cj453
/

dense_reward_trainer_final_opt__NumTrainEpochs5_SaveStrategiesepoch_reward_modeling_anthropic_hh

Generated from Trainer

Model card Files Files and versions Community

dense_reward_trainer_final_opt__NumTrainEpochs5_SaveStrategiesepoch_reward_modeling_anthropic_hh

1 contributor

History: 2 commits

cj453's picture

End of training

14b6698 verified about 2 months ago

.gitattributes

1.52 kB

initial commit about 2 months ago
README.md

9.98 kB

End of training about 2 months ago
config.json

841 Bytes

End of training about 2 months ago
merges.txt

456 kB

End of training about 2 months ago
model-00001-of-00002.safetensors

4.99 GB
LFS

End of training about 2 months ago
model-00002-of-00002.safetensors

680 MB
LFS

End of training about 2 months ago
model.safetensors.index.json

33.9 kB

End of training about 2 months ago
special_tokens_map.json

548 Bytes

End of training about 2 months ago
tokenizer.json

2.11 MB

End of training about 2 months ago
tokenizer_config.json

669 Bytes

End of training about 2 months ago
training_args.bin
Detected Pickle imports (8)
- "torch.device",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.state.PartialState",
- "trl.trainer.reward_config.RewardConfig",
- "transformers.trainer_utils.IntervalStrategy",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.training_args.OptimizerNames"
How to fix it?
4.92 kB
LFS

End of training about 2 months ago
vocab.json

798 kB

End of training about 2 months ago