<!-- 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-vanilla-target-glue-sst2
This model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4800
- Accuracy: 0.8245
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 |
|---|---|---|---|---|
| 0.6144 | 0.24 | 500 | 0.5259 | 0.7477 |
| 0.4695 | 0.48 | 1000 | 0.4724 | 0.7752 |
| 0.4058 | 0.71 | 1500 | 0.4509 | 0.7878 |
| 0.3815 | 0.95 | 2000 | 0.4536 | 0.7993 |
| 0.3447 | 1.19 | 2500 | 0.4393 | 0.8073 |
| 0.3226 | 1.43 | 3000 | 0.4462 | 0.8039 |
| 0.3065 | 1.66 | 3500 | 0.4392 | 0.8119 |
| 0.2972 | 1.9 | 4000 | 0.4412 | 0.8096 |
| 0.2778 | 2.14 | 4500 | 0.4665 | 0.8154 |
| 0.2599 | 2.38 | 5000 | 0.4395 | 0.8211 |
| 0.2503 | 2.61 | 5500 | 0.4468 | 0.8245 |
| 0.2586 | 2.85 | 6000 | 0.4443 | 0.8268 |
| 0.24 | 3.09 | 6500 | 0.4625 | 0.8200 |
| 0.2353 | 3.33 | 7000 | 0.4556 | 0.8268 |
| 0.2207 | 3.56 | 7500 | 0.4507 | 0.8291 |
| 0.2177 | 3.8 | 8000 | 0.4809 | 0.8280 |
| 0.2156 | 4.04 | 8500 | 0.5157 | 0.8234 |
| 0.2073 | 4.28 | 9000 | 0.4800 | 0.8245 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
