Maximum samples (optional, for testing/debugging): 5000

aitraining llm --train \
  --model google/gemma-3-270m \
  --data-path tatsu-lab/alpaca \
  --max-samples 5000 \
  ...

{
  "instruction": "Write a poem about the ocean",
  "input": "",
  "output": "The waves crash upon the shore..."
}

{
  "conversations": [
    { "from": "human", "value": "Hello! How are you?" },
    { "from": "gpt", "value": "I'm doing well, thank you!" },
    { "from": "human", "value": "Can you help me with Python?" },
    { "from": "gpt", "value": "Of course! What do you need help with?" }
  ]
}

{
  "messages": [
    { "role": "system", "content": "You are a helpful assistant." },
    { "role": "user", "content": "What is 2+2?" },
    { "role": "assistant", "content": "2+2 equals 4." }
  ]
}

{
  "question": "What is the capital of France?",
  "answer": "The capital of France is Paris."
}

{
  "prompt": "Explain quantum physics",
  "chosen": "Quantum physics is a branch of science that studies...",
  "rejected": "idk its like small particles or something lol"
}

{
  "text": "This is a document about machine learning. It covers various topics..."
}

🔄 Dataset Format Analysis:
✓ Detected dataset format: alpaca
  • Your dataset is in alpaca format
  • This can be converted to the standard messages format for better compatibility

Do you want to analyze and convert your dataset to the model's chat format? (y/N): y

{ "instruction": "Translate to French", "input": "Hello", "output": "Bonjour" }

<start_of_turn>user
Translate to French

Hello<end_of_turn>
<start_of_turn>model
Bonjour<end_of_turn>

instruction,input,output
"Write a poem about cats","","Soft paws, gentle eyes..."
"Translate to Spanish","Hello","Hola"
"Summarize this","Long article text here","Brief summary"

Dataset (number, HF ID, or command): ./my_data/training.csv

{"instruction": "Write a poem", "output": "..."}
{"instruction": "Translate", "input": "Hello", "output": "Hola"}

my_data/
  train.jsonl
  validation.jsonl  (optional)

Dataset (number, HF ID, or command): ./my_data

✓ Dataset loaded. Splits found: train, test, validation
✓ Using split: train (auto-selected from: train, test, validation)

Validation split name (optional) [validation]:

Maximum samples (optional, for testing/debugging): 1000

📝 Column Mapping:

For instruction tuning (SFT):
• Should contain complete conversations or instruction-response pairs

Text column name [text]: my_instruction_column
✓ text_column: my_instruction_column

DPO/ORPO requires three columns:
  • Prompt column: the instruction/question
  • Chosen column: the preferred response
  • Rejected column: the non-preferred response

Prompt column name [REQUIRED] [prompt]: question
Chosen response column [REQUIRED] [chosen]: good_response
Rejected response column [REQUIRED] [rejected]: bad_response