README.md

metadata

language:
  - en
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: mobilebert_sa_GLUE_Experiment_logit_kd_qnli
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE QNLI
          type: glue
          config: qnli
          split: validation
          args: qnli
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.615595826468973

mobilebert_sa_GLUE_Experiment_logit_kd_qnli

This model is a fine-tuned version of google/mobilebert-uncased on the GLUE QNLI dataset. It achieves the following results on the evaluation set:

• Loss: 0.9573
• Accuracy: 0.6156

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: 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
1.0984	1.0	819	0.9626	0.6220
1.0171	2.0	1638	0.9573	0.6156
0.9717	3.0	2457	0.9651	0.6105
0.9377	4.0	3276	0.9713	0.6024
0.9132	5.0	4095	0.9812	0.5988
0.89	6.0	4914	1.0108	0.5982
0.8683	7.0	5733	1.0290	0.5914

Framework versions

• Transformers 4.26.0
• Pytorch 1.14.0a0+410ce96
• Datasets 2.9.0
• Tokenizers 0.13.2