mmmu-val.log

+ CHECKPOINT=work_dirs/InternVL2-2B
+ DATASET=mmmu-val
++ pwd
+ CHECKPOINT=/mnt/petrelfs/wangweiyun/workspace_zyc/VLM-Dev/work_dirs/InternVL2-2B
++ pwd
+ export PYTHONPATH=/mnt/petrelfs/wangweiyun/workspace_zyc/VLM-Dev:/mnt/petrelfs/wangweiyun/workspace_wwy/pkgs/petrel-oss-sdk-2.3.14:/mnt/petrelfs/share_data/wangweiyun/share_pkgs/petrel-oss-sdk-2.3.12:
+ PYTHONPATH=/mnt/petrelfs/wangweiyun/workspace_zyc/VLM-Dev:/mnt/petrelfs/wangweiyun/workspace_wwy/pkgs/petrel-oss-sdk-2.3.14:/mnt/petrelfs/share_data/wangweiyun/share_pkgs/petrel-oss-sdk-2.3.12:
+ echo 'CHECKPOINT: /mnt/petrelfs/wangweiyun/workspace_zyc/VLM-Dev/work_dirs/InternVL2-2B'
CHECKPOINT: /mnt/petrelfs/wangweiyun/workspace_zyc/VLM-Dev/work_dirs/InternVL2-2B
+ MASTER_PORT=63669
+ PORT=63665
+ GPUS=8
+ GPUS_PER_NODE=8
+ NODES=1
+ export MASTER_PORT=63669
+ MASTER_PORT=63669
+ export PORT=63665
+ PORT=63665
+ ARGS=("$@")
+ [[ 5 -gt 0 ]]
+ case "$1" in
+ shift
+ [[ 4 -gt 0 ]]
+ case "$1" in
+ shift
+ [[ 3 -gt 0 ]]
+ case "$1" in
+ shift
+ [[ 2 -gt 0 ]]
+ case "$1" in
+ shift
+ [[ 1 -gt 0 ]]
+ case "$1" in
+ shift
+ [[ 0 -gt 0 ]]
GPUS: 8
+ echo 'GPUS: 8'
+ [[ /mnt/petrelfs/wangweiyun/workspace_zyc/VLM-Dev/work_dirs/InternVL2-2B == */ ]]
+ '[' mmmu-val == mme ']'
+ '[' mmmu-val == caption ']'
+ '[' mmmu-val == caption-coco ']'
+ '[' mmmu-val == caption-flickr30k ']'
+ '[' mmmu-val == caption-nocaps ']'
+ '[' mmmu-val == vqa ']'
+ '[' mmmu-val == vqa-okvqa-val ']'
+ '[' mmmu-val == vqa-textvqa-val ']'
+ '[' mmmu-val == vqa-textvqa-val-ocr ']'
+ '[' mmmu-val == vqa-vizwiz-val ']'
+ '[' mmmu-val == vqa-vizwiz-test ']'
+ '[' mmmu-val == vqa-vqav2-testdev ']'
+ '[' mmmu-val == vqa-ai2d-test ']'
+ '[' mmmu-val == vqa-vqav2-val ']'
+ '[' mmmu-val == vqa-gqa-testdev ']'
+ '[' mmmu-val == vqa-docvqa-val ']'
+ '[' mmmu-val == vqa-docvqa-test ']'
+ '[' mmmu-val == vqa-chartqa-test ']'
+ '[' mmmu-val == vqa-infovqa-val ']'
+ '[' mmmu-val == vqa-infovqa-test ']'
+ '[' mmmu-val == vqa-chartqa-test-human ']'
+ '[' mmmu-val == vqa-chartqa-test-augmented ']'
+ '[' mmmu-val == vqa-ocrvqa-val ']'
+ '[' mmmu-val == vqa-ocrvqa-test ']'
+ '[' mmmu-val == refcoco ']'
+ '[' mmmu-val == refcoco-val ']'
+ '[' mmmu-val == llava-bench ']'
+ '[' mmmu-val == pope ']'
+ '[' mmmu-val == tiny_lvlm ']'
+ '[' mmmu-val == mmvet ']'
+ '[' mmmu-val == cmmmu ']'
+ '[' mmmu-val == mmbench-dev-en ']'
+ '[' mmmu-val == mmbench-dev-cn ']'
+ '[' mmmu-val == mmbench-test-en ']'
+ '[' mmmu-val == mmbench-test-cn ']'
+ '[' mmmu-val == ccbench-dev ']'
+ '[' mmmu-val == scienceqa ']'
+ '[' mmmu-val == mmmu-dev ']'
+ '[' mmmu-val == mmmu-val ']'
+ torchrun --nnodes=1 --node_rank=0 --master_addr=127.0.0.1 --nproc_per_node=8 --master_port=63669 eval/mmmu/evaluate_mmmu.py --checkpoint /mnt/petrelfs/wangweiyun/workspace_zyc/VLM-Dev/work_dirs/InternVL2-2B --datasets MMMU_validation --dynamic --max-num 6
[2024-08-07 21:56:26,513] torch.distributed.run: [WARNING] 
[2024-08-07 21:56:26,513] torch.distributed.run: [WARNING] *****************************************
[2024-08-07 21:56:26,513] torch.distributed.run: [WARNING] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. 
[2024-08-07 21:56:26,513] torch.distributed.run: [WARNING] *****************************************
datasets: ['MMMU_validation']
datasets: ['MMMU_validation']
datasets: ['MMMU_validation']
datasets: ['MMMU_validation']
datasets: ['MMMU_validation']
datasets: ['MMMU_validation']
datasets: ['MMMU_validation']
datasets: ['MMMU_validation']
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
[test] total_params: 2.205754368B, use num_beams: 1
[test] image_size: 448
[test] template: internlm2-chat
[test] dynamic_image_size: True
[test] use_thumbnail: True
[test] max_num: 6
[test] total_params: 2.205754368B, use num_beams: 1
[test] image_size: 448
[test] template: internlm2-chat
[test] dynamic_image_size: True
[test] use_thumbnail: True
[test] max_num: 6
[test] total_params: 2.205754368B, use num_beams: 1
[test] image_size: 448
[test] template: internlm2-chat
[test] dynamic_image_size: True[test] total_params: 2.205754368B, use num_beams: 1
[test] use_thumbnail: True

[test] max_num: 6[test] image_size: 448

[test] template: internlm2-chat
[test] dynamic_image_size: True
[test] use_thumbnail: True
[test] max_num: 6
[test] total_params: 2.205754368B, use num_beams: 1
[test] image_size: 448
[test] template: internlm2-chat
[test] dynamic_image_size: True
[test] use_thumbnail: True
[test] max_num: 6
[test] total_params: 2.205754368B, use num_beams: 1
[test] image_size: 448
[test] total_params: 2.205754368B, use num_beams: 1
[test] image_size: 448
[test] template: internlm2-chat
[test] template: internlm2-chat
[test] dynamic_image_size: True
[test] use_thumbnail: True
[test] max_num: 6
[test] dynamic_image_size: True
[test] use_thumbnail: True
[test] max_num: 6
[test] total_params: 2.205754368B, use num_beams: 1
[test] image_size: 448
[test] template: internlm2-chat
[test] dynamic_image_size: True
[test] use_thumbnail: True
[test] max_num: 6

