Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
terry69
/
gemma_preference
like
0
PEFT
TensorBoard
Safetensors
preference-data
gemma
alignment-handbook
trl
sft
Generated from Trainer
License:
gemma
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
2dc7763
gemma_preference
/
eval_results.json
terry69
End of training
2dc7763
verified
about 2 months ago
raw
Copy download link
history
blame
Safe
146 Bytes
{
"epoch"
:
1.0
,
"eval_runtime"
:
7.9659
,
"eval_samples"
:
10
,
"eval_samples_per_second"
:
1.255
,
"eval_steps_per_second"
:
0.377
}