metadata
language:
- en
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: hBERTv2_new_pretrain_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: 0.7034313725490197
- name: F1
type: f1
value: 0.8118195956454122
hBERTv2_new_pretrain_mrpc
This model is a fine-tuned version of gokuls/bert_12_layer_model_v2_complete_training_new on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5990
- Accuracy: 0.7034
- F1: 0.8118
- Combined Score: 0.7576
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 |
|---|---|---|---|---|---|---|
| 0.6721 | 1.0 | 29 | 0.6200 | 0.6838 | 0.8122 | 0.7480 |
| 0.6229 | 2.0 | 58 | 0.6098 | 0.6569 | 0.7255 | 0.6912 |
| 0.5689 | 3.0 | 87 | 0.5990 | 0.7034 | 0.8118 | 0.7576 |
| 0.4615 | 4.0 | 116 | 0.6689 | 0.6765 | 0.78 | 0.7282 |
| 0.3475 | 5.0 | 145 | 0.8472 | 0.6054 | 0.6774 | 0.6414 |
| 0.2307 | 6.0 | 174 | 0.9917 | 0.6103 | 0.6913 | 0.6508 |
| 0.166 | 7.0 | 203 | 1.1149 | 0.6544 | 0.7522 | 0.7033 |
| 0.1258 | 8.0 | 232 | 1.3516 | 0.625 | 0.7119 | 0.6684 |
Framework versions
- Transformers 4.29.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3