Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
xinlai
/
Qwen2-7B-SFT-Step-DPO
like
0
Text Generation
Transformers
Safetensors
qwen2
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
d5796e3
Qwen2-7B-SFT-Step-DPO
/
all_results.json
xinlai
upload model
d5796e3
3 months ago
raw
Copy download link
history
blame
No virus
216 Bytes
{
"epoch"
:
8.0
,
"total_flos"
:
0.0
,
"train_loss"
:
0.15622181608736263
,
"train_runtime"
:
4721.8854
,
"train_samples"
:
7548
,
"train_samples_per_second"
:
12.788
,
"train_steps_per_second"
:
0.1
}