  0%|          | 0/30 [00:00<?, ?it/s]
  0%|          | 0/30 [00:00<?, ?it/s]
  0%|          | 0/30 [00:00<?, ?it/s]
  0%|          | 0/30 [00:00<?, ?it/s]
  0%|          | 0/30 [00:00<?, ?it/s]
  0%|          | 0/30 [00:00<?, ?it/s]
  0%|          | 0/30 [00:00<?, ?it/s]
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:21<10:22, 21.48s/it]
  3%|▎         | 1/30 [00:21<10:22, 21.47s/it]
  3%|▎         | 1/30 [00:21<10:25, 21.56s/it]
  3%|▎         | 1/30 [00:21<10:27, 21.62s/it]
  3%|▎         | 1/30 [00:21<10:33, 21.84s/it]
  3%|▎         | 1/30 [00:22<10:55, 22.62s/it]
  3%|▎         | 1/30 [00:22<10:55, 22.60s/it]
  3%|▎         | 1/30 [00:25<12:14, 25.34s/it]
  7%|▋         | 2/30 [00:36<08:19, 17.82s/it]
  7%|▋         | 2/30 [00:37<08:33, 18.35s/it]
  7%|▋         | 2/30 [00:39<09:02, 19.39s/it]
  7%|▋         | 2/30 [00:40<09:14, 19.79s/it]
  7%|▋         | 2/30 [00:40<09:19, 19.98s/it]
  7%|▋         | 2/30 [00:40<09:15, 19.84s/it]
  7%|▋         | 2/30 [00:41<09:16, 19.87s/it]
  7%|▋         | 2/30 [00:41<09:40, 20.74s/it]
 10%|█         | 3/30 [00:51<07:28, 16.59s/it]
 10%|█         | 3/30 [00:54<07:56, 17.64s/it]
 10%|█         | 3/30 [00:56<08:07, 18.07s/it]
 10%|█         | 3/30 [00:57<08:28, 18.82s/it]
 10%|█         | 3/30 [00:57<08:12, 18.23s/it]
 10%|█         | 3/30 [00:57<08:26, 18.75s/it]
 10%|█         | 3/30 [00:59<08:43, 19.37s/it]
 10%|█         | 3/30 [01:00<08:55, 19.82s/it]
 13%|█▎        | 4/30 [01:09<07:25, 17.12s/it]
 13%|█▎        | 4/30 [01:10<07:25, 17.14s/it]
 13%|█▎        | 4/30 [01:11<07:09, 16.51s/it]
 13%|█▎        | 4/30 [01:12<07:29, 17.29s/it]
 13%|█▎        | 4/30 [01:12<07:32, 17.40s/it]
 13%|█▎        | 4/30 [01:16<08:04, 18.63s/it]
 13%|█▎        | 4/30 [01:18<08:29, 19.60s/it]
 13%|█▎        | 4/30 [01:19<08:30, 19.62s/it]
 17%|█▋        | 5/30 [01:27<07:05, 17.04s/it]
 17%|█▋        | 5/30 [01:28<06:58, 16.73s/it]
 17%|█▋        | 5/30 [01:29<07:31, 18.05s/it]
 17%|█▋        | 5/30 [01:30<07:20, 17.61s/it]
 17%|█▋        | 5/30 [01:33<07:28, 17.96s/it]
 17%|█▋        | 5/30 [01:35<08:04, 19.38s/it]
 17%|█▋        | 5/30 [01:37<08:05, 19.40s/it]
 17%|█▋        | 5/30 [01:38<08:04, 19.39s/it]
 20%|██        | 6/30 [01:45<06:43, 16.81s/it]
 20%|██        | 6/30 [01:46<07:03, 17.64s/it]
 20%|██        | 6/30 [01:48<07:21, 18.38s/it]
 20%|██        | 6/30 [01:49<07:13, 18.07s/it]
 20%|██        | 6/30 [01:51<07:08, 17.87s/it]
 20%|██        | 6/30 [01:51<07:16, 18.21s/it]
 20%|██        | 6/30 [01:56<07:41, 19.22s/it]
 20%|██        | 6/30 [01:56<07:35, 18.99s/it]
 23%|██▎       | 7/30 [02:01<06:26, 16.79s/it]
 23%|██▎       | 7/30 [02:03<06:38, 17.32s/it]
 23%|██▎       | 7/30 [02:05<06:51, 17.89s/it]
 23%|██▎       | 7/30 [02:08<07:02, 18.36s/it]
 23%|██▎       | 7/30 [02:10<07:02, 18.36s/it]
 23%|██▎       | 7/30 [02:11<07:12, 18.79s/it]
 23%|██▎       | 7/30 [02:13<07:01, 18.31s/it]
 23%|██▎       | 7/30 [02:14<07:12, 18.83s/it]
 27%|██▋       | 8/30 [02:19<06:21, 17.36s/it]
 27%|██▋       | 8/30 [02:22<06:30, 17.76s/it]
 27%|██▋       | 8/30 [02:23<06:32, 17.83s/it]
 27%|██▋       | 8/30 [02:26<06:42, 18.30s/it]
 27%|██▋       | 8/30 [02:28<06:41, 18.26s/it]
 27%|██▋       | 8/30 [02:29<06:25, 17.50s/it]
 27%|██▋       | 8/30 [02:29<06:49, 18.61s/it]
 27%|██▋       | 8/30 [02:30<06:34, 17.92s/it]
 30%|███       | 9/30 [02:35<05:52, 16.80s/it]
 30%|███       | 9/30 [02:37<05:56, 17.00s/it]
 30%|███       | 9/30 [02:38<05:56, 16.96s/it]
 30%|███       | 9/30 [02:39<05:46, 16.50s/it]
 30%|███       | 9/30 [02:42<05:53, 16.85s/it]
 30%|███       | 9/30 [02:43<06:00, 17.18s/it]
 30%|███       | 9/30 [02:46<06:05, 17.42s/it]
 30%|███       | 9/30 [02:48<06:15, 17.87s/it]
 33%|███▎      | 10/30 [02:49<05:19, 15.98s/it]
 33%|███▎      | 10/30 [02:52<05:26, 16.31s/it]
 33%|███▎      | 10/30 [02:58<06:00, 18.01s/it]
 33%|███▎      | 10/30 [02:59<05:51, 17.58s/it]
 33%|███▎      | 10/30 [02:59<05:38, 16.94s/it]
 33%|███▎      | 10/30 [03:00<05:42, 17.11s/it]
 33%|███▎      | 10/30 [03:03<05:45, 17.28s/it]
 33%|███▎      | 10/30 [03:05<05:53, 17.68s/it]
 37%|███▋      | 11/30 [03:06<05:09, 16.31s/it]
 37%|███▋      | 11/30 [03:07<05:03, 15.99s/it]
 37%|███▋      | 11/30 [03:12<05:15, 16.62s/it]
 37%|███▋      | 11/30 [03:12<05:00, 15.83s/it]
 37%|███▋      | 11/30 [03:13<04:58, 15.74s/it]
 37%|███▋      | 11/30 [03:13<05:15, 16.62s/it]
 37%|███▋      | 11/30 [03:16<05:03, 15.96s/it]
 37%|███▋      | 11/30 [03:17<05:03, 15.96s/it]
 40%|████      | 12/30 [03:22<04:40, 15.59s/it]
 40%|████      | 12/30 [03:24<05:02, 16.80s/it]
 40%|████      | 12/30 [03:28<04:56, 16.48s/it]
 40%|████      | 12/30 [03:28<04:50, 16.12s/it]
 40%|████      | 12/30 [03:29<04:46, 15.93s/it]
 40%|████      | 12/30 [03:32<05:05, 17.00s/it]
 40%|████      | 12/30 [03:33<04:46, 15.92s/it]
 40%|████      | 12/30 [03:38<05:19, 17.75s/it]
 43%|████▎     | 13/30 [03:38<04:28, 15.81s/it]
 43%|████▎     | 13/30 [03:39<04:37, 16.32s/it]
 43%|████▎     | 13/30 [03:42<04:22, 15.45s/it]
 43%|████▎     | 13/30 [03:44<04:37, 16.31s/it]
 43%|████▎     | 13/30 [03:46<04:34, 16.12s/it]
 43%|████▎     | 13/30 [03:47<04:37, 16.33s/it]
 43%|████▎     | 13/30 [03:51<04:43, 16.66s/it]
 47%|████▋     | 14/30 [03:53<04:08, 15.50s/it]
 43%|████▎     | 13/30 [03:55<04:59, 17.61s/it]
 47%|████▋     | 14/30 [03:56<04:22, 16.40s/it]
 47%|████▋     | 14/30 [03:57<04:04, 15.30s/it]
 47%|████▋     | 14/30 [03:58<04:09, 15.58s/it]
 47%|████▋     | 14/30 [04:03<04:19, 16.25s/it]
 47%|████▋     | 14/30 [04:03<04:23, 16.46s/it]
 50%|█████     | 15/30 [04:06<03:42, 14.82s/it]
 47%|████▋     | 14/30 [04:08<04:27, 16.72s/it]
 50%|█████     | 15/30 [04:12<04:03, 16.26s/it]
 47%|████▋     | 14/30 [04:13<04:42, 17.64s/it]
