Seongyun
/

DeepSeek-R1-Distill-Qwen-1.5B-GRPO_mcqa_repetition_penalty

Model card Files Files and versions Community

DeepSeek-R1-Distill-Qwen-1.5B-GRPO_mcqa_repetition_penalty

1 contributor

History: 2 commits

Seongyun's picture

Training in progress, step 1000

31438e5 verified 19 days ago

.gitattributes

1.57 kB

Training in progress, step 1000 19 days ago
config.json

768 Bytes

Training in progress, step 1000 19 days ago
model.safetensors

3.55 GB
LFS

Training in progress, step 1000 19 days ago
special_tokens_map.json

485 Bytes

Training in progress, step 1000 19 days ago
tokenizer.json

11.4 MB
LFS

Training in progress, step 1000 19 days ago
tokenizer_config.json

6.67 kB

Training in progress, step 1000 19 days ago
training_args.bin
Detected Pickle imports (14)
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.state.PartialState",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "transformers.integrations.deepspeed.HfDeepSpeedConfig",
- "torch.device",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "accelerate.utils.dataclasses.DistributedType",
- "open_r1.configs.GRPOConfig",
- "torch.bfloat16",
- "transformers.training_args.OptimizerNames",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
- "transformers.trainer_utils.SaveStrategy"
How to fix it?
10.3 kB
LFS

Training in progress, step 1000 19 days ago