Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
Mastane
/
zephyr-7b-ipo-lora
like
1
PEFT
TensorBoard
Safetensors
mistral
trl-dpo
Generated from Trainer
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
111a004
zephyr-7b-ipo-lora
/
train_results.json
Mastane
Model save
3a36520
11 months ago
raw
Copy download link
history
blame
195 Bytes
{
"epoch"
:
3.0
,
"train_loss"
:
19.467516181882747
,
"train_runtime"
:
42806.6761
,
"train_samples"
:
61966
,
"train_samples_per_second"
:
4.343
,
"train_steps_per_second"
:
0.017
}