Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
satpalsr
/
gemma-sft-qlora
like
0
PEFT
Safetensors
satpalsr/hindi-sample
gemma
alignment-handbook
trl
sft
Generated from Trainer
4-bit precision
bitsandbytes
License:
other
Model card
Files
Files and versions
Community
Train
Use this model
e1b689f
gemma-sft-qlora
/
all_results.json
satpalsr
Model save
e1b689f
verified
11 months ago
raw
Copy download link
history
blame
Safe
195 Bytes
{
"epoch"
:
3.96
,
"train_loss"
:
1.1451922758938151
,
"train_runtime"
:
4455.6354
,
"train_samples"
:
19966
,
"train_samples_per_second"
:
5.447
,
"train_steps_per_second"
:
0.084
}