Track log files with git lfs

runtime_logs/run_2025-02-14_04-23-49.log

@@ -1,382 +1,3 @@
-2025-02-14 04:23:49,942 - training_args.py:2100 - _setup_devices - INFO - PyTorch: setting up devices
-2025-02-14 04:23:49,975 - training_args.py:1837 - __post_init__ - WARNING - When using FSDP full shard, instead of using `gradient_checkpointing` in TrainingArguments, please use `activation_checkpointing` in `fsdp_config`. The former introduces a redundant AllGather operation in backward pass. Reference: https://github.com/huggingface/transformers/issues/30404
-2025-02-14 04:23:50,508 - configuration_utils.py:731 - _get_config_dict - INFO - loading configuration file ./checkpoints/longvu_llama3_2/config.json
-2025-02-14 04:23:50,511 - configuration_utils.py:800 - from_dict - INFO - Model config CambrianConfig {
-  "_name_or_path": "/tmp/iopath_cache/manifold_cache/tree/users/shenx/finetune/09281004-cambrian_llama3_2_t576_ov",
-  "architectures": [
-    "CambrianLlamaForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "bos_token_id": 128000,
-  "connect_layer": 2,
-  "connector_depth": 3,
-  "connector_only": true,
-  "dino_threshold": 0.83,
-  "drop_threshold": 0.8,
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
-  "frame_pos": false,
-  "freeze_mm_mlp_adapter": false,
-  "hidden_act": "silu",
-  "hidden_size": 3072,
-  "highres": true,
-  "highres_connect": false,
-  "image_aspect_ratio": "pad",
-  "image_position": 91,
-  "image_token_len": 144,
-  "initializer_range": 0.02,
-  "intermediate_size": 8192,
-  "is_image_newline": true,
-  "is_st_sampler": false,
-  "lowres_token": 8,
-  "max_position_embeddings": 131072,
-  "mlp_bias": false,
-  "mm_patch_merge_type": "flat",
-  "mm_projector_lr": null,
-  "mm_projector_type": "sva",
-  "mm_use_im_patch_token": false,
-  "mm_use_im_start_end": false,
-  "mm_vision_sampler_lr": null,
-  "mm_vision_select_feature": "patch",
-  "mm_vision_select_layer": -2,
-  "mm_vision_tower_aux_list": [
-    "siglip/CLIP-ViT-SO400M-14-384",
-    "facebook/dinov2-giant-res378"
-  ],
-  "mm_vision_tower_aux_token_len_list": [
-    576,
-    576
-  ],
-  "mm_vision_tower_lr": null,
-  "model_type": "cambrian_llama",
-  "num_attention_heads": 24,
-  "num_hidden_layers": 28,
-  "num_key_value_heads": 8,
-  "num_of_vision_sampler_layers": 10,
-  "num_query_group": 1,
-  "pretraining_tp": 1,
-  "query_num_list": [
-    144
-  ],
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": {
-    "factor": 32.0,
-    "high_freq_factor": 4.0,
-    "low_freq_factor": 1.0,
-    "original_max_position_embeddings": 8192,
-    "rope_type": "llama3"
-  },
-  "rope_theta": 500000.0,
-  "spmd_debug": null,
-  "spmd_fsdp_sharding": null,
-  "spmd_mesh": null,
-  "start_of_vision_sampler_layers": 0,
-  "stride_of_vision_sampler_layers": 3,
-  "tie_word_embeddings": false,
-  "tokenizer_model_max_length": 8192,
-  "tokenizer_padding_side": "right",
-  "torch_dtype": "float32",
-  "transformers_version": "4.43.1",
-  "tune_mm_mlp_adapter": false,
-  "unfreeze_mm_vision_tower": false,
-  "use_cache": false,
-  "use_mm_proj": true,
-  "vision_hidden_size": 1024,
-  "vision_tower_aux_token_len_list": [
-    576,
-    576
-  ],
-  "vocab_size": 128256
-}
-
-2025-02-14 04:23:50,511 - modeling_utils.py:3618 - from_pretrained - INFO - loading weights file ./checkpoints/longvu_llama3_2/pytorch_model.bin
-2025-02-14 04:23:50,551 - configuration_utils.py:1038 - from_dict - INFO - Generate config GenerationConfig {
-  "bos_token_id": 128000,
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
-  "use_cache": false
-}
-
-2025-02-14 04:23:50,771 - configuration_utils.py:733 - _get_config_dict - INFO - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--facebook--dinov2-giant/snapshots/611a9d42f2335e0f921f1e313ad3c1b7178d206d/config.json
-2025-02-14 04:23:50,774 - configuration_utils.py:800 - from_dict - INFO - Model config Dinov2Config {
-  "apply_layernorm": true,
-  "architectures": [
-    "Dinov2Model"
-  ],
-  "attention_probs_dropout_prob": 0.0,
-  "drop_path_rate": 0.0,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.0,
-  "hidden_size": 1536,
-  "image_size": 518,
-  "initializer_range": 0.02,
-  "layer_norm_eps": 1e-06,
-  "layerscale_value": 1.0,
-  "mlp_ratio": 4,
-  "model_type": "dinov2",
-  "num_attention_heads": 24,
-  "num_channels": 3,
-  "num_hidden_layers": 40,
-  "out_features": [
-    "stage40"
-  ],
-  "out_indices": [
-    40
-  ],
-  "patch_size": 14,
-  "qkv_bias": true,
-  "reshape_hidden_states": true,
-  "stage_names": [
-    "stem",
-    "stage1",
-    "stage2",
-    "stage3",
-    "stage4",
-    "stage5",
-    "stage6",
-    "stage7",
-    "stage8",
-    "stage9",
-    "stage10",
-    "stage11",
-    "stage12",
-    "stage13",
-    "stage14",
-    "stage15",
-    "stage16",
-    "stage17",
-    "stage18",
-    "stage19",
-    "stage20",
-    "stage21",
-    "stage22",
-    "stage23",
-    "stage24",
-    "stage25",
-    "stage26",
-    "stage27",
-    "stage28",
-    "stage29",
-    "stage30",
-    "stage31",
-    "stage32",
-    "stage33",
-    "stage34",
-    "stage35",
-    "stage36",
-    "stage37",
-    "stage38",
-    "stage39",
-    "stage40"
-  ],
-  "torch_dtype": "float32",
-  "transformers_version": "4.43.1",
-  "use_swiglu_ffn": true
-}
-
-2025-02-14 04:23:52,141 - modeling_utils.py:4450 - _load_pretrained_model - INFO - All model checkpoint weights were used when initializing CambrianLlamaForCausalLM.
-
-2025-02-14 04:23:52,141 - modeling_utils.py:4458 - _load_pretrained_model - INFO - All the weights of CambrianLlamaForCausalLM were initialized from the model checkpoint at ./checkpoints/longvu_llama3_2.
-If your task is similar to the task the model of the checkpoint was trained on, you can already use CambrianLlamaForCausalLM for predictions without further training.
-2025-02-14 04:23:52,147 - configuration_utils.py:991 - from_pretrained - INFO - loading configuration file ./checkpoints/longvu_llama3_2/generation_config.json
-2025-02-14 04:23:52,147 - configuration_utils.py:1038 - from_dict - INFO - Generate config GenerationConfig {
-  "bos_token_id": 128000,
-  "do_sample": true,
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
-  "temperature": 0.6,
-  "top_p": 0.9
-}
-
-2025-02-14 04:23:52,674 - tokenization_utils_base.py:2287 - from_pretrained - INFO - loading file tokenizer.json
-2025-02-14 04:23:52,674 - tokenization_utils_base.py:2287 - from_pretrained - INFO - loading file added_tokens.json
-2025-02-14 04:23:52,674 - tokenization_utils_base.py:2287 - from_pretrained - INFO - loading file special_tokens_map.json
-2025-02-14 04:23:52,674 - tokenization_utils_base.py:2287 - from_pretrained - INFO - loading file tokenizer_config.json
-2025-02-14 04:23:53,030 - tokenization_utils_base.py:2533 - _from_pretrained - INFO - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
-2025-02-14 04:23:53,702 - configuration_utils.py:733 - _get_config_dict - INFO - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--google--siglip-so400m-patch14-384/snapshots/9fdffc58afc957d1a03a25b10dba0329ab15c2a3/config.json
-2025-02-14 04:23:53,704 - configuration_utils.py:800 - from_dict - INFO - Model config SiglipVisionConfig {
-  "attention_dropout": 0.0,
-  "hidden_act": "gelu_pytorch_tanh",
-  "hidden_size": 1152,
-  "image_size": 384,
-  "intermediate_size": 4304,
-  "layer_norm_eps": 1e-06,
-  "model_type": "siglip_vision_model",
-  "num_attention_heads": 16,
-  "num_channels": 3,
-  "num_hidden_layers": 27,
-  "patch_size": 14,
-  "transformers_version": "4.43.1"
-}
-
-2025-02-14 04:23:53,704 - modeling_utils.py:3621 - from_pretrained - INFO - loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--google--siglip-so400m-patch14-384/snapshots/9fdffc58afc957d1a03a25b10dba0329ab15c2a3/model.safetensors
-2025-02-14 04:23:53,969 - modeling_utils.py:4440 - _load_pretrained_model - INFO - Some weights of the model checkpoint at google/siglip-so400m-patch14-384 were not used when initializing SiglipVisionModel: ['logit_bias', 'logit_scale', 'text_model.embeddings.position_embedding.weight', 'text_model.embeddings.token_embedding.weight', 'text_model.encoder.layers.0.layer_norm1.bias', 'text_model.encoder.layers.0.layer_norm1.weight', 'text_model.encoder.layers.0.layer_norm2.bias', 'text_model.encoder.layers.0.layer_norm2.weight', 'text_model.encoder.layers.0.mlp.fc1.bias', 'text_model.encoder.layers.0.mlp.fc1.weight', 'text_model.encoder.layers.0.mlp.fc2.bias', 'text_model.encoder.layers.0.mlp.fc2.weight', 'text_model.encoder.layers.0.self_attn.k_proj.bias', 'text_model.encoder.layers.0.self_attn.k_proj.weight', 'text_model.encoder.layers.0.self_attn.out_proj.bias', 'text_model.encoder.layers.0.self_attn.out_proj.weight', 'text_model.encoder.layers.0.self_attn.q_proj.bias', 'text_model.encoder.layers.0.self_attn.q_proj.weight', 'text_model.encoder.layers.0.self_attn.v_proj.bias', 'text_model.encoder.layers.0.self_attn.v_proj.weight', 'text_model.encoder.layers.1.layer_norm1.bias', 'text_model.encoder.layers.1.layer_norm1.weight', 'text_model.encoder.layers.1.layer_norm2.bias', 'text_model.encoder.layers.1.layer_norm2.weight', 'text_model.encoder.layers.1.mlp.fc1.bias', 'text_model.encoder.layers.1.mlp.fc1.weight', 'text_model.encoder.layers.1.mlp.fc2.bias', 'text_model.encoder.layers.1.mlp.fc2.weight', 'text_model.encoder.layers.1.self_attn.k_proj.bias', 'text_model.encoder.layers.1.self_attn.k_proj.weight', 'text_model.encoder.layers.1.self_attn.out_proj.bias', 'text_model.encoder.layers.1.self_attn.out_proj.weight', 'text_model.encoder.layers.1.self_attn.q_proj.bias', 'text_model.encoder.layers.1.self_attn.q_proj.weight', 'text_model.encoder.layers.1.self_attn.v_proj.bias', 'text_model.encoder.layers.1.self_attn.v_proj.weight', 'text_model.encoder.layers.10.layer_norm1.bias', 'text_model.encoder.layers.10.layer_norm1.weight', 'text_model.encoder.layers.10.layer_norm2.bias', 'text_model.encoder.layers.10.layer_norm2.weight', 'text_model.encoder.layers.10.mlp.fc1.bias', 'text_model.encoder.layers.10.mlp.fc1.weight', 'text_model.encoder.layers.10.mlp.fc2.bias', 'text_model.encoder.layers.10.mlp.fc2.weight', 'text_model.encoder.layers.10.self_attn.k_proj.bias', 'text_model.encoder.layers.10.self_attn.k_proj.weight', 'text_model.encoder.layers.10.self_attn.out_proj.bias', 'text_model.encoder.layers.10.self_attn.out_proj.weight', 'text_model.encoder.layers.10.self_attn.q_proj.bias', 'text_model.encoder.layers.10.self_attn.q_proj.weight', 'text_model.encoder.layers.10.self_attn.v_proj.bias', 'text_model.encoder.layers.10.self_attn.v_proj.weight', 'text_model.encoder.layers.11.layer_norm1.bias', 'text_model.encoder.layers.11.layer_norm1.weight', 'text_model.encoder.layers.11.layer_norm2.bias', 'text_model.encoder.layers.11.layer_norm2.weight', 'text_model.encoder.layers.11.mlp.fc1.bias', 'text_model.encoder.layers.11.mlp.fc1.weight', 'text_model.encoder.layers.11.mlp.fc2.bias', 'text_model.encoder.layers.11.mlp.fc2.weight', 'text_model.encoder.layers.11.self_attn.k_proj.bias', 'text_model.encoder.layers.11.self_attn.k_proj.weight', 'text_model.encoder.layers.11.self_attn.out_proj.bias', 'text_model.encoder.layers.11.self_attn.out_proj.weight', 'text_model.encoder.layers.11.self_attn.q_proj.bias', 'text_model.encoder.layers.11.self_attn.q_proj.weight', 'text_model.encoder.layers.11.self_attn.v_proj.bias', 'text_model.encoder.layers.11.self_attn.v_proj.weight', 'text_model.encoder.layers.12.layer_norm1.bias', 'text_model.encoder.layers.12.layer_norm1.weight', 'text_model.encoder.layers.12.layer_norm2.bias', 'text_model.encoder.layers.12.layer_norm2.weight', 'text_model.encoder.layers.12.mlp.fc1.bias', 'text_model.encoder.layers.12.mlp.fc1.weight', 'text_model.encoder.layers.12.mlp.fc2.bias', 'text_model.encoder.layers.12.mlp.fc2.weight', 'text_model.encoder.layers.12.self_attn.k_proj.bias', 'text_model.encoder.layers.12.self_attn.k_proj.weight', 'text_model.encoder.layers.12.self_attn.out_proj.bias', 'text_model.encoder.layers.12.self_attn.out_proj.weight', 'text_model.encoder.layers.12.self_attn.q_proj.bias', 'text_model.encoder.layers.12.self_attn.q_proj.weight', 'text_model.encoder.layers.12.self_attn.v_proj.bias', 'text_model.encoder.layers.12.self_attn.v_proj.weight', 'text_model.encoder.layers.13.layer_norm1.bias', 'text_model.encoder.layers.13.layer_norm1.weight', 'text_model.encoder.layers.13.layer_norm2.bias', 'text_model.encoder.layers.13.layer_norm2.weight', 'text_model.encoder.layers.13.mlp.fc1.bias', 'text_model.encoder.layers.13.mlp.fc1.weight', 'text_model.encoder.layers.13.mlp.fc2.bias', 'text_model.encoder.layers.13.mlp.fc2.weight', 'text_model.encoder.layers.13.self_attn.k_proj.bias', 'text_model.encoder.layers.13.self_attn.k_proj.weight', 'text_model.encoder.layers.13.self_attn.out_proj.bias', 'text_model.encoder.layers.13.self_attn.out_proj.weight', 'text_model.encoder.layers.13.self_attn.q_proj.bias', 'text_model.encoder.layers.13.self_attn.q_proj.weight', 'text_model.encoder.layers.13.self_attn.v_proj.bias', 'text_model.encoder.layers.13.self_attn.v_proj.weight', 'text_model.encoder.layers.14.layer_norm1.bias', 'text_model.encoder.layers.14.layer_norm1.weight', 'text_model.encoder.layers.14.layer_norm2.bias', 'text_model.encoder.layers.14.layer_norm2.weight', 'text_model.encoder.layers.14.mlp.fc1.bias', 'text_model.encoder.layers.14.mlp.fc1.weight', 'text_model.encoder.layers.14.mlp.fc2.bias', 'text_model.encoder.layers.14.mlp.fc2.weight', 'text_model.encoder.layers.14.self_attn.k_proj.bias', 'text_model.encoder.layers.14.self_attn.k_proj.weight', 'text_model.encoder.layers.14.self_attn.out_proj.bias', 'text_model.encoder.layers.14.self_attn.out_proj.weight', 'text_model.encoder.layers.14.self_attn.q_proj.bias', 'text_model.encoder.layers.14.self_attn.q_proj.weight', 'text_model.encoder.layers.14.self_attn.v_proj.bias', 'text_model.encoder.layers.14.self_attn.v_proj.weight', 'text_model.encoder.layers.15.layer_norm1.bias', 'text_model.encoder.layers.15.layer_norm1.weight', 'text_model.encoder.layers.15.layer_norm2.bias', 'text_model.encoder.layers.15.layer_norm2.weight', 'text_model.encoder.layers.15.mlp.fc1.bias', 'text_model.encoder.layers.15.mlp.fc1.weight', 'text_model.encoder.layers.15.mlp.fc2.bias', 'text_model.encoder.layers.15.mlp.fc2.weight', 'text_model.encoder.layers.15.self_attn.k_proj.bias', 'text_model.encoder.layers.15.self_attn.k_proj.weight', 'text_model.encoder.layers.15.self_attn.out_proj.bias', 'text_model.encoder.layers.15.self_attn.out_proj.weight', 'text_model.encoder.layers.15.self_attn.q_proj.bias', 'text_model.encoder.layers.15.self_attn.q_proj.weight', 'text_model.encoder.layers.15.self_attn.v_proj.bias', 'text_model.encoder.layers.15.self_attn.v_proj.weight', 'text_model.encoder.layers.16.layer_norm1.bias', 'text_model.encoder.layers.16.layer_norm1.weight', 'text_model.encoder.layers.16.layer_norm2.bias', 'text_model.encoder.layers.16.layer_norm2.weight', 'text_model.encoder.layers.16.mlp.fc1.bias', 'text_model.encoder.layers.16.mlp.fc1.weight', 'text_model.encoder.layers.16.mlp.fc2.bias', 'text_model.encoder.layers.16.mlp.fc2.weight', 'text_model.encoder.layers.16.self_attn.k_proj.bias', 'text_model.encoder.layers.16.self_attn.k_proj.weight', 'text_model.encoder.layers.16.self_attn.out_proj.bias', 'text_model.encoder.layers.16.self_attn.out_proj.weight', 'text_model.encoder.layers.16.self_attn.q_proj.bias', 'text_model.encoder.layers.16.self_attn.q_proj.weight', 'text_model.encoder.layers.16.self_attn.v_proj.bias', 'text_model.encoder.layers.16.self_attn.v_proj.weight', 'text_model.encoder.layers.17.layer_norm1.bias', 'text_model.encoder.layers.17.layer_norm1.weight', 'text_model.encoder.layers.17.layer_norm2.bias', 'text_model.encoder.layers.17.layer_norm2.weight', 'text_model.encoder.layers.17.mlp.fc1.bias', 'text_model.encoder.layers.17.mlp.fc1.weight', 'text_model.encoder.layers.17.mlp.fc2.bias', 'text_model.encoder.layers.17.mlp.fc2.weight', 'text_model.encoder.layers.17.self_attn.k_proj.bias', 'text_model.encoder.layers.17.self_attn.k_proj.weight', 'text_model.encoder.layers.17.self_attn.out_proj.bias', 'text_model.encoder.layers.17.self_attn.out_proj.weight', 'text_model.encoder.layers.17.self_attn.q_proj.bias', 'text_model.encoder.layers.17.self_attn.q_proj.weight', 'text_model.encoder.layers.17.self_attn.v_proj.bias', 'text_model.encoder.layers.17.self_attn.v_proj.weight', 'text_model.encoder.layers.18.layer_norm1.bias', 'text_model.encoder.layers.18.layer_norm1.weight', 'text_model.encoder.layers.18.layer_norm2.bias', 'text_model.encoder.layers.18.layer_norm2.weight', 'text_model.encoder.layers.18.mlp.fc1.bias', 'text_model.encoder.layers.18.mlp.fc1.weight', 'text_model.encoder.layers.18.mlp.fc2.bias', 'text_model.encoder.layers.18.mlp.fc2.weight', 'text_model.encoder.layers.18.self_attn.k_proj.bias', 'text_model.encoder.layers.18.self_attn.k_proj.weight', 'text_model.encoder.layers.18.self_attn.out_proj.bias', 'text_model.encoder.layers.18.self_attn.out_proj.weight', 'text_model.encoder.layers.18.self_attn.q_proj.bias', 'text_model.encoder.layers.18.self_attn.q_proj.weight', 'text_model.encoder.layers.18.self_attn.v_proj.bias', 'text_model.encoder.layers.18.self_attn.v_proj.weight', 'text_model.encoder.layers.19.layer_norm1.bias', 'text_model.encoder.layers.19.layer_norm1.weight', 'text_model.encoder.layers.19.layer_norm2.bias', 'text_model.encoder.layers.19.layer_norm2.weight', 'text_model.encoder.layers.19.mlp.fc1.bias', 'text_model.encoder.layers.19.mlp.fc1.weight', 'text_model.encoder.layers.19.mlp.fc2.bias', 'text_model.encoder.layers.19.mlp.fc2.weight', 'text_model.encoder.layers.19.self_attn.k_proj.bias', 'text_model.encoder.layers.19.self_attn.k_proj.weight', 'text_model.encoder.layers.19.self_attn.out_proj.bias', 'text_model.encoder.layers.19.self_attn.out_proj.weight', 'text_model.encoder.layers.19.self_attn.q_proj.bias', 'text_model.encoder.layers.19.self_attn.q_proj.weight', 'text_model.encoder.layers.19.self_attn.v_proj.bias', 'text_model.encoder.layers.19.self_attn.v_proj.weight', 'text_model.encoder.layers.2.layer_norm1.bias', 'text_model.encoder.layers.2.layer_norm1.weight', 'text_model.encoder.layers.2.layer_norm2.bias', 'text_model.encoder.layers.2.layer_norm2.weight', 'text_model.encoder.layers.2.mlp.fc1.bias', 'text_model.encoder.layers.2.mlp.fc1.weight', 'text_model.encoder.layers.2.mlp.fc2.bias', 'text_model.encoder.layers.2.mlp.fc2.weight', 'text_model.encoder.layers.2.self_attn.k_proj.bias', 'text_model.encoder.layers.2.self_attn.k_proj.weight', 'text_model.encoder.layers.2.self_attn.out_proj.bias', 'text_model.encoder.layers.2.self_attn.out_proj.weight', 'text_model.encoder.layers.2.self_attn.q_proj.bias', 'text_model.encoder.layers.2.self_attn.q_proj.weight', 'text_model.encoder.layers.2.self_attn.v_proj.bias', 'text_model.encoder.layers.2.self_attn.v_proj.weight', 'text_model.encoder.layers.20.layer_norm1.bias', 'text_model.encoder.layers.20.layer_norm1.weight', 'text_model.encoder.layers.20.layer_norm2.bias', 'text_model.encoder.layers.20.layer_norm2.weight', 'text_model.encoder.layers.20.mlp.fc1.bias', 'text_model.encoder.layers.20.mlp.fc1.weight', 'text_model.encoder.layers.20.mlp.fc2.bias', 'text_model.encoder.layers.20.mlp.fc2.weight', 'text_model.encoder.layers.20.self_attn.k_proj.bias', 'text_model.encoder.layers.20.self_attn.k_proj.weight', 'text_model.encoder.layers.20.self_attn.out_proj.bias', 'text_model.encoder.layers.20.self_attn.out_proj.weight', 'text_model.encoder.layers.20.self_attn.q_proj.bias', 'text_model.encoder.layers.20.self_attn.q_proj.weight', 'text_model.encoder.layers.20.self_attn.v_proj.bias', 'text_model.encoder.layers.20.self_attn.v_proj.weight', 'text_model.encoder.layers.21.layer_norm1.bias', 'text_model.encoder.layers.21.layer_norm1.weight', 'text_model.encoder.layers.21.layer_norm2.bias', 'text_model.encoder.layers.21.layer_norm2.weight', 'text_model.encoder.layers.21.mlp.fc1.bias', 'text_model.encoder.layers.21.mlp.fc1.weight', 'text_model.encoder.layers.21.mlp.fc2.bias', 'text_model.encoder.layers.21.mlp.fc2.weight', 'text_model.encoder.layers.21.self_attn.k_proj.bias', 'text_model.encoder.layers.21.self_attn.k_proj.weight', 'text_model.encoder.layers.21.self_attn.out_proj.bias', 'text_model.encoder.layers.21.self_attn.out_proj.weight', 'text_model.encoder.layers.21.self_attn.q_proj.bias', 'text_model.encoder.layers.21.self_attn.q_proj.weight', 'text_model.encoder.layers.21.self_attn.v_proj.bias', 'text_model.encoder.layers.21.self_attn.v_proj.weight', 'text_model.encoder.layers.22.layer_norm1.bias', 'text_model.encoder.layers.22.layer_norm1.weight', 'text_model.encoder.layers.22.layer_norm2.bias', 'text_model.encoder.layers.22.layer_norm2.weight', 'text_model.encoder.layers.22.mlp.fc1.bias', 'text_model.encoder.layers.22.mlp.fc1.weight', 'text_model.encoder.layers.22.mlp.fc2.bias', 'text_model.encoder.layers.22.mlp.fc2.weight', 'text_model.encoder.layers.22.self_attn.k_proj.bias', 'text_model.encoder.layers.22.self_attn.k_proj.weight', 'text_model.encoder.layers.22.self_attn.out_proj.bias', 'text_model.encoder.layers.22.self_attn.out_proj.weight', 'text_model.encoder.layers.22.self_attn.q_proj.bias', 'text_model.encoder.layers.22.self_attn.q_proj.weight', 'text_model.encoder.layers.22.self_attn.v_proj.bias', 'text_model.encoder.layers.22.self_attn.v_proj.weight', 'text_model.encoder.layers.23.layer_norm1.bias', 'text_model.encoder.layers.23.layer_norm1.weight', 'text_model.encoder.layers.23.layer_norm2.bias', 'text_model.encoder.layers.23.layer_norm2.weight', 'text_model.encoder.layers.23.mlp.fc1.bias', 'text_model.encoder.layers.23.mlp.fc1.weight', 'text_model.encoder.layers.23.mlp.fc2.bias', 'text_model.encoder.layers.23.mlp.fc2.weight', 'text_model.encoder.layers.23.self_attn.k_proj.bias', 'text_model.encoder.layers.23.self_attn.k_proj.weight', 'text_model.encoder.layers.23.self_attn.out_proj.bias', 'text_model.encoder.layers.23.self_attn.out_proj.weight', 'text_model.encoder.layers.23.self_attn.q_proj.bias', 'text_model.encoder.layers.23.self_attn.q_proj.weight', 'text_model.encoder.layers.23.self_attn.v_proj.bias', 'text_model.encoder.layers.23.self_attn.v_proj.weight', 'text_model.encoder.layers.24.layer_norm1.bias', 'text_model.encoder.layers.24.layer_norm1.weight', 'text_model.encoder.layers.24.layer_norm2.bias', 'text_model.encoder.layers.24.layer_norm2.weight', 'text_model.encoder.layers.24.mlp.fc1.bias', 'text_model.encoder.layers.24.mlp.fc1.weight', 'text_model.encoder.layers.24.mlp.fc2.bias', 'text_model.encoder.layers.24.mlp.fc2.weight', 'text_model.encoder.layers.24.self_attn.k_proj.bias', 'text_model.encoder.layers.24.self_attn.k_proj.weight', 'text_model.encoder.layers.24.self_attn.out_proj.bias', 'text_model.encoder.layers.24.self_attn.out_proj.weight', 'text_model.encoder.layers.24.self_attn.q_proj.bias', 'text_model.encoder.layers.24.self_attn.q_proj.weight', 'text_model.encoder.layers.24.self_attn.v_proj.bias', 'text_model.encoder.layers.24.self_attn.v_proj.weight', 'text_model.encoder.layers.25.layer_norm1.bias', 'text_model.encoder.layers.25.layer_norm1.weight', 'text_model.encoder.layers.25.layer_norm2.bias', 'text_model.encoder.layers.25.layer_norm2.weight', 'text_model.encoder.layers.25.mlp.fc1.bias', 'text_model.encoder.layers.25.mlp.fc1.weight', 'text_model.encoder.layers.25.mlp.fc2.bias', 'text_model.encoder.layers.25.mlp.fc2.weight', 'text_model.encoder.layers.25.self_attn.k_proj.bias', 'text_model.encoder.layers.25.self_attn.k_proj.weight', 'text_model.encoder.layers.25.self_attn.out_proj.bias', 'text_model.encoder.layers.25.self_attn.out_proj.weight', 'text_model.encoder.layers.25.self_attn.q_proj.bias', 'text_model.encoder.layers.25.self_attn.q_proj.weight', 'text_model.encoder.layers.25.self_attn.v_proj.bias', 'text_model.encoder.layers.25.self_attn.v_proj.weight', 'text_model.encoder.layers.26.layer_norm1.bias', 'text_model.encoder.layers.26.layer_norm1.weight', 'text_model.encoder.layers.26.layer_norm2.bias', 'text_model.encoder.layers.26.layer_norm2.weight', 'text_model.encoder.layers.26.mlp.fc1.bias', 'text_model.encoder.layers.26.mlp.fc1.weight', 'text_model.encoder.layers.26.mlp.fc2.bias', 'text_model.encoder.layers.26.mlp.fc2.weight', 'text_model.encoder.layers.26.self_attn.k_proj.bias', 'text_model.encoder.layers.26.self_attn.k_proj.weight', 'text_model.encoder.layers.26.self_attn.out_proj.bias', 'text_model.encoder.layers.26.self_attn.out_proj.weight', 'text_model.encoder.layers.26.self_attn.q_proj.bias', 'text_model.encoder.layers.26.self_attn.q_proj.weight', 'text_model.encoder.layers.26.self_attn.v_proj.bias', 'text_model.encoder.layers.26.self_attn.v_proj.weight', 'text_model.encoder.layers.3.layer_norm1.bias', 'text_model.encoder.layers.3.layer_norm1.weight', 'text_model.encoder.layers.3.layer_norm2.bias', 'text_model.encoder.layers.3.layer_norm2.weight', 'text_model.encoder.layers.3.mlp.fc1.bias', 'text_model.encoder.layers.3.mlp.fc1.weight', 'text_model.encoder.layers.3.mlp.fc2.bias', 'text_model.encoder.layers.3.mlp.fc2.weight', 'text_model.encoder.layers.3.self_attn.k_proj.bias', 'text_model.encoder.layers.3.self_attn.k_proj.weight', 'text_model.encoder.layers.3.self_attn.out_proj.bias', 'text_model.encoder.layers.3.self_attn.out_proj.weight', 'text_model.encoder.layers.3.self_attn.q_proj.bias', 'text_model.encoder.layers.3.self_attn.q_proj.weight', 'text_model.encoder.layers.3.self_attn.v_proj.bias', 'text_model.encoder.layers.3.self_attn.v_proj.weight', 'text_model.encoder.layers.4.layer_norm1.bias', 'text_model.encoder.layers.4.layer_norm1.weight', 'text_model.encoder.layers.4.layer_norm2.bias', 'text_model.encoder.layers.4.layer_norm2.weight', 'text_model.encoder.layers.4.mlp.fc1.bias', 'text_model.encoder.layers.4.mlp.fc1.weight', 'text_model.encoder.layers.4.mlp.fc2.bias', 'text_model.encoder.layers.4.mlp.fc2.weight', 'text_model.encoder.layers.4.self_attn.k_proj.bias', 'text_model.encoder.layers.4.self_attn.k_proj.weight', 'text_model.encoder.layers.4.self_attn.out_proj.bias', 'text_model.encoder.layers.4.self_attn.out_proj.weight', 'text_model.encoder.layers.4.self_attn.q_proj.bias', 'text_model.encoder.layers.4.self_attn.q_proj.weight', 'text_model.encoder.layers.4.self_attn.v_proj.bias', 'text_model.encoder.layers.4.self_attn.v_proj.weight', 'text_model.encoder.layers.5.layer_norm1.bias', 'text_model.encoder.layers.5.layer_norm1.weight', 'text_model.encoder.layers.5.layer_norm2.bias', 'text_model.encoder.layers.5.layer_norm2.weight', 'text_model.encoder.layers.5.mlp.fc1.bias', 'text_model.encoder.layers.5.mlp.fc1.weight', 'text_model.encoder.layers.5.mlp.fc2.bias', 'text_model.encoder.layers.5.mlp.fc2.weight', 'text_model.encoder.layers.5.self_attn.k_proj.bias', 'text_model.encoder.layers.5.self_attn.k_proj.weight', 'text_model.encoder.layers.5.self_attn.out_proj.bias', 'text_model.encoder.layers.5.self_attn.out_proj.weight', 'text_model.encoder.layers.5.self_attn.q_proj.bias', 'text_model.encoder.layers.5.self_attn.q_proj.weight', 'text_model.encoder.layers.5.self_attn.v_proj.bias', 'text_model.encoder.layers.5.self_attn.v_proj.weight', 'text_model.encoder.layers.6.layer_norm1.bias', 'text_model.encoder.layers.6.layer_norm1.weight', 'text_model.encoder.layers.6.layer_norm2.bias', 'text_model.encoder.layers.6.layer_norm2.weight', 'text_model.encoder.layers.6.mlp.fc1.bias', 'text_model.encoder.layers.6.mlp.fc1.weight', 'text_model.encoder.layers.6.mlp.fc2.bias', 'text_model.encoder.layers.6.mlp.fc2.weight', 'text_model.encoder.layers.6.self_attn.k_proj.bias', 'text_model.encoder.layers.6.self_attn.k_proj.weight', 'text_model.encoder.layers.6.self_attn.out_proj.bias', 'text_model.encoder.layers.6.self_attn.out_proj.weight', 'text_model.encoder.layers.6.self_attn.q_proj.bias', 'text_model.encoder.layers.6.self_attn.q_proj.weight', 'text_model.encoder.layers.6.self_attn.v_proj.bias', 'text_model.encoder.layers.6.self_attn.v_proj.weight', 'text_model.encoder.layers.7.layer_norm1.bias', 'text_model.encoder.layers.7.layer_norm1.weight', 'text_model.encoder.layers.7.layer_norm2.bias', 'text_model.encoder.layers.7.layer_norm2.weight', 'text_model.encoder.layers.7.mlp.fc1.bias', 'text_model.encoder.layers.7.mlp.fc1.weight', 'text_model.encoder.layers.7.mlp.fc2.bias', 'text_model.encoder.layers.7.mlp.fc2.weight', 'text_model.encoder.layers.7.self_attn.k_proj.bias', 'text_model.encoder.layers.7.self_attn.k_proj.weight', 'text_model.encoder.layers.7.self_attn.out_proj.bias', 'text_model.encoder.layers.7.self_attn.out_proj.weight', 'text_model.encoder.layers.7.self_attn.q_proj.bias', 'text_model.encoder.layers.7.self_attn.q_proj.weight', 'text_model.encoder.layers.7.self_attn.v_proj.bias', 'text_model.encoder.layers.7.self_attn.v_proj.weight', 'text_model.encoder.layers.8.layer_norm1.bias', 'text_model.encoder.layers.8.layer_norm1.weight', 'text_model.encoder.layers.8.layer_norm2.bias', 'text_model.encoder.layers.8.layer_norm2.weight', 'text_model.encoder.layers.8.mlp.fc1.bias', 'text_model.encoder.layers.8.mlp.fc1.weight', 'text_model.encoder.layers.8.mlp.fc2.bias', 'text_model.encoder.layers.8.mlp.fc2.weight', 'text_model.encoder.layers.8.self_attn.k_proj.bias', 'text_model.encoder.layers.8.self_attn.k_proj.weight', 'text_model.encoder.layers.8.self_attn.out_proj.bias', 'text_model.encoder.layers.8.self_attn.out_proj.weight', 'text_model.encoder.layers.8.self_attn.q_proj.bias', 'text_model.encoder.layers.8.self_attn.q_proj.weight', 'text_model.encoder.layers.8.self_attn.v_proj.bias', 'text_model.encoder.layers.8.self_attn.v_proj.weight', 'text_model.encoder.layers.9.layer_norm1.bias', 'text_model.encoder.layers.9.layer_norm1.weight', 'text_model.encoder.layers.9.layer_norm2.bias', 'text_model.encoder.layers.9.layer_norm2.weight', 'text_model.encoder.layers.9.mlp.fc1.bias', 'text_model.encoder.layers.9.mlp.fc1.weight', 'text_model.encoder.layers.9.mlp.fc2.bias', 'text_model.encoder.layers.9.mlp.fc2.weight', 'text_model.encoder.layers.9.self_attn.k_proj.bias', 'text_model.encoder.layers.9.self_attn.k_proj.weight', 'text_model.encoder.layers.9.self_attn.out_proj.bias', 'text_model.encoder.layers.9.self_attn.out_proj.weight', 'text_model.encoder.layers.9.self_attn.q_proj.bias', 'text_model.encoder.layers.9.self_attn.q_proj.weight', 'text_model.encoder.layers.9.self_attn.v_proj.bias', 'text_model.encoder.layers.9.self_attn.v_proj.weight', 'text_model.final_layer_norm.bias', 'text_model.final_layer_norm.weight', 'text_model.head.bias', 'text_model.head.weight']
-- This IS expected if you are initializing SiglipVisionModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
-- This IS NOT expected if you are initializing SiglipVisionModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
-2025-02-14 04:23:53,971 - modeling_utils.py:4458 - _load_pretrained_model - INFO - All the weights of SiglipVisionModel were initialized from the model checkpoint at google/siglip-so400m-patch14-384.
