metadata
library_name: transformers
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_keras_callback
model-index:
- name: tl-test-learn-prompt-classifier
results: []
tl-test-learn-prompt-classifier
This model is a fine-tuned version of distilbert-base-uncased on the reddgr/tl-test-learn-prompts dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0794
- Train Accuracy: 1.0
- Validation Loss: 0.2381
- Validation Accuracy: 0.9444
- Epoch: 5
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-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 |
|---|---|---|---|---|
| 0.6829 | 0.5808 | 0.6541 | 0.7639 | 0 |
| 0.6315 | 0.7784 | 0.5824 | 0.8472 | 1 |
| 0.4975 | 0.9222 | 0.4382 | 0.8889 | 2 |
| 0.3094 | 0.9521 | 0.3303 | 0.9028 | 3 |
| 0.1684 | 0.9820 | 0.2741 | 0.9028 | 4 |
| 0.0794 | 1.0 | 0.2381 | 0.9444 | 5 |
Framework versions
- Transformers 4.46.2
- TensorFlow 2.17.1
- Datasets 3.1.0
- Tokenizers 0.20.3