Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO-2
/
zephyr-7b-gpo-v6-i1
like
0
Follow
DUAL-GPO-2
2
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
Generated from Trainer
trl
dpo
License:
mit
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
751bb60
zephyr-7b-gpo-v6-i1
/
train_results.json
lole25
Model save
3b81c80
verified
6 months ago
raw
Copy download link
history
blame
Safe
194 Bytes
{
"epoch"
:
0.6
,
"train_loss"
:
0.2318923625944615
,
"train_runtime"
:
76628.4869
,
"train_samples"
:
6113
,
"train_samples_per_second"
:
0.391
,
"train_steps_per_second"
:
0.033
}