54 lines
32 KiB
Plaintext
54 lines
32 KiB
Plaintext
|
|
/mnt/petrelfs/wangweiyun/miniconda3/envs/internvl_eval/lib/python3.10/site-packages/bitsandbytes/cextension.py:34: UserWarning: The installed version of bitsandbytes was compiled without GPU support. 8-bit optimizers, 8-bit multiplication, and GPU quantization are unavailable.
|
||
|
|
warn("The installed version of bitsandbytes was compiled without GPU support. "
|
||
|
|
/mnt/petrelfs/wangweiyun/miniconda3/envs/internvl_eval/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cpu.so: undefined symbol: cadam32bit_grad_fp32
|
||
|
|
model path is /mnt/petrelfs/wangweiyun/workspace_cz/InternVL/internvl_chat_dev/share_internvl/InternVL2-8B
|
||
|
|
09/30 19:08:03 - OpenCompass - WARNING - No previous results to reuse!
|
||
|
|
09/30 19:08:03 - OpenCompass - INFO - Reusing experiements from 20240930_190803
|
||
|
|
09/30 19:08:03 - OpenCompass - INFO - Current exp folder: /mnt/petrelfs/wangweiyun/workspace_cz/InternVL/internvl_chat_dev/share_internvl/InternVL2-8B/20240930_190803
|
||
|
|
09/30 19:08:06 - OpenCompass - INFO - Partitioned into 64 tasks.
|
||
|
|
[ ] 0/64, elapsed: 0s, ETA:
[ ] 1/64, 0.0 task/s, elapsed: 911s, ETA: 57413s
[ ] 2/64, 0.0 task/s, elapsed: 1067s, ETA: 33069s
[> ] 3/64, 0.0 task/s, elapsed: 1079s, ETA: 21947s
[> ] 4/64, 0.0 task/s, elapsed: 1083s, ETA: 16242s
[>> ] 5/64, 0.0 task/s, elapsed: 1087s, ETA: 12827s
[>> ] 6/64, 0.0 task/s, elapsed: 1112s, ETA: 10746s
[>>> ] 7/64, 0.0 task/s, elapsed: 1147s, ETA: 9336s
[>>> ] 8/64, 0.0 task/s, elapsed: 1147s, ETA: 8028s
[>>>> ] 9/64, 0.0 task/s, elapsed: 1194s, ETA: 7298s
[>>>> ] 10/64, 0.0 task/s, elapsed: 1197s, ETA: 6465s
[>>>>> ] 11/64, 0.0 task/s, elapsed: 1208s, ETA: 5819s
[>>>>> ] 12/64, 0.0 task/s, elapsed: 1218s, ETA: 5278s
[>>>>>> ] 13/64, 0.0 task/s, elapsed: 1229s, ETA: 4823s
[>>>>>> ] 14/64, 0.0 task/s, elapsed: 1233s, ETA: 4403s
[>>>>>>> ] 15/64, 0.0 task/s, elapsed: 1251s, ETA: 4086s
[>>>>>>> ] 16/64, 0.0 task/s, elapsed: 1252s, ETA: 3755s
[>>>>>>> ] 17/64, 0.0 task/s, elapsed: 1261s, ETA: 3485s
[>>>>>>>> ] 18/64, 0.0 task/s, elapsed: 1262s, ETA: 3225s
[>>>>>>>> ] 19/64, 0.0 task/s, elapsed: 1266s, ETA: 2998s
[>>>>>>>>> ] 20/64, 0.0 task/s, elapsed: 1267s, ETA: 2787s
[>>>>>>>>> ] 21/64, 0.0 task/s, elapsed: 1272s, ETA: 2604s
[>>>>>>>>>> ] 22/64, 0.0 task/s, elapsed: 1275s, ETA: 2433s
[>>>>>>>>>> ] 23/64, 0.0 task/s, elapsed: 1288s, ETA: 2296s
[>>>>>>>>>>> ] 24/64, 0.0 task/s, elapsed: 1292s, ETA: 2153s
[>>>>>>>>>>> ] 25/64, 0.0 task/s, elapsed: 1301s, ETA: 2029s
[>>>>>>>>>>>> ] 26/64, 0.0 task/s, elapsed: 1312s, ETA: 1917s
[>>>>>>>>>>>> ] 27/64, 0.0 task/s, elapsed: 1312s, ETA: 1798s
[>>>>>>>>>>>>> ] 28/64, 0.0 task/s, elapsed: 1317s, ETA: 1694s
[>>>>>>>>>>>>> ] 29/64, 0.0 task/s, elapsed: 1333s, ETA: 1608s
[>>>>>>>>>>>>>> ] 30/64, 0.0 task/s, elapsed: 1337s, ETA: 1515s
[>>>>>>>>>>>>>> ] 31/64, 0.0 task/s, elapsed: 1347s, ETA: 1434s
[>>>>>>>>>>>>>>> ] 32/64, 0.0 task/s, elapsed: 1354s, ETA: 1354s
