<!-- 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-cola-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: 1.3812
- Matthews Correlation: 0.5436
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 | Matthews Correlation |
---|---|---|---|---|
No log | 1.0 | 265 | 0.5922 | 0.4074 |
0.4065 | 2.0 | 530 | 0.4494 | 0.6144 |
0.4065 | 3.0 | 795 | 0.4548 | 0.5738 |
0.1623 | 4.0 | 1060 | 0.6883 | 0.5687 |
0.1623 | 5.0 | 1325 | 0.7222 | 0.5183 |
0.081 | 6.0 | 1590 | 1.0246 | 0.5371 |
0.081 | 7.0 | 1855 | 1.1457 | 0.5145 |
0.0344 | 8.0 | 2120 | 1.1771 | 0.5436 |
0.0344 | 9.0 | 2385 | 1.3187 | 0.5485 |
0.0123 | 10.0 | 2650 | 1.3812 | 0.5436 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1
- Datasets 2.14.4
- Tokenizers 0.13.3