vedantjumle/indo-ml-final-test-xlnet-1

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

• Train Loss: 0.7254
• Validation Loss: 0.6440
• Train Accuracy: 0.88
• 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': 6000, '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
5.1411	5.0487	0.01	0
5.0561	4.8924	0.0267	1
4.8362	4.4063	0.2033	2
4.2361	3.4961	0.45	3
3.3575	2.5506	0.6167	4
2.5070	1.8625	0.74	5
1.8507	1.3431	0.8067	6
1.3367	0.9980	0.84	7
0.9787	0.7747	0.86	8
0.7254	0.6440	0.88	9

Framework versions

• Transformers 4.34.0
• TensorFlow 2.13.0
• Datasets 2.14.5
• Tokenizers 0.14.1