Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
EllieS
/
zephyr-7b-dpo-selfgen
like
0
PEFT
TensorBoard
Safetensors
EllieS/pubmedqa_dpo_selfgen_data
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
c38fd08
zephyr-7b-dpo-selfgen
/
train_results.json
EllieS
Model save
c38fd08
verified
8 months ago
raw
Copy download link
history
blame
No virus
188 Bytes
{
"epoch"
:
3.0
,
"train_loss"
:
0.0
,
"train_runtime"
:
0.0617
,
"train_samples"
:
134157
,
"train_samples_per_second"
:
6527181.256
,
"train_steps_per_second"
:
815915.902
}