|
--- |
|
license: cc-by-4.0 |
|
base_model: Goader/liberta-large |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: liberta-large-topic_classification |
|
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. --> |
|
|
|
# liberta-large-topic_classification |
|
|
|
This model is a fine-tuned version of [Goader/liberta-large](https://huggingface.co/Goader/liberta-large) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7957 |
|
- Precision: 0.9167 |
|
- Recall: 0.8749 |
|
- F1: 0.8889 |
|
- Accuracy: 0.8971 |
|
|
|
## 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 88 | 0.7214 | 0.8294 | 0.7438 | 0.7532 | 0.7843 | |
|
| No log | 2.0 | 176 | 0.6388 | 0.8181 | 0.7797 | 0.7826 | 0.8088 | |
|
| No log | 3.0 | 264 | 0.8149 | 0.8625 | 0.8692 | 0.8617 | 0.8725 | |
|
| No log | 4.0 | 352 | 0.8210 | 0.9171 | 0.8603 | 0.8695 | 0.8824 | |
|
| No log | 5.0 | 440 | 0.7850 | 0.9173 | 0.8700 | 0.8841 | 0.8922 | |
|
| 0.3285 | 6.0 | 528 | 0.7936 | 0.8987 | 0.8670 | 0.8770 | 0.8824 | |
|
| 0.3285 | 7.0 | 616 | 0.7794 | 0.9217 | 0.8749 | 0.8913 | 0.8971 | |
|
| 0.3285 | 8.0 | 704 | 0.7835 | 0.9217 | 0.8749 | 0.8913 | 0.8971 | |
|
| 0.3285 | 9.0 | 792 | 0.7947 | 0.9167 | 0.8749 | 0.8889 | 0.8971 | |
|
| 0.3285 | 10.0 | 880 | 0.7957 | 0.9167 | 0.8749 | 0.8889 | 0.8971 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 1.11.0a0+17540c5 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.15.2 |
|
|
