Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
xlm-roberta-threestage-fiqhqa-ML-384 – AI Model by mhdafifan | AlphaNeural AI
You can deploy this model and start earning money today!
mhdafifan
/
xlm-roberta-threestage-fiqhqa-ML-384
like
0
transformers
safetensors
xlm-roberta
question-answering
indonesian
fiqhqa
generated_from_trainer
id
mhdafifan/xlm-roberta-squad-qasina-LR-1e-05-BS-16-ML-384
finetune
mit
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
xlm-roberta-threestage-fiqhqa-ML-384
This model is a fine-tuned version of
mhdafifan/xlm-roberta-squad-qasina-LR-1e-05-BS-16-ML-384
on the FiqhQA dataset. It achieves the following results on the evaluation set:
Loss: 1.1675
F1: 53.43
Exact Match: 29.13
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: 1e-05
train_batch_size: 16
eval_batch_size: 16
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: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5
Training results
Training Loss
Epoch
Step
Validation Loss
F1
Exact Match
1.3204
1.0
204
1.0651
53.89
27.18
1.0482
2.0
408
1.0342
54.47
27.18
0.8148
3.0
612
1.0536
55.01
32.04
0.714
4.0
816
1.1112
53.08
29.13
0.6547
5.0
1020
1.1675
53.43
29.13
Framework versions
Transformers 4.57.1
Pytorch 2.9.1+cu128
Datasets 4.4.1
Tokenizers 0.22.1