-If your task is similar to the task the model of the checkpoint was trained on, you can already use SiglipVisionModel for predictions without further training.
-2025-02-14 04:23:54,163 - image_processing_base.py:375 - get_image_processor_dict - INFO - loading configuration file preprocessor_config.json from cache at /root/.cache/huggingface/hub/models--google--siglip-so400m-patch14-384/snapshots/9fdffc58afc957d1a03a25b10dba0329ab15c2a3/preprocessor_config.json
-2025-02-14 04:23:54,164 - image_processing_base.py:429 - from_dict - INFO - Image processor SiglipImageProcessor {
-  "do_convert_rgb": null,
-  "do_normalize": true,
-  "do_rescale": true,
-  "do_resize": true,
-  "image_mean": [
-    0.5,
-    0.5,
-    0.5
-  ],
-  "image_processor_type": "SiglipImageProcessor",
-  "image_std": [
-    0.5,
-    0.5,
-    0.5
-  ],
-  "processor_class": "SiglipProcessor",
-  "resample": 3,
-  "rescale_factor": 0.00392156862745098,
-  "size": {
-    "height": 384,
-    "width": 384
-  }
-}
-
-2025-02-14 04:23:54,834 - configuration_utils.py:733 - _get_config_dict - INFO - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--facebook--dinov2-giant/snapshots/611a9d42f2335e0f921f1e313ad3c1b7178d206d/config.json
-2025-02-14 04:23:54,837 - configuration_utils.py:800 - from_dict - INFO - Model config Dinov2Config {
-  "apply_layernorm": true,
-  "architectures": [
-    "Dinov2Model"
-  ],
-  "attention_probs_dropout_prob": 0.0,
-  "drop_path_rate": 0.0,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.0,
-  "hidden_size": 1536,
-  "image_size": 518,
-  "initializer_range": 0.02,
-  "layer_norm_eps": 1e-06,
-  "layerscale_value": 1.0,
-  "mlp_ratio": 4,
-  "model_type": "dinov2",
-  "num_attention_heads": 24,
-  "num_channels": 3,
-  "num_hidden_layers": 40,
-  "out_features": [
-    "stage40"
-  ],
-  "out_indices": [
-    40
-  ],
-  "patch_size": 14,
-  "qkv_bias": true,
-  "reshape_hidden_states": true,
-  "stage_names": [
-    "stem",
-    "stage1",
-    "stage2",
-    "stage3",
-    "stage4",
-    "stage5",
-    "stage6",
-    "stage7",
-    "stage8",
-    "stage9",
-    "stage10",
-    "stage11",
-    "stage12",
-    "stage13",
-    "stage14",
-    "stage15",
-    "stage16",
-    "stage17",
-    "stage18",
-    "stage19",
-    "stage20",
-    "stage21",
-    "stage22",
-    "stage23",
-    "stage24",
-    "stage25",
-    "stage26",
-    "stage27",
-    "stage28",
-    "stage29",
-    "stage30",
-    "stage31",
-    "stage32",
-    "stage33",
-    "stage34",
-    "stage35",
-    "stage36",
-    "stage37",
-    "stage38",
-    "stage39",
-    "stage40"
-  ],
-  "torch_dtype": "float32",
-  "transformers_version": "4.43.1",
-  "use_swiglu_ffn": true
-}
-
-2025-02-14 04:23:54,838 - modeling_utils.py:3621 - from_pretrained - INFO - loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--facebook--dinov2-giant/snapshots/611a9d42f2335e0f921f1e313ad3c1b7178d206d/model.safetensors
-2025-02-14 04:23:55,363 - modeling_utils.py:4450 - _load_pretrained_model - INFO - All model checkpoint weights were used when initializing Dinov2Model.
-
-2025-02-14 04:23:55,364 - modeling_utils.py:4458 - _load_pretrained_model - INFO - All the weights of Dinov2Model were initialized from the model checkpoint at facebook/dinov2-giant.
-If your task is similar to the task the model of the checkpoint was trained on, you can already use Dinov2Model for predictions without further training.
-2025-02-14 04:23:55,551 - image_processing_base.py:375 - get_image_processor_dict - INFO - loading configuration file preprocessor_config.json from cache at /root/.cache/huggingface/hub/models--facebook--dinov2-giant/snapshots/611a9d42f2335e0f921f1e313ad3c1b7178d206d/preprocessor_config.json
-2025-02-14 04:23:55,554 - image_processing_base.py:429 - from_dict - INFO - Image processor BitImageProcessor {
-  "crop_size": {
-    "height": 378,
-    "width": 378
-  },
-  "do_center_crop": true,
-  "do_convert_rgb": true,
-  "do_normalize": true,
-  "do_rescale": true,
-  "do_resize": true,
-  "image_mean": [
-    0.485,
-    0.456,
-    0.406
-  ],
-  "image_processor_type": "BitImageProcessor",
-  "image_std": [
-    0.229,
-    0.224,
-    0.225
-  ],
-  "resample": 3,
-  "rescale_factor": 0.00392156862745098,
-  "size": {
-    "shortest_edge": 378
-  }
-}
-
-2025-02-14 04:23:56,625 - finetune_llama.py:1239 - train - INFO - Total params: 3264865280
-2025-02-14 04:23:56,625 - finetune_llama.py:1240 - train - INFO - Trainable params: 12589056
-2025-02-14 04:23:56,625 - finetune_llama.py:1241 - train - INFO - LM head params: 394002432
-2025-02-14 04:23:57,952 - trainer_callback.py:423 - add_callback - WARNING - You are adding a <class 'transformers.integrations.integration_utils.TensorBoardCallback'> to the callbacks of this Trainer, but there is already one. The currentlist of callbacks is
-:DefaultFlowCallback
-TensorBoardCallback
-2025-02-14 04:23:57,952 - trainer.py:648 - __init__ - INFO - Using auto half precision backend
-2025-02-14 04:24:00,013 - trainer.py:2134 - _inner_training_loop - INFO - ***** Running training *****
-2025-02-14 04:24:00,013 - trainer.py:2135 - _inner_training_loop - INFO -   Num examples = 554
-2025-02-14 04:24:00,013 - trainer.py:2136 - _inner_training_loop - INFO -   Num Epochs = 2
-2025-02-14 04:24:00,013 - trainer.py:2137 - _inner_training_loop - INFO -   Instantaneous batch size per device = 1
-2025-02-14 04:24:00,013 - trainer.py:2140 - _inner_training_loop - INFO -   Total train batch size (w. parallel, distributed & accumulation) = 1
-2025-02-14 04:24:00,013 - trainer.py:2141 - _inner_training_loop - INFO -   Gradient Accumulation steps = 1
-2025-02-14 04:24:00,013 - trainer.py:2142 - _inner_training_loop - INFO -   Total optimization steps = 1,108
-2025-02-14 04:24:00,015 - trainer.py:2143 - _inner_training_loop - INFO -   Number of trainable parameters = 406,591,488
-2025-02-14 04:24:26,002 - resource_logging.py:42 - debug_tensor - DEBUG - File: Unknown, Line: Unknown
-2025-02-14 04:24:26,003 - resource_logging.py:45 - debug_tensor - DEBUG - In compute_loss(): inputs['labels']: [torch.Size([1, 8192]), torch.int64, cuda:0]
-2025-02-14 04:24:26,038 - mm_trainer.py:618 - compute_loss - DEBUG - In compute_loss(): assistant token at position 224
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c214f7ce3a6683296aa31dd99ef51f5692f03033e916f7973d03b3cb7b3484d
+size 37176

runtime_logs/run_2025-02-14_04-25-33.log

@@ -1,378 +1,3 @@
-2025-02-14 04:25:33,522 - training_args.py:2100 - _setup_devices - INFO - PyTorch: setting up devices
-2025-02-14 04:25:34,088 - configuration_utils.py:731 - _get_config_dict - INFO - loading configuration file ./checkpoints/longvu_llama3_2/config.json
-2025-02-14 04:25:34,092 - configuration_utils.py:800 - from_dict - INFO - Model config CambrianConfig {
-  "_name_or_path": "/tmp/iopath_cache/manifold_cache/tree/users/shenx/finetune/09281004-cambrian_llama3_2_t576_ov",
-  "architectures": [
-    "CambrianLlamaForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "bos_token_id": 128000,
-  "connect_layer": 2,
-  "connector_depth": 3,
-  "connector_only": true,
-  "dino_threshold": 0.83,
-  "drop_threshold": 0.8,
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
-  "frame_pos": false,
-  "freeze_mm_mlp_adapter": false,
-  "hidden_act": "silu",
-  "hidden_size": 3072,
-  "highres": true,
-  "highres_connect": false,
-  "image_aspect_ratio": "pad",
-  "image_position": 91,
-  "image_token_len": 144,
-  "initializer_range": 0.02,
-  "intermediate_size": 8192,
-  "is_image_newline": true,
-  "is_st_sampler": false,
-  "lowres_token": 8,
-  "max_position_embeddings": 131072,
-  "mlp_bias": false,
-  "mm_patch_merge_type": "flat",
-  "mm_projector_lr": null,
-  "mm_projector_type": "sva",
-  "mm_use_im_patch_token": false,
-  "mm_use_im_start_end": false,
-  "mm_vision_sampler_lr": null,
-  "mm_vision_select_feature": "patch",
-  "mm_vision_select_layer": -2,
-  "mm_vision_tower_aux_list": [
-    "siglip/CLIP-ViT-SO400M-14-384",
-    "facebook/dinov2-giant-res378"
-  ],
-  "mm_vision_tower_aux_token_len_list": [
-    576,
-    576
-  ],
-  "mm_vision_tower_lr": null,
-  "model_type": "cambrian_llama",
-  "num_attention_heads": 24,
-  "num_hidden_layers": 28,
-  "num_key_value_heads": 8,
-  "num_of_vision_sampler_layers": 10,
-  "num_query_group": 1,
-  "pretraining_tp": 1,
-  "query_num_list": [
-    144
-  ],
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": {
-    "factor": 32.0,
-    "high_freq_factor": 4.0,
-    "low_freq_factor": 1.0,
-    "original_max_position_embeddings": 8192,
-    "rope_type": "llama3"
-  },
-  "rope_theta": 500000.0,
-  "spmd_debug": null,
-  "spmd_fsdp_sharding": null,
-  "spmd_mesh": null,
-  "start_of_vision_sampler_layers": 0,
-  "stride_of_vision_sampler_layers": 3,
-  "tie_word_embeddings": false,
-  "tokenizer_model_max_length": 8192,
-  "tokenizer_padding_side": "right",
-  "torch_dtype": "float32",
-  "transformers_version": "4.43.1",
-  "tune_mm_mlp_adapter": false,
-  "unfreeze_mm_vision_tower": false,
-  "use_cache": false,
-  "use_mm_proj": true,
-  "vision_hidden_size": 1024,
-  "vision_tower_aux_token_len_list": [
-    576,
-    576
-  ],
-  "vocab_size": 128256
-}
-
-2025-02-14 04:25:34,092 - modeling_utils.py:3618 - from_pretrained - INFO - loading weights file ./checkpoints/longvu_llama3_2/pytorch_model.bin
-2025-02-14 04:25:34,151 - configuration_utils.py:1038 - from_dict - INFO - Generate config GenerationConfig {
-  "bos_token_id": 128000,
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
-  "use_cache": false
-}
-
-2025-02-14 04:25:34,708 - configuration_utils.py:733 - _get_config_dict - INFO - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--facebook--dinov2-giant/snapshots/611a9d42f2335e0f921f1e313ad3c1b7178d206d/config.json
-2025-02-14 04:25:34,712 - configuration_utils.py:800 - from_dict - INFO - Model config Dinov2Config {
-  "apply_layernorm": true,
-  "architectures": [
-    "Dinov2Model"
-  ],
-  "attention_probs_dropout_prob": 0.0,
-  "drop_path_rate": 0.0,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.0,
-  "hidden_size": 1536,
-  "image_size": 518,
-  "initializer_range": 0.02,
-  "layer_norm_eps": 1e-06,
-  "layerscale_value": 1.0,
-  "mlp_ratio": 4,
-  "model_type": "dinov2",
-  "num_attention_heads": 24,
-  "num_channels": 3,
-  "num_hidden_layers": 40,
-  "out_features": [
-    "stage40"
-  ],
-  "out_indices": [
-    40
-  ],
-  "patch_size": 14,
-  "qkv_bias": true,
-  "reshape_hidden_states": true,
-  "stage_names": [
-    "stem",
-    "stage1",
-    "stage2",
-    "stage3",
-    "stage4",
-    "stage5",
-    "stage6",
-    "stage7",
-    "stage8",
-    "stage9",
-    "stage10",
-    "stage11",
-    "stage12",
-    "stage13",
-    "stage14",
-    "stage15",
-    "stage16",
-    "stage17",
-    "stage18",
-    "stage19",
-    "stage20",
-    "stage21",
-    "stage22",
-    "stage23",
-    "stage24",
-    "stage25",
-    "stage26",
-    "stage27",
-    "stage28",
-    "stage29",
-    "stage30",
-    "stage31",
-    "stage32",
-    "stage33",
-    "stage34",
-    "stage35",
-    "stage36",
-    "stage37",
-    "stage38",
-    "stage39",
-    "stage40"
-  ],
-  "torch_dtype": "float32",
-  "transformers_version": "4.43.1",
-  "use_swiglu_ffn": true
-}
-
-2025-02-14 04:25:36,246 - modeling_utils.py:4450 - _load_pretrained_model - INFO - All model checkpoint weights were used when initializing CambrianLlamaForCausalLM.
-
-2025-02-14 04:25:36,247 - modeling_utils.py:4458 - _load_pretrained_model - INFO - All the weights of CambrianLlamaForCausalLM were initialized from the model checkpoint at ./checkpoints/longvu_llama3_2.
-If your task is similar to the task the model of the checkpoint was trained on, you can already use CambrianLlamaForCausalLM for predictions without further training.
-2025-02-14 04:25:36,252 - configuration_utils.py:991 - from_pretrained - INFO - loading configuration file ./checkpoints/longvu_llama3_2/generation_config.json
-2025-02-14 04:25:36,253 - configuration_utils.py:1038 - from_dict - INFO - Generate config GenerationConfig {
-  "bos_token_id": 128000,
-  "do_sample": true,
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
-  "temperature": 0.6,
-  "top_p": 0.9
-}
-
-2025-02-14 04:25:36,601 - tokenization_utils_base.py:2287 - from_pretrained - INFO - loading file tokenizer.json
-2025-02-14 04:25:36,601 - tokenization_utils_base.py:2287 - from_pretrained - INFO - loading file added_tokens.json
-2025-02-14 04:25:36,601 - tokenization_utils_base.py:2287 - from_pretrained - INFO - loading file special_tokens_map.json
-2025-02-14 04:25:36,601 - tokenization_utils_base.py:2287 - from_pretrained - INFO - loading file tokenizer_config.json
-2025-02-14 04:25:37,048 - tokenization_utils_base.py:2533 - _from_pretrained - INFO - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
-2025-02-14 04:25:37,745 - configuration_utils.py:733 - _get_config_dict - INFO - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--google--siglip-so400m-patch14-384/snapshots/9fdffc58afc957d1a03a25b10dba0329ab15c2a3/config.json
-2025-02-14 04:25:37,748 - configuration_utils.py:800 - from_dict - INFO - Model config SiglipVisionConfig {
-  "attention_dropout": 0.0,
-  "hidden_act": "gelu_pytorch_tanh",
-  "hidden_size": 1152,
-  "image_size": 384,
-  "intermediate_size": 4304,
-  "layer_norm_eps": 1e-06,
-  "model_type": "siglip_vision_model",
-  "num_attention_heads": 16,
-  "num_channels": 3,
-  "num_hidden_layers": 27,
-  "patch_size": 14,
-  "transformers_version": "4.43.1"
-}
-
-2025-02-14 04:25:37,749 - modeling_utils.py:3621 - from_pretrained - INFO - loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--google--siglip-so400m-patch14-384/snapshots/9fdffc58afc957d1a03a25b10dba0329ab15c2a3/model.safetensors
-2025-02-14 04:25:38,020 - modeling_utils.py:4440 - _load_pretrained_model - INFO - Some weights of the model checkpoint at google/siglip-so400m-patch14-384 were not used when initializing SiglipVisionModel: ['logit_bias', 'logit_scale', 'text_model.embeddings.position_embedding.weight', 'text_model.embeddings.token_embedding.weight', 'text_model.encoder.layers.0.layer_norm1.bias', 'text_model.encoder.layers.0.layer_norm1.weight', 'text_model.encoder.layers.0.layer_norm2.bias', 'text_model.encoder.layers.0.layer_norm2.weight', 'text_model.encoder.layers.0.mlp.fc1.bias', 'text_model.encoder.layers.0.mlp.fc1.weight', 'text_model.encoder.layers.0.mlp.fc2.bias', 'text_model.encoder.layers.0.mlp.fc2.weight', 'text_model.encoder.layers.0.self_attn.k_proj.bias', 'text_model.encoder.layers.0.self_attn.k_proj.weight', 'text_model.encoder.layers.0.self_attn.out_proj.bias', 'text_model.encoder.layers.0.self_attn.out_proj.weight', 'text_model.encoder.layers.0.self_attn.q_proj.bias', 'text_model.encoder.layers.0.self_attn.q_proj.weight', 'text_model.encoder.layers.0.self_attn.v_proj.bias', 'text_model.encoder.layers.0.self_attn.v_proj.weight', 'text_model.encoder.layers.1.layer_norm1.bias', 'text_model.encoder.layers.1.layer_norm1.weight', 'text_model.encoder.layers.1.layer_norm2.bias', 'text_model.encoder.layers.1.layer_norm2.weight', 'text_model.encoder.layers.1.mlp.fc1.bias', 'text_model.encoder.layers.1.mlp.fc1.weight', 'text_model.encoder.layers.1.mlp.fc2.bias', 'text_model.encoder.layers.1.mlp.fc2.weight', 'text_model.encoder.layers.1.self_attn.k_proj.bias', 'text_model.encoder.layers.1.self_attn.k_proj.weight', 'text_model.encoder.layers.1.self_attn.out_proj.bias', 'text_model.encoder.layers.1.self_attn.out_proj.weight', 'text_model.encoder.layers.1.self_attn.q_proj.bias', 'text_model.encoder.layers.1.self_attn.q_proj.weight', 'text_model.encoder.layers.1.self_attn.v_proj.bias', 'text_model.encoder.layers.1.self_attn.v_proj.weight', 'text_model.encoder.layers.10.layer_norm1.bias', 'text_model.encoder.layers.10.layer_norm1.weight', 'text_model.encoder.layers.10.layer_norm2.bias', 'text_model.encoder.layers.10.layer_norm2.weight', 'text_model.encoder.layers.10.mlp.fc1.bias', 'text_model.encoder.layers.10.mlp.fc1.weight', 'text_model.encoder.layers.10.mlp.fc2.bias', 'text_model.encoder.layers.10.mlp.fc2.weight', 'text_model.encoder.layers.10.self_attn.k_proj.bias', 'text_model.encoder.layers.10.self_attn.k_proj.weight', 'text_model.encoder.layers.10.self_attn.out_proj.bias', 'text_model.encoder.layers.10.self_attn.out_proj.weight', 'text_model.encoder.layers.10.self_attn.q_proj.bias', 'text_model.encoder.layers.10.self_attn.q_proj.weight', 'text_model.encoder.layers.10.self_attn.v_proj.bias', 'text_model.encoder.layers.10.self_attn.v_proj.weight', 'text_model.encoder.layers.11.layer_norm1.bias', 'text_model.encoder.layers.11.layer_norm1.weight', 'text_model.encoder.layers.11.layer_norm2.bias', 'text_model.encoder.layers.11.layer_norm2.weight', 'text_model.encoder.layers.11.mlp.fc1.bias', 'text_model.encoder.layers.11.mlp.fc1.weight', 'text_model.encoder.layers.11.mlp.fc2.bias', 'text_model.encoder.layers.11.mlp.fc2.weight', 'text_model.encoder.layers.11.self_attn.k_proj.bias', 'text_model.encoder.layers.11.self_attn.k_proj.weight', 'text_model.encoder.layers.11.self_attn.out_proj.bias', 'text_model.encoder.layers.11.self_attn.out_proj.weight', 'text_model.encoder.layers.11.self_attn.q_proj.bias', 'text_model.encoder.layers.11.self_attn.q_proj.weight', 'text_model.encoder.layers.11.self_attn.v_proj.bias', 'text_model.encoder.layers.11.self_attn.v_proj.weight', 'text_model.encoder.layers.12.layer_norm1.bias', 'text_model.encoder.layers.12.layer_norm1.weight', 'text_model.encoder.layers.12.layer_norm2.bias', 'text_model.encoder.layers.12.layer_norm2.weight', 'text_model.encoder.layers.12.mlp.fc1.bias', 'text_model.encoder.layers.12.mlp.fc1.weight', 'text_model.encoder.layers.12.mlp.fc2.bias', 'text_model.encoder.layers.12.mlp.fc2.weight', 'text_model.encoder.layers.12.self_attn.k_proj.bias', 'text_model.encoder.layers.12.self_attn.k_proj.weight', 'text_model.encoder.layers.12.self_attn.out_proj.bias', 'text_model.encoder.layers.12.self_attn.out_proj.weight', 'text_model.encoder.layers.12.self_attn.q_proj.bias', 'text_model.encoder.layers.12.self_attn.q_proj.weight', 'text_model.encoder.layers.12.self_attn.v_proj.bias', 'text_model.encoder.layers.12.self_attn.v_proj.weight', 'text_model.encoder.layers.13.layer_norm1.bias', 'text_model.encoder.layers.13.layer_norm1.weight', 'text_model.encoder.layers.13.layer_norm2.bias', 'text_model.encoder.layers.13.layer_norm2.weight', 'text_model.encoder.layers.13.mlp.fc1.bias', 'text_model.encoder.layers.13.mlp.fc1.weight', 'text_model.encoder.layers.13.mlp.fc2.bias', 'text_model.encoder.layers.13.mlp.fc2.weight', 'text_model.encoder.layers.13.self_attn.k_proj.bias', 'text_model.encoder.layers.13.self_attn.k_proj.weight', 'text_model.encoder.layers.13.self_attn.out_proj.bias', 'text_model.encoder.layers.13.self_attn.out_proj.weight', 'text_model.encoder.layers.13.self_attn.q_proj.bias', 'text_model.encoder.layers.13.self_attn.q_proj.weight', 'text_model.encoder.layers.13.self_attn.v_proj.bias', 'text_model.encoder.layers.13.self_attn.v_proj.weight', 'text_model.encoder.layers.14.layer_norm1.bias', 'text_model.encoder.layers.14.layer_norm1.weight', 'text_model.encoder.layers.14.layer_norm2.bias', 'text_model.encoder.layers.14.layer_norm2.weight', 'text_model.encoder.layers.14.mlp.fc1.bias', 'text_model.encoder.layers.14.mlp.fc1.weight', 'text_model.encoder.layers.14.mlp.fc2.bias', 'text_model.encoder.layers.14.mlp.fc2.weight', 'text_model.encoder.layers.14.self_attn.k_proj.bias', 'text_model.encoder.layers.14.self_attn.k_proj.weight', 'text_model.encoder.layers.14.self_attn.out_proj.bias', 'text_model.encoder.layers.14.self_attn.out_proj.weight', 'text_model.encoder.layers.14.self_attn.q_proj.bias', 'text_model.encoder.layers.14.self_attn.q_proj.weight', 'text_model.encoder.layers.14.self_attn.v_proj.bias', 'text_model.encoder.layers.14.self_attn.v_proj.weight', 'text_model.encoder.layers.15.layer_norm1.bias', 'text_model.encoder.layers.15.layer_norm1.weight', 'text_model.encoder.layers.15.layer_norm2.bias', 'text_model.encoder.layers.15.layer_norm2.weight', 'text_model.encoder.layers.15.mlp.fc1.bias', 'text_model.encoder.layers.15.mlp.fc1.weight', 'text_model.encoder.layers.15.mlp.fc2.bias', 'text_model.encoder.layers.15.mlp.fc2.weight', 'text_model.encoder.layers.15.self_attn.k_proj.bias', 'text_model.encoder.layers.15.self_attn.k_proj.weight', 'text_model.encoder.layers.15.self_attn.out_proj.bias', 'text_model.encoder.layers.15.self_attn.out_proj.weight', 'text_model.encoder.layers.15.self_attn.q_proj.bias', 'text_model.encoder.layers.15.self_attn.q_proj.weight', 'text_model.encoder.layers.15.self_attn.v_proj.bias', 'text_model.encoder.layers.15.self_attn.v_proj.weight', 'text_model.encoder.layers.16.layer_norm1.bias', 'text_model.encoder.layers.16.layer_norm1.weight', 'text_model.encoder.layers.16.layer_norm2.bias', 'text_model.encoder.layers.16.layer_norm2.weight', 'text_model.encoder.layers.16.mlp.fc1.bias', 'text_model.encoder.layers.16.mlp.fc1.weight', 'text_model.encoder.layers.16.mlp.fc2.bias', 'text_model.encoder.layers.16.mlp.fc2.weight', 'text_model.encoder.layers.16.self_attn.k_proj.bias', 'text_model.encoder.layers.16.self_attn.k_proj.weight', 'text_model.encoder.layers.16.self_attn.out_proj.bias', 'text_model.encoder.layers.16.self_attn.out_proj.weight', 'text_model.encoder.layers.16.self_attn.q_proj.bias', 'text_model.encoder.layers.16.self_attn.q_proj.weight', 'text_model.encoder.layers.16.self_attn.v_proj.bias', 'text_model.encoder.layers.16.self_attn.v_proj.weight', 'text_model.encoder.layers.17.layer_norm1.bias', 'text_model.encoder.layers.17.layer_norm1.weight', 'text_model.encoder.layers.17.layer_norm2.bias', 'text_model.encoder.layers.17.layer_norm2.weight', 'text_model.encoder.layers.17.mlp.fc1.bias', 'text_model.encoder.layers.17.mlp.fc1.weight', 'text_model.encoder.layers.17.mlp.fc2.bias', 'text_model.encoder.layers.17.mlp.fc2.weight', 'text_model.encoder.layers.17.self_attn.k_proj.bias', 'text_model.encoder.layers.17.self_attn.k_proj.weight', 'text_model.encoder.layers.17.self_attn.out_proj.bias', 'text_model.encoder.layers.17.self_attn.out_proj.weight', 'text_model.encoder.layers.17.self_attn.q_proj.bias', 'text_model.encoder.layers.17.self_attn.q_proj.weight', 'text_model.encoder.layers.17.self_attn.v_proj.bias', 'text_model.encoder.layers.17.self_attn.v_proj.weight', 'text_model.encoder.layers.18.layer_norm1.bias', 'text_model.encoder.layers.18.layer_norm1.weight', 'text_model.encoder.layers.18.layer_norm2.bias', 'text_model.encoder.layers.18.layer_norm2.weight', 'text_model.encoder.layers.18.mlp.fc1.bias', 'text_model.encoder.layers.18.mlp.fc1.weight', 'text_model.encoder.layers.18.mlp.fc2.bias', 'text_model.encoder.layers.18.mlp.fc2.weight', 'text_model.encoder.layers.18.self_attn.k_proj.bias', 'text_model.encoder.layers.18.self_attn.k_proj.weight', 'text_model.encoder.layers.18.self_attn.out_proj.bias', 'text_model.encoder.layers.18.self_attn.out_proj.weight', 'text_model.encoder.layers.18.self_attn.q_proj.bias', 'text_model.encoder.layers.18.self_attn.q_proj.weight', 'text_model.encoder.layers.18.self_attn.v_proj.bias', 'text_model.encoder.layers.18.self_attn.v_proj.weight', 'text_model.encoder.layers.19.layer_norm1.bias', 'text_model.encoder.layers.19.layer_norm1.weight', 'text_model.encoder.layers.19.layer_norm2.bias', 'text_model.encoder.layers.19.layer_norm2.weight', 'text_model.encoder.layers.19.mlp.fc1.bias', 'text_model.encoder.layers.19.mlp.fc1.weight', 'text_model.encoder.layers.19.mlp.fc2.bias', 'text_model.encoder.layers.19.mlp.fc2.weight', 'text_model.encoder.layers.19.self_attn.k_proj.bias', 'text_model.encoder.layers.19.self_attn.k_proj.weight', 'text_model.encoder.layers.19.self_attn.out_proj.bias', 'text_model.encoder.layers.19.self_attn.out_proj.weight', 'text_model.encoder.layers.19.self_attn.q_proj.bias', 'text_model.encoder.layers.19.self_attn.q_proj.weight', 'text_model.encoder.layers.19.self_attn.v_proj.bias', 