metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_keras_callback
model-index:
- name: Fryktlos/lets_try
results: []
Fryktlos/lets_try
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: 0.1526
- Validation Loss: 0.9756
- Train Accuracy: 0.6875
- Epoch: 1
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': 5e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
Train Loss | Validation Loss | Train Accuracy | Epoch |
---|---|---|---|
0.2363 | 0.7394 | 0.6923 | 0 |
0.1526 | 0.9756 | 0.6875 | 1 |
Framework versions
- Transformers 4.35.2
- TensorFlow 2.15.0
- Datasets 2.15.0
- Tokenizers 0.15.0