task1-100k/config.json

{
  "_name_or_path": "/shared_work/markhsp/checkpoints/X-VLA-Pt",
  "action_mode": "auto",
  "architectures": [
    "XVLA"
  ],
  "auto_map": {
    "AutoConfig": "configuration_xvla.XVLAConfig",
    "AutoModel": "modeling_xvla.XVLA"
  },
  "depth": 24,
  "dim_time": 32,
  "florence_config": {
    "_attn_implementation_autoset": true,
    "bos_token_id": 0,
    "eos_token_id": 2,
    "is_encoder_decoder": true,
    "model_type": "florence2",
    "pad_token_id": 1,
    "text_config": {
      "_attn_implementation_autoset": true,
      "_name_or_path": "",
      "activation_dropout": 0.1,
      "activation_function": "gelu",
      "add_bias_logits": false,
      "add_cross_attention": false,
      "add_final_layer_norm": false,
      "architectures": null,
      "attention_dropout": 0.1,
      "bad_words_ids": null,
      "begin_suppress_tokens": null,
      "bos_token_id": 0,
      "chunk_size_feed_forward": 0,
      "classif_dropout": 0.1,
      "classifier_dropout": 0.0,
      "cross_attention_hidden_size": null,
      "d_model": 1024,
      "decoder_attention_heads": 16,
      "decoder_ffn_dim": 4096,
      "decoder_layerdrop": 0.0,
      "decoder_layers": 12,
      "decoder_start_token_id": 2,
      "diversity_penalty": 0.0,
      "do_sample": false,
      "dropout": 0.1,
      "early_stopping": true,
      "encoder_attention_heads": 16,
      "encoder_ffn_dim": 4096,
      "encoder_layerdrop": 0.0,
      "encoder_layers": 12,
      "encoder_no_repeat_ngram_size": 0,
      "eos_token_id": 2,
      "exponential_decay_length_penalty": null,
      "finetuning_task": null,
      "forced_bos_token_id": 0,
      "forced_eos_token_id": 2,
      "gradient_checkpointing": false,
      "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1",
        "2": "LABEL_2"
      },
      "init_std": 0.02,
      "is_decoder": false,
      "is_encoder_decoder": true,
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1,
        "LABEL_2": 2
      },
      "length_penalty": 1.0,
      "max_length": 20,
      "max_position_embeddings": 4096,
      "min_length": 0,
      "model_type": "florence2_language",
      "no_repeat_ngram_size": 3,
      "normalize_before": false,
      "num_beam_groups": 1,
      "num_beams": 3,
      "num_hidden_layers": 12,
      "num_return_sequences": 1,
      "output_attentions": false,
      "output_hidden_states": false,
      "output_scores": false,
      "pad_token_id": 1,
      "prefix": null,
      "problem_type": null,
      "pruned_heads": {},
      "remove_invalid_values": false,
      "repetition_penalty": 1.0,
      "return_dict": true,
      "return_dict_in_generate": false,
      "scale_embedding": false,
      "sep_token_id": null,
      "suppress_tokens": null,
      "task_specific_params": null,
      "temperature": 1.0,
      "tf_legacy_loss": false,
      "tie_encoder_decoder": false,
      "tie_word_embeddings": true,
      "tokenizer_class": null,
      "top_k": 50,
      "top_p": 1.0,
      "torch_dtype": null,
      "torchscript": false,
      "typical_p": 1.0,
      "use_bfloat16": false,
      "use_cache": true,
      "vocab_size": 51289
    },
    "torch_dtype": "float32",
    "vision_config": {
      "_attn_implementation_autoset": false,
