Yaxin1992
/

llama3-8b-8000-dpo-1000-pt-publish-v2

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

llama3-8b-8000-dpo-1000-pt-publish-v2

1 contributor

History: 4 commits

Yaxin1992's picture

Training in progress, step 600

152783d verified 8 months ago

runs
Training in progress, step 600 8 months ago
.gitattributes

1.52 kB

initial commit 8 months ago
adapter_config.json

660 Bytes

Training in progress, step 200 8 months ago
adapter_model.safetensors

13.6 MB
LFS

Training in progress, step 600 8 months ago
special_tokens_map.json

325 Bytes

Training in progress, step 200 8 months ago
tokenizer.json

9.09 MB

Training in progress, step 200 8 months ago
tokenizer_config.json

51 kB

Training in progress, step 200 8 months ago
training_args.bin
Detected Pickle imports (9)
- "torch.device",
- "accelerate.utils.dataclasses.DistributedType",
- "accelerate.state.PartialState",
- "transformers.training_args.TrainingArguments",
- "transformers.trainer_utils.HubStrategy",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_pt_utils.AcceleratorConfig"
How to fix it?
5.05 kB
LFS

Training in progress, step 200 8 months ago