Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
just1nseo
/
zephyr-7b-dpo-uffull-qlora-5e-7
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
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
c2b556d
zephyr-7b-dpo-uffull-qlora-5e-7
/
all_results.json
just1nseo
Model save
c2b556d
verified
4 months ago
raw
Copy download link
history
blame
193 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.619671463092813
,
"train_runtime"
:
44477.573
,
"train_samples"
:
61134
,
"train_samples_per_second"
:
1.374
,
"train_steps_per_second"
:
0.086
}