Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
Minbyul
/
meditron-7b-dpo-full-sft-wo-live_qa
like
0
Text Generation
Transformers
Safetensors
HuggingFaceH4/ultrafeedback_binarized
llama
alignment-handbook
trl
dpo
Generated from Trainer
Inference Endpoints
text-generation-inference
License:
llama2
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
29d39aa
meditron-7b-dpo-full-sft-wo-live_qa
/
train_results.json
Minbyul
Model save
2ebd25e
verified
about 2 months ago
raw
history
blame
No virus
193 Bytes
{
"epoch"
:
0.99
,
"train_loss"
:
0.5556549103029312
,
"train_runtime"
:
1091.242
,
"train_samples"
:
3974
,
"train_samples_per_second"
:
3.642
,
"train_steps_per_second"
:
0.057
}