README.md

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
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: clinc_oos
          type: clinc_oos
          config: small
          split: test
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9147272727272727
            verified: true
          - name: Precision Macro
            type: precision
            value: 0.9134409304951565
            verified: true
          - name: Precision Micro
            type: precision
            value: 0.9147272727272727
            verified: true
          - name: Precision Weighted
            type: precision
            value: 0.9265787347428621
            verified: true
          - name: Recall Macro
            type: recall
            value: 0.9703421633554087
            verified: true
          - name: Recall Micro
            type: recall
            value: 0.9147272727272727
            verified: true
          - name: Recall Weighted
            type: recall
            value: 0.9147272727272727
            verified: true
          - name: F1 Macro
            type: f1
            value: 0.9383259127958784
            verified: true
          - name: F1 Micro
            type: f1
            value: 0.9147272727272727
            verified: true
          - name: F1 Weighted
            type: f1
            value: 0.9117668013116867
            verified: true
          - name: loss
            type: loss
            value: 0.4619016647338867
            verified: true

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