Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
Minbyul
/
biomistral-7b-wo-kqa_golden-iter-dpo-step2
like
0
Text Generation
Transformers
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
trl
dpo
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
bae4db1
biomistral-7b-wo-kqa_golden-iter-dpo-step2
/
all_results.json
Minbyul
Model save
bae4db1
verified
7 months ago
raw
Copy download link
history
blame
Safe
191 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.680875283606509
,
"train_runtime"
:
1044.3353
,
"train_samples"
:
6013
,
"train_samples_per_second"
:
5.758
,
"train_steps_per_second"
:
0.09
}