Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
ShenaoZ
/
vanilla_dpo_iter_4
like
0
PEFT
Safetensors
updated
original
mistral
alignment-handbook
Generated from Trainer
trl
dpo
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Use this model
2cbbc30
vanilla_dpo_iter_4
/
train_results.json
ShenaoZ
Model save
2cbbc30
verified
9 months ago
raw
Copy download link
history
blame
Safe
195 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.6200787784197391
,
"train_runtime"
:
14536.4272
,
"train_samples"
:
20000
,
"train_samples_per_second"
:
1.376
,
"train_steps_per_second"
:
0.011
}