metadata
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- matthews_correlation
- accuracy
model-index:
- name: hBERTv2_new_pretrain_w_init_48_cola
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: 0.13982593577610886
- name: Accuracy
type: accuracy
value: 0.6768935918807983
hBERTv2_new_pretrain_w_init_48_cola
This model is a fine-tuned version of gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_48 on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.9018
- Matthews Correlation: 0.1398
- Accuracy: 0.6769
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 |
|---|---|---|---|---|---|
| 0.6301 | 1.0 | 67 | 0.6293 | 0.0 | 0.6913 |
| 0.6238 | 2.0 | 134 | 0.6254 | 0.0 | 0.6913 |
| 0.6072 | 3.0 | 201 | 0.6271 | 0.0339 | 0.6759 |
| 0.5821 | 4.0 | 268 | 0.6191 | 0.0821 | 0.6836 |
| 0.5262 | 5.0 | 335 | 0.7057 | 0.1151 | 0.6510 |
| 0.4735 | 6.0 | 402 | 0.6756 | 0.1181 | 0.6577 |
| 0.4127 | 7.0 | 469 | 0.8493 | 0.1229 | 0.6711 |
| 0.349 | 8.0 | 536 | 0.8919 | 0.1434 | 0.6232 |
| 0.311 | 9.0 | 603 | 0.9018 | 0.1398 | 0.6769 |
Framework versions
- Transformers 4.29.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3