---
license: apache-2.0
base_model: mistralai/Mistral-7B-Instruct-v0.2
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: Summary_M2_1000steps_1e7rate_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. -->

# Summary_M2_1000steps_1e7rate_SFT

This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0066

## 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-07
- 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: 1000

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.0146        | 0.2   | 50   | 1.9694          |
| 1.3853        | 0.4   | 100  | 1.2809          |
| 0.139         | 0.6   | 150  | 0.0635          |
| 0.01          | 0.8   | 200  | 0.0086          |
| 0.0075        | 1.0   | 250  | 0.0075          |
| 0.0073        | 1.2   | 300  | 0.0073          |
| 0.0072        | 1.4   | 350  | 0.0071          |
| 0.0071        | 1.6   | 400  | 0.0070          |
| 0.0069        | 1.8   | 450  | 0.0069          |
| 0.0068        | 2.0   | 500  | 0.0068          |
| 0.0067        | 2.2   | 550  | 0.0067          |
| 0.0067        | 2.4   | 600  | 0.0067          |
| 0.0066        | 2.6   | 650  | 0.0067          |
| 0.0066        | 2.8   | 700  | 0.0066          |
| 0.0066        | 3.0   | 750  | 0.0066          |
| 0.0066        | 3.2   | 800  | 0.0066          |
| 0.0066        | 3.4   | 850  | 0.0066          |
| 0.0066        | 3.6   | 900  | 0.0066          |
| 0.0066        | 3.8   | 950  | 0.0066          |
| 0.0066        | 4.0   | 1000 | 0.0066          |


### Framework versions

- Transformers 4.41.2
- Pytorch 2.0.0+cu117
- Datasets 2.19.2
- Tokenizers 0.19.1