Add model card
f64a9ab verified - final_model Model save
- 1.63 kB Model save
- 1.58 kB Add model card
- 874 Bytes Training in progress, step 185
- 361 MB Training in progress, step 185
- 707 Bytes Training in progress, step 500
- 4.12 kB Training in progress, step 500
- 727 Bytes Merged SFT + LoRA model for MCQA tasks
- 117 Bytes Merged SFT + LoRA model for MCQA tasks
- 1.67 MB Training in progress, step 500
- 1.19 GB Merged SFT + LoRA model for MCQA tasks
- 616 Bytes Merged SFT + LoRA model for MCQA tasks
- 11.4 MB Training in progress, step 500
- 5.43 kB Merged SFT + LoRA model for MCQA tasks
training_args.bin Detected Pickle imports (10)
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.trainer_utils.IntervalStrategy",
- "accelerate.state.PartialState",
- "accelerate.utils.dataclasses.DistributedType",
- "torch.device",
- "transformers.training_args.TrainingArguments",
- "transformers.trainer_utils.SaveStrategy",
- "transformers.trainer_utils.SchedulerType",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.HubStrategy"
How to fix it?
5.78 kB Training in progress, step 185 - 2.78 MB Training in progress, step 500
