Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
mdeberta-baseline-fiqhqa-ML-512 – AI Model by mhdafifan | AlphaNeural AI | AlphaNeural AI
You can deploy this model and start earning money today!
mhdafifan
/
mdeberta-baseline-fiqhqa-ML-512
like
0
transformers
safetensors
deberta-v2
question-answering
indonesian
fiqhqa
mdeberta
generated_from_trainer
id
microsoft/mdeberta-v3-base
finetune
mit
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
mdeberta-baseline-fiqhqa-ML-512
This model is a fine-tuned version of
microsoft/mdeberta-v3-base
on the FiqhQA dataset. It achieves the following results on the evaluation set:
Loss: 1.4041
F1: 51.85
Exact Match: 25.24
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
1.4861
1.0
176
1.3719
47.8
22.33
1.1717
2.0
352
1.2064
49.52
25.24
0.956
3.0
528
1.3052
49.38
21.36
0.7946
4.0
704
1.3221
52.12
25.24
0.7122
5.0
880
1.4041
51.85
25.24
Framework versions
Transformers 4.57.1
Pytorch 2.9.1+cu128
Datasets 4.4.1
Tokenizers 0.22.1
