config.yaml

model:
  name: sentiment_classifier
  type: classification
  model:
    pretrained_model: xlm-roberta-base
    num_labels: 3
    dropout: 0.1
    hidden_size: 768
  labels:
  - negative
  - neutral
  - positive
  class_weights: null
  tokenizer:
    max_length: 256
    padding: max_length
    truncation: true
    add_special_tokens: true
  huggingface_hub:
    enabled: true
    repo_id: anpmts/sentiment-classifier
    private: false
    create_model_card: true
    commit_message: Upload sentiment classifier model
    model_card:
      language: multilingual
      license: apache-2.0
      tags:
      - sentiment-analysis
      - text-classification
      - xlm-roberta
      - sequence-classification
      datasets: null
training:
  epochs: 10
  batch_size: 128
  gradient_accumulation_steps: 1
  max_grad_norm: 1.0
  distributed:
    enabled: true
    backend: nccl
    find_unused_parameters: true
  precision:
    mode: bf16
  performance:
    torch_compile: false
    compile_mode: reduce-overhead
    cudnn_benchmark: true
    gradient_checkpointing: false
    tf32: true
    flash_attention_2: false
    matmul_precision: high
    channels_last: false
  optimizer:
    type: adamw
    lr: 2.0e-05
    weight_decay: 0.01
    eps: 1.0e-08
    betas:
    - 0.9
    - 0.999
    fused: false
  scheduler:
    type: cosine
    warmup_ratio: 0.1
    warmup_steps: null
    num_cycles: 0.5
  early_stopping:
    enabled: true
    patience: 3
    min_delta: 0.001
    monitor: val_loss
    mode: min
  checkpoint:
    save_top_k: 2
    monitor: val_loss
    mode: min
    save_last: true
    every_n_epochs: 1
  resume_from_checkpoint: true
  pretrained_checkpoint: null
  load_only_model: true
  eval:
    eval_every_n_steps: null
    eval_accumulation_steps: 1
  dataloader:
    num_workers: 0
    pin_memory: true
    persistent_workers: false
    prefetch_factor: null
  deterministic: false
  benchmark: true
data:
  data_source: local
  chunked:
    enabled: false
    train_path: data/amazon_reviews/train
    val_path: data/amazon_reviews/validation
    test_path: data/amazon_reviews/test
    chunk_size: 100000
    total_train_samples: 3600000
    text_field: text
    label_field: sentiment_label
  huggingface:
    repo: anpmts/trustshop
    split_mapping:
      train: train
      val: validation
      test: test
    field_mapping:
      text: text
      sentiment_label: sentiment_label
      sentiment_score: sentiment_score
      quality_label: quality
    config_name: null
    revision: null
    max_samples: null
  local:
    data_dir: data/amazon_reviews
    processed_dir: data/processed/amazon_reviews
  split:
    train: 0.7
    val: 0.15
    test: 0.15
    stratify: true
  filter_quality:
    enabled: false
    keep_labels:
    - valid
  class_balancing:
    enabled: false
    strategy: oversample
    oversample:
      sampling_strategy: auto
    smote:
      k_neighbors: 5
      sampling_strategy: auto
  augmentation:
    enabled: false
    techniques:
    - synonym_replacement
    - random_deletion
    - random_swap
    augment_ratio: 0.1
  preprocessing:
    lowercase: false
    remove_urls: true
    remove_email: true
    remove_special_chars: false
    min_text_length: 10
  cache:
    enabled: true
    cache_dir: data/.cache/amazon_reviews
  seed: 42
  validation:
    check_missing_fields: false
    check_empty_text: true
    log_invalid_samples: true
project:
  name: ts-train
  seed: 42
  device: cuda
  mixed_precision: true
paths:
  data_dir: data
  data_file: data/output.jsonl
  output_dir: outputs
  model_dir: models
  log_dir: logs
logging:
  use_wandb: true
  wandb_project: ts-absa-classification
  wandb_entity: null
  use_tensorboard: true
  log_interval: 10
experiment:
  name: null
  tags: []
  notes: ''