<!-- 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-qqp-from-scratch-custom-tokenizer-target-glue-sst2
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-qqp-from-scratch-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4349
- Accuracy: 0.8200
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 |
|---|---|---|---|---|
| 0.6858 | 0.24 | 500 | 0.6933 | 0.5218 |
| 0.6738 | 0.48 | 1000 | 0.6651 | 0.6021 |
| 0.6513 | 0.71 | 1500 | 0.6346 | 0.6514 |
| 0.6059 | 0.95 | 2000 | 0.5318 | 0.7443 |
| 0.5101 | 1.19 | 2500 | 0.4794 | 0.7821 |
| 0.4539 | 1.43 | 3000 | 0.4664 | 0.7901 |
| 0.4203 | 1.66 | 3500 | 0.4500 | 0.8016 |
| 0.4003 | 1.9 | 4000 | 0.4241 | 0.8165 |
| 0.3663 | 2.14 | 4500 | 0.4845 | 0.7982 |
| 0.3436 | 2.38 | 5000 | 0.4349 | 0.8200 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