'text_model.encoder.layers.19.self_attn.v_proj.weight', 'text_model.encoder.layers.2.layer_norm1.bias', 'text_model.encoder.layers.2.layer_norm1.weight', 'text_model.encoder.layers.2.layer_norm2.bias', 'text_model.encoder.layers.2.layer_norm2.weight', 'text_model.encoder.layers.2.mlp.fc1.bias', 'text_model.encoder.layers.2.mlp.fc1.weight', 'text_model.encoder.layers.2.mlp.fc2.bias', 'text_model.encoder.layers.2.mlp.fc2.weight', 'text_model.encoder.layers.2.self_attn.k_proj.bias', 'text_model.encoder.layers.2.self_attn.k_proj.weight', 'text_model.encoder.layers.2.self_attn.out_proj.bias', 'text_model.encoder.layers.2.self_attn.out_proj.weight', 'text_model.encoder.layers.2.self_attn.q_proj.bias', 'text_model.encoder.layers.2.self_attn.q_proj.weight', 'text_model.encoder.layers.2.self_attn.v_proj.bias', 'text_model.encoder.layers.2.self_attn.v_proj.weight', 'text_model.encoder.layers.20.layer_norm1.bias', 'text_model.encoder.layers.20.layer_norm1.weight', 'text_model.encoder.layers.20.layer_norm2.bias', 'text_model.encoder.layers.20.layer_norm2.weight', 'text_model.encoder.layers.20.mlp.fc1.bias', 'text_model.encoder.layers.20.mlp.fc1.weight', 'text_model.encoder.layers.20.mlp.fc2.bias', 'text_model.encoder.layers.20.mlp.fc2.weight', 'text_model.encoder.layers.20.self_attn.k_proj.bias', 'text_model.encoder.layers.20.self_attn.k_proj.weight', 'text_model.encoder.layers.20.self_attn.out_proj.bias', 'text_model.encoder.layers.20.self_attn.out_proj.weight', 'text_model.encoder.layers.20.self_attn.q_proj.bias', 'text_model.encoder.layers.20.self_attn.q_proj.weight', 'text_model.encoder.layers.20.self_attn.v_proj.bias', 'text_model.encoder.layers.20.self_attn.v_proj.weight', 'text_model.encoder.layers.21.layer_norm1.bias', 'text_model.encoder.layers.21.layer_norm1.weight', 'text_model.encoder.layers.21.layer_norm2.bias', 'text_model.encoder.layers.21.layer_norm2.weight', 'text_model.encoder.layers.21.mlp.fc1.bias', 'text_model.encoder.layers.21.mlp.fc1.weight', 'text_model.encoder.layers.21.mlp.fc2.bias', 'text_model.encoder.layers.21.mlp.fc2.weight', 'text_model.encoder.layers.21.self_attn.k_proj.bias', 'text_model.encoder.layers.21.self_attn.k_proj.weight', 'text_model.encoder.layers.21.self_attn.out_proj.bias', 'text_model.encoder.layers.21.self_attn.out_proj.weight', 'text_model.encoder.layers.21.self_attn.q_proj.bias', 'text_model.encoder.layers.21.self_attn.q_proj.weight', 'text_model.encoder.layers.21.self_attn.v_proj.bias', 'text_model.encoder.layers.21.self_attn.v_proj.weight', 'text_model.encoder.layers.22.layer_norm1.bias', 'text_model.encoder.layers.22.layer_norm1.weight', 'text_model.encoder.layers.22.layer_norm2.bias', 'text_model.encoder.layers.22.layer_norm2.weight', 'text_model.encoder.layers.22.mlp.fc1.bias', 'text_model.encoder.layers.22.mlp.fc1.weight', 'text_model.encoder.layers.22.mlp.fc2.bias', 'text_model.encoder.layers.22.mlp.fc2.weight', 'text_model.encoder.layers.22.self_attn.k_proj.bias', 'text_model.encoder.layers.22.self_attn.k_proj.weight', 'text_model.encoder.layers.22.self_attn.out_proj.bias', 'text_model.encoder.layers.22.self_attn.out_proj.weight', 'text_model.encoder.layers.22.self_attn.q_proj.bias', 'text_model.encoder.layers.22.self_attn.q_proj.weight', 'text_model.encoder.layers.22.self_attn.v_proj.bias', 'text_model.encoder.layers.22.self_attn.v_proj.weight', 'text_model.encoder.layers.23.layer_norm1.bias', 'text_model.encoder.layers.23.layer_norm1.weight', 'text_model.encoder.layers.23.layer_norm2.bias', 'text_model.encoder.layers.23.layer_norm2.weight', 'text_model.encoder.layers.23.mlp.fc1.bias', 'text_model.encoder.layers.23.mlp.fc1.weight', 'text_model.encoder.layers.23.mlp.fc2.bias', 'text_model.encoder.layers.23.mlp.fc2.weight', 'text_model.encoder.layers.23.self_attn.k_proj.bias', 'text_model.encoder.layers.23.self_attn.k_proj.weight', 'text_model.encoder.layers.23.self_attn.out_proj.bias', 'text_model.encoder.layers.23.self_attn.out_proj.weight', 'text_model.encoder.layers.23.self_attn.q_proj.bias', 'text_model.encoder.layers.23.self_attn.q_proj.weight', 'text_model.encoder.layers.23.self_attn.v_proj.bias', 'text_model.encoder.layers.23.self_attn.v_proj.weight', 'text_model.encoder.layers.24.layer_norm1.bias', 'text_model.encoder.layers.24.layer_norm1.weight', 'text_model.encoder.layers.24.layer_norm2.bias', 'text_model.encoder.layers.24.layer_norm2.weight', 'text_model.encoder.layers.24.mlp.fc1.bias', 'text_model.encoder.layers.24.mlp.fc1.weight', 'text_model.encoder.layers.24.mlp.fc2.bias', 'text_model.encoder.layers.24.mlp.fc2.weight', 'text_model.encoder.layers.24.self_attn.k_proj.bias', 'text_model.encoder.layers.24.self_attn.k_proj.weight', 'text_model.encoder.layers.24.self_attn.out_proj.bias', 'text_model.encoder.layers.24.self_attn.out_proj.weight', 'text_model.encoder.layers.24.self_attn.q_proj.bias', 'text_model.encoder.layers.24.self_attn.q_proj.weight', 'text_model.encoder.layers.24.self_attn.v_proj.bias', 'text_model.encoder.layers.24.self_attn.v_proj.weight', 'text_model.encoder.layers.25.layer_norm1.bias', 'text_model.encoder.layers.25.layer_norm1.weight', 'text_model.encoder.layers.25.layer_norm2.bias', 'text_model.encoder.layers.25.layer_norm2.weight', 'text_model.encoder.layers.25.mlp.fc1.bias', 'text_model.encoder.layers.25.mlp.fc1.weight', 'text_model.encoder.layers.25.mlp.fc2.bias', 'text_model.encoder.layers.25.mlp.fc2.weight', 'text_model.encoder.layers.25.self_attn.k_proj.bias', 'text_model.encoder.layers.25.self_attn.k_proj.weight', 'text_model.encoder.layers.25.self_attn.out_proj.bias', 'text_model.encoder.layers.25.self_attn.out_proj.weight', 'text_model.encoder.layers.25.self_attn.q_proj.bias', 'text_model.encoder.layers.25.self_attn.q_proj.weight', 'text_model.encoder.layers.25.self_attn.v_proj.bias', 'text_model.encoder.layers.25.self_attn.v_proj.weight', 'text_model.encoder.layers.26.layer_norm1.bias', 'text_model.encoder.layers.26.layer_norm1.weight', 'text_model.encoder.layers.26.layer_norm2.bias', 'text_model.encoder.layers.26.layer_norm2.weight', 'text_model.encoder.layers.26.mlp.fc1.bias', 'text_model.encoder.layers.26.mlp.fc1.weight', 'text_model.encoder.layers.26.mlp.fc2.bias', 'text_model.encoder.layers.26.mlp.fc2.weight', 'text_model.encoder.layers.26.self_attn.k_proj.bias', 'text_model.encoder.layers.26.self_attn.k_proj.weight', 'text_model.encoder.layers.26.self_attn.out_proj.bias', 'text_model.encoder.layers.26.self_attn.out_proj.weight', 'text_model.encoder.layers.26.self_attn.q_proj.bias', 'text_model.encoder.layers.26.self_attn.q_proj.weight', 'text_model.encoder.layers.26.self_attn.v_proj.bias', 'text_model.encoder.layers.26.self_attn.v_proj.weight', 'text_model.encoder.layers.3.layer_norm1.bias', 'text_model.encoder.layers.3.layer_norm1.weight', 'text_model.encoder.layers.3.layer_norm2.bias', 'text_model.encoder.layers.3.layer_norm2.weight', 'text_model.encoder.layers.3.mlp.fc1.bias', 'text_model.encoder.layers.3.mlp.fc1.weight', 'text_model.encoder.layers.3.mlp.fc2.bias', 'text_model.encoder.layers.3.mlp.fc2.weight', 'text_model.encoder.layers.3.self_attn.k_proj.bias', 'text_model.encoder.layers.3.self_attn.k_proj.weight', 'text_model.encoder.layers.3.self_attn.out_proj.bias', 'text_model.encoder.layers.3.self_attn.out_proj.weight', 'text_model.encoder.layers.3.self_attn.q_proj.bias', 'text_model.encoder.layers.3.self_attn.q_proj.weight', 'text_model.encoder.layers.3.self_attn.v_proj.bias', 'text_model.encoder.layers.3.self_attn.v_proj.weight', 'text_model.encoder.layers.4.layer_norm1.bias', 'text_model.encoder.layers.4.layer_norm1.weight', 'text_model.encoder.layers.4.layer_norm2.bias', 'text_model.encoder.layers.4.layer_norm2.weight', 'text_model.encoder.layers.4.mlp.fc1.bias', 'text_model.encoder.layers.4.mlp.fc1.weight', 'text_model.encoder.layers.4.mlp.fc2.bias', 'text_model.encoder.layers.4.mlp.fc2.weight', 'text_model.encoder.layers.4.self_attn.k_proj.bias', 'text_model.encoder.layers.4.self_attn.k_proj.weight', 'text_model.encoder.layers.4.self_attn.out_proj.bias', 'text_model.encoder.layers.4.self_attn.out_proj.weight', 'text_model.encoder.layers.4.self_attn.q_proj.bias', 'text_model.encoder.layers.4.self_attn.q_proj.weight', 'text_model.encoder.layers.4.self_attn.v_proj.bias', 'text_model.encoder.layers.4.self_attn.v_proj.weight', 'text_model.encoder.layers.5.layer_norm1.bias', 'text_model.encoder.layers.5.layer_norm1.weight', 'text_model.encoder.layers.5.layer_norm2.bias', 'text_model.encoder.layers.5.layer_norm2.weight', 'text_model.encoder.layers.5.mlp.fc1.bias', 'text_model.encoder.layers.5.mlp.fc1.weight', 'text_model.encoder.layers.5.mlp.fc2.bias', 'text_model.encoder.layers.5.mlp.fc2.weight', 'text_model.encoder.layers.5.self_attn.k_proj.bias', 'text_model.encoder.layers.5.self_attn.k_proj.weight', 'text_model.encoder.layers.5.self_attn.out_proj.bias', 'text_model.encoder.layers.5.self_attn.out_proj.weight', 'text_model.encoder.layers.5.self_attn.q_proj.bias', 'text_model.encoder.layers.5.self_attn.q_proj.weight', 'text_model.encoder.layers.5.self_attn.v_proj.bias', 'text_model.encoder.layers.5.self_attn.v_proj.weight', 'text_model.encoder.layers.6.layer_norm1.bias', 'text_model.encoder.layers.6.layer_norm1.weight', 'text_model.encoder.layers.6.layer_norm2.bias', 'text_model.encoder.layers.6.layer_norm2.weight', 'text_model.encoder.layers.6.mlp.fc1.bias', 'text_model.encoder.layers.6.mlp.fc1.weight', 'text_model.encoder.layers.6.mlp.fc2.bias', 'text_model.encoder.layers.6.mlp.fc2.weight', 'text_model.encoder.layers.6.self_attn.k_proj.bias', 'text_model.encoder.layers.6.self_attn.k_proj.weight', 'text_model.encoder.layers.6.self_attn.out_proj.bias', 'text_model.encoder.layers.6.self_attn.out_proj.weight', 'text_model.encoder.layers.6.self_attn.q_proj.bias', 'text_model.encoder.layers.6.self_attn.q_proj.weight', 'text_model.encoder.layers.6.self_attn.v_proj.bias', 'text_model.encoder.layers.6.self_attn.v_proj.weight', 'text_model.encoder.layers.7.layer_norm1.bias', 'text_model.encoder.layers.7.layer_norm1.weight', 'text_model.encoder.layers.7.layer_norm2.bias', 'text_model.encoder.layers.7.layer_norm2.weight', 'text_model.encoder.layers.7.mlp.fc1.bias', 'text_model.encoder.layers.7.mlp.fc1.weight', 'text_model.encoder.layers.7.mlp.fc2.bias', 'text_model.encoder.layers.7.mlp.fc2.weight', 'text_model.encoder.layers.7.self_attn.k_proj.bias', 'text_model.encoder.layers.7.self_attn.k_proj.weight', 'text_model.encoder.layers.7.self_attn.out_proj.bias', 'text_model.encoder.layers.7.self_attn.out_proj.weight', 'text_model.encoder.layers.7.self_attn.q_proj.bias', 'text_model.encoder.layers.7.self_attn.q_proj.weight', 'text_model.encoder.layers.7.self_attn.v_proj.bias', 'text_model.encoder.layers.7.self_attn.v_proj.weight', 'text_model.encoder.layers.8.layer_norm1.bias', 'text_model.encoder.layers.8.layer_norm1.weight', 'text_model.encoder.layers.8.layer_norm2.bias', 'text_model.encoder.layers.8.layer_norm2.weight', 'text_model.encoder.layers.8.mlp.fc1.bias', 'text_model.encoder.layers.8.mlp.fc1.weight', 'text_model.encoder.layers.8.mlp.fc2.bias', 'text_model.encoder.layers.8.mlp.fc2.weight', 'text_model.encoder.layers.8.self_attn.k_proj.bias', 'text_model.encoder.layers.8.self_attn.k_proj.weight', 'text_model.encoder.layers.8.self_attn.out_proj.bias', 'text_model.encoder.layers.8.self_attn.out_proj.weight', 'text_model.encoder.layers.8.self_attn.q_proj.bias', 'text_model.encoder.layers.8.self_attn.q_proj.weight', 'text_model.encoder.layers.8.self_attn.v_proj.bias', 'text_model.encoder.layers.8.self_attn.v_proj.weight', 'text_model.encoder.layers.9.layer_norm1.bias', 'text_model.encoder.layers.9.layer_norm1.weight', 'text_model.encoder.layers.9.layer_norm2.bias', 'text_model.encoder.layers.9.layer_norm2.weight', 'text_model.encoder.layers.9.mlp.fc1.bias', 'text_model.encoder.layers.9.mlp.fc1.weight', 'text_model.encoder.layers.9.mlp.fc2.bias', 'text_model.encoder.layers.9.mlp.fc2.weight', 'text_model.encoder.layers.9.self_attn.k_proj.bias', 'text_model.encoder.layers.9.self_attn.k_proj.weight', 'text_model.encoder.layers.9.self_attn.out_proj.bias', 'text_model.encoder.layers.9.self_attn.out_proj.weight', 'text_model.encoder.layers.9.self_attn.q_proj.bias', 'text_model.encoder.layers.9.self_attn.q_proj.weight', 'text_model.encoder.layers.9.self_attn.v_proj.bias', 'text_model.encoder.layers.9.self_attn.v_proj.weight', 'text_model.final_layer_norm.bias', 'text_model.final_layer_norm.weight', 'text_model.head.bias', 'text_model.head.weight']
-- This IS expected if you are initializing SiglipVisionModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
-- This IS NOT expected if you are initializing SiglipVisionModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
-2025-02-14 04:25:38,022 - modeling_utils.py:4458 - _load_pretrained_model - INFO - All the weights of SiglipVisionModel were initialized from the model checkpoint at google/siglip-so400m-patch14-384.
-If your task is similar to the task the model of the checkpoint was trained on, you can already use SiglipVisionModel for predictions without further training.
-2025-02-14 04:25:38,212 - image_processing_base.py:375 - get_image_processor_dict - INFO - loading configuration file preprocessor_config.json from cache at /root/.cache/huggingface/hub/models--google--siglip-so400m-patch14-384/snapshots/9fdffc58afc957d1a03a25b10dba0329ab15c2a3/preprocessor_config.json
-2025-02-14 04:25:38,212 - image_processing_base.py:429 - from_dict - INFO - Image processor SiglipImageProcessor {
-  "do_convert_rgb": null,
-  "do_normalize": true,
-  "do_rescale": true,
-  "do_resize": true,
-  "image_mean": [
-    0.5,
-    0.5,
-    0.5
-  ],
-  "image_processor_type": "SiglipImageProcessor",
-  "image_std": [
-    0.5,
-    0.5,
-    0.5
-  ],
-  "processor_class": "SiglipProcessor",
-  "resample": 3,
-  "rescale_factor": 0.00392156862745098,
-  "size": {
-    "height": 384,
-    "width": 384
-  }
-}
-
-2025-02-14 04:25:38,584 - configuration_utils.py:733 - _get_config_dict - INFO - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--facebook--dinov2-giant/snapshots/611a9d42f2335e0f921f1e313ad3c1b7178d206d/config.json
-2025-02-14 04:25:38,587 - configuration_utils.py:800 - from_dict - INFO - Model config Dinov2Config {
-  "apply_layernorm": true,
-  "architectures": [
-    "Dinov2Model"
-  ],
-  "attention_probs_dropout_prob": 0.0,
-  "drop_path_rate": 0.0,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.0,
-  "hidden_size": 1536,
-  "image_size": 518,
-  "initializer_range": 0.02,
-  "layer_norm_eps": 1e-06,
-  "layerscale_value": 1.0,
-  "mlp_ratio": 4,
-  "model_type": "dinov2",
-  "num_attention_heads": 24,
-  "num_channels": 3,
-  "num_hidden_layers": 40,
-  "out_features": [
-    "stage40"
-  ],
-  "out_indices": [
-    40
-  ],
-  "patch_size": 14,
-  "qkv_bias": true,
-  "reshape_hidden_states": true,
-  "stage_names": [
-    "stem",
-    "stage1",
-    "stage2",
-    "stage3",
-    "stage4",
-    "stage5",
-    "stage6",
-    "stage7",
-    "stage8",
-    "stage9",
-    "stage10",
-    "stage11",
-    "stage12",
-    "stage13",
-    "stage14",
-    "stage15",
-    "stage16",
-    "stage17",
-    "stage18",
-    "stage19",
-    "stage20",
-    "stage21",
-    "stage22",
-    "stage23",
-    "stage24",
-    "stage25",
-    "stage26",
-    "stage27",
-    "stage28",
-    "stage29",
-    "stage30",
-    "stage31",
-    "stage32",
-    "stage33",
-    "stage34",
-    "stage35",
-    "stage36",
-    "stage37",
-    "stage38",
-    "stage39",
-    "stage40"
-  ],
-  "torch_dtype": "float32",
-  "transformers_version": "4.43.1",
-  "use_swiglu_ffn": true
-}
-
-2025-02-14 04:25:38,588 - modeling_utils.py:3621 - from_pretrained - INFO - loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--facebook--dinov2-giant/snapshots/611a9d42f2335e0f921f1e313ad3c1b7178d206d/model.safetensors
-2025-02-14 04:25:39,038 - modeling_utils.py:4450 - _load_pretrained_model - INFO - All model checkpoint weights were used when initializing Dinov2Model.
-
-2025-02-14 04:25:39,038 - modeling_utils.py:4458 - _load_pretrained_model - INFO - All the weights of Dinov2Model were initialized from the model checkpoint at facebook/dinov2-giant.
-If your task is similar to the task the model of the checkpoint was trained on, you can already use Dinov2Model for predictions without further training.
-2025-02-14 04:25:39,536 - image_processing_base.py:375 - get_image_processor_dict - INFO - loading configuration file preprocessor_config.json from cache at /root/.cache/huggingface/hub/models--facebook--dinov2-giant/snapshots/611a9d42f2335e0f921f1e313ad3c1b7178d206d/preprocessor_config.json
-2025-02-14 04:25:39,540 - image_processing_base.py:429 - from_dict - INFO - Image processor BitImageProcessor {
-  "crop_size": {
-    "height": 378,
-    "width": 378
-  },
-  "do_center_crop": true,
-  "do_convert_rgb": true,
-  "do_normalize": true,
-  "do_rescale": true,
-  "do_resize": true,
-  "image_mean": [
-    0.485,
-    0.456,
-    0.406
-  ],
-  "image_processor_type": "BitImageProcessor",
-  "image_std": [
-    0.229,
-    0.224,
-    0.225
-  ],
-  "resample": 3,
-  "rescale_factor": 0.00392156862745098,
-  "size": {
-    "shortest_edge": 378
-  }
-}
-
-2025-02-14 04:25:40,430 - finetune_llama.py:1239 - train - INFO - Total params: 3264865280
-2025-02-14 04:25:40,430 - finetune_llama.py:1240 - train - INFO - Trainable params: 12589056
-2025-02-14 04:25:40,430 - finetune_llama.py:1241 - train - INFO - LM head params: 394002432
-2025-02-14 04:25:42,550 - trainer_callback.py:423 - add_callback - WARNING - You are adding a <class 'transformers.integrations.integration_utils.TensorBoardCallback'> to the callbacks of this Trainer, but there is already one. The currentlist of callbacks is
-:DefaultFlowCallback
-TensorBoardCallback
-2025-02-14 04:25:42,550 - trainer.py:648 - __init__ - INFO - Using auto half precision backend
-2025-02-14 04:25:42,857 - trainer.py:2134 - _inner_training_loop - INFO - ***** Running training *****
-2025-02-14 04:25:42,857 - trainer.py:2135 - _inner_training_loop - INFO -   Num examples = 554
-2025-02-14 04:25:42,857 - trainer.py:2136 - _inner_training_loop - INFO -   Num Epochs = 2
-2025-02-14 04:25:42,857 - trainer.py:2137 - _inner_training_loop - INFO -   Instantaneous batch size per device = 1
-2025-02-14 04:25:42,857 - trainer.py:2140 - _inner_training_loop - INFO -   Total train batch size (w. parallel, distributed & accumulation) = 1
-2025-02-14 04:25:42,857 - trainer.py:2141 - _inner_training_loop - INFO -   Gradient Accumulation steps = 1
-2025-02-14 04:25:42,857 - trainer.py:2142 - _inner_training_loop - INFO -   Total optimization steps = 1,108
-2025-02-14 04:25:42,859 - trainer.py:2143 - _inner_training_loop - INFO -   Number of trainable parameters = 406,591,488
+version https://git-lfs.github.com/spec/v1
+oid sha256:b74b5d170fd29d8ff01362cf2bd56abc278847a760cc589f3e9f2986ccc2a236
+size 36433

runtime_logs/run_2025-02-14_05-01-33.log

@@ -1,366 +1,3 @@
-2025-02-14 05:01:33,998 - training_args.py:2100 - _setup_devices - INFO - PyTorch: setting up devices
-2025-02-14 05:01:34,505 - configuration_utils.py:731 - _get_config_dict - INFO - loading configuration file ./checkpoints/longvu_llama3_2/config.json
-2025-02-14 05:01:34,508 - configuration_utils.py:800 - from_dict - INFO - Model config CambrianConfig {
-  "_name_or_path": "/tmp/iopath_cache/manifold_cache/tree/users/shenx/finetune/09281004-cambrian_llama3_2_t576_ov",
-  "architectures": [
-    "CambrianLlamaForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "bos_token_id": 128000,
-  "connect_layer": 2,
-  "connector_depth": 3,
-  "connector_only": true,
-  "dino_threshold": 0.83,
-  "drop_threshold": 0.8,
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
-  "frame_pos": false,
-  "freeze_mm_mlp_adapter": false,
-  "hidden_act": "silu",
-  "hidden_size": 3072,
-  "highres": true,
-  "highres_connect": false,
-  "image_aspect_ratio": "pad",
-  "image_position": 91,
-  "image_token_len": 144,
-  "initializer_range": 0.02,
-  "intermediate_size": 8192,
-  "is_image_newline": true,
-  "is_st_sampler": false,
-  "lowres_token": 8,
-  "max_position_embeddings": 131072,
-  "mlp_bias": false,
-  "mm_patch_merge_type": "flat",
-  "mm_projector_lr": null,
-  "mm_projector_type": "sva",
-  "mm_use_im_patch_token": false,
-  "mm_use_im_start_end": false,
-  "mm_vision_sampler_lr": null,
-  "mm_vision_select_feature": "patch",
-  "mm_vision_select_layer": -2,
-  "mm_vision_tower_aux_list": [
-    "siglip/CLIP-ViT-SO400M-14-384",
-    "facebook/dinov2-giant-res378"
-  ],
-  "mm_vision_tower_aux_token_len_list": [
-    576,
-    576
-  ],
-  "mm_vision_tower_lr": null,
-  "model_type": "cambrian_llama",
-  "num_attention_heads": 24,
-  "num_hidden_layers": 28,
-  "num_key_value_heads": 8,
-  "num_of_vision_sampler_layers": 10,
-  "num_query_group": 1,
-  "pretraining_tp": 1,
-  "query_num_list": [
-    144
-  ],
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": {
-    "factor": 32.0,
-    "high_freq_factor": 4.0,
-    "low_freq_factor": 1.0,
-    "original_max_position_embeddings": 8192,
-    "rope_type": "llama3"
-  },
-  "rope_theta": 500000.0,
-  "spmd_debug": null,
-  "spmd_fsdp_sharding": null,
-  "spmd_mesh": null,
-  "start_of_vision_sampler_layers": 0,
-  "stride_of_vision_sampler_layers": 3,
-  "tie_word_embeddings": false,
-  "tokenizer_model_max_length": 8192,
-  "tokenizer_padding_side": "right",
-  "torch_dtype": "float32",
-  "transformers_version": "4.43.1",
-  "tune_mm_mlp_adapter": false,
-  "unfreeze_mm_vision_tower": false,
-  "use_cache": false,
-  "use_mm_proj": true,
-  "vision_hidden_size": 1024,
-  "vision_tower_aux_token_len_list": [
-    576,
-    576
-  ],
-  "vocab_size": 128256
-}
-
-2025-02-14 05:01:34,508 - modeling_utils.py:3618 - from_pretrained - INFO - loading weights file ./checkpoints/longvu_llama3_2/pytorch_model.bin
-2025-02-14 05:01:34,547 - configuration_utils.py:1038 - from_dict - INFO - Generate config GenerationConfig {
-  "bos_token_id": 128000,
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
-  "use_cache": false
-}
-
-2025-02-14 05:01:34,753 - configuration_utils.py:733 - _get_config_dict - INFO - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--facebook--dinov2-giant/snapshots/611a9d42f2335e0f921f1e313ad3c1b7178d206d/config.json
-2025-02-14 05:01:34,757 - configuration_utils.py:800 - from_dict - INFO - Model config Dinov2Config {
-  "apply_layernorm": true,
-  "architectures": [
-    "Dinov2Model"
-  ],
-  "attention_probs_dropout_prob": 0.0,
-  "drop_path_rate": 0.0,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.0,
-  "hidden_size": 1536,
-  "image_size": 518,
-  "initializer_range": 0.02,
-  "layer_norm_eps": 1e-06,
-  "layerscale_value": 1.0,
-  "mlp_ratio": 4,
-  "model_type": "dinov2",
-  "num_attention_heads": 24,
-  "num_channels": 3,
-  "num_hidden_layers": 40,
-  "out_features": [
-    "stage40"
-  ],
-  "out_indices": [
-    40
-  ],
-  "patch_size": 14,
-  "qkv_bias": true,
-  "reshape_hidden_states": true,
-  "stage_names": [
-    "stem",
-    "stage1",
-    "stage2",
-    "stage3",
-    "stage4",
-    "stage5",
-    "stage6",
-    "stage7",
-    "stage8",
-    "stage9",
-    "stage10",
-    "stage11",
-    "stage12",
-    "stage13",
-    "stage14",
-    "stage15",
-    "stage16",
-    "stage17",
-    "stage18",
-    "stage19",
-    "stage20",
-    "stage21",
-    "stage22",
-    "stage23",
-    "stage24",
-    "stage25",
-    "stage26",
-    "stage27",
-    "stage28",
-    "stage29",
-    "stage30",
-    "stage31",
-    "stage32",
-    "stage33",
-    "stage34",
-    "stage35",
-    "stage36",
-    "stage37",
-    "stage38",
-    "stage39",
-    "stage40"
-  ],
-  "torch_dtype": "float32",
-  "transformers_version": "4.43.1",
-  "use_swiglu_ffn": true
-}
-
-2025-02-14 05:01:36,113 - modeling_utils.py:4450 - _load_pretrained_model - INFO - All model checkpoint weights were used when initializing CambrianLlamaForCausalLM.
