<!-- 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. -->
small-mlm-glue-cola-target-glue-sst2
This model is a fine-tuned version of muhtasham/small-mlm-glue-cola on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4277
- Accuracy: 0.8761
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 |
|---|---|---|---|---|
| 0.3913 | 0.24 | 500 | 0.3633 | 0.8475 |
| 0.3062 | 0.48 | 1000 | 0.3274 | 0.8544 |
| 0.2578 | 0.71 | 1500 | 0.3600 | 0.8589 |
| 0.2378 | 0.95 | 2000 | 0.3271 | 0.8739 |
| 0.183 | 1.19 | 2500 | 0.3521 | 0.8784 |
| 0.1715 | 1.43 | 3000 | 0.3701 | 0.8704 |
| 0.1695 | 1.66 | 3500 | 0.3717 | 0.8773 |
| 0.1712 | 1.9 | 4000 | 0.3340 | 0.8876 |
| 0.1331 | 2.14 | 4500 | 0.6306 | 0.8360 |
| 0.1225 | 2.38 | 5000 | 0.4277 | 0.8761 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
