---
library_name: peft
tags:
- generated_from_trainer
base_model: NousResearch/Llama-2-7b-hf
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: llama-2-ner
  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. -->

# llama-2-ner

This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1035
- Precision: 0.4928
- Recall: 0.5368
- F1: 0.5139
- Accuracy: 0.9789

## 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: 0.0009
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| No log        | 1.0   | 39   | 0.1204          | 0.5       | 0.0789 | 0.1364 | 0.9683   |
| No log        | 2.0   | 78   | 0.1100          | 0.2753    | 0.3579 | 0.3112 | 0.9658   |
| No log        | 3.0   | 117  | 0.0880          | 0.3853    | 0.2211 | 0.2809 | 0.9725   |
| No log        | 4.0   | 156  | 0.0716          | 0.3981    | 0.4526 | 0.4236 | 0.9756   |
| No log        | 5.0   | 195  | 0.0743          | 0.5023    | 0.5842 | 0.5401 | 0.9763   |
| No log        | 6.0   | 234  | 0.1021          | 0.5062    | 0.6474 | 0.5681 | 0.9781   |
| No log        | 7.0   | 273  | 0.1022          | 0.5094    | 0.5684 | 0.5373 | 0.9783   |
| No log        | 8.0   | 312  | 0.1035          | 0.4928    | 0.5368 | 0.5139 | 0.9789   |


### Framework versions

- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.2.2+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1