Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
dmis-lab
/
meditron-7b-olaph
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
4ec7d43
meditron-7b-olaph
/
train_results.json
dmis-lab
Upload 18 files
4ec7d43
verified
6 months ago
raw
Copy download link
history
blame
Safe
192 Bytes
{
"epoch"
:
0.99
,
"train_loss"
:
0.6759306937456131
,
"train_runtime"
:
862.557
,
"train_samples"
:
4102
,
"train_samples_per_second"
:
4.756
,
"train_steps_per_second"
:
0.074
}