Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
EllieS
/
zephyr-dpo-timedial-selfgen-mix2
like
0
PEFT
TensorBoard
Safetensors
EllieS/timedial_dpo
mistral
alignment-handbook
trl
dpo
Generated from Trainer
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
7b5f7f6
zephyr-dpo-timedial-selfgen-mix2
/
train_results.json
EllieS
Model save
7b5f7f6
verified
8 months ago
raw
Copy download link
history
blame
Safe
192 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.06608598743755512
,
"train_runtime"
:
154.0704
,
"train_samples"
:
1157
,
"train_samples_per_second"
:
7.51
,
"train_steps_per_second"
:
1.876
}