Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
chansung
/
coding_llamaduo_result2
like
0
PEFT
TensorBoard
Safetensors
chansung/merged_ds_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
c86992b
coding_llamaduo_result2
/
train_results.json
chansung
Model save
ce4dcad
verified
9 months ago
raw
Copy download link
history
blame
Safe
193 Bytes
{
"epoch"
:
4.98
,
"train_loss"
:
1.826815680011374
,
"train_runtime"
:
4235.156
,
"train_samples"
:
13844
,
"train_samples_per_second"
:
1.156
,
"train_steps_per_second"
:
0.144
}