[>>>>>>>>>>>>>>> ] 33/64, 0.0 task/s, elapsed: 1365s, ETA: 1282s
[>>>>>>>>>>>>>>> ] 34/64, 0.0 task/s, elapsed: 1366s, ETA: 1205s
[>>>>>>>>>>>>>>>> ] 35/64, 0.0 task/s, elapsed: 1372s, ETA: 1137s
[>>>>>>>>>>>>>>>> ] 36/64, 0.0 task/s, elapsed: 1376s, ETA: 1070s
[>>>>>>>>>>>>>>>>> ] 37/64, 0.0 task/s, elapsed: 1397s, ETA: 1019s
[>>>>>>>>>>>>>>>>> ] 38/64, 0.0 task/s, elapsed: 1397s, ETA: 956s
[>>>>>>>>>>>>>>>>>> ] 39/64, 0.0 task/s, elapsed: 1402s, ETA: 899s
[>>>>>>>>>>>>>>>>>> ] 40/64, 0.0 task/s, elapsed: 1416s, ETA: 849s
[>>>>>>>>>>>>>>>>>>> ] 41/64, 0.0 task/s, elapsed: 1442s, ETA: 809s
[>>>>>>>>>>>>>>>>>>> ] 42/64, 0.0 task/s, elapsed: 1458s, ETA: 764s
[>>>>>>>>>>>>>>>>>>>> ] 43/64, 0.0 task/s, elapsed: 1468s, ETA: 717s
[>>>>>>>>>>>>>>>>>>>> ] 44/64, 0.0 task/s, elapsed: 1476s, ETA: 671s
[>>>>>>>>>>>>>>>>>>>>> ] 45/64, 0.0 task/s, elapsed: 1512s, ETA: 638s
[>>>>>>>>>>>>>>>>>>>>> ] 46/64, 0.0 task/s, elapsed: 1550s, ETA: 606s
[>>>>>>>>>>>>>>>>>>>>>> ] 47/64, 0.0 task/s, elapsed: 1567s, ETA: 567s
[>>>>>>>>>>>>>>>>>>>>>> ] 48/64, 0.0 task/s, elapsed: 1583s, ETA: 528s
[>>>>>>>>>>>>>>>>>>>>>> ] 49/64, 0.0 task/s, elapsed: 1607s, ETA: 492s
[>>>>>>>>>>>>>>>>>>>>>>> ] 50/64, 0.0 task/s, elapsed: 1635s, ETA: 458s
[>>>>>>>>>>>>>>>>>
|
||
|
|
09/30 19:52:33 - OpenCompass - INFO - Partitioned into 287 tasks.
|
||
|
|
[ ] 0/287, elapsed: 0s, ETA:
[ ] 1/287, 0.0 task/s, elapsed: 31s, ETA: 8982s
[ ] 2/287, 0.1 task/s, elapsed: 31s, ETA: 4487s
[ ] 3/287, 0.1 task/s, elapsed: 32s, ETA: 2983s
[ ] 4/287, 0.1 task/s, elapsed: 32s, ETA: 2232s
[ ] 5/287, 0.2 task/s, elapsed: 32s, ETA: 1780s
[ ] 6/287, 0.2 task/s, elapsed: 32s, ETA: 1480s
[ ] 7/287, 0.2 task/s, elapsed: 32s, ETA: 1265s
[ ] 8/287, 0.3 task/s, elapsed: 32s, ETA: 1103s
[> ] 9/287, 0.3 task/s, elapsed: 32s, ETA: 977s
[> ] 10/287, 0.3 task/s, elapsed: 32s, ETA: 877s
[> ] 11/287, 0.3 task/s, elapsed: 32s, ETA: 794s
[> ] 12/287, 0.4 task/s, elapsed: 32s, ETA: 725s
[> ] 13/287, 0.4 task/s, elapsed: 32s, ETA: 669s
[> ] 14/287, 0.4 task/s, elapsed: 32s, ETA: 619s
[> ] 15/287, 0.5 task/s, elapsed: 32s, ETA: 576s
[> ] 16/287, 0.5 task/s, elapsed: 32s, ETA: 540s
[> ] 17/287, 0.5 task/s, elapsed: 32s, ETA: 506s
[> ] 18/287, 0.6 task/s, elapsed: 32s, ETA: 479s
[>> ] 19/287, 0.6 task/s, elapsed: 32s, ETA: 453s
[>> ] 20/287, 0.6 task/s, elapsed: 32s, ETA: 429s
[>> ] 21/287, 0.7 task/s, elapsed: 32s, ETA: 407s
[>> ] 22/287, 0.7 task/s, elapsed: 32s, ETA: 388s
[>> ] 23/287, 0.7 task/s, elapsed: 32s, ETA: 370s
[>> ] 24/287, 0.7 task/s, elapsed: 32s, ETA: 353s
[>> ] 25/287, 0.8 task/s, elapsed: 32s, ETA: 338s
[>> ] 26/287, 0.8 task/s, elapsed: 32s, ETA: 325s
[>> ] 27/287, 0.8 task/s, elapsed: 32s, ETA: 312s
[>>> ] 28/287, 0.9 task/s, elapsed: 32s, ETA: 299s
[>>> ] 29/287, 0.9 task/s, elapsed: 32s, ETA: 288s
[>>> ] 30/287, 0.9 task/s, elapsed: 32s, ETA: 278s
[>>> ] 31/287, 1.0 task/s, elapsed: 32s, ETA: 268s
[>>> ] 32/287, 1.0 task/s, elapsed: 32s, ETA: 259s
[>>> ] 33/287, 1.0 task/s, elapsed: 32s, ETA: 250s
