Jforeverss
/

DeepSeek-R1-Distill-Qwen-1.5B-GRPO

Text Generation

Generated from Trainer

length-penalty-grpo

text-generation-inference

Model card Files Files and versions Community

DeepSeek-R1-Distill-Qwen-1.5B-GRPO

Ctrl+K

Ctrl+K

1 contributor

History: 30 commits

Jforeverss's picture

Training in progress, epoch 1

12a4d7e verified 1 day ago

.gitattributes

1.57 kB

Training in progress, step 1000 17 days ago
README.md

2.49 kB

End of training 6 days ago
all_results.json

199 Bytes

Model save 6 days ago
config.json

704 Bytes

Training in progress, epoch 1 1 day ago
generation_config.json

181 Bytes

Model save 16 days ago
model.safetensors

3.55 GB
LFS

Training in progress, epoch 1 1 day ago
special_tokens_map.json

485 Bytes

Training in progress, step 1000 17 days ago
tokenizer.json

11.4 MB
LFS

Training in progress, epoch 1 1 day ago
tokenizer_config.json

6.67 kB

Training in progress, step 1000 17 days ago
train_results.json

199 Bytes

Model save 6 days ago
trainer_state.json

2.31 MB

Model save 6 days ago
training_args.bin
Detected Pickle imports (14)
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
- "transformers.trainer_utils.HubStrategy",
- "transformers.integrations.deepspeed.HfDeepSpeedConfig",
- "torch.bfloat16",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.trainer_utils.SchedulerType",
- "transformers.training_args.OptimizerNames",
- "src.open_r1.configs.LengthPenaltyGRPOConfig",
- "transformers.trainer_utils.IntervalStrategy",
- "accelerate.state.PartialState",
- "transformers.trainer_utils.SaveStrategy",
- "torch.device"
How to fix it?
10.9 kB
LFS

Training in progress, epoch 1 1 day ago