Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
jan-hq
/
stealth-finance-v2-dpo-adapter
like
0
PEFT
Safetensors
8 datasets
mixtral
alignment-handbook
trl
dpo
Generated from Trainer
4-bit precision
bitsandbytes
License:
mit
Model card
Files
Files and versions
Community
Train
Use this model
c7f70d3
stealth-finance-v2-dpo-adapter
/
train_results.json
jan-hq
Model save
c7f70d3
verified
9 months ago
raw
Copy download link
history
blame
Safe
197 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.3931771684165408
,
"train_runtime"
:
248473.0607
,
"train_samples"
:
209976
,
"train_samples_per_second"
:
0.845
,
"train_steps_per_second"
:
0.013
}