Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
zephyr-7b-gpo-log-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
80971cc
zephyr-7b-gpo-log-i0
/
train_results.json
lole25
Model save
81caf98
verified
3 months ago
raw
history
blame
No virus
196 Bytes
{
"epoch"
:
0.48
,
"train_loss"
:
4.683178136915897e-05
,
"train_runtime"
:
5.5433
,
"train_samples"
:
61135
,
"train_samples_per_second"
:
11.029
,
"train_steps_per_second"
:
5.592
}