Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
objects76
/
zephyr-7b-sft-qlora
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrachat_200k
mistral
alignment-handbook
trl
sft
Generated from Trainer
4-bit precision
bitsandbytes
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
900b803
zephyr-7b-sft-qlora
/
eval_results.json
objects76
End of training
900b803
verified
7 months ago
raw
Copy download link
history
blame
Safe
188 Bytes
{
"epoch"
:
1.0
,
"eval_loss"
:
0.9524012804031372
,
"eval_runtime"
:
1936.0539
,
"eval_samples"
:
23109
,
"eval_samples_per_second"
:
7.97
,
"eval_steps_per_second"
:
0.996
}