distilbert-base-uncased-finetuned-banking77

This model is a fine-tuned version of distilbert-base-uncased on the banking77 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2935
  • Accuracy: 0.925
  • F1: 0.9250

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: 9.686210354742596e-05
  • train_batch_size: 64
  • eval_batch_size: 32
  • seed: 40
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Accuracy F1
No log 1.0 126 1.1457 0.7896 0.7685
No log 2.0 252 0.4673 0.8906 0.8889
No log 3.0 378 0.3488 0.9150 0.9151
0.9787 4.0 504 0.3238 0.9180 0.9179
0.9787 5.0 630 0.3126 0.9225 0.9226

Framework versions

  • Transformers 4.17.0
  • Pytorch 1.11.0
  • Datasets 2.0.0
  • Tokenizers 0.11.6
Downloads last month
72
Safetensors
Model size
67M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for optimum/distilbert-base-uncased-finetuned-banking77

Finetuned
(7065)
this model

Dataset used to train optimum/distilbert-base-uncased-finetuned-banking77

Evaluation results