Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
mimicheng
/
mistral-7b-dpo-qlora-2ep
like
0
PEFT
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
Generated from Trainer
trl
dpo
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Use this model
47d1a60
mistral-7b-dpo-qlora-2ep
/
train_results.json
mimicheng
Model save
47d1a60
verified
10 months ago
raw
Copy download link
history
blame
194 Bytes
{
"epoch"
:
2.0
,
"train_loss"
:
0.6517634629204897
,
"train_runtime"
:
44544.264
,
"train_samples"
:
61135
,
"train_samples_per_second"
:
2.745
,
"train_steps_per_second"
:
0.172
}