Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
jcmei
/
DPO-Zephyr-7B
like
0
Text Generation
Transformers
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
trl
dpo
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
License:
mit
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
efaa6a3
DPO-Zephyr-7B
/
train_results.json
jcmei
Model save
efaa6a3
verified
7 months ago
raw
Copy download link
history
blame
217 Bytes
{
"epoch"
:
0.8368200836820083
,
"total_flos"
:
0.0
,
"train_loss"
:
0.0
,
"train_runtime"
:
172.1278
,
"train_samples"
:
15283
,
"train_samples_per_second"
:
88.789
,
"train_steps_per_second"
:
0.343
}