GTMX
/

Qwen2-0.5B-GRPO

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions

Metrics Training metrics Community

Qwen2-0.5B-GRPO

4.96 GB

1 contributor

History: 2 commits

GTMX's picture

End of GRPO training 🚀

9b8f101 verified 19 days ago

runs
End of GRPO training 🚀 19 days ago
.gitattributes

1.57 kB

End of GRPO training 🚀 19 days ago
README.md

2.03 kB

End of GRPO training 🚀 19 days ago
chat_template.jinja

3.83 kB

End of GRPO training 🚀 19 days ago
config.json

857 Bytes

End of GRPO training 🚀 19 days ago
generation_config.json

222 Bytes

End of GRPO training 🚀 19 days ago
model.safetensors

4.94 GB
xet

End of GRPO training 🚀 19 days ago
special_tokens_map.json

325 Bytes

End of GRPO training 🚀 19 days ago
tokenizer.json

17.2 MB
xet

End of GRPO training 🚀 19 days ago
tokenizer_config.json

50.6 kB

End of GRPO training 🚀 19 days ago
training_args.bin
Detected Pickle imports (10)
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "torch.device",
- "transformers.training_args.OptimizerNames",
- "trl.trainer.grpo_config.GRPOConfig",
- "transformers.trainer_utils.SaveStrategy",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.state.PartialState"
How to fix it?
7.19 kB
xet

End of GRPO training 🚀 19 days ago