GaetanMichelet
/

Llama-31-8B_task-2_60-samples_config-1_full_auto

alignment-handbook

Generated from Trainer

4-bit precision

Model card Files Files and versions Metrics Training metrics Community

Llama-31-8B_task-2_60-samples_config-1_full_auto

1 contributor

History: 19 commits

GaetanMichelet's picture

End of training

ea95a66 verified 3 months ago

runs
End of training 3 months ago
.gitattributes

1.52 kB

initial commit 3 months ago
README.md

2.48 kB

End of training 3 months ago
adapter_config.json

740 Bytes

Training in progress, epoch 0 3 months ago
adapter_model.safetensors

168 MB
LFS

Model save 3 months ago
all_results.json

393 Bytes

End of training 3 months ago
config.json

1.4 kB

End of training 3 months ago
eval_results.json

181 Bytes

End of training 3 months ago
special_tokens_map.json

325 Bytes

Training in progress, epoch 0 3 months ago
tokenizer.json

9.09 MB

Training in progress, epoch 0 3 months ago
tokenizer_config.json

55.4 kB

Training in progress, epoch 0 3 months ago
train_results.json

233 Bytes

Model save 3 months ago
trainer_state.json

12.5 kB

Model save 3 months ago
training_args.bin
Detected Pickle imports (10)
- "transformers.trainer_utils.IntervalStrategy",
- "accelerate.state.PartialState",
- "transformers.utils.quantization_config.QuantizationMethod",
- "transformers.trainer_utils.HubStrategy",
- "torch.device",
- "accelerate.utils.dataclasses.DistributedType",
- "alignment.configs.SFTConfig",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.trainer_utils.SchedulerType",
- "transformers.training_args.OptimizerNames"
How to fix it?
6.26 kB
LFS

Training in progress, epoch 0 3 months ago