<!-- 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-sst2-target-glue-stsb
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-sst2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9195
- Pearson: 0.8130
- Spearmanr: 0.8114
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 |
|---|---|---|---|---|---|
| 2.7776 | 2.78 | 500 | 1.1238 | 0.7313 | 0.7669 |
| 0.932 | 5.56 | 1000 | 1.0628 | 0.7833 | 0.8086 |
| 0.737 | 8.33 | 1500 | 1.0050 | 0.8025 | 0.8208 |
| 0.6099 | 11.11 | 2000 | 0.8592 | 0.8165 | 0.8220 |
| 0.5164 | 13.89 | 2500 | 0.8875 | 0.8158 | 0.8181 |
| 0.4659 | 16.67 | 3000 | 0.9524 | 0.8155 | 0.8198 |
| 0.4114 | 19.44 | 3500 | 0.8872 | 0.8173 | 0.8174 |
| 0.3728 | 22.22 | 4000 | 0.9423 | 0.8163 | 0.8166 |
| 0.3396 | 25.0 | 4500 | 0.9953 | 0.8197 | 0.8202 |
| 0.321 | 27.78 | 5000 | 0.9409 | 0.8160 | 0.8160 |
| 0.3034 | 30.56 | 5500 | 0.9273 | 0.8142 | 0.8139 |
| 0.2811 | 33.33 | 6000 | 0.9195 | 0.8130 | 0.8114 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
