<!-- 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-sst2
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: 0.4365
- Accuracy: 0.8085
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 |
|---|---|---|---|---|
| 0.6856 | 0.24 | 500 | 0.6922 | 0.5195 |
| 0.6777 | 0.48 | 1000 | 0.6786 | 0.5849 |
| 0.6106 | 0.71 | 1500 | 0.5295 | 0.7592 |
| 0.4947 | 0.95 | 2000 | 0.4996 | 0.7557 |
| 0.446 | 1.19 | 2500 | 0.4592 | 0.7844 |
| 0.4169 | 1.43 | 3000 | 0.4700 | 0.7752 |
| 0.3997 | 1.66 | 3500 | 0.4481 | 0.7878 |
| 0.3814 | 1.9 | 4000 | 0.4403 | 0.7844 |
| 0.3699 | 2.14 | 4500 | 0.4491 | 0.7833 |
| 0.3497 | 2.38 | 5000 | 0.4365 | 0.8085 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