      "_name_or_path": "",
      "add_cross_attention": false,
      "architectures": null,
      "bad_words_ids": null,
      "begin_suppress_tokens": null,
      "bos_token_id": null,
      "chunk_size_feed_forward": 0,
      "cross_attention_hidden_size": null,
      "decoder_start_token_id": null,
      "depths": [
        1,
        1,
        9,
        1
      ],
      "dim_embed": [
        256,
        512,
        1024,
        2048
      ],
      "diversity_penalty": 0.0,
      "do_sample": false,
      "drop_path_rate": 0.1,
      "early_stopping": false,
      "enable_checkpoint": false,
      "encoder_no_repeat_ngram_size": 0,
      "eos_token_id": null,
      "exponential_decay_length_penalty": null,
      "finetuning_task": null,
      "forced_bos_token_id": null,
      "forced_eos_token_id": null,
      "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
      },
      "image_feature_source": [
        "spatial_avg_pool",
        "temporal_avg_pool"
      ],
      "image_pos_embed": {
        "max_pos_embeddings": 50,
        "type": "learned_abs_2d"
      },
      "is_decoder": false,
      "is_encoder_decoder": false,
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
      },
      "length_penalty": 1.0,
      "max_length": 20,
      "min_length": 0,
      "model_type": "davit",
      "no_repeat_ngram_size": 0,
      "num_beam_groups": 1,
      "num_beams": 1,
      "num_groups": [
        8,
        16,
        32,
        64
      ],
      "num_heads": [
        8,
        16,
        32,
        64
      ],
      "num_return_sequences": 1,
      "output_attentions": false,
      "output_hidden_states": false,
      "output_scores": false,
      "pad_token_id": null,
      "patch_padding": [
        3,
        1,
        1,
        1
      ],
      "patch_prenorm": [
        false,
        true,
        true,
        true
      ],
      "patch_size": [
        7,
        3,
        3,
        3
      ],
      "patch_stride": [
        4,
        2,
        2,
        2
      ],
      "prefix": null,
      "problem_type": null,
      "projection_dim": 1024,
      "pruned_heads": {},
      "remove_invalid_values": false,
      "repetition_penalty": 1.0,
      "return_dict": true,
      "return_dict_in_generate": false,
      "sep_token_id": null,
      "suppress_tokens": null,
      "task_specific_params": null,
      "temperature": 1.0,
      "tf_legacy_loss": false,
      "tie_encoder_decoder": false,
      "tie_word_embeddings": true,
      "tokenizer_class": null,
      "top_k": 50,
      "top_p": 1.0,
      "torch_dtype": null,
      "torchscript": false,
      "typical_p": 1.0,
      "use_bfloat16": false,
      "visual_temporal_embedding": {
        "max_temporal_embeddings": 100,
        "type": "COSINE"
      },
      "window_size": 12
    }
  },
  "hidden_size": 1024,
  "len_soft_prompts": 32,
  "max_action_dim": 23,
  "max_len_seq": 512,
  "mlp_ratio": 4.0,
  "model_type": "xvla",
  "num_actions": 30,
  "num_domains": 30,
  "num_heads": 16,
  "num_objects": 172,
  "num_skills": 34,
  "num_tasks": 50,
  "object_class_weights": [
    0.4501,
    0.4205,
    0.3228,
    0.3057,
    0.3521,
    7.3765,
    0.2465,
    0.5885,
    0.4622,
    0.3009,
    0.281,
