Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
chansung
/
coding_llamaduo_result1
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
fb3d339
coding_llamaduo_result1
/
all_results.json
chansung
Model save
fb3d339
verified
8 months ago
raw
Copy download link
history
blame
Safe
193 Bytes
{
"epoch"
:
4.93
,
"train_loss"
:
3.0282001667552523
,
"train_runtime"
:
1292.0645
,
"train_samples"
:
3481
,
"train_samples_per_second"
:
1.13
,
"train_steps_per_second"
:
0.139
}