Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
phi_3-offline-dpo-noise-0.0-42 – AI Model by Wenboz | AlphaNeural AI
You can deploy this model and start earning money today!
Wenboz
/
phi_3-offline-dpo-noise-0.0-42
like
0
peft
safetensors
phi3
alignment-handbook
trl
dpo
generated_from_trainer
custom_code
microsoft/Phi-3-mini-4k-instruct
adapter
mit
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Visualize in Weights & Biases
phi_3-offline-dpo-noise-0.0-42
This model is a fine-tuned version of
microsoft/Phi-3-mini-4k-instruct
on the None dataset. It achieves the following results on the evaluation set:
Loss: 0.6938
Rewards/chosen: -0.0001
Rewards/rejected: -0.0001
Rewards/accuracies: 0.5357
Rewards/margins: 0.0000
Logps/rejected: -395.4152
Logps/chosen: -396.9144
Logits/rejected: 12.8496
Logits/chosen: 13.9987
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-06
train_batch_size: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 4
total_train_batch_size: 64
total_eval_batch_size: 16
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
Framework versions
PEFT 0.7.1
Transformers 4.42.3
Pytorch 2.3.0+cu121
Datasets 2.14.6
Tokenizers 0.19.1
