albert-base-v2-finetuned-mrpc
This model is a fine-tuned version of albert-base-v2 on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.5610
- Accuracy: 0.8627
- F1: 0.9007
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: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 95
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 115 | 0.3358 | 0.8676 | 0.9004 |
| No log | 2.0 | 230 | 0.3140 | 0.8676 | 0.9029 |
| No log | 3.0 | 345 | 0.3763 | 0.8897 | 0.9201 |
| No log | 4.0 | 460 | 0.4980 | 0.8725 | 0.9085 |
| 0.2512 | 5.0 | 575 | 0.5610 | 0.8627 | 0.9007 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3