Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
indobert-baseline-fiqhqa-ML-384 – AI Model by mhdafifan | AlphaNeural AI
You can deploy this model and start earning money today!
mhdafifan
/
indobert-baseline-fiqhqa-ML-384
like
0
transformers
safetensors
bert
question-answering
indonesian
fiqhqa
indobert
generated_from_trainer
id
indobenchmark/indobert-base-p1
finetune
mit
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
indobert-baseline-fiqhqa-ML-384
This model is a fine-tuned version of
indobenchmark/indobert-base-p1
on the FiqhQA dataset. It achieves the following results on the evaluation set:
Loss: 2.3357
F1: 30.37
Exact Match: 5.83
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: 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
2.0533
1.0
176
1.9014
30.61
6.8
1.7208
2.0
352
1.8658
31.98
6.8
1.533
3.0
528
1.9445
32.9
5.83
1.3684
4.0
704
2.0559
31.54
5.83
1.0365
5.0
880
2.3357
30.37
5.83
Framework versions
Transformers 4.57.1
Pytorch 2.9.1+cu128
Datasets 4.4.1
Tokenizers 0.22.1
