Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
Minbyul
/
meditron-7b-dpo-full-sft-wo-kqa_silver_wogold
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
6878cb3
meditron-7b-dpo-full-sft-wo-kqa_silver_wogold
/
all_results.json
Minbyul
Model save
6878cb3
6 months ago
raw
Copy download link
history
blame
Safe
192 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.5552032154340011
,
"train_runtime"
:
696.2336
,
"train_samples"
:
3326
,
"train_samples_per_second"
:
4.777
,
"train_steps_per_second"
:
0.075
}