`torch_dtype` is deprecated! Use `dtype` instead!
Loaded 494 validation samples

============================================================
Evaluating: Qwen/Qwen3-0.6B-Base
============================================================
Traceback (most recent call last):
  File "/home/ubuntu/thoughtformer/eval_baseline.py", line 195, in <module>
    main()
  File "/home/ubuntu/thoughtformer/eval_baseline.py", line 146, in main
    cor_per_diff, total_per_diff, examples = evaluate_model(model_id, val_data, device=args.device)
                                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ubuntu/thoughtformer/eval_baseline.py", line 67, in evaluate_model
    model = AutoModelForCausalLM.from_pretrained(
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ubuntu/thoughtformer/.venv/lib/python3.12/site-packages/transformers/models/auto/auto_factory.py", line 381, in from_pretrained
    return model_class.from_pretrained(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ubuntu/thoughtformer/.venv/lib/python3.12/site-packages/transformers/modeling_utils.py", line 3993, in from_pretrained
    device_map = check_and_set_device_map(device_map)  # warn, error and fix the device map
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/ubuntu/thoughtformer/.venv/lib/python3.12/site-packages/transformers/integrations/accelerate.py", line 134, in check_and_set_device_map
    raise ValueError(
ValueError: Using a `device_map`, `tp_plan`, `torch.device` context manager or setting `torch.set_default_device(device)` requires `accelerate`. You can install it with `pip install accelerate`