|
--- |
|
license: mit |
|
base_model: roberta-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: roberta_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_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: 1.2731 |
|
- Accuracy: {'accuracy': 0.8465909090909091} |
|
- F1: {'f1': 0.8396445042099528} |
|
|
|
## 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 | 263 | 1.1741 | {'accuracy': 0.6363636363636364} | {'f1': 0.6202787331893512} | |
|
| 1.181 | 2.0 | 526 | 0.9322 | {'accuracy': 0.7386363636363636} | {'f1': 0.7177199655598837} | |
|
| 1.181 | 3.0 | 789 | 0.7835 | {'accuracy': 0.7727272727272727} | {'f1': 0.7657783584890875} | |
|
| 0.3689 | 4.0 | 1052 | 0.8597 | {'accuracy': 0.7727272727272727} | {'f1': 0.768360357103512} | |
|
| 0.3689 | 5.0 | 1315 | 0.7560 | {'accuracy': 0.8125} | {'f1': 0.8031513875852524} | |
|
| 0.165 | 6.0 | 1578 | 0.7579 | {'accuracy': 0.8200757575757576} | {'f1': 0.8142845258630059} | |
|
| 0.165 | 7.0 | 1841 | 0.8900 | {'accuracy': 0.8352272727272727} | {'f1': 0.8316422201059607} | |
|
| 0.0778 | 8.0 | 2104 | 0.9315 | {'accuracy': 0.8295454545454546} | {'f1': 0.825285136658407} | |
|
| 0.0778 | 9.0 | 2367 | 1.1370 | {'accuracy': 0.8181818181818182} | {'f1': 0.8091288762824846} | |
|
| 0.0335 | 10.0 | 2630 | 1.0799 | {'accuracy': 0.8465909090909091} | {'f1': 0.841700330957688} | |
|
| 0.0335 | 11.0 | 2893 | 1.2487 | {'accuracy': 0.8314393939393939} | {'f1': 0.8269815181159639} | |
|
| 0.0162 | 12.0 | 3156 | 1.2194 | {'accuracy': 0.8295454545454546} | {'f1': 0.8243565671691487} | |
|
| 0.0162 | 13.0 | 3419 | 1.2592 | {'accuracy': 0.8333333333333334} | {'f1': 0.8312612314115424} | |
|
| 0.0073 | 14.0 | 3682 | 1.2885 | {'accuracy': 0.8257575757575758} | {'f1': 0.8198413592956925} | |
|
| 0.0073 | 15.0 | 3945 | 1.2133 | {'accuracy': 0.8352272727272727} | {'f1': 0.8291568008253063} | |
|
| 0.0046 | 16.0 | 4208 | 1.2625 | {'accuracy': 0.8409090909090909} | {'f1': 0.8343252944129244} | |
|
| 0.0046 | 17.0 | 4471 | 1.2498 | {'accuracy': 0.8409090909090909} | {'f1': 0.8356461395476784} | |
|
| 0.0032 | 18.0 | 4734 | 1.3041 | {'accuracy': 0.8390151515151515} | {'f1': 0.8307896138032654} | |
|
| 0.0032 | 19.0 | 4997 | 1.2544 | {'accuracy': 0.8446969696969697} | {'f1': 0.83889081905153} | |
|
| 0.0022 | 20.0 | 5260 | 1.2731 | {'accuracy': 0.8465909090909091} | {'f1': 0.8396445042099528} | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.1 |
|
|