metadata
library_name: transformers
license: apache-2.0
base_model: google/bert_uncased_L-2_H-128_A-2
tags:
- generated_from_trainer
metrics:
- matthews_correlation
- accuracy
model-index:
- name: bert_uncased_L-2_H-128_A-2_cola
results: []
bert_uncased_L-2_H-128_A-2_cola
This model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6423
- Matthews Correlation: 0.0951
- Accuracy: 0.6433
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: 256
- eval_batch_size: 256
- seed: 10
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation | Accuracy |
|---|---|---|---|---|---|
| 0.6288 | 1.0 | 34 | 0.6191 | 0.0 | 0.6913 |
| 0.6087 | 2.0 | 68 | 0.6184 | 0.0 | 0.6913 |
| 0.6076 | 3.0 | 102 | 0.6176 | 0.0 | 0.6913 |
| 0.6066 | 4.0 | 136 | 0.6169 | 0.0 | 0.6913 |
| 0.605 | 5.0 | 170 | 0.6170 | 0.0 | 0.6913 |
| 0.6018 | 6.0 | 204 | 0.6164 | 0.0 | 0.6913 |
| 0.5976 | 7.0 | 238 | 0.6163 | 0.0 | 0.6913 |
| 0.5871 | 8.0 | 272 | 0.6159 | 0.0464 | 0.6922 |
| 0.5824 | 9.0 | 306 | 0.6155 | 0.0029 | 0.6903 |
| 0.5711 | 10.0 | 340 | 0.6198 | 0.0198 | 0.6702 |
| 0.5591 | 11.0 | 374 | 0.6221 | 0.0685 | 0.6721 |
| 0.5496 | 12.0 | 408 | 0.6284 | 0.1240 | 0.6702 |
| 0.5397 | 13.0 | 442 | 0.6350 | 0.1096 | 0.6548 |
| 0.529 | 14.0 | 476 | 0.6423 | 0.0951 | 0.6433 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3