Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
LeeSB
/
zephyr-7b-dpo-qlora
like
0
PEFT
TensorBoard
Safetensors
trl
dpo
Generated from Trainer
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Use this model
05f968e
zephyr-7b-dpo-qlora
/
train_results.json
LeeSB
Model save
0ee6e36
verified
6 months ago
raw
Copy download link
history
blame
No virus
198 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.35941912531329934
,
"train_runtime"
:
141935.9761
,
"train_samples"
:
145937
,
"train_samples_per_second"
:
1.028
,
"train_steps_per_second"
:
0.064
}