<!-- 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-stsb
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: 3.1709
- Pearson: 0.1495
- Spearmanr: 0.1510
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 | Pearson | Spearmanr |
|---|---|---|---|---|---|
| 3.3987 | 2.78 | 500 | 2.3377 | 0.0932 | 0.1034 |
| 1.9823 | 5.56 | 1000 | 2.4861 | 0.1129 | 0.1090 |
| 1.7877 | 8.33 | 1500 | 2.6218 | 0.1377 | 0.1223 |
| 1.541 | 11.11 | 2000 | 2.7140 | 0.1509 | 0.1561 |
| 1.3667 | 13.89 | 2500 | 2.7537 | 0.1651 | 0.1701 |
| 1.2522 | 16.67 | 3000 | 2.9782 | 0.1477 | 0.1598 |
| 1.1458 | 19.44 | 3500 | 2.8960 | 0.1695 | 0.1742 |
| 1.0717 | 22.22 | 4000 | 2.9641 | 0.1611 | 0.1646 |
| 0.9937 | 25.0 | 4500 | 2.9701 | 0.1612 | 0.1621 |
| 0.9095 | 27.78 | 5000 | 3.1709 | 0.1495 | 0.1510 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
