Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
wxzhang
/
selective-pairrm-33045197-mt0
like
0
Text Generation
Transformers
Safetensors
snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset
mistral
alignment-handbook
Generated from Trainer
trl
dpo
conversational
text-generation-inference
Inference Endpoints
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
1ec4438
selective-pairrm-33045197-mt0
/
train_results.json
wxzhang
Model save
1ec4438
verified
8 months ago
raw
Copy download link
history
blame
194 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.6714850996549313
,
"train_runtime"
:
5456.9379
,
"train_samples"
:
19766
,
"train_samples_per_second"
:
3.664
,
"train_steps_per_second"
:
0.057
}