Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
NovoCode
/
Tiger-DPO
like
0
PEFT
Safetensors
llama-factory
lora
Generated from Trainer
License:
other
Model card
Files
Files and versions
Community
1
Use this model
7fc4622
Tiger-DPO
/
train_results.json
NovoCode
Upload folder using huggingface_hub
926bbb4
verified
7 months ago
raw
Copy download link
history
blame
No virus
166 Bytes
{
"epoch"
:
0.99
,
"train_loss"
:
1.7228616259314797
,
"train_runtime"
:
47.9316
,
"train_samples_per_second"
:
22.157
,
"train_steps_per_second"
:
1.377
}