{
  // Data Arguments
  //################
  "dataset_HF": "c-bone/mpdb-slme-full",
  "pretrained_tokenizer_dir": "HF-cif-tokenizer",
  "context_length": 1024,
  // Filters
  "remove_CIFs_above_context": false,
  "remove_CIFs_with_unk": true,

    // Conditional Arguments
  //#######################
  "condition_columns": "['norm_SLME']" ,
  "n_prefix_tokens": 1,
  "n_hidden_cond": 768,
  "cond_dropout": 0.14,
  "share_layers": false,
  "n_heads_sharing_slider": 2,
  "cond_lr": 3.27508165E-5,
  "cond_wd": 0.13,
  "activate_conditionality": "PKV",


  // Model Arguments
  //#################
  // Model Depth
  // n_positions has been tied to context_length
  "n_embd": 512,
  "n_layer": 8,
  "n_head": 8,
  // Dropout
  "residual_dropout": 0.1,
  "embedding_dropout": 0.1,
  "attention_dropout": 0.1,

  // Trainer Arguments
  //###################
  // Batching
  "train_batch_size": 32,
  "eval_batch_size": 32,
  "gradient_accumulation_steps": 1,
  "auto_find_batch_size": false,
  // Learning Rate and Optimizer
  "learning_rate": 1.0596703391605471e-06,
  "lr_scheduler_type": "cosine_with_min_lr",
  "lr_scheduler_kwargs": {
    "min_lr_rate": 0.01
  },
  "warmup_steps": 250,
  "adam_beta1": 0.9,
  "adam_beta2": 0.999,
  "grad_clip": 1.0,
  // "max_grad_norm": 1.0,
  "weight_decay": 0.09,
  // Logging
  "output_dir": "model_ckpts/mpdb_slme/PKV-opt",
  "save_total_limit": 2,
  "report_to": "wandb",
  "wandb_project_folder": "SLME",
  "pretrained_model_dir": "model_ckpts/mpdb-small-base-lematerial/checkpoint-1250000",
  "eval_strategy": "no",
  "logging_steps": 50,
  "save_strategy": "steps",
  "max_steps": 16000,
  // Utils
  "seed": 1,
  "data_seed": 1,
  // "load_best_model_at_end": true,
  "metric_for_best_model": "train_loss",
  "greater_is_better": false,
  "torch_compile": true,
  "fp16": true,
  "deepspeed_config": "_config_files/deepspeed_default.json",

  // CodeCarbon Arguments
  //######################
  "codecarbon": true,
  "tracker_project": "CrystaLLM-pi"
}