 50%|█████     | 15/30 [04:16<04:06, 16.43s/it]
 50%|█████     | 15/30 [04:18<04:14, 16.96s/it]
 50%|█████     | 15/30 [04:20<04:09, 16.66s/it]
 53%|█████▎    | 16/30 [04:22<03:30, 15.06s/it]
 50%|█████     | 15/30 [04:23<04:22, 17.48s/it]
 50%|█████     | 15/30 [04:27<04:20, 17.37s/it]
 50%|█████     | 15/30 [04:31<04:25, 17.72s/it]
 53%|█████▎    | 16/30 [04:31<04:01, 17.27s/it]
 53%|█████▎    | 16/30 [04:34<03:53, 16.65s/it]
 53%|█████▎    | 16/30 [04:39<04:02, 17.29s/it]
 53%|█████▎    | 16/30 [04:39<03:58, 17.03s/it]
 53%|█████▎    | 16/30 [04:39<04:18, 18.44s/it]
 57%|█████▋    | 17/30 [04:42<03:34, 16.53s/it]
 53%|█████▎    | 16/30 [04:43<03:56, 16.90s/it]
 53%|█████▎    | 16/30 [04:44<03:49, 16.36s/it]
 57%|█████▋    | 17/30 [04:47<03:38, 16.81s/it]
 57%|█████▋    | 17/30 [04:48<03:27, 15.98s/it]
 57%|█████▋    | 17/30 [04:52<03:38, 16.79s/it]
 57%|█████▋    | 17/30 [04:53<03:32, 16.34s/it]
 57%|█████▋    | 17/30 [04:53<03:29, 16.10s/it]
 60%|██████    | 18/30 [04:57<03:12, 16.06s/it]
 57%|█████▋    | 17/30 [04:58<03:34, 16.47s/it]
 60%|██████    | 18/30 [05:00<03:08, 15.70s/it]
 60%|██████    | 18/30 [05:02<03:04, 15.37s/it]
 57%|█████▋    | 17/30 [05:06<03:54, 18.01s/it]
 60%|██████    | 18/30 [05:06<03:11, 15.92s/it]
 60%|██████    | 18/30 [05:08<03:11, 15.94s/it]
 60%|██████    | 18/30 [05:12<03:23, 16.97s/it]
 63%|██████▎   | 19/30 [05:15<03:03, 16.71s/it]
 63%|██████▎   | 19/30 [05:18<02:59, 16.33s/it]
 60%|██████    | 18/30 [05:20<03:36, 18.07s/it]
 63%|██████▎   | 19/30 [05:24<02:55, 15.99s/it]
 63%|██████▎   | 19/30 [05:25<03:04, 16.80s/it]
 63%|██████▎   | 19/30 [05:25<03:13, 17.60s/it]
 60%|██████    | 18/30 [05:28<03:50, 19.22s/it]
 63%|██████▎   | 19/30 [05:29<03:07, 17.02s/it]
 67%|██████▋   | 20/30 [05:30<02:41, 16.20s/it]
 67%|██████▋   | 20/30 [05:37<02:51, 17.16s/it]
 63%|██████▎   | 19/30 [05:38<03:18, 18.07s/it]
 67%|██████▋   | 20/30 [05:41<02:43, 16.33s/it]
 67%|██████▋   | 20/30 [05:42<02:55, 17.54s/it]
 67%|██████▋   | 20/30 [05:43<02:52, 17.21s/it]
 63%|██████▎   | 19/30 [05:43<03:18, 18.05s/it]
 67%|██████▋   | 20/30 [05:45<02:46, 16.68s/it]
 70%|███████   | 21/30 [05:46<02:24, 16.10s/it]
 70%|███████   | 21/30 [05:50<02:23, 15.89s/it]
 67%|██████▋   | 20/30 [05:57<03:03, 18.34s/it]
 70%|███████   | 21/30 [05:58<02:33, 17.07s/it]
 70%|███████   | 21/30 [05:59<02:30, 16.68s/it]
 67%|██████▋   | 20/30 [06:00<02:56, 17.69s/it]
 70%|███████   | 21/30 [06:00<02:34, 17.15s/it]
 70%|███████   | 21/30 [06:04<02:35, 17.27s/it]
 73%|███████▎  | 22/30 [06:08<02:23, 17.98s/it]
 73%|███████▎  | 22/30 [06:12<02:22, 17.76s/it]
 73%|███████▎  | 22/30 [06:15<02:15, 16.89s/it]
 70%|███████   | 21/30 [06:16<02:45, 18.35s/it]
 73%|███████▎  | 22/30 [06:16<02:14, 16.81s/it]
 73%|███████▎  | 22/30 [06:19<02:12, 16.59s/it]
 70%|███████   | 21/30 [06:20<02:45, 18.44s/it]
 73%|███████▎  | 22/30 [06:23<02:30, 18.85s/it]
 77%|███████▋  | 23/30 [06:26<02:05, 17.93s/it]
 77%|███████▋  | 23/30 [06:32<02:08, 18.34s/it]
 77%|███████▋  | 23/30 [06:32<01:59, 17.00s/it]
 73%|███████▎  | 22/30 [06:36<02:32, 19.07s/it]
 77%|███████▋  | 23/30 [06:36<02:05, 17.88s/it]
 77%|███████▋  | 23/30 [06:37<01:59, 17.09s/it]
 73%|███████▎  | 22/30 [06:38<02:26, 18.28s/it]
 77%|███████▋  | 23/30 [06:43<02:15, 19.31s/it]
 80%|████████  | 24/30 [06:45<01:49, 18.17s/it]
 80%|████████  | 24/30 [06:48<01:46, 17.68s/it]
 77%|███████▋  | 23/30 [06:48<01:58, 16.95s/it]
 80%|████████  | 24/30 [06:48<01:36, 16.12s/it]
 80%|████████  | 24/30 [06:49<01:41, 16.98s/it]
 77%|███████▋  | 23/30 [06:52<01:58, 16.88s/it]
 80%|████████  | 24/30 [06:52<01:39, 16.52s/it]
 80%|████████  | 24/30 [06:56<01:44, 17.36s/it]
 83%|████████▎ | 25/30 [07:00<01:25, 17.10s/it]
 83%|████████▎ | 25/30 [07:02<01:22, 16.54s/it]
 80%|████████  | 24/30 [07:03<01:38, 16.36s/it]
 83%|████████▎ | 25/30 [07:07<01:26, 17.23s/it]
 83%|████████▎ | 25/30 [07:08<01:25, 17.15s/it]
 80%|████████  | 24/30 [07:09<01:41, 16.94s/it]
 83%|████████▎ | 25/30 [07:10<01:24, 16.92s/it]
 83%|████████▎ | 25/30 [07:20<01:36, 19.27s/it]
 87%|████████▋ | 26/30 [07:20<01:12, 18.12s/it]
 87%|████████▋ | 26/30 [07:25<01:14, 18.54s/it]
 87%|████████▋ | 26/30 [07:33<01:18, 19.56s/it]
 83%|████████▎ | 25/30 [07:34<01:43, 20.71s/it]
 87%|████████▋ | 26/30 [07:34<01:21, 20.28s/it]
 87%|████████▋ | 26/30 [07:44<01:28, 22.05s/it]
 83%|████████▎ | 25/30 [07:46<01:55, 23.01s/it]
 90%|█████████ | 27/30 [07:51<01:02, 20.81s/it]
 87%|████████▋ | 26/30 [08:01<01:30, 22.54s/it]
 87%|████████▋ | 26/30 [08:02<01:44, 26.10s/it]
 90%|█████████ | 27/30 [08:02<01:07, 22.43s/it]
 90%|█████████ | 27/30 [08:04<01:09, 23.12s/it]
 87%|████████▋ | 26/30 [08:10<01:32, 23.24s/it]
 90%|█████████ | 27/30 [08:11<01:24, 28.08s/it]
 90%|█████████ | 27/30 [08:17<01:15, 25.25s/it]
 93%|█████████▎| 28/30 [08:23<00:48, 24.12s/it]
 90%|█████████ | 27/30 [08:23<01:07, 22.46s/it]
 93%|█████████▎| 28/30 [08:23<00:44, 22.03s/it]
 90%|█████████ | 27/30 [08:24<01:14, 24.89s/it]
 93%|█████████▎| 28/30 [08:40<00:49, 24.60s/it]
 93%|█████████▎| 28/30 [08:40<00:56, 28.31s/it]
 93%|█████████▎| 28/30 [08:40<00:54, 27.04s/it]
 90%|█████████ | 27/30 [08:40<01:16, 25.38s/it]
 93%|█████████▎| 28/30 [08:44<00:46, 23.47s/it]
 97%|█████████▋| 29/30 [08:47<00:24, 24.15s/it]
 93%|█████████▎| 28/30 [08:50<00:47, 23.73s/it]
 97%|█████████▋| 29/30 [09:03<00:27, 27.39s/it]
 97%|█████████▋| 29/30 [09:04<00:24, 24.49s/it]
 97%|█████████▋| 29/30 [09:05<00:26, 26.41s/it]
 93%|█████████▎| 28/30 [09:06<00:51, 25.57s/it]
 97%|█████████▋| 29/30 [09:08<00:28, 28.13s/it]
 97%|█████████▋| 29/30 [09:17<00:26, 26.37s/it]
 97%|█████████▋| 29/30 [09:20<00:25, 25.61s/it]
100%|██████████| 30/30 [09:20<00:00, 26.81s/it]
100%|██████████| 30/30 [09:20<00:00, 18.70s/it]

