bert-base-cased-fp-sick
This model is a fine-tuned version of bert-base-cased on the sick dataset. It achieves the following results on the evaluation set:
- Loss: 0.3973
- Accuracy: 0.8545
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: 64
- eval_batch_size: 32
- seed: 34
- 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 |
|---|---|---|---|---|
| No log | 1.0 | 70 | 0.6825 | 0.6727 |
| No log | 2.0 | 140 | 0.4141 | 0.8505 |
| No log | 3.0 | 210 | 0.3973 | 0.8545 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 5
Model tree for varun-v-rao/bert-base-cased-fp-sick
Dataset used to train varun-v-rao/bert-base-cased-fp-sick
Evaluation results
- Accuracy on sickvalidation set self-reported0.855