metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- matthews_correlation
model-index:
- name: bert-base-uncased-finetuned-cola-batch-8
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: glue
type: glue
config: cola
split: validation
args: cola
metrics:
- name: Matthews Correlation
type: matthews_correlation
value: 0.5909903281139832
bert-base-uncased-finetuned-cola-batch-8
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: 0.6364
- Matthews Correlation: 0.5910
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: 2e-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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|---|---|---|---|---|
| 0.4737 | 1.0 | 1069 | 0.6579 | 0.4918 |
| 0.3331 | 2.0 | 2138 | 0.6364 | 0.5910 |
| 0.2223 | 3.0 | 3207 | 0.8108 | 0.5658 |
| 0.1445 | 4.0 | 4276 | 0.9036 | 0.5832 |
| 0.0841 | 5.0 | 5345 | 1.0537 | 0.5727 |
| 0.0634 | 6.0 | 6414 | 1.2565 | 0.5763 |
| 0.0384 | 7.0 | 7483 | 1.2944 | 0.5881 |
| 0.0278 | 8.0 | 8552 | 1.3246 | 0.5902 |
| 0.0251 | 9.0 | 9621 | 1.4406 | 0.5651 |
| 0.0091 | 10.0 | 10690 | 1.4599 | 0.5685 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3