Apv/Flaubert_1106

Apv/Distilbert_1106

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

• Train Loss: 0.3007
• Validation Loss: 0.4962
• Train Accuracy: 0.8070
• Epoch: 6

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': 1432, '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
1.0860	0.8075	0.7018	0
0.6507	0.6038	0.7895	1
0.4485	0.5094	0.8095	2
0.3590	0.4962	0.8070	3
0.2974	0.4962	0.8070	4
0.3037	0.4962	0.8070	5
0.3007	0.4962	0.8070	6

Framework versions

• Transformers 4.30.1
• TensorFlow 2.12.0
• Datasets 2.12.0
• Tokenizers 0.13.3