Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
zephyr-2b-gemma-dft-debug – AI Model by ale-bay | AlphaNeural AI
You can deploy this model and start earning money today!
ale-bay
/
zephyr-2b-gemma-dft-debug
like
0
transformers
tensorboard
safetensors
gemma
text-generation
alignment-handbook
trl
sft
generated_from_trainer
conversational
argilla/dpo-mix-7k
autotrain_compatible
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
zephyr-2b-gemma-dft-debug
This model is a fine-tuned version of
data/gemma-2b
on the argilla/dpo-mix-7k dataset. It achieves the following results on the evaluation set:
Loss: 5.7648
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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1
Training results
Training Loss
Epoch
Step
Validation Loss
5.8055
0.9982
270
5.7648
Framework versions
Transformers 4.43.3
Pytorch 2.3.1+cu121
Datasets 2.20.0
Tokenizers 0.19.1
