state_dict_report.json

{
  "base_model": "visobert",
  "total_params": 213,
  "expected_heads_present": {
    "cls_decoder.weight": false,
    "cls_decoder.bias": false,
    "cls_dense.weight": false,
    "cls_dense.bias": false,
    "cls_layer_norm.weight": false,
    "cls_layer_norm.bias": false,
    "mask_n_predictor.mask_predictor_dense.weight": true,
    "mask_n_predictor.mask_predictor_dense.bias": true,
    "mask_n_predictor.mask_predictor_proj.weight": true,
    "mask_n_predictor.mask_predictor_proj.bias": true,
    "nsw_detector.dense.weight": true,
    "nsw_detector.dense.bias": true,
    "nsw_detector.predictor.weight": true,
    "nsw_detector.predictor.bias": true
  },
  "alt_common_heads_present": {
    "lm_head.weight": false,
    "lm_head.bias": false,
    "cls.decoder.weight": true,
    "cls.decoder.bias": true,
    "cls.dense.weight": true,
    "cls.dense.bias": true,
    "cls.layer_norm.weight": true,
    "cls.layer_norm.bias": true
  },
  "aux_heads_present": {
    "nsw_detector.": true,
    "mask_n_predictor.": true
  },
  "example_keys": [
    "roberta.embeddings.word_embeddings.weight",
    "roberta.embeddings.position_embeddings.weight",
    "roberta.embeddings.token_type_embeddings.weight",
    "roberta.embeddings.LayerNorm.weight",
    "roberta.embeddings.LayerNorm.bias",
    "roberta.encoder.layer.0.attention.self.query.weight",
    "roberta.encoder.layer.0.attention.self.query.bias",
    "roberta.encoder.layer.0.attention.self.key.weight",
    "roberta.encoder.layer.0.attention.self.key.bias",
    "roberta.encoder.layer.0.attention.self.value.weight",
    "roberta.encoder.layer.0.attention.self.value.bias",
    "roberta.encoder.layer.0.attention.output.dense.weight",
    "roberta.encoder.layer.0.attention.output.dense.bias",
    "roberta.encoder.layer.0.attention.output.LayerNorm.weight",
    "roberta.encoder.layer.0.attention.output.LayerNorm.bias",
    "roberta.encoder.layer.0.intermediate.dense.weight",
    "roberta.encoder.layer.0.intermediate.dense.bias",
    "roberta.encoder.layer.0.output.dense.weight",
    "roberta.encoder.layer.0.output.dense.bias",
    "roberta.encoder.layer.0.output.LayerNorm.weight"
  ]
}