Closed
Description
Reminder
- I have read the README and searched the existing issues.
Reproduction
Broke after update to 2bec28e
set CUDA_VISIBLE_DEVICES=0 && llamafactory-cli train --stage sft --do_train True --model_name_or_path llava-hf/llava-1.5-13b-hf --preprocessing_num_workers 16 --finetuning_type lora --quantization_bit 8 --template vicuna --rope_scaling linear --flash_attn fa2 --visual_inputs True --dataset_dir data --dataset pokemon_1k --cutoff_len 4096 --learning_rate 2e-05 --num_train_epochs 3.0 --max_samples 100000 --per_device_train_batch_size 1 --gradient_accumulation_steps 1 --lr_scheduler_type cosine --max_grad_norm 1.0 --logging_steps 5 --save_steps 1000 --warmup_steps 0 --optim adamw_torch --packing False --upcast_layernorm True --report_to none --output_dir saves\LLaVA1.5-13B-Chat\lora\LLaVA1.5-13B-Chat_pokemon --fp16 True --plot_loss True --lora_rank 256 --lora_alpha 512 --lora_dropout 0 --create_new_adapter True --lora_target all
:LLaMA-Factory\venv\lib\site-packages\bitsandbytes\autograd\_functions.py:322: UserWarning: MatMul8bitLt: inputs will be cast from torch.float32 to float16 during quantization
warnings.warn(f"MatMul8bitLt: inputs will be cast from {A.dtype} to float16 during quantization")
Traceback (most recent call last):
File "C:\Users\username\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "C:\Users\username\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 86, in _run_code
exec(code, run_globals)
File "C:\LLaMA-Factory\venv\Scripts\llamafactory-cli.exe\__main__.py", line 7, in <module>
sys.exit(main())
File "C:\LLaMA-Factory\src\llamafactory\cli.py", line 65, in main
run_exp()
File "C:\LLaMA-Factory\src\llamafactory\train\tuner.py", line 34, in run_exp
run_sft(model_args, data_args, training_args, finetuning_args, generating_args, callbacks)
File "C:\LLaMA-Factory\src\llamafactory\train\sft\workflow.py", line 73, in run_sft
train_result = trainer.train(resume_from_checkpoint=training_args.resume_from_checkpoint)
File "C:\LLaMA-Factory\venv\lib\site-packages\transformers\trainer.py", line 1859, in train
return inner_training_loop(
File "C:\LLaMA-Factory\venv\lib\site-packages\transformers\trainer.py", line 2203, in _inner_training_loop
tr_loss_step = self.training_step(model, inputs)
File "C:\LLaMA-Factory\venv\lib\site-packages\transformers\trainer.py", line 3138, in training_step
loss = self.compute_loss(model, inputs)
File "C:\LLaMA-Factory\venv\lib\site-packages\transformers\trainer.py", line 3161, in compute_loss
outputs = model(**inputs)
File "C:\LLaMA-Factory\venv\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "C:\LLaMA-Factory\venv\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "C:\LLaMA-Factory\venv\lib\site-packages\accelerate\utils\operations.py", line 822, in forward
return model_forward(*args, **kwargs)
File "C:\LLaMA-Factory\venv\lib\site-packages\accelerate\utils\operations.py", line 810, in __call__
return convert_to_fp32(self.model_forward(*args, **kwargs))
File "C:\LLaMA-Factory\venv\lib\site-packages\torch\amp\autocast_mode.py", line 16, in decorate_autocast
return func(*args, **kwargs)
File "C:\LLaMA-Factory\venv\lib\site-packages\peft\peft_model.py", line 1129, in forward
return self.base_model(
File "C:\LLaMA-Factory\venv\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "C:\LLaMA-Factory\venv\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "C:\LLaMA-Factory\venv\lib\site-packages\peft\tuners\tuners_utils.py", line 161, in forward
return self.model.forward(*args, **kwargs)
File "C:\LLaMA-Factory\venv\lib\site-packages\accelerate\hooks.py", line 166, in new_forward
output = module._old_forward(*args, **kwargs)
File "C:\LLaMA-Factory\venv\lib\site-packages\transformers\models\llava\modeling_llava.py", line 438, in forward
inputs_embeds, attention_mask, labels, position_ids = self._merge_input_ids_with_image_features(
File "C:\LLaMA-Factory\venv\lib\site-packages\transformers\models\llava\modeling_llava.py", line 340, in _merge_input_ids_with_image_features
final_embedding[image_to_overwrite] = image_features.contiguous().reshape(-1, embed_dim).to(target_device)
RuntimeError: Index put requires the source and destination dtypes match, got Half for the destination and Float for the source.
Expected behavior
No response
System Info
No response
Others
No response
Activity