hero2323
/

llama-3-8b-trained-on-all-datasets

Model card Files Files and versions Community

llama-3-8b-trained-on-all-datasets

1 contributor

History: 2 commits

hero2323's picture

Training in progress, epoch 1

f5e84bd verified about 2 months ago

.gitattributes

1.52 kB

initial commit about 2 months ago
adapter_config.json

738 Bytes

Training in progress, epoch 1 about 2 months ago
adapter_model.safetensors

168 MB
LFS

Training in progress, epoch 1 about 2 months ago
special_tokens_map.json

345 Bytes

Training in progress, epoch 1 about 2 months ago
tokenizer.json

9.09 MB

Training in progress, epoch 1 about 2 months ago
tokenizer_config.json

51 kB

Training in progress, epoch 1 about 2 months ago
training_args.bin
Detected Pickle imports (9)
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.SchedulerType",
- "accelerate.state.PartialState",
- "accelerate.utils.dataclasses.DistributedType",
- "trl.trainer.sft_config.SFTConfig",
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "torch.device",
- "transformers.training_args.OptimizerNames"
How to fix it?
5.62 kB
LFS

Training in progress, epoch 1 about 2 months ago