Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
Minbyul
/
mistral-7b-dpo-full-sft-wo-healthsearch_qa
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
2d20acd
mistral-7b-dpo-full-sft-wo-healthsearch_qa
/
train_results.json
Minbyul
Model save
95cf92a
verified
7 months ago
raw
Copy download link
history
blame
191 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.5004948377609253
,
"train_runtime"
:
257.4676
,
"train_samples"
:
1128
,
"train_samples_per_second"
:
4.381
,
"train_steps_per_second"
:
0.07
}