-
-2025-02-14 05:01:36,113 - modeling_utils.py:4458 - _load_pretrained_model - INFO - All the weights of CambrianLlamaForCausalLM were initialized from the model checkpoint at ./checkpoints/longvu_llama3_2.
-If your task is similar to the task the model of the checkpoint was trained on, you can already use CambrianLlamaForCausalLM for predictions without further training.
-2025-02-14 05:01:36,119 - configuration_utils.py:991 - from_pretrained - INFO - loading configuration file ./checkpoints/longvu_llama3_2/generation_config.json
-2025-02-14 05:01:36,119 - configuration_utils.py:1038 - from_dict - INFO - Generate config GenerationConfig {
-  "bos_token_id": 128000,
-  "do_sample": true,
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
-  "temperature": 0.6,
-  "top_p": 0.9
-}
-
-2025-02-14 05:01:36,370 - tokenization_utils_base.py:2287 - from_pretrained - INFO - loading file tokenizer.json
-2025-02-14 05:01:36,370 - tokenization_utils_base.py:2287 - from_pretrained - INFO - loading file added_tokens.json
-2025-02-14 05:01:36,370 - tokenization_utils_base.py:2287 - from_pretrained - INFO - loading file special_tokens_map.json
-2025-02-14 05:01:36,370 - tokenization_utils_base.py:2287 - from_pretrained - INFO - loading file tokenizer_config.json
-2025-02-14 05:01:36,806 - tokenization_utils_base.py:2533 - _from_pretrained - INFO - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
-2025-02-14 05:01:37,166 - configuration_utils.py:733 - _get_config_dict - INFO - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--google--siglip-so400m-patch14-384/snapshots/9fdffc58afc957d1a03a25b10dba0329ab15c2a3/config.json
-2025-02-14 05:01:37,167 - configuration_utils.py:800 - from_dict - INFO - Model config SiglipVisionConfig {
-  "attention_dropout": 0.0,
-  "hidden_act": "gelu_pytorch_tanh",
-  "hidden_size": 1152,
-  "image_size": 384,
-  "intermediate_size": 4304,
-  "layer_norm_eps": 1e-06,
-  "model_type": "siglip_vision_model",
-  "num_attention_heads": 16,
-  "num_channels": 3,
-  "num_hidden_layers": 27,
-  "patch_size": 14,
-  "transformers_version": "4.43.1"
-}
-
-2025-02-14 05:01:37,168 - modeling_utils.py:3621 - from_pretrained - INFO - loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--google--siglip-so400m-patch14-384/snapshots/9fdffc58afc957d1a03a25b10dba0329ab15c2a3/model.safetensors
-2025-02-14 05:01:37,440 - modeling_utils.py:4440 - _load_pretrained_model - INFO - Some weights of the model checkpoint at google/siglip-so400m-patch14-384 were not used when initializing SiglipVisionModel: ['logit_bias', 'logit_scale', 'text_model.embeddings.position_embedding.weight', 'text_model.embeddings.token_embedding.weight', 'text_model.encoder.layers.0.layer_norm1.bias', 'text_model.encoder.layers.0.layer_norm1.weight', 'text_model.encoder.layers.0.layer_norm2.bias', 'text_model.encoder.layers.0.layer_norm2.weight', 'text_model.encoder.layers.0.mlp.fc1.bias', 'text_model.encoder.layers.0.mlp.fc1.weight', 'text_model.encoder.layers.0.mlp.fc2.bias', 'text_model.encoder.layers.0.mlp.fc2.weight', 'text_model.encoder.layers.0.self_attn.k_proj.bias', 'text_model.encoder.layers.0.self_attn.k_proj.weight', 'text_model.encoder.layers.0.self_attn.out_proj.bias', 'text_model.encoder.layers.0.self_attn.out_proj.weight', 'text_model.encoder.layers.0.self_attn.q_proj.bias', 'text_model.encoder.layers.0.self_attn.q_proj.weight', 'text_model.encoder.layers.0.self_attn.v_proj.bias', 'text_model.encoder.layers.0.self_attn.v_proj.weight', 'text_model.encoder.layers.1.layer_norm1.bias', 'text_model.encoder.layers.1.layer_norm1.weight', 'text_model.encoder.layers.1.layer_norm2.bias', 'text_model.encoder.layers.1.layer_norm2.weight', 'text_model.encoder.layers.1.mlp.fc1.bias', 'text_model.encoder.layers.1.mlp.fc1.weight', 'text_model.encoder.layers.1.mlp.fc2.bias', 'text_model.encoder.layers.1.mlp.fc2.weight', 'text_model.encoder.layers.1.self_attn.k_proj.bias', 'text_model.encoder.layers.1.self_attn.k_proj.weight', 'text_model.encoder.layers.1.self_attn.out_proj.bias', 'text_model.encoder.layers.1.self_attn.out_proj.weight', 'text_model.encoder.layers.1.self_attn.q_proj.bias', 'text_model.encoder.layers.1.self_attn.q_proj.weight', 'text_model.encoder.layers.1.self_attn.v_proj.bias', 'text_model.encoder.layers.1.self_attn.v_proj.weight', 'text_model.encoder.layers.10.layer_norm1.bias', 'text_model.encoder.layers.10.layer_norm1.weight', 'text_model.encoder.layers.10.layer_norm2.bias', 'text_model.encoder.layers.10.layer_norm2.weight', 'text_model.encoder.layers.10.mlp.fc1.bias', 'text_model.encoder.layers.10.mlp.fc1.weight', 'text_model.encoder.layers.10.mlp.fc2.bias', 'text_model.encoder.layers.10.mlp.fc2.weight', 'text_model.encoder.layers.10.self_attn.k_proj.bias', 'text_model.encoder.layers.10.self_attn.k_proj.weight', 'text_model.encoder.layers.10.self_attn.out_proj.bias', 'text_model.encoder.layers.10.self_attn.out_proj.weight', 'text_model.encoder.layers.10.self_attn.q_proj.bias', 'text_model.encoder.layers.10.self_attn.q_proj.weight', 'text_model.encoder.layers.10.self_attn.v_proj.bias', 'text_model.encoder.layers.10.self_attn.v_proj.weight', 'text_model.encoder.layers.11.layer_norm1.bias', 'text_model.encoder.layers.11.layer_norm1.weight', 'text_model.encoder.layers.11.layer_norm2.bias', 'text_model.encoder.layers.11.layer_norm2.weight', 'text_model.encoder.layers.11.mlp.fc1.bias', 'text_model.encoder.layers.11.mlp.fc1.weight', 'text_model.encoder.layers.11.mlp.fc2.bias', 'text_model.encoder.layers.11.mlp.fc2.weight', 'text_model.encoder.layers.11.self_attn.k_proj.bias', 'text_model.encoder.layers.11.self_attn.k_proj.weight', 'text_model.encoder.layers.11.self_attn.out_proj.bias', 'text_model.encoder.layers.11.self_attn.out_proj.weight', 'text_model.encoder.layers.11.self_attn.q_proj.bias', 'text_model.encoder.layers.11.self_attn.q_proj.weight', 'text_model.encoder.layers.11.self_attn.v_proj.bias', 'text_model.encoder.layers.11.self_attn.v_proj.weight', 'text_model.encoder.layers.12.layer_norm1.bias', 'text_model.encoder.layers.12.layer_norm1.weight', 'text_model.encoder.layers.12.layer_norm2.bias', 'text_model.encoder.layers.12.layer_norm2.weight', 'text_model.encoder.layers.12.mlp.fc1.bias', 'text_model.encoder.layers.12.mlp.fc1.weight', 'text_model.encoder.layers.12.mlp.fc2.bias', 'text_model.encoder.layers.12.mlp.fc2.weight', 'text_model.encoder.layers.12.self_attn.k_proj.bias', 'text_model.encoder.layers.12.self_attn.k_proj.weight', 'text_model.encoder.layers.12.self_attn.out_proj.bias', 'text_model.encoder.layers.12.self_attn.out_proj.weight', 'text_model.encoder.layers.12.self_attn.q_proj.bias', 'text_model.encoder.layers.12.self_attn.q_proj.weight', 'text_model.encoder.layers.12.self_attn.v_proj.bias', 'text_model.encoder.layers.12.self_attn.v_proj.weight', 'text_model.encoder.layers.13.layer_norm1.bias', 'text_model.encoder.layers.13.layer_norm1.weight', 'text_model.encoder.layers.13.layer_norm2.bias', 'text_model.encoder.layers.13.layer_norm2.weight', 'text_model.encoder.layers.13.mlp.fc1.bias', 'text_model.encoder.layers.13.mlp.fc1.weight', 'text_model.encoder.layers.13.mlp.fc2.bias', 'text_model.encoder.layers.13.mlp.fc2.weight', 'text_model.encoder.layers.13.self_attn.k_proj.bias', 'text_model.encoder.layers.13.self_attn.k_proj.weight', 'text_model.encoder.layers.13.self_attn.out_proj.bias', 'text_model.encoder.layers.13.self_attn.out_proj.weight', 'text_model.encoder.layers.13.self_attn.q_proj.bias', 'text_model.encoder.layers.13.self_attn.q_proj.weight', 'text_model.encoder.layers.13.self_attn.v_proj.bias', 'text_model.encoder.layers.13.self_attn.v_proj.weight', 'text_model.encoder.layers.14.layer_norm1.bias', 'text_model.encoder.layers.14.layer_norm1.weight', 'text_model.encoder.layers.14.layer_norm2.bias', 'text_model.encoder.layers.14.layer_norm2.weight', 'text_model.encoder.layers.14.mlp.fc1.bias', 'text_model.encoder.layers.14.mlp.fc1.weight', 'text_model.encoder.layers.14.mlp.fc2.bias', 'text_model.encoder.layers.14.mlp.fc2.weight', 'text_model.encoder.layers.14.self_attn.k_proj.bias', 'text_model.encoder.layers.14.self_attn.k_proj.weight', 'text_model.encoder.layers.14.self_attn.out_proj.bias', 'text_model.encoder.layers.14.self_attn.out_proj.weight', 'text_model.encoder.layers.14.self_attn.q_proj.bias', 'text_model.encoder.layers.14.self_attn.q_proj.weight', 'text_model.encoder.layers.14.self_attn.v_proj.bias', 'text_model.encoder.layers.14.self_attn.v_proj.weight', 'text_model.encoder.layers.15.layer_norm1.bias', 'text_model.encoder.layers.15.layer_norm1.weight', 'text_model.encoder.layers.15.layer_norm2.bias', 'text_model.encoder.layers.15.layer_norm2.weight', 'text_model.encoder.layers.15.mlp.fc1.bias', 'text_model.encoder.layers.15.mlp.fc1.weight', 'text_model.encoder.layers.15.mlp.fc2.bias', 'text_model.encoder.layers.15.mlp.fc2.weight', 'text_model.encoder.layers.15.self_attn.k_proj.bias', 'text_model.encoder.layers.15.self_attn.k_proj.weight', 'text_model.encoder.layers.15.self_attn.out_proj.bias', 'text_model.encoder.layers.15.self_attn.out_proj.weight', 'text_model.encoder.layers.15.self_attn.q_proj.bias', 'text_model.encoder.layers.15.self_attn.q_proj.weight', 'text_model.encoder.layers.15.self_attn.v_proj.bias', 'text_model.encoder.layers.15.self_attn.v_proj.weight', 'text_model.encoder.layers.16.layer_norm1.bias', 'text_model.encoder.layers.16.layer_norm1.weight', 'text_model.encoder.layers.16.layer_norm2.bias', 'text_model.encoder.layers.16.layer_norm2.weight', 'text_model.encoder.layers.16.mlp.fc1.bias', 'text_model.encoder.layers.16.mlp.fc1.weight', 'text_model.encoder.layers.16.mlp.fc2.bias', 'text_model.encoder.layers.16.mlp.fc2.weight', 'text_model.encoder.layers.16.self_attn.k_proj.bias', 'text_model.encoder.layers.16.self_attn.k_proj.weight', 'text_model.encoder.layers.16.self_attn.out_proj.bias', 'text_model.encoder.layers.16.self_attn.out_proj.weight', 'text_model.encoder.layers.16.self_attn.q_proj.bias', 'text_model.encoder.layers.16.self_attn.q_proj.weight', 'text_model.encoder.layers.16.self_attn.v_proj.bias', 'text_model.encoder.layers.16.self_attn.v_proj.weight', 'text_model.encoder.layers.17.layer_norm1.bias', 'text_model.encoder.layers.17.layer_norm1.weight', 'text_model.encoder.layers.17.layer_norm2.bias', 'text_model.encoder.layers.17.layer_norm2.weight', 'text_model.encoder.layers.17.mlp.fc1.bias', 'text_model.encoder.layers.17.mlp.fc1.weight', 'text_model.encoder.layers.17.mlp.fc2.bias', 'text_model.encoder.layers.17.mlp.fc2.weight', 'text_model.encoder.layers.17.self_attn.k_proj.bias', 'text_model.encoder.layers.17.self_attn.k_proj.weight', 'text_model.encoder.layers.17.self_attn.out_proj.bias', 'text_model.encoder.layers.17.self_attn.out_proj.weight', 'text_model.encoder.layers.17.self_attn.q_proj.bias', 'text_model.encoder.layers.17.self_attn.q_proj.weight', 'text_model.encoder.layers.17.self_attn.v_proj.bias', 'text_model.encoder.layers.17.self_attn.v_proj.weight', 'text_model.encoder.layers.18.layer_norm1.bias', 'text_model.encoder.layers.18.layer_norm1.weight', 'text_model.encoder.layers.18.layer_norm2.bias', 'text_model.encoder.layers.18.layer_norm2.weight', 'text_model.encoder.layers.18.mlp.fc1.bias', 'text_model.encoder.layers.18.mlp.fc1.weight', 'text_model.encoder.layers.18.mlp.fc2.bias', 'text_model.encoder.layers.18.mlp.fc2.weight', 'text_model.encoder.layers.18.self_attn.k_proj.bias', 'text_model.encoder.layers.18.self_attn.k_proj.weight', 'text_model.encoder.layers.18.self_attn.out_proj.bias', 'text_model.encoder.layers.18.self_attn.out_proj.weight', 'text_model.encoder.layers.18.self_attn.q_proj.bias', 'text_model.encoder.layers.18.self_attn.q_proj.weight', 'text_model.encoder.layers.18.self_attn.v_proj.bias', 'text_model.encoder.layers.18.self_attn.v_proj.weight', 'text_model.encoder.layers.19.layer_norm1.bias', 'text_model.encoder.layers.19.layer_norm1.weight', 'text_model.encoder.layers.19.layer_norm2.bias', 'text_model.encoder.layers.19.layer_norm2.weight', 'text_model.encoder.layers.19.mlp.fc1.bias', 'text_model.encoder.layers.19.mlp.fc1.weight', 'text_model.encoder.layers.19.mlp.fc2.bias', 'text_model.encoder.layers.19.mlp.fc2.weight', 'text_model.encoder.layers.19.self_attn.k_proj.bias', 'text_model.encoder.layers.19.self_attn.k_proj.weight', 'text_model.encoder.layers.19.self_attn.out_proj.bias', 'text_model.encoder.layers.19.self_attn.out_proj.weight', 'text_model.encoder.layers.19.self_attn.q_proj.bias', 'text_model.encoder.layers.19.self_attn.q_proj.weight', 'text_model.encoder.layers.19.self_attn.v_proj.bias', 'text_model.encoder.layers.19.self_attn.v_proj.weight', 'text_model.encoder.layers.2.layer_norm1.bias', 'text_model.encoder.layers.2.layer_norm1.weight', 'text_model.encoder.layers.2.layer_norm2.bias', 'text_model.encoder.layers.2.layer_norm2.weight', 'text_model.encoder.layers.2.mlp.fc1.bias', 'text_model.encoder.layers.2.mlp.fc1.weight', 'text_model.encoder.layers.2.mlp.fc2.bias', 'text_model.encoder.layers.2.mlp.fc2.weight', 'text_model.encoder.layers.2.self_attn.k_proj.bias', 'text_model.encoder.layers.2.self_attn.k_proj.weight', 'text_model.encoder.layers.2.self_attn.out_proj.bias', 'text_model.encoder.layers.2.self_attn.out_proj.weight', 'text_model.encoder.layers.2.self_attn.q_proj.bias', 'text_model.encoder.layers.2.self_attn.q_proj.weight', 'text_model.encoder.layers.2.self_attn.v_proj.bias', 'text_model.encoder.layers.2.self_attn.v_proj.weight', 'text_model.encoder.layers.20.layer_norm1.bias', 'text_model.encoder.layers.20.layer_norm1.weight', 'text_model.encoder.layers.20.layer_norm2.bias', 'text_model.encoder.layers.20.layer_norm2.weight', 'text_model.encoder.layers.20.mlp.fc1.bias', 'text_model.encoder.layers.20.mlp.fc1.weight', 'text_model.encoder.layers.20.mlp.fc2.bias', 'text_model.encoder.layers.20.mlp.fc2.weight', 'text_model.encoder.layers.20.self_attn.k_proj.bias', 'text_model.encoder.layers.20.self_attn.k_proj.weight', 'text_model.encoder.layers.20.self_attn.out_proj.bias', 'text_model.encoder.layers.20.self_attn.out_proj.weight', 'text_model.encoder.layers.20.self_attn.q_proj.bias', 'text_model.encoder.layers.20.self_attn.q_proj.weight', 'text_model.encoder.layers.20.self_attn.v_proj.bias', 'text_model.encoder.layers.20.self_attn.v_proj.weight', 'text_model.encoder.layers.21.layer_norm1.bias', 'text_model.encoder.layers.21.layer_norm1.weight', 'text_model.encoder.layers.21.layer_norm2.bias', 'text_model.encoder.layers.21.layer_norm2.weight', 'text_model.encoder.layers.21.mlp.fc1.bias', 'text_model.encoder.layers.21.mlp.fc1.weight', 'text_model.encoder.layers.21.mlp.fc2.bias', 'text_model.encoder.layers.21.mlp.fc2.weight', 'text_model.encoder.layers.21.self_attn.k_proj.bias', 'text_model.encoder.layers.21.self_attn.k_proj.weight', 'text_model.encoder.layers.21.self_attn.out_proj.bias', 'text_model.encoder.layers.21.self_attn.out_proj.weight', 'text_model.encoder.layers.21.self_attn.q_proj.bias', 'text_model.encoder.layers.21.self_attn.q_proj.weight', 'text_model.encoder.layers.21.self_attn.v_proj.bias', 'text_model.encoder.layers.21.self_attn.v_proj.weight', 'text_model.encoder.layers.22.layer_norm1.bias', 'text_model.encoder.layers.22.layer_norm1.weight', 'text_model.encoder.layers.22.layer_norm2.bias', 'text_model.encoder.layers.22.layer_norm2.weight', 'text_model.encoder.layers.22.mlp.fc1.bias', 'text_model.encoder.layers.22.mlp.fc1.weight', 'text_model.encoder.layers.22.mlp.fc2.bias', 'text_model.encoder.layers.22.mlp.fc2.weight', 'text_model.encoder.layers.22.self_attn.k_proj.bias', 'text_model.encoder.layers.22.self_attn.k_proj.weight', 'text_model.encoder.layers.22.self_attn.out_proj.bias', 'text_model.encoder.layers.22.self_attn.out_proj.weight', 'text_model.encoder.layers.22.self_attn.q_proj.bias', 'text_model.encoder.layers.22.self_attn.q_proj.weight', 'text_model.encoder.layers.22.self_attn.v_proj.bias', 'text_model.encoder.layers.22.self_attn.v_proj.weight', 'text_model.encoder.layers.23.layer_norm1.bias', 'text_model.encoder.layers.23.layer_norm1.weight', 'text_model.encoder.layers.23.layer_norm2.bias', 'text_model.encoder.layers.23.layer_norm2.weight', 'text_model.encoder.layers.23.mlp.fc1.bias', 'text_model.encoder.layers.23.mlp.fc1.weight', 'text_model.encoder.layers.23.mlp.fc2.bias', 'text_model.encoder.layers.23.mlp.fc2.weight', 'text_model.encoder.layers.23.self_attn.k_proj.bias', 'text_model.encoder.layers.23.self_attn.k_proj.weight', 'text_model.encoder.layers.23.self_attn.out_proj.bias', 'text_model.encoder.layers.23.self_attn.out_proj.weight', 'text_model.encoder.layers.23.self_attn.q_proj.bias', 'text_model.encoder.layers.23.self_attn.q_proj.weight', 'text_model.encoder.layers.23.self_attn.v_proj.bias', 'text_model.encoder.layers.23.self_attn.v_proj.weight', 'text_model.encoder.layers.24.layer_norm1.bias', 'text_model.encoder.layers.24.layer_norm1.weight', 'text_model.encoder.layers.24.layer_norm2.bias', 'text_model.encoder.layers.24.layer_norm2.weight', 'text_model.encoder.layers.24.mlp.fc1.bias', 'text_model.encoder.layers.24.mlp.fc1.weight', 'text_model.encoder.layers.24.mlp.fc2.bias', 'text_model.encoder.layers.24.mlp.fc2.weight', 'text_model.encoder.layers.24.self_attn.k_proj.bias', 'text_model.encoder.layers.24.self_attn.k_proj.weight', 'text_model.encoder.layers.24.self_attn.out_proj.bias', 'text_model.encoder.layers.24.self_attn.out_proj.weight', 'text_model.encoder.layers.24.self_attn.q_proj.bias', 'text_model.encoder.layers.24.self_attn.q_proj.weight', 'text_model.encoder.layers.24.self_attn.v_proj.bias', 'text_model.encoder.layers.24.self_attn.v_proj.weight', 'text_model.encoder.layers.25.layer_norm1.bias', 'text_model.encoder.layers.25.layer_norm1.weight', 'text_model.encoder.layers.25.layer_norm2.bias', 'text_model.encoder.layers.25.layer_norm2.weight', 'text_model.encoder.layers.25.mlp.fc1.bias', 'text_model.encoder.layers.25.mlp.fc1.weight', 'text_model.encoder.layers.25.mlp.fc2.bias', 'text_model.encoder.layers.25.mlp.fc2.weight', 'text_model.encoder.layers.25.self_attn.k_proj.bias', 'text_model.encoder.layers.25.self_attn.k_proj.weight', 'text_model.encoder.layers.25.self_attn.out_proj.bias', 'text_model.encoder.layers.25.self_attn.out_proj.weight', 'text_model.encoder.layers.25.self_attn.q_proj.bias', 'text_model.encoder.layers.25.self_attn.q_proj.weight', 'text_model.encoder.layers.25.self_attn.v_proj.bias', 'text_model.encoder.layers.25.self_attn.v_proj.weight', 'text_model.encoder.layers.26.layer_norm1.bias', 'text_model.encoder.layers.26.layer_norm1.weight', 'text_model.encoder.layers.26.layer_norm2.bias', 'text_model.encoder.layers.26.layer_norm2.weight', 'text_model.encoder.layers.26.mlp.fc1.bias', 'text_model.encoder.layers.26.mlp.fc1.weight', 'text_model.encoder.layers.26.mlp.fc2.bias', 'text_model.encoder.layers.26.mlp.fc2.weight', 'text_model.encoder.layers.26.self_attn.k_proj.bias', 'text_model.encoder.layers.26.self_attn.k_proj.weight', 'text_model.encoder.layers.26.self_attn.out_proj.bias', 'text_model.encoder.layers.26.self_attn.out_proj.weight', 'text_model.encoder.layers.26.self_attn.q_proj.bias', 'text_model.encoder.layers.26.self_attn.q_proj.weight', 'text_model.encoder.layers.26.self_attn.v_proj.bias', 'text_model.encoder.layers.26.self_attn.v_proj.weight', 'text_model.encoder.layers.3.layer_norm1.bias', 'text_model.encoder.layers.3.layer_norm1.weight', 'text_model.encoder.layers.3.layer_norm2.bias', 'text_model.encoder.layers.3.layer_norm2.weight', 'text_model.encoder.layers.3.mlp.fc1.bias', 'text_model.encoder.layers.3.mlp.fc1.weight', 'text_model.encoder.layers.3.mlp.fc2.bias', 'text_model.encoder.layers.3.mlp.fc2.weight', 'text_model.encoder.layers.3.self_attn.k_proj.bias', 'text_model.encoder.layers.3.self_attn.k_proj.weight', 'text_model.encoder.layers.3.self_attn.out_proj.bias', 'text_model.encoder.layers.3.self_attn.out_proj.weight', 'text_model.encoder.layers.3.self_attn.q_proj.bias', 'text_model.encoder.layers.3.self_attn.q_proj.weight', 'text_model.encoder.layers.3.self_attn.v_proj.bias', 'text_model.encoder.layers.3.self_attn.v_proj.weight', 'text_model.encoder.layers.4.layer_norm1.bias', 'text_model.encoder.layers.4.layer_norm1.weight', 'text_model.encoder.layers.4.layer_norm2.bias', 'text_model.encoder.layers.4.layer_norm2.weight', 'text_model.encoder.layers.4.mlp.fc1.bias', 'text_model.encoder.layers.4.mlp.fc1.weight', 'text_model.encoder.layers.4.mlp.fc2.bias', 'text_model.encoder.layers.4.mlp.fc2.weight', 'text_model.encoder.layers.4.self_attn.k_proj.bias', 'text_model.encoder.layers.4.self_attn.k_proj.weight', 'text_model.encoder.layers.4.self_attn.out_proj.bias', 'text_model.encoder.layers.4.self_attn.out_proj.weight', 'text_model.encoder.layers.4.self_attn.q_proj.bias', 'text_model.encoder.layers.4.self_attn.q_proj.weight', 'text_model.encoder.layers.4.self_attn.v_proj.bias', 'text_model.encoder.layers.4.self_attn.v_proj.weight', 'text_model.encoder.layers.5.layer_norm1.bias', 'text_model.encoder.layers.5.layer_norm1.weight', 'text_model.encoder.layers.5.layer_norm2.bias', 'text_model.encoder.layers.5.layer_norm2.weight', 'text_model.encoder.layers.5.mlp.fc1.bias', 'text_model.encoder.layers.5.mlp.fc1.weight', 'text_model.encoder.layers.5.mlp.fc2.bias', 'text_model.encoder.layers.5.mlp.fc2.weight', 'text_model.encoder.layers.5.self_attn.k_proj.bias', 'text_model.encoder.layers.5.self_attn.k_proj.weight', 'text_model.encoder.layers.5.self_attn.out_proj.bias', 'text_model.encoder.layers.5.self_attn.out_proj.weight', 'text_model.encoder.layers.5.self_attn.q_proj.bias', 'text_model.encoder.layers.5.self_attn.q_proj.weight', 'text_model.encoder.layers.5.self_attn.v_proj.bias', 'text_model.encoder.layers.5.self_attn.v_proj.weight', 'text_model.encoder.layers.6.layer_norm1.bias', 'text_model.encoder.layers.6.layer_norm1.weight', 'text_model.encoder.layers.6.layer_norm2.bias', 'text_model.encoder.layers.6.layer_norm2.weight', 'text_model.encoder.layers.6.mlp.fc1.bias', 'text_model.encoder.layers.6.mlp.fc1.weight', 'text_model.encoder.layers.6.mlp.fc2.bias', 'text_model.encoder.layers.6.mlp.fc2.weight', 'text_model.encoder.layers.6.self_attn.k_proj.bias', 'text_model.encoder.layers.6.self_attn.k_proj.weight', 'text_model.encoder.layers.6.self_attn.out_proj.bias', 'text_model.encoder.layers.6.self_attn.out_proj.weight', 'text_model.encoder.layers.6.self_attn.q_proj.bias', 'text_model.encoder.layers.6.self_attn.q_proj.weight', 'text_model.encoder.layers.6.self_attn.v_proj.bias', 'text_model.encoder.layers.6.self_attn.v_proj.weight', 'text_model.encoder.layers.7.layer_norm1.bias', 'text_model.encoder.layers.7.layer_norm1.weight', 'text_model.encoder.layers.7.layer_norm2.bias', 'text_model.encoder.layers.7.layer_norm2.weight', 'text_model.encoder.layers.7.mlp.fc1.bias', 'text_model.encoder.layers.7.mlp.fc1.weight', 'text_model.encoder.layers.7.mlp.fc2.bias', 'text_model.encoder.layers.7.mlp.fc2.weight', 'text_model.encoder.layers.7.self_attn.k_proj.bias', 'text_model.encoder.layers.7.self_attn.k_proj.weight', 'text_model.encoder.layers.7.self_attn.out_proj.bias', 'text_model.encoder.layers.7.self_attn.out_proj.weight', 'text_model.encoder.layers.7.self_attn.q_proj.bias', 'text_model.encoder.layers.7.self_attn.q_proj.weight', 'text_model.encoder.layers.7.self_attn.v_proj.bias', 'text_model.encoder.layers.7.self_attn.v_proj.weight', 'text_model.encoder.layers.8.layer_norm1.bias', 'text_model.encoder.layers.8.layer_norm1.weight', 'text_model.encoder.layers.8.layer_norm2.bias', 'text_model.encoder.layers.8.layer_norm2.weight', 'text_model.encoder.layers.8.mlp.fc1.bias', 'text_model.encoder.layers.8.mlp.fc1.weight', 'text_model.encoder.layers.8.mlp.fc2.bias', 'text_model.encoder.layers.8.mlp.fc2.weight', 'text_model.encoder.layers.8.self_attn.k_proj.bias', 'text_model.encoder.layers.8.self_attn.k_proj.weight', 'text_model.encoder.layers.8.self_attn.out_proj.bias', 'text_model.encoder.layers.8.self_attn.out_proj.weight', 'text_model.encoder.layers.8.self_attn.q_proj.bias', 'text_model.encoder.layers.8.self_attn.q_proj.weight', 'text_model.encoder.layers.8.self_attn.v_proj.bias', 'text_model.encoder.layers.8.self_attn.v_proj.weight', 'text_model.encoder.layers.9.layer_norm1.bias', 'text_model.encoder.layers.9.layer_norm1.weight', 'text_model.encoder.layers.9.layer_norm2.bias', 'text_model.encoder.layers.9.layer_norm2.weight', 'text_model.encoder.layers.9.mlp.fc1.bias', 'text_model.encoder.layers.9.mlp.fc1.weight', 'text_model.encoder.layers.9.mlp.fc2.bias', 'text_model.encoder.layers.9.mlp.fc2.weight', 'text_model.encoder.layers.9.self_attn.k_proj.bias', 'text_model.encoder.layers.9.self_attn.k_proj.weight', 'text_model.encoder.layers.9.self_attn.out_proj.bias', 'text_model.encoder.layers.9.self_attn.out_proj.weight', 'text_model.encoder.layers.9.self_attn.q_proj.bias', 'text_model.encoder.layers.9.self_attn.q_proj.weight', 'text_model.encoder.layers.9.self_attn.v_proj.bias', 'text_model.encoder.layers.9.self_attn.v_proj.weight', 'text_model.final_layer_norm.bias', 'text_model.final_layer_norm.weight', 'text_model.head.bias', 'text_model.head.weight']
-- This IS expected if you are initializing SiglipVisionModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
-- This IS NOT expected if you are initializing SiglipVisionModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
-2025-02-14 05:01:37,442 - modeling_utils.py:4458 - _load_pretrained_model - INFO - All the weights of SiglipVisionModel were initialized from the model checkpoint at google/siglip-so400m-patch14-384.
