Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
nnheui
/
zephyr-7b-kto-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
9b2e2e5
zephyr-7b-kto-qlora
/
all_results.json
nnheui
Model save
1f448bc
verified
8 months ago
raw
Copy download link
history
blame
Safe
189 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.5000961124897003
,
"train_runtime"
:
87.0205
,
"train_samples"
:
61
,
"train_samples_per_second"
:
0.701
,
"train_steps_per_second"
:
0.023
}