Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
YYYYYYibo
/
approx_nash_maxmin_iter_2
like
0
Text Generation
Transformers
Safetensors
updated
original
mistral
alignment-handbook
trl
dpo
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
abd58f2
approx_nash_maxmin_iter_2
/
train_results.json
YYYYYYibo
Model save
abd58f2
verified
7 months ago
raw
Copy download link
history
blame
Safe
196 Bytes
{
"epoch"
:
0.99
,
"train_loss"
:
0.6859961845516379
,
"train_runtime"
:
39900.7608
,
"train_samples"
:
20000
,
"train_samples_per_second"
:
0.501
,
"train_steps_per_second"
:
0.004
}