Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
just1nseo
/
zephyr-dpo-qlora-uf-ours-5e-6-epoch1
like
0
PEFT
TensorBoard
Safetensors
generation/UF
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
2145b36
zephyr-dpo-qlora-uf-ours-5e-6-epoch1
/
train_results.json
just1nseo
Model save
3fb2d1c
verified
3 months ago
raw
Copy download link
history
blame
193 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.3073710792501208
,
"train_runtime"
:
4217.5244
,
"train_samples"
:
5678
,
"train_samples_per_second"
:
1.346
,
"train_steps_per_second"
:
0.084
}