0it [00:00, ?it/s]/mnt/petrelfs/wangweiyun/miniconda3/envs/internvl/lib/python3.10/site-packages/transformers/generation/configuration_utils.py:392: UserWarning: `do_sample` is set to `False`. However, `temperature` is set to `0.0` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `temperature`.
  warnings.warn(

1it [00:00,  1.51it/s]
2it [00:00,  2.38it/s]
4it [00:01,  4.78it/s]
6it [00:01,  6.64it/s]
7it [00:01,  6.84it/s]
8it [00:01,  6.75it/s]
10it [00:01,  8.42it/s]
11it [00:01,  8.61it/s]
12it [00:01,  8.43it/s]
14it [00:02,  9.72it/s]
15it [00:02,  9.75it/s]
16it [00:02,  9.54it/s]
18it [00:02,  9.50it/s]
19it [00:02,  9.08it/s]
21it [00:02,  9.21it/s]
23it [00:03,  8.62it/s]
24it [00:03,  8.83it/s]
26it [00:03,  9.46it/s]
28it [00:03,  9.25it/s]
29it [00:03,  8.96it/s]
30it [00:03,  8.72it/s]
32it [00:04,  9.19it/s]
33it [00:04,  8.63it/s]
34it [00:04,  8.04it/s]
35it [00:04,  8.02it/s]
36it [00:04,  7.73it/s]
37it [00:04,  8.24it/s]
38it [00:04,  7.98it/s]
39it [00:05,  7.05it/s]
41it [00:05,  8.16it/s]
43it [00:05,  7.37it/s]
44it [00:05,  6.48it/s]
45it [00:05,  6.60it/s]
46it [00:06,  6.88it/s]
48it [00:06,  8.45it/s]
49it [00:06,  8.26it/s]
50it [00:06,  8.16it/s]
52it [00:06,  7.88it/s]
100%|██████████| 30/30 [09:27<00:00, 24.03s/it]
100%|██████████| 30/30 [09:27<00:00, 18.92s/it]

0it [00:00, ?it/s]
53it [00:06,  7.88it/s]
54it [00:06,  8.01it/s]
55it [00:07,  7.97it/s]/mnt/petrelfs/wangweiyun/miniconda3/envs/internvl/lib/python3.10/site-packages/transformers/generation/configuration_utils.py:392: UserWarning: `do_sample` is set to `False`. However, `temperature` is set to `0.0` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `temperature`.
  warnings.warn(

