tiny-mlm-rotten_tomatoes
This model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.7612
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
- num_epochs: 200
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.4536 | 0.47 | 500 | 5.0630 |
| 5.3082 | 0.94 | 1000 | 4.8370 |
| 5.1105 | 1.41 | 1500 | 4.8032 |
| 5.0889 | 1.87 | 2000 | 4.8950 |
| 5.066 | 2.34 | 2500 | 4.7443 |
| 4.9543 | 2.81 | 3000 | 4.7674 |
| 4.9431 | 3.28 | 3500 | 4.8268 |
| 4.8918 | 3.75 | 4000 | 4.7612 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2