Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
EcoBERT-Pretrained – AI Model by ViktorDo | AlphaNeural AI
You can deploy this model and start earning money today!
ViktorDo
/
EcoBERT-Pretrained
like
0
transformers
pytorch
tensorboard
distilbert
fill-mask
generated_from_trainer
apache-2.0
autotrain_compatible
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
EcoBERT-Pretrained
This model is a fine-tuned version of
distilbert-base-uncased
on the None dataset. It achieves the following results on the evaluation set:
Loss: 2.2796
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: 5e-05
train_batch_size: 5
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 40
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3
Training results
Training Loss
Epoch
Step
Validation Loss
2.3457
0.66
500
2.2838
2.3622
1.32
1000
2.2896
2.3474
1.98
1500
2.2877
2.3606
2.64
2000
2.2821
Framework versions
Transformers 4.26.1
Pytorch 1.13.1+cu116
Datasets 2.10.1
Tokenizers 0.13.2
