Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DatPySci
/
pythia-1b-kto-iter0
like
0
Text Generation
Transformers
Safetensors
DatPySci/iter0
gpt_neox
alignment-handbook
Generated from Trainer
conversational
Inference Endpoints
text-generation-inference
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
a188b55
pythia-1b-kto-iter0
/
train_results.json
DatPySci
Model save
0ff9daf
verified
4 months ago
raw
history
blame
No virus
167 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.31094988259020595
,
"train_runtime"
:
9866.2092
,
"train_samples_per_second"
:
5.068
,
"train_steps_per_second"
:
0.079
}