2023-11-02 17:43:26.795 | INFO     | mmgpt.model.builder:build_model_tokenizer:85 - LlamaTokenizer(name_or_path='/data/hypertext/yuangpeng/huggingface_cache/models--lmsys--vicuna-7b-v15', vocab_size=32000, model_max_length=2048, is_fast=False, padding_side='right', truncation_side='right', special_tokens={'bos_token': AddedToken("<s>", rstrip=False, lstrip=False, single_word=False, normalized=False), 'eos_token': AddedToken("</s>", rstrip=False, lstrip=False, single_word=False, normalized=False), 'unk_token': AddedToken("<unk>", rstrip=False, lstrip=False, single_word=False, normalized=False), 'pad_token': '<unk>'}, clean_up_tokenization_spaces=False)
2023-11-02 17:43:30.424 | INFO     | mmgpt.model.mmgpt.base_mmgpt:build_vision_tokenizer:52 - CLIPImageProcessor {
  "crop_size": {
    "height": 448,
    "width": 448
  },
  "do_center_crop": true,
  "do_convert_rgb": true,
  "do_normalize": true,
  "do_rescale": true,
  "do_resize": true,
  "feature_extractor_type": "CLIPFeatureExtractor",
  "image_mean": [
    0.48145466,
    0.4578275,
    0.40821073
  ],
  "image_processor_type": "CLIPImageProcessor",
  "image_std": [
    0.26862954,
    0.26130258,
    0.27577711
  ],
  "resample": 3,
  "rescale_factor": 0.00392156862745098,
  "size": {
    "shortest_edge": 448
  }
}

2023-11-02 17:43:37.183 | INFO     | mmgpt.model.mmgpt.base_mmgpt:build_vision_tokenizer:64 - 2 new tokens are added to be trained.
2023-11-02 17:43:37.310 | INFO     | mmgpt.model.builder:build_model_tokenizer:148 - MMGPTLlamaForCausalLM(
  (model): MMGPTLlamaModel(
    (embed_tokens): Embedding(32003, 4096)
    (layers): ModuleList(
      (0-31): 32 x LlamaDecoderLayer(
        (self_attn): LlamaAttention(
          (q_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (k_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (v_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (o_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (rotary_emb): LlamaRotaryEmbedding()
        )
        (mlp): LlamaMLP(
          (gate_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (up_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (down_proj): Linear(in_features=11008, out_features=4096, bias=False)
          (act_fn): SiLUActivation()
        )
        (input_layernorm): LlamaRMSNorm()
        (post_attention_layernorm): LlamaRMSNorm()
      )
    )
    (norm): LlamaRMSNorm()
    (vision_tower): CLIPVisionTower(
      (vision_tower): CLIPVisionModel(
        (vision_model): CLIPVisionTransformer(
          (embeddings): CLIPVisionEmbeddings(
            (patch_embedding): Conv2d(3, 1024, kernel_size=(14, 14), stride=(14, 14), bias=False)
            (position_embedding): Embedding(1025, 1024)
          )
          (pre_layrnorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
          (encoder): CLIPEncoder(
            (layers): ModuleList(
              (0-23): 24 x CLIPEncoderLayer(
                (self_attn): CLIPAttention(
                  (k_proj): Linear(in_features=1024, out_features=1024, bias=True)
                  (v_proj): Linear(in_features=1024, out_features=1024, bias=True)
                  (q_proj): Linear(in_features=1024, out_features=1024, bias=True)
                  (out_proj): Linear(in_features=1024, out_features=1024, bias=True)
                )
                (layer_norm1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
                (mlp): CLIPMLP(
                  (activation_fn): QuickGELUActivation()
                  (fc1): Linear(in_features=1024, out_features=4096, bias=True)
                  (fc2): Linear(in_features=4096, out_features=1024, bias=True)
                )
                (layer_norm2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
              )
            )
          )
          (post_layernorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
        )
      )
    )
    (projector): ConvProjector(
      (projector): Conv2d(1024, 4096, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
    )
  )
  (lm_head): Linear(in_features=4096, out_features=32003, bias=False)
)
2023-11-02 17:43:55.005 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.embed_tokens.weight
2023-11-02 17:43:55.005 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.0.self_attn.q_proj.weight
2023-11-02 17:43:55.006 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.0.self_attn.k_proj.weight
2023-11-02 17:43:55.006 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.0.self_attn.v_proj.weight
2023-11-02 17:43:55.006 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.0.self_attn.o_proj.weight
2023-11-02 17:43:55.006 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.0.mlp.gate_proj.weight
2023-11-02 17:43:55.007 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.0.mlp.up_proj.weight
2023-11-02 17:43:55.007 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.0.mlp.down_proj.weight
2023-11-02 17:43:55.007 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.0.input_layernorm.weight
2023-11-02 17:43:55.007 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.0.post_attention_layernorm.weight
2023-11-02 17:43:55.007 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.1.self_attn.q_proj.weight
2023-11-02 17:43:55.008 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.1.self_attn.k_proj.weight
2023-11-02 17:43:55.008 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.1.self_attn.v_proj.weight
2023-11-02 17:43:55.008 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.1.self_attn.o_proj.weight
2023-11-02 17:43:55.008 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.1.mlp.gate_proj.weight
2023-11-02 17:43:55.008 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.1.mlp.up_proj.weight
2023-11-02 17:43:55.009 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.1.mlp.down_proj.weight
2023-11-02 17:43:55.009 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.1.input_layernorm.weight
2023-11-02 17:43:55.009 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.1.post_attention_layernorm.weight
2023-11-02 17:43:55.009 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.2.self_attn.q_proj.weight
2023-11-02 17:43:55.009 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.2.self_attn.k_proj.weight
2023-11-02 17:43:55.010 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.2.self_attn.v_proj.weight
2023-11-02 17:43:55.010 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.2.self_attn.o_proj.weight
2023-11-02 17:43:55.010 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.2.mlp.gate_proj.weight
2023-11-02 17:43:55.010 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.2.mlp.up_proj.weight
2023-11-02 17:43:55.010 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.2.mlp.down_proj.weight
2023-11-02 17:43:55.010 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.2.input_layernorm.weight
2023-11-02 17:43:55.011 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.2.post_attention_layernorm.weight
2023-11-02 17:43:55.011 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.3.self_attn.q_proj.weight
2023-11-02 17:43:55.011 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.3.self_attn.k_proj.weight
2023-11-02 17:43:55.011 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.3.self_attn.v_proj.weight
2023-11-02 17:43:55.011 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.3.self_attn.o_proj.weight
2023-11-02 17:43:55.012 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.3.mlp.gate_proj.weight
2023-11-02 17:43:55.012 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.3.mlp.up_proj.weight
2023-11-02 17:43:55.012 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.3.mlp.down_proj.weight
2023-11-02 17:43:55.012 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.3.input_layernorm.weight
2023-11-02 17:43:55.012 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.3.post_attention_layernorm.weight
2023-11-02 17:43:55.013 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.4.self_attn.q_proj.weight
2023-11-02 17:43:55.013 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.4.self_attn.k_proj.weight
2023-11-02 17:43:55.013 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.4.self_attn.v_proj.weight
2023-11-02 17:43:55.013 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.4.self_attn.o_proj.weight
2023-11-02 17:43:55.013 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.4.mlp.gate_proj.weight
2023-11-02 17:43:55.013 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.4.mlp.up_proj.weight
2023-11-02 17:43:55.014 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.4.mlp.down_proj.weight
2023-11-02 17:43:55.014 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.4.input_layernorm.weight
2023-11-02 17:43:55.014 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.4.post_attention_layernorm.weight
2023-11-02 17:43:55.014 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.5.self_attn.q_proj.weight
2023-11-02 17:43:55.014 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.5.self_attn.k_proj.weight
2023-11-02 17:43:55.015 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.5.self_attn.v_proj.weight
2023-11-02 17:43:55.015 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.5.self_attn.o_proj.weight
2023-11-02 17:43:55.015 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.5.mlp.gate_proj.weight
2023-11-02 17:43:55.015 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.5.mlp.up_proj.weight
2023-11-02 17:43:55.015 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.5.mlp.down_proj.weight
2023-11-02 17:43:55.015 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.5.input_layernorm.weight
2023-11-02 17:43:55.016 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.5.post_attention_layernorm.weight
2023-11-02 17:43:55.016 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.6.self_attn.q_proj.weight
2023-11-02 17:43:55.016 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.6.self_attn.k_proj.weight
2023-11-02 17:43:55.016 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.6.self_attn.v_proj.weight
2023-11-02 17:43:55.016 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.6.self_attn.o_proj.weight
2023-11-02 17:43:55.017 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.6.mlp.gate_proj.weight
2023-11-02 17:43:55.017 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.6.mlp.up_proj.weight
2023-11-02 17:43:55.017 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.6.mlp.down_proj.weight
2023-11-02 17:43:55.017 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.6.input_layernorm.weight
2023-11-02 17:43:55.017 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.6.post_attention_layernorm.weight
2023-11-02 17:43:55.018 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.7.self_attn.q_proj.weight
2023-11-02 17:43:55.018 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.7.self_attn.k_proj.weight
2023-11-02 17:43:55.018 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.7.self_attn.v_proj.weight
2023-11-02 17:43:55.018 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.7.self_attn.o_proj.weight
2023-11-02 17:43:55.018 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.7.mlp.gate_proj.weight
2023-11-02 17:43:55.018 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.7.mlp.up_proj.weight
2023-11-02 17:43:55.019 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.7.mlp.down_proj.weight
2023-11-02 17:43:55.019 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.7.input_layernorm.weight
2023-11-02 17:43:55.019 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.7.post_attention_layernorm.weight
2023-11-02 17:43:55.019 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.8.self_attn.q_proj.weight
2023-11-02 17:43:55.019 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.8.self_attn.k_proj.weight
2023-11-02 17:43:55.020 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.8.self_attn.v_proj.weight
2023-11-02 17:43:55.020 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.8.self_attn.o_proj.weight
2023-11-02 17:43:55.020 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.8.mlp.gate_proj.weight
2023-11-02 17:43:55.020 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.8.mlp.up_proj.weight
2023-11-02 17:43:55.020 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.8.mlp.down_proj.weight
2023-11-02 17:43:55.020 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.8.input_layernorm.weight
2023-11-02 17:43:55.021 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.8.post_attention_layernorm.weight
2023-11-02 17:43:55.021 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.9.self_attn.q_proj.weight
2023-11-02 17:43:55.021 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.9.self_attn.k_proj.weight
2023-11-02 17:43:55.021 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.9.self_attn.v_proj.weight
2023-11-02 17:43:55.021 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.9.self_attn.o_proj.weight
2023-11-02 17:43:55.022 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.9.mlp.gate_proj.weight
2023-11-02 17:43:55.022 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.9.mlp.up_proj.weight
2023-11-02 17:43:55.022 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.9.mlp.down_proj.weight
2023-11-02 17:43:55.022 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.9.input_layernorm.weight
2023-11-02 17:43:55.022 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.9.post_attention_layernorm.weight
2023-11-02 17:43:55.022 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.10.self_attn.q_proj.weight
2023-11-02 17:43:55.023 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.10.self_attn.k_proj.weight
2023-11-02 17:43:55.023 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.10.self_attn.v_proj.weight
