Home Explore Help
Sign In
radu
/
LLamaRecipes
mirror of https://github.com/facebookresearch/llama-recipes.git
Watch 1
Star 0
Fork 0
Files Issues 0 Wiki
Branch: transfer_experiment
Branches Tags
LLamaRecipes
/
end-to-end-use-cases
/
transferability
/
config.yaml

config.yaml 7.3 KB
Permalink History Raw

12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061 
  1. task1:
    2. 

  2.   dataset: singhsays/fake-w2-us-tax-form-dataset
    3. 

  3.   is_local: false
    4. 

  4.   system_prompt: null
    5. 

  5.   user_prompt: "You are an expert document information extraction system. I will show you an image of a W-2 tax form. Please extract all the information from this form and return it in a JSON format. Include all fields such as employee details, employer details, wages, federal income tax withheld, social security wages, social security tax withheld, medicare wages and tips, medicare tax withheld, and any other information present on the form. Return ONLY the JSON output without any additional text or explanations following this schema {'properties': {'box_b_employer_identification_number': {'title': 'Box B Employer Identification Number', 'type': 'string'}, 'box_c_employer_name': {'title': 'Box C Employer Name', 'type': 'string'}, 'box_c_employer_street_address': {'title': 'Box C Employer Street Address', 'type': 'string'}, 'box_c_employer_city_state_zip': {'title': 'Box C Employer City State Zip', 'type': 'string'}, 'box_a_employee_ssn': {'title': 'Box A Employee Ssn', 'type': 'string'}, 'box_e_employee_name': {'title': 'Box E Employee Name', 'type': 'string'}, 'box_e_employee_street_address': {'title': 'Box E Employee Street Address', 'type': 'string'}, 'box_e_employee_city_state_zip': {'title': 'Box E Employee City State Zip', 'type': 'string'}, 'box_d_control_number': {'title': 'Box D Control Number', 'type': 'integer'}, 'box_1_wages': {'title': 'Box 1 Wages', 'type': 'number'}, 'box_2_federal_tax_withheld': {'title': 'Box 2 Federal Tax Withheld', 'type': 'number'}, 'box_3_social_security_wages': {'title': 'Box 3 Social Security Wages', 'type': 'number'}, 'box_4_social_security_tax_withheld': {'title': 'Box 4 Social Security Tax Withheld', 'type': 'number'}, 'box_5_medicare_wages': {'title': 'Box 5 Medicare Wages', 'type': 'number'}, 'box_6_medicare_wages_tax_withheld': {'title': 'Box 6 Medicare Wages Tax Withheld', 'type': 'number'}, 'box_7_social_security_tips': {'title': 'Box 7 Social Security Tips', 'type': 'number'}, 'box_8_allocated_tips': {'title': 'Box 8 Allocated Tips', 'type': 'number'}, 'box_9_advance_eic_payment': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Box 9 Advance Eic Payment'}, 'box_10_dependent_care_benefits': {'title': 'Box 10 Dependent Care Benefits', 'type': 'number'}, 'box_11_nonqualified_plans': {'title': 'Box 11 Nonqualified Plans', 'type': 'number'}, 'box_12a_code': {'title': 'Box 12A Code', 'type': 'string'}, 'box_12a_value': {'title': 'Box 12A Value', 'type': 'number'}, 'box_12b_code': {'title': 'Box 12B Code', 'type': 'string'}, 'box_12b_value': {'title': 'Box 12B Value', 'type': 'number'}, 'box_12c_code': {'title': 'Box 12C Code', 'type': 'string'}, 'box_12c_value': {'title': 'Box 12C Value', 'type': 'number'}, 'box_12d_code': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Box 12D Code'}, 'box_12d_value': {'title': 'Box 12D Value', 'type': 'number'}, 'box_13_statutary_employee': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Box 13 Statutary Employee'}, 'box_13_retirement_plan': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Box 13 Retirement Plan'}, 'box_13_third_part_sick_pay': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Box 13 Third Part Sick Pay'}, 'box_15_1_state': {'title': 'Box 15 1 State', 'type': 'string'}, 'box_15_1_employee_state_id': {'title': 'Box 15 1 Employee State Id', 'type': 'string'}, 'box_16_1_state_wages': {'title': 'Box 16 1 State Wages', 'type': 'number'}, 'box_17_1_state_income_tax': {'title': 'Box 17 1 State Income Tax', 'type': 'number'}, 'box_18_1_local_wages': {'title': 'Box 18 1 Local Wages', 'type': 'number'}, 'box_19_1_local_income_tax': {'title': 'Box 19 1 Local Income Tax', 'type': 'number'}, 'box_20_1_locality': {'title': 'Box 20 1 Locality', 'type': 'string'}, 'box_15_2_state': {'title': 'Box 15 2 State', 'type': 'string'}, 'box_15_2_employee_state_id': {'title': 'Box 15 2 Employee State Id', 'type': 'string'}, 'box_16_2_state_wages': {'title': 'Box 16 2 State Wages', 'type': 'number'}, 'box_17_2_state_income_tax': {'title': 'Box 17 2 State Income Tax', 'type': 'number'}, 'box_18_2_local_wages': {'title': 'Box 18 2 Local Wages', 'type': 'number'}, 'box_19_2_local_income_tax': {'title': 'Box 19 2 Local Income Tax', 'type': 'number'}, 'box_20_2_locality': {'title': 'Box 20 2 Locality', 'type': 'string'}}, 'required': ['box_b_employer_identification_number', 'box_c_employer_name', 'box_c_employer_street_address', 'box_c_employer_city_state_zip', 'box_a_employee_ssn', 'box_e_employee_name', 'box_e_employee_street_address', 'box_e_employee_city_state_zip', 'box_d_control_number', 'box_1_wages', 'box_2_federal_tax_withheld', 'box_3_social_security_wages', 'box_4_social_security_tax_withheld', 'box_5_medicare_wages', 'box_6_medicare_wages_tax_withheld', 'box_7_social_security_tips', 'box_8_allocated_tips', 'box_9_advance_eic_payment', 'box_10_dependent_care_benefits', 'box_11_nonqualified_plans', 'box_12a_code', 'box_12a_value', 'box_12b_code', 'box_12b_value', 'box_12c_code', 'box_12c_value', 'box_12d_code', 'box_12d_value', 'box_13_statutary_employee', 'box_13_retirement_plan', 'box_13_third_part_sick_pay', 'box_15_1_state', 'box_15_1_employee_state_id', 'box_16_1_state_wages', 'box_17_1_state_income_tax', 'box_18_1_local_wages', 'box_19_1_local_income_tax', 'box_20_1_locality', 'box_15_2_state', 'box_15_2_employee_state_id', 'box_16_2_state_wages', 'box_17_2_state_income_tax', 'box_18_2_local_wages', 'box_19_2_local_income_tax', 'box_20_2_locality'], 'title': 'W2Form', 'type': 'object'}"
    6. 

