chansung
/

gemma-7b-sft-qlora-no-robots2

alignment-handbook

Generated from Trainer

4-bit precision

Model card Files Files and versions Metrics Training metrics Community

gemma-7b-sft-qlora-no-robots2

1 contributor

History: 3 commits

chansung's picture

End of training

22ab29c verified 8 months ago

runs
End of training 8 months ago
.gitattributes

1.57 kB

Model save 8 months ago
README.md

2.06 kB

End of training 8 months ago
adapter_config.json

645 Bytes

Model save 8 months ago
adapter_model.safetensors

100 MB
LFS

Model save 8 months ago
all_results.json

353 Bytes

End of training 8 months ago
config.json

1.17 kB

End of training 8 months ago
eval_results.json

184 Bytes

End of training 8 months ago
special_tokens_map.json

630 Bytes

Model save 8 months ago
tokenizer.json

17.5 MB
LFS

Model save 8 months ago
tokenizer_config.json

1.89 kB

Model save 8 months ago
train_results.json

190 Bytes

Model save 8 months ago
trainer_state.json

4.27 kB

Model save 8 months ago
training_args.bin
Detected Pickle imports (9)
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "torch.device",
- "alignment.configs.SFTConfig",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.training_args.OptimizerNames",
- "accelerate.state.PartialState"
How to fix it?
5.11 kB
LFS

Model save 8 months ago