Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
lole25
/
phi-2-gpo-test-iter-1
like
0
PEFT
Safetensors
HuggingFaceH4/ultrafeedback_binarized
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
License:
mit
Model card
Files
Files and versions
Community
Use this model
257df80
phi-2-gpo-test-iter-1
/
all_results.json
lole25
Model save
1cb8962
verified
8 months ago
raw
Copy download link
history
blame
195 Bytes
{
"epoch"
:
2.0
,
"train_loss"
:
6.395760283339769e-05
,
"train_runtime"
:
14.4723
,
"train_samples"
:
30567
,
"train_samples_per_second"
:
0.276
,
"train_steps_per_second"
:
0.138
}