---
library_name: peft
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
base_model: NousResearch/Llama-2-7b-hf
model-index:
- name: billm-llama-7b-conll03-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. -->

# billm-llama-7b-conll03-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: 0.1894
- Precision: 0.9228
- Recall: 0.9364
- F1: 0.9296
- Accuracy: 0.9861

## 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
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.0453        | 1.0   | 1756  | 0.1025          | 0.9064    | 0.9227 | 0.9145 | 0.9836   |
| 0.0204        | 2.0   | 3512  | 0.0932          | 0.9187    | 0.9258 | 0.9222 | 0.9846   |
| 0.0105        | 3.0   | 5268  | 0.1267          | 0.9183    | 0.9308 | 0.9245 | 0.9855   |
| 0.0039        | 4.0   | 7024  | 0.1680          | 0.9213    | 0.9384 | 0.9298 | 0.9861   |
| 0.0014        | 5.0   | 8780  | 0.1761          | 0.9228    | 0.9366 | 0.9297 | 0.9861   |
| 0.0008        | 6.0   | 10536 | 0.1835          | 0.9228    | 0.9361 | 0.9294 | 0.9861   |
| 0.0005        | 7.0   | 12292 | 0.1880          | 0.9233    | 0.9363 | 0.9297 | 0.9861   |
| 0.0003        | 8.0   | 14048 | 0.1893          | 0.9230    | 0.9368 | 0.9298 | 0.9861   |
| 0.0003        | 9.0   | 15804 | 0.1895          | 0.9228    | 0.9364 | 0.9296 | 0.9861   |
| 0.0002        | 10.0  | 17560 | 0.1894          | 0.9228    | 0.9364 | 0.9296 | 0.9861   |


### Framework versions

- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.0.1
- Datasets 2.16.0
- Tokenizers 0.15.0