- 1.57 kB Training in progress, step 200
- 267 Bytes Add metadata (#1)
- 605 Bytes Training in progress, step 200
- 172 Bytes Add checkpoint 600 post-trained on curated_rg_math
- 686 Bytes Training in progress, step 200
- 243 Bytes Add checkpoint 600 post-trained on curated_rg_math
- 1.67 MB Training in progress, step 200
- 4.96 GB Training in progress, step 600
- 1.84 GB Training in progress, step 600
- 35.6 kB Training in progress, step 200
- 497 Bytes Training in progress, step 200
- 11.4 MB Training in progress, step 200
- 6.86 kB Training in progress, step 200
- 172 Bytes Add checkpoint 600 post-trained on curated_rg_math
- 252 kB Add checkpoint 600 post-trained on curated_rg_math
training_args.bin Detected Pickle imports (14)
- "transformers.trainer_utils.SaveStrategy",
- "transformers.integrations.deepspeed.HfDeepSpeedConfig",
- "tina.post_train_hf.grpo_config.GRPOConfig",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "accelerate.state.PartialState",
- "transformers.trainer_utils.HubStrategy",
- "torch.bfloat16",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.SchedulerType",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
- "transformers.training_args.OptimizerNames",
- "torch.device"
How to fix it?
7.35 kB Training in progress, step 200 - 2.78 MB Training in progress, step 200