-If your task is similar to the task the model of the checkpoint was trained on, you can already use SiglipVisionModel for predictions without further training.
-2025-02-14 05:01:37,626 - image_processing_base.py:375 - get_image_processor_dict - INFO - loading configuration file preprocessor_config.json from cache at /root/.cache/huggingface/hub/models--google--siglip-so400m-patch14-384/snapshots/9fdffc58afc957d1a03a25b10dba0329ab15c2a3/preprocessor_config.json
-2025-02-14 05:01:37,627 - image_processing_base.py:429 - from_dict - INFO - Image processor SiglipImageProcessor {
-  "do_convert_rgb": null,
-  "do_normalize": true,
-  "do_rescale": true,
-  "do_resize": true,
-  "image_mean": [
-    0.5,
-    0.5,
-    0.5
-  ],
-  "image_processor_type": "SiglipImageProcessor",
-  "image_std": [
-    0.5,
-    0.5,
-    0.5
-  ],
-  "processor_class": "SiglipProcessor",
-  "resample": 3,
-  "rescale_factor": 0.00392156862745098,
-  "size": {
-    "height": 384,
-    "width": 384
-  }
-}
-
-2025-02-14 05:01:37,991 - configuration_utils.py:733 - _get_config_dict - INFO - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--facebook--dinov2-giant/snapshots/611a9d42f2335e0f921f1e313ad3c1b7178d206d/config.json
-2025-02-14 05:01:37,995 - configuration_utils.py:800 - from_dict - INFO - Model config Dinov2Config {
-  "apply_layernorm": true,
-  "architectures": [
-    "Dinov2Model"
-  ],
-  "attention_probs_dropout_prob": 0.0,
-  "drop_path_rate": 0.0,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.0,
-  "hidden_size": 1536,
-  "image_size": 518,
-  "initializer_range": 0.02,
-  "layer_norm_eps": 1e-06,
-  "layerscale_value": 1.0,
-  "mlp_ratio": 4,
-  "model_type": "dinov2",
-  "num_attention_heads": 24,
-  "num_channels": 3,
-  "num_hidden_layers": 40,
-  "out_features": [
-    "stage40"
-  ],
-  "out_indices": [
-    40
-  ],
-  "patch_size": 14,
-  "qkv_bias": true,
-  "reshape_hidden_states": true,
-  "stage_names": [
-    "stem",
-    "stage1",
-    "stage2",
-    "stage3",
-    "stage4",
-    "stage5",
-    "stage6",
-    "stage7",
-    "stage8",
-    "stage9",
-    "stage10",
-    "stage11",
-    "stage12",
-    "stage13",
-    "stage14",
-    "stage15",
-    "stage16",
-    "stage17",
-    "stage18",
-    "stage19",
-    "stage20",
-    "stage21",
-    "stage22",
-    "stage23",
-    "stage24",
-    "stage25",
-    "stage26",
-    "stage27",
-    "stage28",
-    "stage29",
-    "stage30",
-    "stage31",
-    "stage32",
-    "stage33",
-    "stage34",
-    "stage35",
-    "stage36",
-    "stage37",
-    "stage38",
-    "stage39",
-    "stage40"
-  ],
-  "torch_dtype": "float32",
-  "transformers_version": "4.43.1",
-  "use_swiglu_ffn": true
-}
-
-2025-02-14 05:01:37,995 - modeling_utils.py:3621 - from_pretrained - INFO - loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--facebook--dinov2-giant/snapshots/611a9d42f2335e0f921f1e313ad3c1b7178d206d/model.safetensors
-2025-02-14 05:01:38,584 - modeling_utils.py:4450 - _load_pretrained_model - INFO - All model checkpoint weights were used when initializing Dinov2Model.
-
-2025-02-14 05:01:38,584 - modeling_utils.py:4458 - _load_pretrained_model - INFO - All the weights of Dinov2Model were initialized from the model checkpoint at facebook/dinov2-giant.
-If your task is similar to the task the model of the checkpoint was trained on, you can already use Dinov2Model for predictions without further training.
-2025-02-14 05:01:38,771 - image_processing_base.py:375 - get_image_processor_dict - INFO - loading configuration file preprocessor_config.json from cache at /root/.cache/huggingface/hub/models--facebook--dinov2-giant/snapshots/611a9d42f2335e0f921f1e313ad3c1b7178d206d/preprocessor_config.json
-2025-02-14 05:01:38,774 - image_processing_base.py:429 - from_dict - INFO - Image processor BitImageProcessor {
-  "crop_size": {
-    "height": 378,
-    "width": 378
-  },
-  "do_center_crop": true,
-  "do_convert_rgb": true,
-  "do_normalize": true,
-  "do_rescale": true,
-  "do_resize": true,
-  "image_mean": [
-    0.485,
-    0.456,
-    0.406
-  ],
-  "image_processor_type": "BitImageProcessor",
-  "image_std": [
-    0.229,
-    0.224,
-    0.225
-  ],
-  "resample": 3,
-  "rescale_factor": 0.00392156862745098,
-  "size": {
-    "shortest_edge": 378
-  }
-}
-
-2025-02-14 05:01:39,569 - finetune_llama.py:1239 - train - INFO - Total params: 3264865280
-2025-02-14 05:01:39,569 - finetune_llama.py:1240 - train - INFO - Trainable params: 12589056
-2025-02-14 05:01:39,569 - finetune_llama.py:1241 - train - INFO - LM head params: 394002432
+version https://git-lfs.github.com/spec/v1
+oid sha256:fae628e76df568dd5e80f7f8759f86215724ca5777ddddb01d6531886e78a9ce
+size 35149

runtime_logs/run_2025-02-14_17-32-33.log

@@ -1,378 +1,3 @@
-2025-02-14 17:32:33,162 - training_args.py:2100 - _setup_devices - INFO - PyTorch: setting up devices
-2025-02-14 17:32:33,810 - configuration_utils.py:731 - _get_config_dict - INFO - loading configuration file ./checkpoints/longvu_llama3_2/config.json
-2025-02-14 17:32:33,813 - configuration_utils.py:800 - from_dict - INFO - Model config CambrianConfig {
-  "_name_or_path": "/tmp/iopath_cache/manifold_cache/tree/users/shenx/finetune/09281004-cambrian_llama3_2_t576_ov",
-  "architectures": [
-    "CambrianLlamaForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "bos_token_id": 128000,
-  "connect_layer": 2,
-  "connector_depth": 3,
-  "connector_only": true,
-  "dino_threshold": 0.83,
-  "drop_threshold": 0.8,
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
-  "frame_pos": false,
-  "freeze_mm_mlp_adapter": false,
-  "hidden_act": "silu",
-  "hidden_size": 3072,
-  "highres": true,
-  "highres_connect": false,
-  "image_aspect_ratio": "pad",
-  "image_position": 91,
-  "image_token_len": 144,
-  "initializer_range": 0.02,
-  "intermediate_size": 8192,
-  "is_image_newline": true,
-  "is_st_sampler": false,
-  "lowres_token": 8,
-  "max_position_embeddings": 131072,
-  "mlp_bias": false,
-  "mm_patch_merge_type": "flat",
-  "mm_projector_lr": null,
-  "mm_projector_type": "sva",
-  "mm_use_im_patch_token": false,
-  "mm_use_im_start_end": false,
-  "mm_vision_sampler_lr": null,
-  "mm_vision_select_feature": "patch",
-  "mm_vision_select_layer": -2,
-  "mm_vision_tower_aux_list": [
-    "siglip/CLIP-ViT-SO400M-14-384",
-    "facebook/dinov2-giant-res378"
-  ],
-  "mm_vision_tower_aux_token_len_list": [
-    576,
-    576
-  ],
-  "mm_vision_tower_lr": null,
-  "model_type": "cambrian_llama",
-  "num_attention_heads": 24,
-  "num_hidden_layers": 28,
-  "num_key_value_heads": 8,
-  "num_of_vision_sampler_layers": 10,
-  "num_query_group": 1,
-  "pretraining_tp": 1,
-  "query_num_list": [
-    144
-  ],
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": {
-    "factor": 32.0,
-    "high_freq_factor": 4.0,
-    "low_freq_factor": 1.0,
-    "original_max_position_embeddings": 8192,
-    "rope_type": "llama3"
-  },
-  "rope_theta": 500000.0,
-  "spmd_debug": null,
-  "spmd_fsdp_sharding": null,
-  "spmd_mesh": null,
-  "start_of_vision_sampler_layers": 0,
-  "stride_of_vision_sampler_layers": 3,
-  "tie_word_embeddings": false,
-  "tokenizer_model_max_length": 8192,
-  "tokenizer_padding_side": "right",
-  "torch_dtype": "float32",
-  "transformers_version": "4.43.1",
-  "tune_mm_mlp_adapter": false,
-  "unfreeze_mm_vision_tower": false,
-  "use_cache": false,
-  "use_mm_proj": true,
-  "vision_hidden_size": 1024,
-  "vision_tower_aux_token_len_list": [
-    576,
-    576
-  ],
-  "vocab_size": 128256
-}
-
-2025-02-14 17:32:33,813 - modeling_utils.py:3618 - from_pretrained - INFO - loading weights file ./checkpoints/longvu_llama3_2/pytorch_model.bin
-2025-02-14 17:32:33,874 - configuration_utils.py:1038 - from_dict - INFO - Generate config GenerationConfig {
-  "bos_token_id": 128000,
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
-  "use_cache": false
-}
-
-2025-02-14 17:32:34,467 - configuration_utils.py:733 - _get_config_dict - INFO - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--facebook--dinov2-giant/snapshots/611a9d42f2335e0f921f1e313ad3c1b7178d206d/config.json
-2025-02-14 17:32:34,470 - configuration_utils.py:800 - from_dict - INFO - Model config Dinov2Config {
-  "apply_layernorm": true,
-  "architectures": [
-    "Dinov2Model"
-  ],
-  "attention_probs_dropout_prob": 0.0,
-  "drop_path_rate": 0.0,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.0,
-  "hidden_size": 1536,
-  "image_size": 518,
-  "initializer_range": 0.02,
-  "layer_norm_eps": 1e-06,
-  "layerscale_value": 1.0,
-  "mlp_ratio": 4,
-  "model_type": "dinov2",
-  "num_attention_heads": 24,
-  "num_channels": 3,
-  "num_hidden_layers": 40,
-  "out_features": [
-    "stage40"
-  ],
-  "out_indices": [
-    40
-  ],
-  "patch_size": 14,
-  "qkv_bias": true,
-  "reshape_hidden_states": true,
-  "stage_names": [
-    "stem",
-    "stage1",
-    "stage2",
-    "stage3",
-    "stage4",
-    "stage5",
-    "stage6",
-    "stage7",
-    "stage8",
-    "stage9",
-    "stage10",
-    "stage11",
-    "stage12",
-    "stage13",
-    "stage14",
-    "stage15",
-    "stage16",
-    "stage17",
-    "stage18",
-    "stage19",
-    "stage20",
-    "stage21",
-    "stage22",
-    "stage23",
-    "stage24",
-    "stage25",
-    "stage26",
-    "stage27",
-    "stage28",
-    "stage29",
-    "stage30",
-    "stage31",
-    "stage32",
-    "stage33",
-    "stage34",
-    "stage35",
-    "stage36",
-    "stage37",
-    "stage38",
-    "stage39",
-    "stage40"
-  ],
-  "torch_dtype": "float32",
-  "transformers_version": "4.43.1",
-  "use_swiglu_ffn": true
-}
-
-2025-02-14 17:32:35,842 - modeling_utils.py:4450 - _load_pretrained_model - INFO - All model checkpoint weights were used when initializing CambrianLlamaForCausalLM.
-
-2025-02-14 17:32:35,843 - modeling_utils.py:4458 - _load_pretrained_model - INFO - All the weights of CambrianLlamaForCausalLM were initialized from the model checkpoint at ./checkpoints/longvu_llama3_2.
-If your task is similar to the task the model of the checkpoint was trained on, you can already use CambrianLlamaForCausalLM for predictions without further training.
-2025-02-14 17:32:35,848 - configuration_utils.py:991 - from_pretrained - INFO - loading configuration file ./checkpoints/longvu_llama3_2/generation_config.json
-2025-02-14 17:32:35,848 - configuration_utils.py:1038 - from_dict - INFO - Generate config GenerationConfig {
-  "bos_token_id": 128000,
-  "do_sample": true,
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
-  "temperature": 0.6,
-  "top_p": 0.9
-}
-
-2025-02-14 17:32:36,138 - tokenization_utils_base.py:2287 - from_pretrained - INFO - loading file tokenizer.json
-2025-02-14 17:32:36,138 - tokenization_utils_base.py:2287 - from_pretrained - INFO - loading file added_tokens.json
-2025-02-14 17:32:36,139 - tokenization_utils_base.py:2287 - from_pretrained - INFO - loading file special_tokens_map.json
-2025-02-14 17:32:36,139 - tokenization_utils_base.py:2287 - from_pretrained - INFO - loading file tokenizer_config.json
-2025-02-14 17:32:36,540 - tokenization_utils_base.py:2533 - _from_pretrained - INFO - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
-2025-02-14 17:32:36,920 - configuration_utils.py:733 - _get_config_dict - INFO - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--google--siglip-so400m-patch14-384/snapshots/9fdffc58afc957d1a03a25b10dba0329ab15c2a3/config.json
-2025-02-14 17:32:36,923 - configuration_utils.py:800 - from_dict - INFO - Model config SiglipVisionConfig {
-  "attention_dropout": 0.0,
-  "hidden_act": "gelu_pytorch_tanh",
-  "hidden_size": 1152,
-  "image_size": 384,
-  "intermediate_size": 4304,
-  "layer_norm_eps": 1e-06,
-  "model_type": "siglip_vision_model",
-  "num_attention_heads": 16,
-  "num_channels": 3,
-  "num_hidden_layers": 27,
-  "patch_size": 14,
-  "transformers_version": "4.43.1"
-}
-
-2025-02-14 17:32:36,924 - modeling_utils.py:3621 - from_pretrained - INFO - loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--google--siglip-so400m-patch14-384/snapshots/9fdffc58afc957d1a03a25b10dba0329ab15c2a3/model.safetensors
-2025-02-14 17:32:37,192 - modeling_utils.py:4440 - _load_pretrained_model - INFO - Some weights of the model checkpoint at google/siglip-so400m-patch14-384 were not used when initializing SiglipVisionModel: ['logit_bias', 'logit_scale', 'text_model.embeddings.position_embedding.weight', 'text_model.embeddings.token_embedding.weight', 'text_model.encoder.layers.0.layer_norm1.bias', 'text_model.encoder.layers.0.layer_norm1.weight', 'text_model.encoder.layers.0.layer_norm2.bias', 'text_model.encoder.layers.0.layer_norm2.weight', 'text_model.encoder.layers.0.mlp.fc1.bias', 'text_model.encoder.layers.0.mlp.fc1.weight', 'text_model.encoder.layers.0.mlp.fc2.bias', 'text_model.encoder.layers.0.mlp.fc2.weight', 'text_model.encoder.layers.0.self_attn.k_proj.bias', 'text_model.encoder.layers.0.self_attn.k_proj.weight', 'text_model.encoder.layers.0.self_attn.out_proj.bias', 'text_model.encoder.layers.0.self_attn.out_proj.weight', 'text_model.encoder.layers.0.self_attn.q_proj.bias', 'text_model.encoder.layers.0.self_attn.q_proj.weight', 'text_model.encoder.layers.0.self_attn.v_proj.bias', 'text_model.encoder.layers.0.self_attn.v_proj.weight', 'text_model.encoder.layers.1.layer_norm1.bias', 'text_model.encoder.layers.1.layer_norm1.weight', 'text_model.encoder.layers.1.layer_norm2.bias', 'text_model.encoder.layers.1.layer_norm2.weight', 'text_model.encoder.layers.1.mlp.fc1.bias', 'text_model.encoder.layers.1.mlp.fc1.weight', 'text_model.encoder.layers.1.mlp.fc2.bias', 'text_model.encoder.layers.1.mlp.fc2.weight', 'text_model.encoder.layers.1.self_attn.k_proj.bias', 'text_model.encoder.layers.1.self_attn.k_proj.weight', 'text_model.encoder.layers.1.self_attn.out_proj.bias', 'text_model.encoder.layers.1.self_attn.out_proj.weight', 'text_model.encoder.layers.1.self_attn.q_proj.bias', 'text_model.encoder.layers.1.self_attn.q_proj.weight', 'text_model.encoder.layers.1.self_attn.v_proj.bias', 'text_model.encoder.layers.1.self_attn.v_proj.weight', 'text_model.encoder.layers.10.layer_norm1.bias', 'text_model.encoder.layers.10.layer_norm1.weight', 'text_model.encoder.layers.10.layer_norm2.bias', 'text_model.encoder.layers.10.layer_norm2.weight', 'text_model.encoder.layers.10.mlp.fc1.bias', 'text_model.encoder.layers.10.mlp.fc1.weight', 'text_model.encoder.layers.10.mlp.fc2.bias', 'text_model.encoder.layers.10.mlp.fc2.weight', 'text_model.encoder.layers.10.self_attn.k_proj.bias', 'text_model.encoder.layers.10.self_attn.k_proj.weight', 'text_model.encoder.layers.10.self_attn.out_proj.bias', 'text_model.encoder.layers.10.self_attn.out_proj.weight', 'text_model.encoder.layers.10.self_attn.q_proj.bias', 'text_model.encoder.layers.10.self_attn.q_proj.weight', 'text_model.encoder.layers.10.self_attn.v_proj.bias', 'text_model.encoder.layers.10.self_attn.v_proj.weight', 'text_model.encoder.layers.11.layer_norm1.bias', 'text_model.encoder.layers.11.layer_norm1.weight', 'text_model.encoder.layers.11.layer_norm2.bias', 'text_model.encoder.layers.11.layer_norm2.weight', 'text_model.encoder.layers.11.mlp.fc1.bias', 'text_model.encoder.layers.11.mlp.fc1.weight', 'text_model.encoder.layers.11.mlp.fc2.bias', 'text_model.encoder.layers.11.mlp.fc2.weight', 'text_model.encoder.layers.11.self_attn.k_proj.bias', 'text_model.encoder.layers.11.self_attn.k_proj.weight', 'text_model.encoder.layers.11.self_attn.out_proj.bias', 'text_model.encoder.layers.11.self_attn.out_proj.weight', 'text_model.encoder.layers.11.self_attn.q_proj.bias', 'text_model.encoder.layers.11.self_attn.q_proj.weight', 'text_model.encoder.layers.11.self_attn.v_proj.bias', 'text_model.encoder.layers.11.self_attn.v_proj.weight', 'text_model.encoder.layers.12.layer_norm1.bias', 'text_model.encoder.layers.12.layer_norm1.weight', 'text_model.encoder.layers.12.layer_norm2.bias', 'text_model.encoder.layers.12.layer_norm2.weight', 'text_model.encoder.layers.12.mlp.fc1.bias', 'text_model.encoder.layers.12.mlp.fc1.weight', 'text_model.encoder.layers.12.mlp.fc2.bias', 'text_model.encoder.layers.12.mlp.fc2.weight', 'text_model.encoder.layers.12.self_attn.k_proj.bias', 'text_model.encoder.layers.12.self_attn.k_proj.weight', 'text_model.encoder.layers.12.self_attn.out_proj.bias', 'text_model.encoder.layers.12.self_attn.out_proj.weight', 'text_model.encoder.layers.12.self_attn.q_proj.bias', 'text_model.encoder.layers.12.self_attn.q_proj.weight', 'text_model.encoder.layers.12.self_attn.v_proj.bias', 'text_model.encoder.layers.12.self_attn.v_proj.weight', 'text_model.encoder.layers.13.layer_norm1.bias', 'text_model.encoder.layers.13.layer_norm1.weight', 'text_model.encoder.layers.13.layer_norm2.bias', 'text_model.encoder.layers.13.layer_norm2.weight', 'text_model.encoder.layers.13.mlp.fc1.bias', 'text_model.encoder.layers.13.mlp.fc1.weight', 'text_model.encoder.layers.13.mlp.fc2.bias', 'text_model.encoder.layers.13.mlp.fc2.weight', 'text_model.encoder.layers.13.self_attn.k_proj.bias', 'text_model.encoder.layers.13.self_attn.k_proj.weight', 'text_model.encoder.layers.13.self_attn.out_proj.bias', 'text_model.encoder.layers.13.self_attn.out_proj.weight', 'text_model.encoder.layers.13.self_attn.q_proj.bias', 'text_model.encoder.layers.13.self_attn.q_proj.weight', 'text_model.encoder.layers.13.self_attn.v_proj.bias', 'text_model.encoder.layers.13.self_attn.v_proj.weight', 'text_model.encoder.layers.14.layer_norm1.bias', 'text_model.encoder.layers.14.layer_norm1.weight', 'text_model.encoder.layers.14.layer_norm2.bias', 'text_model.encoder.layers.14.layer_norm2.weight', 'text_model.encoder.layers.14.mlp.fc1.bias', 'text_model.encoder.layers.14.mlp.fc1.weight', 'text_model.encoder.layers.14.mlp.fc2.bias', 'text_model.encoder.layers.14.mlp.fc2.weight', 'text_model.encoder.layers.14.self_attn.k_proj.bias', 'text_model.encoder.layers.14.self_attn.k_proj.weight', 'text_model.encoder.layers.14.self_attn.out_proj.bias', 'text_model.encoder.layers.14.self_attn.out_proj.weight', 'text_model.encoder.layers.14.self_attn.q_proj.bias', 'text_model.encoder.layers.14.self_attn.q_proj.weight', 'text_model.encoder.layers.14.self_attn.v_proj.bias', 'text_model.encoder.layers.14.self_attn.v_proj.weight', 'text_model.encoder.layers.15.layer_norm1.bias', 'text_model.encoder.layers.15.layer_norm1.weight', 'text_model.encoder.layers.15.layer_norm2.bias', 'text_model.encoder.layers.15.layer_norm2.weight', 'text_model.encoder.layers.15.mlp.fc1.bias', 'text_model.encoder.layers.15.mlp.fc1.weight', 'text_model.encoder.layers.15.mlp.fc2.bias', 'text_model.encoder.layers.15.mlp.fc2.weight', 'text_model.encoder.layers.15.self_attn.k_proj.bias', 'text_model.encoder.layers.15.self_attn.k_proj.weight', 'text_model.encoder.layers.15.self_attn.out_proj.bias', 'text_model.encoder.layers.15.self_attn.out_proj.weight', 'text_model.encoder.layers.15.self_attn.q_proj.bias', 'text_model.encoder.layers.15.self_attn.q_proj.weight', 'text_model.encoder.layers.15.self_attn.v_proj.bias', 'text_model.encoder.layers.15.self_attn.v_proj.weight', 'text_model.encoder.layers.16.layer_norm1.bias', 'text_model.encoder.layers.16.layer_norm1.weight', 'text_model.encoder.layers.16.layer_norm2.bias', 'text_model.encoder.layers.16.layer_norm2.weight', 'text_model.encoder.layers.16.mlp.fc1.bias', 'text_model.encoder.layers.16.mlp.fc1.weight', 'text_model.encoder.layers.16.mlp.fc2.bias', 'text_model.encoder.layers.16.mlp.fc2.weight', 'text_model.encoder.layers.16.self_attn.k_proj.bias', 'text_model.encoder.layers.16.self_attn.k_proj.weight', 'text_model.encoder.layers.16.self_attn.out_proj.bias', 'text_model.encoder.layers.16.self_attn.out_proj.weight', 'text_model.encoder.layers.16.self_attn.q_proj.bias', 'text_model.encoder.layers.16.self_attn.q_proj.weight', 'text_model.encoder.layers.16.self_attn.v_proj.bias', 'text_model.encoder.layers.16.self_attn.v_proj.weight', 'text_model.encoder.layers.17.layer_norm1.bias', 'text_model.encoder.layers.17.layer_norm1.weight', 'text_model.encoder.layers.17.layer_norm2.bias', 'text_model.encoder.layers.17.layer_norm2.weight', 'text_model.encoder.layers.17.mlp.fc1.bias', 'text_model.encoder.layers.17.mlp.fc1.weight', 'text_model.encoder.layers.17.mlp.fc2.bias', 'text_model.encoder.layers.17.mlp.fc2.weight', 'text_model.encoder.layers.17.self_attn.k_proj.bias', 'text_model.encoder.layers.17.self_attn.k_proj.weight', 'text_model.encoder.layers.17.self_attn.out_proj.bias', 'text_model.encoder.layers.17.self_attn.out_proj.weight', 'text_model.encoder.layers.17.self_attn.q_proj.bias', 'text_model.encoder.layers.17.self_attn.q_proj.weight', 'text_model.encoder.layers.17.self_attn.v_proj.bias', 'text_model.encoder.layers.17.self_attn.v_proj.weight', 'text_model.encoder.layers.18.layer_norm1.bias', 'text_model.encoder.layers.18.layer_norm1.weight', 'text_model.encoder.layers.18.layer_norm2.bias', 'text_model.encoder.layers.18.layer_norm2.weight', 'text_model.encoder.layers.18.mlp.fc1.bias', 'text_model.encoder.layers.18.mlp.fc1.weight', 'text_model.encoder.layers.18.mlp.fc2.bias', 'text_model.encoder.layers.18.mlp.fc2.weight', 'text_model.encoder.layers.18.self_attn.k_proj.bias', 'text_model.encoder.layers.18.self_attn.k_proj.weight', 'text_model.encoder.layers.18.self_attn.out_proj.bias', 'text_model.encoder.layers.18.self_attn.out_proj.weight', 'text_model.encoder.layers.18.self_attn.q_proj.bias', 'text_model.encoder.layers.18.self_attn.q_proj.weight', 'text_model.encoder.layers.18.self_attn.v_proj.bias', 'text_model.encoder.layers.18.self_attn.v_proj.weight', 'text_model.encoder.layers.19.layer_norm1.bias', 'text_model.encoder.layers.19.layer_norm1.weight', 'text_model.encoder.layers.19.layer_norm2.bias', 'text_model.encoder.layers.19.layer_norm2.weight', 'text_model.encoder.layers.19.mlp.fc1.bias', 'text_model.encoder.layers.19.mlp.fc1.weight', 'text_model.encoder.layers.19.mlp.fc2.bias', 'text_model.encoder.layers.19.mlp.fc2.weight', 'text_model.encoder.layers.19.self_attn.k_proj.bias', 'text_model.encoder.layers.19.self_attn.k_proj.weight', 'text_model.encoder.layers.19.self_attn.out_proj.bias', 'text_model.encoder.layers.19.self_attn.out_proj.weight', 'text_model.encoder.layers.19.self_attn.q_proj.bias', 'text_model.encoder.layers.19.self_attn.q_proj.weight', 'text_model.encoder.layers.19.self_attn.v_proj.bias', 'text_model.encoder.layers.19.self_attn.v_proj.weight', 'text_model.encoder.layers.2.layer_norm1.bias', 'text_model.encoder.layers.2.layer_norm1.weight', 'text_model.encoder.layers.2.layer_norm2.bias', 'text_model.encoder.layers.2.layer_norm2.weight', 'text_model.encoder.layers.2.mlp.fc1.bias', 'text_model.encoder.layers.2.mlp.fc1.weight', 'text_model.encoder.layers.2.mlp.fc2.bias', 'text_model.encoder.layers.2.mlp.fc2.weight', 'text_model.encoder.layers.2.self_attn.k_proj.bias', 'text_model.encoder.layers.2.self_attn.k_proj.weight', 'text_model.encoder.layers.2.self_attn.out_proj.bias', 'text_model.encoder.layers.2.self_attn.out_proj.weight', 'text_model.encoder.layers.2.self_attn.q_proj.bias', 'text_model.encoder.layers.2.self_attn.q_proj.weight', 'text_model.encoder.layers.2.self_attn.v_proj.bias', 'text_model.encoder.layers.2.self_attn.v_proj.weight', 'text_model.encoder.layers.20.layer_norm1.bias', 'text_model.encoder.layers.20.layer_norm1.weight', 'text_model.encoder.layers.20.layer_norm2.bias', 