roberta-base-rte
This model is a fine-tuned version of roberta-base on the GLUE RTE dataset. It achieves the following results on the evaluation set:
- Loss: 0.5446
- Accuracy: 0.7978
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 156 | 0.7023 | 0.4729 |
| No log | 2.0 | 312 | 0.6356 | 0.6895 |
| No log | 3.0 | 468 | 0.5177 | 0.7617 |
| 0.6131 | 4.0 | 624 | 0.6238 | 0.7473 |
| 0.6131 | 5.0 | 780 | 0.5446 | 0.7978 |
| 0.6131 | 6.0 | 936 | 0.9697 | 0.7545 |
| 0.2528 | 7.0 | 1092 | 1.1004 | 0.7690 |
| 0.2528 | 8.0 | 1248 | 1.1937 | 0.7726 |
| 0.2528 | 9.0 | 1404 | 1.3313 | 0.7726 |
| 0.1073 | 10.0 | 1560 | 1.3534 | 0.7726 |
Framework versions
- Transformers 4.20.0.dev0
- Pytorch 1.11.0+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1