metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: bert-finetuned-mrpc
results: []
bert-finetuned-mrpc
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4508
- Accuracy: 0.8676
- F1: 0.9091
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 459 | 0.5627 | 0.6961 | 0.7660 |
| 0.6109 | 2.0 | 918 | 0.5162 | 0.7966 | 0.8676 |
| 0.4471 | 3.0 | 1377 | 0.4508 | 0.8676 | 0.9091 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.0.1+cu117
- Datasets 2.15.0
- Tokenizers 0.15.0