlp.up_proj.weight]
Loading weights: 85%|████████▍ | 145/171 [00:03<00:00, 51.56it/s, Materializing param=model.layers.23.mlp.up_proj.weight]
Loading weights: 85%|████████▍ | 145/171 [00:03<00:00, 51.56it/s, Materializing param=model.layers.23.post_attention_layernorm.weight]
Loading weights: 85%|████████▍ | 145/171 [00:03<00:00, 51.56it/s, Materializing param=model.layers.23.post_attention_layernorm.weight]
Loading weights: 85%|████████▌ | 146/171 [00:03<00:00, 51.56it/s, Materializing param=model.layers.23.self_attn.o_proj.weight]
Loading weights: 85%|████████▌ | 146/171 [00:03<00:00, 51.56it/s, Materializing param=model.layers.23.self_attn.o_proj.weight]
Loading weights: 86%|████████▌ | 147/171 [00:03<00:00, 51.56it/s, Materializing param=model.layers.24.input_layernorm.weight]
Loading weights: 86%|████████▌ | 147/171 [00:03<00:00, 51.56it/s, Materializing param=model.layers.24.input_layernorm.weight]
Loading weights: 87%|████████▋ | 148/171 [00:03<00:00, 51.56it/s, Materializing param=model.layers.24.mlp.down_proj.weight]
Loading weights: 87%|████████▋ | 148/171 [00:03<00:00, 51.56it/s, Materializing param=model.layers.24.mlp.down_proj.weight]
Loading weights: 87%|████████▋ | 149/171 [00:03<00:00, 51.56it/s, Materializing param=model.layers.24.mlp.gate_proj.weight]
Loading weights: 87%|████████▋ | 149/171 [00:03<00:00, 51.56it/s, Materializing param=model.layers.24.mlp.gate_proj.weight]
Loading weights: 88%|████████▊ | 150/171 [00:03<00:00, 51.56it/s, Materializing param=model.layers.24.mlp.up_proj.weight]
Loading weights: 88%|████████▊ | 150/171 [00:03<00:00, 51.56it/s, Materializing param=model.layers.24.mlp.up_proj.weight]
Loading weights: 88%|████████▊ | 151/171 [00:03<00:00, 51.56it/s, Materializing param=model.layers.24.post_attention_layernorm.weight]
Loading weights: 88%|████████▊ | 151/171 [00:03<00:00, 51.56it/s, Materializing param=model.layers.24.post_attention_layernorm.weight]
Loading weights: 89%|████████▉ | 152/171 [00:03<00:00, 51.56it/s, Materializing param=model.layers.24.self_attn.o_proj.weight]
Loading weights: 89%|████████▉ | 152/171 [00:03<00:00, 51.56it/s, Materializing param=model.layers.24.self_attn.o_proj.weight]
Loading weights: 89%|████████▉ | 153/171 [00:03<00:00, 51.56it/s, Materializing param=model.layers.25.input_layernorm.weight]
Loading weights: 89%|████████▉ | 153/171 [00:03<00:00, 51.56it/s, Materializing param=model.layers.25.input_layernorm.weight]
Loading weights: 90%|█████████ | 154/171 [00:03<00:00, 51.56it/s, Materializing param=model.layers.25.mlp.down_proj.weight]
Loading weights: 90%|█████████ | 154/171 [00:03<00:00, 51.56it/s, Materializing param=model.layers.25.mlp.down_proj.weight]
Loading weights: 91%|█████████ | 155/171 [00:03<00:00, 52.13it/s, Materializing param=model.layers.25.mlp.down_proj.weight]
Loading weights: 91%|█████████ | 155/171 [00:03<00:00, 52.13it/s, Materializing param=model.layers.25.mlp.gate_proj.weight]
Loading weights: 91%|█████████ | 155/171 [00:03<00:00, 52.13it/s, Materializing param=model.layers.25.mlp.gate_proj.weight]
Loading weights: 91%|█████████ | 156/171 [00:03<00:00, 52.13it/s, Materializing param=model.layers.25.mlp.up_proj.weight]
Loading weights: 91%|█████████ | 156/171 [00:03<00:00, 52.13it/s, Materializing param=model.layers.25.mlp.up_proj.weight]
Loading weights: 92%|█████████▏| 157/171 [00:03<00:00, 52.13it/s, Materializing param=model.layers.25.post_attention_layernorm.weight]
Loading weights: 92%|█████████▏| 157/171 [00:03<00:00, 52.13it/s, Materializing param=model.layers.25.post_attention_layernorm.weight]
Loading weights: 92%|█████████▏| 158/171 [00:03<00:00, 52.13it/s, Materializing param=model.layers.25.self_attn.o_proj.weight]
Loading weights: 92%|█████████▏| 158/171 [00:03<00:00, 52.13it/s, Materializing param=model.layers.25.self_attn.o_proj.weight]
Loading weights: 93%|█████████▎| 159/171 [00:03<00:00, 52.13it/s, Materializing param=model.layers.26.input_layernorm.weight]
Loading weights: 93%|█████████▎| 159/171 [00:03<00:00, 52.13it/s, Materializing param=model.layers.26.input_layernorm.weight]
Loading weights: 94%|█████████▎| 160/171 [00:03<00:00, 52.13it/s, Materializing param=model.layers.26.mlp.down_proj.weight]
Loading weights: 94%|█████████▎| 160/171 [00:03<00:00, 52.13it/s, Materializing param=model.layers.26.mlp.down_proj.weight]
Loading weights: 94%|█████████▍| 161/171 [00:03<00:00, 52.13it/s, Materializing param=model.layers.26.mlp.gate_proj.weight]
Loading weights: 94%|█████████▍| 161/171 [00:03<00:00, 52.13it/s, Materializing param=model.layers.26.mlp.gate_proj.weight]
Loading weights: 95%|█████████▍| 162/171 [00:03<00:00, 55.22it/s, Materializing param=model.layers.26.mlp.gate_proj.weight]
Loading weights: 95%|█████████▍| 162/171 [00:03<00:00, 55.22it/s, Materializing param=model.layers.26.mlp.up_proj.weight]
Loading weights: 95%|█████████▍| 162/171 [00:03<00:00, 55.22it/s, Materializing param=model.layers.26.mlp.up_proj.weight]
Loading weights: 95%|█████████▌| 163/171 [00:03<00:00, 55.22it/s, Materializing param=model.layers.26.post_attention_layernorm.weight]
Loading weights: 95%|█████████▌| 163/171 [00:03<00:00, 55.22it/s, Materializing param=model.layers.26.post_attention_layernorm.weight]
Loading weights: 96%|█████████▌| 164/171 [00:03<00:00, 55.22it/s, Materializing param=model.layers.26.self_attn.o_proj.weight]
Loading weights: 96%|█████████▌| 164/171 [00:03<00:00, 55.22it/s, Materializing param=model.layers.26.self_attn.o_proj.weight]
Loading weights: 96%|█████████▋| 165/171 [00:03<00:00, 55.22it/s, Materializing param=model.layers.27.input_layernorm.weight]
Loading weights: 96%|█████████▋| 165/171 [00:03<00:00, 55.22it/s, Materializing param=model.layers.27.input_layernorm.weight]
Loading weights: 97%|█████████▋| 166/171 [00:03<00:00, 55.22it/s, Materializing param=model.layers.27.mlp.down_proj.weight]
Loading weights: 97%|█████████▋| 166/171 [00:03<00:00, 55.22it/s, Materializing param=model.layers.27.mlp.down_proj.weight]
Loading weights: 98%|█████████▊| 167/171 [00:03<00:00, 55.22it/s, Materializing param=model.layers.27.mlp.gate_proj.weight]
Loading weights: 98%|█████████▊| 167/171 [00:03<00:00, 55.22it/s, Materializing param=model.layers.27.mlp.gate_proj.weight]
Loading weights: 98%|█████████▊| 168/171 [00:03<00:00, 55.22it/s, Materializing param=model.layers.27.mlp.up_proj.weight]
Loading weights: 98%|█████████▊| 168/171 [00:03<00:00, 55.22it/s, Materializing param=model.layers.27.mlp.up_proj.weight]
Loading weights: 99%|█████████▉| 169/171 [00:03<00:00, 55.22it/s, Materializing param=model.layers.27.post_attention_layernorm.weight]
Loading weights: 99%|█████████▉| 169/171 [00:03<00:00, 55.22it/s, Materializing param=model.layers.27.post_attention_layernorm.weight]
Loading weights: 99%|█████████▉| 170/171 [00:03<00:00, 55.22it/s, Materializing param=model.layers.27.self_attn.o_proj.weight]
Loading weights: 99%|█████████▉| 170/171 [00:03<00:00, 55.22it/s, Materializing param=model.layers.27.self_attn.o_proj.weight]
Loading weights: 100%|██████████| 171/171 [00:03<00:00, 55.22it/s, Materializing param=model.norm.weight]
Loading weights: 100%|██████████| 171/171 [00:03<00:00, 55.22it/s, Materializing param=model.norm.weight]
Loading weights: 100%|██████████| 171/171 [00:03<00:00, 44.86it/s, Materializing param=model.norm.weight]
The tied weights mapping and config for this model specifies to tie model.embed_tokens.weight to lm_head.weight, but both are present in the checkpoints, so we will NOT tie them. You should update the config with `tie_word_embeddings=False` to silence this warning
LlamaForCausalLM LOAD REPORT from: /PROJECT/0325120031_A/ghong/taketimes/llm-bang/eval/outputs/hf_3b_base
Key | Status |
----------------------------------------------+---------+-
model.layers.{0...27}.self_attn.q_proj.weight | MISSING |
model.layers.{0...27}.self_attn.v_proj.weight | MISSING |
model.layers.{0...27}.self_attn.k_proj.weight | MISSING |
Notes:
- MISSING :those params were newly initialized because missing from the checkpoint. Consider training on your downstream task.
Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads.
