Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
YYYYYYibo
/
two_agent_1_epoch_2_rdpo_iter_6
like
0
Safetensors
updated
original
mistral
alignment-handbook
trl
dpo
Generated from Trainer
Model card
Files
Files and versions
Community
Train
adefe4c
two_agent_1_epoch_2_rdpo_iter_6
/
all_results.json
YYYYYYibo
Model save
811d9fc
verified
5 months ago
raw
Copy download link
history
blame
Safe
194 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.688920441902045
,
"train_runtime"
:
33857.0653
,
"train_samples"
:
21135
,
"train_samples_per_second"
:
0.624
,
"train_steps_per_second"
:
0.005
}