metadata
language:
- en
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: hBERTv1_new_pretrain_48_KD_w_init_mrpc
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE MRPC
type: glue
config: mrpc
split: validation
args: mrpc
metrics:
- name: Accuracy
type: accuracy
value: 0.7156862745098039
- name: F1
type: f1
value: 0.8104575163398692
hBERTv1_new_pretrain_48_KD_w_init_mrpc
This model is a fine-tuned version of gokuls/bert_12_layer_model_v1_complete_training_new_48_KD_wt_init on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5878
- Accuracy: 0.7157
- F1: 0.8105
- Combined Score: 0.7631
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 | Accuracy | F1 | Combined Score |
|---|---|---|---|---|---|---|
| 0.6514 | 1.0 | 29 | 0.6205 | 0.6887 | 0.8146 | 0.7517 |
| 0.619 | 2.0 | 58 | 0.6165 | 0.6618 | 0.7366 | 0.6992 |
| 0.6208 | 3.0 | 87 | 0.5878 | 0.7157 | 0.8105 | 0.7631 |
| 0.578 | 4.0 | 116 | 0.5952 | 0.7132 | 0.7986 | 0.7559 |
| 0.5612 | 5.0 | 145 | 0.5910 | 0.6936 | 0.7899 | 0.7418 |
| 0.4844 | 6.0 | 174 | 0.6261 | 0.6520 | 0.7290 | 0.6905 |
| 0.4281 | 7.0 | 203 | 0.6146 | 0.7010 | 0.7932 | 0.7471 |
| 0.3919 | 8.0 | 232 | 0.7273 | 0.6838 | 0.7795 | 0.7317 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.13.0
- Tokenizers 0.13.3