Generating test split: 0%| | 0/900 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 900/900 [00:00<00:00, 178793.80 examples/s]
Generating test split: 0%| | 0/14042 [00:00<?, ? examples/s]
Generating test split: 100%|██████████| 14042/14042 [00:00<00:00, 785484.55 examples/s]
Generating dev split: 0%| | 0/285 [00:00<?, ? examples/s]
Generating dev split: 100%|██████████| 285/285 [00:00<00:00, 120453.11 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 48144.37 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 112478.49 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 111205.05 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 60907.81 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111323.89 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110428.16 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 65886.38 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 109308.51 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 108639.32 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 62591.72 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 112723.85 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 111911.01 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 65604.34 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 113015.18 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 112324.43 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 63364.78 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 112597.25 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 111818.59 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 61408.44 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 112774.87 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 112018.08 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 61782.96 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 112190.41 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 111453.58 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 58425.06 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 110765.31 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110063.31 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 57121.26 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111143.70 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110434.78 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 60178.04 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 110261.08 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 109508.51 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 62759.31 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111994.45 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110993.38 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 60311.64 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111576.60 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110818.99 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 61544.39 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111468.37 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110296.63 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 65196.44 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 109774.35 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 108936.31 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 65737.83 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111618.17 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110485.33 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 58772.64 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 109977.03 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 108169.03 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 59990.80 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111575.86 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110240.89 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 67061.80 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111448.63 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110664.49 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 67303.45 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111353.70 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110545.68 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 58333.82 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 110372.55 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 109775.08 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 64545.17 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111225.49 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110424.02 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 59715.09 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 109399.98 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 108948.40 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 63334.57 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111402.50 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110625.83 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 58827.59 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111825.49 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 111037.74 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 64054.05 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 112605.82 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 111475.09 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 64828.71 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111729.43 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110601.94 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 62914.56 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111393.62 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110595.50 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 60845.80 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111298.79 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110502.33 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 65356.84 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111734.63 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110976.23 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 61601.48 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111176.85 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110279.08 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 63381.58 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111445.42 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110702.76 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 56263.61 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 110895.88 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110072.98 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 59521.82 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111488.12 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110697.98 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 63814.68 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111674.89 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110903.72 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 62934.43 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111610.25 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110767.51 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 66024.67 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111281.31 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110496.94 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 60275.14 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111207.06 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110354.71 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 65111.21 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111713.55 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110931.92 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 62604.83 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 108212.64 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 107652.21 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 58445.05 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111081.15 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110315.64 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 60982.38 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111409.89 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110515.81 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 62418.50 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 109277.89 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 108826.81 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 64426.90 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 110805.79 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110026.71 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 61943.03 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 107998.56 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 107156.68 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 63479.19 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 110504.13 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 109694.53 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 60329.90 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111334.98 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110584.91 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 61257.39 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 110938.17 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110219.85 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 59080.54 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111107.64 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110281.35 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 60470.29 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111578.83 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110718.58 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 64277.93 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111285.74 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110500.05 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 65792.10 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111430.37 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110545.68 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 66554.01 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111931.18 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 111083.82 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 60966.83 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 110460.48 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 109693.50 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 63773.83 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111404.72 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110578.68 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 64146.85 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 111702.15 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 110885.97 examples/s]
Filter: 0%| | 0/285 [00:00<?, ? examples/s]
Filter: 100%|██████████| 285/285 [00:00<00:00, 57809.10 examples/s]
Filter: 0%| | 0/14042 [00:00<?, ? examples/s]
Filter: 85%|████████▌ | 12000/14042 [00:00<00:00, 110140.44 examples/s]
Filter: 100%|██████████| 14042/14042 [00:00<00:00, 109313.39 examples/s]
2026-03-05:01:48:08 INFO [tasks:700] Selected tasks:
2026-03-05:01:48:08 INFO [tasks:703] Group: global_mmlu_full_ko
2026-03-05:01:48:08 INFO [tasks:711] Subgroup: global_mmlu_full_ko_stem
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_abstract_algebra (global_mmlu/full/ko/global_mmlu_full_ko_abstract_algebra.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_anatomy (global_mmlu/full/ko/global_mmlu_full_ko_anatomy.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_astronomy (global_mmlu/full/ko/global_mmlu_full_ko_astronomy.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_college_biology (global_mmlu/full/ko/global_mmlu_full_ko_college_biology.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_college_chemistry (global_mmlu/full/ko/global_mmlu_full_ko_college_chemistry.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_college_computer_science (global_mmlu/full/ko/global_mmlu_full_ko_college_computer_science.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_college_mathematics (global_mmlu/full/ko/global_mmlu_full_ko_college_mathematics.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_college_physics (global_mmlu/full/ko/global_mmlu_full_ko_college_physics.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_computer_security (global_mmlu/full/ko/global_mmlu_full_ko_computer_security.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_conceptual_physics (global_mmlu/full/ko/global_mmlu_full_ko_conceptual_physics.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_electrical_engineering (global_mmlu/full/ko/global_mmlu_full_ko_electrical_engineering.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_elementary_mathematics (global_mmlu/full/ko/global_mmlu_full_ko_elementary_mathematics.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_high_school_biology (global_mmlu/full/ko/global_mmlu_full_ko_high_school_biology.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_high_school_chemistry (global_mmlu/full/ko/global_mmlu_full_ko_high_school_chemistry.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_high_school_computer_science (global_mmlu/full/ko/global_mmlu_full_ko_high_school_computer_science.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_high_school_mathematics (global_mmlu/full/ko/global_mmlu_full_ko_high_school_mathematics.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_high_school_physics (global_mmlu/full/ko/global_mmlu_full_ko_high_school_physics.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_high_school_statistics (global_mmlu/full/ko/global_mmlu_full_ko_high_school_statistics.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_machine_learning (global_mmlu/full/ko/global_mmlu_full_ko_machine_learning.yaml)
2026-03-05:01:48:08 INFO [tasks:711] Subgroup: global_mmlu_full_ko_other
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_business_ethics (global_mmlu/full/ko/global_mmlu_full_ko_business_ethics.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_clinical_knowledge (global_mmlu/full/ko/global_mmlu_full_ko_clinical_knowledge.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_college_medicine (global_mmlu/full/ko/global_mmlu_full_ko_college_medicine.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_global_facts (global_mmlu/full/ko/global_mmlu_full_ko_global_facts.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_human_aging (global_mmlu/full/ko/global_mmlu_full_ko_human_aging.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_management (global_mmlu/full/ko/global_mmlu_full_ko_management.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_marketing (global_mmlu/full/ko/global_mmlu_full_ko_marketing.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_medical_genetics (global_mmlu/full/ko/global_mmlu_full_ko_medical_genetics.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_miscellaneous (global_mmlu/full/ko/global_mmlu_full_ko_miscellaneous.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_nutrition (global_mmlu/full/ko/global_mmlu_full_ko_nutrition.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_professional_accounting (global_mmlu/full/ko/global_mmlu_full_ko_professional_accounting.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_professional_medicine (global_mmlu/full/ko/global_mmlu_full_ko_professional_medicine.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_virology (global_mmlu/full/ko/global_mmlu_full_ko_virology.yaml)
2026-03-05:01:48:08 INFO [tasks:711] Subgroup: global_mmlu_full_ko_social_sciences
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_econometrics (global_mmlu/full/ko/global_mmlu_full_ko_econometrics.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_high_school_geography (global_mmlu/full/ko/global_mmlu_full_ko_high_school_geography.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_high_school_government_and_politics (global_mmlu/full/ko/global_mmlu_full_ko_high_school_government_and_politics.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_high_school_macroeconomics (global_mmlu/full/ko/global_mmlu_full_ko_high_school_macroeconomics.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_high_school_microeconomics (global_mmlu/full/ko/global_mmlu_full_ko_high_school_microeconomics.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_high_school_psychology (global_mmlu/full/ko/global_mmlu_full_ko_high_school_psychology.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_human_sexuality (global_mmlu/full/ko/global_mmlu_full_ko_human_sexuality.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_professional_psychology (global_mmlu/full/ko/global_mmlu_full_ko_professional_psychology.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_public_relations (global_mmlu/full/ko/global_mmlu_full_ko_public_relations.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_security_studies (global_mmlu/full/ko/global_mmlu_full_ko_security_studies.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_sociology (global_mmlu/full/ko/global_mmlu_full_ko_sociology.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_us_foreign_policy (global_mmlu/full/ko/global_mmlu_full_ko_us_foreign_policy.yaml)
2026-03-05:01:48:08 INFO [tasks:711] Subgroup: global_mmlu_full_ko_humanities
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_formal_logic (global_mmlu/full/ko/global_mmlu_full_ko_formal_logic.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_high_school_european_history (global_mmlu/full/ko/global_mmlu_full_ko_high_school_european_history.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_high_school_us_history (global_mmlu/full/ko/global_mmlu_full_ko_high_school_us_history.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_high_school_world_history (global_mmlu/full/ko/global_mmlu_full_ko_high_school_world_history.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_international_law (global_mmlu/full/ko/global_mmlu_full_ko_international_law.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_jurisprudence (global_mmlu/full/ko/global_mmlu_full_ko_jurisprudence.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_logical_fallacies (global_mmlu/full/ko/global_mmlu_full_ko_logical_fallacies.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_moral_disputes (global_mmlu/full/ko/global_mmlu_full_ko_moral_disputes.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_moral_scenarios (global_mmlu/full/ko/global_mmlu_full_ko_moral_scenarios.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_philosophy (global_mmlu/full/ko/global_mmlu_full_ko_philosophy.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_prehistory (global_mmlu/full/ko/global_mmlu_full_ko_prehistory.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_professional_law (global_mmlu/full/ko/global_mmlu_full_ko_professional_law.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: global_mmlu_full_ko_world_religions (global_mmlu/full/ko/global_mmlu_full_ko_world_religions.yaml)
2026-03-05:01:48:08 INFO [tasks:691] Task: belebele_kor_Hang (belebele/belebele_kor_Hang.yaml)
2026-03-05:01:48:08 INFO [api.task:311] Building contexts for global_mmlu_full_ko_abstract_algebra on rank 0...
0%| | 0/100 [00:00<?, ?it/s]
100%|██████████| 100/100 [00:00<00:00, 2567.98it/s]
2026-03-05:01:48:08 INFO [api.task:311] Building contexts for global_mmlu_full_ko_anatomy on rank 0...
0%| | 0/135 [00:00<?, ?it/s]
100%|██████████| 135/135 [00:00<00:00, 2610.31it/s]
2026-03-05:01:48:08 INFO [api.task:311] Building contexts for global_mmlu_full_ko_astronomy on rank 0...
