{
 "fixture": "hf-internal-testing/mic-modernbert-slim",
 "key": "d109ab451c9f7a8a6aeb04c254057ae16e8c3460136a84504b08919b51276649",
 "key_fields": {
  "architectures": [
   "ModernBertForMaskedLM"
  ],
  "output_hidden_states": false,
  "return_dict": true,
  "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": 64,
  "intermediate_size": 128,
  "num_hidden_layers": 2,
  "num_attention_heads": 4,
  "hidden_activation": "gelu",
  "max_position_embeddings": 8192,
  "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"
  ],
  "rope_parameters": {
   "sliding_attention": {
    "rope_type": "default",
    "rope_theta": 10000.0
   },
   "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,
  "global_attn_every_n_layers": 3,
  "gradient_checkpointing": false,
  "layer_norm_eps": 1e-05,
  "model_type": "modernbert",
  "position_embedding_type": "absolute",
  "output_attentions": false
 },
 "covers": {
  "answerdotai/ModernBERT-base": "8949b909ec900327062f0ebf497f51aef5e6f0c8"
 },
 "built_from": {
  "repo": "answerdotai/ModernBERT-base",
  "revision": "8949b909ec900327062f0ebf497f51aef5e6f0c8"
 },
 "seed": 17,
 "dtype": "float32",
 "builder": "example/build_fixtures.py",
 "model_class": "ModernBertForMaskedLM",
 "parameters": 3360320,
 "missing_parameters": [],
 "checkpoint_inspection": "parameter metadata",
 "captured": {
  "call": "training step",
  "inputs": [
   "attention_mask",
   "input_ids",
   "labels"
  ]
 },
 "weights": "random",
 "gate": {
  "random": {
   "pass": true,
   "accepted_insensitive": {},
   "threshold": 0.001,
   "deltas": {
    "input_ids:roll_batch": 1.0035998821258545,
    "input_ids:reverse": 0.9506410360336304,
    "attention_mask:all_ones": 0.0012112059630453587
   },
   "weakest": "attention_mask:all_ones",
   "no_perturbation_defined": []
  }
 },
 "numeric_health": {
  "float32": {
   "outputs_finite": true,
   "loss_finite": true,
   "gradients_finite": true,
   "finite": true
  },
  "bfloat16": {
   "outputs_finite": true,
   "loss_finite": true,
   "gradients_finite": true,
   "finite": true
  },
  "float16": {
   "outputs_finite": true,
   "loss_finite": true,
   "gradients_finite": true,
   "finite": true
  }
 },
 "copied_unchanged": [
  "special_tokens_map.json",
  "tokenizer.json",
  "tokenizer_config.json"
 ],
 "environment": {
  "python": "3.10.12",
  "machine": "x86_64",
  "torch": "2.11.0+cu128",
  "transformers": "5.19.0.dev0",
  "tokenizers": "0.23.1"
 },
 "sha256": {
  "config.json": "3b557176a3bdbf59ca67c5a669c764a8f33f2e59b220c7dca5243ccc95c5de11",
  "model.safetensors": "b1df64c09126f5732a80d9ad460cacb17f95c58cc350e35d0fd6aa5ec26ff48b",
  "special_tokens_map.json": "ea97ecdbcc73713039d8d64dbb05e3689495c96657fbd9a18f5bed381be81049",
  "tokenizer.json": "9fd55248d51d33976b324fc11592e28071da7d41e0e9401dfb7082e30574b7b1",
  "tokenizer_config.json": "3cd2017ff46d0a527e5d39cae39272eccfa1f19bb9f89b05d166aab2e38354e2"
 }
}