<!-- 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-mnli-target-glue-stsb
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-mnli on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9147
- Pearson: 0.8161
- Spearmanr: 0.8166
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 | Pearson | Spearmanr |
|---|---|---|---|---|---|
| 3.1849 | 2.78 | 500 | 1.1212 | 0.7265 | 0.7541 |
| 0.9758 | 5.56 | 1000 | 1.0688 | 0.7790 | 0.7990 |
| 0.7441 | 8.33 | 1500 | 1.0145 | 0.8030 | 0.8178 |
| 0.6177 | 11.11 | 2000 | 0.8751 | 0.8166 | 0.8220 |
| 0.5205 | 13.89 | 2500 | 0.9216 | 0.8143 | 0.8173 |
| 0.4664 | 16.67 | 3000 | 1.0287 | 0.8147 | 0.8200 |
| 0.4095 | 19.44 | 3500 | 0.9147 | 0.8161 | 0.8166 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