0%| | 0/152 [00:00<?, ?it/s]
100%|██████████| 152/152 [00:00<00:00, 2645.68it/s]
2026-03-05:01:48:08 INFO [api.task:311] Building contexts for global_mmlu_full_ko_college_biology on rank 0...
0%| | 0/144 [00:00<?, ?it/s]
100%|██████████| 144/144 [00:00<00:00, 2652.07it/s]
2026-03-05:01:48:08 INFO [api.task:311] Building contexts for global_mmlu_full_ko_college_chemistry on rank 0...
0%| | 0/100 [00:00<?, ?it/s]
100%|██████████| 100/100 [00:00<00:00, 2622.73it/s]
2026-03-05:01:48:09 INFO [api.task:311] Building contexts for global_mmlu_full_ko_college_computer_science on rank 0...
0%| | 0/100 [00:00<?, ?it/s]
100%|██████████| 100/100 [00:00<00:00, 2591.04it/s]
2026-03-05:01:48:09 INFO [api.task:311] Building contexts for global_mmlu_full_ko_college_mathematics on rank 0...
0%| | 0/100 [00:00<?, ?it/s]
100%|██████████| 100/100 [00:00<00:00, 2609.23it/s]
2026-03-05:01:48:09 INFO [api.task:311] Building contexts for global_mmlu_full_ko_college_physics on rank 0...
0%| | 0/102 [00:00<?, ?it/s]
100%|██████████| 102/102 [00:00<00:00, 2601.85it/s]
2026-03-05:01:48:09 INFO [api.task:311] Building contexts for global_mmlu_full_ko_computer_security on rank 0...
0%| | 0/100 [00:00<?, ?it/s]
100%|██████████| 100/100 [00:00<00:00, 2626.59it/s]
2026-03-05:01:48:09 INFO [api.task:311] Building contexts for global_mmlu_full_ko_conceptual_physics on rank 0...
0%| | 0/235 [00:00<?, ?it/s]
100%|██████████| 235/235 [00:00<00:00, 2642.05it/s]
2026-03-05:01:48:09 INFO [api.task:311] Building contexts for global_mmlu_full_ko_electrical_engineering on rank 0...
0%| | 0/145 [00:00<?, ?it/s]
100%|██████████| 145/145 [00:00<00:00, 2634.73it/s]
2026-03-05:01:48:09 INFO [api.task:311] Building contexts for global_mmlu_full_ko_elementary_mathematics on rank 0...
0%| | 0/378 [00:00<?, ?it/s]
71%|███████ | 268/378 [00:00<00:00, 2678.07it/s]
100%|██████████| 378/378 [00:00<00:00, 2685.30it/s]
2026-03-05:01:48:09 INFO [api.task:311] Building contexts for global_mmlu_full_ko_high_school_biology on rank 0...
0%| | 0/310 [00:00<?, ?it/s]
87%|████████▋ | 269/310 [00:00<00:00, 2686.67it/s]
100%|██████████| 310/310 [00:00<00:00, 2682.42it/s]
2026-03-05:01:48:09 INFO [api.task:311] Building contexts for global_mmlu_full_ko_high_school_chemistry on rank 0...
0%| | 0/203 [00:00<?, ?it/s]
100%|██████████| 203/203 [00:00<00:00, 2653.44it/s]
2026-03-05:01:48:09 INFO [api.task:311] Building contexts for global_mmlu_full_ko_high_school_computer_science on rank 0...
0%| | 0/100 [00:00<?, ?it/s]
100%|██████████| 100/100 [00:00<00:00, 2633.93it/s]
2026-03-05:01:48:09 INFO [api.task:311] Building contexts for global_mmlu_full_ko_high_school_mathematics on rank 0...
0%| | 0/270 [00:00<?, ?it/s]
99%|█████████▉| 267/270 [00:00<00:00, 2661.86it/s]
100%|██████████| 270/270 [00:00<00:00, 2659.17it/s]
2026-03-05:01:48:09 INFO [api.task:311] Building contexts for global_mmlu_full_ko_high_school_physics on rank 0...
0%| | 0/151 [00:00<?, ?it/s]
100%|██████████| 151/151 [00:00<00:00, 2633.09it/s]
2026-03-05:01:48:09 INFO [api.task:311] Building contexts for global_mmlu_full_ko_high_school_statistics on rank 0...
0%| | 0/216 [00:00<?, ?it/s]
100%|██████████| 216/216 [00:00<00:00, 2570.98it/s]
2026-03-05:01:48:10 INFO [api.task:311] Building contexts for global_mmlu_full_ko_machine_learning on rank 0...
0%| | 0/112 [00:00<?, ?it/s]
100%|██████████| 112/112 [00:00<00:00, 2615.28it/s]
2026-03-05:01:48:10 INFO [api.task:311] Building contexts for global_mmlu_full_ko_business_ethics on rank 0...
0%| | 0/100 [00:00<?, ?it/s]
100%|██████████| 100/100 [00:00<00:00, 2617.87it/s]
2026-03-05:01:48:10 INFO [api.task:311] Building contexts for global_mmlu_full_ko_clinical_knowledge on rank 0...
0%| | 0/265 [00:00<?, ?it/s]
100%|██████████| 265/265 [00:00<00:00, 2649.04it/s]
100%|██████████| 265/265 [00:00<00:00, 2647.16it/s]
2026-03-05:01:48:10 INFO [api.task:311] Building contexts for global_mmlu_full_ko_college_medicine on rank 0...
0%| | 0/173 [00:00<?, ?it/s]
100%|██████████| 173/173 [00:00<00:00, 2643.10it/s]
2026-03-05:01:48:10 INFO [api.task:311] Building contexts for global_mmlu_full_ko_global_facts on rank 0...
0%| | 0/100 [00:00<?, ?it/s]
100%|██████████| 100/100 [00:00<00:00, 2626.84it/s]
2026-03-05:01:48:10 INFO [api.task:311] Building contexts for global_mmlu_full_ko_human_aging on rank 0...
0%| | 0/223 [00:00<?, ?it/s]
100%|██████████| 223/223 [00:00<00:00, 2658.30it/s]
2026-03-05:01:48:10 INFO [api.task:311] Building contexts for global_mmlu_full_ko_management on rank 0...
0%| | 0/103 [00:00<?, ?it/s]
100%|██████████| 103/103 [00:00<00:00, 2635.03it/s]
2026-03-05:01:48:10 INFO [api.task:311] Building contexts for global_mmlu_full_ko_marketing on rank 0...
0%| | 0/234 [00:00<?, ?it/s]
100%|██████████| 234/234 [00:00<00:00, 2645.74it/s]
2026-03-05:01:48:10 INFO [api.task:311] Building contexts for global_mmlu_full_ko_medical_genetics on rank 0...
0%| | 0/100 [00:00<?, ?it/s]
100%|██████████| 100/100 [00:00<00:00, 2616.70it/s]
2026-03-05:01:48:10 INFO [api.task:311] Building contexts for global_mmlu_full_ko_miscellaneous on rank 0...
0%| | 0/783 [00:00<?, ?it/s]
34%|███▍ | 266/783 [00:00<00:00, 2657.08it/s]
68%|██████▊ | 534/783 [00:00<00:00, 2665.01it/s]
100%|██████████| 783/783 [00:00<00:00, 2668.39it/s]
2026-03-05:01:48:11 INFO [api.task:311] Building contexts for global_mmlu_full_ko_nutrition on rank 0...
0%| | 0/306 [00:00<?, ?it/s]
87%|████████▋ | 265/306 [00:00<00:00, 2648.78it/s]
100%|██████████| 306/306 [00:00<00:00, 2642.07it/s]
2026-03-05:01:48:11 INFO [api.task:311] Building contexts for global_mmlu_full_ko_professional_accounting on rank 0...
0%| | 0/282 [00:00<?, ?it/s]
95%|█████████▍| 267/282 [00:00<00:00, 2663.42it/s]
100%|██████████| 282/282 [00:00<00:00, 2662.57it/s]
2026-03-05:01:48:11 INFO [api.task:311] Building contexts for global_mmlu_full_ko_professional_medicine on rank 0...
0%| | 0/272 [00:00<?, ?it/s]
98%|█████████▊| 266/272 [00:00<00:00, 2659.76it/s]
100%|██████████| 272/272 [00:00<00:00, 2658.26it/s]
2026-03-05:01:48:11 INFO [api.task:311] Building contexts for global_mmlu_full_ko_virology on rank 0...
0%| | 0/166 [00:00<?, ?it/s]
100%|██████████| 166/166 [00:00<00:00, 2659.39it/s]
2026-03-05:01:48:11 INFO [api.task:311] Building contexts for global_mmlu_full_ko_econometrics on rank 0...
0%| | 0/114 [00:00<?, ?it/s]
100%|██████████| 114/114 [00:00<00:00, 2651.84it/s]
2026-03-05:01:48:11 INFO [api.task:311] Building contexts for global_mmlu_full_ko_high_school_geography on rank 0...
0%| | 0/198 [00:00<?, ?it/s]
100%|██████████| 198/198 [00:00<00:00, 2631.49it/s]
2026-03-05:01:48:11 INFO [api.task:311] Building contexts for global_mmlu_full_ko_high_school_government_and_politics on rank 0...
0%| | 0/193 [00:00<?, ?it/s]
100%|██████████| 193/193 [00:00<00:00, 2658.01it/s]
2026-03-05:01:48:11 INFO [api.task:311] Building contexts for global_mmlu_full_ko_high_school_macroeconomics on rank 0...
0%| | 0/390 [00:00<?, ?it/s]
68%|██████▊ | 266/390 [00:00<00:00, 2658.97it/s]
100%|██████████| 390/390 [00:00<00:00, 2662.06it/s]
2026-03-05:01:48:11 INFO [api.task:311] Building contexts for global_mmlu_full_ko_high_school_microeconomics on rank 0...
0%| | 0/238 [00:00<?, ?it/s]
100%|██████████| 238/238 [00:00<00:00, 2673.17it/s]
2026-03-05:01:48:12 INFO [api.task:311] Building contexts for global_mmlu_full_ko_high_school_psychology on rank 0...
0%| | 0/545 [00:00<?, ?it/s]
49%|████▉ | 266/545 [00:00<00:00, 2659.89it/s]
98%|█████████▊| 533/545 [00:00<00:00, 2664.62it/s]
100%|██████████| 545/545 [00:00<00:00, 2663.47it/s]
2026-03-05:01:48:12 INFO [api.task:311] Building contexts for global_mmlu_full_ko_human_sexuality on rank 0...
