trl-lib
/

Qwen2-0.5B-Reward-Math-Sheperd

Token Classification

Generated from Trainer

stepwise-reward-trainer

text-generation-inference

Model card Files Files and versions

Metrics Training metrics Community

Qwen2-0.5B-Reward-Math-Sheperd

1.99 GB

1 contributor

History: 14 commits

qgallouedec's picture

qgallouedec HF Staff

Training in progress, step 6500

4bf2479 verified 10 months ago

runs
Training in progress, step 6500 10 months ago
.gitattributes

1.57 kB

Training in progress, step 500 10 months ago
added_tokens.json

80 Bytes

Training in progress, step 500 10 months ago
config.json

757 Bytes

Training in progress, step 500 10 months ago
merges.txt

1.67 MB

Training in progress, step 500 10 months ago
model.safetensors

1.98 GB
xet

Training in progress, step 6500 10 months ago
special_tokens_map.json

370 Bytes

Training in progress, step 500 10 months ago
tokenizer.json

11.4 MB
xet

Training in progress, step 500 10 months ago
tokenizer_config.json

1.3 kB

Training in progress, step 500 10 months ago
training_args.bin
Detected Pickle imports (9)
- "trl.trainer.stepwise_reward_config.StepwiseRewardConfig",
- "transformers.trainer_utils.IntervalStrategy",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.trainer_utils.SchedulerType",
- "transformers.training_args.OptimizerNames",
- "accelerate.state.PartialState",
- "torch.device",
- "transformers.trainer_utils.HubStrategy"
How to fix it?
5.5 kB
xet

Training in progress, step 500 10 months ago
vocab.json

2.78 MB

Training in progress, step 500 10 months ago