Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
zephyr-7b-gpo-update4-i0
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
Generated from Trainer
trl
dpo
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
c899517
zephyr-7b-gpo-update4-i0
/
train_results.json
lole25
Model save
c899517
verified
4 months ago
raw
Copy download link
history
blame
No virus
198 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.028345070170466266
,
"train_runtime"
:
172193.3354
,
"train_samples"
:
61135
,
"train_samples_per_second"
:
0.355
,
"train_steps_per_second"
:
0.089
}