nikoslefkos/relex

nikoslefkos/rebert_trex

This model is a fine-tuned version of distilbert-base-cased on relbert/t_rex.Containing 291 labels for examples with more than 100 occurences. It achieves the following results on the evaluation set:

• Train Loss: 0.8598
• Train Accuracy: 0.7326
• Validation Loss: 1.0456
• Validation Accuracy: 0.6906
• 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': 0.01, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Train Accuracy	Validation Loss	Validation Accuracy	Epoch
1.5343	0.6115	1.1212	0.6767	0
1.1175	0.6771	1.0503	0.6895	1
0.9745	0.7068	1.0405	0.6900	2
0.8598	0.7326	1.0456	0.6906	3

Framework versions

• Transformers 4.33.0
• TensorFlow 2.12.0
• Datasets 2.14.4
• Tokenizers 0.13.3