eole_model/config.json

{
  "save_data": "zh_en/data_spm",
  "src_vocab": "zh-en-benchmark/src.eole.vocab",
  "report_every": 100,
  "share_vocab": false,
  "tgt_vocab": "zh-en-benchmark/tgt.eole.vocab",
  "vocab_size_multiple": 8,
  "tensorboard_log_dir_dated": "tensorboard/Feb-12_13-34-26",
  "src_vocab_size": 32000,
  "tensorboard": true,
  "n_sample": 0,
  "tgt_vocab_size": 32000,
  "valid_metrics": [
    "BLEU"
  ],
  "tensorboard_log_dir": "tensorboard",
  "seed": 1234,
  "overwrite": true,
  "transforms": [
    "sentencepiece",
    "filtertoolong"
  ],
  "training": {
    "accum_count": [
      16
    ],
    "train_steps": 100000,
    "gpu_ranks": [
      0
    ],
    "save_checkpoint_steps": 2000,
    "decay_method": "noam",
    "bucket_size": 128000,
    "world_size": 1,
    "accum_steps": [
      0
    ],
    "optim": "pagedadamw8bit",
    "prefetch_factor": 100,
    "compute_dtype": "torch.bfloat16",
    "normalization": "tokens",
    "label_smoothing": 0.1,
    "batch_size_multiple": 8,
    "dropout_steps": [
      0
    ],
    "average_decay": 0.0001,
    "dropout": [
      0.1
    ],
    "batch_type": "tokens",
    "valid_batch_size": 8192,
    "param_init_method": "xavier_uniform",
    "adam_beta2": 0.998,
    "model_path": "zh-en-benchmark/model",
    "keep_checkpoint": 4,
    "num_workers": 0,
    "batch_size": 8192,
    "attention_dropout": [
      0.1
    ],
    "warmup_steps": 10000,
    "valid_steps": 2000,
    "max_grad_norm": 2.0,
    "learning_rate": 2.0
  },
  "data": {
    "corpus_1": {
      "path_align": null,
      "path_src": "zh-en/train.ready.zh",
      "path_tgt": "zh-en/train.ready.en",
      "transforms": [
        "sentencepiece",
        "filtertoolong"
      ]
    },
    "valid": {
      "path_align": null,
      "path_src": "zh-en-benchmark/dev.zho",
      "path_tgt": "zh-en-benchmark/dev.eng",
      "transforms": [
        "sentencepiece",
        "filtertoolong"
      ]
    }
  },
  "transforms_configs": {
    "sentencepiece": {
      "tgt_subword_model": "${MODEL_PATH}/tgt.spm.model",
      "src_subword_model": "${MODEL_PATH}/src.spm.model"
    },
    "filtertoolong": {
      "tgt_seq_length": 256,
      "src_seq_length": 256
    }
  },
  "model": {
    "share_decoder_embeddings": true,
    "position_encoding_type": "SinusoidalInterleaved",
    "add_qkvbias": false,
    "architecture": "transformer",
    "add_ffnbias": true,
    "hidden_size": 1024,
    "transformer_ff": 4096,
    "mlp_activation_fn": "gelu",
    "norm_eps": 1e-06,
    "layer_norm": "standard",
    "heads": 16,
    "add_estimator": false,
    "share_embeddings": false,
    "decoder": {
      "heads": 16,
      "decoder_type": "transformer",
      "position_encoding_type": "SinusoidalInterleaved",
      "add_qkvbias": false,
      "layers": 2,
      "add_ffnbias": true,
      "hidden_size": 1024,
      "n_positions": null,
      "transformer_ff": 4096,
      "rope_config": null,
      "mlp_activation_fn": "gelu",
      "norm_eps": 1e-06,
      "layer_norm": "standard",
      "tgt_word_vec_size": 1024
    },
    "embeddings": {
      "word_vec_size": 1024,
      "position_encoding_type": "SinusoidalInterleaved",
      "tgt_word_vec_size": 1024,
      "src_word_vec_size": 1024
    },
    "encoder": {
      "heads": 16,
      "position_encoding_type": "SinusoidalInterleaved",
      "add_qkvbias": false,
      "layers": 8,
      "add_ffnbias": true,
      "hidden_size": 1024,
      "n_positions": null,
      "src_word_vec_size": 1024,
      "transformer_ff": 4096,
      "rope_config": null,
      "mlp_activation_fn": "gelu",
      "norm_eps": 1e-06,
      "layer_norm": "standard",
      "encoder_type": "transformer"
    }
  }
}