Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
zephyr-7b-gpo-v4-i2
like
0
Follow
DUAL Group
2
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
1bac891
zephyr-7b-gpo-v4-i2
/
all_results.json
lole25
Model save
bc4c4d5
verified
6 months ago
raw
Copy download link
history
blame
Safe
196 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.07767095326809656
,
"train_runtime"
:
21725.9611
,
"train_samples"
:
21000
,
"train_samples_per_second"
:
0.967
,
"train_steps_per_second"
:
0.242
}