webui上选择的是bf16, 跑的时候报错并提示只支持bf16

[xudong2019]

Reminder

• I have read the above rules and searched the existing issues.

System Info

webui上选择的是bf16, 跑的时候提示却提示只支持bf16 ? 请问这个是怎么回事呢？

0%| | 0/35325 [00:00<?, ?it/s]Traceback (most recent call last):
File "/opt/anaconda3/envs/factory/bin/llamafactory-cli", line 8, in
sys.exit(main())
^^^^^^
File "/home/being/github/LLaMA-Factory/src/llamafactory/cli.py", line 112, in main
run_exp()
File "/home/being/github/LLaMA-Factory/src/llamafactory/train/tuner.py", line 93, in run_exp
_training_function(config={"args": args, "callbacks": callbacks})
File "/home/being/github/LLaMA-Factory/src/llamafactory/train/tuner.py", line 67, in _training_function
run_sft(model_args, data_args, training_args, finetuning_args, generating_args, callbacks)
File "/home/being/github/LLaMA-Factory/src/llamafactory/train/sft/workflow.py", line 102, in run_sft
train_result = trainer.train(resume_from_checkpoint=training_args.resume_from_checkpoint)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/transformers/trainer.py", line 2171, in train
return inner_training_loop(
^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/transformers/trainer.py", line 2531, in _inner_training_loop
tr_loss_step = self.training_step(model, inputs, num_items_in_batch)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/transformers/trainer.py", line 3675, in training_step
loss = self.compute_loss(model, inputs, num_items_in_batch=num_items_in_batch)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/transformers/trainer.py", line 3731, in compute_loss
outputs = model(**inputs)
^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1739, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1750, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/accelerate/utils/operations.py", line 823, in forward
return model_forward(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/accelerate/utils/operations.py", line 811, in call
return convert_to_fp32(self.model_forward(*args, **kwargs))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/torch/amp/autocast_mode.py", line 44, in decorate_autocast
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/transformers/models/qwen2/modeling_qwen2.py", line 816, in forward
outputs = self.model(
^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1739, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1750, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/transformers/models/qwen2/modeling_qwen2.py", line 562, in forward
layer_outputs = self._gradient_checkpointing_func(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/being/github/LLaMA-Factory/src/llamafactory/model/model_utils/checkpointing.py", line 97, in custom_gradient_checkpointing_func
return gradient_checkpointing_func(func, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/torch/_compile.py", line 32, in inner
return disable_fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/torch/_dynamo/eval_frame.py", line 745, in _fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/torch/utils/checkpoint.py", line 489, in checkpoint
return CheckpointFunction.apply(function, preserve, *args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/torch/autograd/function.py", line 575, in apply
return super().apply(*args, **kwargs) # type: ignore[misc]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/torch/utils/checkpoint.py", line 264, in forward
outputs = run_function(*args)
^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1739, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1750, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/transformers/models/qwen2/modeling_qwen2.py", line 259, in forward
hidden_states, self_attn_weights = self.self_attn(
^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1739, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1750, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/transformers/models/qwen2/modeling_qwen2.py", line 191, in forward
attn_output, attn_weights = attention_interface(
^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/transformers/integrations/flash_attention.py", line 50, in flash_attention_forward
attn_output = _flash_attention_forward(
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/transformers/modeling_flash_attention_utils.py", line 311, in _flash_attention_forward
attn_output_unpad = flash_attn_varlen_func(
^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/flash_attn/flash_attn_interface.py", line 1448, in flash_attn_varlen_func
return FlashAttnVarlenFunc.apply(
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/torch/autograd/function.py", line 575, in apply
return super().apply(*args, **kwargs) # type: ignore[misc]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/flash_attn/flash_attn_interface.py", line 930, in forward
out_padded, softmax_lse, S_dmask, rng_state = _wrapped_flash_attn_varlen_forward(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/torch/_ops.py", line 1123, in call
return self._op(*args, **(kwargs or {}))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/torch/_library/autograd.py", line 113, in autograd_impl
result = forward_no_grad(*args, Metadata(keyset, keyword_only_args))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/torch/_library/autograd.py", line 40, in forward_no_grad
result = op.redispatch(keyset & _C._after_autograd_keyset, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/torch/_ops.py", line 728, in redispatch
return self._handle.redispatch_boxed(keyset, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/torch/_library/custom_ops.py", line 305, in backend_impl
result = self._backend_fns[device_type](*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/torch/_compile.py", line 32, in inner
return disable_fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/torch/_dynamo/eval_frame.py", line 745, in _fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/torch/_library/custom_ops.py", line 337, in wrapped_fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/envs/factory/lib/python3.12/site-packages/flash_attn/flash_attn_interface.py", line 170, in _flash_attn_varlen_forward
out, softmax_lse, S_dmask, rng_state = flash_attn_gpu.varlen_fwd(
^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: FlashAttention only support fp16 and bf16 data type

Reproduction

Put your message here.

Others

No response