Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
ShenaoZ
/
0.0001_withdpo_4iters_bs256_4444lr_iter_1
like
0
Text Generation
Transformers
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
Generated from Trainer
trl
dpo
conversational
text-generation-inference
Inference Endpoints
License:
mit
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
e4d2c80
0.0001_withdpo_4iters_bs256_4444lr_iter_1
/
train_results.json
ShenaoZ
Model save
e4d2c80
verified
6 months ago
raw
Copy download link
history
blame
195 Bytes
{
"epoch"
:
0.99
,
"train_loss"
:
0.6501501697604939
,
"train_runtime"
:
1921.1604
,
"train_samples"
:
15283
,
"train_samples_per_second"
:
7.955
,
"train_steps_per_second"
:
0.031
}