metadata
license: apache-2.0
base_model: distilroberta-base
tags:
- generated_from_keras_callback
model-index:
- name: rubakha/roberta
results: []
rubakha/roberta
This model is a fine-tuned version of distilroberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.1366
- Train Accuracy: 0.942
- Validation Loss: 0.1600
- Validation Accuracy: 0.9420
- Train Precision: 0.9442
- Train Recall: 0.942
- Train F1: 0.9417
- 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 |
|---|---|---|---|---|---|---|---|
| 0.4729 | 0.928 | 0.2098 | 0.9280 | 0.9292 | 0.928 | 0.9275 | 0 |
| 0.1705 | 0.94 | 0.1964 | 0.9400 | 0.9434 | 0.94 | 0.9395 | 1 |
| 0.1366 | 0.942 | 0.1600 | 0.9420 | 0.9442 | 0.942 | 0.9417 | 2 |
Framework versions
- Transformers 4.38.2
- TensorFlow 2.15.0
- Datasets 2.18.0
- Tokenizers 0.15.2