--- 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: [] datasets: - reddgr/tl-test-learn-prompts --- # tl-test-learn-prompt-classifier This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.1733 - Train Accuracy: 0.9756 - Validation Loss: 0.3006 - Validation Accuracy: 0.8977 - 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 | |:----------:|:--------------:|:---------------:|:-------------------:|:-----:| | 0.6870 | 0.5707 | 0.6656 | 0.6136 | 0 | | 0.6542 | 0.6293 | 0.6289 | 0.6477 | 1 | | 0.5970 | 0.7902 | 0.5541 | 0.7955 | 2 | | 0.4936 | 0.8829 | 0.4490 | 0.8523 | 3 | | 0.3649 | 0.9415 | 0.3775 | 0.875 | 4 | | 0.2563 | 0.9561 | 0.3254 | 0.8977 | 5 | | 0.1733 | 0.9756 | 0.3006 | 0.8977 | 6 | ### Framework versions - Transformers 4.44.2 - TensorFlow 2.18.0-dev20240717 - Datasets 2.21.0 - Tokenizers 0.19.1