Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
just1nseo
/
zephyr-dpo-qlora-uf-ours-uffull-5e-7
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
45f5c7c
zephyr-dpo-qlora-uf-ours-uffull-5e-7
/
train_results.json
just1nseo
Model save
45f5c7c
verified
4 months ago
raw
Copy download link
history
blame
Safe
195 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.6106676421631342
,
"train_runtime"
:
67977.0297
,
"train_samples"
:
66812
,
"train_samples_per_second"
:
0.983
,
"train_steps_per_second"
:
0.061
}