<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
sentiment-model-saagie
This model is a fine-tuned version of prajjwal1/bert-tiny on the sst2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5562
- Accuracy: 0.78
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.5106 | 1.0 | 1500 | 0.4798 | 0.7783 |
0.3776 | 2.0 | 3000 | 0.5531 | 0.7783 |
0.3338 | 3.0 | 4500 | 0.5562 | 0.78 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.8.1
- Datasets 2.12.0
- Tokenizers 0.12.1