README.md

metadata

license: mit
base_model: FacebookAI/roberta-base
tags:
  - generated_from_trainer
datasets:
  - emotion
metrics:
  - accuracy
model-index:
  - name: my_model_nlp_workshop_2
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: emotion
          type: emotion
          config: split
          split: validation
          args: split
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.942

my_model_nlp_workshop_2

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

• Loss: 0.1369
• Accuracy: 0.942

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: 224
• 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
0.2639	1.0	1000	0.2136	0.9305
0.1664	2.0	2000	0.1485	0.9385
0.105	3.0	3000	0.1369	0.942

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2