runtime error

Exit code: 1. Reason: The `load_in_4bit` and `load_in_8bit` arguments are deprecated and will be removed in the future versions. Please, pass a `BitsAndBytesConfig` object in `quantization_config` argument instead. Fetching 3 files: 0%| | 0/3 [00:00<?, ?it/s] Fetching 3 files: 33%|███▎ | 1/3 [00:27<00:54, 27.35s/it] Fetching 3 files: 67%|██████▋ | 2/3 [00:27<00:11, 11.49s/it] Fetching 3 files: 100%|██████████| 3/3 [00:27<00:00, 9.24s/it] Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s] Loading checkpoint shards: 33%|███▎ | 1/3 [02:44<05:28, 164.06s/it] Loading checkpoint shards: 67%|██████▋ | 2/3 [05:36<02:49, 169.16s/it] Loading checkpoint shards: 100%|██████████| 3/3 [08:04<00:00, 159.59s/it] Loading checkpoint shards: 100%|██████████| 3/3 [08:04<00:00, 161.66s/it] Generating train split: 0 examples [00:00, ? examples/s] Generating train split: 30 examples [00:00, 650.91 examples/s] Traceback (most recent call last): File "/workspace/train_dpo.py", line 25, in <module> training_args = TrainingArguments( File "<string>", line 135, in __init__ File "/usr/local/lib/python3.10/site-packages/transformers/training_args.py", line 1747, in __post_init__ raise ValueError(error_message) ValueError: Your setup doesn't support bf16/gpu.

Container logs: