Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
statking
/
zephyr-7b-sft-qdora
like
0
PEFT
Safetensors
HuggingFaceH4/ultrachat_200k
mistral
alignment-handbook
trl
sft
Generated from Trainer
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Use this model
bb643ee
zephyr-7b-sft-qdora
/
eval_results.json
statking
End of training
bb643ee
verified
6 months ago
raw
Copy download link
history
blame
Safe
190 Bytes
{
"epoch"
:
1.0
,
"eval_loss"
:
0.9432145357131958
,
"eval_runtime"
:
1411.7173
,
"eval_samples"
:
23109
,
"eval_samples_per_second"
:
10.931
,
"eval_steps_per_second"
:
0.086
}