burtenshaw
/

Qwen2-1.5B-GRPO-overlong

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions

Qwen2-1.5B-GRPO-overlong

3.1 GB

1 contributor

History: 5 commits

burtenshaw's picture

burtenshaw HF Staff

Training in progress, step 200

00e2ee0 verified 27 days ago

.gitattributes

1.57 kB

Training in progress, step 200 27 days ago
README.md

2.04 kB

Training in progress, step 200 27 days ago
added_tokens.json

80 Bytes

Training in progress, step 200 27 days ago
chat_template.jinja

328 Bytes

Training in progress, step 200 27 days ago
config.json

1.32 kB

Training in progress, step 200 27 days ago
merges.txt

1.67 MB

Training in progress, step 200 27 days ago
model.safetensors

3.09 GB
xet

Training in progress, step 200 27 days ago
special_tokens_map.json

367 Bytes

Training in progress, step 200 27 days ago
tokenizer.json

11.4 MB
xet

Training in progress, step 200 27 days ago
tokenizer_config.json

973 Bytes

Training in progress, step 200 27 days ago
training_args.bin
Detected Pickle imports (10)
- "transformers.trainer_utils.IntervalStrategy",
- "accelerate.state.PartialState",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.SchedulerType",
- "trl.internal.configs.GRPOConfig",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "torch.device",
- "transformers.trainer_utils.SaveStrategy"
How to fix it?
7.89 kB
xet

Training in progress, step 200 27 days ago
vocab.json

2.78 MB

Training in progress, step 200 27 days ago