metadata

language:
  - en
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - matthews_correlation
  - accuracy
model-index:
  - name: hBERTv2_new_pretrain_48_emb_com_cola
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE COLA
          type: glue
          config: cola
          split: validation
          args: cola
        metrics:
          - name: Matthews Correlation
            type: matthews_correlation
            value: 0
          - name: Accuracy
            type: accuracy
            value: 0.6912751793861389

hBERTv2_new_pretrain_48_emb_com_cola

This model is a fine-tuned version of gokuls/bert_12_layer_model_v2_complete_training_new_emb_compress_48 on the GLUE COLA dataset. It achieves the following results on the evaluation set:

Loss: 0.6181
Matthews Correlation: 0.0
Accuracy: 0.6913

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
0.6308	1.0	67	0.6420	0.6913
0.6219	2.0	134	0.6212	0.6913
0.6122	3.0	201	0.6237	0.6913
0.6165	4.0	268	0.6198	0.6913
0.6133	5.0	335	0.6236	0.6913
0.6105	6.0	402	0.6181	0.6913
0.6132	7.0	469	0.6288	0.6913
0.61	8.0	536	0.6188	0.6913
0.6103	9.0	603	0.6252	0.6913
0.6099	10.0	670	0.6301	0.6913
0.6091	11.0	737	0.6183	0.6913

Framework versions

Transformers 4.30.2
Pytorch 1.14.0a0+410ce96
Datasets 2.12.0
Tokenizers 0.13.3