Step Training Loss

100 9.552530

200 7.434567

300 6.307720

400 5.781603

500 5.459788

600 5.196931

700 4.950012

800 4.757678

900 4.617741

1000 4.509363

1100 4.377576

1200 4.273639

1300 4.202172

1400 4.124585

1500 4.049357

1600 3.946516

1700 3.853138

1800 3.818091

1900 3.790880

2000 3.793084

Downloads last month
301
Safetensors
Model size
34M params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including anwgpt/anwllama-1-base