mbert-roman-urdu-sentiment – AI Model by abdullaharoon | AlphaNeural AI

You can deploy this model and start earning money today!

abdullaharoon/
mbert-roman-urdu-sentiment

like

0

text-classification

generated_from_trainer

google-bert/bert-base-multilingual-cased

text-embeddings-inference

endpoints_compatible

Views

No views yet

mbert-roman-urdu-sentiment

This model is a fine-tuned version of bert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.3639
Macro F1: 0.9437
Accuracy: 0.9453

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: 16
eval_batch_size: 32
seed: 42
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
lr_scheduler_warmup_steps: 0.1
num_epochs: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Macro F1	Accuracy
0.3677	1.0	915	0.2048	0.9227	0.9244
0.1757	2.0	1830	0.2257	0.9331	0.9354
0.0958	3.0	2745	0.3059	0.9356	0.9373
0.0634	4.0	3660	0.3364	0.9377	0.9391
0.0339	5.0	4575	0.3639	0.9437	0.9453

Framework versions

Transformers 5.14.1
Pytorch 2.6.0+cu124
Tokenizers 0.22.2