Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
ale-bay
/
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
9227392
zephyr-7b-sft-qlora
/
eval_results.json
ale-bay
End of training
9227392
verified
6 months ago
raw
Copy download link
history
blame
Safe
188 Bytes
{
"epoch"
:
1.0
,
"eval_loss"
:
0.9517214298248291
,
"eval_runtime"
:
970.177
,
"eval_samples"
:
23109
,
"eval_samples_per_second"
:
15.905
,
"eval_steps_per_second"
:
0.995
}