metadata
license: mit
base_model: xlnet/xlnet-base-cased
tags:
- generated_from_keras_callback
model-index:
- name: lamia6001/xlnet-base
results: []
lamia6001/xlnet-base
This model is a fine-tuned version of xlnet/xlnet-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.1395
- Train Accuracy: 0.936
- Validation Loss: 0.1985
- Validation Accuracy: 0.9360
- Train Precision: 0.9386
- Train Recall: 0.936
- Train F1: 0.9353
- Epoch: 2
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': 5000, '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 | Train Accuracy | Validation Loss | Validation Accuracy | Train Precision | Train Recall | Train F1 | Epoch |
|---|---|---|---|---|---|---|---|
| 0.6647 | 0.9205 | 0.2528 | 0.9205 | 0.9226 | 0.9205 | 0.9200 | 0 |
| 0.1997 | 0.931 | 0.1945 | 0.9310 | 0.9330 | 0.931 | 0.9305 | 1 |
| 0.1395 | 0.936 | 0.1985 | 0.9360 | 0.9386 | 0.936 | 0.9353 | 2 |
Framework versions
- Transformers 4.38.2
- TensorFlow 2.15.0
- Datasets 2.18.0
- Tokenizers 0.15.2