Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
DatPySci
/
pythia-1b-self-kto-iter0
like
0
Text Generation
Transformers
Safetensors
DatPySci/SPIN_iter0
gpt_neox
alignment-handbook
Generated from Trainer
conversational
text-generation-inference
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
1
Train
Deploy
Use this model
a21e894
pythia-1b-self-kto-iter0
/
train_results.json
DatPySci
Model save
fc3cb35
verified
over 1 year ago
raw
Copy download link
history
blame
Safe
167 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.41590739681687156
,
"train_runtime"
:
9143.8407
,
"train_samples_per_second"
:
5.468
,
"train_steps_per_second"
:
0.085
}