2023-11-02 17:43:55.023 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.10.self_attn.o_proj.weight
2023-11-02 17:43:55.023 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.10.mlp.gate_proj.weight
2023-11-02 17:43:55.023 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.10.mlp.up_proj.weight
2023-11-02 17:43:55.024 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.10.mlp.down_proj.weight
2023-11-02 17:43:55.024 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.10.input_layernorm.weight
2023-11-02 17:43:55.024 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.10.post_attention_layernorm.weight
2023-11-02 17:43:55.024 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.11.self_attn.q_proj.weight
2023-11-02 17:43:55.024 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.11.self_attn.k_proj.weight
2023-11-02 17:43:55.024 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.11.self_attn.v_proj.weight
2023-11-02 17:43:55.025 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.11.self_attn.o_proj.weight
2023-11-02 17:43:55.025 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.11.mlp.gate_proj.weight
2023-11-02 17:43:55.025 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.11.mlp.up_proj.weight
2023-11-02 17:43:55.025 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.11.mlp.down_proj.weight
2023-11-02 17:43:55.025 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.11.input_layernorm.weight
2023-11-02 17:43:55.026 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.11.post_attention_layernorm.weight
2023-11-02 17:43:55.026 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.12.self_attn.q_proj.weight
2023-11-02 17:43:55.026 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.12.self_attn.k_proj.weight
2023-11-02 17:43:55.026 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.12.self_attn.v_proj.weight
2023-11-02 17:43:55.026 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.12.self_attn.o_proj.weight
2023-11-02 17:43:55.026 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.12.mlp.gate_proj.weight
2023-11-02 17:43:55.027 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.12.mlp.up_proj.weight
2023-11-02 17:43:55.027 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.12.mlp.down_proj.weight
2023-11-02 17:43:55.027 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.12.input_layernorm.weight
2023-11-02 17:43:55.027 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.12.post_attention_layernorm.weight
2023-11-02 17:43:55.027 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.13.self_attn.q_proj.weight
2023-11-02 17:43:55.028 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.13.self_attn.k_proj.weight
2023-11-02 17:43:55.028 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.13.self_attn.v_proj.weight
2023-11-02 17:43:55.028 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.13.self_attn.o_proj.weight
2023-11-02 17:43:55.028 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.13.mlp.gate_proj.weight
2023-11-02 17:43:55.028 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.13.mlp.up_proj.weight
2023-11-02 17:43:55.028 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.13.mlp.down_proj.weight
2023-11-02 17:43:55.029 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.13.input_layernorm.weight
2023-11-02 17:43:55.029 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.13.post_attention_layernorm.weight
2023-11-02 17:43:55.029 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.14.self_attn.q_proj.weight
2023-11-02 17:43:55.029 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.14.self_attn.k_proj.weight
2023-11-02 17:43:55.029 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.14.self_attn.v_proj.weight
2023-11-02 17:43:55.030 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.14.self_attn.o_proj.weight
2023-11-02 17:43:55.030 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.14.mlp.gate_proj.weight
2023-11-02 17:43:55.030 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.14.mlp.up_proj.weight
2023-11-02 17:43:55.030 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.14.mlp.down_proj.weight
2023-11-02 17:43:55.030 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.14.input_layernorm.weight
2023-11-02 17:43:55.030 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.14.post_attention_layernorm.weight
2023-11-02 17:43:55.031 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.15.self_attn.q_proj.weight
2023-11-02 17:43:55.031 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.15.self_attn.k_proj.weight
2023-11-02 17:43:55.031 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.15.self_attn.v_proj.weight
2023-11-02 17:43:55.031 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.15.self_attn.o_proj.weight
2023-11-02 17:43:55.031 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.15.mlp.gate_proj.weight
2023-11-02 17:43:55.032 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.15.mlp.up_proj.weight
2023-11-02 17:43:55.032 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.15.mlp.down_proj.weight
2023-11-02 17:43:55.032 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.15.input_layernorm.weight
2023-11-02 17:43:55.032 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.15.post_attention_layernorm.weight
2023-11-02 17:43:55.032 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.16.self_attn.q_proj.weight
2023-11-02 17:43:55.032 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.16.self_attn.k_proj.weight
2023-11-02 17:43:55.033 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.16.self_attn.v_proj.weight
2023-11-02 17:43:55.033 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.16.self_attn.o_proj.weight
2023-11-02 17:43:55.033 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.16.mlp.gate_proj.weight
2023-11-02 17:43:55.033 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.16.mlp.up_proj.weight
2023-11-02 17:43:55.033 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.16.mlp.down_proj.weight
2023-11-02 17:43:55.034 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.16.input_layernorm.weight
2023-11-02 17:43:55.034 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.16.post_attention_layernorm.weight
2023-11-02 17:43:55.034 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.17.self_attn.q_proj.weight
2023-11-02 17:43:55.034 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.17.self_attn.k_proj.weight
2023-11-02 17:43:55.034 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.17.self_attn.v_proj.weight
2023-11-02 17:43:55.034 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.17.self_attn.o_proj.weight
2023-11-02 17:43:55.035 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.17.mlp.gate_proj.weight
2023-11-02 17:43:55.035 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.17.mlp.up_proj.weight
2023-11-02 17:43:55.035 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.17.mlp.down_proj.weight
2023-11-02 17:43:55.035 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.17.input_layernorm.weight
2023-11-02 17:43:55.035 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.17.post_attention_layernorm.weight
2023-11-02 17:43:55.036 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.18.self_attn.q_proj.weight
2023-11-02 17:43:55.036 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.18.self_attn.k_proj.weight
2023-11-02 17:43:55.036 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.18.self_attn.v_proj.weight
2023-11-02 17:43:55.036 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.18.self_attn.o_proj.weight
2023-11-02 17:43:55.036 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.18.mlp.gate_proj.weight
2023-11-02 17:43:55.036 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.18.mlp.up_proj.weight
2023-11-02 17:43:55.037 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.18.mlp.down_proj.weight
2023-11-02 17:43:55.037 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.18.input_layernorm.weight
2023-11-02 17:43:55.037 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.18.post_attention_layernorm.weight
2023-11-02 17:43:55.037 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.19.self_attn.q_proj.weight
2023-11-02 17:43:55.037 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.19.self_attn.k_proj.weight
2023-11-02 17:43:55.038 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.19.self_attn.v_proj.weight
2023-11-02 17:43:55.038 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.19.self_attn.o_proj.weight
2023-11-02 17:43:55.038 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.19.mlp.gate_proj.weight
2023-11-02 17:43:55.038 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.19.mlp.up_proj.weight
2023-11-02 17:43:55.038 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.19.mlp.down_proj.weight
2023-11-02 17:43:55.038 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.19.input_layernorm.weight
2023-11-02 17:43:55.039 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.19.post_attention_layernorm.weight
2023-11-02 17:43:55.039 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.20.self_attn.q_proj.weight
2023-11-02 17:43:55.039 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.20.self_attn.k_proj.weight
2023-11-02 17:43:55.039 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.20.self_attn.v_proj.weight
2023-11-02 17:43:55.039 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.20.self_attn.o_proj.weight
2023-11-02 17:43:55.040 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.20.mlp.gate_proj.weight
2023-11-02 17:43:55.040 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.20.mlp.up_proj.weight
2023-11-02 17:43:55.040 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.20.mlp.down_proj.weight
2023-11-02 17:43:55.040 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.20.input_layernorm.weight
2023-11-02 17:43:55.040 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.20.post_attention_layernorm.weight
2023-11-02 17:43:55.041 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.21.self_attn.q_proj.weight
2023-11-02 17:43:55.041 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.21.self_attn.k_proj.weight
2023-11-02 17:43:55.041 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.21.self_attn.v_proj.weight
2023-11-02 17:43:55.041 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.21.self_attn.o_proj.weight
2023-11-02 17:43:55.041 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.21.mlp.gate_proj.weight
2023-11-02 17:43:55.041 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.21.mlp.up_proj.weight
2023-11-02 17:43:55.042 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.21.mlp.down_proj.weight
2023-11-02 17:43:55.042 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.21.input_layernorm.weight
2023-11-02 17:43:55.042 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.21.post_attention_layernorm.weight
2023-11-02 17:43:55.042 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.22.self_attn.q_proj.weight
2023-11-02 17:43:55.042 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.22.self_attn.k_proj.weight
2023-11-02 17:43:55.043 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.22.self_attn.v_proj.weight
2023-11-02 17:43:55.043 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.22.self_attn.o_proj.weight
2023-11-02 17:43:55.043 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.22.mlp.gate_proj.weight
2023-11-02 17:43:55.043 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.22.mlp.up_proj.weight
2023-11-02 17:43:55.043 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.22.mlp.down_proj.weight
2023-11-02 17:43:55.043 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.22.input_layernorm.weight
2023-11-02 17:43:55.044 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.22.post_attention_layernorm.weight
2023-11-02 17:43:55.044 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.23.self_attn.q_proj.weight
2023-11-02 17:43:55.044 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.23.self_attn.k_proj.weight
2023-11-02 17:43:55.044 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.23.self_attn.v_proj.weight
2023-11-02 17:43:55.044 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.23.self_attn.o_proj.weight
2023-11-02 17:43:55.045 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.23.mlp.gate_proj.weight
2023-11-02 17:43:55.045 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.23.mlp.up_proj.weight
2023-11-02 17:43:55.045 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.23.mlp.down_proj.weight
2023-11-02 17:43:55.045 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.23.input_layernorm.weight
2023-11-02 17:43:55.045 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.23.post_attention_layernorm.weight
2023-11-02 17:43:55.045 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.24.self_attn.q_proj.weight
2023-11-02 17:43:55.046 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.24.self_attn.k_proj.weight
2023-11-02 17:43:55.046 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.24.self_attn.v_proj.weight
2023-11-02 17:43:55.046 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.24.self_attn.o_proj.weight
2023-11-02 17:43:55.046 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.24.mlp.gate_proj.weight
2023-11-02 17:43:55.046 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.24.mlp.up_proj.weight
2023-11-02 17:43:55.047 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.24.mlp.down_proj.weight
2023-11-02 17:43:55.047 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.24.input_layernorm.weight
2023-11-02 17:43:55.047 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.24.post_attention_layernorm.weight
