Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
huseyinatahaninan
/
phi-2-dpo
like
0
PEFT
Safetensors
HuggingFaceH4/ultrafeedback_binarized
phi
alignment-handbook
Generated from Trainer
custom_code
License:
mit
Model card
Files
Files and versions
Community
1
Use this model
refs/pr/1
phi-2-dpo
/
train_results.json
huseyinatahaninan
model
231d660
verified
9 months ago
raw
Copy download link
history
blame
195 Bytes
{
"epoch"
:
3.0
,
"train_loss"
:
0.6659654320045311
,
"train_runtime"
:
38381.4335
,
"train_samples"
:
61135
,
"train_samples_per_second"
:
4.778
,
"train_steps_per_second"
:
0.149
}