Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
chansung
/
gemma-7b-sft-qlora-no-robots2
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
ed79e38
gemma-7b-sft-qlora-no-robots2
/
all_results.json
chansung
Model save
ed79e38
verified
8 months ago
raw
Copy download link
history
blame
Safe
190 Bytes
{
"epoch"
:
9.09
,
"train_loss"
:
6.66651237487793
,
"train_runtime"
:
191.2414
,
"train_samples"
:
926
,
"train_samples_per_second"
:
4.602
,
"train_steps_per_second"
:
0.261
}