Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO-2
/
zephyr-7b-gpo-v14-i1
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
Generated from Trainer
trl
dpo
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
b6ee936
zephyr-7b-gpo-v14-i1
/
train_results.json
lole25
Model save
a755005
verified
4 months ago
raw
Copy download link
history
blame
No virus
196 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.14500870579197292
,
"train_runtime"
:
22293.6001
,
"train_samples"
:
21000
,
"train_samples_per_second"
:
0.942
,
"train_steps_per_second"
:
0.235
}