Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
just1nseo
/
tulu2-13b-cost-UI-UF-HHRLHF-5e-7
like
0
PEFT
Safetensors
trl
dpo
Generated from Trainer
Model card
Files
Files and versions
Community
Use this model
314d009
tulu2-13b-cost-UI-UF-HHRLHF-5e-7
/
train_results.json
just1nseo
Model save
314d009
verified
about 1 year ago
raw
Copy download link
history
blame
Safe
194 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.658518510975374
,
"train_runtime"
:
42431.3226
,
"train_samples"
:
42110
,
"train_samples_per_second"
:
0.992
,
"train_steps_per_second"
:
0.062
}