README.md

metadata

language:
  - en
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: hBERTv1_no_pretrain_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: 0.3522172497965826

hBERTv1_no_pretrain_mnli

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

• Loss: 1.0982
• Accuracy: 0.3522

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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.1069	1.0	3068	1.0985	0.3545
1.0987	2.0	6136	1.0986	0.3182
1.0986	3.0	9204	1.0984	0.3274
1.0986	4.0	12272	1.0982	0.3545
1.0986	5.0	15340	1.0984	0.3545
1.0985	6.0	18408	nan	0.3545
0.0	7.0	21476	nan	0.3545
0.0	8.0	24544	nan	0.3545
0.0	9.0	27612	nan	0.3545

Framework versions

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