metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: albert-base-v2-finetuned-mrpc
results: []
albert-base-v2-finetuned-mrpc
This model is a fine-tuned version of albert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6790
- Accuracy: 0.8824
- F1: 0.9161
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: 16
- eval_batch_size: 16
- seed: 42
- 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 | 230 | 0.4008 | 0.8725 | 0.9113 |
| No log | 2.0 | 460 | 0.4873 | 0.8799 | 0.9114 |
| 0.1743 | 3.0 | 690 | 0.6790 | 0.8824 | 0.9161 |
| 0.1743 | 4.0 | 920 | 0.7307 | 0.8775 | 0.9117 |
| 0.0455 | 5.0 | 1150 | 0.7307 | 0.8775 | 0.9117 |
Framework versions
- Transformers 4.16.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2