elfayoumi
/

Qwen2.5-7B-Instruct-GRPO-test

Generated from Trainer

Model card Files Files and versions

Metrics Training metrics Community

Qwen2.5-7B-Instruct-GRPO-test

13.7 MB

Ctrl+K

Ctrl+K

1 contributor

History: 19 commits

elfayoumi's picture

End of training

c807f78 verified 7 months ago

runs
Training in progress, step 113 7 months ago
.gitattributes

1.57 kB
Training in progress, step 10 7 months ago
README.md

2.13 kB
End of training 7 months ago
adapter_config.json

1.03 kB
Training in progress, step 10 7 months ago
adapter_model.safetensors

2.18 MB
xet

Training in progress, step 113 7 months ago
chat_template.jinja

2.51 kB
Training in progress, step 10 7 months ago
tokenizer.json

11.4 MB
xet

Training in progress, step 10 7 months ago
tokenizer_config.json

720 Bytes
Training in progress, step 10 7 months ago
training_args.bin
Detected Pickle imports (10)
- "trl.trainer.grpo_config.GRPOConfig",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_utils.SaveStrategy",
- "accelerate.state.PartialState",
- "transformers.trainer_utils.HubStrategy",
- "torch.device",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.trainer_utils.IntervalStrategy",
- "accelerate.utils.dataclasses.DistributedType"
How to fix it?
7.12 kB
xet

Training in progress, step 10 7 months ago