mdeberta-qasina-LR-1e-05-BS-16-ML-384 – AI Model by mhdafifan | AlphaNeural AI

You can deploy this model and start earning money today!

mhdafifan/
mdeberta-qasina-LR-1e-05-BS-16-ML-384

like

0

question-answering

generated_from_trainer

microsoft/mdeberta-v3-base

endpoints_compatible

Views

No views yet

mdeberta-qasina-LR-1e-05-BS-16-ML-384

This model is a fine-tuned version of microsoft/mdeberta-v3-base on the QASiNa dataset. It achieves the following results on the evaluation set:

Loss: 2.0209
F1: 45.2921
Exact Match: 33.0189

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: 0.2
num_epochs: 7

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Exact Match
No log	1.0	46	5.6686	5.2271	0.0
No log	2.0	92	4.0595	8.153	2.8302
No log	3.0	138	3.0802	25.7918	16.9811
No log	4.0	184	2.3496	41.8537	30.1887
No log	5.0	230	2.1333	44.4657	33.0189
No log	6.0	276	2.0413	45.9929	33.9623
No log	7.0	322	2.0209	45.2921	33.0189

Framework versions

Transformers 4.57.1
Pytorch 2.9.1+cu128
Datasets 4.4.1
Tokenizers 0.22.1