Checklist / 检查清单
Question Description / 问题描述
运行命令：
swift sft
--model /home/yw/models/Qwen3-Reranker-8B
--task_type generative_reranker
--loss_type generative_reranker
--tuner_type lora
--lora_rank 8
--lora_alpha 32
--lora_dropout 0.1
--target_modules all-linear
--dataset /home/yw/reranker_ft/train_data/qwen3/single_pos_10.jsonl
--output_dir qwen3_output_lora
--num_train_epochs 2
--save_steps 200
--per_device_train_batch_size 2
--gradient_accumulation_steps 1
--learning_rate 2e-4
--dataloader_drop_last true
--fp16 true
--bf16 false
报错：
[INFO:swift] Dataset filtered, origin length: 10, filtered dataset length: 0
[INFO:swift] train_dataset: None
[INFO:swift] val_dataset: None
Traceback (most recent call last):
File "/home/yw/.conda/envs/swift/lib/python3.10/site-packages/swift/cli/sft.py", line 20, in
sft_main()
File "/home/yw/.conda/envs/swift/lib/python3.10/site-packages/swift/pipelines/train/sft.py", line 354, in sft_main
return SwiftSft(args).main()
File "/home/yw/.conda/envs/swift/lib/python3.10/site-packages/swift/pipelines/base.py", line 52, in main
result = self.run()
File "/home/yw/.conda/envs/swift/lib/python3.10/site-packages/swift/ray/base.py", line 168, in wrapper
return func(self, *args, **kwargs)
File "/home/yw/.conda/envs/swift/lib/python3.10/site-packages/swift/pipelines/train/sft.py", line 174, in run
train_dataset, val_dataset = self._prepare_dataset()
File "/home/yw/.conda/envs/swift/lib/python3.10/site-packages/swift/ray/base.py", line 168, in wrapper
return func(self, *args, **kwargs)
File "/home/yw/.conda/envs/swift/lib/python3.10/site-packages/swift/pipelines/train/sft.py", line 135, in _prepare_dataset
self._show_dataset(*datasets)
File "/home/yw/.conda/envs/swift/lib/python3.10/site-packages/swift/pipelines/train/sft.py", line 295, in _show_dataset
inputs = train_dataset[0] if hasattr(train_dataset, 'len') else next(iter(train_dataset))
TypeError: 'NoneType' object is not iterable
Checklist / 检查清单
Question Description / 问题描述
运行命令：
swift sft
--model /home/yw/models/Qwen3-Reranker-8B
--task_type generative_reranker
--loss_type generative_reranker
--tuner_type lora
--lora_rank 8
--lora_alpha 32
--lora_dropout 0.1
--target_modules all-linear
--dataset /home/yw/reranker_ft/train_data/qwen3/single_pos_10.jsonl
--output_dir qwen3_output_lora
--num_train_epochs 2
--save_steps 200
--per_device_train_batch_size 2
--gradient_accumulation_steps 1
--learning_rate 2e-4
--dataloader_drop_last true
--fp16 true
--bf16 false
报错：
[INFO:swift] Dataset filtered, origin length: 10, filtered dataset length: 0
[INFO:swift] train_dataset: None
[INFO:swift] val_dataset: None
Traceback (most recent call last):
File "/home/yw/.conda/envs/swift/lib/python3.10/site-packages/swift/cli/sft.py", line 20, in
sft_main()
File "/home/yw/.conda/envs/swift/lib/python3.10/site-packages/swift/pipelines/train/sft.py", line 354, in sft_main
return SwiftSft(args).main()
File "/home/yw/.conda/envs/swift/lib/python3.10/site-packages/swift/pipelines/base.py", line 52, in main
result = self.run()
File "/home/yw/.conda/envs/swift/lib/python3.10/site-packages/swift/ray/base.py", line 168, in wrapper
return func(self, *args, **kwargs)
File "/home/yw/.conda/envs/swift/lib/python3.10/site-packages/swift/pipelines/train/sft.py", line 174, in run
train_dataset, val_dataset = self._prepare_dataset()
File "/home/yw/.conda/envs/swift/lib/python3.10/site-packages/swift/ray/base.py", line 168, in wrapper
return func(self, *args, **kwargs)
File "/home/yw/.conda/envs/swift/lib/python3.10/site-packages/swift/pipelines/train/sft.py", line 135, in _prepare_dataset
self._show_dataset(*datasets)
File "/home/yw/.conda/envs/swift/lib/python3.10/site-packages/swift/pipelines/train/sft.py", line 295, in _show_dataset
inputs = train_dataset[0] if hasattr(train_dataset, 'len') else next(iter(train_dataset))
TypeError: 'NoneType' object is not iterable