Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
mimicheng
/
zephyr-7b-sft-qlora
like
0
PEFT
Safetensors
HuggingFaceH4/ultrachat_200k
mixtral
alignment-handbook
Generated from Trainer
trl
sft
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Use this model
9b06825
zephyr-7b-sft-qlora
/
train_results.json
mimicheng
Model save
9b06825
verified
about 1 year ago
raw
Copy download link
history
blame
Safe
196 Bytes
{
"epoch"
:
2.0
,
"train_loss"
:
0.9321640750150876
,
"train_runtime"
:
247978.1019
,
"train_samples"
:
207865
,
"train_samples_per_second"
:
1.125
,
"train_steps_per_second"
:
0.07
}