YSKartal/scibert_scivocab_uncased-finetuned-2-ref_disam

This model is a fine-tuned version of allenai/scibert_scivocab_uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 4.3345
• Validation Loss: 5.5243
• Train Accuracy: 0.1562
• Epoch: 3

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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 16308, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, '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
6.8503	6.9170	0.0323	0
5.7494	6.3086	0.0738	1
4.9365	5.8427	0.1206	2
4.3345	5.5243	0.1562	3

Framework versions

• Transformers 4.27.4
• TensorFlow 2.12.0
• Datasets 2.11.0
• Tokenizers 0.13.2