Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
Minbyul
/
mistral-7b-dpo-full-sft-wo-kqa_golden
like
0
Text Generation
Transformers
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
trl
dpo
Generated from Trainer
text-generation-inference
Inference Endpoints
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
f862b9b
mistral-7b-dpo-full-sft-wo-kqa_golden
/
train_results.json
Minbyul
Model save
f862b9b
verified
6 months ago
raw
Copy download link
history
blame
195 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.23720380818807385
,
"train_runtime"
:
5120.8034
,
"train_samples"
:
20928
,
"train_samples_per_second"
:
4.087
,
"train_steps_per_second"
:
0.064
}