|
--- |
|
license: mit |
|
base_model: roberta-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: roberta-base-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. --> |
|
|
|
# roberta-base-classification |
|
|
|
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: 1.8665 |
|
- Accuracy: {'accuracy': 0.7342799188640974} |
|
- F1: {'f1': 0.7306952447422118} |
|
|
|
## 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 | 163 | 1.3840 | {'accuracy': 0.6024340770791075} | {'f1': 0.5642145589948825} | |
|
| No log | 2.0 | 326 | 1.0832 | {'accuracy': 0.6511156186612576} | {'f1': 0.6334471187444455} | |
|
| No log | 3.0 | 489 | 1.0334 | {'accuracy': 0.6977687626774848} | {'f1': 0.6897630671623124} | |
|
| 1.0727 | 4.0 | 652 | 1.0970 | {'accuracy': 0.6876267748478702} | {'f1': 0.6871985325785717} | |
|
| 1.0727 | 5.0 | 815 | 1.0281 | {'accuracy': 0.7342799188640974} | {'f1': 0.7301024691928815} | |
|
| 1.0727 | 6.0 | 978 | 1.1807 | {'accuracy': 0.7018255578093306} | {'f1': 0.7067299604929954} | |
|
| 0.2589 | 7.0 | 1141 | 1.2407 | {'accuracy': 0.7342799188640974} | {'f1': 0.7314658348123809} | |
|
| 0.2589 | 8.0 | 1304 | 1.3048 | {'accuracy': 0.7403651115618661} | {'f1': 0.731151961567854} | |
|
| 0.2589 | 9.0 | 1467 | 1.5180 | {'accuracy': 0.718052738336714} | {'f1': 0.7137872411382804} | |
|
| 0.0808 | 10.0 | 1630 | 1.3989 | {'accuracy': 0.7606490872210954} | {'f1': 0.7557677624013166} | |
|
| 0.0808 | 11.0 | 1793 | 1.5029 | {'accuracy': 0.7606490872210954} | {'f1': 0.7552919114782913} | |
|
| 0.0808 | 12.0 | 1956 | 1.7512 | {'accuracy': 0.7241379310344828} | {'f1': 0.7171770258544846} | |
|
| 0.0186 | 13.0 | 2119 | 1.6777 | {'accuracy': 0.7363083164300203} | {'f1': 0.7298768119446929} | |
|
| 0.0186 | 14.0 | 2282 | 1.8128 | {'accuracy': 0.7363083164300203} | {'f1': 0.7328169574773649} | |
|
| 0.0186 | 15.0 | 2445 | 1.7922 | {'accuracy': 0.7383367139959433} | {'f1': 0.7355194715827496} | |
|
| 0.0039 | 16.0 | 2608 | 1.8762 | {'accuracy': 0.7281947261663286} | {'f1': 0.7221386387545444} | |
|
| 0.0039 | 17.0 | 2771 | 1.8840 | {'accuracy': 0.7363083164300203} | {'f1': 0.7317008958800432} | |
|
| 0.0039 | 18.0 | 2934 | 1.8368 | {'accuracy': 0.7383367139959433} | {'f1': 0.7340167563730315} | |
|
| 0.0027 | 19.0 | 3097 | 1.8687 | {'accuracy': 0.7363083164300203} | {'f1': 0.7319705371219094} | |
|
| 0.0027 | 20.0 | 3260 | 1.8665 | {'accuracy': 0.7342799188640974} | {'f1': 0.7306952447422118} | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.1 |
|
|