0%| | 0/131 [00:00<?, ?it/s]
100%|██████████| 131/131 [00:00<00:00, 2643.12it/s]
2026-03-05:01:48:12 INFO [api.task:311] Building contexts for global_mmlu_full_ko_professional_psychology on rank 0...
0%| | 0/612 [00:00<?, ?it/s]
44%|████▎ | 267/612 [00:00<00:00, 2664.93it/s]
88%|████████▊ | 537/612 [00:00<00:00, 2685.39it/s]
100%|██████████| 612/612 [00:00<00:00, 2681.13it/s]
2026-03-05:01:48:12 INFO [api.task:311] Building contexts for global_mmlu_full_ko_public_relations on rank 0...
0%| | 0/110 [00:00<?, ?it/s]
100%|██████████| 110/110 [00:00<00:00, 2629.52it/s]
2026-03-05:01:48:12 INFO [api.task:311] Building contexts for global_mmlu_full_ko_security_studies on rank 0...
0%| | 0/245 [00:00<?, ?it/s]
100%|██████████| 245/245 [00:00<00:00, 2660.38it/s]
2026-03-05:01:48:12 INFO [api.task:311] Building contexts for global_mmlu_full_ko_sociology on rank 0...
0%| | 0/201 [00:00<?, ?it/s]
100%|██████████| 201/201 [00:00<00:00, 2659.71it/s]
2026-03-05:01:48:12 INFO [api.task:311] Building contexts for global_mmlu_full_ko_us_foreign_policy on rank 0...
0%| | 0/100 [00:00<?, ?it/s]
100%|██████████| 100/100 [00:00<00:00, 2654.17it/s]
2026-03-05:01:48:12 INFO [api.task:311] Building contexts for global_mmlu_full_ko_formal_logic on rank 0...
0%| | 0/126 [00:00<?, ?it/s]
100%|██████████| 126/126 [00:00<00:00, 2607.54it/s]
2026-03-05:01:48:12 INFO [api.task:311] Building contexts for global_mmlu_full_ko_high_school_european_history on rank 0...
0%| | 0/165 [00:00<?, ?it/s]
100%|██████████| 165/165 [00:00<00:00, 2635.66it/s]
2026-03-05:01:48:13 INFO [api.task:311] Building contexts for global_mmlu_full_ko_high_school_us_history on rank 0...
0%| | 0/204 [00:00<?, ?it/s]
100%|██████████| 204/204 [00:00<00:00, 2639.29it/s]
2026-03-05:01:48:13 INFO [api.task:311] Building contexts for global_mmlu_full_ko_high_school_world_history on rank 0...
0%| | 0/237 [00:00<?, ?it/s]
100%|██████████| 237/237 [00:00<00:00, 2654.20it/s]
2026-03-05:01:48:13 INFO [api.task:311] Building contexts for global_mmlu_full_ko_international_law on rank 0...
0%| | 0/121 [00:00<?, ?it/s]
100%|██████████| 121/121 [00:00<00:00, 2629.51it/s]
2026-03-05:01:48:13 INFO [api.task:311] Building contexts for global_mmlu_full_ko_jurisprudence on rank 0...
0%| | 0/108 [00:00<?, ?it/s]
100%|██████████| 108/108 [00:00<00:00, 2619.73it/s]
2026-03-05:01:48:13 INFO [api.task:311] Building contexts for global_mmlu_full_ko_logical_fallacies on rank 0...
0%| | 0/163 [00:00<?, ?it/s]
100%|██████████| 163/163 [00:00<00:00, 2664.95it/s]
2026-03-05:01:48:13 INFO [api.task:311] Building contexts for global_mmlu_full_ko_moral_disputes on rank 0...
0%| | 0/346 [00:00<?, ?it/s]
77%|███████▋ | 267/346 [00:00<00:00, 2663.62it/s]
100%|██████████| 346/346 [00:00<00:00, 2667.41it/s]
2026-03-05:01:48:13 INFO [api.task:311] Building contexts for global_mmlu_full_ko_moral_scenarios on rank 0...
0%| | 0/895 [00:00<?, ?it/s]
30%|██▉ | 267/895 [00:00<00:00, 2667.60it/s]
60%|█████▉ | 535/895 [00:00<00:00, 2674.03it/s]
90%|████████▉ | 803/895 [00:00<00:00, 2673.21it/s]
100%|██████████| 895/895 [00:00<00:00, 2672.90it/s]
2026-03-05:01:48:13 INFO [api.task:311] Building contexts for global_mmlu_full_ko_philosophy on rank 0...
0%| | 0/311 [00:00<?, ?it/s]
86%|████████▌ | 266/311 [00:00<00:00, 2650.97it/s]
100%|██████████| 311/311 [00:00<00:00, 2649.39it/s]
2026-03-05:01:48:14 INFO [api.task:311] Building contexts for global_mmlu_full_ko_prehistory on rank 0...
0%| | 0/324 [00:00<?, ?it/s]
83%|████████▎ | 269/324 [00:00<00:00, 2682.21it/s]
100%|██████████| 324/324 [00:00<00:00, 2676.35it/s]
2026-03-05:01:48:14 INFO [api.task:311] Building contexts for global_mmlu_full_ko_professional_law on rank 0...
0%| | 0/1534 [00:00<?, ?it/s]
18%|█▊ | 269/1534 [00:00<00:00, 2683.96it/s]
35%|███▌ | 539/1534 [00:00<00:00, 2688.33it/s]
53%|█████▎ | 808/1534 [00:00<00:00, 2685.68it/s]
70%|███████ | 1077/1534 [00:00<00:00, 2683.27it/s]
88%|████████▊ | 1346/1534 [00:00<00:00, 2681.83it/s]
100%|██████████| 1534/1534 [00:00<00:00, 2683.84it/s]
2026-03-05:01:48:14 INFO [api.task:311] Building contexts for global_mmlu_full_ko_world_religions on rank 0...
0%| | 0/171 [00:00<?, ?it/s]
100%|██████████| 171/171 [00:00<00:00, 2544.60it/s]
2026-03-05:01:48:14 INFO [api.task:311] Building contexts for belebele_kor_Hang on rank 0...
0%| | 0/900 [00:00<?, ?it/s]
11%|█ | 100/900 [00:00<00:02, 270.80it/s]
25%|██▌ | 226/900 [00:00<00:01, 546.15it/s]
39%|███▉ | 354/900 [00:00<00:00, 753.67it/s]
54%|█████▍ | 485/900 [00:00<00:00, 913.87it/s]
69%|██████▊ | 617/900 [00:00<00:00, 1030.62it/s]
83%|████████▎ | 749/900 [00:00<00:00, 1114.43it/s]
98%|█████████▊| 881/900 [00:00<00:00, 1174.47it/s]
100%|██████████| 900/900 [00:00<00:00, 912.40it/s]
2026-03-05:01:48:15 INFO [evaluator:584] Running loglikelihood requests
Running loglikelihood requests: 0%| | 0/59768 [00:00<?, ?it/s]
Running loglikelihood requests: 0%| | 1/59768 [00:01<17:47:28, 1.07s/it]
Running loglikelihood requests: 0%| | 65/59768 [00:01<13:57, 71.28it/s]
Running loglikelihood requests: 0%| | 129/59768 [00:01<07:02, 141.04it/s]
Running loglikelihood requests: 0%| | 193/59768 [00:01<04:47, 207.33it/s]
Running loglikelihood requests: 0%| | 257/59768 [00:01<03:42, 267.98it/s]
Running loglikelihood requests: 1%| | 321/59768 [00:01<03:05, 319.97it/s]
Running loglikelihood requests: 1%| | 385/59768 [00:01<02:43, 362.69it/s]
Running loglikelihood requests: 1%| | 449/59768 [00:02<02:28, 399.14it/s]
Running loglikelihood requests: 1%| | 513/59768 [00:02<02:17, 432.35it/s]
Running loglikelihood requests: 1%| | 577/59768 [00:02<02:09, 457.33it/s]
Running loglikelihood requests: 1%| | 641/59768 [00:02<02:03, 477.92it/s]
Running loglikelihood requests: 1%| | 705/59768 [00:02<02:00, 491.75it/s]
Running loglikelihood requests: 1%|▏ | 769/59768 [00:02<01:58, 497.98it/s]
Running loglikelihood requests: 1%|▏ | 833/59768 [00:02<01:55, 509.62it/s]
Running loglikelihood requests: 2%|▏ | 897/59768 [00:02<01:53, 520.43it/s]
Running loglikelihood requests: 2%|▏ | 961/59768 [00:02<01:51, 528.98it/s]
Running loglikelihood requests: 2%|▏ | 1025/59768 [00:03<01:49, 536.65it/s]
Running loglikelihood requests: 2%|▏ | 1089/59768 [00:03<01:48, 540.03it/s]
Running loglikelihood requests: 2%|▏ | 1153/59768 [00:03<01:47, 544.61it/s]
Running loglikelihood requests: 2%|▏ | 1217/59768 [00:03<01:47, 545.19it/s]
Running loglikelihood requests: 2%|▏ | 1281/59768 [00:03<01:46, 547.38it/s]
Running loglikelihood requests: 2%|▏ | 1345/59768 [00:03<01:46, 547.67it/s]
Running loglikelihood requests: 2%|▏ | 1409/59768 [00:03<01:45, 552.93it/s]
Running loglikelihood requests: 2%|▏ | 1473/59768 [00:03<01:44, 557.23it/s]
Running loglikelihood requests: 3%|▎ | 1537/59768 [00:04<01:43, 560.44it/s]
Running loglikelihood requests: 3%|▎ | 1601/59768 [00:04<01:43, 563.55it/s]
Running loglikelihood requests: 3%|▎ | 1697/59768 [00:04<01:36, 601.76it/s]
Running loglikelihood requests: 3%|▎ | 1761/59768 [00:04<01:38, 589.81it/s]
Running loglikelihood requests: 3%|▎ | 1825/59768 [00:04<01:38, 585.57it/s]
Running loglikelihood requests: 3%|▎ | 1889/59768 [00:04<01:39, 581.46it/s]
Running loglikelihood requests: 3%|▎ | 1953/59768 [00:04<01:39, 580.57it/s]
Running loglikelihood requests: 3%|▎ | 2017/59768 [00:04<01:39, 579.90it/s]
Running loglikelihood requests: 3%|▎ | 2081/59768 [00:04<01:39, 576.95it/s]
Running loglikelihood requests: 4%|▎ | 2177/59768 [00:05<01:32, 620.28it/s]
