metadata

language:
  - en
base_model: gokuls/bert_12_layer_model_v2_complete_training_new_48
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: hBERTv2_new_pretrain_48_ver2_wnli
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE WNLI
          type: glue
          config: wnli
          split: validation
          args: wnli
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.5633802816901409

hBERTv2_new_pretrain_48_ver2_wnli

This model is a fine-tuned version of gokuls/bert_12_layer_model_v2_complete_training_new_48 on the GLUE WNLI dataset. It achieves the following results on the evaluation set:

Loss: 0.6858
Accuracy: 0.5634

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
0.8132	1.0	10	0.7425	0.4366
0.7131	2.0	20	0.6970	0.4366
0.7083	3.0	30	0.6858	0.5634
0.6956	4.0	40	0.6939	0.5352
0.7103	5.0	50	0.7313	0.4366
0.7169	6.0	60	0.7041	0.4366
0.7039	7.0	70	0.6862	0.5634
0.7041	8.0	80	0.6919	0.5352

Framework versions

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