metadata
language:
- en
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- matthews_correlation
model-index:
- name: mobilebert_add_GLUE_Experiment_logit_kd_cola
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE COLA
type: glue
config: cola
split: validation
args: cola
metrics:
- name: Matthews Correlation
type: matthews_correlation
value: -0.007887379670285008
mobilebert_add_GLUE_Experiment_logit_kd_cola
This model is a fine-tuned version of google/mobilebert-uncased on the GLUE COLA dataset. It achieves the following results on the evaluation set:
- Loss: 0.6744
- Matthews Correlation: -0.0079
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: 128
- eval_batch_size: 128
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|---|---|---|---|---|
| 0.8111 | 1.0 | 67 | 0.6859 | 0.0 |
| 0.7968 | 2.0 | 134 | 0.6865 | 0.0 |
| 0.796 | 3.0 | 201 | 0.6835 | 0.0 |
| 0.7938 | 4.0 | 268 | 0.6813 | 0.0 |
| 0.7828 | 5.0 | 335 | 0.6768 | 0.0 |
| 0.7651 | 6.0 | 402 | 0.6750 | 0.0 |
| 0.7594 | 7.0 | 469 | 0.6960 | 0.0 |
| 0.7592 | 8.0 | 536 | 0.6800 | 0.0 |
| 0.7463 | 9.0 | 603 | 0.6789 | 0.0 |
| 0.7437 | 10.0 | 670 | 0.6795 | 0.0 |
| 0.7401 | 11.0 | 737 | 0.6745 | -0.0079 |
| 0.7398 | 12.0 | 804 | 0.6744 | -0.0079 |
| 0.7328 | 13.0 | 871 | 0.6813 | 0.0587 |
| 0.7321 | 14.0 | 938 | 0.6881 | 0.0794 |
| 0.7315 | 15.0 | 1005 | 0.6784 | 0.0615 |
| 0.7295 | 16.0 | 1072 | 0.6816 | 0.0385 |
| 0.7297 | 17.0 | 1139 | 0.6986 | 0.0503 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2