metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: roberta-base-finetuned-stationary-temporal-tags
results: []
roberta-base-finetuned-stationary-temporal-tags
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0128
- Accuracy: 0.7439
- F1: 0.7382
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: 64
- eval_batch_size: 64
- 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 | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.6087 | 1.0 | 36 | 0.5982 | 0.6367 | 0.6351 |
| 0.491 | 2.0 | 72 | 0.4945 | 0.7612 | 0.7638 |
| 0.3862 | 3.0 | 108 | 0.4793 | 0.7785 | 0.7807 |
| 0.3 | 4.0 | 144 | 0.5702 | 0.7578 | 0.7572 |
| 0.2155 | 5.0 | 180 | 0.7004 | 0.7647 | 0.7636 |
| 0.1604 | 6.0 | 216 | 0.7589 | 0.7612 | 0.7562 |
| 0.1274 | 7.0 | 252 | 0.7798 | 0.7509 | 0.7497 |
| 0.0936 | 8.0 | 288 | 1.0196 | 0.7543 | 0.7425 |
| 0.0662 | 9.0 | 324 | 0.9769 | 0.7405 | 0.7359 |
| 0.0661 | 10.0 | 360 | 1.0128 | 0.7439 | 0.7382 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0