Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
dball
/
zephyr-tiny-sft-qlora-unquantized-psp
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrachat_200k
llama
alignment-handbook
Generated from Trainer
trl
sft
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
ca98cd9
zephyr-tiny-sft-qlora-unquantized-psp
/
train_results.json
dball
Model save
25a210c
verified
9 months ago
raw
Copy download link
history
blame
194 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
1.1159586102780843
,
"train_runtime"
:
26065.8571
,
"train_samples"
:
207865
,
"train_samples_per_second"
:
5.603
,
"train_steps_per_second"
:
0.7
}