notKrisna/distilbert-10

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: 0.0114
• Validation Loss: 0.7885
• Train Accuracy: 0.8144
• 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': False, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 2700, '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
0.0233	0.7613	0.8144	0
0.0210	0.7611	0.8144	1
0.0193	0.7918	0.8144	2
0.0178	0.7694	0.7938	3
0.0204	0.7999	0.8144	4
0.0213	0.7653	0.8144	5
0.0138	0.7865	0.8144	6
0.0133	0.7804	0.8144	7
0.0122	0.7702	0.8247	8
0.0114	0.7885	0.8144	9

Framework versions

• Transformers 4.40.1
• TensorFlow 2.15.0
• Datasets 2.19.0
• Tokenizers 0.19.1