Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
llama-duo
/
llama3-8b-closedqa-gpt4o-100k
like
0
Follow
llama-duo
15
PEFT
TensorBoard
Safetensors
llama-duo/synth_closed_qa_dataset_dedup
llama
alignment-handbook
trl
sft
Generated from Trainer
4-bit precision
bitsandbytes
License:
llama3
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
9be2824
llama3-8b-closedqa-gpt4o-100k
/
eval_results.json
chansung
End of training
9be2824
verified
5 months ago
raw
Copy download link
history
blame
Safe
185 Bytes
{
"epoch"
:
10.0
,
"eval_loss"
:
2.1007895469665527
,
"eval_runtime"
:
0.5646
,
"eval_samples"
:
15
,
"eval_samples_per_second"
:
10.627
,
"eval_steps_per_second"
:
1.771
}