LBK95
/

Llama-3.2-1B-hf-DPO-LookAhead-5_TTree1.2_TT0.9_TP0.7_TE0.2_V10

Generated from Trainer

Model card Files Files and versions

Llama-3.2-1B-hf-DPO-LookAhead-5_TTree1.2_TT0.9_TP0.7_TE0.2_V10

62.4 MB

1 contributor

History: 5 commits

LBK95's picture

Training in progress, step 2757

07bcabe verified 18 days ago

.gitattributes

1.57 kB

Training in progress, step 690 18 days ago
adapter_config.json

856 Bytes

Training in progress, step 690 18 days ago
adapter_model.safetensors

45.1 MB
xet

Training in progress, step 2757 18 days ago
special_tokens_map.json

335 Bytes

Training in progress, step 690 18 days ago
tokenizer.json

17.2 MB
xet

Training in progress, step 690 18 days ago
tokenizer_config.json

50.9 kB

Training in progress, step 690 18 days ago
training_args.bin
Detected Pickle imports (10)
- "trl.trainer.dpo_config.DPOConfig",
- "transformers.trainer_utils.SchedulerType",
- "accelerate.state.PartialState",
- "torch.device",
- "trl.trainer.dpo_config.FDivergenceType",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.HubStrategy"
How to fix it?
6.48 kB
xet

Training in progress, step 690 18 days ago