2023-11-02 17:43:55.047 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.25.self_attn.q_proj.weight
2023-11-02 17:43:55.047 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.25.self_attn.k_proj.weight
2023-11-02 17:43:55.047 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.25.self_attn.v_proj.weight
2023-11-02 17:43:55.048 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.25.self_attn.o_proj.weight
2023-11-02 17:43:55.048 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.25.mlp.gate_proj.weight
2023-11-02 17:43:55.048 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.25.mlp.up_proj.weight
2023-11-02 17:43:55.048 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.25.mlp.down_proj.weight
2023-11-02 17:43:55.048 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.25.input_layernorm.weight
2023-11-02 17:43:55.049 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.25.post_attention_layernorm.weight
2023-11-02 17:43:55.049 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.26.self_attn.q_proj.weight
2023-11-02 17:43:55.049 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.26.self_attn.k_proj.weight
2023-11-02 17:43:55.049 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.26.self_attn.v_proj.weight
2023-11-02 17:43:55.049 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.26.self_attn.o_proj.weight
2023-11-02 17:43:55.049 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.26.mlp.gate_proj.weight
2023-11-02 17:43:55.050 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.26.mlp.up_proj.weight
2023-11-02 17:43:55.050 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.26.mlp.down_proj.weight
2023-11-02 17:43:55.050 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.26.input_layernorm.weight
2023-11-02 17:43:55.050 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.26.post_attention_layernorm.weight
2023-11-02 17:43:55.050 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.27.self_attn.q_proj.weight
2023-11-02 17:43:55.051 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.27.self_attn.k_proj.weight
2023-11-02 17:43:55.051 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.27.self_attn.v_proj.weight
2023-11-02 17:43:55.051 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.27.self_attn.o_proj.weight
2023-11-02 17:43:55.051 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.27.mlp.gate_proj.weight
2023-11-02 17:43:55.051 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.27.mlp.up_proj.weight
2023-11-02 17:43:55.051 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.27.mlp.down_proj.weight
2023-11-02 17:43:55.052 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.27.input_layernorm.weight
2023-11-02 17:43:55.052 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.27.post_attention_layernorm.weight
2023-11-02 17:43:55.052 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.28.self_attn.q_proj.weight
2023-11-02 17:43:55.052 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.28.self_attn.k_proj.weight
2023-11-02 17:43:55.052 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.28.self_attn.v_proj.weight
2023-11-02 17:43:55.053 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.28.self_attn.o_proj.weight
2023-11-02 17:43:55.053 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.28.mlp.gate_proj.weight
2023-11-02 17:43:55.053 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.28.mlp.up_proj.weight
2023-11-02 17:43:55.053 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.28.mlp.down_proj.weight
2023-11-02 17:43:55.053 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.28.input_layernorm.weight
2023-11-02 17:43:55.053 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.28.post_attention_layernorm.weight
2023-11-02 17:43:55.054 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.29.self_attn.q_proj.weight
2023-11-02 17:43:55.054 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.29.self_attn.k_proj.weight
2023-11-02 17:43:55.054 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.29.self_attn.v_proj.weight
2023-11-02 17:43:55.054 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.29.self_attn.o_proj.weight
2023-11-02 17:43:55.054 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.29.mlp.gate_proj.weight
2023-11-02 17:43:55.054 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.29.mlp.up_proj.weight
2023-11-02 17:43:55.055 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.29.mlp.down_proj.weight
2023-11-02 17:43:55.055 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.29.input_layernorm.weight
2023-11-02 17:43:55.055 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.29.post_attention_layernorm.weight
2023-11-02 17:43:55.055 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.30.self_attn.q_proj.weight
2023-11-02 17:43:55.055 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.30.self_attn.k_proj.weight
2023-11-02 17:43:55.056 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.30.self_attn.v_proj.weight
2023-11-02 17:43:55.056 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.30.self_attn.o_proj.weight
2023-11-02 17:43:55.056 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.30.mlp.gate_proj.weight
2023-11-02 17:43:55.056 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.30.mlp.up_proj.weight
2023-11-02 17:43:55.056 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.30.mlp.down_proj.weight
2023-11-02 17:43:55.056 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.30.input_layernorm.weight
2023-11-02 17:43:55.057 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.30.post_attention_layernorm.weight
2023-11-02 17:43:55.057 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.31.self_attn.q_proj.weight
2023-11-02 17:43:55.057 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.31.self_attn.k_proj.weight
2023-11-02 17:43:55.057 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.31.self_attn.v_proj.weight
2023-11-02 17:43:55.057 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.31.self_attn.o_proj.weight
2023-11-02 17:43:55.058 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.31.mlp.gate_proj.weight
2023-11-02 17:43:55.058 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.31.mlp.up_proj.weight
2023-11-02 17:43:55.058 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.31.mlp.down_proj.weight
2023-11-02 17:43:55.058 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.31.input_layernorm.weight
2023-11-02 17:43:55.058 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.layers.31.post_attention_layernorm.weight
2023-11-02 17:43:55.058 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.norm.weight
2023-11-02 17:43:55.059 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.embeddings.class_embedding
2023-11-02 17:43:55.059 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight
2023-11-02 17:43:55.059 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight
2023-11-02 17:43:55.059 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight
2023-11-02 17:43:55.059 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias
2023-11-02 17:43:55.060 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight
2023-11-02 17:43:55.060 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias
2023-11-02 17:43:55.060 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight
2023-11-02 17:43:55.060 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias
2023-11-02 17:43:55.060 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight
2023-11-02 17:43:55.060 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias
2023-11-02 17:43:55.061 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight
2023-11-02 17:43:55.061 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias
2023-11-02 17:43:55.061 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight
2023-11-02 17:43:55.061 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias
2023-11-02 17:43:55.061 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight
2023-11-02 17:43:55.062 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias
2023-11-02 17:43:55.062 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight
2023-11-02 17:43:55.062 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias
2023-11-02 17:43:55.062 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight
2023-11-02 17:43:55.062 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias
2023-11-02 17:43:55.062 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight
2023-11-02 17:43:55.063 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias
2023-11-02 17:43:55.063 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight
2023-11-02 17:43:55.063 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias
2023-11-02 17:43:55.063 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight
2023-11-02 17:43:55.063 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias
2023-11-02 17:43:55.063 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight
2023-11-02 17:43:55.064 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias
2023-11-02 17:43:55.064 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight
2023-11-02 17:43:55.064 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias
2023-11-02 17:43:55.064 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight
2023-11-02 17:43:55.064 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias
2023-11-02 17:43:55.065 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight
2023-11-02 17:43:55.065 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias
2023-11-02 17:43:55.065 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight
2023-11-02 17:43:55.065 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias
2023-11-02 17:43:55.065 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight
2023-11-02 17:43:55.065 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias
2023-11-02 17:43:55.066 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight
2023-11-02 17:43:55.066 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias
2023-11-02 17:43:55.066 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight
2023-11-02 17:43:55.066 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias
2023-11-02 17:43:55.066 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight
2023-11-02 17:43:55.066 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias
2023-11-02 17:43:55.067 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight
2023-11-02 17:43:55.067 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias
2023-11-02 17:43:55.067 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight
2023-11-02 17:43:55.067 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias
2023-11-02 17:43:55.067 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight
2023-11-02 17:43:55.068 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias
2023-11-02 17:43:55.068 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight
2023-11-02 17:43:55.068 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias
2023-11-02 17:43:55.068 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight
2023-11-02 17:43:55.068 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias
2023-11-02 17:43:55.068 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight
2023-11-02 17:43:55.069 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias
2023-11-02 17:43:55.069 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight
2023-11-02 17:43:55.069 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias
2023-11-02 17:43:55.069 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight
2023-11-02 17:43:55.069 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias
2023-11-02 17:43:55.069 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight
2023-11-02 17:43:55.070 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias
2023-11-02 17:43:55.070 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight
2023-11-02 17:43:55.070 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias
2023-11-02 17:43:55.070 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight
2023-11-02 17:43:55.070 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias
2023-11-02 17:43:55.071 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight
2023-11-02 17:43:55.071 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias
2023-11-02 17:43:55.071 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight
2023-11-02 17:43:55.071 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias
2023-11-02 17:43:55.071 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight
2023-11-02 17:43:55.071 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias
2023-11-02 17:43:55.072 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight
2023-11-02 17:43:55.072 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias
2023-11-02 17:43:55.072 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight
2023-11-02 17:43:55.072 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias
2023-11-02 17:43:55.072 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight
2023-11-02 17:43:55.072 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias
2023-11-02 17:43:55.073 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight
2023-11-02 17:43:55.073 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias
2023-11-02 17:43:55.073 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight
2023-11-02 17:43:55.073 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias
2023-11-02 17:43:55.073 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight
2023-11-02 17:43:55.074 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias
2023-11-02 17:43:55.074 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight
