<!-- 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-mrpc-target-glue-qqp
This model is a fine-tuned version of muhtasham/small-mlm-glue-mrpc on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3314
- Accuracy: 0.8515
- F1: 0.8122
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 | F1 |
|---|---|---|---|---|---|
| 0.4782 | 0.04 | 500 | 0.4205 | 0.7932 | 0.7493 |
| 0.4193 | 0.09 | 1000 | 0.3913 | 0.8109 | 0.7696 |
| 0.4021 | 0.13 | 1500 | 0.3765 | 0.8203 | 0.7732 |
| 0.3853 | 0.18 | 2000 | 0.3753 | 0.8193 | 0.7874 |
| 0.3788 | 0.22 | 2500 | 0.3609 | 0.8345 | 0.7965 |
| 0.3614 | 0.26 | 3000 | 0.3482 | 0.8386 | 0.8000 |
| 0.358 | 0.31 | 3500 | 0.3342 | 0.8500 | 0.8020 |
| 0.3522 | 0.35 | 4000 | 0.3331 | 0.8481 | 0.8076 |
| 0.3575 | 0.4 | 4500 | 0.3235 | 0.8533 | 0.8101 |
| 0.3422 | 0.44 | 5000 | 0.3314 | 0.8515 | 0.8122 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
