README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - emotion
metrics:
  - accuracy
model-index:
  - name: sagemaker-distilbert-emotion-1
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: emotion
          type: emotion
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9325
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: emotion
          type: emotion
          config: default
          split: test
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9325
            verified: true
          - name: Precision Macro
            type: precision
            value: 0.8890885758596073
            verified: true
          - name: Precision Micro
            type: precision
            value: 0.9325
            verified: true
          - name: Precision Weighted
            type: precision
            value: 0.9357939294839482
            verified: true
          - name: Recall Macro
            type: recall
            value: 0.9037949715525094
            verified: true
          - name: Recall Micro
            type: recall
            value: 0.9325
            verified: true
          - name: Recall Weighted
            type: recall
            value: 0.9325
            verified: true
          - name: F1 Macro
            type: f1
            value: 0.8917817566377219
            verified: true
          - name: F1 Micro
            type: f1
            value: 0.9325
            verified: true
          - name: F1 Weighted
            type: f1
            value: 0.932691644399741
            verified: true
          - name: loss
            type: loss
            value: 0.16507503390312195
            verified: true

sagemaker-distilbert-emotion-1

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: 0.1651
• Accuracy: 0.9325

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: 3e-05
• train_batch_size: 32
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.966	1.0	500	0.2497	0.921
0.1913	2.0	1000	0.1651	0.9325
0.1037	3.0	1500	0.1501	0.9285

Framework versions

• Transformers 4.12.3
• Pytorch 1.9.1
• Datasets 1.15.1
• Tokenizers 0.10.3