---
license: apache-2.0
base_model: mistralai/Mistral-7B-Instruct-v0.1
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: v1_750_STEPS_1e5_SFT_SFT
  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. -->

# v1_750_STEPS_1e5_SFT_SFT

This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3202

## 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: 1e-05
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 750

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.4004        | 0.05  | 50   | 0.4035          |
| 0.3957        | 0.1   | 100  | 0.4218          |
| 0.4288        | 0.15  | 150  | 0.4015          |
| 0.4599        | 0.2   | 200  | 0.3914          |
| 0.3886        | 0.24  | 250  | 0.3879          |
| 0.3968        | 0.29  | 300  | 0.3768          |
| 0.3678        | 0.34  | 350  | 0.3688          |
| 0.3559        | 0.39  | 400  | 0.3574          |
| 0.3606        | 0.44  | 450  | 0.3467          |
| 0.3473        | 0.49  | 500  | 0.3384          |
| 0.3278        | 0.54  | 550  | 0.3308          |
| 0.3294        | 0.59  | 600  | 0.3248          |
| 0.314         | 0.64  | 650  | 0.3214          |
| 0.3049        | 0.68  | 700  | 0.3202          |
| 0.3119        | 0.73  | 750  | 0.3202          |


### Framework versions

- Transformers 4.39.3
- Pytorch 2.0.0+cu117
- Datasets 2.18.0
- Tokenizers 0.15.2