2023-11-02 17:43:55.074 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias
2023-11-02 17:43:55.074 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight
2023-11-02 17:43:55.074 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias
2023-11-02 17:43:55.074 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight
2023-11-02 17:43:55.075 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias
2023-11-02 17:43:55.075 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight
2023-11-02 17:43:55.075 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias
2023-11-02 17:43:55.075 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight
2023-11-02 17:43:55.075 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias
2023-11-02 17:43:55.075 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight
2023-11-02 17:43:55.076 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias
2023-11-02 17:43:55.076 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight
2023-11-02 17:43:55.076 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias
2023-11-02 17:43:55.076 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight
2023-11-02 17:43:55.076 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias
2023-11-02 17:43:55.077 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight
2023-11-02 17:43:55.077 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias
2023-11-02 17:43:55.077 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight
2023-11-02 17:43:55.077 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias
2023-11-02 17:43:55.077 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight
2023-11-02 17:43:55.077 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias
2023-11-02 17:43:55.078 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight
2023-11-02 17:43:55.078 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias
2023-11-02 17:43:55.078 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight
2023-11-02 17:43:55.078 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias
2023-11-02 17:43:55.078 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight
2023-11-02 17:43:55.078 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias
2023-11-02 17:43:55.079 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight
2023-11-02 17:43:55.079 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias
2023-11-02 17:43:55.079 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight
2023-11-02 17:43:55.079 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias
2023-11-02 17:43:55.079 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight
2023-11-02 17:43:55.080 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias
2023-11-02 17:43:55.080 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight
2023-11-02 17:43:55.080 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias
2023-11-02 17:43:55.080 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight
2023-11-02 17:43:55.080 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias
2023-11-02 17:43:55.080 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight
2023-11-02 17:43:55.081 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias
2023-11-02 17:43:55.081 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight
2023-11-02 17:43:55.081 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias
2023-11-02 17:43:55.081 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight
2023-11-02 17:43:55.081 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias
2023-11-02 17:43:55.082 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight
2023-11-02 17:43:55.082 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias
2023-11-02 17:43:55.082 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight
2023-11-02 17:43:55.082 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias
2023-11-02 17:43:55.082 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight
2023-11-02 17:43:55.082 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias
2023-11-02 17:43:55.083 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight
2023-11-02 17:43:55.083 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias
2023-11-02 17:43:55.083 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight
2023-11-02 17:43:55.083 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias
2023-11-02 17:43:55.083 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight
2023-11-02 17:43:55.083 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias
2023-11-02 17:43:55.084 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight
2023-11-02 17:43:55.084 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias
2023-11-02 17:43:55.084 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight
2023-11-02 17:43:55.084 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias
2023-11-02 17:43:55.084 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight
2023-11-02 17:43:55.085 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias
2023-11-02 17:43:55.085 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight
2023-11-02 17:43:55.085 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias
2023-11-02 17:43:55.085 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight
2023-11-02 17:43:55.085 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias
2023-11-02 17:43:55.085 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight
2023-11-02 17:43:55.086 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias
2023-11-02 17:43:55.086 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight
2023-11-02 17:43:55.086 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias
2023-11-02 17:43:55.086 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight
2023-11-02 17:43:55.086 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias
2023-11-02 17:43:55.086 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight
2023-11-02 17:43:55.087 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias
2023-11-02 17:43:55.087 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight
2023-11-02 17:43:55.087 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias
2023-11-02 17:43:55.087 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight
2023-11-02 17:43:55.087 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias
2023-11-02 17:43:55.088 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight
2023-11-02 17:43:55.088 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias
2023-11-02 17:43:55.088 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight
2023-11-02 17:43:55.088 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias
2023-11-02 17:43:55.088 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight
2023-11-02 17:43:55.088 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias
2023-11-02 17:43:55.089 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight
2023-11-02 17:43:55.089 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias
2023-11-02 17:43:55.089 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight
2023-11-02 17:43:55.089 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias
2023-11-02 17:43:55.089 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight
2023-11-02 17:43:55.089 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias
2023-11-02 17:43:55.090 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight
2023-11-02 17:43:55.090 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias
2023-11-02 17:43:55.090 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight
2023-11-02 17:43:55.090 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias
2023-11-02 17:43:55.090 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight
2023-11-02 17:43:55.091 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias
2023-11-02 17:43:55.091 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight
2023-11-02 17:43:55.091 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias
2023-11-02 17:43:55.091 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight
2023-11-02 17:43:55.091 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias
2023-11-02 17:43:55.091 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight
2023-11-02 17:43:55.092 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias
2023-11-02 17:43:55.092 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight
2023-11-02 17:43:55.092 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias
2023-11-02 17:43:55.092 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight
2023-11-02 17:43:55.092 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias
2023-11-02 17:43:55.093 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight
2023-11-02 17:43:55.093 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias
2023-11-02 17:43:55.093 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight
2023-11-02 17:43:55.093 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias
2023-11-02 17:43:55.093 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight
2023-11-02 17:43:55.093 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias
2023-11-02 17:43:55.094 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight
2023-11-02 17:43:55.094 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias
2023-11-02 17:43:55.094 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight
2023-11-02 17:43:55.094 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias
2023-11-02 17:43:55.094 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight
2023-11-02 17:43:55.094 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias
2023-11-02 17:43:55.095 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight
2023-11-02 17:43:55.095 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias
2023-11-02 17:43:55.095 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight
2023-11-02 17:43:55.095 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias
2023-11-02 17:43:55.095 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight
2023-11-02 17:43:55.096 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias
2023-11-02 17:43:55.096 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight
2023-11-02 17:43:55.096 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias
2023-11-02 17:43:55.096 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight
2023-11-02 17:43:55.096 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias
2023-11-02 17:43:55.096 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight
2023-11-02 17:43:55.097 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias
2023-11-02 17:43:55.097 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight
2023-11-02 17:43:55.097 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias
2023-11-02 17:43:55.097 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight
2023-11-02 17:43:55.097 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias
2023-11-02 17:43:55.098 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight
2023-11-02 17:43:55.098 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias
2023-11-02 17:43:55.098 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight
2023-11-02 17:43:55.098 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias
2023-11-02 17:43:55.098 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight
2023-11-02 17:43:55.098 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias
2023-11-02 17:43:55.099 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight
2023-11-02 17:43:55.099 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias
2023-11-02 17:43:55.099 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight
2023-11-02 17:43:55.099 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias
2023-11-02 17:43:55.099 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight
2023-11-02 17:43:55.099 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias
2023-11-02 17:43:55.100 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight
2023-11-02 17:43:55.100 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias
2023-11-02 17:43:55.100 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight
2023-11-02 17:43:55.100 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias
2023-11-02 17:43:55.100 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight
2023-11-02 17:43:55.101 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias
2023-11-02 17:43:55.101 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight
2023-11-02 17:43:55.101 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias
2023-11-02 17:43:55.101 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight
2023-11-02 17:43:55.101 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias
2023-11-02 17:43:55.101 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight
2023-11-02 17:43:55.102 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias
2023-11-02 17:43:55.102 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight
2023-11-02 17:43:55.102 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias
2023-11-02 17:43:55.102 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight
2023-11-02 17:43:55.102 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias
2023-11-02 17:43:55.102 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight
2023-11-02 17:43:55.103 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias
2023-11-02 17:43:55.103 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight
2023-11-02 17:43:55.103 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias
2023-11-02 17:43:55.103 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight
2023-11-02 17:43:55.103 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias
2023-11-02 17:43:55.104 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight
2023-11-02 17:43:55.104 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias
