|
--- |
|
license: mit |
|
base_model: roberta-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: roberta-base-topic_classification_simple |
|
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. --> |
|
|
|
# roberta-base-topic_classification_simple |
|
|
|
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: 1.3253 |
|
- Accuracy: {'accuracy': 0.8445839874411303} |
|
- F1: {'f1': 0.8435559601445874} |
|
|
|
## 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: 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: 20 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------------------------------:|:--------------------------:| |
|
| No log | 1.0 | 353 | 0.6772 | {'accuracy': 0.7905359946176272} | {'f1': 0.7881026657042776} | |
|
| 0.8304 | 2.0 | 706 | 0.6028 | {'accuracy': 0.8187934514465127} | {'f1': 0.8207294945978928} | |
|
| 0.3839 | 3.0 | 1059 | 0.5942 | {'accuracy': 0.8344920385736713} | {'f1': 0.8333019225828988} | |
|
| 0.3839 | 4.0 | 1412 | 0.6904 | {'accuracy': 0.8340435075128952} | {'f1': 0.8330992428789376} | |
|
| 0.2015 | 5.0 | 1765 | 0.8314 | {'accuracy': 0.8264184794797039} | {'f1': 0.82429813311833} | |
|
| 0.118 | 6.0 | 2118 | 0.8572 | {'accuracy': 0.8356133662256111} | {'f1': 0.8349736274018552} | |
|
| 0.118 | 7.0 | 2471 | 0.9742 | {'accuracy': 0.8383045525902669} | {'f1': 0.8376600364979794} | |
|
| 0.0804 | 8.0 | 2824 | 1.0628 | {'accuracy': 0.8333707109217313} | {'f1': 0.8313400577604307} | |
|
| 0.0508 | 9.0 | 3177 | 1.0866 | {'accuracy': 0.8333707109217313} | {'f1': 0.832415418717587} | |
|
| 0.0406 | 10.0 | 3530 | 1.1633 | {'accuracy': 0.8432383942588024} | {'f1': 0.8425868379595812} | |
|
| 0.0406 | 11.0 | 3883 | 1.2132 | {'accuracy': 0.8400986768333707} | {'f1': 0.8388873470699977} | |
|
| 0.0245 | 12.0 | 4236 | 1.2799 | {'accuracy': 0.836958959407939} | {'f1': 0.8378019487138132} | |
|
| 0.0139 | 13.0 | 4589 | 1.2379 | {'accuracy': 0.8434626597891904} | {'f1': 0.8429633731503271} | |
|
| 0.0139 | 14.0 | 4942 | 1.2578 | {'accuracy': 0.8445839874411303} | {'f1': 0.8439974594663667} | |
|
| 0.014 | 15.0 | 5295 | 1.3392 | {'accuracy': 0.8407714734245346} | {'f1': 0.8405188286141088} | |
|
| 0.0111 | 16.0 | 5648 | 1.2977 | {'accuracy': 0.8443597219107423} | {'f1': 0.8438293082262649} | |
|
| 0.0099 | 17.0 | 6001 | 1.3405 | {'accuracy': 0.8412200044853106} | {'f1': 0.8400992068548403} | |
|
| 0.0099 | 18.0 | 6354 | 1.3433 | {'accuracy': 0.8405472078941467} | {'f1': 0.839917724407298} | |
|
| 0.0041 | 19.0 | 6707 | 1.3269 | {'accuracy': 0.8445839874411303} | {'f1': 0.8434224071770644} | |
|
| 0.0041 | 20.0 | 7060 | 1.3253 | {'accuracy': 0.8445839874411303} | {'f1': 0.8435559601445874} | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.1 |
|
|