Running loglikelihood requests: 4%|▍ | 2273/59768 [00:05<01:28, 649.23it/s]
Running loglikelihood requests: 4%|▍ | 2338/59768 [00:05<01:30, 633.97it/s]
Running loglikelihood requests: 4%|▍ | 2401/59768 [00:05<01:33, 615.79it/s]
Running loglikelihood requests: 4%|▍ | 2497/59768 [00:05<01:28, 647.91it/s]
Running loglikelihood requests: 4%|▍ | 2562/59768 [00:05<01:30, 633.16it/s]
Running loglikelihood requests: 4%|▍ | 2657/59768 [00:05<01:26, 657.08it/s]
Running loglikelihood requests: 5%|▍ | 2753/59768 [00:05<01:25, 667.85it/s]
Running loglikelihood requests: 5%|▍ | 2849/59768 [00:06<01:23, 681.08it/s]
Running loglikelihood requests: 5%|▍ | 2945/59768 [00:06<01:16, 745.98it/s]
Running loglikelihood requests: 5%|▌ | 3021/59768 [00:06<01:17, 734.44it/s]
Running loglikelihood requests: 5%|▌ | 3105/59768 [00:06<01:19, 708.38it/s]
Running loglikelihood requests: 5%|▌ | 3201/59768 [00:06<01:18, 718.32it/s]
Running loglikelihood requests: 5%|▌ | 3274/59768 [00:06<01:19, 709.88it/s]
Running loglikelihood requests: 6%|▌ | 3346/59768 [00:06<01:20, 701.16it/s]
Running loglikelihood requests: 6%|▌ | 3439/59768 [00:06<01:13, 763.32it/s]
Running loglikelihood requests: 6%|▌ | 3516/59768 [00:06<01:14, 753.14it/s]
Running loglikelihood requests: 6%|▌ | 3592/59768 [00:07<01:26, 649.36it/s]
Running loglikelihood requests: 6%|▌ | 3660/59768 [00:07<01:27, 641.62it/s]
Running loglikelihood requests: 6%|▌ | 3726/59768 [00:07<01:27, 638.74it/s]
Running loglikelihood requests: 6%|▋ | 3809/59768 [00:07<01:27, 641.65it/s]
Running loglikelihood requests: 6%|▋ | 3874/59768 [00:07<01:28, 633.56it/s]
Running loglikelihood requests: 7%|▋ | 3938/59768 [00:07<01:29, 627.29it/s]
Running loglikelihood requests: 7%|▋ | 4033/59768 [00:07<01:23, 664.99it/s]
Running loglikelihood requests: 7%|▋ | 4100/59768 [00:07<01:24, 658.68it/s]
Running loglikelihood requests: 7%|▋ | 4166/59768 [00:08<03:29, 265.15it/s]
Running loglikelihood requests: 7%|▋ | 4257/59768 [00:08<02:43, 338.77it/s]
Running loglikelihood requests: 7%|▋ | 4385/59768 [00:08<01:57, 472.68it/s]
Running loglikelihood requests: 7%|▋ | 4456/59768 [00:08<01:48, 511.86it/s]
Running loglikelihood requests: 8%|▊ | 4577/59768 [00:09<01:32, 598.18it/s]
Running loglikelihood requests: 8%|▊ | 4673/59768 [00:09<01:25, 642.01it/s]
Running loglikelihood requests: 8%|▊ | 4801/59768 [00:09<01:12, 754.33it/s]
Running loglikelihood requests: 8%|▊ | 4897/59768 [00:09<01:12, 759.55it/s]
Running loglikelihood requests: 8%|▊ | 4993/59768 [00:09<01:11, 763.96it/s]
Running loglikelihood requests: 9%|▊ | 5089/59768 [00:09<01:11, 766.65it/s]
Running loglikelihood requests: 9%|▊ | 5185/59768 [00:09<01:10, 770.94it/s]
Running loglikelihood requests: 9%|▉ | 5281/59768 [00:09<01:10, 772.20it/s]
Running loglikelihood requests: 9%|▉ | 5409/59768 [00:10<01:07, 809.45it/s]
Running loglikelihood requests: 9%|▉ | 5505/59768 [00:10<01:07, 804.83it/s]
Running loglikelihood requests: 9%|▉ | 5633/59768 [00:10<01:04, 836.62it/s]
Running loglikelihood requests: 10%|▉ | 5761/59768 [00:10<00:59, 914.22it/s]
Running loglikelihood requests: 10%|▉ | 5857/59768 [00:10<01:01, 881.05it/s]
Running loglikelihood requests: 10%|▉ | 5953/59768 [00:10<01:02, 856.00it/s]
Running loglikelihood requests: 10%|█ | 6081/59768 [00:10<01:02, 859.71it/s]
Running loglikelihood requests: 10%|█ | 6177/59768 [00:10<01:03, 842.27it/s]
Running loglikelihood requests: 11%|█ | 6305/59768 [00:11<01:02, 859.95it/s]
Running loglikelihood requests: 11%|█ | 6401/59768 [00:11<01:03, 839.65it/s]
Running loglikelihood requests: 11%|█ | 6529/59768 [00:11<01:01, 862.20it/s]
Running loglikelihood requests: 11%|█ | 6625/59768 [00:11<01:02, 846.44it/s]
Running loglikelihood requests: 11%|█▏ | 6753/59768 [00:11<00:57, 928.42it/s]
Running loglikelihood requests: 11%|█▏ | 6849/59768 [00:11<00:59, 892.47it/s]
Running loglikelihood requests: 12%|█▏ | 6977/59768 [00:11<00:54, 965.67it/s]
Running loglikelihood requests: 12%|█▏ | 7075/59768 [00:11<00:57, 916.76it/s]
Running loglikelihood requests: 12%|█▏ | 7201/59768 [00:12<00:53, 983.12it/s]
Running loglikelihood requests: 12%|█▏ | 7301/59768 [00:12<00:55, 941.50it/s]
Running loglikelihood requests: 12%|█▏ | 7425/59768 [00:12<00:52, 997.32it/s]
Running loglikelihood requests: 13%|█▎ | 7526/59768 [00:12<00:54, 957.40it/s]
Running loglikelihood requests: 13%|█▎ | 7649/59768 [00:12<00:55, 938.56it/s]
Running loglikelihood requests: 13%|█▎ | 7745/59768 [00:12<00:57, 907.68it/s]
Running loglikelihood requests: 13%|█▎ | 7873/59768 [00:12<00:52, 990.43it/s]
Running loglikelihood requests: 13%|█▎ | 8001/59768 [00:12<00:52, 978.38it/s]
Running loglikelihood requests: 14%|█▎ | 8100/59768 [00:13<00:54, 944.36it/s]
Running loglikelihood requests: 14%|█▍ | 8225/59768 [00:13<00:50, 1014.96it/s]
Running loglikelihood requests: 14%|█▍ | 8328/59768 [00:13<00:52, 982.17it/s]
Running loglikelihood requests: 14%|█▍ | 8449/59768 [00:13<00:49, 1035.46it/s]
Running loglikelihood requests: 14%|█▍ | 8554/59768 [00:13<00:51, 998.57it/s]
Running loglikelihood requests: 15%|█▍ | 8673/59768 [00:13<00:49, 1041.60it/s]
Running loglikelihood requests: 15%|█▍ | 8778/59768 [00:13<00:50, 1003.16it/s]
Running loglikelihood requests: 15%|█▍ | 8897/59768 [00:13<00:48, 1049.57it/s]
Running loglikelihood requests: 15%|█▌ | 9025/59768 [00:13<00:49, 1021.88it/s]
Running loglikelihood requests: 15%|█▌ | 9153/59768 [00:13<00:46, 1086.25it/s]
Running loglikelihood requests: 16%|█▌ | 9281/59768 [00:14<00:48, 1048.91it/s]
Running loglikelihood requests: 16%|█▌ | 9409/59768 [00:14<00:49, 1022.28it/s]
Running loglikelihood requests: 16%|█▌ | 9537/59768 [00:14<00:46, 1082.12it/s]
Running loglikelihood requests: 16%|█▌ | 9647/59768 [00:14<00:47, 1049.42it/s]
Running loglikelihood requests: 16%|█▋ | 9761/59768 [00:14<00:46, 1069.64it/s]
Running loglikelihood requests: 17%|█▋ | 9889/59768 [00:14<00:48, 1037.16it/s]
Running loglikelihood requests: 17%|█▋ | 10017/59768 [00:14<00:45, 1100.28it/s]
Running loglikelihood requests: 17%|█▋ | 10145/59768 [00:14<00:46, 1057.98it/s]
Running loglikelihood requests: 17%|█▋ | 10273/59768 [00:15<00:44, 1116.09it/s]
Running loglikelihood requests: 17%|█▋ | 10401/59768 [00:15<00:42, 1160.34it/s]
Running loglikelihood requests: 18%|█▊ | 10529/59768 [00:15<00:41, 1183.73it/s]
Running loglikelihood requests: 18%|█▊ | 10657/59768 [00:15<00:40, 1210.24it/s]
Running loglikelihood requests: 18%|█▊ | 10785/59768 [00:15<00:40, 1222.55it/s]
Running loglikelihood requests: 18%|█▊ | 10913/59768 [00:15<00:42, 1147.99it/s]
Running loglikelihood requests: 19%|█▊ | 11072/59768 [00:15<00:38, 1270.87it/s]
Running loglikelihood requests: 19%|█▊ | 11202/59768 [00:15<00:39, 1235.21it/s]
Running loglikelihood requests: 19%|█▉ | 11329/59768 [00:15<00:41, 1160.73it/s]
Running loglikelihood requests: 19%|█▉ | 11481/59768 [00:16<00:38, 1258.75it/s]
Running loglikelihood requests: 19%|█▉ | 11617/59768 [00:16<00:41, 1152.39it/s]
Running loglikelihood requests: 20%|█▉ | 11767/59768 [00:16<00:38, 1244.02it/s]
Running loglikelihood requests: 20%|█▉ | 11905/59768 [00:16<00:41, 1147.11it/s]
Running loglikelihood requests: 20%|██ | 12065/59768 [00:16<00:38, 1225.61it/s]
Running loglikelihood requests: 20%|██ | 12193/59768 [00:16<00:41, 1156.83it/s]
Running loglikelihood requests: 21%|██ | 12353/59768 [00:16<00:38, 1234.77it/s]
Running loglikelihood requests: 21%|██ | 12513/59768 [00:16<00:39, 1209.16it/s]
