<!-- 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-mrpc-target-glue-sst2
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-mrpc on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4921
- Accuracy: 0.8314
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 |
|---|---|---|---|---|
| 0.5814 | 0.24 | 500 | 0.4938 | 0.7706 |
| 0.4444 | 0.48 | 1000 | 0.4690 | 0.7844 |
| 0.3934 | 0.71 | 1500 | 0.4458 | 0.7982 |
| 0.3733 | 0.95 | 2000 | 0.4633 | 0.7890 |
| 0.3319 | 1.19 | 2500 | 0.4503 | 0.7982 |
| 0.3151 | 1.43 | 3000 | 0.4525 | 0.8028 |
| 0.2971 | 1.66 | 3500 | 0.4431 | 0.8142 |
| 0.2899 | 1.9 | 4000 | 0.4452 | 0.8108 |
| 0.2716 | 2.14 | 4500 | 0.4914 | 0.7993 |
| 0.2548 | 2.38 | 5000 | 0.4419 | 0.8177 |
| 0.2443 | 2.61 | 5500 | 0.4475 | 0.8245 |
| 0.2515 | 2.85 | 6000 | 0.4462 | 0.8257 |
| 0.2357 | 3.09 | 6500 | 0.4509 | 0.8314 |
| 0.2279 | 3.33 | 7000 | 0.4641 | 0.8337 |
| 0.2134 | 3.56 | 7500 | 0.4615 | 0.8326 |
| 0.2136 | 3.8 | 8000 | 0.4882 | 0.8314 |
| 0.2122 | 4.04 | 8500 | 0.4921 | 0.8314 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
