You can deploy this model and start earning money today!

snikhiel/
distilbert_v1

Name: distilbert_v1
Availability: InStock

transformers

distilbert

text-classification

generated_from_keras_callback

distilbert/distilbert-base-uncased

Views

No views yet

snikhiel/distilbert_v1

This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

Train Loss: 0.2719
Validation Loss: 0.4048
Train Accuracy: 0.9068
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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 3125, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
training_precision: float32

Training results

Train Loss	Validation Loss	Train Accuracy	Epoch
3.0587	1.7529	0.6922	0
1.1574	0.7906	0.8510	1
0.5728	0.5193	0.8857	2
0.3732	0.4324	0.8971	3
0.2934	0.4048	0.9068	4
0.2737	0.4048	0.9068	5
0.2729	0.4048	0.9068	6
0.2715	0.4048	0.9068	7
0.2688	0.4048	0.9068	8
0.2719	0.4048	0.9068	9

Framework versions

Transformers 4.38.2
TensorFlow 2.15.0
Datasets 2.18.0
Tokenizers 0.15.2