Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
YYYYYYibo
/
gshf_ours_1_iter_3
like
0
Safetensors
updated
original
mistral
alignment-handbook
trl
dpo
Generated from Trainer
Model card
Files
Files and versions
Community
Train
389395f
gshf_ours_1_iter_3
/
train_results.json
YYYYYYibo
Model save
389395f
verified
3 months ago
raw
Copy download link
history
blame
Safe
195 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.6651211370121349
,
"train_runtime"
:
19266.0029
,
"train_samples"
:
21135
,
"train_samples_per_second"
:
1.097
,
"train_steps_per_second"
:
0.009
}