<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
bert-base-uncased-mrpc-epochs-10-lr-5e-05
This model is a fine-tuned version of bert-base-uncased on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 1.1650
- Accuracy: 0.83
- F1: 0.8794
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: 32
- eval_batch_size: 32
- seed: 28
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
No log | 1.0 | 112 | 0.4455 | 0.77 | 0.8414 |
No log | 2.0 | 224 | 0.4557 | 0.8 | 0.8611 |
No log | 3.0 | 336 | 0.6409 | 0.8 | 0.8551 |
No log | 4.0 | 448 | 0.6648 | 0.82 | 0.8767 |
0.2723 | 5.0 | 560 | 0.8845 | 0.84 | 0.8873 |
0.2723 | 6.0 | 672 | 0.9873 | 0.84 | 0.8841 |
0.2723 | 7.0 | 784 | 1.0540 | 0.83 | 0.8777 |
0.2723 | 8.0 | 896 | 1.0712 | 0.85 | 0.8921 |
0.0161 | 9.0 | 1008 | 1.1467 | 0.84 | 0.8857 |
0.0161 | 10.0 | 1120 | 1.1650 | 0.83 | 0.8794 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1
- Datasets 2.14.4
- Tokenizers 0.13.3