Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
OUTPUT – AI Model by Youssef320 | AlphaNeural AI
You can deploy this model and start earning money today!
Youssef320
/
OUTPUT
like
0
transformers
pytorch
tensorboard
bert
text-classification
generated_from_trainer
autotrain_compatible
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
OUTPUT
This model is a fine-tuned version of
Youssef320/LSTM-finetuned-50label-15epoch
on the None dataset. It achieves the following results on the evaluation set:
Loss: 2.9546
Top 1 Macro F1 Score: 0.1199
Top 1 Weighted F1score: 0.1730
Top 3 Macro F1 Score: 0.2702
Top3 3 Weighted F1 Score : 0.3774
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: 0.0002
train_batch_size: 64
eval_batch_size: 64
seed: 42
gradient_accumulation_steps: 32
total_train_batch_size: 2048
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant
num_epochs: 1.0
Training results
Training Loss
Epoch
Step
Validation Loss
Top 1 Macro F1 Score
Top 1 Weighted F1score
Top 3 Macro F1 Score
Top3 3 Weighted F1 Score
3.0865
0.53
32
2.9546
0.1199
0.1730
0.2702
0.3774
Framework versions
Transformers 4.28.1
Pytorch 1.12.1+cu102
Datasets 2.6.1
Tokenizers 0.13.3
