{
  "format": "troncore/1",
  "encoder_config": {
    "transformers_version": "5.17.0",
    "architectures": [
      "ModernBertForMaskedLM"
    ],
    "output_hidden_states": false,
    "return_dict": true,
    "dtype": "float32",
    "chunk_size_feed_forward": 0,
    "is_encoder_decoder": false,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "problem_type": null,
    "vocab_size": 50368,
    "hidden_size": 1792,
    "intermediate_size": 3840,
    "num_hidden_layers": 28,
    "num_attention_heads": 28,
    "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": 50282,
    "bos_token_id": 50281,
    "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",
      "sliding_attention",
      "sliding_attention",
      "full_attention",
      "sliding_attention",
      "sliding_attention",
      "full_attention"
    ],
    "rope_parameters": {
      "sliding_attention": {
        "rope_type": "default",
        "rope_theta": 160000.0
      },
      "full_attention": {
        "rope_type": "default",
        "rope_theta": 160000.0
      }
    },
    "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": "jhu-clsp/ettin-encoder-1b",
    "global_attn_every_n_layers": 3,
    "gradient_checkpointing": false,
    "layer_norm_eps": 1e-05,
    "model_type": "modernbert",
    "position_embedding_type": "sans_pos",
    "is_causal": false,
    "causal_mask": false,
    "output_attentions": false
  },
  "head": {
    "width": 1024,
    "mixer_layers": 2,
    "mixer_heads": 8,
    "dropout": 0.1,
    "n_types": 3
  },
  "layout": {
    "max_len": 4096,
    "question_max_tokens": 128,
    "option_max_tokens": 48,
    "option_budget": 1536,
    "min_state_tokens": 32
  },
  "calibration": {
    "*": 1.0549,
    "yesno": 1.0678,
    "choice": 1.0075,
    "score": 1.2359,
    "yesno:2": 1.0678,
    "choice:2": 1.0955,
    "choice:3-5": 1.0086,
    "choice:6-10": 1.1039,
    "score:3-5": 1.2381,
    "choice:11-30": 0.8095,
    "score:6-10": 1.5212,
    "choice:31+": 0.9561
  },
  "model_name": "tron-1b",
  "val_macro": 0.8492879196203449,
  "val_ece": 0.02179274528040747,
  "val_accuracy": {
    "unsafe_prompt": 0.857707509881423,
    "commonsense_mc": 0.904,
    "injection": 0.9783080260303688,
    "choice": 0.7426666666666667,
    "routing_binary": 0.8611803823773898,
    "noul": 0.8262857142857143,
    "knowledge_mc": 0.6967213114754098,
    "bench_emotion": 0.9447983014861996,
    "zeroshot": 0.9006666666666666,
    "score": 0.6576819407008087,
    "bench_ag_news": 0.9386331938633193,
    "tool_choice": 0.9793103448275862,
    "intent": 0.976063829787234,
    "unsafe_response": 0.8703071672354948,
    "typed_decisions_synth": 0.834,
    "harm_category": 0.8549019607843137,
    "routing": 0.6683291770573566,
    "preference": 0.788135593220339,
    "typed_decisions": 0.8,
    "bench_banking77": 0.906060606060606
  },
  "trained_steps": 18582,
  "base_model": "jhu-clsp/ettin-encoder-1b"
}