README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - emotion
metrics:
  - accuracy
  - f1
model_index:
  - name: distilbert-base-uncased-finetuned-emotion
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: emotion
          type: emotion
          args: default
        metric:
          name: F1
          type: f1
          value: 0.9327347950817506
model-index:
  - name: jsoutherland/distilbert-base-uncased-finetuned-emotion
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: emotion
          type: emotion
          config: default
          split: test
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.925
            verified: true
          - name: Precision Macro
            type: precision
            value: 0.8954208010579672
            verified: true
          - name: Precision Micro
            type: precision
            value: 0.925
            verified: true
          - name: Precision Weighted
            type: precision
            value: 0.9256567173431012
            verified: true
          - name: Recall Macro
            type: recall
            value: 0.8711059962680445
            verified: true
          - name: Recall Micro
            type: recall
            value: 0.925
            verified: true
          - name: Recall Weighted
            type: recall
            value: 0.925
            verified: true
          - name: F1 Macro
            type: f1
            value: 0.8794773714607985
            verified: true
          - name: F1 Micro
            type: f1
            value: 0.925
            verified: true
          - name: F1 Weighted
            type: f1
            value: 0.9244781949774824
            verified: true
          - name: loss
            type: loss
            value: 0.17752596735954285
            verified: true

distilbert-base-uncased-finetuned-emotion

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: 0.1649
• Accuracy: 0.9325
• F1: 0.9327

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	1.0	250	0.2838	0.9065	0.9036
No log	2.0	500	0.1795	0.9255	0.9255
No log	3.0	750	0.1649	0.9325	0.9327

Framework versions

• Transformers 4.8.2
• Pytorch 1.9.0+cu102
• Datasets 2.1.0
• Tokenizers 0.10.3