Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
SolaceAI – AI Model by SolaceinLoneSun | AlphaNeural AI | AlphaNeural AI
You can deploy this model and start earning money today!
SolaceinLoneSun
/
SolaceAI
like
0
peft
tensorboard
safetensors
generated_from_trainer
google/gemma-2b
adapter
gemma
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
SolaceAI
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: 3.0826
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: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Use adamw_bnb_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 2
training_steps: 3000
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
12.5314
0.1692
1000
3.1412
12.3003
0.3385
2000
3.0979
12.4202
0.5077
3000
3.0826
Framework versions
PEFT 0.14.0
Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0
