Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
dball
/
zephyr-tiny-sft-qlora-quantized-2
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrachat_200k
llama
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
1
Train
Use this model
effd86f
zephyr-tiny-sft-qlora-quantized-2
/
train_results.json
dball
Model save
eb58f2d
verified
9 months ago
raw
Copy download link
history
blame
Safe
194 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
1.12879814357651
,
"train_runtime"
:
29105.4566
,
"train_samples"
:
207865
,
"train_samples_per_second"
:
5.018
,
"train_steps_per_second"
:
0.627
}