Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
orpo-explorers
/
kaist-sft-mistral-OHP-15k-Stratified-1-fix
like
0
Follow
ORPO Explorers
16
Text Generation
Transformers
TensorBoard
Safetensors
orpo-explorers/OHP-15k-Stratified-1
mistral
alignment-handbook
trl
orpo
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
4ad4751
kaist-sft-mistral-OHP-15k-Stratified-1-fix
/
all_results.json
nlee-208
Model save
a33e189
verified
9 months ago
raw
Copy download link
history
blame
Safe
195 Bytes
{
"epoch"
:
3.0
,
"train_loss"
:
0.7502862380468454
,
"train_runtime"
:
21621.4849
,
"train_samples"
:
14928
,
"train_samples_per_second"
:
2.071
,
"train_steps_per_second"
:
0.032
}