NADI-Country-DID-MARBERTv2 – AI Model by ashabrawy | AlphaNeural AI

You can deploy this model and start earning money today!

ashabrawy/
NADI-Country-DID-MARBERTv2

like

0

text-classification

generated_from_trainer

UBC-NLP/MARBERTv2

autotrain_compatible

endpoints_compatible

Views

No views yet

NADI-Country-DID-MARBERTv2

This model is a fine-tuned version of UBC-NLP/MARBERTv2 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 2.9474
Accuracy: 0.3212
F1: 0.3031

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
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
2.5971	1.0	883	2.4084	0.2990	0.2699
1.5502	2.0	1766	2.4697	0.3207	0.3072
0.9672	3.0	2649	2.6677	0.3222	0.3057
0.6248	4.0	3532	2.8501	0.3152	0.2951
0.5022	5.0	4415	2.9474	0.3212	0.3031

Framework versions

Transformers 4.55.2
Pytorch 2.8.0+cu128
Datasets 2.16.0
Tokenizers 0.21.4