Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
lole25
/
phi-2-dpo-ultrachat-lora
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
License:
mit
Model card
Files
Files and versions
Metrics
Training metrics
Community
Use this model
c5be93f
phi-2-dpo-ultrachat-lora
/
train_results.json
lole25
Model save
c5be93f
verified
5 months ago
raw
Copy download link
history
blame
No virus
194 Bytes
{
"epoch"
:
2.0
,
"train_loss"
:
0.3994182998029441
,
"train_runtime"
:
8026.3391
,
"train_samples"
:
30567
,
"train_samples_per_second"
:
7.617
,
"train_steps_per_second"
:
0.119
}