2023-11-02 17:43:55.104 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight
2023-11-02 17:43:55.104 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias
2023-11-02 17:43:55.104 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight
2023-11-02 17:43:55.104 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias
2023-11-02 17:43:55.105 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight
2023-11-02 17:43:55.105 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias
2023-11-02 17:43:55.105 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight
2023-11-02 17:43:55.105 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias
2023-11-02 17:43:55.105 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight
2023-11-02 17:43:55.105 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias
2023-11-02 17:43:55.106 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight
2023-11-02 17:43:55.106 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias
2023-11-02 17:43:55.106 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight
2023-11-02 17:43:55.106 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias
2023-11-02 17:43:55.106 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight
2023-11-02 17:43:55.107 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias
2023-11-02 17:43:55.107 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight
2023-11-02 17:43:55.107 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias
2023-11-02 17:43:55.107 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight
2023-11-02 17:43:55.107 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias
2023-11-02 17:43:55.107 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight
2023-11-02 17:43:55.108 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias
2023-11-02 17:43:55.108 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight
2023-11-02 17:43:55.108 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias
2023-11-02 17:43:55.108 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight
2023-11-02 17:43:55.108 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias
2023-11-02 17:43:55.108 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight
2023-11-02 17:43:55.109 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias
2023-11-02 17:43:55.109 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight
2023-11-02 17:43:55.109 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias
2023-11-02 17:43:55.109 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight
2023-11-02 17:43:55.109 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias
2023-11-02 17:43:55.110 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight
2023-11-02 17:43:55.110 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias
2023-11-02 17:43:55.110 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight
2023-11-02 17:43:55.110 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias
2023-11-02 17:43:55.110 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight
2023-11-02 17:43:55.110 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias
2023-11-02 17:43:55.111 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight
2023-11-02 17:43:55.111 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias
2023-11-02 17:43:55.111 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight
2023-11-02 17:43:55.111 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias
2023-11-02 17:43:55.111 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight
2023-11-02 17:43:55.111 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias
2023-11-02 17:43:55.112 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight
2023-11-02 17:43:55.112 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias
2023-11-02 17:43:55.112 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight
2023-11-02 17:43:55.112 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias
2023-11-02 17:43:55.112 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight
2023-11-02 17:43:55.113 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias
2023-11-02 17:43:55.113 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight
2023-11-02 17:43:55.113 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias
2023-11-02 17:43:55.113 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight
2023-11-02 17:43:55.113 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias
2023-11-02 17:43:55.113 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight
2023-11-02 17:43:55.114 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias
2023-11-02 17:43:55.114 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight
2023-11-02 17:43:55.114 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias
2023-11-02 17:43:55.114 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight
2023-11-02 17:43:55.114 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias
2023-11-02 17:43:55.114 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight
2023-11-02 17:43:55.115 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias
2023-11-02 17:43:55.115 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight
2023-11-02 17:43:55.115 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias
2023-11-02 17:43:55.115 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight
2023-11-02 17:43:55.115 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias
2023-11-02 17:43:55.115 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight
2023-11-02 17:43:55.116 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias
2023-11-02 17:43:55.116 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight
2023-11-02 17:43:55.116 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias
2023-11-02 17:43:55.116 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight
2023-11-02 17:43:55.116 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias
2023-11-02 17:43:55.117 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight
2023-11-02 17:43:55.117 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias
2023-11-02 17:43:55.117 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight
2023-11-02 17:43:55.117 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias
2023-11-02 17:43:55.117 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight
2023-11-02 17:43:55.117 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias
2023-11-02 17:43:55.118 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight
2023-11-02 17:43:55.118 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias
2023-11-02 17:43:55.118 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight
2023-11-02 17:43:55.118 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias
2023-11-02 17:43:55.118 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight
2023-11-02 17:43:55.118 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias
2023-11-02 17:43:55.119 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight
2023-11-02 17:43:55.119 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias
2023-11-02 17:43:55.119 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight
2023-11-02 17:43:55.119 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias
2023-11-02 17:43:55.119 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight
2023-11-02 17:43:55.120 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias
2023-11-02 17:43:55.120 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight
2023-11-02 17:43:55.120 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias
2023-11-02 17:43:55.120 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight
2023-11-02 17:43:55.120 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias
2023-11-02 17:43:55.120 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight
2023-11-02 17:43:55.121 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias
2023-11-02 17:43:55.121 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight
2023-11-02 17:43:55.121 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias
2023-11-02 17:43:55.121 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight
2023-11-02 17:43:55.121 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias
2023-11-02 17:43:55.121 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight
2023-11-02 17:43:55.122 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias
2023-11-02 17:43:55.122 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight
2023-11-02 17:43:55.122 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias
2023-11-02 17:43:55.122 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight
2023-11-02 17:43:55.122 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias
2023-11-02 17:43:55.123 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight
2023-11-02 17:43:55.123 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias
2023-11-02 17:43:55.123 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight
2023-11-02 17:43:55.123 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias
2023-11-02 17:43:55.123 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight
2023-11-02 17:43:55.123 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias
2023-11-02 17:43:55.124 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight
2023-11-02 17:43:55.124 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias
2023-11-02 17:43:55.124 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight
2023-11-02 17:43:55.124 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias
2023-11-02 17:43:55.124 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight
2023-11-02 17:43:55.124 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias
2023-11-02 17:43:55.125 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight
2023-11-02 17:43:55.125 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias
2023-11-02 17:43:55.125 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight
2023-11-02 17:43:55.125 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias
2023-11-02 17:43:55.125 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight
2023-11-02 17:43:55.126 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias
2023-11-02 17:43:55.126 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight
2023-11-02 17:43:55.126 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias
2023-11-02 17:43:55.126 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight
2023-11-02 17:43:55.126 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias
2023-11-02 17:43:55.126 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight
2023-11-02 17:43:55.127 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias
2023-11-02 17:43:55.127 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight
2023-11-02 17:43:55.127 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias
2023-11-02 17:43:55.127 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight
2023-11-02 17:43:55.127 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias
2023-11-02 17:43:55.127 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.post_layernorm.weight
2023-11-02 17:43:55.128 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.vision_tower.vision_tower.vision_model.post_layernorm.bias
2023-11-02 17:43:55.128 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.projector.projector.weight
2023-11-02 17:43:55.128 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: model.projector.projector.bias
2023-11-02 17:43:55.128 | INFO     | mmgpt.utils.logger:log_model_parameters:194 - -> Trainable Parameters: lm_head.weight
2023-11-02 17:43:55.131 | INFO     | mmgpt.utils.logger:log_model_parameters:199 - >> Total params: 6752.17M
2023-11-02 17:43:55.132 | INFO     | mmgpt.utils.logger:log_model_parameters:200 - >> Train params: 6752.17M, Ratio 100.00%
2023-11-02 17:43:55.148 | INFO     | mmgpt.data.dataset.pair_webdataset:__init__:53 - 1666666 interleaved (6-merged) image-text pairs (splitted to 8 workers) are sampled from dataset: laion2b_10m_6merge.
2023-11-02 17:43:55.375 | INFO     | mmgpt.data.dataset.pair_webdataset:__init__:53 - 833333 interleaved (6-merged) image-text pairs (splitted to 8 workers) are sampled from dataset: grit_5m_6merge.
2023-11-02 17:43:55.382 | INFO     | mmgpt.data.dataset.interpair_webdataset:__init__:51 - 500000 interleaved (2-merged) image-text pairs (splitted to 8 workers) are sampled from dataset: track_1m_v1_2merge.
2023-11-02 17:43:55.392 | INFO     | mmgpt.data.dataset.interpair_webdataset:__init__:51 - 1250000 interleaved (4-merged) image-text pairs (splitted to 8 workers) are sampled from dataset: det_5m_v1_en_4merge.
2023-11-02 17:43:55.392 | INFO     | mmgpt.data.builder:build_dataloader:65 - After processing, totally 4249999 samples are involved.
2023-11-02 17:43:55.543 | INFO     | mmgpt.engine.train.trainer:create_optimizer:62 - ->> Number of Optimizer Groups: 50
2023-11-02 17:43:55.544 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 0: 233 groups of parameters maintains a learning rate of 5e-05
2023-11-02 17:43:55.544 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 1: 2 groups of parameters maintains a learning rate of 5e-06
2023-11-02 17:43:55.544 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 2: 6 groups of parameters maintains a learning rate of 4.923854510918059e-06
2023-11-02 17:43:55.544 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 3: 6 groups of parameters maintains a learning rate of 5.470949456575621e-06
2023-11-02 17:43:55.544 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 4: 6 groups of parameters maintains a learning rate of 6.078832729528468e-06
2023-11-02 17:43:55.545 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 5: 6 groups of parameters maintains a learning rate of 6.7542585883649645e-06
2023-11-02 17:43:55.545 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 6: 6 groups of parameters maintains a learning rate of 7.504731764849959e-06
