metadata

language:
  - en
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: hBERTv1_new_pretrain_w_init__sst2
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE SST2
          type: glue
          config: sst2
          split: validation
          args: sst2
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8038990825688074

hBERTv1_new_pretrain_w_init__sst2

This model is a fine-tuned version of gokuls/bert_12_layer_model_v1_complete_training_new_wt_init on the GLUE SST2 dataset. It achieves the following results on the evaluation set:

Loss: 0.4606
Accuracy: 0.8039

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
0.363	1.0	527	0.4606	0.8039
0.2256	2.0	1054	0.6466	0.8119
0.1754	3.0	1581	0.5101	0.8177
0.1394	4.0	2108	0.4921	0.8177
0.1111	5.0	2635	0.5110	0.8200
0.0937	6.0	3162	0.6468	0.8211

Framework versions

Transformers 4.29.2
Pytorch 1.14.0a0+410ce96
Datasets 2.12.0
Tokenizers 0.13.3