clembench-playpen
/

meta-llama_KTO_binary_dataset_wordle_wordlewithclue_same-family-all_2eps

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

meta-llama_KTO_binary_dataset_wordle_wordlewithclue_same-family-all_2eps

1 contributor

History: 2 commits

mazzaqq's picture

End of training

e761214 verified 5 days ago

.gitattributes

1.57 kB

End of training 5 days ago
README.md

2.29 kB

End of training 5 days ago
adapter_config.json

832 Bytes

End of training 5 days ago
adapter_model.safetensors

671 MB
LFS

End of training 5 days ago
special_tokens_map.json

454 Bytes

End of training 5 days ago
tokenizer.json

17.2 MB
LFS

End of training 5 days ago
tokenizer_config.json

55.5 kB

End of training 5 days ago
training_args.bin
Detected Pickle imports (9)
- "accelerate.state.PartialState",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_utils.HubStrategy",
- "transformers.training_args.OptimizerNames",
- "trl.trainer.kto_config.KTOConfig",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.trainer_utils.IntervalStrategy",
- "torch.device"
How to fix it?
5.69 kB
LFS

End of training 5 days ago