{
  "transformers_version": "5.19.0",
  "architectures": [
    "ModernBertModel"
  ],
  "output_hidden_states": false,
  "return_dict": true,
  "dtype": "float32",
  "chunk_size_feed_forward": 0,
  "is_encoder_decoder": false,
  "id2label": {
    "0": "LABEL_0"
  },
  "label2id": {
    "LABEL_0": 0
  },
  "problem_type": null,
  "vocab_size": 50369,
  "hidden_size": 768,
  "intermediate_size": 1152,
  "num_hidden_layers": 22,
  "num_attention_heads": 12,
  "hidden_activation": "gelu",
  "max_position_embeddings": 7999,
  "initializer_range": 0.02,
  "initializer_cutoff_factor": 2.0,
  "norm_eps": 1e-05,
  "norm_bias": false,
  "pad_token_id": 50283,
  "eos_token_id": null,
  "bos_token_id": null,
  "cls_token_id": 50281,
  "sep_token_id": 50282,
  "attention_bias": false,
  "attention_dropout": 0.0,
  "layer_types": [
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention"
  ],
  "rope_parameters": {
    "full_attention": {
      "rope_theta": 160000.0,
      "rope_type": "default"
    },
    "sliding_attention": {
      "rope_theta": 160000.0,
      "rope_type": "default"
    }
  },
  "local_attention": 128,
  "embedding_dropout": 0.0,
  "mlp_bias": false,
  "mlp_dropout": 0.0,
  "decoder_bias": true,
  "classifier_pooling": "mean",
  "classifier_dropout": 0.0,
  "classifier_bias": false,
  "classifier_activation": "gelu",
  "deterministic_flash_attn": false,
  "sparse_prediction": false,
  "sparse_pred_ignore_index": -100,
  "tie_word_embeddings": true,
  "_name_or_path": "cross-encoder/ettin-reranker-150m-v1",
  "causal_mask": false,
  "global_attn_every_n_layers": 3,
  "gradient_checkpointing": false,
  "is_causal": false,
  "layer_norm_eps": 1e-05,
  "model_type": "modernbert",
  "position_embedding_type": "sans_pos",
  "output_attentions": false,
  "decision": {
    "opt_token": "[OPT]",
    "opt_token_id": 50368,
    "question_types": {
      "noul": 0,
      "choice": 1,
      "score": 2
    },
    "base": "cross-encoder/ettin-reranker-150m-v1",
    "step": 2589,
    "args": {
      "base": "cross-encoder/ettin-reranker-150m-v1",
      "train": "../data/mix400_s3.train.jsonl.gz",
      "dev": "../data/mix400_s3.dev.jsonl.gz",
      "out": "../runs/c150v2s3",
      "epochs": 1.0,
      "lr": 1.5e-05,
      "head_lr": 0.0001,
      "wd": 0.01,
      "warmup": 0.03,
      "max_len": 8192,
      "max_tokens": 8192,
      "max_items": 64,
      "brier": 0.5,
      "eval_every": 100000,
      "save_every": 0,
      "seed": 0,
      "attn": "sdpa",
      "workers": 12,
      "limit": 0,
      "init": "../runs/c150v2s2",
      "teacher": null,
      "kd_alpha": 0.5,
      "kd_tau_multi": 2.0,
      "kd_tau_bin": 1.0,
      "kd_gold_only": "t1/,extra/home,bekko/bpomp",
      "ema": 0.0,
      "grad_accum": 4,
      "grad_ckpt": false,
      "skip_oom": true,
      "save_at": []
    }
  }
}