bert-base-uncased-sst2-distilled
This model is a fine-tuned version of bert-base-uncased on an unkown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2676
- Accuracy: 0.9025
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: 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3797 | 1.0 | 2105 | 0.2512 | 0.9002 |
| 0.3036 | 2.0 | 4210 | 0.2643 | 0.8933 |
| 0.2609 | 3.0 | 6315 | 0.2831 | 0.8956 |
| 0.2417 | 4.0 | 8420 | 0.2676 | 0.9025 |
| 0.2305 | 5.0 | 10525 | 0.2740 | 0.9025 |
Framework versions
- Transformers 4.9.1
- Pytorch 1.8.1
- Datasets 1.11.0
- Tokenizers 0.10.1