README.md

metadata

language:
  - en
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - accuracy
model-index:
  - name: bert-base-uncased-mnli
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE MNLI
          type: glue
          args: mnli
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8500813669650122
      - task:
          type: natural-language-inference
          name: Natural Language Inference
        dataset:
          name: glue
          type: glue
          config: mnli_matched
          split: validation
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8467651553744269
            verified: true
          - name: Precision Macro
            type: precision
            value: 0.8460148987014974
            verified: true
          - name: Precision Micro
            type: precision
            value: 0.8467651553744269
            verified: true
          - name: Precision Weighted
            type: precision
            value: 0.8475656756385261
            verified: true
          - name: Recall Macro
            type: recall
            value: 0.8463172075485045
            verified: true
          - name: Recall Micro
            type: recall
            value: 0.8467651553744269
            verified: true
          - name: Recall Weighted
            type: recall
            value: 0.8467651553744269
            verified: true
          - name: F1 Macro
            type: f1
            value: 0.8459654597797398
            verified: true
          - name: F1 Micro
            type: f1
            value: 0.8467651553744269
            verified: true
          - name: F1 Weighted
            type: f1
            value: 0.8469586362613581
            verified: true
          - name: loss
            type: loss
            value: 0.42515239119529724
            verified: true

bert-base-uncased-mnli

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

• Loss: 0.4056
• Accuracy: 0.8501

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: 2e-05
• train_batch_size: 32
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4526	1.0	12272	0.4244	0.8388
0.3344	2.0	24544	0.4252	0.8469
0.2307	3.0	36816	0.4974	0.8445

Framework versions

• Transformers 4.20.0.dev0
• Pytorch 1.11.0+cu113
• Datasets 2.1.0
• Tokenizers 0.12.1