---
library_name: transformers
license: apache-2.0
base_model: mistralai/Mistral-7B-Instruct-v0.2
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: IE_M2_1000steps_1e5rate_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. -->

# IE_M2_1000steps_1e5rate_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: 2.3766

## 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: 1000

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.3716        | 0.4   | 50   | 1.4602          |
| 1.5169        | 0.8   | 100  | 1.5011          |
| 0.966         | 1.2   | 150  | 1.6278          |
| 1.0177        | 1.6   | 200  | 1.6570          |
| 1.0172        | 2.0   | 250  | 1.5973          |
| 0.4143        | 2.4   | 300  | 1.8360          |
| 0.3924        | 2.8   | 350  | 1.8596          |
| 0.18          | 3.2   | 400  | 1.9868          |
| 0.2024        | 3.6   | 450  | 1.9613          |
| 0.1845        | 4.0   | 500  | 2.0203          |
| 0.082         | 4.4   | 550  | 2.1891          |
| 0.0848        | 4.8   | 600  | 2.1597          |
| 0.0384        | 5.2   | 650  | 2.1956          |
| 0.0371        | 5.6   | 700  | 2.2413          |
| 0.0369        | 6.0   | 750  | 2.2445          |
| 0.024         | 6.4   | 800  | 2.3157          |
| 0.0197        | 6.8   | 850  | 2.3503          |
| 0.0156        | 7.2   | 900  | 2.3690          |
| 0.0151        | 7.6   | 950  | 2.3765          |
| 0.0155        | 8.0   | 1000 | 2.3766          |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.0.0+cu117
- Datasets 3.0.0
- Tokenizers 0.19.1