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
6569e33
zephyr-7b-dpo-qlora
/
train_results.json
LeeSB
Model save
6569e33
verified
6 months ago
raw
Copy download link
history
blame
No virus
196 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.23287739991377154
,
"train_runtime"
:
68266.2327
,
"train_samples"
:
59881
,
"train_samples_per_second"
:
0.877
,
"train_steps_per_second"
:
0.055
}