shahiryar/primitive-bot

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: 0.5500
• Train Accuracy: 1.0
• Epoch: 14

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': 60, '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	Train Accuracy	Epoch
1.1025	0.3571	0
1.0767	0.3571	1
1.0419	0.4643	2
1.0119	0.6071	3
0.9470	0.6071	4
0.8949	0.6786	5
0.8078	0.8571	6
0.7862	0.8929	7
0.6954	0.9643	8
0.6665	0.9286	9
0.6258	0.9643	10
0.5865	0.9643	11
0.5914	1.0	12
0.5816	1.0	13
0.5500	1.0	14

Framework versions

• Transformers 4.38.1
• TensorFlow 2.15.0
• Datasets 2.18.0
• Tokenizers 0.15.2