Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
alignment-handbook
/
zephyr-7b-sft-qlora
like
7
Follow
H4 Alignment Handbook
22
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrachat_200k
mistral
alignment-handbook
Generated from Trainer
trl
sft
4-bit precision
bitsandbytes
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
2
Train
Use this model
d98910a
zephyr-7b-sft-qlora
/
eval_results.json
lewtun
HF staff
Model save
76e3ad6
11 months ago
raw
Copy download link
history
blame
Safe
189 Bytes
{
"epoch"
:
1.0
,
"eval_loss"
:
0.9693147540092468
,
"eval_runtime"
:
358.5672
,
"eval_samples"
:
23110
,
"eval_samples_per_second"
:
42.179
,
"eval_steps_per_second"
:
0.661
}