---
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
tags:
- generated_from_trainer
model-index:
- name: Mistral_CN_pretrain
  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_CN_pretrain

This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3577

## 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 250

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.6683        | 0.28  | 10   | 1.9046          |
| 1.6163        | 0.56  | 20   | 1.4504          |
| 1.4282        | 0.83  | 30   | 1.3945          |
| 1.3711        | 1.11  | 40   | 1.3662          |
| 1.3638        | 1.39  | 50   | 1.3578          |
| 1.3366        | 1.67  | 60   | 1.3611          |
| 1.3283        | 1.94  | 70   | 1.3405          |
| 1.322         | 2.22  | 80   | 1.3464          |
| 1.3165        | 2.5   | 90   | 1.3409          |
| 1.304         | 2.78  | 100  | 1.3355          |
| 1.3067        | 3.06  | 110  | 1.3495          |
| 1.2947        | 3.33  | 120  | 1.3337          |
| 1.2883        | 3.61  | 130  | 1.3396          |
| 1.2965        | 3.89  | 140  | 1.3391          |
| 1.2756        | 4.17  | 150  | 1.3404          |
| 1.265         | 4.44  | 160  | 1.3405          |
| 1.2801        | 4.72  | 170  | 1.3407          |
| 1.2661        | 5.0   | 180  | 1.3325          |
| 1.2489        | 5.28  | 190  | 1.3515          |
| 1.2529        | 5.56  | 200  | 1.3461          |
| 1.2576        | 5.83  | 210  | 1.3524          |
| 1.2512        | 6.11  | 220  | 1.3476          |
| 1.2358        | 6.39  | 230  | 1.3607          |
| 1.2469        | 6.67  | 240  | 1.3618          |
| 1.2341        | 6.94  | 250  | 1.3577          |


### Framework versions

- Transformers 4.39.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2