OpenAlex/distilbert-base-cased-finetuned-topic-classification-title-abstract

distilbert-base-cased-finetuned-concept-classification-title-abstract

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

• Train Loss: 2.8398
• Validation Loss: 3.2378
• Train Accuracy: 0.4618
• Epoch: 9

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:

• 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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 167960, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Validation Loss	Train Accuracy	Epoch
5.1779	3.9338	0.3457	0
3.8441	3.5523	0.4044	1
3.5070	3.4169	0.4267	2
3.3152	3.3286	0.4402	3
3.1797	3.2789	0.4488	4
3.0756	3.2612	0.4537	5
2.9929	3.2459	0.4575	6
2.9266	3.2380	0.4598	7
2.8758	3.2390	0.4611	8
2.8398	3.2378	0.4618	9

Framework versions

• Transformers 4.35.2
• TensorFlow 2.13.0
• Datasets 2.15.0
• Tokenizers 0.15.0