<!-- 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-custom-tokenizer-target-glue-mnli
This model is a fine-tuned version of muhtasham/small-mlm-glue-mrpc-custom-tokenizer on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8198
- Accuracy: 0.6328
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 |
|---|---|---|---|---|
| 1.052 | 0.04 | 500 | 1.0262 | 0.4857 |
| 0.9703 | 0.08 | 1000 | 0.9454 | 0.5575 |
| 0.9365 | 0.12 | 1500 | 0.9063 | 0.5835 |
| 0.9001 | 0.16 | 2000 | 0.8998 | 0.5903 |
| 0.8888 | 0.2 | 2500 | 0.8922 | 0.5980 |
| 0.8817 | 0.24 | 3000 | 0.8697 | 0.6075 |
| 0.8669 | 0.29 | 3500 | 0.8602 | 0.6139 |
| 0.8538 | 0.33 | 4000 | 0.8531 | 0.6174 |
| 0.8356 | 0.37 | 4500 | 0.8470 | 0.6250 |
| 0.8401 | 0.41 | 5000 | 0.8198 | 0.6328 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
