Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
lewtun
/
zephyr-7b-dpo-qlora
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
Generated from Trainer
trl
dpo
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
d03ce14
zephyr-7b-dpo-qlora
/
train_results.json
lewtun
HF staff
Model save
df12624
10 months ago
raw
Copy download link
history
blame
Safe
194 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.5648497628454511
,
"train_runtime"
:
7573.6114
,
"train_samples"
:
61135
,
"train_samples_per_second"
:
8.072
,
"train_steps_per_second"
:
0.252
}