Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
chchen
/
Falcon-7B-Instruct-ORPO-SFT
like
0
PEFT
Safetensors
llama-factory
lora
Generated from Trainer
License:
apache-2.0
Model card
Files
Files and versions
Community
Use this model
a1f8010
Falcon-7B-Instruct-ORPO-SFT
/
eval_results.json
chchen
End of training
a1f8010
verified
5 months ago
raw
Copy download link
history
blame
Safe
176 Bytes
{
"epoch"
:
2.986666666666667
,
"eval_loss"
:
0.16554969549179077
,
"eval_runtime"
:
2.7017
,
"eval_samples_per_second"
:
37.014
,
"eval_steps_per_second"
:
18.507
}