Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
chansung
/
gemma-7b-sft-qlora-no-robots15
like
0
PEFT
TensorBoard
Safetensors
chansung/no_robots_only_coding
gemma
alignment-handbook
trl
sft
Generated from Trainer
4-bit precision
bitsandbytes
License:
gemma
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
8f05ef0
gemma-7b-sft-qlora-no-robots15
/
eval_results.json
chansung
End of training
8f05ef0
verified
7 months ago
raw
Copy download link
history
blame
185 Bytes
{
"epoch"
:
13.64
,
"eval_loss"
:
1.2830009460449219
,
"eval_runtime"
:
0.6019
,
"eval_samples"
:
16
,
"eval_samples_per_second"
:
3.323
,
"eval_steps_per_second"
:
1.661
}