xlm-roberta-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/
xlm-roberta-qasina-LR-1e-05-BS-16-ML-384

like

0

question-answering

generated_from_trainer

FacebookAI/xlm-roberta-base

endpoints_compatible

Views

No views yet

xlm-roberta-qasina-LR-1e-05-BS-16-ML-384

This model is a fine-tuned version of FacebookAI/xlm-roberta-base on the QASiNa dataset. It achieves the following results on the evaluation set:

Loss: 3.1062
F1: 34.0922
Exact Match: 24.5283

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	39	5.7997	5.8625	0.0
No log	2.0	78	4.7489	9.8554	3.7736
No log	3.0	117	4.1791	9.5742	4.717
No log	4.0	156	3.8108	16.8552	12.2642
No log	5.0	195	3.5761	20.8936	15.0943
No log	6.0	234	3.2855	30.696	23.5849
No log	7.0	273	3.1062	34.0922	24.5283

Framework versions

Transformers 4.57.1
Pytorch 2.9.1+cu128
Datasets 4.4.1
Tokenizers 0.22.1