'text_model.encoder.layers.20.layer_norm2.weight', 'text_model.encoder.layers.20.mlp.fc1.bias', 'text_model.encoder.layers.20.mlp.fc1.weight', 'text_model.encoder.layers.20.mlp.fc2.bias', 'text_model.encoder.layers.20.mlp.fc2.weight', 'text_model.encoder.layers.20.self_attn.k_proj.bias', 'text_model.encoder.layers.20.self_attn.k_proj.weight', 'text_model.encoder.layers.20.self_attn.out_proj.bias', 'text_model.encoder.layers.20.self_attn.out_proj.weight', 'text_model.encoder.layers.20.self_attn.q_proj.bias', 'text_model.encoder.layers.20.self_attn.q_proj.weight', 'text_model.encoder.layers.20.self_attn.v_proj.bias', 'text_model.encoder.layers.20.self_attn.v_proj.weight', 'text_model.encoder.layers.21.layer_norm1.bias', 'text_model.encoder.layers.21.layer_norm1.weight', 'text_model.encoder.layers.21.layer_norm2.bias', 'text_model.encoder.layers.21.layer_norm2.weight', 'text_model.encoder.layers.21.mlp.fc1.bias', 'text_model.encoder.layers.21.mlp.fc1.weight', 'text_model.encoder.layers.21.mlp.fc2.bias', 'text_model.encoder.layers.21.mlp.fc2.weight', 'text_model.encoder.layers.21.self_attn.k_proj.bias', 'text_model.encoder.layers.21.self_attn.k_proj.weight', 'text_model.encoder.layers.21.self_attn.out_proj.bias', 'text_model.encoder.layers.21.self_attn.out_proj.weight', 'text_model.encoder.layers.21.self_attn.q_proj.bias', 'text_model.encoder.layers.21.self_attn.q_proj.weight', 'text_model.encoder.layers.21.self_attn.v_proj.bias', 'text_model.encoder.layers.21.self_attn.v_proj.weight', 'text_model.encoder.layers.22.layer_norm1.bias', 'text_model.encoder.layers.22.layer_norm1.weight', 'text_model.encoder.layers.22.layer_norm2.bias', 'text_model.encoder.layers.22.layer_norm2.weight', 'text_model.encoder.layers.22.mlp.fc1.bias', 'text_model.encoder.layers.22.mlp.fc1.weight', 'text_model.encoder.layers.22.mlp.fc2.bias', 'text_model.encoder.layers.22.mlp.fc2.weight', 'text_model.encoder.layers.22.self_attn.k_proj.bias', 'text_model.encoder.layers.22.self_attn.k_proj.weight', 'text_model.encoder.layers.22.self_attn.out_proj.bias', 'text_model.encoder.layers.22.self_attn.out_proj.weight', 'text_model.encoder.layers.22.self_attn.q_proj.bias', 'text_model.encoder.layers.22.self_attn.q_proj.weight', 'text_model.encoder.layers.22.self_attn.v_proj.bias', 'text_model.encoder.layers.22.self_attn.v_proj.weight', 'text_model.encoder.layers.23.layer_norm1.bias', 'text_model.encoder.layers.23.layer_norm1.weight', 'text_model.encoder.layers.23.layer_norm2.bias', 'text_model.encoder.layers.23.layer_norm2.weight', 'text_model.encoder.layers.23.mlp.fc1.bias', 'text_model.encoder.layers.23.mlp.fc1.weight', 'text_model.encoder.layers.23.mlp.fc2.bias', 'text_model.encoder.layers.23.mlp.fc2.weight', 'text_model.encoder.layers.23.self_attn.k_proj.bias', 'text_model.encoder.layers.23.self_attn.k_proj.weight', 'text_model.encoder.layers.23.self_attn.out_proj.bias', 'text_model.encoder.layers.23.self_attn.out_proj.weight', 'text_model.encoder.layers.23.self_attn.q_proj.bias', 'text_model.encoder.layers.23.self_attn.q_proj.weight', 'text_model.encoder.layers.23.self_attn.v_proj.bias', 'text_model.encoder.layers.23.self_attn.v_proj.weight', 'text_model.encoder.layers.24.layer_norm1.bias', 'text_model.encoder.layers.24.layer_norm1.weight', 'text_model.encoder.layers.24.layer_norm2.bias', 'text_model.encoder.layers.24.layer_norm2.weight', 'text_model.encoder.layers.24.mlp.fc1.bias', 'text_model.encoder.layers.24.mlp.fc1.weight', 'text_model.encoder.layers.24.mlp.fc2.bias', 'text_model.encoder.layers.24.mlp.fc2.weight', 'text_model.encoder.layers.24.self_attn.k_proj.bias', 'text_model.encoder.layers.24.self_attn.k_proj.weight', 'text_model.encoder.layers.24.self_attn.out_proj.bias', 'text_model.encoder.layers.24.self_attn.out_proj.weight', 'text_model.encoder.layers.24.self_attn.q_proj.bias', 'text_model.encoder.layers.24.self_attn.q_proj.weight', 'text_model.encoder.layers.24.self_attn.v_proj.bias', 'text_model.encoder.layers.24.self_attn.v_proj.weight', 'text_model.encoder.layers.25.layer_norm1.bias', 'text_model.encoder.layers.25.layer_norm1.weight', 'text_model.encoder.layers.25.layer_norm2.bias', 'text_model.encoder.layers.25.layer_norm2.weight', 'text_model.encoder.layers.25.mlp.fc1.bias', 'text_model.encoder.layers.25.mlp.fc1.weight', 'text_model.encoder.layers.25.mlp.fc2.bias', 'text_model.encoder.layers.25.mlp.fc2.weight', 'text_model.encoder.layers.25.self_attn.k_proj.bias', 'text_model.encoder.layers.25.self_attn.k_proj.weight', 'text_model.encoder.layers.25.self_attn.out_proj.bias', 'text_model.encoder.layers.25.self_attn.out_proj.weight', 'text_model.encoder.layers.25.self_attn.q_proj.bias', 'text_model.encoder.layers.25.self_attn.q_proj.weight', 'text_model.encoder.layers.25.self_attn.v_proj.bias', 'text_model.encoder.layers.25.self_attn.v_proj.weight', 'text_model.encoder.layers.26.layer_norm1.bias', 'text_model.encoder.layers.26.layer_norm1.weight', 'text_model.encoder.layers.26.layer_norm2.bias', 'text_model.encoder.layers.26.layer_norm2.weight', 'text_model.encoder.layers.26.mlp.fc1.bias', 'text_model.encoder.layers.26.mlp.fc1.weight', 'text_model.encoder.layers.26.mlp.fc2.bias', 'text_model.encoder.layers.26.mlp.fc2.weight', 'text_model.encoder.layers.26.self_attn.k_proj.bias', 'text_model.encoder.layers.26.self_attn.k_proj.weight', 'text_model.encoder.layers.26.self_attn.out_proj.bias', 'text_model.encoder.layers.26.self_attn.out_proj.weight', 'text_model.encoder.layers.26.self_attn.q_proj.bias', 'text_model.encoder.layers.26.self_attn.q_proj.weight', 'text_model.encoder.layers.26.self_attn.v_proj.bias', 'text_model.encoder.layers.26.self_attn.v_proj.weight', 'text_model.encoder.layers.3.layer_norm1.bias', 'text_model.encoder.layers.3.layer_norm1.weight', 'text_model.encoder.layers.3.layer_norm2.bias', 'text_model.encoder.layers.3.layer_norm2.weight', 'text_model.encoder.layers.3.mlp.fc1.bias', 'text_model.encoder.layers.3.mlp.fc1.weight', 'text_model.encoder.layers.3.mlp.fc2.bias', 'text_model.encoder.layers.3.mlp.fc2.weight', 'text_model.encoder.layers.3.self_attn.k_proj.bias', 'text_model.encoder.layers.3.self_attn.k_proj.weight', 'text_model.encoder.layers.3.self_attn.out_proj.bias', 'text_model.encoder.layers.3.self_attn.out_proj.weight', 'text_model.encoder.layers.3.self_attn.q_proj.bias', 'text_model.encoder.layers.3.self_attn.q_proj.weight', 'text_model.encoder.layers.3.self_attn.v_proj.bias', 'text_model.encoder.layers.3.self_attn.v_proj.weight', 'text_model.encoder.layers.4.layer_norm1.bias', 'text_model.encoder.layers.4.layer_norm1.weight', 'text_model.encoder.layers.4.layer_norm2.bias', 'text_model.encoder.layers.4.layer_norm2.weight', 'text_model.encoder.layers.4.mlp.fc1.bias', 'text_model.encoder.layers.4.mlp.fc1.weight', 'text_model.encoder.layers.4.mlp.fc2.bias', 'text_model.encoder.layers.4.mlp.fc2.weight', 'text_model.encoder.layers.4.self_attn.k_proj.bias', 'text_model.encoder.layers.4.self_attn.k_proj.weight', 'text_model.encoder.layers.4.self_attn.out_proj.bias', 'text_model.encoder.layers.4.self_attn.out_proj.weight', 'text_model.encoder.layers.4.self_attn.q_proj.bias', 'text_model.encoder.layers.4.self_attn.q_proj.weight', 'text_model.encoder.layers.4.self_attn.v_proj.bias', 'text_model.encoder.layers.4.self_attn.v_proj.weight', 'text_model.encoder.layers.5.layer_norm1.bias', 'text_model.encoder.layers.5.layer_norm1.weight', 'text_model.encoder.layers.5.layer_norm2.bias', 'text_model.encoder.layers.5.layer_norm2.weight', 'text_model.encoder.layers.5.mlp.fc1.bias', 'text_model.encoder.layers.5.mlp.fc1.weight', 'text_model.encoder.layers.5.mlp.fc2.bias', 'text_model.encoder.layers.5.mlp.fc2.weight', 'text_model.encoder.layers.5.self_attn.k_proj.bias', 'text_model.encoder.layers.5.self_attn.k_proj.weight', 'text_model.encoder.layers.5.self_attn.out_proj.bias', 'text_model.encoder.layers.5.self_attn.out_proj.weight', 'text_model.encoder.layers.5.self_attn.q_proj.bias', 'text_model.encoder.layers.5.self_attn.q_proj.weight', 'text_model.encoder.layers.5.self_attn.v_proj.bias', 'text_model.encoder.layers.5.self_attn.v_proj.weight', 'text_model.encoder.layers.6.layer_norm1.bias', 'text_model.encoder.layers.6.layer_norm1.weight', 'text_model.encoder.layers.6.layer_norm2.bias', 'text_model.encoder.layers.6.layer_norm2.weight', 'text_model.encoder.layers.6.mlp.fc1.bias', 'text_model.encoder.layers.6.mlp.fc1.weight', 'text_model.encoder.layers.6.mlp.fc2.bias', 'text_model.encoder.layers.6.mlp.fc2.weight', 'text_model.encoder.layers.6.self_attn.k_proj.bias', 'text_model.encoder.layers.6.self_attn.k_proj.weight', 'text_model.encoder.layers.6.self_attn.out_proj.bias', 'text_model.encoder.layers.6.self_attn.out_proj.weight', 'text_model.encoder.layers.6.self_attn.q_proj.bias', 'text_model.encoder.layers.6.self_attn.q_proj.weight', 'text_model.encoder.layers.6.self_attn.v_proj.bias', 'text_model.encoder.layers.6.self_attn.v_proj.weight', 'text_model.encoder.layers.7.layer_norm1.bias', 'text_model.encoder.layers.7.layer_norm1.weight', 'text_model.encoder.layers.7.layer_norm2.bias', 'text_model.encoder.layers.7.layer_norm2.weight', 'text_model.encoder.layers.7.mlp.fc1.bias', 'text_model.encoder.layers.7.mlp.fc1.weight', 'text_model.encoder.layers.7.mlp.fc2.bias', 'text_model.encoder.layers.7.mlp.fc2.weight', 'text_model.encoder.layers.7.self_attn.k_proj.bias', 'text_model.encoder.layers.7.self_attn.k_proj.weight', 'text_model.encoder.layers.7.self_attn.out_proj.bias', 'text_model.encoder.layers.7.self_attn.out_proj.weight', 'text_model.encoder.layers.7.self_attn.q_proj.bias', 'text_model.encoder.layers.7.self_attn.q_proj.weight', 'text_model.encoder.layers.7.self_attn.v_proj.bias', 'text_model.encoder.layers.7.self_attn.v_proj.weight', 'text_model.encoder.layers.8.layer_norm1.bias', 'text_model.encoder.layers.8.layer_norm1.weight', 'text_model.encoder.layers.8.layer_norm2.bias', 'text_model.encoder.layers.8.layer_norm2.weight', 'text_model.encoder.layers.8.mlp.fc1.bias', 'text_model.encoder.layers.8.mlp.fc1.weight', 'text_model.encoder.layers.8.mlp.fc2.bias', 'text_model.encoder.layers.8.mlp.fc2.weight', 'text_model.encoder.layers.8.self_attn.k_proj.bias', 'text_model.encoder.layers.8.self_attn.k_proj.weight', 'text_model.encoder.layers.8.self_attn.out_proj.bias', 'text_model.encoder.layers.8.self_attn.out_proj.weight', 'text_model.encoder.layers.8.self_attn.q_proj.bias', 'text_model.encoder.layers.8.self_attn.q_proj.weight', 'text_model.encoder.layers.8.self_attn.v_proj.bias', 'text_model.encoder.layers.8.self_attn.v_proj.weight', 'text_model.encoder.layers.9.layer_norm1.bias', 'text_model.encoder.layers.9.layer_norm1.weight', 'text_model.encoder.layers.9.layer_norm2.bias', 'text_model.encoder.layers.9.layer_norm2.weight', 'text_model.encoder.layers.9.mlp.fc1.bias', 'text_model.encoder.layers.9.mlp.fc1.weight', 'text_model.encoder.layers.9.mlp.fc2.bias', 'text_model.encoder.layers.9.mlp.fc2.weight', 'text_model.encoder.layers.9.self_attn.k_proj.bias', 'text_model.encoder.layers.9.self_attn.k_proj.weight', 'text_model.encoder.layers.9.self_attn.out_proj.bias', 'text_model.encoder.layers.9.self_attn.out_proj.weight', 'text_model.encoder.layers.9.self_attn.q_proj.bias', 'text_model.encoder.layers.9.self_attn.q_proj.weight', 'text_model.encoder.layers.9.self_attn.v_proj.bias', 'text_model.encoder.layers.9.self_attn.v_proj.weight', 'text_model.final_layer_norm.bias', 'text_model.final_layer_norm.weight', 'text_model.head.bias', 'text_model.head.weight']
-- This IS expected if you are initializing SiglipVisionModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
-- This IS NOT expected if you are initializing SiglipVisionModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
-2025-02-14 17:32:37,194 - modeling_utils.py:4458 - _load_pretrained_model - INFO - All the weights of SiglipVisionModel were initialized from the model checkpoint at google/siglip-so400m-patch14-384.
-If your task is similar to the task the model of the checkpoint was trained on, you can already use SiglipVisionModel for predictions without further training.
-2025-02-14 17:32:37,381 - image_processing_base.py:375 - get_image_processor_dict - INFO - loading configuration file preprocessor_config.json from cache at /root/.cache/huggingface/hub/models--google--siglip-so400m-patch14-384/snapshots/9fdffc58afc957d1a03a25b10dba0329ab15c2a3/preprocessor_config.json
-2025-02-14 17:32:37,382 - image_processing_base.py:429 - from_dict - INFO - Image processor SiglipImageProcessor {
-  "do_convert_rgb": null,
-  "do_normalize": true,
-  "do_rescale": true,
-  "do_resize": true,
-  "image_mean": [
-    0.5,
-    0.5,
-    0.5
-  ],
-  "image_processor_type": "SiglipImageProcessor",
-  "image_std": [
-    0.5,
-    0.5,
-    0.5
-  ],
-  "processor_class": "SiglipProcessor",
-  "resample": 3,
-  "rescale_factor": 0.00392156862745098,
-  "size": {
-    "height": 384,
-    "width": 384
-  }
-}
-
-2025-02-14 17:32:38,400 - configuration_utils.py:733 - _get_config_dict - INFO - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--facebook--dinov2-giant/snapshots/611a9d42f2335e0f921f1e313ad3c1b7178d206d/config.json
-2025-02-14 17:32:38,403 - configuration_utils.py:800 - from_dict - INFO - Model config Dinov2Config {
-  "apply_layernorm": true,
-  "architectures": [
-    "Dinov2Model"
-  ],
-  "attention_probs_dropout_prob": 0.0,
-  "drop_path_rate": 0.0,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.0,
-  "hidden_size": 1536,
-  "image_size": 518,
-  "initializer_range": 0.02,
-  "layer_norm_eps": 1e-06,
-  "layerscale_value": 1.0,
-  "mlp_ratio": 4,
-  "model_type": "dinov2",
-  "num_attention_heads": 24,
-  "num_channels": 3,
-  "num_hidden_layers": 40,
-  "out_features": [
-    "stage40"
-  ],
-  "out_indices": [
-    40
-  ],
-  "patch_size": 14,
-  "qkv_bias": true,
-  "reshape_hidden_states": true,
-  "stage_names": [
-    "stem",
-    "stage1",
-    "stage2",
-    "stage3",
-    "stage4",
-    "stage5",
-    "stage6",
-    "stage7",
-    "stage8",
-    "stage9",
-    "stage10",
-    "stage11",
-    "stage12",
-    "stage13",
-    "stage14",
-    "stage15",
-    "stage16",
-    "stage17",
-    "stage18",
-    "stage19",
-    "stage20",
-    "stage21",
-    "stage22",
-    "stage23",
-    "stage24",
-    "stage25",
-    "stage26",
-    "stage27",
-    "stage28",
-    "stage29",
-    "stage30",
-    "stage31",
-    "stage32",
-    "stage33",
-    "stage34",
-    "stage35",
-    "stage36",
-    "stage37",
-    "stage38",
-    "stage39",
-    "stage40"
-  ],
-  "torch_dtype": "float32",
-  "transformers_version": "4.43.1",
-  "use_swiglu_ffn": true
-}
-
-2025-02-14 17:32:38,404 - modeling_utils.py:3621 - from_pretrained - INFO - loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--facebook--dinov2-giant/snapshots/611a9d42f2335e0f921f1e313ad3c1b7178d206d/model.safetensors
-2025-02-14 17:32:38,981 - modeling_utils.py:4450 - _load_pretrained_model - INFO - All model checkpoint weights were used when initializing Dinov2Model.
-
-2025-02-14 17:32:38,981 - modeling_utils.py:4458 - _load_pretrained_model - INFO - All the weights of Dinov2Model were initialized from the model checkpoint at facebook/dinov2-giant.
-If your task is similar to the task the model of the checkpoint was trained on, you can already use Dinov2Model for predictions without further training.
-2025-02-14 17:32:39,176 - image_processing_base.py:375 - get_image_processor_dict - INFO - loading configuration file preprocessor_config.json from cache at /root/.cache/huggingface/hub/models--facebook--dinov2-giant/snapshots/611a9d42f2335e0f921f1e313ad3c1b7178d206d/preprocessor_config.json
-2025-02-14 17:32:39,179 - image_processing_base.py:429 - from_dict - INFO - Image processor BitImageProcessor {
-  "crop_size": {
-    "height": 378,
-    "width": 378
-  },
-  "do_center_crop": true,
-  "do_convert_rgb": true,
-  "do_normalize": true,
-  "do_rescale": true,
-  "do_resize": true,
-  "image_mean": [
-    0.485,
-    0.456,
-    0.406
-  ],
-  "image_processor_type": "BitImageProcessor",
-  "image_std": [
-    0.229,
-    0.224,
-    0.225
-  ],
-  "resample": 3,
-  "rescale_factor": 0.00392156862745098,
-  "size": {
-    "shortest_edge": 378
-  }
-}
-
-2025-02-14 17:32:39,938 - finetune_llama.py:1239 - train - INFO - Total params: 3264865280
-2025-02-14 17:32:39,938 - finetune_llama.py:1240 - train - INFO - Trainable params: 12589056
-2025-02-14 17:32:39,938 - finetune_llama.py:1241 - train - INFO - LM head params: 394002432
-2025-02-14 17:32:42,649 - trainer_callback.py:423 - add_callback - WARNING - You are adding a <class 'transformers.integrations.integration_utils.TensorBoardCallback'> to the callbacks of this Trainer, but there is already one. The currentlist of callbacks is
-:DefaultFlowCallback
-TensorBoardCallback
-2025-02-14 17:32:42,649 - trainer.py:648 - __init__ - INFO - Using auto half precision backend
-2025-02-14 17:32:43,183 - trainer.py:2134 - _inner_training_loop - INFO - ***** Running training *****
-2025-02-14 17:32:43,184 - trainer.py:2135 - _inner_training_loop - INFO -   Num examples = 550
-2025-02-14 17:32:43,184 - trainer.py:2136 - _inner_training_loop - INFO -   Num Epochs = 2
-2025-02-14 17:32:43,184 - trainer.py:2137 - _inner_training_loop - INFO -   Instantaneous batch size per device = 1
-2025-02-14 17:32:43,184 - trainer.py:2140 - _inner_training_loop - INFO -   Total train batch size (w. parallel, distributed & accumulation) = 1
-2025-02-14 17:32:43,184 - trainer.py:2141 - _inner_training_loop - INFO -   Gradient Accumulation steps = 1
-2025-02-14 17:32:43,184 - trainer.py:2142 - _inner_training_loop - INFO -   Total optimization steps = 1,100
-2025-02-14 17:32:43,186 - trainer.py:2143 - _inner_training_loop - INFO -   Number of trainable parameters = 406,591,488
+version https://git-lfs.github.com/spec/v1
+oid sha256:056216c6b30ea50e9aeb44579620fe3d934c8fcb178331c5e9d64e261c2eada6
+size 36433

runtime_logs/run_2025-02-15_02-56-12.log

@@ -1,378 +1,3 @@
-2025-02-15 02:56:12,191 - training_args.py:2100 - _setup_devices - INFO - PyTorch: setting up devices
-2025-02-15 02:56:12,699 - configuration_utils.py:731 - _get_config_dict - INFO - loading configuration file ./checkpoints/longvu_llama3_2/config.json
-2025-02-15 02:56:12,703 - configuration_utils.py:800 - from_dict - INFO - Model config CambrianConfig {
-  "_name_or_path": "/tmp/iopath_cache/manifold_cache/tree/users/shenx/finetune/09281004-cambrian_llama3_2_t576_ov",
-  "architectures": [
-    "CambrianLlamaForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "bos_token_id": 128000,
-  "connect_layer": 2,
-  "connector_depth": 3,
-  "connector_only": true,
-  "dino_threshold": 0.83,
-  "drop_threshold": 0.8,
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
-  "frame_pos": false,
-  "freeze_mm_mlp_adapter": false,
-  "hidden_act": "silu",
-  "hidden_size": 3072,
-  "highres": true,
-  "highres_connect": false,
-  "image_aspect_ratio": "pad",
-  "image_position": 91,
-  "image_token_len": 144,
-  "initializer_range": 0.02,
-  "intermediate_size": 8192,
-  "is_image_newline": true,
-  "is_st_sampler": false,
-  "lowres_token": 8,
-  "max_position_embeddings": 131072,
-  "mlp_bias": false,
-  "mm_patch_merge_type": "flat",
-  "mm_projector_lr": null,
-  "mm_projector_type": "sva",
-  "mm_use_im_patch_token": false,
-  "mm_use_im_start_end": false,
-  "mm_vision_sampler_lr": null,
-  "mm_vision_select_feature": "patch",
-  "mm_vision_select_layer": -2,
-  "mm_vision_tower_aux_list": [
-    "siglip/CLIP-ViT-SO400M-14-384",
-    "facebook/dinov2-giant-res378"
-  ],
-  "mm_vision_tower_aux_token_len_list": [
-    576,
-    576
-  ],
-  "mm_vision_tower_lr": null,
-  "model_type": "cambrian_llama",
-  "num_attention_heads": 24,
-  "num_hidden_layers": 28,
-  "num_key_value_heads": 8,
-  "num_of_vision_sampler_layers": 10,
-  "num_query_group": 1,
-  "pretraining_tp": 1,
-  "query_num_list": [
-    144
-  ],
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": {
-    "factor": 32.0,
-    "high_freq_factor": 4.0,
-    "low_freq_factor": 1.0,
-    "original_max_position_embeddings": 8192,
-    "rope_type": "llama3"
-  },
-  "rope_theta": 500000.0,
-  "spmd_debug": null,
-  "spmd_fsdp_sharding": null,
-  "spmd_mesh": null,
-  "start_of_vision_sampler_layers": 0,
-  "stride_of_vision_sampler_layers": 3,
-  "tie_word_embeddings": false,
-  "tokenizer_model_max_length": 8192,
-  "tokenizer_padding_side": "right",
-  "torch_dtype": "float32",
-  "transformers_version": "4.43.1",
-  "tune_mm_mlp_adapter": false,
-  "unfreeze_mm_vision_tower": false,
-  "use_cache": false,
-  "use_mm_proj": true,
-  "vision_hidden_size": 1024,
-  "vision_tower_aux_token_len_list": [
-    576,
-    576
-  ],
-  "vocab_size": 128256
-}
-
-2025-02-15 02:56:12,703 - modeling_utils.py:3618 - from_pretrained - INFO - loading weights file ./checkpoints/longvu_llama3_2/pytorch_model.bin
-2025-02-15 02:56:12,742 - configuration_utils.py:1038 - from_dict - INFO - Generate config GenerationConfig {
-  "bos_token_id": 128000,
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
-  "use_cache": false
-}
-
-2025-02-15 02:56:12,964 - configuration_utils.py:733 - _get_config_dict - INFO - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--facebook--dinov2-giant/snapshots/611a9d42f2335e0f921f1e313ad3c1b7178d206d/config.json
-2025-02-15 02:56:12,967 - configuration_utils.py:800 - from_dict - INFO - Model config Dinov2Config {
-  "apply_layernorm": true,
-  "architectures": [
-    "Dinov2Model"
-  ],
-  "attention_probs_dropout_prob": 0.0,
-  "drop_path_rate": 0.0,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.0,
-  "hidden_size": 1536,
-  "image_size": 518,
-  "initializer_range": 0.02,
-  "layer_norm_eps": 1e-06,
-  "layerscale_value": 1.0,
-  "mlp_ratio": 4,
-  "model_type": "dinov2",
-  "num_attention_heads": 24,
-  "num_channels": 3,
-  "num_hidden_layers": 40,
-  "out_features": [
-    "stage40"
-  ],
-  "out_indices": [
-    40
-  ],
-  "patch_size": 14,
-  "qkv_bias": true,
-  "reshape_hidden_states": true,
-  "stage_names": [
-    "stem",
-    "stage1",
-    "stage2",
-    "stage3",
-    "stage4",
-    "stage5",
-    "stage6",
-    "stage7",
-    "stage8",
-    "stage9",
-    "stage10",
-    "stage11",
-    "stage12",
-    "stage13",
-    "stage14",
-    "stage15",
-    "stage16",
-    "stage17",
-    "stage18",
-    "stage19",
-    "stage20",
-    "stage21",
-    "stage22",
-    "stage23",
-    "stage24",
-    "stage25",
-    "stage26",
-    "stage27",
-    "stage28",
-    "stage29",
-    "stage30",
-    "stage31",
-    "stage32",
-    "stage33",
-    "stage34",
-    "stage35",
-    "stage36",
-    "stage37",
-    "stage38",
-    "stage39",
-    "stage40"
-  ],
-  "torch_dtype": "float32",
-  "transformers_version": "4.43.1",
-  "use_swiglu_ffn": true
-}
-
-2025-02-15 02:56:14,324 - modeling_utils.py:4450 - _load_pretrained_model - INFO - All model checkpoint weights were used when initializing CambrianLlamaForCausalLM.
-
-2025-02-15 02:56:14,324 - modeling_utils.py:4458 - _load_pretrained_model - INFO - All the weights of CambrianLlamaForCausalLM were initialized from the model checkpoint at ./checkpoints/longvu_llama3_2.
-If your task is similar to the task the model of the checkpoint was trained on, you can already use CambrianLlamaForCausalLM for predictions without further training.
