Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DatPySci
/
zephyr-7b-kto-iter0
like
0
Text Generation
Transformers
Safetensors
generated/iter0
mistral
alignment-handbook
Generated from Trainer
trl
kto
conversational
text-generation-inference
Inference Endpoints
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
34fd191
zephyr-7b-kto-iter0
/
train_results.json
DatPySci
End of training
34fd191
verified
5 months ago
raw
Copy download link
history
blame
No virus
167 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.1710020688315347
,
"train_runtime"
:
11106.5263
,
"train_samples_per_second"
:
9.004
,
"train_steps_per_second"
:
0.141
}