spanbert-base-cased / README.md
ahmetayrnc's picture
update model card README.md
22ef16c
|
raw
history blame
2.26 kB
metadata
tags:
  - generated_from_trainer
datasets:
  - silicone
metrics:
  - accuracy
model-index:
  - name: spanbert-base-cased
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: silicone
          type: silicone
          config: swda
          split: test
          args: swda
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.7114959469417833

spanbert-base-cased

This model is a fine-tuned version of SpanBERT/spanbert-base-cased on the silicone dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0346
  • Accuracy: 0.7115
  • Micro-precision: 0.7115
  • Micro-recall: 0.7115
  • Micro-f1: 0.7115
  • Macro-precision: 0.2484
  • Macro-recall: 0.2508
  • Macro-f1: 0.2412
  • Weighted-precision: 0.6569
  • Weighted-recall: 0.7115
  • Weighted-f1: 0.6741

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: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss Accuracy Micro-precision Micro-recall Micro-f1 Macro-precision Macro-recall Macro-f1 Weighted-precision Weighted-recall Weighted-f1
1.043 1.0 2980 1.0346 0.7115 0.7115 0.7115 0.7115 0.2484 0.2508 0.2412 0.6569 0.7115 0.6741

Framework versions

  • Transformers 4.26.0
  • Pytorch 1.13.1+cu116
  • Datasets 2.9.0
  • Tokenizers 0.13.2