lewtun's picture
lewtun HF staff
End of training
1e90b7d
metadata
license: mit
tags:
  - generated_from_trainer
datasets:
  - clinc_oos
metrics:
  - accuracy
model-index:
  - name: roberta-large-finetuned-clinc
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: clinc_oos
          type: clinc_oos
          args: plus
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9767741935483871

roberta-large-finetuned-clinc

This model is a fine-tuned version of roberta-large on the clinc_oos dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1545
  • Accuracy: 0.9768

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
  • distributed_type: sagemaker_data_parallel
  • num_devices: 8
  • total_train_batch_size: 128
  • total_eval_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 5
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
5.0548 1.0 120 5.0359 0.0071
4.4725 2.0 240 2.9385 0.7558
1.8924 3.0 360 0.6456 0.9374
0.4552 4.0 480 0.2297 0.9626
0.1589 5.0 600 0.1545 0.9768

Framework versions

  • Transformers 4.17.0
  • Pytorch 1.10.2+cu113
  • Datasets 1.18.4
  • Tokenizers 0.11.6