<!-- 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-glue-cola-from-scratch-custom-tokenizer-target-glue-qqp
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-cola-from-scratch-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5427
- Accuracy: 0.7318
- F1: 0.5719
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 |
|---|---|---|---|---|---|
| 0.6414 | 0.04 | 500 | 0.6217 | 0.6544 | 0.4756 |
| 0.6157 | 0.09 | 1000 | 0.6047 | 0.6738 | 0.5091 |
| 0.6019 | 0.13 | 1500 | 0.5899 | 0.6825 | 0.5814 |
| 0.5812 | 0.18 | 2000 | 0.5686 | 0.7068 | 0.5646 |
| 0.572 | 0.22 | 2500 | 0.5590 | 0.7170 | 0.5716 |
| 0.5641 | 0.26 | 3000 | 0.5543 | 0.7194 | 0.5891 |
| 0.5572 | 0.31 | 3500 | 0.5491 | 0.7252 | 0.5919 |
| 0.5529 | 0.35 | 4000 | 0.5529 | 0.7199 | 0.6169 |
| 0.556 | 0.4 | 4500 | 0.5471 | 0.7260 | 0.6145 |
| 0.5482 | 0.44 | 5000 | 0.5427 | 0.7318 | 0.5719 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
