badokorach/afriqa-finetuned-010224

This model is a fine-tuned version of badokorach/afriqa_afroxlmr_lug_290124 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.1430
• Validation Loss: 0.0
• 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: {'inner_optimizer': {'module': 'transformers.optimization_tf', 'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-05, 'decay_steps': 2025, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.8999999761581421, 'beta_2': 0.9990000128746033, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.02}, 'registered_name': 'AdamWeightDecay'}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
• training_precision: mixed_float16

Training results

Train Loss	Validation Loss	Epoch
1.8096	0.0	0
1.2902	0.0	1
1.0617	0.0	2
0.9096	0.0	3
0.7383	0.0	4
0.5826	0.0	5
0.4711	0.0	6
0.3859	0.0	7
0.2942	0.0	8
0.2342	0.0	9
0.1990	0.0	10
0.1929	0.0	11
0.1501	0.0	12
0.1463	0.0	13
0.1430	0.0	14

Framework versions

• Transformers 4.35.2
• TensorFlow 2.15.0
• Datasets 2.16.1
• Tokenizers 0.15.1