Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
yyx123
/
Yi-6B-ruozhiba
like
0
PEFT
Safetensors
ruozhiba
llama
alignment-handbook
Generated from Trainer
trl
sft
4-bit precision
bitsandbytes
License:
other
Model card
Files
Files and versions
Community
Train
Use this model
7f216d1
Yi-6B-ruozhiba
/
train_results.json
yyx123
Model save
7f216d1
verified
6 months ago
raw
Copy download link
history
blame
Safe
193 Bytes
{
"epoch"
:
20.0
,
"train_loss"
:
0.5375886155258526
,
"train_runtime"
:
2988.6301
,
"train_samples"
:
217
,
"train_samples_per_second"
:
1.452
,
"train_steps_per_second"
:
0.368
}