metadata
library_name: transformers
license: apache-2.0
base_model: albert/albert-base-v2
tags:
- generated_from_keras_callback
model-index:
- name: classiv1_albert_model
results: []
classiv1_albert_model
This model is a fine-tuned version of albert/albert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.1577
- Train Accuracy: 0.9334
- Validation Loss: 0.2818
- Validation Accuracy: 0.8990
- 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': 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': np.float32(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 |
|---|---|---|---|---|
| 0.9344 | 0.6647 | 0.4468 | 0.8440 | 0 |
| 0.2788 | 0.9076 | 0.2503 | 0.9170 | 1 |
| 0.1689 | 0.9293 | 0.2698 | 0.9110 | 2 |
| 0.1577 | 0.9334 | 0.2818 | 0.8990 | 3 |
Framework versions
- Transformers 4.52.4
- TensorFlow 2.19.0
- Datasets 3.6.0
- Tokenizers 0.21.1