google

/

gemma-3-1b-it

like 458

Follow

Google 16k

Hi, I've encountered an error during evaluation phase:

Traceback (most recent call last):
    train_stats = trainer.train()
                  ^^^^^^^^^^^^^^^
  File "/root/anaconda3/envs/ME/lib/python3.11/site-packages/trl/trainer/sft_trainer.py", line 361, in train
    output = super().train(*args, **kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/anaconda3/envs/ME/lib/python3.11/site-packages/transformers/trainer.py", line 2250, in train
    return inner_training_loop(
           ^^^^^^^^^^^^^^^^^^^^
  File "/root/anaconda3/envs/ME/lib/python3.11/site-packages/transformers/trainer.py", line 2625, in _inner_training_loop
    self._maybe_log_save_evaluate(
  File "/root/anaconda3/envs/ME/lib/python3.11/site-packages/transformers/trainer.py", line 3098, in _maybe_log_save_evaluate
    metrics = self._evaluate(trial, ignore_keys_for_eval)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/anaconda3/envs/ME/lib/python3.11/site-packages/transformers/trainer.py", line 3052, in _evaluate
    metrics = self.evaluate(ignore_keys=ignore_keys_for_eval)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/anaconda3/envs/ME/lib/python3.11/site-packages/transformers/trainer.py", line 4118, in evaluate
    output = eval_loop(
             ^^^^^^^^^^
  File "/root/anaconda3/envs/ME/lib/python3.11/site-packages/transformers/trainer.py", line 4312, in evaluation_loop
    losses, logits, labels = self.prediction_step(model, inputs, prediction_loss_only, ignore_keys=ignore_keys)
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/anaconda3/envs/ME/lib/python3.11/site-packages/transformers/trainer.py", line 4528, in prediction_step
    loss, outputs = self.compute_loss(model, inputs, return_outputs=True)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/anaconda3/envs/ME/lib/python3.11/site-packages/transformers/trainer.py", line 3772, in compute_loss
    outputs = model(**inputs)
              ^^^^^^^^^^^^^^^
  File "/root/anaconda3/envs/ME/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/anaconda3/envs/ME/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/anaconda3/envs/ME/lib/python3.11/site-packages/accelerate/utils/operations.py", line 823, in forward
    return model_forward(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/anaconda3/envs/ME/lib/python3.11/site-packages/accelerate/utils/operations.py", line 811, in __call__
    return convert_to_fp32(self.model_forward(*args, **kwargs))
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/anaconda3/envs/ME/lib/python3.11/site-packages/accelerate/utils/operations.py", line 790, in convert_to_fp32
    return recursively_apply(_convert_to_fp32, tensor, test_type=_is_fp16_bf16_tensor)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/anaconda3/envs/ME/lib/python3.11/site-packages/accelerate/utils/operations.py", line 119, in recursively_apply
    {
  File "/root/anaconda3/envs/ME/lib/python3.11/site-packages/accelerate/utils/operations.py", line 120, in <dictcomp>
    k: recursively_apply(
       ^^^^^^^^^^^^^^^^^^
  File "/root/anaconda3/envs/ME/lib/python3.11/site-packages/accelerate/utils/operations.py", line 127, in recursively_apply
    return func(data, *args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/anaconda3/envs/ME/lib/python3.11/site-packages/accelerate/utils/operations.py", line 782, in _convert_to_fp32
    return tensor.float()
           ^^^^^^^^^^^^
AttributeError: 'HybridCache' object has no attribute 'float'