---
library_name: peft
license: apache-2.0
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
tags:
- generated_from_trainer
model-index:
- name: XPFaculty-ft
  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. -->

# XPFaculty-ft

This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2620

## 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: 3
- eval_batch_size: 3
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 12
- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 7
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 10.0354       | 1.0   | 25   | 2.1524          |
| 8.0146        | 2.0   | 50   | 1.7660          |
| 6.243         | 3.0   | 75   | 1.3734          |
| 5.268         | 4.0   | 100  | 1.2929          |
| 5.0111        | 5.0   | 125  | 1.2709          |
| 4.8748        | 6.0   | 150  | 1.2624          |
| 4.8125        | 7.0   | 175  | 1.2620          |


### Framework versions

- PEFT 0.14.0
- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0