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 an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.2656
- Train Accuracy: 0.9728
- Validation Loss: 0.3730
- Validation Accuracy: 0.8500
- Epoch: 6
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': False, 'is_legacy_optimizer': False, 'learning_rate': 5e-06, '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 |
|---|---|---|---|---|
| 0.6956 | 0.4728 | 0.6850 | 0.625 | 0 |
| 0.6722 | 0.6685 | 0.6670 | 0.75 | 1 |
| 0.6520 | 0.7120 | 0.6367 | 0.6875 | 2 |
| 0.6002 | 0.8261 | 0.5741 | 0.8000 | 3 |
| 0.5079 | 0.875 | 0.4797 | 0.8875 | 4 |
| 0.3805 | 0.9511 | 0.4118 | 0.8250 | 5 |
| 0.2656 | 0.9728 | 0.3730 | 0.8500 | 6 |
Framework versions
- Transformers 4.44.2
- TensorFlow 2.18.0-dev20240717
- Datasets 2.21.0
- Tokenizers 0.19.1