<!-- 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-rte-target-glue-stsb
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-rte on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9754
- Pearson: 0.8093
- Spearmanr: 0.8107
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 |
|---|---|---|---|---|---|
| 3.2461 | 2.78 | 500 | 1.1464 | 0.7083 | 0.7348 |
| 1.0093 | 5.56 | 1000 | 1.1455 | 0.7664 | 0.7934 |
| 0.7582 | 8.33 | 1500 | 1.0140 | 0.7980 | 0.8136 |
| 0.6329 | 11.11 | 2000 | 0.8708 | 0.8136 | 0.8184 |
| 0.5285 | 13.89 | 2500 | 0.8894 | 0.8139 | 0.8159 |
| 0.4747 | 16.67 | 3000 | 0.9908 | 0.8116 | 0.8165 |
| 0.4154 | 19.44 | 3500 | 0.9260 | 0.8137 | 0.8145 |
| 0.3792 | 22.22 | 4000 | 0.9264 | 0.8161 | 0.8156 |
| 0.3445 | 25.0 | 4500 | 0.9664 | 0.8155 | 0.8164 |
| 0.3246 | 27.78 | 5000 | 0.9735 | 0.8110 | 0.8121 |
| 0.3033 | 30.56 | 5500 | 0.9754 | 0.8093 | 0.8107 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
