bert-fa-base-uncased-finetuned-IR_sum_QA

This model is a fine-tuned version of HooshvareLab/bert-fa-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.2566
{'exact_match': 78.1, 'f1': 81.18920440326781}

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
num_epochs: 3
mixed_precision_training: Native AMP
fp16 = True

Training results

Training Loss	Epoch	Step	Validation Loss
0.8955	1.0	1590	1.0928
0.5267	2.0	3180	1.0997
0.3214	3.0	4770	1.2566

Framework versions

Transformers 4.57.3
Pytorch 2.9.0+cu126
Datasets 4.0.0
Tokenizers 0.22.1

Downloads last month: 8

Safetensors

Model size

0.2B params

Tensor type

F32

Model tree for Z-Jafari/bert-fa-base-uncased-finetuned-IR_sum_QA

Base model

HooshvareLab/bert-fa-base-uncased

Finetuned

(56)

this model

Datasets used to train Z-Jafari/bert-fa-base-uncased-finetuned-IR_sum_QA

Collection including Z-Jafari/bert-fa-base-uncased-finetuned-IR_sum_QA

IR_Sum

Collection

7 items • Updated Jan 7