56it [00:07,  7.97it/s]
57it [00:07,  7.94it/s]
1it [00:00,  1.58it/s]
58it [00:07,  7.91it/s]
59it [00:07,  8.41it/s]
61it [00:07,  9.17it/s]
2it [00:00,  2.18it/s]
62it [00:07,  9.08it/s]
4it [00:01,  4.43it/s]
63it [00:08,  9.12it/s]
64it [00:08,  9.04it/s]
6it [00:01,  5.75it/s]
7it [00:01,  6.41it/s]
66it [00:08,  9.57it/s]
8it [00:01,  6.88it/s]
68it [00:08, 10.12it/s]
69it [00:08,  9.77it/s]
10it [00:01,  7.87it/s]
12it [00:01,  8.89it/s]
71it [00:08,  9.83it/s]
72it [00:08,  9.70it/s]
14it [00:02,  8.98it/s]
73it [00:09,  9.71it/s]
15it [00:02,  9.02it/s]
75it [00:09, 10.64it/s]
17it [00:02, 10.04it/s]
77it [00:09,  9.75it/s]
19it [00:02,  8.88it/s]
79it [00:09, 10.33it/s]
21it [00:02,  8.90it/s]
81it [00:09, 10.18it/s]
22it [00:03,  8.75it/s]
23it [00:03,  8.39it/s]
83it [00:10,  9.29it/s]
85it [00:10,  9.90it/s]
25it [00:03,  8.84it/s]
27it [00:03,  9.61it/s]
87it [00:10,  9.17it/s]
29it [00:03, 10.42it/s]
88it [00:10,  8.72it/s]
31it [00:03, 11.27it/s]
90it [00:10,  9.47it/s]
33it [00:04,  9.85it/s]
91it [00:11,  7.54it/s]
35it [00:04,  9.68it/s]
92it [00:11,  6.86it/s]
93it [00:11,  7.17it/s]
94it [00:11,  7.71it/s]
37it [00:04,  9.21it/s]
95it [00:11,  7.54it/s]
39it [00:04,  9.07it/s]
96it [00:11,  6.67it/s]
41it [00:05,  9.14it/s]
97it [00:12,  5.81it/s]
42it [00:05,  8.63it/s]
98it [00:12,  6.29it/s]
43it [00:05,  8.46it/s]
99it [00:12,  6.50it/s]
44it [00:05,  7.02it/s]
45it [00:05,  7.22it/s]
100it [00:12,  5.49it/s]
46it [00:05,  7.38it/s]
102it [00:12,  6.67it/s]
47it [00:05,  7.50it/s]
49it [00:06,  9.01it/s]
103it [00:13,  5.42it/s]
51it [00:06,  9.61it/s]
104it [00:13,  5.90it/s]
52it [00:06,  9.19it/s]
105it [00:13,  6.34it/s]
53it [00:06,  8.82it/s]
106it [00:13,  6.69it/s]
54it [00:06,  8.55it/s]
56it [00:06,  8.86it/s]
108it [00:13,  6.22it/s]
58it [00:07,  9.96it/s]
59it [00:07,  9.43it/s]
110it [00:14,  6.47it/s]
61it [00:07,  9.03it/s]
111it [00:14,  5.92it/s]
112it [00:14,  7.77it/s]

62it [00:07,  7.91it/s]
63it [00:07,  6.50it/s]
64it [00:08,  5.65it/s]
65it [00:08,  6.12it/s]
66it [00:08,  6.51it/s]
67it [00:08,  6.85it/s]
68it [00:08,  6.98it/s]
70it [00:09,  5.94it/s]
71it [00:09,  6.30it/s]
72it [00:09,  6.63it/s]
100%|██████████| 30/30 [09:37<00:00, 29.17s/it]
100%|██████████| 30/30 [09:37<00:00, 19.23s/it]

0it [00:00, ?it/s]
73it [00:09,  6.72it/s]
74it [00:09,  6.95it/s]
75it [00:09,  7.18it/s]/mnt/petrelfs/wangweiyun/miniconda3/envs/internvl/lib/python3.10/site-packages/transformers/generation/configuration_utils.py:392: UserWarning: `do_sample` is set to `False`. However, `temperature` is set to `0.0` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `temperature`.
  warnings.warn(

76it [00:09,  7.18it/s]
1it [00:00,  1.61it/s]
77it [00:09,  7.29it/s]
78it [00:10,  7.45it/s]
79it [00:10,  8.06it/s]
2it [00:00,  2.31it/s]
80it [00:10,  8.52it/s]
81it [00:10,  8.91it/s]
4it [00:01,  4.39it/s]
82it [00:10,  9.20it/s]
5it [00:01,  5.02it/s]
83it [00:10,  8.77it/s]
6it [00:01,  5.91it/s]
7it [00:01,  6.73it/s]
85it [00:10,  9.18it/s]
8it [00:01,  7.47it/s]
86it [00:10,  9.36it/s]
87it [00:11,  8.91it/s]
10it [00:01,  9.36it/s]
88it [00:11,  8.54it/s]
12it [00:01,  9.51it/s]
89it [00:11,  8.34it/s]
90it [00:11,  8.22it/s]
14it [00:02,  9.26it/s]
15it [00:02,  8.93it/s]
92it [00:11,  8.49it/s]
100%|██████████| 30/30 [09:39<00:00, 29.01s/it]
100%|██████████| 30/30 [09:39<00:00, 19.32s/it]

17it [00:02, 10.14it/s]
0it [00:00, ?it/s]
93it [00:11,  7.64it/s]
94it [00:11,  8.12it/s]
19it [00:02, 10.28it/s]
96it [00:12, 10.19it/s]
21it [00:02, 10.10it/s]
98it [00:12, 11.76it/s]/mnt/petrelfs/wangweiyun/miniconda3/envs/internvl/lib/python3.10/site-packages/transformers/generation/configuration_utils.py:392: UserWarning: `do_sample` is set to `False`. However, `temperature` is set to `0.0` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `temperature`.
  warnings.warn(

23it [00:03, 10.45it/s]
100it [00:12, 10.51it/s]
1it [00:00,  1.37it/s]
25it [00:03, 10.26it/s]
102it [00:12,  9.47it/s]
27it [00:03, 10.56it/s]
2it [00:01,  2.00it/s]
29it [00:03, 10.76it/s]
104it [00:12,  8.89it/s]
100%|██████████| 30/30 [09:40<00:00, 29.02s/it]
100%|██████████| 30/30 [09:40<00:00, 19.36s/it]

3it [00:01,  2.86it/s]
105it [00:13,  9.04it/s]
0it [00:00, ?it/s]
106it [00:13,  8.76it/s]
5it [00:01,  5.00it/s]
107it [00:13,  8.54it/s]
7it [00:01,  6.90it/s]
108it [00:13,  8.36it/s]
8it [00:01,  5.86it/s]
110it [00:13,  8.99it/s]
31it [00:04,  5.72it/s]
111it [00:13,  8.71it/s]
9it [00:01,  6.19it/s]
10it [00:02,  6.56it/s]
112it [00:13,  8.09it/s]
/mnt/petrelfs/wangweiyun/miniconda3/envs/internvl/lib/python3.10/site-packages/transformers/generation/configuration_utils.py:392: UserWarning: `do_sample` is set to `False`. However, `temperature` is set to `0.0` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `temperature`.
  warnings.warn(

32it [00:04,  5.13it/s]
11it [00:02,  7.25it/s]
12it [00:02,  7.85it/s]
1it [00:01,  1.10s/it]
14it [00:02,  8.81it/s]
33it [00:05,  4.02it/s]
15it [00:02,  8.56it/s]
2it [00:01,  1.52it/s]
17it [00:02,  9.60it/s]
3it [00:01,  2.39it/s]
19it [00:02, 10.77it/s]
4it [00:01,  3.29it/s]
21it [00:03, 11.31it/s]
23it [00:03, 11.61it/s]
34it [00:05,  2.87it/s]
5it [00:02,  2.98it/s]
35it [00:05,  3.39it/s]
25it [00:03, 11.81it/s]
36it [00:05,  3.98it/s]
6it [00:02,  3.59it/s]
27it [00:03, 12.10it/s]
37it [00:06,  4.58it/s]
29it [00:03, 13.04it/s]
7it [00:02,  3.23it/s]
31it [00:03, 10.82it/s]
 97%|█████████▋| 29/30 [09:43<00:28, 28.89s/it]
9it [00:02,  4.88it/s]
33it [00:04, 10.51it/s]
38it [00:06,  3.04it/s]
35it [00:04, 10.51it/s]
37it [00:04,  9.51it/s]
10it [00:03,  3.49it/s]
39it [00:04, 10.16it/s]
39it [00:07,  2.36it/s]
41it [00:04,  9.90it/s]
40it [00:07,  2.96it/s]
11it [00:03,  2.89it/s]
43it [00:05,  9.65it/s]
13it [00:04,  4.17it/s]
45it [00:05,  8.94it/s]
46it [00:05,  8.74it/s]
41it [00:08,  2.49it/s]
48it [00:05,  8.98it/s]
15it [00:04,  4.03it/s]
49it [00:05,  8.76it/s]
51it [00:06,  9.17it/s]
100%|██████████| 30/30 [09:45<00:00, 26.83s/it]
100%|██████████| 30/30 [09:45<00:00, 19.52s/it]