-2025-02-15 02:56:14,328 - configuration_utils.py:991 - from_pretrained - INFO - loading configuration file ./checkpoints/longvu_llama3_2/generation_config.json
-2025-02-15 02:56:14,328 - configuration_utils.py:1038 - from_dict - INFO - Generate config GenerationConfig {
-  "bos_token_id": 128000,
-  "do_sample": true,
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
-  "temperature": 0.6,
-  "top_p": 0.9
-}
-
-2025-02-15 02:56:14,485 - tokenization_utils_base.py:2287 - from_pretrained - INFO - loading file tokenizer.json
-2025-02-15 02:56:14,485 - tokenization_utils_base.py:2287 - from_pretrained - INFO - loading file added_tokens.json
-2025-02-15 02:56:14,485 - tokenization_utils_base.py:2287 - from_pretrained - INFO - loading file special_tokens_map.json
-2025-02-15 02:56:14,485 - tokenization_utils_base.py:2287 - from_pretrained - INFO - loading file tokenizer_config.json
-2025-02-15 02:56:14,682 - tokenization_utils_base.py:2533 - _from_pretrained - INFO - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
-2025-02-15 02:56:15,344 - configuration_utils.py:733 - _get_config_dict - INFO - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--google--siglip-so400m-patch14-384/snapshots/9fdffc58afc957d1a03a25b10dba0329ab15c2a3/config.json
-2025-02-15 02:56:15,347 - configuration_utils.py:800 - from_dict - INFO - Model config SiglipVisionConfig {
-  "attention_dropout": 0.0,
-  "hidden_act": "gelu_pytorch_tanh",
-  "hidden_size": 1152,
-  "image_size": 384,
-  "intermediate_size": 4304,
-  "layer_norm_eps": 1e-06,
-  "model_type": "siglip_vision_model",
-  "num_attention_heads": 16,
-  "num_channels": 3,
-  "num_hidden_layers": 27,
-  "patch_size": 14,
-  "transformers_version": "4.43.1"
-}
-
-2025-02-15 02:56:15,347 - modeling_utils.py:3621 - from_pretrained - INFO - loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--google--siglip-so400m-patch14-384/snapshots/9fdffc58afc957d1a03a25b10dba0329ab15c2a3/model.safetensors
-2025-02-15 02:56:15,490 - modeling_utils.py:4440 - _load_pretrained_model - INFO - Some weights of the model checkpoint at google/siglip-so400m-patch14-384 were not used when initializing SiglipVisionModel: ['logit_bias', 'logit_scale', 'text_model.embeddings.position_embedding.weight', 'text_model.embeddings.token_embedding.weight', 'text_model.encoder.layers.0.layer_norm1.bias', 'text_model.encoder.layers.0.layer_norm1.weight', 'text_model.encoder.layers.0.layer_norm2.bias', 'text_model.encoder.layers.0.layer_norm2.weight', 'text_model.encoder.layers.0.mlp.fc1.bias', 'text_model.encoder.layers.0.mlp.fc1.weight', 'text_model.encoder.layers.0.mlp.fc2.bias', 'text_model.encoder.layers.0.mlp.fc2.weight', 'text_model.encoder.layers.0.self_attn.k_proj.bias', 'text_model.encoder.layers.0.self_attn.k_proj.weight', 'text_model.encoder.layers.0.self_attn.out_proj.bias', 'text_model.encoder.layers.0.self_attn.out_proj.weight', 'text_model.encoder.layers.0.self_attn.q_proj.bias', 'text_model.encoder.layers.0.self_attn.q_proj.weight', 'text_model.encoder.layers.0.self_attn.v_proj.bias', 'text_model.encoder.layers.0.self_attn.v_proj.weight', 'text_model.encoder.layers.1.layer_norm1.bias', 'text_model.encoder.layers.1.layer_norm1.weight', 'text_model.encoder.layers.1.layer_norm2.bias', 'text_model.encoder.layers.1.layer_norm2.weight', 'text_model.encoder.layers.1.mlp.fc1.bias', 'text_model.encoder.layers.1.mlp.fc1.weight', 'text_model.encoder.layers.1.mlp.fc2.bias', 'text_model.encoder.layers.1.mlp.fc2.weight', 'text_model.encoder.layers.1.self_attn.k_proj.bias', 'text_model.encoder.layers.1.self_attn.k_proj.weight', 'text_model.encoder.layers.1.self_attn.out_proj.bias', 'text_model.encoder.layers.1.self_attn.out_proj.weight', 'text_model.encoder.layers.1.self_attn.q_proj.bias', 'text_model.encoder.layers.1.self_attn.q_proj.weight', 'text_model.encoder.layers.1.self_attn.v_proj.bias', 'text_model.encoder.layers.1.self_attn.v_proj.weight', 'text_model.encoder.layers.10.layer_norm1.bias', 'text_model.encoder.layers.10.layer_norm1.weight', 'text_model.encoder.layers.10.layer_norm2.bias', 'text_model.encoder.layers.10.layer_norm2.weight', 'text_model.encoder.layers.10.mlp.fc1.bias', 'text_model.encoder.layers.10.mlp.fc1.weight', 'text_model.encoder.layers.10.mlp.fc2.bias', 'text_model.encoder.layers.10.mlp.fc2.weight', 'text_model.encoder.layers.10.self_attn.k_proj.bias', 'text_model.encoder.layers.10.self_attn.k_proj.weight', 'text_model.encoder.layers.10.self_attn.out_proj.bias', 'text_model.encoder.layers.10.self_attn.out_proj.weight', 'text_model.encoder.layers.10.self_attn.q_proj.bias', 'text_model.encoder.layers.10.self_attn.q_proj.weight', 'text_model.encoder.layers.10.self_attn.v_proj.bias', 'text_model.encoder.layers.10.self_attn.v_proj.weight', 'text_model.encoder.layers.11.layer_norm1.bias', 'text_model.encoder.layers.11.layer_norm1.weight', 'text_model.encoder.layers.11.layer_norm2.bias', 'text_model.encoder.layers.11.layer_norm2.weight', 'text_model.encoder.layers.11.mlp.fc1.bias', 'text_model.encoder.layers.11.mlp.fc1.weight', 'text_model.encoder.layers.11.mlp.fc2.bias', 'text_model.encoder.layers.11.mlp.fc2.weight', 'text_model.encoder.layers.11.self_attn.k_proj.bias', 'text_model.encoder.layers.11.self_attn.k_proj.weight', 'text_model.encoder.layers.11.self_attn.out_proj.bias', 'text_model.encoder.layers.11.self_attn.out_proj.weight', 'text_model.encoder.layers.11.self_attn.q_proj.bias', 'text_model.encoder.layers.11.self_attn.q_proj.weight', 'text_model.encoder.layers.11.self_attn.v_proj.bias', 'text_model.encoder.layers.11.self_attn.v_proj.weight', 'text_model.encoder.layers.12.layer_norm1.bias', 'text_model.encoder.layers.12.layer_norm1.weight', 'text_model.encoder.layers.12.layer_norm2.bias', 'text_model.encoder.layers.12.layer_norm2.weight', 'text_model.encoder.layers.12.mlp.fc1.bias', 'text_model.encoder.layers.12.mlp.fc1.weight', 'text_model.encoder.layers.12.mlp.fc2.bias', 'text_model.encoder.layers.12.mlp.fc2.weight', 'text_model.encoder.layers.12.self_attn.k_proj.bias', 'text_model.encoder.layers.12.self_attn.k_proj.weight', 'text_model.encoder.layers.12.self_attn.out_proj.bias', 'text_model.encoder.layers.12.self_attn.out_proj.weight', 'text_model.encoder.layers.12.self_attn.q_proj.bias', 'text_model.encoder.layers.12.self_attn.q_proj.weight', 'text_model.encoder.layers.12.self_attn.v_proj.bias', 'text_model.encoder.layers.12.self_attn.v_proj.weight', 'text_model.encoder.layers.13.layer_norm1.bias', 'text_model.encoder.layers.13.layer_norm1.weight', 'text_model.encoder.layers.13.layer_norm2.bias', 'text_model.encoder.layers.13.layer_norm2.weight', 'text_model.encoder.layers.13.mlp.fc1.bias', 'text_model.encoder.layers.13.mlp.fc1.weight', 'text_model.encoder.layers.13.mlp.fc2.bias', 'text_model.encoder.layers.13.mlp.fc2.weight', 'text_model.encoder.layers.13.self_attn.k_proj.bias', 'text_model.encoder.layers.13.self_attn.k_proj.weight', 'text_model.encoder.layers.13.self_attn.out_proj.bias', 'text_model.encoder.layers.13.self_attn.out_proj.weight', 'text_model.encoder.layers.13.self_attn.q_proj.bias', 'text_model.encoder.layers.13.self_attn.q_proj.weight', 'text_model.encoder.layers.13.self_attn.v_proj.bias', 'text_model.encoder.layers.13.self_attn.v_proj.weight', 'text_model.encoder.layers.14.layer_norm1.bias', 'text_model.encoder.layers.14.layer_norm1.weight', 'text_model.encoder.layers.14.layer_norm2.bias', 'text_model.encoder.layers.14.layer_norm2.weight', 'text_model.encoder.layers.14.mlp.fc1.bias', 'text_model.encoder.layers.14.mlp.fc1.weight', 'text_model.encoder.layers.14.mlp.fc2.bias', 'text_model.encoder.layers.14.mlp.fc2.weight', 'text_model.encoder.layers.14.self_attn.k_proj.bias', 'text_model.encoder.layers.14.self_attn.k_proj.weight', 'text_model.encoder.layers.14.self_attn.out_proj.bias', 'text_model.encoder.layers.14.self_attn.out_proj.weight', 'text_model.encoder.layers.14.self_attn.q_proj.bias', 'text_model.encoder.layers.14.self_attn.q_proj.weight', 'text_model.encoder.layers.14.self_attn.v_proj.bias', 'text_model.encoder.layers.14.self_attn.v_proj.weight', 'text_model.encoder.layers.15.layer_norm1.bias', 'text_model.encoder.layers.15.layer_norm1.weight', 'text_model.encoder.layers.15.layer_norm2.bias', 'text_model.encoder.layers.15.layer_norm2.weight', 'text_model.encoder.layers.15.mlp.fc1.bias', 'text_model.encoder.layers.15.mlp.fc1.weight', 'text_model.encoder.layers.15.mlp.fc2.bias', 'text_model.encoder.layers.15.mlp.fc2.weight', 'text_model.encoder.layers.15.self_attn.k_proj.bias', 'text_model.encoder.layers.15.self_attn.k_proj.weight', 'text_model.encoder.layers.15.self_attn.out_proj.bias', 'text_model.encoder.layers.15.self_attn.out_proj.weight', 'text_model.encoder.layers.15.self_attn.q_proj.bias', 'text_model.encoder.layers.15.self_attn.q_proj.weight', 'text_model.encoder.layers.15.self_attn.v_proj.bias', 'text_model.encoder.layers.15.self_attn.v_proj.weight', 'text_model.encoder.layers.16.layer_norm1.bias', 'text_model.encoder.layers.16.layer_norm1.weight', 'text_model.encoder.layers.16.layer_norm2.bias', 'text_model.encoder.layers.16.layer_norm2.weight', 'text_model.encoder.layers.16.mlp.fc1.bias', 'text_model.encoder.layers.16.mlp.fc1.weight', 'text_model.encoder.layers.16.mlp.fc2.bias', 'text_model.encoder.layers.16.mlp.fc2.weight', 'text_model.encoder.layers.16.self_attn.k_proj.bias', 'text_model.encoder.layers.16.self_attn.k_proj.weight', 'text_model.encoder.layers.16.self_attn.out_proj.bias', 'text_model.encoder.layers.16.self_attn.out_proj.weight', 'text_model.encoder.layers.16.self_attn.q_proj.bias', 'text_model.encoder.layers.16.self_attn.q_proj.weight', 'text_model.encoder.layers.16.self_attn.v_proj.bias', 'text_model.encoder.layers.16.self_attn.v_proj.weight', 'text_model.encoder.layers.17.layer_norm1.bias', 'text_model.encoder.layers.17.layer_norm1.weight', 'text_model.encoder.layers.17.layer_norm2.bias', 'text_model.encoder.layers.17.layer_norm2.weight', 'text_model.encoder.layers.17.mlp.fc1.bias', 'text_model.encoder.layers.17.mlp.fc1.weight', 'text_model.encoder.layers.17.mlp.fc2.bias', 'text_model.encoder.layers.17.mlp.fc2.weight', 'text_model.encoder.layers.17.self_attn.k_proj.bias', 'text_model.encoder.layers.17.self_attn.k_proj.weight', 'text_model.encoder.layers.17.self_attn.out_proj.bias', 'text_model.encoder.layers.17.self_attn.out_proj.weight', 'text_model.encoder.layers.17.self_attn.q_proj.bias', 'text_model.encoder.layers.17.self_attn.q_proj.weight', 'text_model.encoder.layers.17.self_attn.v_proj.bias', 'text_model.encoder.layers.17.self_attn.v_proj.weight', 'text_model.encoder.layers.18.layer_norm1.bias', 'text_model.encoder.layers.18.layer_norm1.weight', 'text_model.encoder.layers.18.layer_norm2.bias', 'text_model.encoder.layers.18.layer_norm2.weight', 'text_model.encoder.layers.18.mlp.fc1.bias', 'text_model.encoder.layers.18.mlp.fc1.weight', 'text_model.encoder.layers.18.mlp.fc2.bias', 'text_model.encoder.layers.18.mlp.fc2.weight', 'text_model.encoder.layers.18.self_attn.k_proj.bias', 'text_model.encoder.layers.18.self_attn.k_proj.weight', 'text_model.encoder.layers.18.self_attn.out_proj.bias', 'text_model.encoder.layers.18.self_attn.out_proj.weight', 'text_model.encoder.layers.18.self_attn.q_proj.bias', 'text_model.encoder.layers.18.self_attn.q_proj.weight', 'text_model.encoder.layers.18.self_attn.v_proj.bias', 'text_model.encoder.layers.18.self_attn.v_proj.weight', 'text_model.encoder.layers.19.layer_norm1.bias', 'text_model.encoder.layers.19.layer_norm1.weight', 'text_model.encoder.layers.19.layer_norm2.bias', 'text_model.encoder.layers.19.layer_norm2.weight', 'text_model.encoder.layers.19.mlp.fc1.bias', 'text_model.encoder.layers.19.mlp.fc1.weight', 'text_model.encoder.layers.19.mlp.fc2.bias', 'text_model.encoder.layers.19.mlp.fc2.weight', 'text_model.encoder.layers.19.self_attn.k_proj.bias', 'text_model.encoder.layers.19.self_attn.k_proj.weight', 'text_model.encoder.layers.19.self_attn.out_proj.bias', 'text_model.encoder.layers.19.self_attn.out_proj.weight', 'text_model.encoder.layers.19.self_attn.q_proj.bias', 'text_model.encoder.layers.19.self_attn.q_proj.weight', 'text_model.encoder.layers.19.self_attn.v_proj.bias', 'text_model.encoder.layers.19.self_attn.v_proj.weight', 'text_model.encoder.layers.2.layer_norm1.bias', 'text_model.encoder.layers.2.layer_norm1.weight', 'text_model.encoder.layers.2.layer_norm2.bias', 'text_model.encoder.layers.2.layer_norm2.weight', 'text_model.encoder.layers.2.mlp.fc1.bias', 'text_model.encoder.layers.2.mlp.fc1.weight', 'text_model.encoder.layers.2.mlp.fc2.bias', 'text_model.encoder.layers.2.mlp.fc2.weight', 'text_model.encoder.layers.2.self_attn.k_proj.bias', 'text_model.encoder.layers.2.self_attn.k_proj.weight', 'text_model.encoder.layers.2.self_attn.out_proj.bias', 'text_model.encoder.layers.2.self_attn.out_proj.weight', 'text_model.encoder.layers.2.self_attn.q_proj.bias', 'text_model.encoder.layers.2.self_attn.q_proj.weight', 'text_model.encoder.layers.2.self_attn.v_proj.bias', 'text_model.encoder.layers.2.self_attn.v_proj.weight', 'text_model.encoder.layers.20.layer_norm1.bias', 'text_model.encoder.layers.20.layer_norm1.weight', 'text_model.encoder.layers.20.layer_norm2.bias', 'text_model.encoder.layers.20.layer_norm2.weight', 'text_model.encoder.layers.20.mlp.fc1.bias', 'text_model.encoder.layers.20.mlp.fc1.weight', 'text_model.encoder.layers.20.mlp.fc2.bias', 'text_model.encoder.layers.20.mlp.fc2.weight', 'text_model.encoder.layers.20.self_attn.k_proj.bias', 'text_model.encoder.layers.20.self_attn.k_proj.weight', 'text_model.encoder.layers.20.self_attn.out_proj.bias', 'text_model.encoder.layers.20.self_attn.out_proj.weight', 'text_model.encoder.layers.20.self_attn.q_proj.bias', 'text_model.encoder.layers.20.self_attn.q_proj.weight', 'text_model.encoder.layers.20.self_attn.v_proj.bias', 'text_model.encoder.layers.20.self_attn.v_proj.weight', 'text_model.encoder.layers.21.layer_norm1.bias', 'text_model.encoder.layers.21.layer_norm1.weight', 'text_model.encoder.layers.21.layer_norm2.bias', 'text_model.encoder.layers.21.layer_norm2.weight', 'text_model.encoder.layers.21.mlp.fc1.bias', 'text_model.encoder.layers.21.mlp.fc1.weight', 'text_model.encoder.layers.21.mlp.fc2.bias', 'text_model.encoder.layers.21.mlp.fc2.weight', 'text_model.encoder.layers.21.self_attn.k_proj.bias', 'text_model.encoder.layers.21.self_attn.k_proj.weight', 'text_model.encoder.layers.21.self_attn.out_proj.bias', 'text_model.encoder.layers.21.self_attn.out_proj.weight', 'text_model.encoder.layers.21.self_attn.q_proj.bias', 'text_model.encoder.layers.21.self_attn.q_proj.weight', 'text_model.encoder.layers.21.self_attn.v_proj.bias', 'text_model.encoder.layers.21.self_attn.v_proj.weight', 'text_model.encoder.layers.22.layer_norm1.bias', 'text_model.encoder.layers.22.layer_norm1.weight', 'text_model.encoder.layers.22.layer_norm2.bias', 'text_model.encoder.layers.22.layer_norm2.weight', 'text_model.encoder.layers.22.mlp.fc1.bias', 'text_model.encoder.layers.22.mlp.fc1.weight', 'text_model.encoder.layers.22.mlp.fc2.bias', 'text_model.encoder.layers.22.mlp.fc2.weight', 'text_model.encoder.layers.22.self_attn.k_proj.bias', 'text_model.encoder.layers.22.self_attn.k_proj.weight', 'text_model.encoder.layers.22.self_attn.out_proj.bias', 'text_model.encoder.layers.22.self_attn.out_proj.weight', 'text_model.encoder.layers.22.self_attn.q_proj.bias', 'text_model.encoder.layers.22.self_attn.q_proj.weight', 'text_model.encoder.layers.22.self_attn.v_proj.bias', 'text_model.encoder.layers.22.self_attn.v_proj.weight', 'text_model.encoder.layers.23.layer_norm1.bias', 'text_model.encoder.layers.23.layer_norm1.weight', 'text_model.encoder.layers.23.layer_norm2.bias', 'text_model.encoder.layers.23.layer_norm2.weight', 'text_model.encoder.layers.23.mlp.fc1.bias', 'text_model.encoder.layers.23.mlp.fc1.weight', 'text_model.encoder.layers.23.mlp.fc2.bias', 'text_model.encoder.layers.23.mlp.fc2.weight', 'text_model.encoder.layers.23.self_attn.k_proj.bias', 'text_model.encoder.layers.23.self_attn.k_proj.weight', 'text_model.encoder.layers.23.self_attn.out_proj.bias', 'text_model.encoder.layers.23.self_attn.out_proj.weight', 'text_model.encoder.layers.23.self_attn.q_proj.bias', 'text_model.encoder.layers.23.self_attn.q_proj.weight', 'text_model.encoder.layers.23.self_attn.v_proj.bias', 'text_model.encoder.layers.23.self_attn.v_proj.weight', 'text_model.encoder.layers.24.layer_norm1.bias', 'text_model.encoder.layers.24.layer_norm1.weight', 'text_model.encoder.layers.24.layer_norm2.bias', 'text_model.encoder.layers.24.layer_norm2.weight', 'text_model.encoder.layers.24.mlp.fc1.bias', 'text_model.encoder.layers.24.mlp.fc1.weight', 'text_model.encoder.layers.24.mlp.fc2.bias', 'text_model.encoder.layers.24.mlp.fc2.weight', 'text_model.encoder.layers.24.self_attn.k_proj.bias', 'text_model.encoder.layers.24.self_attn.k_proj.weight', 'text_model.encoder.layers.24.self_attn.out_proj.bias', 'text_model.encoder.layers.24.self_attn.out_proj.weight', 'text_model.encoder.layers.24.self_attn.q_proj.bias', 'text_model.encoder.layers.24.self_attn.q_proj.weight', 'text_model.encoder.layers.24.self_attn.v_proj.bias', 'text_model.encoder.layers.24.self_attn.v_proj.weight', 'text_model.encoder.layers.25.layer_norm1.bias', 'text_model.encoder.layers.25.layer_norm1.weight', 'text_model.encoder.layers.25.layer_norm2.bias', 'text_model.encoder.layers.25.layer_norm2.weight', 'text_model.encoder.layers.25.mlp.fc1.bias', 'text_model.encoder.layers.25.mlp.fc1.weight', 'text_model.encoder.layers.25.mlp.fc2.bias', 'text_model.encoder.layers.25.mlp.fc2.weight', 'text_model.encoder.layers.25.self_attn.k_proj.bias', 'text_model.encoder.layers.25.self_attn.k_proj.weight', 'text_model.encoder.layers.25.self_attn.out_proj.bias', 'text_model.encoder.layers.25.self_attn.out_proj.weight', 'text_model.encoder.layers.25.self_attn.q_proj.bias', 'text_model.encoder.layers.25.self_attn.q_proj.weight', 'text_model.encoder.layers.25.self_attn.v_proj.bias', 'text_model.encoder.layers.25.self_attn.v_proj.weight', 'text_model.encoder.layers.26.layer_norm1.bias', 'text_model.encoder.layers.26.layer_norm1.weight', 'text_model.encoder.layers.26.layer_norm2.bias', 'text_model.encoder.layers.26.layer_norm2.weight', 'text_model.encoder.layers.26.mlp.fc1.bias', 'text_model.encoder.layers.26.mlp.fc1.weight', 'text_model.encoder.layers.26.mlp.fc2.bias', 'text_model.encoder.layers.26.mlp.fc2.weight', 'text_model.encoder.layers.26.self_attn.k_proj.bias', 'text_model.encoder.layers.26.self_attn.k_proj.weight', 'text_model.encoder.layers.26.self_attn.out_proj.bias', 'text_model.encoder.layers.26.self_attn.out_proj.weight', 'text_model.encoder.layers.26.self_attn.q_proj.bias', 'text_model.encoder.layers.26.self_attn.q_proj.weight', 'text_model.encoder.layers.26.self_attn.v_proj.bias', 'text_model.encoder.layers.26.self_attn.v_proj.weight', 'text_model.encoder.layers.3.layer_norm1.bias', 'text_model.encoder.layers.3.layer_norm1.weight', 'text_model.encoder.layers.3.layer_norm2.bias', 'text_model.encoder.layers.3.layer_norm2.weight', 'text_model.encoder.layers.3.mlp.fc1.bias', 'text_model.encoder.layers.3.mlp.fc1.weight', 'text_model.encoder.layers.3.mlp.fc2.bias', 'text_model.encoder.layers.3.mlp.fc2.weight', 'text_model.encoder.layers.3.self_attn.k_proj.bias', 'text_model.encoder.layers.3.self_attn.k_proj.weight', 'text_model.encoder.layers.3.self_attn.out_proj.bias', 'text_model.encoder.layers.3.self_attn.out_proj.weight', 'text_model.encoder.layers.3.self_attn.q_proj.bias', 'text_model.encoder.layers.3.self_attn.q_proj.weight', 'text_model.encoder.layers.3.self_attn.v_proj.bias', 'text_model.encoder.layers.3.self_attn.v_proj.weight', 'text_model.encoder.layers.4.layer_norm1.bias', 'text_model.encoder.layers.4.layer_norm1.weight', 'text_model.encoder.layers.4.layer_norm2.bias', 'text_model.encoder.layers.4.layer_norm2.weight', 'text_model.encoder.layers.4.mlp.fc1.bias', 'text_model.encoder.layers.4.mlp.fc1.weight', 'text_model.encoder.layers.4.mlp.fc2.bias', 'text_model.encoder.layers.4.mlp.fc2.weight', 'text_model.encoder.layers.4.self_attn.k_proj.bias', 'text_model.encoder.layers.4.self_attn.k_proj.weight', 'text_model.encoder.layers.4.self_attn.out_proj.bias', 'text_model.encoder.layers.4.self_attn.out_proj.weight', 'text_model.encoder.layers.4.self_attn.q_proj.bias', 'text_model.encoder.layers.4.self_attn.q_proj.weight', 'text_model.encoder.layers.4.self_attn.v_proj.bias', 'text_model.encoder.layers.4.self_attn.v_proj.weight', 'text_model.encoder.layers.5.layer_norm1.bias', 'text_model.encoder.layers.5.layer_norm1.weight', 'text_model.encoder.layers.5.layer_norm2.bias', 'text_model.encoder.layers.5.layer_norm2.weight', 'text_model.encoder.layers.5.mlp.fc1.bias', 'text_model.encoder.layers.5.mlp.fc1.weight', 'text_model.encoder.layers.5.mlp.fc2.bias', 'text_model.encoder.layers.5.mlp.fc2.weight', 'text_model.encoder.layers.5.self_attn.k_proj.bias', 'text_model.encoder.layers.5.self_attn.k_proj.weight', 'text_model.encoder.layers.5.self_attn.out_proj.bias', 'text_model.encoder.layers.5.self_attn.out_proj.weight', 'text_model.encoder.layers.5.self_attn.q_proj.bias', 'text_model.encoder.layers.5.self_attn.q_proj.weight', 'text_model.encoder.layers.5.self_attn.v_proj.bias', 'text_model.encoder.layers.5.self_attn.v_proj.weight', 'text_model.encoder.layers.6.layer_norm1.bias', 'text_model.encoder.layers.6.layer_norm1.weight', 'text_model.encoder.layers.6.layer_norm2.bias', 'text_model.encoder.layers.6.layer_norm2.weight', 'text_model.encoder.layers.6.mlp.fc1.bias', 'text_model.encoder.layers.6.mlp.fc1.weight', 'text_model.encoder.layers.6.mlp.fc2.bias', 'text_model.encoder.layers.6.mlp.fc2.weight', 'text_model.encoder.layers.6.self_attn.k_proj.bias', 'text_model.encoder.layers.6.self_attn.k_proj.weight', 'text_model.encoder.layers.6.self_attn.out_proj.bias', 'text_model.encoder.layers.6.self_attn.out_proj.weight', 'text_model.encoder.layers.6.self_attn.q_proj.bias', 'text_model.encoder.layers.6.self_attn.q_proj.weight', 'text_model.encoder.layers.6.self_attn.v_proj.bias', 'text_model.encoder.layers.6.self_attn.v_proj.weight', 'text_model.encoder.layers.7.layer_norm1.bias', 'text_model.encoder.layers.7.layer_norm1.weight', 'text_model.encoder.layers.7.layer_norm2.bias', 'text_model.encoder.layers.7.layer_norm2.weight', 'text_model.encoder.layers.7.mlp.fc1.bias', 'text_model.encoder.layers.7.mlp.fc1.weight', 'text_model.encoder.layers.7.mlp.fc2.bias', 'text_model.encoder.layers.7.mlp.fc2.weight', 'text_model.encoder.layers.7.self_attn.k_proj.bias', 'text_model.encoder.layers.7.self_attn.k_proj.weight', 'text_model.encoder.layers.7.self_attn.out_proj.bias', 'text_model.encoder.layers.7.self_attn.out_proj.weight', 'text_model.encoder.layers.7.self_attn.q_proj.bias', 'text_model.encoder.layers.7.self_attn.q_proj.weight', 'text_model.encoder.layers.7.self_attn.v_proj.bias', 'text_model.encoder.layers.7.self_attn.v_proj.weight', 'text_model.encoder.layers.8.layer_norm1.bias', 'text_model.encoder.layers.8.layer_norm1.weight', 'text_model.encoder.layers.8.layer_norm2.bias', 'text_model.encoder.layers.8.layer_norm2.weight', 'text_model.encoder.layers.8.mlp.fc1.bias', 'text_model.encoder.layers.8.mlp.fc1.weight', 'text_model.encoder.layers.8.mlp.fc2.bias', 'text_model.encoder.layers.8.mlp.fc2.weight', 'text_model.encoder.layers.8.self_attn.k_proj.bias', 'text_model.encoder.layers.8.self_attn.k_proj.weight', 'text_model.encoder.layers.8.self_attn.out_proj.bias', 'text_model.encoder.layers.8.self_attn.out_proj.weight', 'text_model.encoder.layers.8.self_attn.q_proj.bias', 'text_model.encoder.layers.8.self_attn.q_proj.weight', 'text_model.encoder.layers.8.self_attn.v_proj.bias', 'text_model.encoder.layers.8.self_attn.v_proj.weight', 'text_model.encoder.layers.9.layer_norm1.bias', 'text_model.encoder.layers.9.layer_norm1.weight', 'text_model.encoder.layers.9.layer_norm2.bias', 'text_model.encoder.layers.9.layer_norm2.weight', 'text_model.encoder.layers.9.mlp.fc1.bias', 'text_model.encoder.layers.9.mlp.fc1.weight', 'text_model.encoder.layers.9.mlp.fc2.bias', 'text_model.encoder.layers.9.mlp.fc2.weight', 'text_model.encoder.layers.9.self_attn.k_proj.bias', 'text_model.encoder.layers.9.self_attn.k_proj.weight', 'text_model.encoder.layers.9.self_attn.out_proj.bias', 'text_model.encoder.layers.9.self_attn.out_proj.weight', 'text_model.encoder.layers.9.self_attn.q_proj.bias', 'text_model.encoder.layers.9.self_attn.q_proj.weight', 'text_model.encoder.layers.9.self_attn.v_proj.bias', 'text_model.encoder.layers.9.self_attn.v_proj.weight', 'text_model.final_layer_norm.bias', 'text_model.final_layer_norm.weight', 'text_model.head.bias', 'text_model.head.weight']
-- This IS expected if you are initializing SiglipVisionModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
-- This IS NOT expected if you are initializing SiglipVisionModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
-2025-02-15 02:56:15,491 - modeling_utils.py:4458 - _load_pretrained_model - INFO - All the weights of SiglipVisionModel were initialized from the model checkpoint at google/siglip-so400m-patch14-384.
-If your task is similar to the task the model of the checkpoint was trained on, you can already use SiglipVisionModel for predictions without further training.
-2025-02-15 02:56:15,674 - image_processing_base.py:375 - get_image_processor_dict - INFO - loading configuration file preprocessor_config.json from cache at /root/.cache/huggingface/hub/models--google--siglip-so400m-patch14-384/snapshots/9fdffc58afc957d1a03a25b10dba0329ab15c2a3/preprocessor_config.json
-2025-02-15 02:56:15,674 - image_processing_base.py:429 - from_dict - INFO - Image processor SiglipImageProcessor {
-  "do_convert_rgb": null,
-  "do_normalize": true,
-  "do_rescale": true,
-  "do_resize": true,
-  "image_mean": [
-    0.5,
-    0.5,
-    0.5
-  ],
-  "image_processor_type": "SiglipImageProcessor",
-  "image_std": [
-    0.5,
-    0.5,
-    0.5
-  ],
-  "processor_class": "SiglipProcessor",
-  "resample": 3,
-  "rescale_factor": 0.00392156862745098,
-  "size": {
-    "height": 384,
-    "width": 384
-  }
-}
-
-2025-02-15 02:56:16,050 - configuration_utils.py:733 - _get_config_dict - INFO - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--facebook--dinov2-giant/snapshots/611a9d42f2335e0f921f1e313ad3c1b7178d206d/config.json
-2025-02-15 02:56:16,052 - configuration_utils.py:800 - from_dict - INFO - Model config Dinov2Config {
-  "apply_layernorm": true,
-  "architectures": [
-    "Dinov2Model"
-  ],
-  "attention_probs_dropout_prob": 0.0,
-  "drop_path_rate": 0.0,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.0,
-  "hidden_size": 1536,
-  "image_size": 518,
-  "initializer_range": 0.02,
-  "layer_norm_eps": 1e-06,
-  "layerscale_value": 1.0,
-  "mlp_ratio": 4,
-  "model_type": "dinov2",
-  "num_attention_heads": 24,
-  "num_channels": 3,
-  "num_hidden_layers": 40,
-  "out_features": [
-    "stage40"
-  ],
-  "out_indices": [
-    40
-  ],
-  "patch_size": 14,
-  "qkv_bias": true,
-  "reshape_hidden_states": true,
-  "stage_names": [
-    "stem",
-    "stage1",
-    "stage2",
-    "stage3",
-    "stage4",
-    "stage5",
-    "stage6",
-    "stage7",
-    "stage8",
-    "stage9",
-    "stage10",
-    "stage11",
-    "stage12",
-    "stage13",
-    "stage14",
-    "stage15",
-    "stage16",
-    "stage17",
-    "stage18",
-    "stage19",
-    "stage20",
-    "stage21",
-    "stage22",
-    "stage23",
-    "stage24",
-    "stage25",
-    "stage26",
-    "stage27",
-    "stage28",
-    "stage29",
-    "stage30",
-    "stage31",
-    "stage32",
-    "stage33",
-    "stage34",
-    "stage35",
-    "stage36",
-    "stage37",
-    "stage38",
-    "stage39",
-    "stage40"
-  ],
-  "torch_dtype": "float32",
-  "transformers_version": "4.43.1",
-  "use_swiglu_ffn": true
-}
-
-2025-02-15 02:56:16,053 - modeling_utils.py:3621 - from_pretrained - INFO - loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--facebook--dinov2-giant/snapshots/611a9d42f2335e0f921f1e313ad3c1b7178d206d/model.safetensors
-2025-02-15 02:56:16,377 - modeling_utils.py:4450 - _load_pretrained_model - INFO - All model checkpoint weights were used when initializing Dinov2Model.
