tinybert_book_ent_15p_b_mrpc
This model is a fine-tuned version of gokulsrinivasagan/tinybert_book_ent_15p_b on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5913
- Accuracy: 0.6887
- F1: 0.7994
- Combined Score: 0.7440
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: 5e-05
- train_batch_size: 256
- eval_batch_size: 256
- seed: 10
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
|---|---|---|---|---|---|---|
| 0.6214 | 1.0 | 15 | 0.6032 | 0.6887 | 0.8 | 0.7444 |
| 0.5895 | 2.0 | 30 | 0.5913 | 0.6887 | 0.7994 | 0.7440 |
| 0.5682 | 3.0 | 45 | 0.6076 | 0.6961 | 0.8127 | 0.7544 |
| 0.5412 | 4.0 | 60 | 0.6187 | 0.6863 | 0.7762 | 0.7312 |
| 0.4784 | 5.0 | 75 | 0.6746 | 0.6520 | 0.7455 | 0.6987 |
| 0.409 | 6.0 | 90 | 0.8154 | 0.6348 | 0.7315 | 0.6832 |
| 0.3176 | 7.0 | 105 | 0.8858 | 0.6471 | 0.7568 | 0.7019 |
Framework versions
- Transformers 4.51.2
- Pytorch 2.6.0+cu126
- Datasets 3.5.0
- Tokenizers 0.21.1