---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
datasets:
- generator
base_model: mistralai/Mistral-7B-Instruct-v0.1
model-index:
- name: mistral_instruct_generation
  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_instruct_generation

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 generator dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3268

## 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: 0.0002
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 0.03
- training_steps: 200
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.4515        | 0.0   | 20   | 1.3677          |
| 1.4001        | 0.0   | 40   | 1.3462          |
| 1.4109        | 0.01  | 60   | 1.3316          |
| 1.3631        | 0.01  | 80   | 1.3256          |
| 1.3463        | 0.01  | 100  | 1.3231          |
| 1.3541        | 0.01  | 120  | 1.3173          |
| 1.3072        | 0.01  | 140  | 1.3156          |
| 1.2798        | 0.02  | 160  | 1.3114          |
| 1.3276        | 0.02  | 180  | 1.3143          |
| 1.2681        | 0.02  | 200  | 1.3268          |


### Framework versions

- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2