    0.3189,
    0.1221,
    0.4479,
    0.312,
    0.4966,
    0.3079,
    0.2972,
    0.5216,
    0.1139,
    0.2091,
    0.2318,
    0.1754,
    0.2122,
    0.3788,
    0.2522,
    0.2869,
    0.2588,
    0.5604,
    0.2401,
    0.4887,
    0.2479,
    0.4339,
    0.2858,
    0.4104,
    0.1655,
    0.5658,
    0.1832,
    0.4361,
    0.3443,
    0.4715,
    0.4035,
    0.3555,
    0.5542,
    0.5411,
    0.3756,
    0.6119,
    0.3592,
    0.3795,
    0.17,
    0.6553,
    1.8098,
    0.2901,
    0.2248,
    0.2027,
    0.4599,
    0.5536,
    0.508,
    0.2674,
    0.5678,
    0.3297,
    0.4523,
    0.2186,
    0.2029,
    0.4368,
    0.432,
    0.0822,
    0.3718,
    0.6172,
    0.3748,
    0.2685,
    0.2913,
    0.4405,
    0.3391,
    0.3676,
    6.0925,
    2.0803,
    2.153,
    2.2968,
    2.1286,
    12.6916,
    0.5856,
    5.4459,
    2.6565,
    13.1846,
    23.4236,
    0.478,
    0.462,
    0.1174,
    0.4406,
    0.2615,
    0.2668,
    0.2285,
    0.3084,
    0.2523,
    0.3026,
    0.2844,
    0.5057,
    0.343,
    0.2129,
    0.2497,
    0.3409,
    0.3574,
    0.3983,
    0.1783,
    0.2182,
    0.3948,
    3.4148,
    0.3134,
    0.4798,
    0.3458,
    0.2877,
    0.4385,
    0.2716,
    0.4203,
    0.2383,
    0.2431,
    0.2523,
    0.4795,
    0.4197,
    0.2102,
    0.15,
    0.3516,
    1.1414,
    0.1527,
    0.4403,
    0.188,
    0.5024,
    0.367,
    0.4584,
    0.293,
    0.3649,
    23.0659,
    0.1816,
    0.4641,
    0.438,
    0.2461,
    2.3487,
    0.3496,
    0.405,
    0.3314,
    0.489,
    0.4397,
    0.4996,
    0.1229,
    3.6319,
    0.4439,
    0.2366,
    0.2766,
    0.2168,
    0.3219,
    0.3337,
    0.4465,
    0.7571,
    0.257,
    0.3779,
    0.1382,
    0.2154,
    0.2358,
    0.4292,
    0.3343,
    0.3047,
    0.8751,
    0.3987,
    0.146,
    0.2943,
    0.8747,
    0.1515,
    0.1481,
    0.5527,
    2.8632,
    0.3923
  ],
  "object_classifier_weight": 0.1,
  "real_action_dim": 23,
  "skill_class_weights": [
    0.0859,
    0.1021,
    0.2138,
    0.1674,
    0.8973,
    1.059,
    1.6727,
    0.9436,
    0.1984,
    1.1787,
    0.2744,
    0.621,
    0.6252,
    1.8634,
    0.5304,
    0.5203,
    0.8339,
    0.8988,
    1.4175,
    2.2557,
    0.5537,
    1.1661,
    3.0415,
    0.1975,
    0.3228,
    1.2419,
    0.6963,
    1.2705,
    0.4855,
    1.1792,
    1.4312,
    2.6619,
    1.3428,
    2.0497
  ],
  "skill_classifier_weight": 0.1,
  "soft_prompt_length": 32,
  "task_class_weights": [
    2.173,
    1.4191,
    0.8104,
    0.8292,
    0.8919,
    0.9968,
    1.1146,
    0.707,
    1.029,
    0.8308,
    1.2263,
    0.928,
    1.0689,
    0.6989,
    0.8124,
    0.8448,
    0.8113,
    1.0045,
    0.9249,
    0.9423,
    0.8886,
    0.7005,
    1.1158,
    0.6354,
    0.6881,
    0.8477,
    0.5946,
    0.7707,
    0.7753,
    0.6626,
    1.0688,
    1.0711,
    1.0735,
    0.9245,
    2.0169,
    1.6108,
    0.8854,
    1.4132,
    1.2177,
    1.0697,
    1.7812,
    0.8162,
    1.2199,
    0.7956,
    0.9433,
    1.0236,
    1.1092,
    0.8773,
    0.6393,
    0.6997
  ],
  "task_classifier_weight": 0.1,
  "torch_dtype": "float32",
  "transformers_version": "4.49.0",
  "use_hetero_proj": false,
  "use_proprio": true
}