small-vanilla-target-rotten_tomatoes
This model is a fine-tuned version of google/bert_uncased_L-4_H-512_A-8 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3343
- Accuracy: 0.8039
- F1: 0.8039
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- training_steps: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.4688 | 1.87 | 500 | 0.4332 | 0.7992 | 0.7992 |
| 0.242 | 3.75 | 1000 | 0.5337 | 0.8180 | 0.8178 |
| 0.1128 | 5.62 | 1500 | 0.9190 | 0.8161 | 0.8161 |
| 0.0673 | 7.49 | 2000 | 1.0798 | 0.8171 | 0.8171 |
| 0.0396 | 9.36 | 2500 | 1.3343 | 0.8039 | 0.8039 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2