casarf/comment_model_test

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: 0.2065
• Validation Loss: 0.6270
• Train Accuracy: 0.7349
• Epoch: 19

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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 205, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, '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
0.2042	0.6270	0.7349	0
0.2066	0.6270	0.7349	1
0.2124	0.6270	0.7349	2
0.2138	0.6270	0.7349	3
0.2062	0.6270	0.7349	4
0.2135	0.6270	0.7349	5
0.2113	0.6270	0.7349	6
0.2019	0.6270	0.7349	7
0.2055	0.6270	0.7349	8
0.2129	0.6270	0.7349	9
0.2129	0.6270	0.7349	10
0.2058	0.6270	0.7349	11
0.2016	0.6270	0.7349	12
0.2053	0.6270	0.7349	13
0.2114	0.6270	0.7349	14
0.2037	0.6270	0.7349	15
0.2063	0.6270	0.7349	16
0.2006	0.6270	0.7349	17
0.2114	0.6270	0.7349	18
0.2065	0.6270	0.7349	19

Framework versions

• Transformers 4.28.1
• TensorFlow 2.12.0
• Datasets 2.11.0
• Tokenizers 0.13.3