Hi nice work! I was aware that Thai is difficult to optimize so I'm very interested in the perf eval of this work!
When I started to run the code, it gave me this assertion error, you guys know why it happened?
$python run.py configs/eval_sailor.py -w outputs/sailor --num-gpus 2 --max-num-workers 64
03/08 10:47:25 - OpenCompass - WARNING - SlurmRunner is not used, so the partition argument is ignored.
03/08 10:47:25 - OpenCompass - INFO - Partitioned into 12 tasks.
0%| | 0/12 [00:00<?, ?it/s]Traceback (most recent call last):
File "/home/opencompass/opencompass-main/run.py", line 357, in
main()
File "/home/opencompass/opencompass-main/run.py", line 309, in main
runner(tasks)
File "/home/opencompass/opencompass-main/opencompass/runners/base.py", line 39, in call
self.summarize(status)
File "/home/opencompass/opencompass-main/opencompass/runners/base.py", line 61, in summarize
for _task, code in status:
File "/home/.conda/envs/opencompass/lib/python3.10/concurrent/futures/_base.py", line 609, in result_iterator
yield fs.pop().result()
File "/home/.conda/envs/opencompass/lib/python3.10/concurrent/futures/_base.py", line 439, in result
return self.get_result()
File "/home/.conda/envs/opencompass/lib/python3.10/concurrent/futures/_base.py", line 391, in get_result
raise self._exception
File "/home/.conda/envs/opencompass/lib/python3.10/concurrent/futures/thread.py", line 58, in run
result = self.fn(*self.args, **self.kwargs)
File "/home/opencompass/opencompass-main/opencompass/runners/local.py", line123, in submit
assert len(gpus) >= num_gpus
AssertionError
0%| | 0/12 [00:00<?, ?it/s]
(opencompass)
My environment was set up as the guideline you gave, and my GPUs are A800 * 2. they work fine. could you help and see how to resolve the error? Much appreciate it!
Hi nice work! I was aware that Thai is difficult to optimize so I'm very interested in the perf eval of this work! When I started to run the code, it gave me this assertion error, you guys know why it happened?
$python run.py configs/eval_sailor.py -w outputs/sailor --num-gpus 2 --max-num-workers 64 03/08 10:47:25 - OpenCompass - WARNING - SlurmRunner is not used, so the partition argument is ignored. 03/08 10:47:25 - OpenCompass - INFO - Partitioned into 12 tasks. 0%| | 0/12 [00:00<?, ?it/s]Traceback (most recent call last): File "/home/opencompass/opencompass-main/run.py", line 357, in
main()
File "/home/opencompass/opencompass-main/run.py", line 309, in main
runner(tasks)
File "/home/opencompass/opencompass-main/opencompass/runners/base.py", line 39, in call
self.summarize(status)
File "/home/opencompass/opencompass-main/opencompass/runners/base.py", line 61, in summarize
for _task, code in status:
File "/home/.conda/envs/opencompass/lib/python3.10/concurrent/futures/_base.py", line 609, in result_iterator
yield fs.pop().result()
File "/home/.conda/envs/opencompass/lib/python3.10/concurrent/futures/_base.py", line 439, in result
return self.get_result()
File "/home/.conda/envs/opencompass/lib/python3.10/concurrent/futures/_base.py", line 391, in get_result
raise self._exception
File "/home/.conda/envs/opencompass/lib/python3.10/concurrent/futures/thread.py", line 58, in run
result = self.fn(*self.args, **self.kwargs)
File "/home/opencompass/opencompass-main/opencompass/runners/local.py", line123, in submit
assert len(gpus) >= num_gpus
AssertionError
0%| | 0/12 [00:00<?, ?it/s]
(opencompass)
My environment was set up as the guideline you gave, and my GPUs are A800 * 2. they work fine. could you help and see how to resolve the error? Much appreciate it!