Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
csb-sent-6epochs – AI Model by livles | AlphaNeural AI
You can deploy this model and start earning money today!
livles
/
csb-sent-6epochs
like
0
tensorboard
safetensors
t5
generated_from_trainer
google/byt5-small
finetune
apache-2.0
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
csb-sent-6epochs
This model is a fine-tuned version of
google/byt5-small
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 0.7390
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: 6
Training results
Training Loss
Epoch
Step
Validation Loss
14.4759
1.0
563
1.3543
1.2754
2.0
1126
0.9288
0.9732
3.0
1689
0.8446
0.9023
4.0
2252
0.7943
0.8676
5.0
2815
0.7452
0.8341
6.0
3378
0.7390
Framework versions
Transformers 4.36.2
Pytorch 2.9.1+cu128
Datasets 4.3.0
Tokenizers 0.15.2
