1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
|
/u/yurenh2/miniforge3/envs/eval/lib/python3.11/site-packages/transformers/utils/hub.py:110: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.
warnings.warn(
/u/yurenh2/miniforge3/envs/eval/lib/python3.11/site-packages/transformers/utils/hub.py:110: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.
warnings.warn(
[0;36m(EngineCore_DP0 pid=2400286)[0;0m
Loading safetensors checkpoint shards: 0% Completed | 0/4 [00:00<?, ?it/s]
[0;36m(EngineCore_DP0 pid=2400286)[0;0m
Loading safetensors checkpoint shards: 25% Completed | 1/4 [00:03<00:11, 3.75s/it]
[0;36m(EngineCore_DP0 pid=2400286)[0;0m
Loading safetensors checkpoint shards: 50% Completed | 2/4 [00:05<00:05, 2.54s/it]
[0;36m(EngineCore_DP0 pid=2400286)[0;0m
Loading safetensors checkpoint shards: 75% Completed | 3/4 [00:12<00:04, 4.60s/it]
[0;36m(EngineCore_DP0 pid=2400286)[0;0m
Loading safetensors checkpoint shards: 100% Completed | 4/4 [00:16<00:00, 4.28s/it]
[0;36m(EngineCore_DP0 pid=2400286)[0;0m
Loading safetensors checkpoint shards: 100% Completed | 4/4 [00:16<00:00, 4.07s/it]
[0;36m(EngineCore_DP0 pid=2400286)[0;0m
[0;36m(EngineCore_DP0 pid=2400286)[0;0m
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 0%| | 0/51 [00:00<?, ?it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 4%|▍ | 2/51 [00:00<00:03, 14.89it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 8%|▊ | 4/51 [00:00<00:03, 15.63it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 12%|█▏ | 6/51 [00:00<00:02, 16.10it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 16%|█▌ | 8/51 [00:00<00:02, 16.66it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 22%|██▏ | 11/51 [00:00<00:02, 18.08it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 27%|██▋ | 14/51 [00:00<00:01, 18.87it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 33%|███▎ | 17/51 [00:00<00:01, 19.62it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 39%|███▉ | 20/51 [00:01<00:01, 20.60it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 45%|████▌ | 23/51 [00:01<00:01, 21.25it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 51%|█████ | 26/51 [00:01<00:01, 21.79it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 57%|█████▋ | 29/51 [00:01<00:01, 20.08it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 63%|██████▎ | 32/51 [00:01<00:00, 21.01it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 69%|██████▊ | 35/51 [00:01<00:00, 21.87it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 75%|███████▍ | 38/51 [00:01<00:00, 22.54it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 80%|████████ | 41/51 [00:01<00:00, 23.14it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 86%|████████▋ | 44/51 [00:02<00:00, 23.73it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 92%|█████████▏| 47/51 [00:02<00:00, 23.48it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 98%|█████████▊| 50/51 [00:02<00:00, 24.09it/s]
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 100%|██████████| 51/51 [00:02<00:00, 20.82it/s]
[0;36m(EngineCore_DP0 pid=2400286)[0;0m
Capturing CUDA graphs (decode, FULL): 0%| | 0/35 [00:00<?, ?it/s]
Capturing CUDA graphs (decode, FULL): 3%|▎ | 1/35 [00:00<00:05, 6.28it/s]
Capturing CUDA graphs (decode, FULL): 11%|█▏ | 4/35 [00:00<00:02, 15.17it/s]
Capturing CUDA graphs (decode, FULL): 20%|██ | 7/35 [00:00<00:01, 18.56it/s]
Capturing CUDA graphs (decode, FULL): 29%|██▊ | 10/35 [00:00<00:01, 19.82it/s]
Capturing CUDA graphs (decode, FULL): 37%|███▋ | 13/35 [00:00<00:01, 20.21it/s]
Capturing CUDA graphs (decode, FULL): 46%|████▌ | 16/35 [00:00<00:00, 21.27it/s]
Capturing CUDA graphs (decode, FULL): 54%|█████▍ | 19/35 [00:00<00:00, 21.99it/s]
Capturing CUDA graphs (decode, FULL): 63%|██████▎ | 22/35 [00:01<00:00, 22.54it/s]
Capturing CUDA graphs (decode, FULL): 71%|███████▏ | 25/35 [00:01<00:00, 22.97it/s]
Capturing CUDA graphs (decode, FULL): 80%|████████ | 28/35 [00:01<00:00, 22.23it/s]
Capturing CUDA graphs (decode, FULL): 89%|████████▊ | 31/35 [00:01<00:00, 22.90it/s]
Capturing CUDA graphs (decode, FULL): 97%|█████████▋| 34/35 [00:01<00:00, 23.36it/s]
Capturing CUDA graphs (decode, FULL): 100%|██████████| 35/35 [00:01<00:00, 21.34it/s]
[0;36m(APIServer pid=2399803)[0;0m INFO: Started server process [2399803]
[0;36m(APIServer pid=2399803)[0;0m INFO: Waiting for application startup.
[0;36m(APIServer pid=2399803)[0;0m INFO: Application startup complete.
Traceback (most recent call last):
File "/projects/bfqt/users/yurenh2/ml-projects/personalization-user-model/scripts/test_local_reward_batch.py", line 202, in <module>
main()
File "/projects/bfqt/users/yurenh2/ml-projects/personalization-user-model/scripts/test_local_reward_batch.py", line 147, in main
samples = [
^
File "/projects/bfqt/users/yurenh2/ml-projects/personalization-user-model/scripts/test_local_reward_batch.py", line 148, in <listcomp>
TurnSample(
TypeError: TurnSample.__init__() missing 4 required positional arguments: 'user_id', 'session_id', 'turn_id', and 'memories'
|