Running loglikelihood requests: 21%|██ | 12673/59768 [00:16<00:36, 1280.82it/s]
Running loglikelihood requests: 21%|██▏ | 12833/59768 [00:17<00:35, 1334.22it/s]
Running loglikelihood requests: 22%|██▏ | 12969/59768 [00:17<00:36, 1265.85it/s]
Running loglikelihood requests: 22%|██▏ | 13121/59768 [00:17<00:35, 1305.33it/s]
Running loglikelihood requests: 22%|██▏ | 13281/59768 [00:17<00:34, 1354.29it/s]
Running loglikelihood requests: 22%|██▏ | 13441/59768 [00:17<00:33, 1381.03it/s]
Running loglikelihood requests: 23%|██▎ | 13601/59768 [00:17<00:32, 1399.59it/s]
Running loglikelihood requests: 23%|██▎ | 13761/59768 [00:17<00:32, 1421.31it/s]
Running loglikelihood requests: 23%|██▎ | 13921/59768 [00:17<00:31, 1441.94it/s]
Running loglikelihood requests: 24%|██▎ | 14081/59768 [00:17<00:31, 1456.01it/s]
Running loglikelihood requests: 24%|██▍ | 14241/59768 [00:18<00:31, 1465.09it/s]
Running loglikelihood requests: 24%|██▍ | 14401/59768 [00:18<00:30, 1475.65it/s]
Running loglikelihood requests: 24%|██▍ | 14549/59768 [00:18<00:45, 986.18it/s]
Running loglikelihood requests: 25%|██▍ | 14724/59768 [00:18<00:39, 1148.91it/s]
Running loglikelihood requests: 25%|██▍ | 14885/59768 [00:18<00:38, 1168.49it/s]
Running loglikelihood requests: 25%|██▌ | 15077/59768 [00:18<00:34, 1309.41it/s]
Running loglikelihood requests: 26%|██▌ | 15269/59768 [00:18<00:31, 1421.68it/s]
Running loglikelihood requests: 26%|██▌ | 15461/59768 [00:19<00:29, 1504.98it/s]
Running loglikelihood requests: 26%|██▌ | 15653/59768 [00:19<00:29, 1487.40it/s]
Running loglikelihood requests: 27%|██▋ | 15881/59768 [00:19<00:27, 1591.05it/s]
Running loglikelihood requests: 27%|██▋ | 16073/59768 [00:19<00:26, 1636.27it/s]
Running loglikelihood requests: 27%|██▋ | 16265/59768 [00:19<00:26, 1671.51it/s]
Running loglikelihood requests: 28%|██▊ | 16489/59768 [00:19<00:23, 1811.15it/s]
Running loglikelihood requests: 28%|██▊ | 16681/59768 [00:19<00:24, 1793.01it/s]
Running loglikelihood requests: 28%|██▊ | 16873/59768 [00:19<00:24, 1777.88it/s]
Running loglikelihood requests: 29%|██▊ | 17065/59768 [00:19<00:24, 1763.29it/s]
Running loglikelihood requests: 29%|██▉ | 17289/59768 [00:20<00:22, 1885.80it/s]
Running loglikelihood requests: 29%|██▉ | 17481/59768 [00:20<00:22, 1846.74it/s]
Running loglikelihood requests: 30%|██▉ | 17673/59768 [00:20<00:23, 1814.78it/s]
Running loglikelihood requests: 30%|██▉ | 17897/59768 [00:20<00:21, 1919.97it/s]
Running loglikelihood requests: 30%|███ | 18091/59768 [00:20<00:22, 1862.80it/s]
Running loglikelihood requests: 31%|███ | 18313/59768 [00:20<00:21, 1953.55it/s]
Running loglikelihood requests: 31%|███ | 18510/59768 [00:20<00:21, 1909.57it/s]
Running loglikelihood requests: 31%|███▏ | 18729/59768 [00:20<00:20, 1984.56it/s]
Running loglikelihood requests: 32%|███▏ | 18929/59768 [00:20<00:21, 1940.76it/s]
Running loglikelihood requests: 32%|███▏ | 19145/59768 [00:21<00:20, 1999.89it/s]
Running loglikelihood requests: 32%|███▏ | 19346/59768 [00:21<00:20, 1956.71it/s]
Running loglikelihood requests: 33%|███▎ | 19593/59768 [00:21<00:19, 2034.69it/s]
Running loglikelihood requests: 33%|███▎ | 19797/59768 [00:21<00:20, 1998.18it/s]
Running loglikelihood requests: 34%|███▎ | 20041/59768 [00:21<00:19, 2054.28it/s]
Running loglikelihood requests: 34%|███▍ | 20247/59768 [00:21<00:19, 2015.94it/s]
Running loglikelihood requests: 34%|███▍ | 20489/59768 [00:21<00:19, 2064.11it/s]
Running loglikelihood requests: 35%|███▍ | 20696/59768 [00:21<00:19, 2029.58it/s]
Running loglikelihood requests: 35%|███▌ | 20941/59768 [00:21<00:18, 2082.15it/s]
Running loglikelihood requests: 35%|███▌ | 21149/59768 [00:21<00:18, 2034.06it/s]
Running loglikelihood requests: 36%|███▌ | 21379/59768 [00:22<00:18, 2108.88it/s]
Running loglikelihood requests: 36%|███▌ | 21608/59768 [00:22<00:17, 2160.72it/s]
Running loglikelihood requests: 37%|███▋ | 21825/59768 [00:22<00:18, 2034.83it/s]
Running loglikelihood requests: 37%|███▋ | 22061/59768 [00:22<00:18, 2058.17it/s]
Running loglikelihood requests: 37%|███▋ | 22268/59768 [00:22<00:18, 2033.52it/s]
Running loglikelihood requests: 38%|███▊ | 22477/59768 [00:22<00:19, 1955.51it/s]
Running loglikelihood requests: 38%|███▊ | 22733/59768 [00:22<00:17, 2064.24it/s]
Running loglikelihood requests: 38%|███▊ | 22941/59768 [00:22<00:18, 2037.89it/s]
Running loglikelihood requests: 39%|███▉ | 23181/59768 [00:22<00:17, 2084.48it/s]
Running loglikelihood requests: 39%|███▉ | 23390/59768 [00:23<00:17, 2060.48it/s]
Running loglikelihood requests: 39%|███▉ | 23597/59768 [00:23<00:18, 1973.77it/s]
Running loglikelihood requests: 40%|███▉ | 23821/59768 [00:23<00:18, 1955.54it/s]
Running loglikelihood requests: 40%|████ | 24081/59768 [00:23<00:18, 1949.08it/s]
Running loglikelihood requests: 41%|████ | 24309/59768 [00:23<00:18, 1959.03it/s]
Running loglikelihood requests: 41%|████ | 24565/59768 [00:23<00:17, 1972.86it/s]
Running loglikelihood requests: 42%|████▏ | 24821/59768 [00:23<00:16, 2090.66it/s]
Running loglikelihood requests: 42%|████▏ | 25032/59768 [00:23<00:16, 2082.99it/s]
Running loglikelihood requests: 42%|████▏ | 25242/59768 [00:24<00:17, 2014.01it/s]
Running loglikelihood requests: 43%|████▎ | 25444/59768 [00:24<00:17, 2012.27it/s]
Running loglikelihood requests: 43%|████▎ | 25689/59768 [00:24<00:16, 2108.75it/s]
Running loglikelihood requests: 43%|████▎ | 25901/59768 [00:24<00:16, 2097.64it/s]
Running loglikelihood requests: 44%|████▎ | 26112/59768 [00:24<00:16, 2031.35it/s]
Running loglikelihood requests: 44%|████▍ | 26333/59768 [00:24<00:16, 2010.59it/s]
Running loglikelihood requests: 44%|████▍ | 26589/59768 [00:24<00:15, 2136.08it/s]
Running loglikelihood requests: 45%|████▍ | 26804/59768 [00:24<00:15, 2119.64it/s]
Running loglikelihood requests: 45%|████▌ | 27037/59768 [00:24<00:15, 2160.59it/s]
Running loglikelihood requests: 46%|████▌ | 27254/59768 [00:24<00:15, 2157.90it/s]
Running loglikelihood requests: 46%|████▌ | 27471/59768 [00:25<00:15, 2083.85it/s]
Running loglikelihood requests: 46%|████▋ | 27709/59768 [00:25<00:14, 2144.78it/s]
Running loglikelihood requests: 47%|████▋ | 27924/59768 [00:25<00:14, 2144.80it/s]
Running loglikelihood requests: 47%|████▋ | 28139/59768 [00:25<00:15, 2078.06it/s]
Running loglikelihood requests: 47%|████▋ | 28385/59768 [00:25<00:14, 2171.92it/s]
Running loglikelihood requests: 48%|████▊ | 28603/59768 [00:25<00:14, 2173.40it/s]
Running loglikelihood requests: 48%|████▊ | 28821/59768 [00:25<00:14, 2110.24it/s]
Running loglikelihood requests: 49%|████▊ | 29061/59768 [00:25<00:14, 2180.66it/s]
Running loglikelihood requests: 49%|████▉ | 29289/59768 [00:25<00:14, 2124.42it/s]
Running loglikelihood requests: 49%|████▉ | 29549/59768 [00:26<00:13, 2239.19it/s]
Running loglikelihood requests: 50%|████▉ | 29774/59768 [00:26<00:13, 2165.13it/s]
Running loglikelihood requests: 50%|█████ | 30033/59768 [00:26<00:13, 2268.71it/s]
Running loglikelihood requests: 51%|█████ | 30261/59768 [00:26<00:13, 2205.44it/s]
Running loglikelihood requests: 51%|█████ | 30517/59768 [00:26<00:12, 2301.63it/s]
Running loglikelihood requests: 51%|█████▏ | 30749/59768 [00:26<00:12, 2240.87it/s]
Running loglikelihood requests: 52%|█████▏ | 31001/59768 [00:26<00:12, 2318.16it/s]
Running loglikelihood requests: 52%|█████▏ | 31234/59768 [00:26<00:12, 2253.07it/s]
Running loglikelihood requests: 53%|█████▎ | 31485/59768 [00:26<00:12, 2319.07it/s]
