README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - emotion
metrics:
  - accuracy
model-index:
  - name: multi-class-classification
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: emotion
          type: emotion
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.928
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: emotion
          type: emotion
          config: default
          split: test
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9185
            verified: true
          - name: Precision Macro
            type: precision
            value: 0.8738350796775306
            verified: true
          - name: Precision Micro
            type: precision
            value: 0.9185
            verified: true
          - name: Precision Weighted
            type: precision
            value: 0.9179425177997311
            verified: true
          - name: Recall Macro
            type: recall
            value: 0.8650962919021573
            verified: true
          - name: Recall Micro
            type: recall
            value: 0.9185
            verified: true
          - name: Recall Weighted
            type: recall
            value: 0.9185
            verified: true
          - name: F1 Macro
            type: f1
            value: 0.8692821860210945
            verified: true
          - name: F1 Micro
            type: f1
            value: 0.9185
            verified: true
          - name: F1 Weighted
            type: f1
            value: 0.9181177508591364
            verified: true
          - name: loss
            type: loss
            value: 0.20905950665473938
            verified: true
          - name: matthews_correlation
            type: matthews_correlation
            value: 0.8920254536671932
            verified: true
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: emotion
          type: emotion
          config: default
          split: validation
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.928
            verified: true
          - name: Precision Macro
            type: precision
            value: 0.9021100779342405
            verified: true
          - name: Precision Micro
            type: precision
            value: 0.928
            verified: true
          - name: Precision Weighted
            type: precision
            value: 0.9280919251001837
            verified: true
          - name: Recall Macro
            type: recall
            value: 0.8968051962257172
            verified: true
          - name: Recall Micro
            type: recall
            value: 0.928
            verified: true
          - name: Recall Weighted
            type: recall
            value: 0.928
            verified: true
          - name: F1 Macro
            type: f1
            value: 0.8991718089322509
            verified: true
          - name: F1 Micro
            type: f1
            value: 0.928
            verified: true
          - name: F1 Weighted
            type: f1
            value: 0.9279314819862883
            verified: true
          - name: loss
            type: loss
            value: 0.20090055465698242
            verified: true
          - name: pearsonr
            type: pearsonr
            value: 0.9157453001659976
            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