LBK95
/

Llama-2-7b-hf-DPO-LookAhead5_FullEval_TTree1.4_TLoop0.7_TEval0.2_V2.0

Generated from Trainer

Model card Files Files and versions Community

Llama-2-7b-hf-DPO-LookAhead5_FullEval_TTree1.4_TLoop0.7_TEval0.2_V2.0

1 contributor

History: 5 commits

LBK95's picture

Training in progress, step 780

3e07d4c verified 20 days ago

.gitattributes

1.52 kB

initial commit 20 days ago
adapter_config.json

727 Bytes

Training in progress, step 195 20 days ago
adapter_model.safetensors

684 MB
LFS

Training in progress, step 780 20 days ago
added_tokens.json

51 Bytes

Training in progress, step 195 20 days ago
special_tokens_map.json

230 Bytes

Training in progress, step 195 20 days ago
tokenizer.json

1.84 MB

Training in progress, step 195 20 days ago
tokenizer.model

500 kB
LFS

Training in progress, step 195 20 days ago
tokenizer_config.json

1.64 kB

Training in progress, step 195 20 days ago
training_args.bin
Detected Pickle imports (10)
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.HubStrategy",
- "trl.trainer.dpo_config.FDivergenceType",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.training_args.OptimizerNames",
- "torch.device",
- "accelerate.state.PartialState",
- "trl.trainer.dpo_config.DPOConfig",
- "transformers.trainer_utils.SchedulerType"
How to fix it?
6.01 kB
LFS

Training in progress, step 195 20 days ago