metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- nyu-mll/glue
metrics:
- matthews_correlation
model-index:
- name: bert-base-uncased-8-10-0.01
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: glue
type: glue
args: cola
metrics:
- type: matthews_correlation
value: 0
name: Matthews Correlation
bert-base-uncased-8-10-0.01
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: 0.8324
- Matthews Correlation: 0.0
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: 0.01
- 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 |
|---|---|---|---|---|
| No log | 1.0 | 400 | 0.8324 | 0.0 |
| 1.0904 | 2.0 | 800 | 1.3157 | 0.0 |
| 0.9461 | 3.0 | 1200 | 0.4407 | 0.0 |
| 0.9565 | 4.0 | 1600 | 2.1082 | 0.0 |
| 1.024 | 5.0 | 2000 | 0.7220 | 0.0 |
| 1.024 | 6.0 | 2400 | 0.7414 | 0.0 |
| 0.8362 | 7.0 | 2800 | 0.4442 | 0.0 |
| 0.6765 | 8.0 | 3200 | 0.5481 | 0.0 |
| 0.5902 | 9.0 | 3600 | 0.5642 | 0.0 |
| 0.5476 | 10.0 | 4000 | 0.4449 | 0.0 |
Framework versions
- Transformers 4.16.2
- Pytorch 1.9.0
- Datasets 1.18.3
- Tokenizers 0.11.0