<!-- 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-sst2-target-glue-sst2
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-sst2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5101
- Accuracy: 0.8211
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
- num_epochs: 200
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.596 | 0.24 | 500 | 0.4978 | 0.7764 |
| 0.4456 | 0.48 | 1000 | 0.4674 | 0.7936 |
| 0.3949 | 0.71 | 1500 | 0.4466 | 0.7936 |
| 0.3741 | 0.95 | 2000 | 0.4565 | 0.7947 |
| 0.3364 | 1.19 | 2500 | 0.4468 | 0.8085 |
| 0.3173 | 1.43 | 3000 | 0.4493 | 0.8016 |
| 0.3008 | 1.66 | 3500 | 0.4444 | 0.8108 |
| 0.2935 | 1.9 | 4000 | 0.4513 | 0.8177 |
| 0.2748 | 2.14 | 4500 | 0.4994 | 0.7959 |
| 0.2554 | 2.38 | 5000 | 0.4577 | 0.8188 |
| 0.2474 | 2.61 | 5500 | 0.4609 | 0.8268 |
| 0.2569 | 2.85 | 6000 | 0.4606 | 0.8245 |
| 0.2376 | 3.09 | 6500 | 0.4710 | 0.8234 |
| 0.2333 | 3.33 | 7000 | 0.4720 | 0.8303 |
| 0.2173 | 3.56 | 7500 | 0.4658 | 0.8326 |
| 0.2143 | 3.8 | 8000 | 0.5016 | 0.8234 |
| 0.2132 | 4.04 | 8500 | 0.5265 | 0.8222 |
| 0.2045 | 4.28 | 9000 | 0.5101 | 0.8211 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
