Edit model card

Some cringe... Oh well, hello! I present GPT2 to you, but with a bit of kawaii.

Chat template

<|USER|> Hello <|ASSISTANT|> 

Training Results

The following metrics are from the latest training session of our model:

Overview

  • Global Step: 615
  • Training Loss: 0.1303

Detailed Metrics

  • Training Runtime: 413.1481 seconds
  • Training Samples per Second: 5.947
  • Training Steps per Second: 1.489
  • Total Floating Point Operations (FLOs): 641,994,522,624,000.0
  • Training Loss: 0.13032278840134784
  • Epoch: 3.0

Downloads last month
4
Safetensors
Model size
124M params
Tensor type
F32
·
Inference Examples
Inference API (serverless) is not available, repository is disabled.

Dataset used to train Barishni-blinchik/uwbruh-124M