File size: 2,703 Bytes
cdc3398
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
architecture:
    backbone_dtype: int4
    force_embedding_gradients: false
    gradient_checkpointing: true
    intermediate_dropout: 0.0
    pretrained: true
    pretrained_weights: ''
augmentation:
    neftune_noise_alpha: 0.0
    random_parent_probability: 0.0
    skip_parent_probability: 0.0
    token_mask_probability: 0.0
dataset:
    add_eos_token_to_answer: false
    add_eos_token_to_prompt: false
    add_eos_token_to_system: false
    answer_column: Category_ID
    chatbot_author: H2O.ai
    chatbot_name: h2oGPT
    data_sample: 1.0
    data_sample_choice:
    - Train
    - Validation
    limit_chained_samples: false
    mask_prompt_labels: true
    num_classes: 11
    parent_id_column: None
    personalize: false
    prompt_column:
    - Description
    system_column: None
    text_answer_separator: ''
    text_prompt_start: ''
    text_system_start: ''
    train_dataframe: /home/llmstudio/mount/data/user/bank_transactions_categories_v2/bank_transactions_categories_train.csv
    validation_dataframe: /home/llmstudio/mount/data/user/bank_transactions_categories_v2/bank_transactions_categories_test.csv
    validation_size: 0.01
    validation_strategy: custom
environment:
    compile_model: false
    deepspeed_reduce_bucket_size: 1000000
    deepspeed_stage3_param_persistence_threshold: 1000000
    deepspeed_stage3_prefetch_bucket_size: 1000000
    find_unused_parameters: false
    gpus:
    - '0'
    huggingface_branch: main
    mixed_precision: true
    number_of_workers: 8
    seed: -1
    trust_remote_code: true
    use_deepspeed: false
experiment_name: bank_tx_cat_opt_125m
llm_backbone: facebook/opt-125m
logging:
    logger: None
    neptune_project: ''
output_directory: /home/llmstudio/mount/output/user/bank_tx_cat_opt_125m/
prediction:
    batch_size_inference: 0
    metric: LogLoss
problem_type: text_causal_classification_modeling
tokenizer:
    add_prefix_space: false
    add_prompt_answer_tokens: false
    max_length: 512
    max_length_answer: 256
    max_length_prompt: 256
    padding_quantile: 1.0
    use_fast: true
training:
    batch_size: 2
    differential_learning_rate: 1.0e-05
    differential_learning_rate_layers:
    - classification_head
    drop_last_batch: true
    epochs: 1
    evaluate_before_training: false
    evaluation_epochs: 1.0
    grad_accumulation: 1
    gradient_clip: 0.0
    learning_rate: 0.0001
    lora: true
    lora_alpha: 16
    lora_dropout: 0.05
    lora_r: 4
    lora_target_modules: ''
    loss_function: CrossEntropyLoss
    optimizer: AdamW
    save_best_checkpoint: false
    schedule: Cosine
    train_validation_data: false
    use_flash_attention_2: false
    warmup_epochs: 0.0
    weight_decay: 0.0