Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
zephyr-7b-gpo-iter1
like
0
PEFT
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
Generated from Trainer
trl
dpo
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Use this model
2289479
zephyr-7b-gpo-iter1
/
train_results.json
lole25
Model save
5941df8
verified
5 months ago
raw
Copy download link
history
blame
No virus
197 Bytes
{
"epoch"
:
2.0
,
"train_loss"
:
0.005910432943725027
,
"train_runtime"
:
19053.6119
,
"train_samples"
:
61135
,
"train_samples_per_second"
:
0.105
,
"train_steps_per_second"
:
0.052
}