Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
WDong
/
sft_0622_policy2
like
0
PEFT
Safetensors
llama-factory
lora
Generated from Trainer
License:
other
Model card
Files
Files and versions
Community
Use this model
5888bd0
sft_0622_policy2
/
eval_results.json
WDong
Upload 16 files
5888bd0
verified
8 months ago
raw
Copy download link
history
blame
Safe
161 Bytes
{
"epoch"
:
5.0
,
"eval_loss"
:
0.8860704898834229
,
"eval_runtime"
:
0.6946
,
"eval_samples_per_second"
:
21.597
,
"eval_steps_per_second"
:
21.597
}