Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
objects76
/
zephyr-7b-dpo-qlora
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
trl
dpo
Generated from Trainer
4-bit precision
bitsandbytes
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
666e963
zephyr-7b-dpo-qlora
/
all_results.json
objects76
Model save
dd9949b
verified
5 months ago
raw
Copy download link
history
blame
No virus
192 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.521260229900413
,
"train_runtime"
:
42446.6624
,
"train_samples"
:
61134
,
"train_samples_per_second"
:
1.44
,
"train_steps_per_second"
:
0.09
}