Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
ZHLiu627
/
zephyr-gemma-rpo
like
0
Text Generation
Transformers
Safetensors
argilla/dpo-mix-7k
gemma
alignment-handbook
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
License:
other
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
6d63f74
zephyr-gemma-rpo
/
train_results.json
ZHLiu627
1
251b0a9
10 months ago
raw
Copy download link
history
blame
232 Bytes
{
"epoch"
:
1.971563981042654
,
"total_flos"
:
0.0
,
"train_loss"
:
0.48392796287169826
,
"train_runtime"
:
15946.9173
,
"train_samples"
:
6750
,
"train_samples_per_second"
:
0.847
,
"train_steps_per_second"
:
0.007
}