Running loglikelihood requests: 53%|█████▎ | 31741/59768 [00:26<00:12, 2230.55it/s]
Running loglikelihood requests: 54%|█████▎ | 31997/59768 [00:27<00:12, 2313.13it/s]
Running loglikelihood requests: 54%|█████▍ | 32230/59768 [00:27<00:12, 2255.69it/s]
Running loglikelihood requests: 54%|█████▍ | 32477/59768 [00:27<00:11, 2309.72it/s]
Running loglikelihood requests: 55%|█████▍ | 32710/59768 [00:27<00:12, 2253.70it/s]
Running loglikelihood requests: 55%|█████▌ | 32965/59768 [00:27<00:11, 2337.83it/s]
Running loglikelihood requests: 56%|█████▌ | 33200/59768 [00:27<00:11, 2273.80it/s]
Running loglikelihood requests: 56%|█████▌ | 33477/59768 [00:27<00:11, 2350.80it/s]
Running loglikelihood requests: 56%|█████▋ | 33713/59768 [00:27<00:11, 2303.39it/s]
Running loglikelihood requests: 57%|█████▋ | 33989/59768 [00:27<00:10, 2371.59it/s]
Running loglikelihood requests: 57%|█████▋ | 34227/59768 [00:28<00:11, 2320.07it/s]
Running loglikelihood requests: 58%|█████▊ | 34505/59768 [00:28<00:10, 2387.05it/s]
Running loglikelihood requests: 58%|█████▊ | 34744/59768 [00:28<00:10, 2338.92it/s]
Running loglikelihood requests: 59%|█████▊ | 35021/59768 [00:28<00:10, 2399.66it/s]
Running loglikelihood requests: 59%|█████▉ | 35261/59768 [00:28<00:10, 2345.90it/s]
Running loglikelihood requests: 59%|█████▉ | 35537/59768 [00:28<00:10, 2402.51it/s]
Running loglikelihood requests: 60%|█████▉ | 35778/59768 [00:28<00:10, 2351.13it/s]
Running loglikelihood requests: 60%|██████ | 36053/59768 [00:28<00:09, 2409.38it/s]
Running loglikelihood requests: 61%|██████ | 36294/59768 [00:28<00:09, 2366.61it/s]
Running loglikelihood requests: 61%|██████ | 36573/59768 [00:29<00:09, 2442.55it/s]
Running loglikelihood requests: 62%|██████▏ | 36818/59768 [00:29<00:09, 2405.64it/s]
Running loglikelihood requests: 62%|██████▏ | 37093/59768 [00:29<00:09, 2452.44it/s]
Running loglikelihood requests: 62%|██████▏ | 37353/59768 [00:29<00:09, 2309.70it/s]
Running loglikelihood requests: 63%|██████▎ | 37645/59768 [00:29<00:09, 2451.32it/s]
Running loglikelihood requests: 63%|██████▎ | 37945/59768 [00:29<00:08, 2573.27it/s]
Running loglikelihood requests: 64%|██████▍ | 38205/59768 [00:29<00:08, 2483.71it/s]
Running loglikelihood requests: 64%|██████▍ | 38489/59768 [00:29<00:08, 2563.17it/s]
Running loglikelihood requests: 65%|██████▍ | 38747/59768 [00:29<00:08, 2472.33it/s]
Running loglikelihood requests: 65%|██████▌ | 39033/59768 [00:30<00:08, 2559.94it/s]
Running loglikelihood requests: 66%|██████▌ | 39291/59768 [00:30<00:08, 2540.17it/s]
Running loglikelihood requests: 66%|██████▌ | 39557/59768 [00:30<00:07, 2556.79it/s]
Running loglikelihood requests: 67%|██████▋ | 39849/59768 [00:30<00:08, 2480.88it/s]
Running loglikelihood requests: 67%|██████▋ | 40141/59768 [00:30<00:07, 2579.46it/s]
Running loglikelihood requests: 68%|██████▊ | 40429/59768 [00:30<00:07, 2641.23it/s]
Running loglikelihood requests: 68%|██████▊ | 40695/59768 [00:30<00:07, 2546.91it/s]
Running loglikelihood requests: 69%|██████▊ | 40977/59768 [00:30<00:07, 2605.59it/s]
Running loglikelihood requests: 69%|██████▉ | 41239/59768 [00:30<00:07, 2514.22it/s]
Running loglikelihood requests: 69%|██████▉ | 41525/59768 [00:30<00:07, 2591.59it/s]
Running loglikelihood requests: 70%|██████▉ | 41786/59768 [00:31<00:07, 2568.59it/s]
Running loglikelihood requests: 70%|███████ | 42045/59768 [00:31<00:06, 2567.99it/s]
Running loglikelihood requests: 71%|███████ | 42341/59768 [00:31<00:06, 2657.81it/s]
Running loglikelihood requests: 71%|███████▏ | 42608/59768 [00:31<00:06, 2555.35it/s]
Running loglikelihood requests: 72%|███████▏ | 42889/59768 [00:31<00:06, 2602.73it/s]
Running loglikelihood requests: 72%|███████▏ | 43151/59768 [00:31<00:06, 2503.72it/s]
Running loglikelihood requests: 73%|███████▎ | 43437/59768 [00:31<00:06, 2593.96it/s]
Running loglikelihood requests: 73%|███████▎ | 43729/59768 [00:31<00:05, 2674.28it/s]
Running loglikelihood requests: 74%|███████▎ | 43998/59768 [00:31<00:06, 2575.38it/s]
Running loglikelihood requests: 74%|███████▍ | 44304/59768 [00:32<00:05, 2712.94it/s]
Running loglikelihood requests: 75%|███████▍ | 44577/59768 [00:32<00:05, 2571.52it/s]
Running loglikelihood requests: 75%|███████▌ | 44881/59768 [00:32<00:05, 2703.13it/s]
Running loglikelihood requests: 76%|███████▌ | 45185/59768 [00:32<00:05, 2799.28it/s]
Running loglikelihood requests: 76%|███████▌ | 45468/59768 [00:32<00:05, 2646.06it/s]
Running loglikelihood requests: 77%|███████▋ | 45757/59768 [00:32<00:05, 2713.99it/s]
Running loglikelihood requests: 77%|███████▋ | 46031/59768 [00:32<00:05, 2635.21it/s]
Running loglikelihood requests: 77%|███████▋ | 46310/59768 [00:32<00:05, 2678.89it/s]
Running loglikelihood requests: 78%|███████▊ | 46593/59768 [00:32<00:04, 2719.27it/s]
Running loglikelihood requests: 78%|███████▊ | 46867/59768 [00:32<00:04, 2640.95it/s]
Running loglikelihood requests: 79%|███████▉ | 47167/59768 [00:33<00:04, 2744.04it/s]
Running loglikelihood requests: 79%|███████▉ | 47443/59768 [00:33<00:04, 2588.54it/s]
Running loglikelihood requests: 80%|███████▉ | 47747/59768 [00:33<00:04, 2715.21it/s]
Running loglikelihood requests: 80%|████████ | 48040/59768 [00:33<00:04, 2776.38it/s]
Running loglikelihood requests: 81%|████████ | 48320/59768 [00:33<00:04, 2615.01it/s]
Running loglikelihood requests: 81%|████████▏ | 48621/59768 [00:33<00:04, 2725.68it/s]
Running loglikelihood requests: 82%|████████▏ | 48917/59768 [00:33<00:03, 2726.55it/s]
Running loglikelihood requests: 82%|████████▏ | 49192/59768 [00:33<00:03, 2650.86it/s]
Running loglikelihood requests: 83%|████████▎ | 49497/59768 [00:33<00:03, 2763.70it/s]
Running loglikelihood requests: 83%|████████▎ | 49805/59768 [00:34<00:03, 2782.02it/s]
Running loglikelihood requests: 84%|████████▍ | 50085/59768 [00:34<00:03, 2700.76it/s]
Running loglikelihood requests: 84%|████████▍ | 50389/59768 [00:34<00:03, 2729.05it/s]
Running loglikelihood requests: 85%|████████▍ | 50691/59768 [00:34<00:03, 2811.31it/s]
Running loglikelihood requests: 85%|████████▌ | 50974/59768 [00:34<00:03, 2661.77it/s]
Running loglikelihood requests: 86%|████████▌ | 51279/59768 [00:34<00:03, 2770.33it/s]
Running loglikelihood requests: 86%|████████▋ | 51559/59768 [00:34<00:03, 2626.47it/s]
Running loglikelihood requests: 87%|████████▋ | 51866/59768 [00:34<00:02, 2749.65it/s]
Running loglikelihood requests: 87%|████████▋ | 52173/59768 [00:34<00:02, 2772.04it/s]
Running loglikelihood requests: 88%|████████▊ | 52453/59768 [00:35<00:02, 2685.94it/s]
Running loglikelihood requests: 88%|████████▊ | 52749/59768 [00:35<00:02, 2697.31it/s]
Running loglikelihood requests: 89%|████████▉ | 53054/59768 [00:35<00:02, 2796.60it/s]
Running loglikelihood requests: 89%|████████▉ | 53336/59768 [00:35<00:02, 2640.28it/s]
Running loglikelihood requests: 90%|████████▉ | 53640/59768 [00:35<00:02, 2751.65it/s]
Running loglikelihood requests: 90%|█████████ | 53918/59768 [00:35<00:02, 2609.55it/s]
Running loglikelihood requests: 91%|█████████ | 54226/59768 [00:35<00:02, 2740.05it/s]
Running loglikelihood requests: 91%|█████████ | 54521/59768 [00:35<00:01, 2738.03it/s]
Running loglikelihood requests: 92%|█████████▏| 54797/59768 [00:35<00:01, 2633.91it/s]
Running loglikelihood requests: 92%|█████████▏| 55101/59768 [00:36<00:01, 2689.30it/s]
Running loglikelihood requests: 93%|█████████▎| 55393/59768 [00:36<00:01, 2584.45it/s]
