od2961
/

Llama-8B-Open-R1-GRPO-math-v1

Model card Files Files and versions

Llama-8B-Open-R1-GRPO-math-v1

17.3 MB

Ctrl+K

Ctrl+K

1 contributor

History: 2 commits

od2961's picture

Training in progress, step 100

8449007 verified 8 months ago

.gitattributes

1.57 kB
Training in progress, step 100 8 months ago
config.json

936 Bytes
Training in progress, step 100 8 months ago
special_tokens_map.json

325 Bytes
Training in progress, step 100 8 months ago
tokenizer.json

17.2 MB
xet

Training in progress, step 100 8 months ago
tokenizer_config.json

55.4 kB
Training in progress, step 100 8 months ago
training_args.bin
Detected Pickle imports (14)
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.integrations.deepspeed.HfDeepSpeedConfig",
- "accelerate.state.PartialState",
- "transformers.trainer_utils.HubStrategy",
- "open_r1.configs.GRPOConfig",
- "torch.bfloat16",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.SchedulerType",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "torch.device",
- "transformers.trainer_utils.SaveStrategy",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig"
How to fix it?
10.2 kB
xet

Training in progress, step 100 8 months ago