<!-- 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-mrpc
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: 1.3255
- Accuracy: 0.6814
- F1: 0.7774
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 |
|---|---|---|---|---|---|
| 0.6335 | 4.35 | 500 | 0.6141 | 0.6838 | 0.8122 |
| 0.5775 | 8.7 | 1000 | 0.6149 | 0.6863 | 0.7816 |
| 0.4672 | 13.04 | 1500 | 0.6877 | 0.6740 | 0.7703 |
| 0.3568 | 17.39 | 2000 | 0.7828 | 0.6887 | 0.7858 |
| 0.2805 | 21.74 | 2500 | 0.9508 | 0.6275 | 0.7164 |
| 0.2304 | 26.09 | 3000 | 0.9905 | 0.6912 | 0.7886 |
| 0.1817 | 30.43 | 3500 | 1.0912 | 0.6814 | 0.7804 |
| 0.1534 | 34.78 | 4000 | 1.2402 | 0.6446 | 0.7434 |
| 0.1338 | 39.13 | 4500 | 1.3255 | 0.6814 | 0.7774 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
