Model save
d56ab9e
verified
-
checkpoint
Model save
-
grpo_saved_lora
Training in progress, step 253
-
1.57 kB
Training in progress, step 2
-
2.32 kB
Model save
-
874 Bytes
Training in progress, step 253
-
323 MB
Training in progress, step 253
-
605 Bytes
Training in progress, step 2
-
663 Bytes
Upload config.json
-
1.67 MB
Training in progress, step 2
-
614 Bytes
Training in progress, step 2
-
11.4 MB
Training in progress, step 2
-
7.36 kB
Training in progress, step 2
training_args.bin
Detected Pickle imports (10)
- "UnslothGRPOTrainer.UnslothGRPOConfig",
- "torch.device",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.state.PartialState",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.SaveStrategy",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.trainer_utils.IntervalStrategy"
How to fix it?
5.94 kB
Training in progress, step 253
-
2.78 MB
Training in progress, step 2