Running loglikelihood requests: 93%|█████████▎| 55702/59768 [00:36<00:01, 2722.86it/s]
Running loglikelihood requests: 94%|█████████▎| 55977/59768 [00:36<00:01, 2589.36it/s]
Running loglikelihood requests: 94%|█████████▍| 56289/59768 [00:36<00:01, 2735.19it/s]
Running loglikelihood requests: 95%|█████████▍| 56581/59768 [00:36<00:01, 2727.67it/s]
Running loglikelihood requests: 95%|█████████▌| 56856/59768 [00:36<00:01, 2655.19it/s]
Running loglikelihood requests: 96%|█████████▌| 57165/59768 [00:36<00:00, 2710.18it/s]
Running loglikelihood requests: 96%|█████████▌| 57438/59768 [00:36<00:00, 2629.19it/s]
Running loglikelihood requests: 97%|█████████▋| 57743/59768 [00:37<00:00, 2747.08it/s]
Running loglikelihood requests: 97%|█████████▋| 58020/59768 [00:37<00:00, 2607.93it/s]
Running loglikelihood requests: 98%|█████████▊| 58329/59768 [00:37<00:00, 2528.72it/s]
Running loglikelihood requests: 98%|█████████▊| 58640/59768 [00:37<00:00, 2684.70it/s]
Running loglikelihood requests: 99%|█████████▊| 58912/59768 [00:37<00:00, 2532.74it/s]
Running loglikelihood requests: 99%|█████████▉| 59169/59768 [00:37<00:00, 2465.79it/s]
Running loglikelihood requests: 99%|█████████▉| 59421/59768 [00:37<00:00, 2422.87it/s]
Running loglikelihood requests: 100%|█████████▉| 59665/59768 [00:37<00:00, 2297.83it/s]
Running loglikelihood requests: 100%|██████████| 59768/59768 [00:37<00:00, 1576.92it/s]
2026-03-05:01:49:09 INFO [loggers.evaluation_tracker:247] Saving results aggregated
hf ({'pretrained': '/PROJECT/0325120031_A/ghong/taketimes/llm-bang/eval/outputs/hf_3b_base', 'dtype': 'bfloat16'}), gen_kwargs: ({}), limit: None, num_fewshot: None, batch_size: 8
| Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr|
|-----------------------------------------------------------|------:|------|-----:|--------|---|-----:|---|-----:|
|belebele_kor_Hang | 0|none | 0|acc |↑ |0.2189|± |0.0138|
| | |none | 0|acc_norm|↑ |0.2189|± |0.0138|
|global_mmlu_full_ko | 0|none | |acc |↑ |0.2339|± |0.0036|
| - global_mmlu_full_ko_humanities | 0|none | |acc |↑ |0.2389|± |0.0062|
| - global_mmlu_full_ko_formal_logic | 0|none | 0|acc |↑ |0.2857|± |0.0404|
| - global_mmlu_full_ko_high_school_european_history | 0|none | 0|acc |↑ |0.2000|± |0.0312|
| - global_mmlu_full_ko_high_school_us_history | 0|none | 0|acc |↑ |0.2500|± |0.0304|
| - global_mmlu_full_ko_high_school_world_history | 0|none | 0|acc |↑ |0.2447|± |0.0280|
| - global_mmlu_full_ko_international_law | 0|none | 0|acc |↑ |0.1653|± |0.0339|
| - global_mmlu_full_ko_jurisprudence | 0|none | 0|acc |↑ |0.2130|± |0.0396|
| - global_mmlu_full_ko_logical_fallacies | 0|none | 0|acc |↑ |0.2147|± |0.0323|
| - global_mmlu_full_ko_moral_disputes | 0|none | 0|acc |↑ |0.2312|± |0.0227|
| - global_mmlu_full_ko_moral_scenarios | 0|none | 0|acc |↑ |0.2536|± |0.0146|
| - global_mmlu_full_ko_philosophy | 0|none | 0|acc |↑ |0.2219|± |0.0236|
| - global_mmlu_full_ko_prehistory | 0|none | 0|acc |↑ |0.2500|± |0.0241|
| - global_mmlu_full_ko_professional_law | 0|none | 0|acc |↑ |0.2373|± |0.0109|
| - global_mmlu_full_ko_world_religions | 0|none | 0|acc |↑ |0.2749|± |0.0342|
| - global_mmlu_full_ko_other | 0|none | |acc |↑ |0.2327|± |0.0076|
| - global_mmlu_full_ko_business_ethics | 0|none | 0|acc |↑ |0.3000|± |0.0461|
| - global_mmlu_full_ko_clinical_knowledge | 0|none | 0|acc |↑ |0.2340|± |0.0261|
| - global_mmlu_full_ko_college_medicine | 0|none | 0|acc |↑ |0.2543|± |0.0332|
| - global_mmlu_full_ko_global_facts | 0|none | 0|acc |↑ |0.2200|± |0.0416|
| - global_mmlu_full_ko_human_aging | 0|none | 0|acc |↑ |0.2511|± |0.0291|
| - global_mmlu_full_ko_management | 0|none | 0|acc |↑ |0.2718|± |0.0441|
| - global_mmlu_full_ko_marketing | 0|none | 0|acc |↑ |0.2991|± |0.0300|
| - global_mmlu_full_ko_medical_genetics | 0|none | 0|acc |↑ |0.2500|± |0.0435|
| - global_mmlu_full_ko_miscellaneous | 0|none | 0|acc |↑ |0.2031|± |0.0144|
| - global_mmlu_full_ko_nutrition | 0|none | 0|acc |↑ |0.2222|± |0.0238|
| - global_mmlu_full_ko_professional_accounting | 0|none | 0|acc |↑ |0.2057|± |0.0241|
| - global_mmlu_full_ko_professional_medicine | 0|none | 0|acc |↑ |0.2059|± |0.0246|
| - global_mmlu_full_ko_virology | 0|none | 0|acc |↑ |0.2711|± |0.0346|
| - global_mmlu_full_ko_social_sciences | 0|none | |acc |↑ |0.2301|± |0.0076|
| - global_mmlu_full_ko_econometrics | 0|none | 0|acc |↑ |0.2456|± |0.0405|
| - global_mmlu_full_ko_high_school_geography | 0|none | 0|acc |↑ |0.2828|± |0.0321|
| - global_mmlu_full_ko_high_school_government_and_politics| 0|none | 0|acc |↑ |0.1762|± |0.0275|
| - global_mmlu_full_ko_high_school_macroeconomics | 0|none | 0|acc |↑ |0.2128|± |0.0208|
| - global_mmlu_full_ko_high_school_microeconomics | 0|none | 0|acc |↑ |0.2269|± |0.0272|
| - global_mmlu_full_ko_high_school_psychology | 0|none | 0|acc |↑ |0.2440|± |0.0184|
| - global_mmlu_full_ko_human_sexuality | 0|none | 0|acc |↑ |0.1832|± |0.0339|
| - global_mmlu_full_ko_professional_psychology | 0|none | 0|acc |↑ |0.2337|± |0.0171|
| - global_mmlu_full_ko_public_relations | 0|none | 0|acc |↑ |0.2636|± |0.0422|
| - global_mmlu_full_ko_security_studies | 0|none | 0|acc |↑ |0.2000|± |0.0256|
| - global_mmlu_full_ko_sociology | 0|none | 0|acc |↑ |0.2289|± |0.0297|
| - global_mmlu_full_ko_us_foreign_policy | 0|none | 0|acc |↑ |0.2900|± |0.0456|
| - global_mmlu_full_ko_stem | 0|none | |acc |↑ |0.2312|± |0.0075|
| - global_mmlu_full_ko_abstract_algebra | 0|none | 0|acc |↑ |0.2100|± |0.0409|
| - global_mmlu_full_ko_anatomy | 0|none | 0|acc |↑ |0.2296|± |0.0363|
| - global_mmlu_full_ko_astronomy | 0|none | 0|acc |↑ |0.2237|± |0.0339|
| - global_mmlu_full_ko_college_biology | 0|none | 0|acc |↑ |0.2569|± |0.0365|
| - global_mmlu_full_ko_college_chemistry | 0|none | 0|acc |↑ |0.2100|± |0.0409|
| - global_mmlu_full_ko_college_computer_science | 0|none | 0|acc |↑ |0.2100|± |0.0409|
| - global_mmlu_full_ko_college_mathematics | 0|none | 0|acc |↑ |0.2700|± |0.0446|
| - global_mmlu_full_ko_college_physics | 0|none | 0|acc |↑ |0.2451|± |0.0428|
| - global_mmlu_full_ko_computer_security | 0|none | 0|acc |↑ |0.3100|± |0.0465|
| - global_mmlu_full_ko_conceptual_physics | 0|none | 0|acc |↑ |0.2511|± |0.0283|
| - global_mmlu_full_ko_electrical_engineering | 0|none | 0|acc |↑ |0.2138|± |0.0342|
| - global_mmlu_full_ko_elementary_mathematics | 0|none | 0|acc |↑ |0.2090|± |0.0209|
| - global_mmlu_full_ko_high_school_biology | 0|none | 0|acc |↑ |0.2258|± |0.0238|
| - global_mmlu_full_ko_high_school_chemistry | 0|none | 0|acc |↑ |0.1823|± |0.0272|
| - global_mmlu_full_ko_high_school_computer_science | 0|none | 0|acc |↑ |0.2300|± |0.0423|
| - global_mmlu_full_ko_high_school_mathematics | 0|none | 0|acc |↑ |0.2593|± |0.0267|
| - global_mmlu_full_ko_high_school_physics | 0|none | 0|acc |↑ |0.2384|± |0.0348|
| - global_mmlu_full_ko_high_school_statistics | 0|none | 0|acc |↑ |0.1898|± |0.0267|
| - global_mmlu_full_ko_machine_learning | 0|none | 0|acc |↑ |0.3125|± |0.0440|
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|--------------------------------------|------:|------|------|------|---|-----:|---|-----:|
|global_mmlu_full_ko | 0|none | |acc |↑ |0.2339|± |0.0036|
| - global_mmlu_full_ko_humanities | 0|none | |acc |↑ |0.2389|± |0.0062|
| - global_mmlu_full_ko_other | 0|none | |acc |↑ |0.2327|± |0.0076|
| - global_mmlu_full_ko_social_sciences| 0|none | |acc |↑ |0.2301|± |0.0076|
| - global_mmlu_full_ko_stem | 0|none | |acc |↑ |0.2312|± |0.0075|