以上代码出现问题：(style_tune) C:\Users\28996\Desktop\AI\persona_contrastive_finetuning>python Contrastive_Training_LM.py
Generating train split: 2 examples [00:00, 2.15 examples/s]
Map: 100%|████████████████████████████████████████████████████████████████████████| 2/2 [00:00<00:00, 71.39 examples/s]
Generating train split: 2 examples [00:00, 252.61 examples/s]
Map: 100%|███████████████████████████████████████████████████████████████████████| 2/2 [00:00<00:00, 399.72 examples/s]
训练集样本示例: {'anchor_input_ids': [56568, 118919, 116122, 11319], 'positive_input_ids': [116122, 20412, 107340, 9370, 100357, 102323, 3837, 109202, 104078, 103975, 100675, 101940, 100912, 105054, 6313], 'negative_input_ids': [100323, 104307, 99245, 9370, 106059, 104060, 3837, 104530, 115604, 99329, 11319]}
验证集样本示例: {'anchor_input_ids': [56568, 118919, 116122, 11319], 'positive_input_ids': [116122, 20412, 107340, 9370, 100357, 102323, 3837, 109202, 104078, 103975, 100675, 101940, 100912, 105054, 6313], 'negative_input_ids': [100323, 104307, 99245, 9370, 106059, 104060, 3837, 104530, 115604, 99329, 11319]}
0%| | 0/3 [00:00<?, ?it/s]You're using a Qwen2TokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.
Traceback (most recent call last):
File "C:\Users\28996\Desktop\AI\persona_contrastive_finetuning\Contrastive_Training_LM.py", line 290, in <module>
trainer.train()
File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\transformers\trainer.py", line 2171, in train
return inner_training_loop(
File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\transformers\trainer.py", line 2531, in _inner_training_loop
tr_loss_step = self.training_step(model, inputs, num_items_in_batch)
File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\transformers\trainer.py", line 3676, in training_step
loss = self.compute_loss(model, inputs)
File "C:\Users\28996\Desktop\AI\persona_contrastive_finetuning\Contrastive_Training_LM.py", line 173, in compute_loss
anchor_emb = get_embeddings(anchor_ids, anchor_mask)
File "C:\Users\28996\Desktop\AI\persona_contrastive_finetuning\Contrastive_Training_LM.py", line 164, in get_embeddings
outputs = model(
File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl
return forward_call(*args, **kwargs)
File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\accelerate\utils\operations.py", line 818, in forward
return model_forward(*args, **kwargs)
File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\accelerate\utils\operations.py", line 806, in __call__
return convert_to_fp32(self.model_forward(*args, **kwargs))
File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\accelerate\utils\operations.py", line 785, in convert_to_fp32
return recursively_apply(_convert_to_fp32, tensor, test_type=_is_fp16_bf16_tensor)
File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\accelerate\utils\operations.py", line 118, in recursively_apply
{
File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\accelerate\utils\operations.py", line 119, in <dictcomp>
k: recursively_apply(
File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\accelerate\utils\operations.py", line 126, in recursively_apply
return func(data, *args, **kwargs)
File "C:\Users\28996\miniconda3\envs\style_tune\lib\site-packages\accelerate\utils\operations.py", line 777, in _convert_to_fp32
return tensor.float()
torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 594.00 MiB. GPU 0 has a total capacity of 8.00 GiB of which 0 bytes is free. Of the allocated memory 13.03 GiB is allocated by PyTorch, and 129.95 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
0%| | 0/3 [00:15<?, ?it/s]
最新发布
博客介绍了Konqueror的新进展，它已通过Acid2 CSS测试，领先于Firefox、Internet Explorer，还增加了ad - block功能。此外，新增了SuperKaramba，Kopete提供了对MSN、Yahoo!即时消息工具的支持。
扫一扫
1606
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
