Baghdad99/saad-english-text-to-hausa-text

Baghdad99/saad-opus-en-to-ha

This model is a fine-tuned version of dammyogt/damilola-finetuned-NLP-opus-mt-en-ha on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 2.0684
• Validation Loss: 3.9404
• Epoch: 24

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': 2e-05, '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
5.2122	4.9730	0
4.6878	4.6863	1
4.3583	4.5021	2
4.0971	4.3766	3
3.9068	4.2787	4
3.7374	4.2102	5
3.5895	4.1610	6
3.4658	4.1177	7
3.3482	4.0878	8
3.2306	4.0586	9
3.1316	4.0345	10
3.0379	4.0138	11
2.9368	3.9958	12
2.8479	3.9840	13
2.7622	3.9701	14
2.6861	3.9627	15
2.6094	3.9544	16
2.5217	3.9510	17
2.4538	3.9470	18
2.3906	3.9395	19
2.3162	3.9393	20
2.2632	3.9368	21
2.1933	3.9382	22
2.1325	3.9424	23
2.0684	3.9404	24

Framework versions

• Transformers 4.35.0
• TensorFlow 2.14.0
• Datasets 2.14.6
• Tokenizers 0.14.1