Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
test-lora-data1 – AI Model by chaimachabir | AlphaNeural AI
You can deploy this model and start earning money today!
chaimachabir
/
test-lora-data1
like
0
peft
safetensors
generated_from_trainer
openai-community/gpt2
adapter
mit
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
test-lora-data1
This model is a fine-tuned version of
gpt2
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 3.4346
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: 4
eval_batch_size: 4
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 3
Training results
Training Loss
Epoch
Step
Validation Loss
3.5227
1.0
818
3.4732
3.5928
2.0
1636
3.4427
3.5506
3.0
2454
3.4346
Framework versions
PEFT 0.13.2
Transformers 4.46.3
Pytorch 2.5.1+cu121
Datasets 3.2.0
Tokenizers 0.20.3
