Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
google-gemma-2b – AI Model by codewizardUV | AlphaNeural AI
You can deploy this model and start earning money today!
codewizardUV
/
google-gemma-2b
like
0
peft
tensorboard
safetensors
trl
sft
generated_from_trainer
google/gemma-2b
adapter
other
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
google-gemma-2b
This model is a fine-tuned version of
google/gemma-2b
on the None dataset. It achieves the following results on the evaluation set:
Loss: 0.6530
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: 0.00025
train_batch_size: 4
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant
lr_scheduler_warmup_ratio: 0.03
num_epochs: 3
Training results
Training Loss
Epoch
Step
Validation Loss
0.8637
0.76
100
0.9368
0.5961
1.52
200
0.7724
0.3952
2.27
300
0.6530
Framework versions
PEFT 0.8.2
Transformers 4.38.1
Pytorch 2.1.0+cu121
Datasets 2.17.1
Tokenizers 0.15.2
