Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
Minbyul
/
meditron-7b-dpo-full-sft-wo-medication_qa
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
9ff5e19
meditron-7b-dpo-full-sft-wo-medication_qa
/
train_results.json
Minbyul
Model save
299e008
verified
6 months ago
raw
Copy download link
history
blame
Safe
193 Bytes
{
"epoch"
:
0.99
,
"train_loss"
:
0.5082056158680027
,
"train_runtime"
:
904.9767
,
"train_samples"
:
3790
,
"train_samples_per_second"
:
4.188
,
"train_steps_per_second"
:
0.065
}