--- license: other base_model: meta-llama/Meta-Llama-3.1-8B-Instruct tags: - llama-factory - full - generated_from_trainer model-index: - name: prm_conversations_math-l5-train-full-ref-mix_gpt-4o-mini_rm_best_of_16_with_ref_with_hint_all_full_solution_as_ref results: [] --- # 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](https://huggingface.co/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