  6.   sample_percent: 1      # % of the dataset to use; 1.0 means use the entire dataset
    7. 

  7.   resplit_train_percent: 0.3   # % of the sampled dataset to use for training; the rest is used for validation
    8. 

  8.   image_column: image
    9. 

  9.   user_text_column: null
    10. 

  10.   assistant_text_column: ground_truth
    11. 

  11.   grader: JSONGrader  # Task-specific grader
    12. 

  12. 

  13. 

  14. task2:
    15. 

  15.   dataset: getomni-ai/ocr-benchmark
    16. 

  16.   is_local: false
    17. 

  17.   system_prompt: You are a helpful assistant, you will always respond only in JSON following the provided JSON schema.
    18. 

  18.   user_prompt: "Extract the data in this image as a JSON. Use the following JSON schema:\n"
    19. 

  19.   sample_percent: 0.6
    20. 

  20.   resplit_train_percent: 0.0
    21. 

  21.   image_column: image
    22. 

  22.   user_text_column: json_schema
    23. 

  23.   assistant_text_column: true_json_output
    24. 

  24.   grader: JSONGrader
    25. 

  25. 

  26. 

  27. finetuning:
    28. 

  28.   ### FFT LAYERS TO TRAIN - ALL FALSE FOR NO FFT
    29. 

  29.   fusion: true
    30. 

  30.   fusion+encoder: false
    31. 

  31.   fusion+decoder: false
    32. 

  32.   fusion+encoder+decoder: true
    33. 

  33.   ### LORA RANKS TO TRAIN - EMPTY LIST FOR NO LORA
    34. 

  34.   lora_ranks: [8, 64]
    35. 

  35.   ### TORCHTUNE CONFIG
    36. 

  36.   fft_torchtune_config: transferability/finetune/8b_full.yaml
    37. 

  37.   lora_torchtune_config: transferability/finetune/8b_lora.yaml
    38. 

  38.   ### TORCHTUNE ARGS
    39. 

  39.   model_path: /path/to/llama31/ckpt
    40. 

  40.   tokenizer_path: /path/to/llama31/ckpt/tokenizer.model
    41. 

  41.   epochs: 5                # Number of training epochs
    42. 

  42.   batch_size: 8                 # Batch size per device for training
    43. 

  43.   ngpu: 4
    44. 

  44.   distributed: true             # Whether to use distributed training
    45. 

  45. 

  46. 

  47. 

  48. evals:
    49. 

  49.   nb_eval_samples: null   # Number of samples to use for evaluation; null means use the entire dataset.
    50. 

  50.   checkpoint_to_eval: -1
    51. 

  51.   model_server_args:
    52. 

  52.     tensor_parallel_size: 2
    53. 

  53.     max_model_len: 8192
    54. 

  54.     max_num_seqs: 128
    55. 

  55.     enforce_eager: true
    56. 

  56.   inference_params:
    57. 

  57.     temperature: 0
    58. 

  58.     top_p: 1.0
    59. 

  59.     max_completion_tokens: 4096
    60. 

  60.     seed: 42
    61. 

  61.