README.md

metadata

language:
  - en
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: hBERTv1_new_pretrain_rte
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE RTE
          type: glue
          config: rte
          split: validation
          args: rte
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.4729241877256318

hBERTv1_new_pretrain_rte

This model is a fine-tuned version of gokuls/bert_12_layer_model_v1_complete_training_new on the GLUE RTE dataset. It achieves the following results on the evaluation set:

• Loss: 28.2681
• Accuracy: 0.4729

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: 0.0005
• 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
28.8034	1.0	20	28.2681	0.4729
28.8444	2.0	40	28.2681	0.4729
28.6738	3.0	60	28.2681	0.4729
29.3662	4.0	80	28.2681	0.4729
30.0413	5.0	100	28.2681	0.4729
28.4423	6.0	120	28.2681	0.4729

Framework versions

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