metadata

language:
  - en
base_model: gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
  - f1
model-index:
  - name: hBERTv1_new_pretrain_w_init_48_ver2_qqp
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE QQP
          type: glue
          config: qqp
          split: validation
          args: qqp
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.7601038832550087
          - name: F1
            type: f1
            value: 0.6952012821721505

hBERTv1_new_pretrain_w_init_48_ver2_qqp

This model is a fine-tuned version of gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48 on the GLUE QQP dataset. It achieves the following results on the evaluation set:

Loss: 0.4918
Accuracy: 0.7601
F1: 0.6952
Combined Score: 0.7277

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: 64
eval_batch_size: 64
seed: 10
distributed_type: multi-GPU
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Combined Score
0.5279	1.0	5686	0.4918	0.7601	0.6952	0.7277
0.4826	2.0	11372	0.5367	0.7644	0.6556	0.7100
0.4943	3.0	17058	0.5223	0.7594	0.6440	0.7017
0.492	4.0	22744	0.5379	0.7600	0.6465	0.7032
0.505	5.0	28430	0.5431	0.7423	0.6507	0.6965
0.5428	6.0	34116	0.5789	0.7089	0.6289	0.6689

Framework versions

Transformers 4.34.0
Pytorch 1.14.0a0+410ce96
Datasets 2.14.5
Tokenizers 0.14.1