Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Posts
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

DatPySci
/
pythia-410m-sft-full

Text Generation
Transformers
gpt_neox
alignment-handbook
trl
sft
Generated from Trainer
conversational
Model card Files Files and versions Community
pythia-410m-sft-full
Ctrl+K
Ctrl+K
  • 1 contributor
History: 42 commits
DatPySci's picture
DatPySci
End of training
571a3a4 verified about 1 year ago
  • .gitattributes
    1.52 kB
    initial commit about 1 year ago
  • README.md
    1.64 kB
    End of training about 1 year ago
  • all_results.json
    364 Bytes
    End of training about 1 year ago
  • config.json
    759 Bytes
    End of training about 1 year ago
  • eval_results.json
    188 Bytes
    End of training about 1 year ago
  • special_tokens_map.json
    473 Bytes
    Training in progress, step 100 about 1 year ago
  • tokenizer.json
    2.11 MB
    Training in progress, step 100 about 1 year ago
  • tokenizer_config.json
    5.21 kB
    Training in progress, step 100 about 1 year ago
  • train_results.json
    196 Bytes
    Model save about 1 year ago
  • trainer_state.json
    120 kB
    Model save about 1 year ago
  • training_args.bin

    Detected Pickle imports (9)

    • "accelerate.utils.dataclasses.DistributedType",
    • "transformers.trainer_utils.SchedulerType",
    • "alignment.configs.SFTConfig",
    • "transformers.trainer_pt_utils.AcceleratorConfig",
    • "accelerate.state.PartialState",
    • "transformers.training_args.OptimizerNames",
    • "transformers.trainer_utils.IntervalStrategy",
    • "torch.device",
    • "transformers.trainer_utils.HubStrategy"

    How to fix it?

    4.98 kB
    LFS
    Training in progress, step 100 about 1 year ago