Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
zephyr-7b-gpo-v3-1-i2
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
83e9d28
zephyr-7b-gpo-v3-1-i2
/
all_results.json
lole25
Model save
83e9d28
verified
3 months ago
raw
Copy download link
history
blame
No virus
194 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.06912825773557027
,
"train_runtime"
:
9941.711
,
"train_samples"
:
15000
,
"train_samples_per_second"
:
1.509
,
"train_steps_per_second"
:
0.189
}