{
  "transforms": [
    "sentencepiece",
    "filtertoolong"
  ],
  "share_vocab": false,
  "save_data": "data",
  "tensorboard_log_dir": "tensorboard",
  "overwrite": true,
  "valid_metrics": [
    "BLEU"
  ],
  "report_every": 100,
  "tgt_vocab": "faen/en.eole.vocab",
  "vocab_size_multiple": 8,
  "n_sample": 0,
  "seed": 1234,
  "tensorboard": true,
  "tensorboard_log_dir_dated": "tensorboard/Jan-02_10-23-54",
  "src_vocab_size": 32000,
  "src_vocab": "faen/fa.eole.vocab",
  "tgt_vocab_size": 32000,
  "training": {
    "dropout_steps": [
      0
    ],
    "world_size": 1,
    "warmup_steps": 5000,
    "num_workers": 0,
    "batch_size_multiple": 8,
    "compute_dtype": "torch.float16",
    "param_init_method": "xavier_uniform",
    "normalization": "tokens",
    "accum_steps": [
      0
    ],
    "decay_method": "noam",
    "model_path": "quickmt-fa-en-eole-model",
    "prefetch_factor": 128,
    "batch_type": "tokens",
    "valid_batch_size": 2048,
    "save_checkpoint_steps": 5000,
    "train_steps": 200000,
    "dropout": [
      0.1
    ],
    "attention_dropout": [
      0.1
    ],
    "batch_size": 6000,
    "label_smoothing": 0.1,
    "average_decay": 0.0001,
    "learning_rate": 3.0,
    "max_grad_norm": 0.0,
    "accum_count": [
      20
    ],
    "gpu_ranks": [
      0
    ],
    "keep_checkpoint": 4,
    "bucket_size": 256000,
    "optim": "adamw",
    "valid_steps": 5000,
    "adam_beta2": 0.998
  },
  "data": {
    "corpus_1": {
      "transforms": [
        "sentencepiece",
        "filtertoolong"
      ],
      "weight": 2,
      "path_align": null,
      "path_tgt": "faen/train.cleaned.filtered.en",
      "path_src": "faen/train.cleaned.filtered.fa"
    },
    "corpus_2": {
      "transforms": [
        "sentencepiece",
        "filtertoolong"
      ],
      "weight": 1,
      "path_align": null,
      "path_tgt": "/home/mark/mt/data/newscrawl.2024.en",
      "path_src": "/home/mark/mt/data/newscrawl.backtrans.fa"
    },
    "corpus_3": {
      "transforms": [
        "sentencepiece",
        "filtertoolong"
      ],
      "weight": 2,
      "path_align": null,
      "path_tgt": "/home/mark/mt/data/madlad.en",
      "path_src": "/home/mark/mt/data/madlad.backtrans.fa"
    },
    "valid": {
      "transforms": [
        "sentencepiece",
        "filtertoolong"
      ],
      "path_tgt": "faen/dev.en",
      "path_src": "faen/dev.fa",
      "path_align": null
    }
  },
  "model": {
    "heads": 16,
    "share_embeddings": false,
    "add_estimator": false,
    "layer_norm": "standard",
    "position_encoding_type": "SinusoidalInterleaved",
    "add_qkvbias": false,
    "transformer_ff": 4096,
    "share_decoder_embeddings": false,
    "hidden_size": 768,
    "architecture": "transformer",
    "add_ffnbias": true,
    "mlp_activation_fn": "gelu",
    "embeddings": {
      "word_vec_size": 768,
      "src_word_vec_size": 768,
      "position_encoding_type": "SinusoidalInterleaved",
      "tgt_word_vec_size": 768
    },
    "encoder": {
      "heads": 16,
      "encoder_type": "transformer",
      "layer_norm": "standard",
      "position_encoding_type": "SinusoidalInterleaved",
      "add_qkvbias": false,
      "n_positions": null,
      "transformer_ff": 4096,
      "src_word_vec_size": 768,
      "layers": 12,
      "add_ffnbias": true,
      "hidden_size": 768,
      "mlp_activation_fn": "gelu"
    },
    "decoder": {
      "heads": 16,
      "layer_norm": "standard",
      "position_encoding_type": "SinusoidalInterleaved",
      "add_qkvbias": false,
      "decoder_type": "transformer",
      "n_positions": null,
      "transformer_ff": 4096,
      "tgt_word_vec_size": 768,
      "layers": 2,
      "add_ffnbias": true,
      "hidden_size": 768,
      "mlp_activation_fn": "gelu"
    }
  },
  "transforms_configs": {
    "sentencepiece": {
      "tgt_subword_model": "${MODEL_PATH}/en.spm.model",
      "src_subword_model": "${MODEL_PATH}/fa.spm.model"
    },
    "filtertoolong": {
      "src_seq_length": 256,
      "tgt_seq_length": 256
    }
  }
}