README.md

metadata

language:
  - en
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
  - f1
model-index:
  - name: hBERTv2_mrpc
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE MRPC
          type: glue
          config: mrpc
          split: validation
          args: mrpc
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.6936274509803921
          - name: F1
            type: f1
            value: 0.8085758039816232

hBERTv2_mrpc

This model is a fine-tuned version of gokuls/bert_12_layer_model_v2 on the GLUE MRPC dataset. It achieves the following results on the evaluation set:

• Loss: 0.5772
• Accuracy: 0.6936
• F1: 0.8086
• Combined Score: 0.7511

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: 5e-05
• train_batch_size: 256
• eval_batch_size: 256
• 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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Accuracy	Combined Score	F1	Validation Loss
0.6388	1.0	15	0.6838	0.7480	0.8122	0.6297
0.612	2.0	30	0.6887	0.7511	0.8135	0.6315
0.5725	3.0	45	0.6936	0.7511	0.8086	0.5772
0.512	4.0	60	0.6261	0.7010	0.8152	0.7581
0.3924	5.0	75	0.6433	0.7279	0.8195	0.7737
0.2592	6.0	90	0.7531	0.6863	0.7594	0.7228
0.1689	7.0	105	0.7904	0.7377	0.8158	0.7768
0.1292	8.0	120	0.9954	0.7623	0.8381	0.8002

Framework versions

• Transformers 4.26.1
• Pytorch 1.14.0a0+410ce96
• Datasets 2.10.1
• Tokenizers 0.13.2