<!-- 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. -->
tiny-mlm-wikitext-target-rotten_tomatoes
This model is a fine-tuned version of muhtasham/tiny-mlm-wikitext on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8868
- Accuracy: 0.7533
- F1: 0.7528
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 |
|---|---|---|---|---|---|
| 0.6236 | 1.87 | 500 | 0.5413 | 0.7289 | 0.7285 |
| 0.4892 | 3.75 | 1000 | 0.5137 | 0.7448 | 0.7435 |
| 0.4112 | 5.62 | 1500 | 0.5224 | 0.7636 | 0.7629 |
| 0.3454 | 7.49 | 2000 | 0.5365 | 0.7627 | 0.7624 |
| 0.2899 | 9.36 | 2500 | 0.5962 | 0.7655 | 0.7651 |
| 0.2447 | 11.24 | 3000 | 0.6489 | 0.7561 | 0.7554 |
| 0.2025 | 13.11 | 3500 | 0.6943 | 0.7692 | 0.7688 |
| 0.1671 | 14.98 | 4000 | 0.7455 | 0.7627 | 0.7621 |
| 0.1418 | 16.85 | 4500 | 0.7962 | 0.7608 | 0.7600 |
| 0.1239 | 18.73 | 5000 | 0.8868 | 0.7533 | 0.7528 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
