|
--- |
|
library_name: transformers |
|
base_model: afmck/testing-llama-tiny |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: llma-finetuned-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. --> |
|
|
|
# llma-finetuned-ner |
|
|
|
This model is a fine-tuned version of [afmck/testing-llama-tiny](https://huggingface.co/afmck/testing-llama-tiny) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1003 |
|
- Precision: 0.9755 |
|
- Recall: 0.9764 |
|
- F1: 0.9759 |
|
- Accuracy: 0.9815 |
|
|
|
## 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: 2e-05 |
|
- 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: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.0726 | 1.0 | 5285 | 0.1305 | 0.9820 | 0.9672 | 0.9745 | 0.9749 | |
|
| 0.0558 | 2.0 | 10570 | 0.1090 | 0.9733 | 0.9740 | 0.9737 | 0.9796 | |
|
| 0.07 | 3.0 | 15855 | 0.1003 | 0.9755 | 0.9764 | 0.9759 | 0.9815 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.19.1 |
|
|
