Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
vain05
/
stablelm-2-1_6b-orpo-full-v3
like
0
Text Generation
Transformers
Safetensors
argilla/ultrafeedback-binarized-preferences-cleaned
argilla/distilabel-capybara-dpo-7k-binarized
stablelm
alignment-handbook
trl
orpo
Generated from Trainer
conversational
Inference Endpoints
License:
other
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
312af03
stablelm-2-1_6b-orpo-full-v3
/
all_results.json
vain05
Model save
380ea7b
verified
9 months ago
raw
Copy download link
history
blame
Safe
193 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
1.2897131164005442
,
"train_runtime"
:
9812.389
,
"train_samples"
:
68479
,
"train_samples_per_second"
:
6.979
,
"train_steps_per_second"
:
0.145
}