0it [00:00, ?it/s]
52it [00:06,  8.89it/s]
53it [00:06,  8.64it/s]
43it [00:08,  2.53it/s]
16it [00:05,  3.21it/s]
17it [00:05,  3.81it/s]
55it [00:06,  9.63it/s]/mnt/petrelfs/wangweiyun/miniconda3/envs/internvl/lib/python3.10/site-packages/transformers/generation/configuration_utils.py:392: UserWarning: `do_sample` is set to `False`. However, `temperature` is set to `0.0` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `temperature`.
  warnings.warn(

18it [00:05,  4.34it/s]
19it [00:05,  5.09it/s]
20it [00:05,  5.64it/s]
1it [00:00,  1.56it/s]
56it [00:06,  6.45it/s]
44it [00:09,  2.18it/s]
57it [00:07,  5.43it/s]
2it [00:00,  2.22it/s]
58it [00:07,  6.14it/s]
21it [00:06,  3.92it/s]
3it [00:01,  3.24it/s]
60it [00:07,  7.20it/s]
4it [00:01,  4.17it/s]
23it [00:06,  5.18it/s]
61it [00:07,  7.35it/s]
5it [00:01,  4.98it/s]
45it [00:10,  2.01it/s]
6it [00:01,  5.69it/s]
25it [00:06,  6.23it/s]
63it [00:07,  8.21it/s]
64it [00:07,  8.14it/s]
7it [00:01,  5.46it/s]
46it [00:10,  2.28it/s]
27it [00:06,  7.32it/s]
8it [00:01,  6.05it/s]
28it [00:06,  7.72it/s]
29it [00:06,  8.13it/s]
9it [00:01,  6.59it/s]
10it [00:02,  6.55it/s]
31it [00:07,  9.09it/s]
47it [00:10,  2.28it/s]
11it [00:02,  7.32it/s]
32it [00:07,  8.69it/s]
12it [00:02,  7.49it/s]
65it [00:08,  4.07it/s]
33it [00:07,  8.48it/s]
13it [00:02,  7.61it/s]
67it [00:08,  5.28it/s]
35it [00:07,  8.98it/s]
48it [00:11,  2.26it/s]
14it [00:02,  7.08it/s]
68it [00:08,  5.73it/s]
36it [00:07,  9.16it/s]
15it [00:02,  7.30it/s]
70it [00:09,  7.30it/s]
38it [00:07, 10.14it/s]
49it [00:11,  2.52it/s]
17it [00:02,  8.67it/s]
71it [00:09,  7.43it/s]
40it [00:07, 10.86it/s]
18it [00:03,  7.88it/s]
42it [00:08, 10.28it/s]
20it [00:03,  8.75it/s]
73it [00:09,  6.17it/s]
44it [00:08, 10.59it/s]
21it [00:03,  8.49it/s]
74it [00:09,  6.48it/s]
22it [00:03,  8.29it/s]
50it [00:12,  2.10it/s]
46it [00:08, 10.08it/s]
75it [00:09,  6.75it/s]
23it [00:03,  8.18it/s]
51it [00:12,  2.68it/s]
24it [00:03,  8.08it/s]
48it [00:08, 10.11it/s]
77it [00:10,  6.84it/s]
78it [00:10,  7.18it/s]
50it [00:08,  9.99it/s]
26it [00:04,  8.39it/s]
79it [00:10,  7.33it/s]
27it [00:04,  8.27it/s]
80it [00:10,  7.47it/s]
28it [00:04,  8.16it/s]
52it [00:09,  9.18it/s]
52it [00:12,  2.23it/s]
53it [00:09,  9.17it/s]
82it [00:10,  9.40it/s]
30it [00:04,  8.82it/s]
83it [00:10,  8.98it/s]
55it [00:09,  9.63it/s]
53it [00:13,  2.50it/s]
31it [00:04,  8.56it/s]
84it [00:10,  8.69it/s]
32it [00:04,  8.62it/s]
57it [00:09, 10.66it/s]
33it [00:04,  8.40it/s]
59it [00:09, 11.13it/s]
86it [00:11,  8.74it/s]
34it [00:04,  8.25it/s]
87it [00:11,  8.52it/s]
61it [00:09, 11.49it/s]
88it [00:11,  8.35it/s]
36it [00:05,  9.27it/s]
63it [00:10, 10.95it/s]
54it [00:13,  2.09it/s]
89it [00:11,  8.23it/s]
38it [00:05,  9.11it/s]
91it [00:11, 10.66it/s]
55it [00:14,  2.60it/s]
65it [00:10, 11.21it/s]
39it [00:05,  8.79it/s]
56it [00:14,  3.29it/s]
67it [00:10, 11.46it/s]
93it [00:11, 10.06it/s]
57it [00:14,  3.96it/s]
41it [00:05,  9.53it/s]
69it [00:10, 11.93it/s]
42it [00:05,  9.10it/s]
95it [00:12,  9.56it/s]
71it [00:10, 11.49it/s]
43it [00:05,  8.79it/s]
97it [00:12,  9.71it/s]
44it [00:06,  8.54it/s]
73it [00:11, 11.28it/s]
98it [00:12,  9.31it/s]
45it [00:06,  8.36it/s]
58it [00:14,  2.80it/s]
100it [00:12,  8.96it/s]
47it [00:06,  8.84it/s]
75it [00:11,  8.58it/s]
101it [00:12,  9.12it/s]
49it [00:06,  9.27it/s]
77it [00:11,  9.68it/s]
103it [00:12, 10.79it/s]
50it [00:06,  8.94it/s]
79it [00:11, 10.18it/s]
105it [00:13, 10.95it/s]
52it [00:06, 10.25it/s]
59it [00:15,  2.21it/s]
107it [00:13, 10.49it/s]
54it [00:07, 11.03it/s]
81it [00:11,  9.38it/s]
83it [00:12,  9.50it/s]
109it [00:13,  9.47it/s]
56it [00:07,  9.81it/s]
85it [00:12,  9.98it/s]
111it [00:13,  9.43it/s]
58it [00:07,  9.09it/s]
60it [00:16,  1.96it/s]
112it [00:13,  8.10it/s]

