You can deploy this model and start earning money today!

ozeniny/
franco-sentiment-classifier

generated_from_trainer

ozeniny/xlm-roberta-arabizi-base

finetune

text-embeddings-inference

endpoints_compatible

Views

No views yet

franco-sentiment-classifier

This model is a fine-tuned version of ozeniny/xlm-roberta-arabizi-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.5426
Accuracy: 0.7793
F1 Macro: 0.7800
F1 Positive: 0.8119
F1 Neutral: 0.7379
F1 Negative: 0.7903

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: 128
eval_batch_size: 256
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 0.1
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	F1 Positive	F1 Neutral	F1 Negative
0.6024	1.0	892	0.5677	0.7592	0.7603	0.7953	0.7218	0.7638
0.5375	2.0	1784	0.5594	0.7662	0.7679	0.8041	0.7331	0.7665
0.4926	3.0	2676	0.5363	0.7797	0.7805	0.8074	0.7411	0.7931
0.4306	4.0	3568	0.5658	0.7766	0.7776	0.8085	0.7368	0.7876
0.4069	5.0	4460	0.5752	0.7766	0.7774	0.8061	0.7359	0.7901

Framework versions

Transformers 5.10.2
Pytorch 2.8.0+cu128
Datasets 5.0.0
Tokenizers 0.22.2

ozeniny/franco-sentiment-classifier

franco-sentiment-classifier

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

ozeniny/
franco-sentiment-classifier