tiny-mlm-glue-stsb-target-glue-rte
This model is a fine-tuned version of muhtasham/tiny-mlm-glue-stsb on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.7196
- Accuracy: 0.5848
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 | Accuracy |
|---|---|---|---|---|
| 0.6488 | 6.41 | 500 | 0.6737 | 0.5957 |
| 0.4369 | 12.82 | 1000 | 0.8455 | 0.6029 |
| 0.253 | 19.23 | 1500 | 1.1070 | 0.5740 |
| 0.1381 | 25.64 | 2000 | 1.3458 | 0.5921 |
| 0.0817 | 32.05 | 2500 | 1.7196 | 0.5848 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2