Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
statking
/
MetaLlama8BInstructQLoRA
like
0
PEFT
Safetensors
HuggingFaceH4/ultrachat_200k
llama
alignment-handbook
trl
sft
Generated from Trainer
License:
llama3
Model card
Files
Files and versions
Community
Train
Use this model
4061eaa
MetaLlama8BInstructQLoRA
/
eval_results.json
statking
End of training
4061eaa
verified
6 months ago
raw
Copy download link
history
blame
Safe
201 Bytes
{
"epoch"
:
0.9997336884154461
,
"eval_loss"
:
1.118857979774475
,
"eval_runtime"
:
1662.5703
,
"eval_samples"
:
23109
,
"eval_samples_per_second"
:
7.996
,
"eval_steps_per_second"
:
0.5
}