---
library_name: peft
license: apache-2.0
base_model: mistralai/Mistral-7B-Instruct-v0.1
tags:
- generated_from_trainer
metrics:
- bleu
- f1
model-index:
- name: Mistral-7B-v0.1_AviationQA
  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-v0.1_AviationQA

This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 4.8939
- Bleu: 0.4256
- F1: 0.9813

## 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: 2
- eval_batch_size: 3
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 5

### Training results

| Training Loss | Epoch | Step | Validation Loss | Bleu   | F1     |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
| 6.5778        | 1.0   | 25   | 4.9328          | 0.2183 | 0.9821 |
| 4.9001        | 2.0   | 50   | 4.8955          | 0.3297 | 0.9820 |
| 4.8728        | 3.0   | 75   | 4.8911          | 0.4116 | 0.9816 |
| 4.8634        | 4.0   | 100  | 4.8931          | 0.4004 | 0.9813 |
| 4.8598        | 5.0   | 125  | 4.8939          | 0.4256 | 0.9813 |


### Framework versions

- PEFT 0.14.0
- Transformers 4.49.0
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0