distilbert-ft-test3

This model is a fine-tuned version of distilbert-base-uncased on thomasavare/waste-classification-v2. It is part of my master thesis at Politecnico di Torino in partenership with ReLearn.

It achieves the following results on the test set:

accuracy	precision	recall	f1
0.974	0.9805	0.9732	0.9725

Model description

DistilBERT finetuned for waste classification on 50 different classes as part of my master thesis at Politecnico di Torino.

Intended uses & limitations

Use for waste classification on 50 different waste classes (see dataset)

Training and evaluation data

waste-classification-v2 dataset

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 5e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
• training_precision: float32

Training results

Framework versions

• Transformers 4.28.1
• TensorFlow 2.12.0
• Datasets 2.12.0
• Tokenizers 0.13.3