Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
just1nseo
/
zephyr-dpo-qlora-uf-ours-uffull-5e-6
like
0
PEFT
TensorBoard
Safetensors
generation/UF
generation/UFfull2
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
992db9f
zephyr-dpo-qlora-uf-ours-uffull-5e-6
/
train_results.json
just1nseo
Model save
992db9f
verified
4 months ago
raw
Copy download link
history
blame
195 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.5053737083043175
,
"train_runtime"
:
67897.0602
,
"train_samples"
:
66812
,
"train_samples_per_second"
:
0.984
,
"train_steps_per_second"
:
0.062
}