Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
CharlesLi
/
OpenELM-1_1B-CPO
like
0
Text Generation
Transformers
TensorBoard
Safetensors
openelm
trl
cpo
alignment-handbook
Generated from Trainer
conversational
custom_code
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
8e8e7ca
OpenELM-1_1B-CPO
/
train_results.json
CharlesLi
Model save
8e8e7ca
verified
about 2 months ago
raw
Copy download link
history
blame
Safe
222 Bytes
{
"epoch"
:
2.998953427524856
,
"total_flos"
:
0.0
,
"train_loss"
:
0.0
,
"train_runtime"
:
0.0505
,
"train_samples"
:
61134
,
"train_samples_per_second"
:
3630511.85
,
"train_steps_per_second"
:
56713.757
}