2023-11-02 17:43:55.545 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 7: 6 groups of parameters maintains a learning rate of 8.338590849833288e-06
2023-11-02 17:43:55.545 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 8: 6 groups of parameters maintains a learning rate of 9.265100944259208e-06
2023-11-02 17:43:55.545 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 9: 6 groups of parameters maintains a learning rate of 1.0294556604732453e-05
2023-11-02 17:43:55.546 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 10: 6 groups of parameters maintains a learning rate of 1.1438396227480504e-05
2023-11-02 17:43:55.546 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 11: 6 groups of parameters maintains a learning rate of 1.2709329141645005e-05
2023-11-02 17:43:55.546 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 12: 6 groups of parameters maintains a learning rate of 1.4121476824050005e-05
2023-11-02 17:43:55.546 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 13: 6 groups of parameters maintains a learning rate of 1.5690529804500005e-05
2023-11-02 17:43:55.546 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 14: 6 groups of parameters maintains a learning rate of 1.7433922005000004e-05
2023-11-02 17:43:55.546 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 15: 6 groups of parameters maintains a learning rate of 1.9371024450000006e-05
2023-11-02 17:43:55.547 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 16: 6 groups of parameters maintains a learning rate of 2.1523360500000007e-05
2023-11-02 17:43:55.547 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 17: 6 groups of parameters maintains a learning rate of 2.3914845000000007e-05
2023-11-02 17:43:55.547 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 18: 6 groups of parameters maintains a learning rate of 2.6572050000000003e-05
2023-11-02 17:43:55.547 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 19: 6 groups of parameters maintains a learning rate of 2.9524500000000005e-05
2023-11-02 17:43:55.547 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 20: 6 groups of parameters maintains a learning rate of 3.2805e-05
2023-11-02 17:43:55.547 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 21: 6 groups of parameters maintains a learning rate of 3.6450000000000005e-05
2023-11-02 17:43:55.548 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 22: 6 groups of parameters maintains a learning rate of 4.05e-05
2023-11-02 17:43:55.548 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 23: 6 groups of parameters maintains a learning rate of 4.5e-05
2023-11-02 17:43:55.548 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 24: 6 groups of parameters maintains a learning rate of 5.555555555555556e-05
2023-11-02 17:43:55.548 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 25: 76 groups of parameters maintains a learning rate of 5e-05
2023-11-02 17:43:55.548 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 26: 5 groups of parameters maintains a learning rate of 5e-06
2023-11-02 17:43:55.548 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 27: 10 groups of parameters maintains a learning rate of 4.923854510918059e-06
2023-11-02 17:43:55.549 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 28: 10 groups of parameters maintains a learning rate of 5.470949456575621e-06
2023-11-02 17:43:55.549 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 29: 10 groups of parameters maintains a learning rate of 6.078832729528468e-06
2023-11-02 17:43:55.549 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 30: 10 groups of parameters maintains a learning rate of 6.7542585883649645e-06
2023-11-02 17:43:55.549 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 31: 10 groups of parameters maintains a learning rate of 7.504731764849959e-06
2023-11-02 17:43:55.549 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 32: 10 groups of parameters maintains a learning rate of 8.338590849833288e-06
2023-11-02 17:43:55.549 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 33: 10 groups of parameters maintains a learning rate of 9.265100944259208e-06
2023-11-02 17:43:55.550 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 34: 10 groups of parameters maintains a learning rate of 1.0294556604732453e-05
2023-11-02 17:43:55.550 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 35: 10 groups of parameters maintains a learning rate of 1.1438396227480504e-05
2023-11-02 17:43:55.550 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 36: 10 groups of parameters maintains a learning rate of 1.2709329141645005e-05
2023-11-02 17:43:55.550 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 37: 10 groups of parameters maintains a learning rate of 1.4121476824050005e-05
2023-11-02 17:43:55.550 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 38: 10 groups of parameters maintains a learning rate of 1.5690529804500005e-05
2023-11-02 17:43:55.551 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 39: 10 groups of parameters maintains a learning rate of 1.7433922005000004e-05
2023-11-02 17:43:55.551 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 40: 10 groups of parameters maintains a learning rate of 1.9371024450000006e-05
2023-11-02 17:43:55.551 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 41: 10 groups of parameters maintains a learning rate of 2.1523360500000007e-05
2023-11-02 17:43:55.551 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 42: 10 groups of parameters maintains a learning rate of 2.3914845000000007e-05
2023-11-02 17:43:55.551 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 43: 10 groups of parameters maintains a learning rate of 2.6572050000000003e-05
2023-11-02 17:43:55.551 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 44: 10 groups of parameters maintains a learning rate of 2.9524500000000005e-05
2023-11-02 17:43:55.552 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 45: 10 groups of parameters maintains a learning rate of 3.2805e-05
2023-11-02 17:43:55.552 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 46: 10 groups of parameters maintains a learning rate of 3.6450000000000005e-05
2023-11-02 17:43:55.552 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 47: 10 groups of parameters maintains a learning rate of 4.05e-05
2023-11-02 17:43:55.552 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 48: 10 groups of parameters maintains a learning rate of 4.5e-05
2023-11-02 17:43:55.552 | INFO     | mmgpt.engine.train.trainer:create_optimizer:64 - *********>> 49: 10 groups of parameters maintains a learning rate of 5.555555555555556e-05
2023-11-02 17:44:20.020 | INFO     | mmgpt.data.dataset.pair_webdataset:token_processor:102 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:44:20.021 | INFO     | mmgpt.data.dataset.pair_webdataset:token_processor:103 - (None, 'check MRP of kitchen curtains modern JUPON')
2023-11-02 17:44:28.265 | INFO     | mmgpt.data.dataset.pair_webdataset:token_processor:102 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:44:28.266 | INFO     | mmgpt.data.dataset.pair_webdataset:token_processor:103 - (None, 'LHS Science Olympiad team [288, 143, 430, 357] [487, 394, 635, 907] [609, 394, 734, 899] [014, 375, 192, 897] [263, 381, 440, 896] [128, 358, 320, 938] [717, 397, 888, 962] smiles bright at the camera as they take on their region competition in downtown.')
2023-11-02 17:44:35.145 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:114 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:44:35.145 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:115 - ('<image>\nDetect all.The category:[xmin,ymin,xmax,ymax] format should be rigorously followed in your response.', 'bow and arrow:[445, 153, 925, 840].')
2023-11-02 17:44:39.895 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:114 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:44:39.895 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:115 - ('<image>\nDetect all.Your answer should be structured precisely according to the category:[xmin,ymin,xmax,ymax] format.', 'Boat:[084, 314, 900, 863],[002, 001, 998, 853];Lifesaver:[408, 221, 446, 278];Person:[524, 420, 555, 568],[521, 624, 560, 757],[435, 149, 456, 278],[345, 151, 380, 274].')
2023-11-02 17:45:36.474 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:114 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:45:36.475 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:115 - ('<image>\nDetect all.Maintain strict adherence to the format category:[xmin,ymin,xmax,ymax] when presenting your answer.', 'Person:[013, 525, 181, 948],[242, 575, 484, 909],[338, 545, 383, 841],[418, 518, 596, 830],[554, 539, 658, 786];Backpack:[002, 651, 135, 930],[423, 597, 531, 726],[542, 590, 637, 733];Camera:[500, 700, 539, 742].')
2023-11-02 17:45:52.309 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:114 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:45:52.309 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:115 - ('Given frame1:<image> and frame2:<image>,track car<Id1>Frame1:[442, 632, 526, 740]</Id1>,bus<Id4>Frame1:[666, 571, 772, 720]</Id4> in this video clip.Ensure you use the exact format category<Idi>Frame t:[xmin,ymin,xmax,ymax]</Idi> in your response.', 'car<Id1>Frame1:[442, 632, 526, 740];Frame2:[443, 632, 526, 740]</Id1>,bus<Id4>Frame1:[666, 571, 772, 720];Frame2:[666, 571, 772, 720]</Id4>.')
2023-11-02 17:46:28.735 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:114 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:46:28.736 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:115 - ('Given a video clip including frame1<image>,frame2<image>,frame3<image> and frame4<image>,please tell me what is this<Id12>Frame1:[466, 002, 618, 172]</Id12> and track its trajectory.When detailing trajectories in your response, adhere to the <Idi>Frame t:[xmin,ymin,xmax,ymax]</Idi> format.', 'This is a gray monkey playing with a cat<Id12>Frame1:[466, 002, 618, 172];Frame2:[762, 008, 879, 277];Frame3:[002, 002, 002, 002];Frame4:[002, 002, 002, 002]</Id12>.')
2023-11-02 17:46:47.304 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:114 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:46:47.304 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:115 - ('<image>\nDetect all.When submitting your answer, maintain the category:[xmin,ymin,xmax,ymax] structure consistently.', 'man:[276, 270, 400, 894],[000, 000, 804, 998],[822, 392, 865, 578],[960, 387, 999, 791];clothing:[000, 118, 275, 702],[217, 311, 300, 998],[304, 358, 399, 998],[375, 393, 425, 747],[411, 370, 432, 682],[423, 381, 467, 677],[461, 395, 501, 673],[476, 397, 517, 647],[513, 404, 560, 558],[564, 402, 599, 643],[586, 393, 615, 591],[610, 428, 631, 604],[641, 428, 676, 600],[691, 434, 722, 561],[749, 402, 790, 586],[778, 388, 811, 584],[830, 422, 861, 520],[969, 404, 999, 793].')
2023-11-02 17:47:11.930 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:114 - exceeding max length 2048, ignore last 3 samples!
2023-11-02 17:47:11.931 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:115 - ('<image>\ndetect Sneakers,Helmet and Book in this image.Your output should conform exactly to the category:[xmin,ymin,xmax,ymax] format.', 'Sneakers:[586, 757, 628, 864],[502, 802, 540, 897],[408, 834, 483, 934],[320, 816, 380, 933];Helmet:[474, 119, 546, 239],[406, 113, 482, 219];Book:[696, 585, 741, 650].')
2023-11-02 17:47:18.576 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:114 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:47:18.576 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:115 - ('Given a video clip including frame1<image>,frame2<image> and frame3<image>,can you tell me the trajectory of the the person feeding food to the lizard. in this video clip?For clarity, represent trajectories using the Tracki<Idi>Frame t:[xmin,ymin,xmax,ymax]</Idi> format in your response.', 'There is one the person feeding food to the lizard..Track1<Id1>frame:1:[649, 000, 999, 693];frame:2:[649, 000, 999, 693];frame:3:[492, 000, 998, 739]</Id1>.')
2023-11-02 17:47:33.184 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:114 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:47:33.185 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:115 - ('Given a video clip including frame1<image>,frame2<image>,frame3<image> and frame4<image>,please tell me what is this<Id34>Frame1:[296, 194, 364, 341]</Id34> and track its trajectory.Your response should highlight trajectories using the established <Idi>Frame t:[xmin,ymin,xmax,ymax]</Idi> structure.', 'This is a ice bear<Id34>Frame1:[296, 194, 364, 341];Frame2:[279, 181, 333, 337];Frame3:[275, 181, 326, 337];Frame4:[285, 173, 332, 338]</Id34>.')
2023-11-02 17:47:59.642 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:114 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:47:59.642 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:115 - ('<image>\ndetect all.Ensure your response adheres strictly to the format category:[xmin,ymin,xmax,ymax]', 'Umbrella:[471, 193, 580, 484],[192, 245, 265, 355],[648, 172, 749, 324],[511, 262, 601, 390],[392, 255, 523, 390],[042, 256, 075, 309];Hat:[104, 714, 229, 803],[383, 474, 420, 505].')
2023-11-02 17:48:04.038 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:114 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:48:04.038 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:115 - ('<image>\ndetect all.Please make sure your answer follows the category:[xmin,ymin,xmax,ymax] configuration precisely.', 'Wild Bird:[385, 557, 484, 648],[379, 678, 477, 798],[416, 850, 474, 900],[686, 099, 721, 146],[546, 090, 581, 147],[475, 194, 510, 242].')
