Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
Minbyul
/
meditron-7b-dpo-full-wo-kqa_golden-ep3
like
0
Text Generation
Transformers
Safetensors
HuggingFaceH4/ultrafeedback_binarized
llama
alignment-handbook
trl
dpo
Generated from Trainer
text-generation-inference
Inference Endpoints
License:
llama2
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
8af1b21
meditron-7b-dpo-full-wo-kqa_golden-ep3
/
train_results.json
Minbyul
Model save
501e263
verified
7 months ago
raw
Copy download link
history
blame
194 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.5449820566177368
,
"train_runtime"
:
3295.9797
,
"train_samples"
:
12791
,
"train_samples_per_second"
:
3.881
,
"train_steps_per_second"
:
0.061
}