afrimt5_Hausa – AI Model by ahmadmwali | AlphaNeural AI

You can deploy this model and start earning money today!

ahmadmwali/
afrimt5_Hausa

like

0

generated_from_trainer

castorini/afrimt5-base-ft-msmarco

Views

No views yet

afrimt5_Hausa

This model is a fine-tuned version of castorini/afrimt5-base-ft-msmarco on the None dataset. It achieves the following results on the evaluation set:

Bleu: 0.6535
F1: 0.8333
Wer: 0.2508
Cer: 0.0931
Meteor: 0.8025
Loss: 0.0755

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:

learning_rate: 0.0005
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Bleu	F1	Wer	Cer	Meteor	Validation Loss
0.1618	1.0	500	0.5482	0.7805	0.5010	0.3054	0.7335	0.0995
0.1359	2.0	1000	0.6303	0.8243	0.2879	0.1201	0.7885	0.0814
0.1209	3.0	1500	0.6535	0.8333	0.2508	0.0931	0.8025	0.0755

Framework versions

PEFT 0.15.2
Transformers 4.51.3
Pytorch 2.6.0+cu124
Datasets 2.14.4
Tokenizers 0.21.1