87it [00:12,  9.40it/s]
59it [00:07,  8.84it/s]
61it [00:16,  2.53it/s]
60it [00:07,  8.61it/s]
88it [00:12,  9.01it/s]
62it [00:16,  3.17it/s]
89it [00:12,  8.77it/s]
62it [00:08,  8.71it/s]
91it [00:13, 10.41it/s]
64it [00:16,  4.50it/s]
66it [00:16,  5.71it/s]
93it [00:13,  9.63it/s]
64it [00:08,  7.50it/s]
67it [00:17,  6.29it/s]
95it [00:13, 10.47it/s]
68it [00:17,  6.87it/s]
65it [00:08,  7.58it/s]
66it [00:08,  7.66it/s]
69it [00:17,  7.07it/s]
97it [00:13,  9.81it/s]
67it [00:08,  7.74it/s]
71it [00:17,  8.27it/s]
99it [00:13,  8.99it/s]
68it [00:08,  6.52it/s]
73it [00:17,  9.12it/s]
100it [00:14,  8.75it/s]
69it [00:09,  6.83it/s]
74it [00:17,  8.62it/s]
101it [00:14,  8.97it/s]
70it [00:09,  7.45it/s]
75it [00:17,  8.87it/s]
71it [00:09,  7.55it/s]
103it [00:14,  9.77it/s]
77it [00:18,  9.00it/s]
105it [00:14, 10.30it/s]
73it [00:09,  8.24it/s]
78it [00:18,  8.69it/s]
79it [00:18,  8.92it/s]
107it [00:14, 10.06it/s]
75it [00:09,  8.47it/s]
81it [00:18,  9.15it/s]
109it [00:14, 10.14it/s]
77it [00:09,  9.25it/s]
82it [00:18,  9.25it/s]
78it [00:10,  8.38it/s]
111it [00:15, 10.03it/s]
84it [00:18,  9.65it/s]
79it [00:10,  7.53it/s]
85it [00:18,  9.39it/s]
113it [00:15,  9.85it/s]
113it [00:15,  7.37it/s]

86it [00:19,  9.44it/s]
80it [00:10,  7.63it/s]
88it [00:19, 11.04it/s]
82it [00:10,  7.65it/s]
90it [00:19,  9.38it/s]
83it [00:10,  6.59it/s]
91it [00:19,  8.99it/s]
84it [00:11,  6.88it/s]
92it [00:19,  8.68it/s]
85it [00:11,  6.99it/s]
93it [00:19,  8.46it/s]
86it [00:11,  7.22it/s]
94it [00:19,  8.29it/s]
88it [00:11,  8.22it/s]
95it [00:20,  7.22it/s]
96it [00:20,  7.12it/s]
89it [00:11,  7.27it/s]
97it [00:20,  6.71it/s]
91it [00:11,  8.20it/s]
98it [00:20,  6.99it/s]
92it [00:11,  7.98it/s]
99it [00:20,  7.22it/s]
93it [00:12,  7.97it/s]
100it [00:20,  7.39it/s]
101it [00:20,  8.01it/s]
95it [00:12,  8.67it/s]
96it [00:12,  8.49it/s]
102it [00:21,  7.08it/s]
97it [00:12,  8.33it/s]
103it [00:21,  7.29it/s]
98it [00:12,  8.21it/s]
100%|██████████| 30/30 [09:58<00:00, 29.34s/it]
100%|██████████| 30/30 [09:58<00:00, 19.95s/it]

104it [00:21,  6.37it/s]
0it [00:00, ?it/s]
99it [00:12,  8.12it/s]
105it [00:21,  6.32it/s]
101it [00:13,  9.18it/s]
106it [00:21,  6.71it/s]
103it [00:13,  9.48it/s]/mnt/petrelfs/wangweiyun/miniconda3/envs/internvl/lib/python3.10/site-packages/transformers/generation/configuration_utils.py:392: UserWarning: `do_sample` is set to `False`. However, `temperature` is set to `0.0` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `temperature`.
  warnings.warn(

107it [00:21,  6.83it/s]
104it [00:13,  9.06it/s]
108it [00:22,  6.77it/s]
1it [00:00,  1.43it/s]
110it [00:22,  6.40it/s]
105it [00:13,  5.70it/s]
2it [00:00,  2.19it/s]
111it [00:22,  6.16it/s]
3it [00:01,  3.18it/s]
113it [00:22,  7.07it/s]
113it [00:22,  4.94it/s]

107it [00:14,  4.70it/s]
4it [00:01,  2.95it/s]
5it [00:01,  3.73it/s]
109it [00:14,  5.66it/s]
6it [00:01,  4.54it/s]
110it [00:14,  6.00it/s]
7it [00:01,  5.51it/s]
8it [00:02,  5.83it/s]
9it [00:02,  5.79it/s]
111it [00:15,  4.42it/s]
10it [00:02,  6.25it/s]
112it [00:15,  4.95it/s]
11it [00:02,  7.04it/s]
12it [00:02,  7.27it/s]
13it [00:02,  7.45it/s]
113it [00:15,  3.95it/s]
113it [00:15,  7.24it/s]

14it [00:02,  7.58it/s]
15it [00:02,  7.54it/s]
16it [00:03,  7.64it/s]
17it [00:03,  7.71it/s]
18it [00:03,  7.52it/s]
19it [00:03,  7.82it/s]
20it [00:03,  8.35it/s]
21it [00:03,  8.21it/s]
23it [00:03,  8.09it/s]
24it [00:04,  8.02it/s]
26it [00:04,  7.97it/s]
27it [00:04,  7.70it/s]
28it [00:04,  8.15it/s]
30it [00:04,  8.51it/s]
31it [00:04,  8.59it/s]
33it [00:05,  8.99it/s]
34it [00:05,  8.73it/s]
35it [00:05,  8.19it/s]
36it [00:05,  8.06it/s]
38it [00:05,  9.21it/s]
40it [00:05,  9.26it/s]
42it [00:06,  9.26it/s]
44it [00:06, 10.06it/s]
46it [00:06, 10.25it/s]
48it [00:06,  9.10it/s]
50it [00:06,  9.52it/s]
51it [00:07,  9.59it/s]
53it [00:07, 10.39it/s]
55it [00:07,  8.69it/s]
57it [00:07,  9.61it/s]
59it [00:07,  9.87it/s]
61it [00:08,  9.85it/s]
63it [00:08, 10.29it/s]
65it [00:08, 10.87it/s]
67it [00:08, 12.00it/s]
69it [00:08, 10.81it/s]
71it [00:08, 10.56it/s]
73it [00:09, 11.16it/s]
75it [00:09, 10.74it/s]
77it [00:09,  9.84it/s]
79it [00:09,  9.84it/s]
81it [00:09,  9.32it/s]
83it [00:10,  9.16it/s]
84it [00:10,  9.27it/s]
85it [00:10,  8.92it/s]
86it [00:10,  9.13it/s]
88it [00:10,  9.39it/s]
89it [00:10,  9.50it/s]
90it [00:10,  9.07it/s]
91it [00:11,  8.70it/s]
93it [00:11,  9.94it/s]
94it [00:11,  8.48it/s]
95it [00:11,  8.66it/s]
96it [00:11,  8.42it/s]
97it [00:11,  8.28it/s]
100%|██████████| 30/30 [10:10<00:00, 28.34s/it]
100%|██████████| 30/30 [10:10<00:00, 20.35s/it]

99it [00:12,  8.92it/s]
0it [00:00, ?it/s]
100it [00:12,  9.15it/s]
101it [00:12,  9.33it/s]
102it [00:12,  9.47it/s]/mnt/petrelfs/wangweiyun/miniconda3/envs/internvl/lib/python3.10/site-packages/transformers/generation/configuration_utils.py:392: UserWarning: `do_sample` is set to `False`. However, `temperature` is set to `0.0` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `temperature`.
  warnings.warn(

103it [00:12,  7.44it/s]
104it [00:12,  7.41it/s]
1it [00:00,  1.51it/s]
106it [00:12,  7.96it/s]
2it [00:00,  2.21it/s]
107it [00:13,  7.93it/s]
3it [00:01,  3.21it/s]
109it [00:13,  8.74it/s]
4it [00:01,  4.01it/s]
111it [00:13, 10.01it/s]
6it [00:01,  5.86it/s]
112it [00:13,  8.28it/s]

