Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
YYYYYYibo
/
spin_dpo_dpo_iter_2
like
0
Safetensors
updated
original
mistral
alignment-handbook
trl
dpo
Generated from Trainer
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
3388f08
spin_dpo_dpo_iter_2
/
all_results.json
YYYYYYibo
Model save
c6523f5
verified
6 months ago
raw
Copy download link
history
blame
Safe
196 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.37798528717114377
,
"train_runtime"
:
17606.5611
,
"train_samples"
:
20000
,
"train_samples_per_second"
:
1.136
,
"train_steps_per_second"
:
0.009
}