Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
jikaixuan
/
zephyr-7b-dpo-qlora
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
Generated from Trainer
trl
dpo
4-bit precision
bitsandbytes
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
1b1d13d
zephyr-7b-dpo-qlora
/
train_results.json
jikaixuan
Model save
49b9b9f
verified
8 months ago
raw
Copy download link
history
blame
Safe
194 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
2164.5614415454666
,
"train_runtime"
:
32346.8016
,
"train_samples"
:
61135
,
"train_samples_per_second"
:
1.89
,
"train_steps_per_second"
:
0.015
}