Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
hansh
/
hansken_human_hql_v2
like
0
PEFT
TensorBoard
Safetensors
hansh/hansken_hql_large
llama
alignment-handbook
trl
sft
Generated from Trainer
4-bit precision
bitsandbytes
License:
llama3.1
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
ff66b11
hansken_human_hql_v2
/
eval_results.json
hansh
End of training
ff66b11
verified
6 months ago
raw
Copy download link
history
blame
Safe
201 Bytes
{
"epoch"
:
8.999365884590995
,
"eval_loss"
:
0.3030637502670288
,
"eval_runtime"
:
1446.9718
,
"eval_samples"
:
17988
,
"eval_samples_per_second"
:
1.09
,
"eval_steps_per_second"
:
1.09
}