prm_conversations_math-l5-train-full-ref-mix_gpt-4o-mini_rm_best_of_16_with_ref_with_hint_all_full_solution_as_ref
This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the prm_conversations_math-l5-train-full-ref-mix_gpt-4o-mini_rm_best_of_16_with_ref_with_hint_all_full_solution_as_ref dataset. It achieves the following results on the evaluation set:
- Loss: 0.1171
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.1455 | 0.4877 | 500 | 0.1367 |
| 0.1229 | 0.9755 | 1000 | 0.1171 |
Framework versions
- Transformers 4.43.4
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 5
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.
Model tree for DongfuJiang/prm_math-l5_only
Base model
meta-llama/Llama-3.1-8B
Finetuned
meta-llama/Llama-3.1-8B-Instruct