roberta-base-sst2
This model is a fine-tuned version of roberta-base on the GLUE SST2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2314
- Accuracy: 0.9358
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: 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 |
|---|---|---|---|---|
| 0.2287 | 1.0 | 4210 | 0.2314 | 0.9358 |
| 0.1959 | 2.0 | 8420 | 0.3027 | 0.9266 |
| 0.1635 | 3.0 | 12630 | 0.3022 | 0.9300 |
| 0.1148 | 4.0 | 16840 | 0.3162 | 0.9289 |
Framework versions
- Transformers 4.20.0.dev0
- Pytorch 1.11.0+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1