thrunlab
/

Mistral_Sparse_refined_web_graceful_reg_90p_debugging_2024-03-15

Text Generation

Generated from Trainer

Model card Files Files and versions Community

Mistral_Sparse_refined_web_graceful_reg_90p_debugging_2024-03-15

1 contributor

History: 3 commits

lukeleeai's picture

End of training

fa3a993 verified 9 months ago

.gitattributes

1.52 kB

initial commit 9 months ago
README.md

1.28 kB

End of training 9 months ago
adapter_config.json

601 Bytes

Training in progress, step 10 9 months ago
adapter_model.safetensors

611 kB
LFS

Training in progress, step 10 9 months ago
config.json

1.01 kB

Training in progress, step 10 9 months ago
generation_config.json

111 Bytes

Training in progress, step 10 9 months ago
model.safetensors

16.8 MB
LFS

End of training 9 months ago
sparsification_sftt.py

34.7 kB

Training in progress, step 10 9 months ago
special_tokens_map.json

437 Bytes

Training in progress, step 10 9 months ago
tokenizer.json

1.8 MB

Training in progress, step 10 9 months ago
tokenizer_config.json

969 Bytes

Training in progress, step 10 9 months ago
training_args.bin
Detected Pickle imports (8)
- "torch.device",
- "accelerate.state.PartialState",
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_utils.SchedulerType",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.IntervalStrategy",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.training_args.TrainingArguments"
How to fix it?
4.73 kB
LFS

Training in progress, step 10 9 months ago