Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
chansung
/
coding_llamaduo_result3
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
02cb558
coding_llamaduo_result3
/
eval_results.json
chansung
End of training
02cb558
verified
5 months ago
raw
Copy download link
history
blame
No virus
183 Bytes
{
"epoch"
:
10.0
,
"eval_loss"
:
1.750213384628296
,
"eval_runtime"
:
1.1155
,
"eval_samples"
:
16
,
"eval_samples_per_second"
:
1.793
,
"eval_steps_per_second"
:
0.896
}