Namespace(annotations_path='/projects/nlp_mgr-AUDIT/data/dataset/sxk199/mscoco/annotations', features_path='/projects/nlp_mgr-AUDIT/data/dataset/sxk199/mscoco/resnet101_faster_rcnn_genome_imgfeats', dataset='mscoco', masked_splits=None, dataset_splits_dir=None, from_pretrained='/home/sxk199/mnt/volta/cFGANaAtmN', config_file='/home/sxk199/code/multimodal-gender-bias/src/volta/config/original_lxmert.json', resume_file='', output_dir='/home/sxk199/experiments-output/multimodal/pretrain/lxmert_original', logdir='logs/mscoco', timestamp=True, max_seq_length=20, train_batch_size=256, learning_rate=5e-05, grad_acc_steps=1, num_train_epochs=1.0, p_neutral_cap=0.15, warmup_proportion=0.05, warmup_steps=None, last_epoch=None, seed=42, local_rank=-1, num_workers=25, distributed=False, objective=1, adam_epsilon=1e-06, adam_betas=[0.9, 0.999], weight_decay=0.01, clip_grad_norm=1.0, use_wandb=True, wandb_entity='lcp', wandb_run_name='lxmert_original_train')


{
  "add_global_imgfeat": null,
  "attention_probs_dropout_prob": 0.1,
  "bert_layer2attn_sublayer": {
    "0": 0,
    "1": 2,
    "10": 22,
    "11": 25,
    "2": 4,
    "3": 6,
    "4": 8,
    "5": 10,
    "6": 12,
    "7": 14,
    "8": 16,
    "9": 19
  },
  "bert_layer2ff_sublayer": {
    "0": 1,
    "1": 3,
    "10": 23,
    "11": 26,
    "2": 5,
    "3": 7,
    "4": 9,
    "5": 11,
    "6": 13,
    "7": 15,
    "8": 17,
    "9": 20
  },
  "bert_model": "bert-base-uncased",
  "clf_hidden_size": 1536,
  "do_lower_case": true,
  "fixed_embs": null,
  "fixed_layers": [],
  "fusion_act": "relu",
  "fusion_method": "text",
  "has_mapping": "linear",
  "has_mapping_bias": false,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "image_embeddings": "lxmert",
  "image_head_ln": true,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "itm_dim": 2,
  "layer_norm_eps": 1e-12,
  "load_x_model": false,
  "m_encoder": null,
  "m_layer": 0,
  "max_position_embeddings": 512,
  "model": "bert",
  "norm_embeddings": false,
  "num_attention_heads": 12,
  "num_locs": 4,
  "objective": 0,
  "pad_token_id": 0,
  "pooler_size": 768,
  "qa_num_answers": 9500,
  "qa_task_weight": 1,
  "shared_sublayers": [
    18,
    21,
    24,
    27,
    30
  ],
  "single_ln_sublayers": [],
  "sublayer2attn_hidden_size": {},
  "sublayer2intermediate_size": {},
  "sublayer2num_attention_heads": {},
  "sublayer2v_attn_hidden_size": {},
  "sublayer2v_intermediate_size": {},
  "sublayer2v_num_attention_heads": {},
  "t_ff_sublayers": [
    1,
    3,
    5,
    7,
    9,
    11,
    13,
    15,
    17,
    20,
    23,
    26,
    29,
    32
  ],
  "tt_attn_sublayers": [
    0,
    2,
    4,
    6,
    8,
    10,
    12,
    14,
    16,
    19,
    22,
    25,
    28,
    31
  ],
  "tv_attn_sublayers": [
    18,
    21,
    24,
    27,
    30
  ],
  "type_vocab_size": 2,
  "v_attention_probs_dropout_prob": 0.1,
  "v_coordinate_embeddings_dim": null,
  "v_feature_size": 2048,
  "v_ff_sublayers": [
    1,
    3,
    5,
    7,
    9,
    20,
    23,
    26,
    29,
    32
  ],
  "v_hidden_act": "gelu",
  "v_hidden_dropout_prob": 0.1,
  "v_hidden_size": 768,
  "v_initializer_range": 0.02,
  "v_intermediate_size": 3072,
  "v_layers": [],
  "v_num_attention_heads": 12,
  "v_pooler_size": 1024,
  "visual_target_weights": {
    "3": 6.667,
    "4": 6.667,
    "5": 6.667
  },
  "visualization": false,
  "vocab_size": 30522,
  "vt_attn_sublayers": [
    18,
    21,
    24,
    27,
    30
  ],
  "vv_attn_sublayers": [
    0,
    2,
    4,
    6,
    8,
    19,
    22,
    25,
    28,
    31
  ]
}