metadata
license: apache-2.0
tags:
- generated_from_keras_callback
base_model: distilroberta-base
model-index:
- name: mlm_soft_finetune_bert
results: []
mlm_soft_finetune_bert
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: 0.0020
- 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': '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': 1e-04, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Epoch |
|---|---|
| 0.0058 | 0 |
| 0.0032 | 1 |
| 0.0029 | 2 |
| 0.0025 | 3 |
| 0.0024 | 4 |
| 0.0023 | 5 |
| 0.0022 | 6 |
| 0.0021 | 7 |
| 0.0021 | 8 |
| 0.0020 | 9 |
Framework versions
- Transformers 4.37.2
- TensorFlow 2.15.0
- Tokenizers 0.15.1