mobilebert_add_GLUE_Experiment_mrpc_256
This model is a fine-tuned version of google/mobilebert-uncased on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.6207
- Accuracy: 0.6838
- F1: 0.8122
- Combined Score: 0.7480
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: 128
- eval_batch_size: 128
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
|---|---|---|---|---|---|---|
| 0.6419 | 1.0 | 29 | 0.6266 | 0.6838 | 0.8122 | 0.7480 |
| 0.6297 | 2.0 | 58 | 0.6236 | 0.6838 | 0.8122 | 0.7480 |
| 0.6307 | 3.0 | 87 | 0.6241 | 0.6838 | 0.8122 | 0.7480 |
| 0.63 | 4.0 | 116 | 0.6243 | 0.6838 | 0.8122 | 0.7480 |
| 0.6283 | 5.0 | 145 | 0.6219 | 0.6838 | 0.8122 | 0.7480 |
| 0.6243 | 6.0 | 174 | 0.6207 | 0.6838 | 0.8122 | 0.7480 |
| 0.6206 | 7.0 | 203 | 0.6346 | 0.6838 | 0.8122 | 0.7480 |
| 0.6034 | 8.0 | 232 | 0.6519 | 0.6348 | 0.7545 | 0.6947 |
| 0.5877 | 9.0 | 261 | 0.6375 | 0.6838 | 0.8122 | 0.7480 |
| 0.5722 | 10.0 | 290 | 0.6446 | 0.6299 | 0.7504 | 0.6902 |
| 0.5619 | 11.0 | 319 | 0.6733 | 0.6814 | 0.8105 | 0.7459 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.8.0
- Tokenizers 0.13.2