metadata
library_name: transformers
license: apache-2.0
base_model: google/bert_uncased_L-4_H-128_A-2
tags:
- generated_from_trainer
metrics:
- matthews_correlation
- accuracy
model-index:
- name: bert_uncased_L-4_H-128_A-2_cola
results: []
bert_uncased_L-4_H-128_A-2_cola
This model is a fine-tuned version of google/bert_uncased_L-4_H-128_A-2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6383
- Matthews Correlation: 0.1031
- Accuracy: 0.6548
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 |
|---|---|---|---|---|---|
| 0.6362 | 1.0 | 34 | 0.6191 | 0.0 | 0.6913 |
| 0.608 | 2.0 | 68 | 0.6191 | 0.0 | 0.6913 |
| 0.607 | 3.0 | 102 | 0.6168 | 0.0 | 0.6913 |
| 0.6055 | 4.0 | 136 | 0.6145 | 0.0 | 0.6913 |
| 0.6009 | 5.0 | 170 | 0.6107 | 0.0 | 0.6913 |
| 0.5939 | 6.0 | 204 | 0.6092 | 0.0 | 0.6913 |
| 0.5799 | 7.0 | 238 | 0.6168 | 0.0855 | 0.6951 |
| 0.5679 | 8.0 | 272 | 0.6162 | 0.0848 | 0.6913 |
| 0.5553 | 9.0 | 306 | 0.6236 | 0.0638 | 0.6855 |
| 0.5361 | 10.0 | 340 | 0.6316 | 0.0837 | 0.6587 |
| 0.5249 | 11.0 | 374 | 0.6383 | 0.1031 | 0.6548 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3