metadata

language:
  - en
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: hBERTv2_new_pretrain_w_init_48_mnli
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE MNLI
          type: glue
          config: mnli
          split: validation_matched
          args: mnli
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.730166802278275

hBERTv2_new_pretrain_w_init_48_mnli

This model is a fine-tuned version of gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_48 on the GLUE MNLI dataset. It achieves the following results on the evaluation set:

Loss: 0.6485
Accuracy: 0.7302

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
0.9886	1.0	3068	0.8886	0.6062
0.7987	2.0	6136	0.7297	0.6876
0.6963	3.0	9204	0.6939	0.7117
0.6249	4.0	12272	0.6649	0.7244
0.5633	5.0	15340	0.6887	0.7289
0.5075	6.0	18408	0.6931	0.7329
0.4547	7.0	21476	0.6907	0.7326
0.4109	8.0	24544	0.7298	0.7333
0.3636	9.0	27612	0.7582	0.7340

Framework versions

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