Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
albert-large-v2-finetuned-squad – AI Model by lauraparra28 | AlphaNeural AI
You can deploy this model and start earning money today!
lauraparra28
/
albert-large-v2-finetuned-squad
like
0
transformers
pytorch
albert
question-answering
generated_from_trainer
squad_v2
albert/albert-large-v2
finetune
apache-2.0
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
albert-large-v2-finetuned-squad
This model is a fine-tuned version of
albert-large-v2
on the squad_v2 dataset. It achieves the following results on the evaluation set:
Loss: 1.1819
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5
Training results
Training Loss
Epoch
Step
Validation Loss
0.8412
1.0
8248
0.8427
0.6729
2.0
16496
0.7978
0.5069
3.0
24744
0.8760
0.357
4.0
32992
1.0229
0.2374
5.0
41240
1.1819
Framework versions
Transformers 4.34.0
Pytorch 1.12.1
Datasets 2.14.5
Tokenizers 0.14.1
