PhilSad
/

lucie-7b-GRPO-science-long-thinking-step2-boxed-accuracy

Model card Files Files and versions

lucie-7b-GRPO-science-long-thinking-step2-boxed-accuracy

Ctrl+K

Ctrl+K

1 contributor

History: 146 commits

PhilSad's picture

Training in progress, step 920

6476f5a verified 3 months ago

.gitattributes

1.52 kB

initial commit 3 months ago
adapter_config.json

786 Bytes

Training in progress, step 10 3 months ago
adapter_model.safetensors

13.6 MB
xet

Training in progress, step 920 3 months ago
chat_template.jinja

284 Bytes

Training in progress, step 10 3 months ago
special_tokens_map.json

659 Bytes

Training in progress, step 10 3 months ago
tokenizer.json

4.67 MB

Training in progress, step 10 3 months ago
tokenizer_config.json

1.84 kB

Training in progress, step 10 3 months ago
training_args.bin
Detected Pickle imports (10)
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "trl.trainer.grpo_config.GRPOConfig",
- "torch.device",
- "transformers.trainer_utils.IntervalStrategy",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_utils.SaveStrategy",
- "transformers.trainer_utils.SchedulerType",
- "accelerate.state.PartialState"
How to fix it?
6.87 kB
xet

Training in progress, step 10 3 months ago