<!-- 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-from-scratch-target-rotten_tomatoes
This model is a fine-tuned version of muhtasham/tiny-mlm-wikitext-from-scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1447
- Accuracy: 0.7402
- F1: 0.7399
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 |
|---|---|---|---|---|---|
| 0.6933 | 1.87 | 500 | 0.6917 | 0.5075 | 0.3529 |
| 0.6284 | 3.75 | 1000 | 0.6015 | 0.6801 | 0.6801 |
| 0.432 | 5.62 | 1500 | 0.5991 | 0.7223 | 0.7202 |
| 0.3062 | 7.49 | 2000 | 0.6654 | 0.7373 | 0.7372 |
| 0.2301 | 9.36 | 2500 | 0.7174 | 0.7402 | 0.7399 |
| 0.1764 | 11.24 | 3000 | 0.8125 | 0.7467 | 0.7467 |
| 0.1387 | 13.11 | 3500 | 0.8903 | 0.7467 | 0.7463 |
| 0.1126 | 14.98 | 4000 | 0.9890 | 0.7467 | 0.7463 |
| 0.0971 | 16.85 | 4500 | 1.1447 | 0.7402 | 0.7399 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