2023-11-02 17:48:35.672 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:114 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:48:35.674 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:115 - ('Given a video cluo including frame1<image>,frame2<image>,frame3<image>,frame4<image> and frame5<image>,can you tell me what is this<Id89>Frame1:[812, 666, 1000, 997]</Id89> and track its trajectory.Use the specified <Idi>Frame t:[xmin,ymin,xmax,ymax]</Idi> format for all trajectories in your reply.', 'This is a brown bear hunting on the ground<Id89>Frame1:[812, 666, 1000, 997];Frame2:[827, 672, 1000, 997];Frame3:[835, 680, 1000, 1000];Frame4:[856, 683, 1000, 991];Frame5:[864, 688, 1000, 991]</Id89>.')
2023-11-02 17:49:29.092 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:114 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:49:29.092 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:115 - ('<image>\nDetect all.The category:[xmin,ymin,xmax,ymax] format should be rigorously followed in your response.', 'human body:[194, 000, 999, 364],[179, 347, 238, 440],[197, 213, 461, 340],[212, 589, 346, 766],[310, 685, 999, 999],[320, 342, 999, 745];human hair:[140, 731, 363, 959],[108, 546, 212, 669],[125, 765, 173, 839],[141, 410, 366, 658],[148, 031, 215, 174];human head:[169, 749, 324, 940],[107, 871, 175, 949],[108, 545, 221, 658],[112, 014, 255, 167],[148, 420, 303, 603];clothing:[208, 000, 1000, 348],[184, 342, 248, 423],[190, 216, 451, 337],[203, 306, 248, 370],[213, 595, 330, 730],[243, 334, 374, 440],[300, 671, 999, 999],[326, 345, 999, 742];person:[081, 000, 999, 999];mammal:[069, 000, 999, 339],[078, 535, 338, 723],[096, 700, 998, 999],[108, 852, 200, 940],[108, 921, 275, 999],[133, 313, 999, 775],[144, 000, 459, 432],[186, 710, 282, 755];human face:[136, 553, 220, 655],[147, 064, 243, 155],[163, 462, 301, 573],[188, 815, 305, 933];human arm:[207, 215, 338, 243],[214, 000, 430, 190],[219, 296, 325, 340],[299, 169, 598, 343],[325, 543, 561, 745],[336, 338, 575, 512];human hand:[493, 532, 558, 655],[518, 422, 574, 515].')
2023-11-02 17:49:39.187 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:114 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:49:39.187 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:115 - ('<image>\nDetect all.Your output should conform exactly to the category:[xmin,ymin,xmax,ymax] format.', 'Person:[327, 200, 732, 850],[677, 202, 759, 313];Bicycle:[372, 478, 679, 937],[689, 249, 749, 330];Sneakers:[638, 765, 706, 850],[443, 667, 521, 748];Helmet:[475, 201, 605, 276].')
2023-11-02 17:49:43.100 | INFO     | mmgpt.data.dataset.pair_webdataset:token_processor:102 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:49:43.100 | INFO     | mmgpt.data.dataset.pair_webdataset:token_processor:103 - (None, 'Under the knife: Nadia Bartel [225, 051, 721, 996] made a discreet exit from a private hospital in Melbourne on Thursday morning, possibly after undergoing a rhinoplasty')
2023-11-02 17:50:00.656 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:114 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:50:00.657 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:115 - ('<image>\ndetect all.To maintain clarity, use the prescribed category:[x0,y0,x1,y1] format for your answer.', 'Stool:[734, 838, 925, 1000],[782, 707, 948, 842],[874, 651, 988, 750];Desk:[623, 566, 951, 936];Person:[231, 245, 756, 998],[260, 271, 353, 403],[209, 919, 468, 999];TV:[770, 551, 848, 647],[001, 398, 085, 706].')
2023-11-02 17:50:06.706 | INFO     | mmgpt.data.dataset.pair_webdataset:token_processor:102 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:50:06.707 | INFO     | mmgpt.data.dataset.pair_webdataset:token_processor:103 - (None, '[110, 560, 162, 799] [565, 321, 619, 511] [657, 287, 717, 496] Foreign tourists and [320, 323, 353, 471] [250, 465, 314, 768] locals alike walk along the popular Kuta beach covered with debris and rubbish washed up by the tide, near Denpasar on the resort island of Bali.')
2023-11-02 17:50:12.526 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:114 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:50:12.526 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:115 - ('<image>\nDetect all.To maintain clarity, use the prescribed category:[x0,y0,x1,y1] format for your answer.', 'Flower:[229, 771, 396, 999],[453, 683, 879, 1000];Vase:[560, 891, 711, 1000];Desk:[069, 847, 1000, 999],[691, 599, 949, 794];Person:[002, 322, 249, 918],[355, 265, 693, 898];Hat:[002, 260, 210, 486],[420, 265, 633, 482];Tie:[513, 591, 543, 734];Cup:[184, 825, 242, 984],[039, 864, 080, 998],[929, 798, 986, 999],[779, 911, 859, 998];Bottle:[102, 798, 206, 999],[676, 633, 703, 739];Wine Glass:[002, 796, 059, 1000],[362, 690, 422, 964],[447, 710, 510, 950].')
2023-11-02 17:50:16.927 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:114 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:50:16.927 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:115 - ('<image>\nDetect all.When composing your answer, be sure to consistently utilize the category:[xmin,ymin,xmax,ymax] structure.', 'Towel:[748, 621, 805, 687];Flower:[670, 539, 792, 630];Chair:[864, 668, 997, 999],[694, 713, 900, 999],[508, 668, 697, 999],[420, 598, 593, 932],[472, 550, 523, 716],[001, 583, 061, 721],[018, 530, 145, 740],[140, 519, 211, 687],[201, 493, 295, 678],[267, 476, 322, 637],[376, 497, 473, 673],[471, 502, 543, 603],[637, 493, 684, 565],[949, 570, 999, 684],[914, 508, 967, 676],[938, 464, 997, 568],[866, 474, 941, 598],[801, 474, 856, 550],[726, 463, 792, 553];Cup:[706, 482, 755, 555].')
2023-11-02 17:50:19.865 | INFO     | mmgpt.data.dataset.pair_webdataset:token_processor:102 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:50:19.865 | INFO     | mmgpt.data.dataset.pair_webdataset:token_processor:103 - (None, 'Kohler Generators has introduced [150, 186, 838, 809] a new 30-kilowatt standby generator that the company says is targeted at large custom homes and small businesses.')
2023-11-02 17:50:34.951 | INFO     | mmgpt.data.dataset.pair_webdataset:token_processor:102 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:50:34.951 | INFO     | mmgpt.data.dataset.pair_webdataset:token_processor:103 - (None, '[180, 056, 297, 280] [182, 386, 299, 609] [679, 389, 795, 619] [040, 722, 180, 941] [794, 041, 947, 271] [794, 386, 943, 615] [296, 714, 439, 937] [531, 394, 676, 619] [038, 063, 181, 281] [532, 051, 680, 279] [295, 380, 440, 604] [293, 053, 440, 277] Three Dresses - [005, 006, 988, 993] variable edition of a drypoint etching')
2023-11-02 17:51:05.260 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:114 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:51:05.260 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:115 - ('<image>\nDetect all.The category:[xmin,ymin,xmax,ymax] format should be rigorously followed in your response.', 'shelf:[059, 272, 352, 928],[194, 129, 571, 531],[557, 067, 943, 928],[060, 138, 214, 473];Person:[411, 209, 526, 694];Book:[202, 856, 310, 925],[081, 859, 209, 927].')
2023-11-02 17:51:31.796 | INFO     | mmgpt.data.dataset.pair_webdataset:token_processor:102 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:51:31.796 | INFO     | mmgpt.data.dataset.pair_webdataset:token_processor:103 - (None, 'Easy up-do / Edwardian hairstyle [021, 063, 417, 432]. Start with a medium height ponytail. Flip ponytail in on ...')
2023-11-02 17:51:47.783 | INFO     | mmgpt.data.dataset.pair_webdataset:token_processor:102 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:51:47.784 | INFO     | mmgpt.data.dataset.pair_webdataset:token_processor:103 - (None, '[430, 177, 682, 884] An elderly artist working at his easel while [168, 189, 324, 743] his wife looks on from the doorway')
2023-11-02 17:51:49.721 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:114 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:51:49.722 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:115 - ('<image>\nDetect all.For your response, please adhere to the specified category:[xmin,ymin,xmax,ymax] format.', 'human body:[831, 330, 993, 745],[000, 487, 061, 713],[102, 320, 248, 596],[286, 274, 998, 906];woman:[839, 339, 1000, 621],[332, 323, 462, 646],[793, 363, 870, 547];mammal:[089, 311, 239, 558],[000, 485, 060, 715],[198, 337, 264, 510],[291, 356, 378, 568],[332, 325, 460, 641],[428, 271, 681, 905],[622, 365, 678, 568],[652, 334, 711, 563],[693, 343, 799, 625],[788, 371, 870, 546],[834, 339, 999, 735],[939, 378, 999, 633];man:[092, 314, 243, 570],[000, 485, 064, 716],[299, 350, 371, 562],[425, 272, 687, 914],[643, 328, 713, 564],[678, 345, 805, 632],[700, 369, 737, 468];footwear:[495, 812, 602, 911],[102, 567, 165, 605],[476, 813, 551, 860],[840, 702, 941, 738],[861, 676, 941, 709];human leg:[000, 540, 050, 714],[115, 438, 177, 601],[181, 446, 243, 601],[351, 499, 419, 644],[398, 513, 439, 632],[485, 641, 557, 834],[503, 606, 644, 890],[674, 515, 740, 617],[706, 499, 783, 620],[839, 543, 954, 736];human hair:[533, 330, 636, 372],[903, 343, 986, 391];human arm:[000, 483, 056, 588],[106, 380, 184, 441],[339, 393, 414, 476],[635, 412, 685, 657],[713, 396, 777, 513],[868, 403, 999, 504];jeans:[343, 492, 438, 613],[676, 445, 698, 547].')
