albert-large-v1-finetuned-mrpc
This model is a fine-tuned version of albert-large-v1 on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.4479
- Accuracy: 0.8725
- F1: 0.9075
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: 69
- 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 | 0.3323 | 0.8554 | 0.8970 |
| No log | 2.0 | 230 | 0.3164 | 0.8799 | 0.9127 |
| No log | 3.0 | 345 | 0.3368 | 0.8603 | 0.9019 |
| No log | 4.0 | 460 | 0.4099 | 0.8676 | 0.9049 |
| 0.2727 | 5.0 | 575 | 0.4479 | 0.8725 | 0.9075 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.13.3