metadata
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: jganzabalseenka/bert-on-glue-ds
results: []
jganzabalseenka/bert-on-glue-ds
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.6481
- Train Accuracy: 0.6600
- Validation Loss: 0.6265
- Validation Accuracy: 0.6838
- Epoch: 7
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': 0.001, '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 |
|---|---|---|---|---|
| 0.6820 | 0.6379 | 0.9020 | 0.6838 | 0 |
| 0.6714 | 0.6429 | 0.6782 | 0.6838 | 1 |
| 0.6742 | 0.6461 | 0.6520 | 0.6838 | 2 |
| 0.6923 | 0.6287 | 0.6333 | 0.6838 | 3 |
| 0.6743 | 0.6363 | 0.6259 | 0.6838 | 4 |
| 0.6697 | 0.6423 | 0.6365 | 0.6838 | 5 |
| 0.6587 | 0.6505 | 0.6273 | 0.6838 | 6 |
| 0.6481 | 0.6600 | 0.6265 | 0.6838 | 7 |
Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3