---
library_name: peft
base_model: peiyi9979/math-shepherd-mistral-7b-prm
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: v1_5_mistral_lora
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# v1_5_mistral_lora

This model is a fine-tuned version of [peiyi9979/math-shepherd-mistral-7b-prm](https://huggingface.co/peiyi9979/math-shepherd-mistral-7b-prm) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3143
- Accuracy: 0.8639
- Precision: 0.7383
- Recall: 0.7453
- F1: 0.7418

## 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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 765837
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- total_eval_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| No log        | 0      | 0    | 0.5958          | 0.7376   | 0.5       | 0.0660 | 0.1167 |
| 0.6808        | 0.0575 | 20   | 0.5704          | 0.7401   | 0.5385    | 0.0660 | 0.1176 |
| 0.4764        | 0.1149 | 40   | 0.4768          | 0.7574   | 0.5303    | 0.6604 | 0.5882 |
| 0.4099        | 0.1724 | 60   | 0.4052          | 0.8020   | 0.6275    | 0.6038 | 0.6154 |
| 0.346         | 0.2299 | 80   | 0.3761          | 0.8366   | 0.6961    | 0.6698 | 0.6827 |
| 0.2929        | 0.2874 | 100  | 0.3664          | 0.8366   | 0.6887    | 0.6887 | 0.6887 |
| 0.3822        | 0.3448 | 120  | 0.3551          | 0.8515   | 0.6983    | 0.7642 | 0.7297 |
| 0.3955        | 0.4023 | 140  | 0.3442          | 0.8589   | 0.7634    | 0.6698 | 0.7136 |
| 0.34          | 0.4598 | 160  | 0.3399          | 0.8614   | 0.7232    | 0.7642 | 0.7431 |
| 0.2897        | 0.5172 | 180  | 0.3244          | 0.8614   | 0.7404    | 0.7264 | 0.7333 |
| 0.2599        | 0.5747 | 200  | 0.3225          | 0.8639   | 0.7383    | 0.7453 | 0.7418 |
| 0.34          | 0.6322 | 220  | 0.3178          | 0.8688   | 0.7573    | 0.7358 | 0.7464 |
| 0.2969        | 0.6897 | 240  | 0.3178          | 0.8564   | 0.7222    | 0.7358 | 0.7290 |
| 0.3179        | 0.7471 | 260  | 0.3128          | 0.8663   | 0.7453    | 0.7453 | 0.7453 |
| 0.2901        | 0.8046 | 280  | 0.3146          | 0.8639   | 0.7383    | 0.7453 | 0.7418 |
| 0.2587        | 0.8621 | 300  | 0.3138          | 0.8639   | 0.7383    | 0.7453 | 0.7418 |
| 0.326         | 0.9195 | 320  | 0.3151          | 0.8589   | 0.7248    | 0.7453 | 0.7349 |
| 0.3475        | 0.9770 | 340  | 0.3143          | 0.8639   | 0.7383    | 0.7453 | 0.7418 |


### Framework versions

- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3