Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
lole25
/
phi-2-gpo-ultrachat-lora-0.1
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
7c13450
phi-2-gpo-ultrachat-lora-0.1
/
train_results.json
lole25
Model save
e412c7e
verified
7 months ago
raw
Copy download link
history
blame
No virus
194 Bytes
{
"epoch"
:
0.99
,
"train_loss"
:
0.009997876410029437
,
"train_runtime"
:
1153.3315
,
"train_samples"
:
6113
,
"train_samples_per_second"
:
5.3
,
"train_steps_per_second"
:
0.082
}