metadata
license: mit
base_model: FacebookAI/roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: STS-Conventional-Fine-Tuning-pipe-roberta-base
results: []
STS-Conventional-Fine-Tuning-pipe-roberta-base
This model is a fine-tuned version of FacebookAI/roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.9623
- Accuracy: 0.7210
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: 3e-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: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 113 | 0.7397 | 0.6760 |
| No log | 2.0 | 226 | 0.7139 | 0.7135 |
| No log | 3.0 | 339 | 0.7846 | 0.7041 |
| No log | 4.0 | 452 | 0.8368 | 0.6816 |
| 0.5292 | 5.0 | 565 | 1.0395 | 0.6873 |
| 0.5292 | 6.0 | 678 | 1.0863 | 0.7154 |
| 0.5292 | 7.0 | 791 | 1.2668 | 0.7097 |
| 0.5292 | 8.0 | 904 | 1.5312 | 0.7135 |
| 0.1806 | 9.0 | 1017 | 1.6574 | 0.7041 |
| 0.1806 | 10.0 | 1130 | 1.7880 | 0.7041 |
| 0.1806 | 11.0 | 1243 | 1.7902 | 0.7116 |
| 0.1806 | 12.0 | 1356 | 1.9168 | 0.7154 |
| 0.1806 | 13.0 | 1469 | 1.8637 | 0.7210 |
| 0.0717 | 14.0 | 1582 | 1.9391 | 0.7210 |
| 0.0717 | 15.0 | 1695 | 1.9623 | 0.7210 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2