metadata
license: mit
base_model: roberta-base
tags:
- generated_from_keras_callback
model-index:
- name: jmassot/masked-lm-tpu
results: []
jmassot/masked-lm-tpu
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 9.8173
- Train Accuracy: 0.0164
- Validation Loss: 9.6999
- Validation Accuracy: 0.0210
- 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': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 0.0001, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0001, 'decay_steps': 22325, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'passive_serialization': True}, 'warmup_steps': 1175, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.001}
- training_precision: float32
Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|---|---|---|---|---|
| 10.2539 | 0.0 | 10.2414 | 0.0000 | 0 |
| 10.2396 | 0.0000 | 10.2294 | 0.0000 | 1 |
| 10.2338 | 0.0000 | 10.2031 | 0.0000 | 2 |
| 10.2003 | 0.0000 | 10.1587 | 0.0000 | 3 |
| 10.1691 | 0.0 | 10.1081 | 0.0 | 4 |
| 10.1135 | 0.0000 | 10.0415 | 0.0001 | 5 |
| 10.0630 | 0.0001 | 9.9697 | 0.0013 | 6 |
| 9.9906 | 0.0011 | 9.8881 | 0.0097 | 7 |
| 9.9059 | 0.0070 | 9.7998 | 0.0183 | 8 |
| 9.8173 | 0.0164 | 9.6999 | 0.0210 | 9 |
Framework versions
- Transformers 4.35.0
- TensorFlow 2.12.0
- Tokenizers 0.14.1