<!-- 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-mnli
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: 0.8094
- Accuracy: 0.6373
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 |
|---|---|---|---|---|
| 1.0737 | 0.04 | 500 | 1.0366 | 0.4615 |
| 1.0169 | 0.08 | 1000 | 0.9833 | 0.5194 |
| 0.9799 | 0.12 | 1500 | 0.9344 | 0.5719 |
| 0.9452 | 0.16 | 2000 | 0.9106 | 0.5879 |
| 0.9293 | 0.2 | 2500 | 0.8905 | 0.5962 |
| 0.9189 | 0.24 | 3000 | 0.8801 | 0.6026 |
| 0.9017 | 0.29 | 3500 | 0.8705 | 0.6103 |
| 0.896 | 0.33 | 4000 | 0.8619 | 0.6178 |
| 0.881 | 0.37 | 4500 | 0.8574 | 0.6211 |
| 0.8854 | 0.41 | 5000 | 0.8495 | 0.6201 |
| 0.8756 | 0.45 | 5500 | 0.8434 | 0.6223 |
| 0.8713 | 0.49 | 6000 | 0.8410 | 0.6263 |
| 0.8757 | 0.53 | 6500 | 0.8337 | 0.6301 |
| 0.8624 | 0.57 | 7000 | 0.8363 | 0.6284 |
| 0.8576 | 0.61 | 7500 | 0.8203 | 0.6356 |
| 0.8583 | 0.65 | 8000 | 0.8188 | 0.6378 |
| 0.8523 | 0.69 | 8500 | 0.8294 | 0.6304 |
| 0.8533 | 0.73 | 9000 | 0.8052 | 0.6429 |
| 0.8448 | 0.77 | 9500 | 0.8180 | 0.6356 |
| 0.8368 | 0.81 | 10000 | 0.8030 | 0.6399 |
| 0.8389 | 0.86 | 10500 | 0.8094 | 0.6373 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
