{
  "alpha_contrastive_loss": 0.5,
  "architectures": [
    "BacformerForCausalGM"
  ],
  "attention_probs_dropout_prob": 0.1,
  "auto_map": {
    "AutoConfig": "configuration_bacformer.BacformerConfig",
    "AutoModelForCausalLM": "modeling_bacformer.BacformerForCausalGM"
  },
  "batch_size": 1,
  "ckpt_path": null,
  "dataloader_num_workers": 10,
  "early_stopping_patience": 8,
  "end_token_id": 5,
  "eval_steps": 4000,
  "gradient_accumulation_steps": 8,
  "hidden_dropout_prob": 0.1,
  "hidden_size": 480,
  "id2label": {
    "0": "LABEL_0"
  },
  "initializer_range": 0.02,
  "input_dir": "/rds/user/mw896/rds-flotolab-9X9gY1OFt4M/projects/bacformer/input-data/eval-genomes/",
  "intermediate_size": 1280,
  "is_causal_gm": true,
  "label2id": {
    "LABEL_0": 0
  },
  "layer_norm_eps": 1e-12,
  "logging_steps": 500,
  "lr": 0.00015,
  "mask_token_id": 1,
  "max_epochs": 10,
  "max_grad_norm": 2.0,
  "max_n_contigs": 1000,
  "max_n_proteins": 6000,
  "max_position_embeddings": 6000,
  "max_token_type_embeddings": 1000,
  "mgm_probability": 0.0,
  "model_type": "bacformer",
  "monitor_metric": "loss",
  "n_nodes": 1,
  "n_total_samples": 1203731,
  "num_attention_heads": 8,
  "num_hidden_layers": 12,
  "num_special_tokens": 6,
  "output_dir": "/rds/user/mw896/rds-flotolab-9X9gY1OFt4M/projects/bacformer/output-data/all-genomes/runs-causal/12L-full-data-rotary-lr15e-5/",
  "pad_token_id": 0,
  "pretrained_model_dir": null,
  "problem_type": "single_label_classification",
  "prot_emb_token_id": 4,
  "protein_clusters_vocab_size": 50000,
  "random_state": 30,
  "return_attn_weights": false,
  "return_dict": false,
  "save_steps": 4000,
  "special_tokens_dict": {
    "CLS": 2,
    "END": 5,
    "MASK": 1,
    "PAD": 0,
    "PROT_EMB": 4,
    "SEP": 3
  },
  "test": false,
  "test_after_train": false,
  "torch_dtype": "bfloat16",
  "train_subset_prop": 1.0,
  "transformers_version": "4.50.3",
  "warmup_proportion": 0.1,
  "weight_decay": 0.01
}