metadata
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- matthews_correlation
model-index:
- name: mobilebert_sa_GLUE_Experiment_cola
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: glue
type: glue
config: cola
split: train
args: cola
metrics:
- name: Matthews Correlation
type: matthews_correlation
value: 0.09007205990892461
mobilebert_sa_GLUE_Experiment_cola
This model is a fine-tuned version of on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.6893
- Matthews Correlation: 0.0901
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
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|---|---|---|---|---|
| 0.6197 | 1.0 | 34 | 0.6239 | 0.0 |
| 0.6078 | 2.0 | 68 | 0.6179 | 0.0 |
| 0.6064 | 3.0 | 102 | 0.6180 | 0.0 |
| 0.6073 | 4.0 | 136 | 0.6176 | 0.0 |
| 0.6069 | 5.0 | 170 | 0.6173 | 0.0 |
| 0.6043 | 6.0 | 204 | 0.6166 | 0.0 |
| 0.6004 | 7.0 | 238 | 0.6131 | 0.0 |
| 0.5842 | 8.0 | 272 | 0.6241 | 0.0951 |
| 0.5192 | 9.0 | 306 | 0.6362 | 0.0598 |
| 0.4884 | 10.0 | 340 | 0.7010 | 0.0801 |
| 0.4559 | 11.0 | 374 | 0.6731 | 0.0905 |
| 0.4367 | 12.0 | 408 | 0.6893 | 0.0901 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.14.0a0+410ce96
- Datasets 2.8.0
- Tokenizers 0.13.2