Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
Minbyul
/
mistral-7b-wo-kqa_golden-iter-dpo-step2
like
1
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
8a9e02c
mistral-7b-wo-kqa_golden-iter-dpo-step2
/
train_results.json
Minbyul
Model save
a6310e0
verified
6 months ago
raw
Copy download link
history
blame
Safe
195 Bytes
{
"epoch"
:
0.99
,
"train_loss"
:
0.49557680382833375
,
"train_runtime"
:
1348.5444
,
"train_samples"
:
5827
,
"train_samples_per_second"
:
4.321
,
"train_steps_per_second"
:
0.067
}