---
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: mistralai/Mistral-7B-v0.1
metrics:
- accuracy
- precision
- recall
model-index:
- name: Mistral_7B_Fact_U
  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. -->

# Mistral_7B_Fact_U

This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6060
- Accuracy: 0.7941
- Precision: 0.8486
- Recall: 0.7353
- F1 score: 0.7879

## 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: 0.0001
- train_batch_size: 8
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5

### Training results

| Training Loss | Epoch  | Step | Accuracy | F1 score | Precision | Recall | Validation Loss |
|:-------------:|:------:|:----:|:--------:|:--------:|:---------:|:------:|:---------------:|
| 1.4759        | 0.2509 | 200  | 0.6494   | 0.6674   | 0.6586    | 0.6765 | 1.2749          |
| 1.033         | 0.5019 | 400  | 0.6682   | 0.5841   | 0.8390    | 0.4480 | 1.1062          |
| 0.8323        | 0.7528 | 600  | 0.7094   | 0.7487   | 0.6802    | 0.8326 | 0.6781          |
| 0.6895        | 1.0038 | 800  | 0.9914   | 0.7529   | 0.9113    | 0.5814 | 0.7099          |
| 0.5692        | 1.2547 | 1000 | 0.5985   | 0.7741   | 0.7962    | 0.7602 | 0.7778          |
| 0.5514        | 1.5056 | 1200 | 0.6206   | 0.7259   | 0.6961    | 0.8394 | 0.7610          |
| 0.5011        | 1.7566 | 1400 | 0.5612   | 0.7835   | 0.8377    | 0.7240 | 0.7767          |
| 0.4772        | 2.0075 | 1600 | 0.7216   | 0.7482   | 0.7446    | 0.7851 | 0.7643          |
| 0.4001        | 2.2585 | 1800 | 0.8057   | 0.7106   | 0.6782    | 0.8439 | 0.7520          |
| 0.3915        | 2.5094 | 2000 | 0.6729   | 0.7706   | 0.7800    | 0.7783 | 0.7792          |
| 0.3691        | 2.7604 | 2200 | 0.6833   | 0.7624   | 0.7679    | 0.7783 | 0.7730          |
| 0.387         | 3.0113 | 2400 | 0.6916   | 0.7529   | 0.7489    | 0.7896 | 0.7687          |
| 0.2261        | 3.2622 | 2600 | 1.2210   | 0.7988   | 0.8575    | 0.7353 | 0.7917          |
| 0.236         | 3.5132 | 2800 | 1.0130   | 0.7965   | 0.8645    | 0.7217 | 0.7867          |
| 0.2332        | 3.7641 | 3000 | 1.3376   | 0.7412   | 0.7229    | 0.8145 | 0.7660          |
| 0.2334        | 4.0151 | 3200 | 1.2199   | 0.7847   | 0.8381    | 0.7262 | 0.7782          |
| 0.1039        | 4.2660 | 3400 | 1.4260   | 0.7941   | 0.8380    | 0.7489 | 0.7909          |
| 0.0987        | 4.5169 | 3600 | 1.5102   | 0.7706   | 0.7839    | 0.7715 | 0.7777          |
| 0.0887        | 4.7679 | 3800 | 1.6060   | 0.7941   | 0.8486    | 0.7353 | 0.7879          |


### Framework versions

- PEFT 0.11.1
- Transformers 4.44.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1