README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - emotion
metrics:
  - accuracy
model-index:
  - name: autoevaluate/multi-class-classification
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: emotion
          type: emotion
          config: default
          split: test
        metrics:
          - type: accuracy
            value: 0.9185
            name: Accuracy
            verified: true
          - type: precision
            value: 0.8738350796775306
            name: Precision Macro
            verified: true
          - type: precision
            value: 0.9185
            name: Precision Micro
            verified: true
          - type: precision
            value: 0.9179425177997311
            name: Precision Weighted
            verified: true
          - type: recall
            value: 0.8650962919021573
            name: Recall Macro
            verified: true
          - type: recall
            value: 0.9185
            name: Recall Micro
            verified: true
          - type: recall
            value: 0.9185
            name: Recall Weighted
            verified: true
          - type: f1
            value: 0.8692821860210945
            name: F1 Macro
            verified: true
          - type: f1
            value: 0.9185
            name: F1 Micro
            verified: true
          - type: f1
            value: 0.9181177508591364
            name: F1 Weighted
            verified: true
          - type: loss
            value: 0.20907790958881378
            name: loss
            verified: true

multi-class-classification

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

• Loss: 0.2009
• Accuracy: 0.928

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2643	1.0	1000	0.2009	0.928

Framework versions

• Transformers 4.19.2
• Pytorch 1.11.0+cu113
• Datasets 2.2.2
• Tokenizers 0.12.1