|
--- |
|
license: mit |
|
base_model: roberta-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: Llama3-q4_k_m |
|
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. --> |
|
|
|
# Llama3-q4_k_m |
|
|
|
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0938 |
|
- Accuracy: 0.9825 |
|
- F1: 0.9827 |
|
|
|
## 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: 5e-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: 8 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| 0.3823 | 1.0 | 129 | 0.1932 | 0.9532 | 0.9535 | |
|
| 0.1585 | 2.0 | 258 | 0.3872 | 0.8977 | 0.9057 | |
|
| 0.3048 | 3.0 | 387 | 0.1816 | 0.9474 | 0.9477 | |
|
| 0.2353 | 4.0 | 516 | 0.1817 | 0.9591 | 0.9605 | |
|
| 0.2928 | 5.0 | 645 | 0.2058 | 0.9503 | 0.9524 | |
|
| 0.2452 | 6.0 | 774 | 0.1246 | 0.9737 | 0.9742 | |
|
| 0.348 | 7.0 | 903 | 0.0932 | 0.9825 | 0.9827 | |
|
| 0.1316 | 8.0 | 1032 | 0.0938 | 0.9825 | 0.9827 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.2 |
|
- Tokenizers 0.19.1 |
|
|