2023-11-02 17:51:55.122 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:114 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:51:55.123 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:115 - ('Given a video cluo including frame1<image>,frame2<image>,frame3<image>,frame4<image> and frame5<image>,what is this<Id31>Frame1:[343, 239, 521, 829]</Id31> and track its trajectory.All trajectories in your reply should conform to the <Idi>Frame t:[xmin,ymin,xmax,ymax]</Idi> pattern.', 'This is a gemsbok<Id31>Frame1:[343, 239, 521, 829];Frame2:[321, 260, 487, 814];Frame3:[285, 231, 629, 822];Frame4:[248, 233, 712, 795];Frame5:[301, 258, 731, 812]</Id31>.')
2023-11-02 17:51:56.253 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:114 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:51:56.253 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:115 - ('<image>\nDetect all.Maintain strict adherence to the format category:[x0,y0,x1,y1] when presenting your answer.', 'person:[555, 439, 855, 1000],[063, 336, 248, 663],[228, 342, 411, 763],[315, 367, 571, 836].')
2023-11-02 17:52:26.931 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:114 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:52:26.932 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:115 - ('<image>\nDetect all.The category:[xmin,ymin,xmax,ymax] format should be rigorously followed in your response.', 'human body:[386, 225, 673, 976],[057, 121, 997, 999];woman:[456, 214, 710, 998],[338, 352, 504, 999],[841, 253, 951, 707];human hair:[177, 227, 316, 433],[088, 260, 181, 370],[358, 354, 453, 581],[468, 218, 591, 530],[563, 211, 625, 304],[615, 222, 660, 326],[633, 125, 787, 286],[859, 245, 932, 376];human head:[475, 223, 603, 426],[069, 219, 173, 399],[200, 230, 315, 442],[374, 353, 456, 474],[557, 219, 607, 331],[608, 213, 679, 334],[633, 122, 769, 361],[847, 254, 920, 361];human arm:[890, 400, 981, 956],[121, 515, 288, 999],[149, 413, 211, 516],[321, 622, 395, 990],[344, 682, 363, 807],[350, 559, 428, 840],[420, 419, 503, 723],[609, 267, 706, 480],[644, 443, 703, 657];human hand:[330, 882, 410, 994],[420, 421, 475, 561],[606, 267, 674, 349],[900, 871, 974, 957];hat:[056, 198, 168, 316];man:[050, 197, 211, 959],[555, 219, 621, 357],[586, 223, 702, 719],[631, 132, 993, 999];girl:[346, 355, 513, 996],[431, 223, 704, 999],[858, 247, 931, 439];human face:[074, 291, 117, 391],[230, 264, 310, 438],[491, 264, 567, 407],[584, 249, 610, 312],[649, 170, 750, 356],[850, 277, 878, 356].')
2023-11-02 17:52:40.947 | INFO     | mmgpt.data.dataset.pair_webdataset:token_processor:102 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:52:40.948 | INFO     | mmgpt.data.dataset.pair_webdataset:token_processor:103 - (None, 'A block diagram [016, 064, 977, 987] illustrating the interconnectivity of the Invoicing module in the Compass suite.')
2023-11-02 17:52:41.871 | INFO     | mmgpt.data.dataset.pair_webdataset:token_processor:102 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:52:41.871 | INFO     | mmgpt.data.dataset.pair_webdataset:token_processor:103 - (None, '[562, 757, 612, 928] [440, 640, 545, 989] kids fly [221, 210, 259, 258] [835, 077, 955, 140] [481, 037, 512, 095] [372, 051, 408, 098] [799, 152, 887, 257] [249, 383, 295, 449] [297, 532, 339, 593] [788, 248, 846, 303] kites at the waterfront of a park')
2023-11-02 17:53:07.575 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:114 - exceeding max length 2048, ignore last 2 samples!
2023-11-02 17:53:07.575 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:115 - ('<image>\nDetect all.Consistently apply the category:[xmin,ymin,xmax,ymax] format to your answer.', 'bird:[440, 168, 776, 880].')
2023-11-02 17:53:30.964 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:114 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:53:30.964 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:115 - ('<image>\nDetect all.Please make sure your answer follows the category:[xmin,ymin,xmax,ymax] configuration precisely.', 'tree:[000, 348, 617, 902],[027, 261, 104, 321],[181, 376, 714, 518],[614, 376, 999, 837],[709, 320, 888, 588],[783, 048, 999, 357].')
2023-11-02 17:53:32.378 | INFO     | mmgpt.data.dataset.pair_webdataset:token_processor:102 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:53:32.379 | INFO     | mmgpt.data.dataset.pair_webdataset:token_processor:103 - (None, 'Women [470, 626, 550, 933] [331, 227, 468, 945] [553, 341, 623, 938] [797, 164, 944, 953] exercise in front of a trainer [075, 416, 145, 939] as the sun sets, March 13, 2014.')
2023-11-02 17:53:49.722 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:114 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:53:49.722 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:115 - ('Given a video clip including frame1<image>,frame2<image> and frame3<image>,what is this<Id3>Frame1:[746, 179, 963, 413]</Id3> and track its trajectory.Ensure the trajectories in your answer follow the <Idi>Frame t:[xmin,ymin,xmax,ymax]</Idi> structure.', 'This is a bird walking on the grass ground<Id3>Frame1:[746, 179, 963, 413];Frame2:[728, 241, 972, 440];Frame3:[696, 227, 953, 411]</Id3>.')
2023-11-02 17:53:53.101 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:114 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:53:53.102 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:115 - ('<image>\nDetect all.Your answer should be structured precisely according to the category:[xmin,ymin,xmax,ymax] format.', 'Person:[742, 003, 941, 694],[002, 003, 780, 1000],[178, 003, 442, 484],[426, 003, 701, 923].')
2023-11-02 17:53:55.924 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:114 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:53:55.925 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:115 - ('<image>\nDetect all.Please make sure your answer follows the category:[xmin,ymin,xmax,ymax] configuration precisely.', 'suit:[880, 195, 991, 873],[000, 281, 124, 797],[002, 313, 110, 556],[112, 239, 255, 860],[294, 308, 368, 769],[328, 289, 468, 817],[352, 274, 438, 306],[455, 431, 645, 607],[501, 302, 601, 443],[568, 302, 710, 616],[703, 316, 832, 841],[806, 289, 891, 575],[844, 300, 923, 754];man:[873, 169, 995, 866],[052, 189, 122, 825],[116, 141, 255, 885],[208, 172, 253, 302],[278, 169, 362, 323],[291, 228, 356, 623],[300, 208, 470, 844],[458, 341, 640, 630],[471, 186, 536, 355],[549, 197, 620, 316],[570, 217, 703, 613],[663, 197, 701, 269];human face:[036, 248, 070, 325],[171, 164, 208, 239],[310, 245, 343, 309],[386, 228, 423, 300],[525, 352, 571, 442],[541, 245, 575, 308],[620, 223, 652, 302],[697, 239, 730, 302],[748, 252, 785, 322],[911, 209, 956, 284].')
2023-11-02 17:53:57.787 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:114 - exceeding max length 2048, ignore last 2 samples!
2023-11-02 17:53:57.788 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:115 - ('<image>\nDetect all.When composing your answer, be sure to consistently utilize the category:[xmin,ymin,xmax,ymax] structure.', 'Flower:[247, 815, 370, 951],[574, 807, 701, 945];Potted Plant:[484, 811, 509, 849],[553, 814, 585, 853],[404, 809, 445, 851].')
2023-11-02 17:54:12.402 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:114 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:54:12.403 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:115 - ('<image>\nDetect all.Please make sure your answer follows the category:[xmin,ymin,xmax,ymax] configuration precisely.', 'Moniter:[550, 044, 872, 554];Storage box:[034, 661, 303, 999],[526, 588, 706, 994],[755, 552, 892, 848],[003, 552, 079, 645];Desk:[651, 515, 742, 719],[421, 535, 545, 799],[408, 508, 500, 703],[362, 489, 443, 645],[332, 478, 392, 611],[216, 500, 303, 672],[201, 522, 304, 672],[128, 489, 205, 656],[119, 565, 275, 673],[002, 504, 042, 712].')
2023-11-02 17:55:08.397 | INFO     | mmgpt.data.dataset.pair_webdataset:token_processor:102 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:55:08.397 | INFO     | mmgpt.data.dataset.pair_webdataset:token_processor:103 - (None, 'View of people [849, 484, 925, 766] [253, 579, 354, 924] [495, 501, 593, 829] [612, 524, 707, 812] looking over the top deck [088, 347, 998, 992] of BB Riverboats cruise on the ohio river [003, 329, 461, 994]')
2023-11-02 17:55:13.224 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:114 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:55:13.224 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:115 - ('<image>\nDetect all.For your response, please adhere to the specified category:[xmin,ymin,xmax,ymax] format.', 'Person:[184, 260, 511, 1000],[211, 089, 999, 1000],[338, 006, 589, 543],[763, 130, 918, 508];Glasses:[410, 208, 584, 388],[597, 183, 739, 238];Bottle:[402, 798, 471, 996],[755, 783, 828, 923].')
2023-11-02 17:55:57.548 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:114 - exceeding max length 2048, ignore last 1 samples!
2023-11-02 17:55:57.548 | INFO     | mmgpt.data.dataset.interpair_webdataset:token_processor:115 - ('<image>\nDetect all.Maintain strict adherence to the format category:[xmin,ymin,xmax,ymax] when presenting your answer.', 'SUV:[800, 499, 906, 547],[157, 508, 258, 566];Street Lights:[719, 273, 745, 362],[522, 185, 555, 388];Traffic cone:[251, 559, 275, 615],[211, 565, 228, 605],[167, 558, 187, 601];Bench:[280, 537, 305, 580],[429, 542, 486, 588];Person:[231, 263, 500, 930],[494, 306, 630, 842],[678, 489, 735, 746],[432, 524, 451, 587],[300, 522, 313, 610],[177, 514, 200, 617],[219, 495, 234, 563];Watch:[503, 480, 517, 500],[607, 489, 616, 509];Glasses:[553, 335, 585, 354];Hat:[362, 264, 411, 312];Sneakers:[678, 724, 706, 745],[699, 732, 718, 746],[538, 790, 562, 841],[531, 770, 556, 829],[344, 871, 379, 928],[309, 753, 347, 855].')