xlmr-base-finetuned-hausa – AI Model by grace-pro | AlphaNeural AI

You can deploy this model and start earning money today!

grace-pro/
xlmr-base-finetuned-hausa

like

0

token-classification

generated_from_trainer

autotrain_compatible

endpoints_compatible

Views

No views yet

xlmr-base-finetuned-hausa

This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1457
Precision: 0.7098
Recall: 0.5546
F1: 0.6227
Accuracy: 0.9581

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: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.1659	1.0	2624	0.1544	0.6311	0.4655	0.5358	0.9480
0.1403	2.0	5248	0.1402	0.6728	0.5248	0.5896	0.9534
0.1145	3.0	7872	0.1429	0.7280	0.5130	0.6018	0.9570
0.1017	4.0	10496	0.1413	0.6952	0.5543	0.6168	0.9569
0.0862	5.0	13120	0.1457	0.7098	0.5546	0.6227	0.9581

Framework versions

Transformers 4.30.2
Pytorch 2.0.1+cu118
Datasets 2.13.1
Tokenizers 0.13.3