---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: mistralai/Mistral-7B-Instruct-v0.2
datasets:
- generator
model-index:
- name: Mistral_Sentiment_Classification_2024-06-02
  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_Sentiment_Classification_2024-06-02

This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3000

## 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: 2.5e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.03
- num_epochs: 5

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.4414        | 0.1126 | 100  | 0.3360          |
| 0.3434        | 0.2252 | 200  | 0.3211          |
| 0.3107        | 0.3378 | 300  | 0.3150          |
| 0.3306        | 0.4505 | 400  | 0.3103          |
| 0.3087        | 0.5631 | 500  | 0.3071          |
| 0.3226        | 0.6757 | 600  | 0.3044          |
| 0.3091        | 0.7883 | 700  | 0.3021          |
| 0.3277        | 0.9009 | 800  | 0.3004          |
| 0.3068        | 1.0135 | 900  | 0.2991          |
| 0.295         | 1.1261 | 1000 | 0.2981          |
| 0.2844        | 1.2387 | 1100 | 0.2964          |
| 0.2885        | 1.3514 | 1200 | 0.2949          |
| 0.3047        | 1.4640 | 1300 | 0.2938          |
| 0.2985        | 1.5766 | 1400 | 0.2929          |
| 0.2792        | 1.6892 | 1500 | 0.2922          |
| 0.2739        | 1.8018 | 1600 | 0.2906          |
| 0.2757        | 1.9144 | 1700 | 0.2897          |
| 0.2632        | 2.0270 | 1800 | 0.2920          |
| 0.2707        | 2.1396 | 1900 | 0.2927          |
| 0.2615        | 2.2523 | 2000 | 0.2919          |
| 0.2428        | 2.3649 | 2100 | 0.2913          |
| 0.2614        | 2.4775 | 2200 | 0.2908          |
| 0.2661        | 2.5901 | 2300 | 0.2904          |
| 0.2711        | 2.7027 | 2400 | 0.2900          |
| 0.2566        | 2.8153 | 2500 | 0.2888          |
| 0.252         | 2.9279 | 2600 | 0.2884          |
| 0.2623        | 3.0405 | 2700 | 0.2927          |
| 0.2222        | 3.1532 | 2800 | 0.2942          |
| 0.2446        | 3.2658 | 2900 | 0.2943          |
| 0.2281        | 3.3784 | 3000 | 0.2942          |
| 0.2284        | 3.4910 | 3100 | 0.2942          |
| 0.2282        | 3.6036 | 3200 | 0.2937          |
| 0.2218        | 3.7162 | 3300 | 0.2939          |
| 0.2531        | 3.8288 | 3400 | 0.2919          |
| 0.2396        | 3.9414 | 3500 | 0.2922          |
| 0.2261        | 4.0541 | 3600 | 0.2989          |
| 0.2202        | 4.1667 | 3700 | 0.3000          |
| 0.2085        | 4.2793 | 3800 | 0.3001          |
| 0.2132        | 4.3919 | 3900 | 0.3001          |
| 0.2119        | 4.5045 | 4000 | 0.3005          |
| 0.2285        | 4.6171 | 4100 | 0.2999          |
| 0.2053        | 4.7297 | 4200 | 0.3003          |
| 0.2097        | 4.8423 | 4300 | 0.3005          |
| 0.2273        | 4.9550 | 4400 | 0.3000          |


### Framework versions

- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1