Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
defaullatdev – AI Model by devdefalut20 | AlphaNeural AI
You can deploy this model and start earning money today!
devdefalut20
/
defaullatdev
like
0
pytorch
tensorboard
electra
generated_from_trainer
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
defaullatdev
This model is a fine-tuned version of
ZeyadAhmed/AraElectra-Arabic-SQuADv2-QA
on the None dataset. It achieves the following results on the evaluation set:
Loss: 1.9295
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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 3.0
Training results
Training Loss
Epoch
Step
Validation Loss
1.4232
1.0
1208
1.9295
1.3005
2.0
2417
1.9295
1.33
3.0
3624
1.9295
Framework versions
Transformers 4.30.0
Pytorch 2.4.0+cu121
Datasets 3.0.0
Tokenizers 0.13.3
