Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
gotzmann
/
V16-LoRA
like
0
PEFT
Safetensors
llama-factory
lora
unsloth
Generated from Trainer
License:
other
Model card
Files
Files and versions
Community
Use this model
1af6403
V16-LoRA
/
all_results.json
gotzmann
..
1af6403
4 months ago
raw
Copy download link
history
blame
Safe
207 Bytes
{
"epoch"
:
1.0
,
"total_flos"
:
6.212058917275435e+18
,
"train_loss"
:
1.7427738688708856
,
"train_runtime"
:
80585.133
,
"train_samples_per_second"
:
0.204
,
"train_steps_per_second"
:
0.051
}