---
base_model: mistralai/Mistral-7B-v0.1
library_name: peft
license: apache-2.0
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: ncis
  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. -->

[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/phdatdt/Fine%20tuning%20mistral%207B/runs/8lpu7o4v)
# ncis

This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8757
- Accuracy: 0.9320

## 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: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log        | 1.0   | 19   | 2.5491          | 0.6408   |
| No log        | 2.0   | 38   | 6.8450          | 0.5922   |
| No log        | 3.0   | 57   | 2.3423          | 0.7282   |
| No log        | 4.0   | 76   | 3.2814          | 0.6990   |
| No log        | 5.0   | 95   | 0.7817          | 0.9320   |
| No log        | 6.0   | 114  | 0.8577          | 0.9320   |
| No log        | 7.0   | 133  | 0.8714          | 0.9320   |
| No log        | 8.0   | 152  | 0.8742          | 0.9320   |
| No log        | 9.0   | 171  | 0.8755          | 0.9320   |
| No log        | 10.0  | 190  | 0.8757          | 0.9320   |


### Framework versions

- PEFT 0.11.1
- Transformers 4.42.4
- Pytorch 2.1.2
- Datasets 2.16.0
- Tokenizers 0.19.1