bert-base-cased-sst2
This model is a fine-tuned version of bert-base-cased on the sst2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2103
- Accuracy: 0.9140
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: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2267 | 1.0 | 527 | 0.2103 | 0.9140 |
| 0.1091 | 2.0 | 1054 | 0.2637 | 0.9174 |
| 0.0722 | 3.0 | 1581 | 0.2673 | 0.9174 |
| 0.0467 | 4.0 | 2108 | 0.2947 | 0.9266 |
| 0.0298 | 5.0 | 2635 | 0.3344 | 0.9209 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.14.0
- Downloads last month
- 5
Model tree for VityaVitalich/bert-base-cased-sst2
Base model
google-bert/bert-base-casedDataset used to train VityaVitalich/bert-base-cased-sst2
Evaluation results
- Accuracy on sst2validation set self-reported0.914