[>>> ] 34/287, 1.0 task/s, elapsed: 33s, ETA: 242s
[>>> ] 35/287, 1.1 task/s, elapsed: 33s, ETA: 235s
[>>> ] 36/287, 1.1 task/s, elapsed: 33s, ETA: 227s
[>>> ] 37/287, 1.1 task/s, elapsed: 33s, ETA: 220s
[>>>> ] 38/287, 1.2 task/s, elapsed: 33s, ETA: 214s
[>>>> ] 39/287, 1.2 task/s, elapsed: 33s, ETA: 207s
[>>>> ] 40/287, 1.2 task/s, elapsed: 33s, ETA: 202s
[>>>> ] 41/287, 1.3 task/s, elapsed: 33s, ETA: 196s
[>>>> ] 42/287, 1.3 task/s, elapsed: 33s, ETA: 191s
[>>>> ] 43/287, 1.3 task/s, elapsed: 33s, ETA: 185s
[>>>> ] 44/287, 1.3 task/s, elapsed: 33s, ETA: 181s
[>>>> ] 45/287, 1.4 task/s, elapsed: 33s, ETA: 176s
[>>>> ] 46/287, 1.4 task/s, elapsed: 33s, ETA: 171s
[>>>>> ] 47/287, 1.4 task/s, elapsed: 33s, ETA: 167s
[>>>>> ] 48/287, 1.5 task/s, elapsed: 33s, ETA: 163s
[>>>>> ] 49/287, 1.5 task/s, elapsed: 33s, ETA: 159s
[>>>>> ] 50/287, 1.5 task/s, elapsed: 33s, ETA: 155s
[>>>>>
|
||
|
|
dataset version metric mode internvl-chat-20b
|
||
|
|
---------------------------- --------- ---------------------------- ------ -------------------
|
||
|
|
mmlu - naive_average gen 73.17
|
||
|
|
cmmlu - naive_average gen 79.21
|
||
|
|
ceval - naive_average gen 80.14
|
||
|
|
agieval - - - -
|
||
|
|
GaokaoBench - weighted_average gen 74.99
|
||
|
|
triviaqa 2121ce score gen 62.03
|
||
|
|
triviaqa_wiki_1shot - - - -
|
||
|
|
nq 3dcea1 score gen 28.12
|
||
|
|
C3 8c358f accuracy gen 94.19
|
||
|
|
race-high 9a54b6 accuracy gen 90.82
|
||
|
|
flores_100 - - - -
|
||
|
|
winogrande b36770 accuracy gen 85.87
|
||
|
|
hellaswag e42710 accuracy gen 94.91
|
||
|
|
bbh - naive_average gen 72.67
|
||
|
|
gsm8k 1d7fe4 accuracy gen 75.59
|
||
|
|
math 393424 accuracy gen 39.50
|
||
|
|
TheoremQA 6f0af8 score gen 15.62
|
||
|
|
MathBench - - - -
|
||
|
|
openai_humaneval 8e312c humaneval_pass@1 gen 69.51
|
||
|
|
humanevalx - - - -
|
||
|
|
sanitized_mbpp a447ff score gen 58.75
|
||
|
|
mbpp_cn 6fb572 score gen 48.20
|
||
|
|
leval - - - -
|
||
|
|
leval_closed - - - -
|
||
|
|
leval_open - - - -
|
||
|
|
longbench - - - -
|
||
|
|
longbench_single-document-qa - - - -
|
||
|
|
longbench_multi-document-qa - - - -
|
||
|
|
longbench_summarization - - - -
|
||
|
|
longbench_few-shot-learning - - - -
|
||
|
|
longbench_synthetic-tasks - - - -
|
||
|
|
longbench_code-completion - - - -
|
||
|
|
teval - - - -
|
||
|
|
teval_zh - - - -
|
||
|
|
IFEval 3321a3 Prompt-level-strict-accuracy gen 52.31
|
||
|
|
IFEval 3321a3 Inst-level-strict-accuracy gen 62.71
|
||
|
|
IFEval 3321a3 Prompt-level-loose-accuracy gen 54.90
|
||
|
|
IFEval 3321a3 Inst-level-loose-accuracy gen 64.87
|
||
|
|
09/30 19:55:16 - OpenCompass - INFO - write summary to /mnt/petrelfs/wangweiyun/workspace_cz/InternVL/internvl_chat_dev/share_internvl/InternVL2-8B/20240930_190803/summary/summary_20240930_190803.txt
|
||
|
|
09/30 19:55:16 - OpenCompass - INFO - write csv to /mnt/petrelfs/wangweiyun/workspace_cz/InternVL/internvl_chat_dev/share_internvl/InternVL2-8B/20240930_190803/summary/summary_20240930_190803.csv
|