7it [00:01,  4.68it/s]
8it [00:02,  3.83it/s]
10it [00:02,  5.46it/s]
11it [00:02,  5.79it/s]
12it [00:02,  5.20it/s]
13it [00:02,  5.66it/s]
14it [00:03,  5.31it/s]
15it [00:03,  5.61it/s]
17it [00:03,  6.80it/s]
18it [00:03,  6.74it/s]
19it [00:03,  5.50it/s]
21it [00:04,  5.48it/s]
22it [00:04,  5.48it/s]
23it [00:04,  5.46it/s]
25it [00:04,  6.29it/s]
26it [00:05,  6.36it/s]
27it [00:05,  5.33it/s]
28it [00:05,  5.81it/s]
29it [00:05,  5.62it/s]
31it [00:05,  6.04it/s]
33it [00:06,  7.14it/s]
34it [00:06,  6.60it/s]
35it [00:06,  5.49it/s]
36it [00:06,  5.95it/s]
37it [00:06,  6.20it/s]
38it [00:06,  6.57it/s]
40it [00:07,  7.73it/s]
41it [00:07,  7.76it/s]
42it [00:07,  7.79it/s]
43it [00:07,  7.71it/s]
45it [00:07,  8.35it/s]
46it [00:07,  8.25it/s]
48it [00:08,  8.90it/s]
50it [00:08,  9.40it/s]
51it [00:08,  8.73it/s]/mnt/petrelfs/wangweiyun/miniconda3/envs/internvl/lib/python3.10/site-packages/PIL/Image.py:1000: UserWarning: Palette images with Transparency expressed in bytes should be converted to RGBA images
  warnings.warn(

52it [00:08,  8.52it/s]
53it [00:08,  8.36it/s]
54it [00:08,  8.06it/s]
55it [00:08,  8.02it/s]
56it [00:09,  7.98it/s]
57it [00:09,  7.96it/s]
58it [00:09,  7.95it/s]
60it [00:09,  8.77it/s]
61it [00:09,  9.03it/s]
62it [00:09,  8.70it/s]
64it [00:09,  9.56it/s]
65it [00:10,  9.10it/s]
66it [00:10,  9.24it/s]
67it [00:10,  8.83it/s]
69it [00:10,  9.83it/s]
71it [00:10, 10.72it/s]
73it [00:10, 11.00it/s]
75it [00:11, 10.13it/s]
77it [00:11,  7.74it/s]
79it [00:11,  8.43it/s]
80it [00:11,  7.58it/s]
82it [00:11,  9.19it/s]
84it [00:12,  8.72it/s]
85it [00:12,  8.53it/s]
86it [00:12,  7.31it/s]
87it [00:12,  7.78it/s]
88it [00:12,  7.41it/s]
89it [00:13,  6.48it/s]
90it [00:13,  6.42it/s]
91it [00:13,  6.76it/s]
93it [00:13,  5.51it/s]
95it [00:13,  6.30it/s]
96it [00:14,  6.60it/s]
98it [00:14,  7.76it/s]
99it [00:14,  7.94it/s]
100it [00:14,  7.93it/s]
101it [00:14,  6.15it/s]
103it [00:14,  7.88it/s]
105it [00:15,  9.37it/s]
107it [00:15,  9.29it/s]
108it [00:15,  8.97it/s]
110it [00:15,  9.13it/s]
111it [00:15,  8.85it/s]
112it [00:15,  9.07it/s]
113it [00:16,  7.06it/s]
Evaluating MMMU_validation ...
Results saved to results/MMMU_validation_240807220709.json
Evaluating ...
python eval/mmmu/main_eval_only.py --output_path results/MMMU_validation_240807220709.json --answer_path eval/mmmu/answer_dict_val.json
Evaluating: Accounting
Evaluating: Agriculture
Evaluating: Architecture_and_Engineering
Evaluating: Art
Evaluating: Art_Theory
Evaluating: Basic_Medical_Science
Evaluating: Biology
Evaluating: Chemistry
Evaluating: Clinical_Medicine
Evaluating: Computer_Science
Evaluating: Design
Evaluating: Diagnostics_and_Laboratory_Medicine
Evaluating: Economics
Evaluating: Electronics
Evaluating: Energy_and_Power
Evaluating: Finance
Evaluating: Geography
Evaluating: History
Evaluating: Literature
Evaluating: Manage
Evaluating: Marketing
Evaluating: Materials
Evaluating: Math
Evaluating: Mechanical_Engineering
Evaluating: Music
Evaluating: Pharmacy
Evaluating: Physics
Evaluating: Psychology
Evaluating: Public_Health
Evaluating: Sociology
{'Overall-Art and Design':{'num': 120, 'acc': 0.408}, 'Art': {'num': 30, 'acc': 0.467}, 'Art_Theory': {'num': 30, 'acc': 0.433}, 'Design': {'num': 30, 'acc': 0.533}, 'Music': {'num': 30, 'acc': 0.2}, 
 'Overall-Business': {'num': 150, 'acc': 0.347}, 'Accounting': {'num': 30, 'acc': 0.367}, 'Economics': {'num': 30, 'acc': 0.333}, 'Finance': {'num': 30, 'acc': 0.333}, 'Manage': {'num': 30, 'acc': 0.367}, 'Marketing': {'num': 30, 'acc': 0.333}, 
 'Overall-Science': {'num': 150, 'acc': 0.227}, 'Biology': {'num': 30, 'acc': 0.267}, 'Chemistry': {'num': 30, 'acc': 0.1}, 'Geography': {'num': 30, 'acc': 0.167}, 'Math': {'num': 30, 'acc': 0.4}, 'Physics': {'num': 30, 'acc': 0.2}, 
 'Overall-Health and Medicine': {'num': 150, 'acc': 0.367}, 'Basic_Medical_Science': {'num': 30, 'acc': 0.433}, 'Clinical_Medicine': {'num': 30, 'acc': 0.4}, 'Diagnostics_and_Laboratory_Medicine': {'num': 30, 'acc': 0.4}, 'Pharmacy': {'num': 30, 'acc': 0.267}, 'Public_Health': {'num': 30, 'acc': 0.333}, 
 'Overall-Humanities and Social Science': {'num': 120, 'acc': 0.492}, 'History': {'num': 30, 'acc': 0.367}, 'Literature': {'num': 30, 'acc': 0.767}, 'Sociology': {'num': 30, 'acc': 0.467}, 'Psychology': {'num': 30, 'acc': 0.367}, 
 'Overall-Tech and Engineering': {'num': 210, 'acc': 0.305}, 'Agriculture': {'num': 30, 'acc': 0.433}, 'Architecture_and_Engineering': {'num': 30, 'acc': 0.233}, 'Computer_Science': {'num': 30, 'acc': 0.233}, 'Electronics': {'num': 30, 'acc': 0.4}, 'Energy_and_Power': {'num': 30, 'acc': 0.267}, 'Materials': {'num': 30, 'acc': 0.367}, 'Mechanical_Engineering': {'num': 30, 'acc': 0.2}, 'Overall': {'num': 900, 'acc': 0.348}}
Results saved to results/MMMU_validation_240807220709.jsonl
+ '[' mmmu-val == mmmu-test ']'
+ '[' mmmu-val == mmmu-dev-cot ']'
+ '[' mmmu-val == mmmu-val-cot ']'
+ '[' mmmu-val == mmmu-test-cot ']'
+ '[' mmmu-val == mmvp ']'
+ '[' mmmu-val == mathvista-testmini ']'
+ '[' mmmu-val == mathvista-test ']'
+ '[' mmmu-val == seed ']'
+ '[' mmmu-val == mvbench ']'