small-mlm-glue-cola-target-glue-qqp
This model is a fine-tuned version of muhtasham/small-mlm-glue-cola on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3251
- Accuracy: 0.8529
- F1: 0.8136
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 | F1 |
|---|---|---|---|---|---|
| 0.4794 | 0.04 | 500 | 0.4274 | 0.7869 | 0.7456 |
| 0.4234 | 0.09 | 1000 | 0.3931 | 0.8098 | 0.7678 |
| 0.4052 | 0.13 | 1500 | 0.3758 | 0.8202 | 0.7764 |
| 0.3892 | 0.18 | 2000 | 0.3740 | 0.8217 | 0.7864 |
| 0.3808 | 0.22 | 2500 | 0.3637 | 0.8309 | 0.7934 |
| 0.3633 | 0.26 | 3000 | 0.3488 | 0.8388 | 0.7993 |
| 0.3619 | 0.31 | 3500 | 0.3346 | 0.8491 | 0.8000 |
| 0.355 | 0.35 | 4000 | 0.3303 | 0.8487 | 0.8065 |
| 0.3586 | 0.4 | 4500 | 0.3261 | 0.8508 | 0.8090 |
| 0.344 | 0.44 | 5000 | 0.3251 | 0.8529 | 0.8136 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2