metadata
language:
- en
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- matthews_correlation
- accuracy
model-index:
- name: hBERTv1_new_pretrain_48_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
- name: Accuracy
type: accuracy
value: 0.6912751793861389
hBERTv1_new_pretrain_48_cola
This model is a fine-tuned version of gokuls/bert_12_layer_model_v1_complete_training_new_48 on the GLUE COLA dataset. It achieves the following results on the evaluation set:
- Loss: 0.6153
- Matthews Correlation: 0.0
- Accuracy: 0.6913
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: 4e-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 | Accuracy |
---|---|---|---|---|---|
0.6296 | 1.0 | 67 | 0.6343 | 0.0 | 0.6913 |
0.6166 | 2.0 | 134 | 0.6423 | 0.0 | 0.6913 |
0.611 | 3.0 | 201 | 0.6202 | 0.0 | 0.6913 |
0.6085 | 4.0 | 268 | 0.6188 | 0.0 | 0.6913 |
0.6107 | 5.0 | 335 | 0.6153 | 0.0 | 0.6913 |
0.5988 | 6.0 | 402 | 0.6260 | 0.0 | 0.6913 |
0.5826 | 7.0 | 469 | 0.6354 | 0.0 | 0.6913 |
0.5536 | 8.0 | 536 | 0.6534 | 0.0304 | 0.6539 |
0.5402 | 9.0 | 603 | 0.6798 | 0.0917 | 0.5954 |
0.5341 | 10.0 | 670 | 0.7670 | 0.0513 | 0.6836 |
Framework versions
- Transformers 4.29.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3