[{'content': 'Help write a letter of 100 -200 words to my future self for '
             'Kyra, reflecting on her goals and aspirations.',
  'role': 'user'},
 {'content': 'Dear Future Self,\n'
             '\n'
             "I hope you're happy and proud of what you've achieved. As I "
             "write this, I'm excited to think about our goals and how far "
             "you've come. One goal was to be a machine learning engineer. I "
             "hope you've worked hard and become skilled in this field. Keep "
             'learning and innovating. Traveling was important to us. I hope '
             "you've seen different places and enjoyed the beauty of our "
             'world. Remember the memories and lessons. Starting a family '
             'mattered to us. If you have kids, treasure every moment. Be '
             'patient, loving, and grateful for your family.\n'
             '\n'
             'Take care of yourself. Rest, reflect, and cherish the time you '
             'spend with loved ones. Remember your dreams and celebrate what '
             "you've achieved. Your determination brought you here. I'm "
             "excited to see the person you've become, the impact you've made, "
             'and the love and joy in your life. Embrace opportunities and '
             'keep dreaming big.\n'
             '\n'
             'With love,\n'
             'Kyra',
  'role': 'assistant'}]

[{"content": "hello", "role": "user"}, {"content": "hi nice to meet you", "role": "assistant"}]
[{"content": "how are you", "role": "user"}, {"content": "I am fine", "role": "assistant"}]
[{"content": "What is your name?", "role": "user"}, {"content": "My name is Mary", "role": "assistant"}]
[{"content": "Which is the best programming language?", "role": "user"}, {"content": "Python", "role": "assistant"}]
.
.
.

<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 03 Oct 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nHelp write a letter of 100 -200 words to my future self for Kyra, reflecting on her goals and aspirations.<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\nDear Future Self,\n\nI hope you're happy and proud of what you've achieved. As I write this, I'm excited to think about our goals and how far you've come. One goal was to be a machine learning engineer. I hope you've worked hard and become skilled in this field. Keep learning and innovating. Traveling was important to us. I hope you've seen different places and enjoyed the beauty of our world. Remember the memories and lessons. Starting a family mattered to us. If you have kids, treasure every moment. Be patient, loving, and grateful for your family.\n\nTake care of yourself. Rest, reflect, and cherish the time you spend with loved ones. Remember your dreams and celebrate what you've achieved. Your determination brought you here. I'm excited to see the person you've become, the impact you've made, and the love and joy in your life. Embrace opportunities and keep dreaming big.\n\nWith love,\nKyra<|eot_id|>

[{"text": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 03 Oct 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nhello<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\nhi nice to meet you<|eot_id|>"}]
[{"text": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 03 Oct 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nhow are you<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\nI am fine<|eot_id|>"}]
[{"text": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 03 Oct 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nWhat is your name?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\nMy name is Mary<|eot_id|>"}]
[{"text": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 03 Oct 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nWhich is the best programming language?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\nPython<|eot_id|>"}]
.
.
.

task: llm-orpo
base_model: meta-llama/Meta-Llama-3-8B-Instruct
project_name: autotrain-llama3-8b-orpo
log: tensorboard
backend: local

data:
  path: argilla/distilabel-capybara-dpo-7k-binarized
  train_split: train
  valid_split: null
  chat_template: chatml
  column_mapping:
    text_column: chosen
    rejected_text_column: rejected
    prompt_text_column: prompt

params:
  block_size: 1024
  model_max_length: 8192
  max_prompt_length: 512
  epochs: 3
  batch_size: 2
  lr: 3e-5
  peft: true
  quantization: int4
  target_modules: all-linear
  padding: right
  optimizer: adamw_torch
  scheduler: linear
  gradient_accumulation: 4
  mixed_precision: fp16

hub:
  username: ${HF_USERNAME}
  token: ${HF_TOKEN}
  push_to_hub: true

data:
  path: path/to/training/file
  train_split: train # name of the training file
  valid_split: null
  chat_template: chatml
  column_mapping:
    text_column: chosen
    rejected_text_column: rejected
    prompt_text_column: prompt

$ autotrain --config config.yaml

--add_eos_token, --add-eos-token
                    Toggle whether to automatically add an End Of Sentence (EOS) token at the end of texts, which can be critical for certain
                    types of models like language models. Only used for `default` trainer
--block_size BLOCK_SIZE, --block-size BLOCK_SIZE
                    Specify the block size for processing sequences. This is maximum sequence length or length of one block of text. Setting to
                    -1 determines block size automatically. Default is -1.
--model_max_length MODEL_MAX_LENGTH, --model-max-length MODEL_MAX_LENGTH
                    Set the maximum length for the model to process in a single batch, which can affect both performance and memory usage.
                    Default is 1024

--block_size BLOCK_SIZE, --block-size BLOCK_SIZE
                    Specify the block size for processing sequences. This is maximum sequence length or length of one block of text. Setting to
                    -1 determines block size automatically. Default is -1.
--model_max_length MODEL_MAX_LENGTH, --model-max-length MODEL_MAX_LENGTH
                    Set the maximum length for the model to process in a single batch, which can affect both performance and memory usage.
                    Default is 1024

--block_size BLOCK_SIZE, --block-size BLOCK_SIZE
                    Specify the block size for processing sequences. This is maximum sequence length or length of one block of text. Setting to
                    -1 determines block size automatically. Default is -1.
--model_max_length MODEL_MAX_LENGTH, --model-max-length MODEL_MAX_LENGTH
                    Set the maximum length for the model to process in a single batch, which can affect both performance and memory usage.
                    Default is 1024

--dpo-beta DPO_BETA, --dpo-beta DPO_BETA
                    Beta for DPO trainer

--model-ref MODEL_REF
                    Reference model to use for DPO when not using PEFT
--block_size BLOCK_SIZE, --block-size BLOCK_SIZE
                    Specify the block size for processing sequences. This is maximum sequence length or length of one block of text. Setting to
                    -1 determines block size automatically. Default is -1.
--model_max_length MODEL_MAX_LENGTH, --model-max-length MODEL_MAX_LENGTH
                    Set the maximum length for the model to process in a single batch, which can affect both performance and memory usage.
                    Default is 1024
--max_prompt_length MAX_PROMPT_LENGTH, --max-prompt-length MAX_PROMPT_LENGTH
                    Specify the maximum length for prompts used in training, particularly relevant for tasks requiring initial contextual input.
                    Used only for `orpo` trainer.
--max_completion_length MAX_COMPLETION_LENGTH, --max-completion-length MAX_COMPLETION_LENGTH
                    Completion length to use, for orpo: encoder-decoder models only

--block_size BLOCK_SIZE, --block-size BLOCK_SIZE
                    Specify the block size for processing sequences. This is maximum sequence length or length of one block of text. Setting to
                    -1 determines block size automatically. Default is -1.
--model_max_length MODEL_MAX_LENGTH, --model-max-length MODEL_MAX_LENGTH
                    Set the maximum length for the model to process in a single batch, which can affect both performance and memory usage.
                    Default is 1024
--max_prompt_length MAX_PROMPT_LENGTH, --max-prompt-length MAX_PROMPT_LENGTH
                    Specify the maximum length for prompts used in training, particularly relevant for tasks requiring initial contextual input.
                    Used only for `orpo` trainer.
--max_completion_length MAX_COMPLETION_LENGTH, --max-completion-length MAX_COMPLETION_LENGTH
                    Completion length to use, for orpo: encoder-decoder models only