<!-- 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-qqp-target-glue-mrpc
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-qqp on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0859
- Accuracy: 0.7451
- F1: 0.8255
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 | F1 |
|---|---|---|---|---|---|
| 0.5865 | 4.35 | 500 | 0.5528 | 0.7206 | 0.8125 |
| 0.4509 | 8.7 | 1000 | 0.5715 | 0.7402 | 0.8274 |
| 0.3154 | 13.04 | 1500 | 0.6199 | 0.7696 | 0.8412 |
| 0.2093 | 17.39 | 2000 | 0.7304 | 0.75 | 0.8265 |
| 0.1328 | 21.74 | 2500 | 0.9197 | 0.7426 | 0.8161 |
| 0.0913 | 26.09 | 3000 | 1.0859 | 0.7451 | 0.8255 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
