394 lines
136 KiB
Plaintext
394 lines
136 KiB
Plaintext
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
|
||
[1mLlamaForCausalLM LOAD REPORT[0m 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 |
|
||
|
||
[3mNotes:
|
||
- MISSING[3m :those params were newly initialized because missing from the checkpoint. Consider training on your downstream task.[0m
|
||
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|
|
||
|