Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
just1nseo
/
zephyr-dpo-qlora-uf-oursuf6k-5e-7
like
0
PEFT
TensorBoard
Safetensors
generation/UF6k
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
f7ec731
zephyr-dpo-qlora-uf-oursuf6k-5e-7
/
all_results.json
just1nseo
Model save
f7ec731
verified
3 months ago
raw
Copy download link
history
blame
No virus
194 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.6679948979651021
,
"train_runtime"
:
9131.6092
,
"train_samples"
:
10941
,
"train_samples_per_second"
:
1.198
,
"train_steps_per_second"
:
0.075
}