tiny-mlm-imdb-target-rotten_tomatoes
This model is a fine-tuned version of muhtasham/small-mlm-wikitext on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3909
- Accuracy: 0.8021
- F1: 0.8017
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 |
|---|---|---|---|---|---|
| 0.4528 | 1.87 | 500 | 0.4296 | 0.8030 | 0.8028 |
| 0.2265 | 3.75 | 1000 | 0.5558 | 0.8096 | 0.8096 |
| 0.1111 | 5.62 | 1500 | 0.9042 | 0.8039 | 0.8039 |
| 0.0584 | 7.49 | 2000 | 1.1252 | 0.8058 | 0.8058 |
| 0.0405 | 9.36 | 2500 | 1.3909 | 0.8021 | 0.8017 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2