Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
xinlai
/
Llama-3-70B-SFT-Step-DPO
like
0
Text Generation
Transformers
Safetensors
llama
conversational
text-generation-inference
Inference Endpoints
arxiv:
2406.18629
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
af41505
Llama-3-70B-SFT-Step-DPO
/
all_results.json
xinlai
upload model
af41505
4 months ago
raw
Copy download link
history
blame
Safe
217 Bytes
{
"epoch"
:
8.0
,
"total_flos"
:
0.0
,
"train_loss"
:
0.11897581996064696
,
"train_runtime"
:
99870.155
,
"train_samples"
:
7548
,
"train_samples_per_second"
:
0.605
,
"train_steps_per_second"
:
0.005
}