training/data_config.json

{
  "model": "google/t5gemma-2-1b-1b",
  "mixture": "t5gemma2_200k",
  "samples": 200000,
  "seed": 42,
  "sources": [
    {
      "source": "ultrachat",
      "converter": "auto",
      "requested": 60000,
      "kept": 60000
    },
    {
      "source": "sharegpt",
      "converter": "auto",
      "requested": 20000,
      "kept": 20000
    },
    {
      "source": "hf:ise-uiuc/Magicoder-Evol-Instruct-110K::train",
      "converter": "instruction_response",
      "requested": 50000,
      "kept": 50000
    },
    {
      "source": "hf:Salesforce/xlam-function-calling-60k::train",
      "converter": "xlam_function_calling",
      "requested": 40000,
      "kept": 40000
    },
    {
      "source": "hf:glaiveai/glaive-function-calling-v2::train",
      "converter": "glaive_function_calling",
      "requested": 20000,
      "kept": 20000
    },
    {
      "source": "hf:TIGER-Lab/MathInstruct::train",
      "converter": "instruction_output",
      "requested": 10000,
      "kept": 10000
    }
  ],
  "decoder_start_token_id": 2,
  "eos_token_id": 1
}