Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
EvgeniyZh
/
zephyr-7b-dpo-lora
like
0
Safetensors
Generated from Trainer
License:
apache-2.0
Model card
Files
Files and versions
Community
099fba1
zephyr-7b-dpo-lora
/
train_results.json
EvgeniyZh
Model save
099fba1
11 months ago
raw
Copy download link
history
blame
195 Bytes
{
"epoch"
:
3.0
,
"train_loss"
:
0.5707186016333662
,
"train_runtime"
:
142661.7128
,
"train_samples"
:
61966
,
"train_samples_per_second"
:
1.303
,
"train_steps_per_second"
:
0.02
}