mekjr1/Feel-bert-base-uncased-trial-vent

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

• Train Loss: 3.0961
• Validation Loss: 3.2267
• 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': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': -992, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'passive_serialization': True}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: mixed_float16

Training results

Train Loss	Validation Loss	Epoch
3.1524	2.8831	0
3.3046	2.9650	1
3.3182	2.2945	2
3.2669	3.1812	3
3.1702	2.7750	4
3.2273	2.0445	5
3.2955	2.7407	6
3.1915	3.0679	7
3.2005	2.0120	8
3.0654	2.3347	9
3.0985	2.9339	10
3.0161	2.8847	11
3.1455	3.1531	12
3.1237	3.3190	13
3.1059	2.5587	14
3.0486	2.8180	15
2.9230	2.2432	16
3.0667	3.0650	17
2.9550	2.4731	18
3.0961	3.2267	19

Framework versions

• Transformers 4.26.1
• TensorFlow 2.11.0
• Datasets 2.9.0
• Tokenizers 0.13.2