Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
YYYYYYibo
/
zephyr-7b-dpo-qlora-min-pi-part-0
like
0
PEFT
Safetensors
updated
original
mistral
alignment-handbook
Generated from Trainer
trl
dpo
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Use this model
26517f2
zephyr-7b-dpo-qlora-min-pi-part-0
/
all_results.json
YYYYYYibo
Model save
4738e8b
verified
7 months ago
raw
Copy download link
history
blame
Safe
193 Bytes
{
"epoch"
:
0.77
,
"train_loss"
:
0.692988375822703
,
"train_runtime"
:
257.3561
,
"train_samples"
:
10000
,
"train_samples_per_second"
:
3.886
,
"train_steps_per_second"
:
0.012
}