Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
phi4-lora-pbhsahxt-1742310636 – AI Model by Swephoenix | AlphaNeural AI
You can deploy this model and start earning money today!
Swephoenix
/
phi4-lora-pbhsahxt-1742310636
like
0
peft
safetensors
generated_from_trainer
microsoft/Phi-4-mini-instruct
adapter
mit
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
phi4-lora-xaji0y6d-1742307792
This model is a fine-tuned version of
microsoft/Phi-4-mini-instruct
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 17.2192
Perplexity: 30074056.0078
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: 1e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 8
optimizer: Use adamw_hf with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.15
num_epochs: 15
Training results
Training Loss
Epoch
Step
Validation Loss
Perplexity
5.712
0.0664
5
17.2155
29964122.9417
6.9157
0.1329
10
17.2185
30054100.7563
6.8786
0.1993
15
17.2190
30069467.4211
6.785
0.2658
20
17.2192
30074056.0078
Framework versions
PEFT 0.14.0
Transformers 4.48.2
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0