-
-2025-02-15 02:56:16,377 - modeling_utils.py:4458 - _load_pretrained_model - INFO - All the weights of Dinov2Model were initialized from the model checkpoint at facebook/dinov2-giant.
-If your task is similar to the task the model of the checkpoint was trained on, you can already use Dinov2Model for predictions without further training.
-2025-02-15 02:56:16,563 - image_processing_base.py:375 - get_image_processor_dict - INFO - loading configuration file preprocessor_config.json from cache at /root/.cache/huggingface/hub/models--facebook--dinov2-giant/snapshots/611a9d42f2335e0f921f1e313ad3c1b7178d206d/preprocessor_config.json
-2025-02-15 02:56:16,566 - image_processing_base.py:429 - from_dict - INFO - Image processor BitImageProcessor {
-  "crop_size": {
-    "height": 378,
-    "width": 378
-  },
-  "do_center_crop": true,
-  "do_convert_rgb": true,
-  "do_normalize": true,
-  "do_rescale": true,
-  "do_resize": true,
-  "image_mean": [
-    0.485,
-    0.456,
-    0.406
-  ],
-  "image_processor_type": "BitImageProcessor",
-  "image_std": [
-    0.229,
-    0.224,
-    0.225
-  ],
-  "resample": 3,
-  "rescale_factor": 0.00392156862745098,
-  "size": {
-    "shortest_edge": 378
-  }
-}
-
-2025-02-15 02:56:17,230 - finetune_llama.py:1239 - train - INFO - Total params: 3264865280
-2025-02-15 02:56:17,230 - finetune_llama.py:1240 - train - INFO - Trainable params: 12589056
-2025-02-15 02:56:17,230 - finetune_llama.py:1241 - train - INFO - LM head params: 394002432
-2025-02-15 02:56:19,287 - trainer_callback.py:423 - add_callback - WARNING - You are adding a <class 'transformers.integrations.integration_utils.TensorBoardCallback'> to the callbacks of this Trainer, but there is already one. The currentlist of callbacks is
-:DefaultFlowCallback
-TensorBoardCallback
-2025-02-15 02:56:19,287 - trainer.py:648 - __init__ - INFO - Using auto half precision backend
-2025-02-15 02:56:19,591 - trainer.py:2134 - _inner_training_loop - INFO - ***** Running training *****
-2025-02-15 02:56:19,591 - trainer.py:2135 - _inner_training_loop - INFO -   Num examples = 2
-2025-02-15 02:56:19,591 - trainer.py:2136 - _inner_training_loop - INFO -   Num Epochs = 2
-2025-02-15 02:56:19,591 - trainer.py:2137 - _inner_training_loop - INFO -   Instantaneous batch size per device = 1
-2025-02-15 02:56:19,591 - trainer.py:2140 - _inner_training_loop - INFO -   Total train batch size (w. parallel, distributed & accumulation) = 1
-2025-02-15 02:56:19,591 - trainer.py:2141 - _inner_training_loop - INFO -   Gradient Accumulation steps = 1
-2025-02-15 02:56:19,591 - trainer.py:2142 - _inner_training_loop - INFO -   Total optimization steps = 4
-2025-02-15 02:56:19,593 - trainer.py:2143 - _inner_training_loop - INFO -   Number of trainable parameters = 406,591,488
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb53b35784cd4c3deffdb4f7fbb4b55778d0370f0a55cccf53af92339759f3a2
+size 36427

runtime_logs/run_2025-02-15_03-02-43.log

@@ -1,383 +1,3 @@
-2025-02-15 03:02:43,575 - training_args.py:2100 - _setup_devices - INFO - PyTorch: setting up devices
-2025-02-15 03:02:44,236 - configuration_utils.py:731 - _get_config_dict - INFO - loading configuration file ./checkpoints/longvu_llama3_2/config.json
-2025-02-15 03:02:44,240 - configuration_utils.py:800 - from_dict - INFO - Model config CambrianConfig {
-  "_name_or_path": "/tmp/iopath_cache/manifold_cache/tree/users/shenx/finetune/09281004-cambrian_llama3_2_t576_ov",
-  "architectures": [
-    "CambrianLlamaForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "bos_token_id": 128000,
-  "connect_layer": 2,
-  "connector_depth": 3,
-  "connector_only": true,
-  "dino_threshold": 0.83,
-  "drop_threshold": 0.8,
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
-  "frame_pos": false,
-  "freeze_mm_mlp_adapter": false,
-  "hidden_act": "silu",
-  "hidden_size": 3072,
-  "highres": true,
-  "highres_connect": false,
-  "image_aspect_ratio": "pad",
-  "image_position": 91,
-  "image_token_len": 144,
-  "initializer_range": 0.02,
-  "intermediate_size": 8192,
-  "is_image_newline": true,
-  "is_st_sampler": false,
-  "lowres_token": 8,
-  "max_position_embeddings": 131072,
-  "mlp_bias": false,
-  "mm_patch_merge_type": "flat",
-  "mm_projector_lr": null,
-  "mm_projector_type": "sva",
-  "mm_use_im_patch_token": false,
-  "mm_use_im_start_end": false,
-  "mm_vision_sampler_lr": null,
-  "mm_vision_select_feature": "patch",
-  "mm_vision_select_layer": -2,
-  "mm_vision_tower_aux_list": [
-    "siglip/CLIP-ViT-SO400M-14-384",
-    "facebook/dinov2-giant-res378"
-  ],
-  "mm_vision_tower_aux_token_len_list": [
-    576,
-    576
-  ],
-  "mm_vision_tower_lr": null,
-  "model_type": "cambrian_llama",
-  "num_attention_heads": 24,
-  "num_hidden_layers": 28,
-  "num_key_value_heads": 8,
-  "num_of_vision_sampler_layers": 10,
-  "num_query_group": 1,
-  "pretraining_tp": 1,
-  "query_num_list": [
-    144
-  ],
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": {
-    "factor": 32.0,
-    "high_freq_factor": 4.0,
-    "low_freq_factor": 1.0,
-    "original_max_position_embeddings": 8192,
-    "rope_type": "llama3"
-  },
-  "rope_theta": 500000.0,
-  "spmd_debug": null,
-  "spmd_fsdp_sharding": null,
-  "spmd_mesh": null,
-  "start_of_vision_sampler_layers": 0,
-  "stride_of_vision_sampler_layers": 3,
-  "tie_word_embeddings": false,
-  "tokenizer_model_max_length": 8192,
-  "tokenizer_padding_side": "right",
-  "torch_dtype": "float32",
-  "transformers_version": "4.43.1",
-  "tune_mm_mlp_adapter": false,
-  "unfreeze_mm_vision_tower": false,
-  "use_cache": false,
-  "use_mm_proj": true,
-  "vision_hidden_size": 1024,
-  "vision_tower_aux_token_len_list": [
-    576,
-    576
-  ],
-  "vocab_size": 128256
-}
-
-2025-02-15 03:02:44,240 - modeling_utils.py:3618 - from_pretrained - INFO - loading weights file ./checkpoints/longvu_llama3_2/pytorch_model.bin
-2025-02-15 03:02:44,301 - configuration_utils.py:1038 - from_dict - INFO - Generate config GenerationConfig {
-  "bos_token_id": 128000,
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
-  "use_cache": false
-}
-
-2025-02-15 03:02:44,543 - configuration_utils.py:733 - _get_config_dict - INFO - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--facebook--dinov2-giant/snapshots/611a9d42f2335e0f921f1e313ad3c1b7178d206d/config.json
-2025-02-15 03:02:44,547 - configuration_utils.py:800 - from_dict - INFO - Model config Dinov2Config {
-  "apply_layernorm": true,
-  "architectures": [
-    "Dinov2Model"
-  ],
-  "attention_probs_dropout_prob": 0.0,
-  "drop_path_rate": 0.0,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.0,
-  "hidden_size": 1536,
-  "image_size": 518,
-  "initializer_range": 0.02,
-  "layer_norm_eps": 1e-06,
-  "layerscale_value": 1.0,
-  "mlp_ratio": 4,
-  "model_type": "dinov2",
-  "num_attention_heads": 24,
-  "num_channels": 3,
-  "num_hidden_layers": 40,
-  "out_features": [
-    "stage40"
-  ],
-  "out_indices": [
-    40
-  ],
-  "patch_size": 14,
-  "qkv_bias": true,
-  "reshape_hidden_states": true,
-  "stage_names": [
-    "stem",
-    "stage1",
-    "stage2",
-    "stage3",
-    "stage4",
-    "stage5",
-    "stage6",
-    "stage7",
-    "stage8",
-    "stage9",
-    "stage10",
-    "stage11",
-    "stage12",
-    "stage13",
-    "stage14",
-    "stage15",
-    "stage16",
-    "stage17",
-    "stage18",
-    "stage19",
-    "stage20",
-    "stage21",
-    "stage22",
-    "stage23",
-    "stage24",
-    "stage25",
-    "stage26",
-    "stage27",
-    "stage28",
-    "stage29",
-    "stage30",
-    "stage31",
-    "stage32",
-    "stage33",
-    "stage34",
-    "stage35",
-    "stage36",
-    "stage37",
-    "stage38",
-    "stage39",
-    "stage40"
-  ],
-  "torch_dtype": "float32",
-  "transformers_version": "4.43.1",
-  "use_swiglu_ffn": true
-}
-
-2025-02-15 03:02:46,020 - modeling_utils.py:4450 - _load_pretrained_model - INFO - All model checkpoint weights were used when initializing CambrianLlamaForCausalLM.
-
-2025-02-15 03:02:46,020 - modeling_utils.py:4458 - _load_pretrained_model - INFO - All the weights of CambrianLlamaForCausalLM were initialized from the model checkpoint at ./checkpoints/longvu_llama3_2.
-If your task is similar to the task the model of the checkpoint was trained on, you can already use CambrianLlamaForCausalLM for predictions without further training.
-2025-02-15 03:02:46,026 - configuration_utils.py:991 - from_pretrained - INFO - loading configuration file ./checkpoints/longvu_llama3_2/generation_config.json
-2025-02-15 03:02:46,026 - configuration_utils.py:1038 - from_dict - INFO - Generate config GenerationConfig {
-  "bos_token_id": 128000,
-  "do_sample": true,
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
-  "temperature": 0.6,
-  "top_p": 0.9
-}
-
-2025-02-15 03:02:46,298 - tokenization_utils_base.py:2287 - from_pretrained - INFO - loading file tokenizer.json
-2025-02-15 03:02:46,298 - tokenization_utils_base.py:2287 - from_pretrained - INFO - loading file added_tokens.json
-2025-02-15 03:02:46,299 - tokenization_utils_base.py:2287 - from_pretrained - INFO - loading file special_tokens_map.json
-2025-02-15 03:02:46,299 - tokenization_utils_base.py:2287 - from_pretrained - INFO - loading file tokenizer_config.json
-2025-02-15 03:02:46,709 - tokenization_utils_base.py:2533 - _from_pretrained - INFO - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
-2025-02-15 03:02:47,394 - configuration_utils.py:733 - _get_config_dict - INFO - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--google--siglip-so400m-patch14-384/snapshots/9fdffc58afc957d1a03a25b10dba0329ab15c2a3/config.json
-2025-02-15 03:02:47,396 - configuration_utils.py:800 - from_dict - INFO - Model config SiglipVisionConfig {
-  "attention_dropout": 0.0,
-  "hidden_act": "gelu_pytorch_tanh",
-  "hidden_size": 1152,
-  "image_size": 384,
-  "intermediate_size": 4304,
-  "layer_norm_eps": 1e-06,
-  "model_type": "siglip_vision_model",
-  "num_attention_heads": 16,
-  "num_channels": 3,
-  "num_hidden_layers": 27,
-  "patch_size": 14,
-  "transformers_version": "4.43.1"
-}
-
-2025-02-15 03:02:47,397 - modeling_utils.py:3621 - from_pretrained - INFO - loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--google--siglip-so400m-patch14-384/snapshots/9fdffc58afc957d1a03a25b10dba0329ab15c2a3/model.safetensors
-2025-02-15 03:02:47,666 - modeling_utils.py:4440 - _load_pretrained_model - INFO - Some weights of the model checkpoint at google/siglip-so400m-patch14-384 were not used when initializing SiglipVisionModel: ['logit_bias', 'logit_scale', 'text_model.embeddings.position_embedding.weight', 'text_model.embeddings.token_embedding.weight', 'text_model.encoder.layers.0.layer_norm1.bias', 'text_model.encoder.layers.0.layer_norm1.weight', 'text_model.encoder.layers.0.layer_norm2.bias', 'text_model.encoder.layers.0.layer_norm2.weight', 'text_model.encoder.layers.0.mlp.fc1.bias', 'text_model.encoder.layers.0.mlp.fc1.weight', 'text_model.encoder.layers.0.mlp.fc2.bias', 'text_model.encoder.layers.0.mlp.fc2.weight', 'text_model.encoder.layers.0.self_attn.k_proj.bias', 'text_model.encoder.layers.0.self_attn.k_proj.weight', 'text_model.encoder.layers.0.self_attn.out_proj.bias', 'text_model.encoder.layers.0.self_attn.out_proj.weight', 'text_model.encoder.layers.0.self_attn.q_proj.bias', 'text_model.encoder.layers.0.self_attn.q_proj.weight', 'text_model.encoder.layers.0.self_attn.v_proj.bias', 'text_model.encoder.layers.0.self_attn.v_proj.weight', 'text_model.encoder.layers.1.layer_norm1.bias', 'text_model.encoder.layers.1.layer_norm1.weight', 'text_model.encoder.layers.1.layer_norm2.bias', 'text_model.encoder.layers.1.layer_norm2.weight', 'text_model.encoder.layers.1.mlp.fc1.bias', 'text_model.encoder.layers.1.mlp.fc1.weight', 'text_model.encoder.layers.1.mlp.fc2.bias', 'text_model.encoder.layers.1.mlp.fc2.weight', 'text_model.encoder.layers.1.self_attn.k_proj.bias', 'text_model.encoder.layers.1.self_attn.k_proj.weight', 'text_model.encoder.layers.1.self_attn.out_proj.bias', 'text_model.encoder.layers.1.self_attn.out_proj.weight', 'text_model.encoder.layers.1.self_attn.q_proj.bias', 'text_model.encoder.layers.1.self_attn.q_proj.weight', 'text_model.encoder.layers.1.self_attn.v_proj.bias', 'text_model.encoder.layers.1.self_attn.v_proj.weight', 'text_model.encoder.layers.10.layer_norm1.bias', 'text_model.encoder.layers.10.layer_norm1.weight', 'text_model.encoder.layers.10.layer_norm2.bias', 'text_model.encoder.layers.10.layer_norm2.weight', 'text_model.encoder.layers.10.mlp.fc1.bias', 'text_model.encoder.layers.10.mlp.fc1.weight', 'text_model.encoder.layers.10.mlp.fc2.bias', 'text_model.encoder.layers.10.mlp.fc2.weight', 'text_model.encoder.layers.10.self_attn.k_proj.bias', 'text_model.encoder.layers.10.self_attn.k_proj.weight', 'text_model.encoder.layers.10.self_attn.out_proj.bias', 'text_model.encoder.layers.10.self_attn.out_proj.weight', 'text_model.encoder.layers.10.self_attn.q_proj.bias', 'text_model.encoder.layers.10.self_attn.q_proj.weight', 'text_model.encoder.layers.10.self_attn.v_proj.bias', 'text_model.encoder.layers.10.self_attn.v_proj.weight', 'text_model.encoder.layers.11.layer_norm1.bias', 'text_model.encoder.layers.11.layer_norm1.weight', 'text_model.encoder.layers.11.layer_norm2.bias', 'text_model.encoder.layers.11.layer_norm2.weight', 'text_model.encoder.layers.11.mlp.fc1.bias', 'text_model.encoder.layers.11.mlp.fc1.weight', 'text_model.encoder.layers.11.mlp.fc2.bias', 'text_model.encoder.layers.11.mlp.fc2.weight', 'text_model.encoder.layers.11.self_attn.k_proj.bias', 'text_model.encoder.layers.11.self_attn.k_proj.weight', 'text_model.encoder.layers.11.self_attn.out_proj.bias', 'text_model.encoder.layers.11.self_attn.out_proj.weight', 'text_model.encoder.layers.11.self_attn.q_proj.bias', 'text_model.encoder.layers.11.self_attn.q_proj.weight', 'text_model.encoder.layers.11.self_attn.v_proj.bias', 'text_model.encoder.layers.11.self_attn.v_proj.weight', 'text_model.encoder.layers.12.layer_norm1.bias', 'text_model.encoder.layers.12.layer_norm1.weight', 'text_model.encoder.layers.12.layer_norm2.bias', 'text_model.encoder.layers.12.layer_norm2.weight', 'text_model.encoder.layers.12.mlp.fc1.bias', 'text_model.encoder.layers.12.mlp.fc1.weight', 'text_model.encoder.layers.12.mlp.fc2.bias', 'text_model.encoder.layers.12.mlp.fc2.weight', 'text_model.encoder.layers.12.self_attn.k_proj.bias', 'text_model.encoder.layers.12.self_attn.k_proj.weight', 'text_model.encoder.layers.12.self_attn.out_proj.bias', 'text_model.encoder.layers.12.self_attn.out_proj.weight', 'text_model.encoder.layers.12.self_attn.q_proj.bias', 'text_model.encoder.layers.12.self_attn.q_proj.weight', 'text_model.encoder.layers.12.self_attn.v_proj.bias', 'text_model.encoder.layers.12.self_attn.v_proj.weight', 'text_model.encoder.layers.13.layer_norm1.bias', 'text_model.encoder.layers.13.layer_norm1.weight', 'text_model.encoder.layers.13.layer_norm2.bias', 'text_model.encoder.layers.13.layer_norm2.weight', 'text_model.encoder.layers.13.mlp.fc1.bias', 'text_model.encoder.layers.13.mlp.fc1.weight', 'text_model.encoder.layers.13.mlp.fc2.bias', 'text_model.encoder.layers.13.mlp.fc2.weight', 'text_model.encoder.layers.13.self_attn.k_proj.bias', 'text_model.encoder.layers.13.self_attn.k_proj.weight', 'text_model.encoder.layers.13.self_attn.out_proj.bias', 'text_model.encoder.layers.13.self_attn.out_proj.weight', 'text_model.encoder.layers.13.self_attn.q_proj.bias', 'text_model.encoder.layers.13.self_attn.q_proj.weight', 'text_model.encoder.layers.13.self_attn.v_proj.bias', 'text_model.encoder.layers.13.self_attn.v_proj.weight', 'text_model.encoder.layers.14.layer_norm1.bias', 'text_model.encoder.layers.14.layer_norm1.weight', 'text_model.encoder.layers.14.layer_norm2.bias', 'text_model.encoder.layers.14.layer_norm2.weight', 'text_model.encoder.layers.14.mlp.fc1.bias', 'text_model.encoder.layers.14.mlp.fc1.weight', 'text_model.encoder.layers.14.mlp.fc2.bias', 'text_model.encoder.layers.14.mlp.fc2.weight', 'text_model.encoder.layers.14.self_attn.k_proj.bias', 'text_model.encoder.layers.14.self_attn.k_proj.weight', 'text_model.encoder.layers.14.self_attn.out_proj.bias', 'text_model.encoder.layers.14.self_attn.out_proj.weight', 'text_model.encoder.layers.14.self_attn.q_proj.bias', 'text_model.encoder.layers.14.self_attn.q_proj.weight', 'text_model.encoder.layers.14.self_attn.v_proj.bias', 'text_model.encoder.layers.14.self_attn.v_proj.weight', 'text_model.encoder.layers.15.layer_norm1.bias', 'text_model.encoder.layers.15.layer_norm1.weight', 'text_model.encoder.layers.15.layer_norm2.bias', 'text_model.encoder.layers.15.layer_norm2.weight', 'text_model.encoder.layers.15.mlp.fc1.bias', 'text_model.encoder.layers.15.mlp.fc1.weight', 'text_model.encoder.layers.15.mlp.fc2.bias', 'text_model.encoder.layers.15.mlp.fc2.weight', 'text_model.encoder.layers.15.self_attn.k_proj.bias', 'text_model.encoder.layers.15.self_attn.k_proj.weight', 'text_model.encoder.layers.15.self_attn.out_proj.bias', 'text_model.encoder.layers.15.self_attn.out_proj.weight', 'text_model.encoder.layers.15.self_attn.q_proj.bias', 'text_model.encoder.layers.15.self_attn.q_proj.weight', 'text_model.encoder.layers.15.self_attn.v_proj.bias', 'text_model.encoder.layers.15.self_attn.v_proj.weight', 'text_model.encoder.layers.16.layer_norm1.bias', 'text_model.encoder.layers.16.layer_norm1.weight', 'text_model.encoder.layers.16.layer_norm2.bias', 'text_model.encoder.layers.16.layer_norm2.weight', 'text_model.encoder.layers.16.mlp.fc1.bias', 'text_model.encoder.layers.16.mlp.fc1.weight', 'text_model.encoder.layers.16.mlp.fc2.bias', 'text_model.encoder.layers.16.mlp.fc2.weight', 'text_model.encoder.layers.16.self_attn.k_proj.bias', 'text_model.encoder.layers.16.self_attn.k_proj.weight', 'text_model.encoder.layers.16.self_attn.out_proj.bias', 'text_model.encoder.layers.16.self_attn.out_proj.weight', 'text_model.encoder.layers.16.self_attn.q_proj.bias', 'text_model.encoder.layers.16.self_attn.q_proj.weight', 'text_model.encoder.layers.16.self_attn.v_proj.bias', 'text_model.encoder.layers.16.self_attn.v_proj.weight', 'text_model.encoder.layers.17.layer_norm1.bias', 'text_model.encoder.layers.17.layer_norm1.weight', 'text_model.encoder.layers.17.layer_norm2.bias', 'text_model.encoder.layers.17.layer_norm2.weight', 'text_model.encoder.layers.17.mlp.fc1.bias', 'text_model.encoder.layers.17.mlp.fc1.weight', 'text_model.encoder.layers.17.mlp.fc2.bias', 'text_model.encoder.layers.17.mlp.fc2.weight', 'text_model.encoder.layers.17.self_attn.k_proj.bias', 'text_model.encoder.layers.17.self_attn.k_proj.weight', 'text_model.encoder.layers.17.self_attn.out_proj.bias', 'text_model.encoder.layers.17.self_attn.out_proj.weight', 'text_model.encoder.layers.17.self_attn.q_proj.bias', 'text_model.encoder.layers.17.self_attn.q_proj.weight', 'text_model.encoder.layers.17.self_attn.v_proj.bias', 'text_model.encoder.layers.17.self_attn.v_proj.weight', 'text_model.encoder.layers.18.layer_norm1.bias', 'text_model.encoder.layers.18.layer_norm1.weight', 'text_model.encoder.layers.18.layer_norm2.bias', 'text_model.encoder.layers.18.layer_norm2.weight', 'text_model.encoder.layers.18.mlp.fc1.bias', 'text_model.encoder.layers.18.mlp.fc1.weight', 'text_model.encoder.layers.18.mlp.fc2.bias', 'text_model.encoder.layers.18.mlp.fc2.weight', 'text_model.encoder.layers.18.self_attn.k_proj.bias', 'text_model.encoder.layers.18.self_attn.k_proj.weight', 'text_model.encoder.layers.18.self_attn.out_proj.bias', 'text_model.encoder.layers.18.self_attn.out_proj.weight', 'text_model.encoder.layers.18.self_attn.q_proj.bias', 'text_model.encoder.layers.18.self_attn.q_proj.weight', 'text_model.encoder.layers.18.self_attn.v_proj.bias', 'text_model.encoder.layers.18.self_attn.v_proj.weight', 'text_model.encoder.layers.19.layer_norm1.bias', 'text_model.encoder.layers.19.layer_norm1.weight', 'text_model.encoder.layers.19.layer_norm2.bias', 'text_model.encoder.layers.19.layer_norm2.weight', 'text_model.encoder.layers.19.mlp.fc1.bias', 'text_model.encoder.layers.19.mlp.fc1.weight', 'text_model.encoder.layers.19.mlp.fc2.bias', 'text_model.encoder.layers.19.mlp.fc2.weight', 'text_model.encoder.layers.19.self_attn.k_proj.bias', 'text_model.encoder.layers.19.self_attn.k_proj.weight', 'text_model.encoder.layers.19.self_attn.out_proj.bias', 'text_model.encoder.layers.19.self_attn.out_proj.weight', 'text_model.encoder.layers.19.self_attn.q_proj.bias', 'text_model.encoder.layers.19.self_attn.q_proj.weight', 'text_model.encoder.layers.19.self_attn.v_proj.bias', 'text_model.encoder.layers.19.self_attn.v_proj.weight', 'text_model.encoder.layers.2.layer_norm1.bias', 'text_model.encoder.layers.2.layer_norm1.weight', 'text_model.encoder.layers.2.layer_norm2.bias', 'text_model.encoder.layers.2.layer_norm2.weight', 'text_model.encoder.layers.2.mlp.fc1.bias', 'text_model.encoder.layers.2.mlp.fc1.weight', 'text_model.encoder.layers.2.mlp.fc2.bias', 'text_model.encoder.layers.2.mlp.fc2.weight', 'text_model.encoder.layers.2.self_attn.k_proj.bias', 'text_model.encoder.layers.2.self_attn.k_proj.weight', 'text_model.encoder.layers.2.self_attn.out_proj.bias', 'text_model.encoder.layers.2.self_attn.out_proj.weight', 'text_model.encoder.layers.2.self_attn.q_proj.bias', 'text_model.encoder.layers.2.self_attn.q_proj.weight', 'text_model.encoder.layers.2.self_attn.v_proj.bias', 'text_model.encoder.layers.2.self_attn.v_proj.weight', 'text_model.encoder.layers.20.layer_norm1.bias', 'text_model.encoder.layers.20.layer_norm1.weight', 'text_model.encoder.layers.20.layer_norm2.bias', 'text_model.encoder.layers.20.layer_norm2.weight', 'text_model.encoder.layers.20.mlp.fc1.bias', 'text_model.encoder.layers.20.mlp.fc1.weight', 'text_model.encoder.layers.20.mlp.fc2.bias', 'text_model.encoder.layers.20.mlp.fc2.weight', 'text_model.encoder.layers.20.self_attn.k_proj.bias', 'text_model.encoder.layers.20.self_attn.k_proj.weight', 'text_model.encoder.layers.20.self_attn.out_proj.bias', 'text_model.encoder.layers.20.self_attn.out_proj.weight', 'text_model.encoder.layers.20.self_attn.q_proj.bias', 'text_model.encoder.layers.20.self_attn.q_proj.weight', 'text_model.encoder.layers.20.self_attn.v_proj.bias', 'text_model.encoder.layers.20.self_attn.v_proj.weight', 'text_model.encoder.layers.21.layer_norm1.bias', 'text_model.encoder.layers.21.layer_norm1.weight', 'text_model.encoder.layers.21.layer_norm2.bias', 'text_model.encoder.layers.21.layer_norm2.weight', 'text_model.encoder.layers.21.mlp.fc1.bias', 'text_model.encoder.layers.21.mlp.fc1.weight', 'text_model.encoder.layers.21.mlp.fc2.bias', 'text_model.encoder.layers.21.mlp.fc2.weight', 'text_model.encoder.layers.21.self_attn.k_proj.bias', 'text_model.encoder.layers.21.self_attn.k_proj.weight', 'text_model.encoder.layers.21.self_attn.out_proj.bias', 'text_model.encoder.layers.21.self_attn.out_proj.weight', 'text_model.encoder.layers.21.self_attn.q_proj.bias', 'text_model.encoder.layers.21.self_attn.q_proj.weight', 'text_model.encoder.layers.21.self_attn.v_proj.bias', 'text_model.encoder.layers.21.self_attn.v_proj.weight', 'text_model.encoder.layers.22.layer_norm1.bias', 'text_model.encoder.layers.22.layer_norm1.weight', 'text_model.encoder.layers.22.layer_norm2.bias', 'text_model.encoder.layers.22.layer_norm2.weight', 'text_model.encoder.layers.22.mlp.fc1.bias', 'text_model.encoder.layers.22.mlp.fc1.weight', 'text_model.encoder.layers.22.mlp.fc2.bias', 'text_model.encoder.layers.22.mlp.fc2.weight', 'text_model.encoder.layers.22.self_attn.k_proj.bias', 'text_model.encoder.layers.22.self_attn.k_proj.weight', 'text_model.encoder.layers.22.self_attn.out_proj.bias', 'text_model.encoder.layers.22.self_attn.out_proj.weight', 'text_model.encoder.layers.22.self_attn.q_proj.bias', 'text_model.encoder.layers.22.self_attn.q_proj.weight', 'text_model.encoder.layers.22.self_attn.v_proj.bias', 'text_model.encoder.layers.22.self_attn.v_proj.weight', 'text_model.encoder.layers.23.layer_norm1.bias', 'text_model.encoder.layers.23.layer_norm1.weight', 'text_model.encoder.layers.23.layer_norm2.bias', 'text_model.encoder.layers.23.layer_norm2.weight', 'text_model.encoder.layers.23.mlp.fc1.bias', 'text_model.encoder.layers.23.mlp.fc1.weight', 'text_model.encoder.layers.23.mlp.fc2.bias', 'text_model.encoder.layers.23.mlp.fc2.weight', 'text_model.encoder.layers.23.self_attn.k_proj.bias', 'text_model.encoder.layers.23.self_attn.k_proj.weight', 'text_model.encoder.layers.23.self_attn.out_proj.bias', 'text_model.encoder.layers.23.self_attn.out_proj.weight', 'text_model.encoder.layers.23.self_attn.q_proj.bias', 'text_model.encoder.layers.23.self_attn.q_proj.weight', 'text_model.encoder.layers.23.self_attn.v_proj.bias', 'text_model.encoder.layers.23.self_attn.v_proj.weight', 'text_model.encoder.layers.24.layer_norm1.bias', 'text_model.encoder.layers.24.layer_norm1.weight', 'text_model.encoder.layers.24.layer_norm2.bias', 'text_model.encoder.layers.24.layer_norm2.weight', 'text_model.encoder.layers.24.mlp.fc1.bias', 'text_model.encoder.layers.24.mlp.fc1.weight', 'text_model.encoder.layers.24.mlp.fc2.bias', 'text_model.encoder.layers.24.mlp.fc2.weight', 'text_model.encoder.layers.24.self_attn.k_proj.bias', 'text_model.encoder.layers.24.self_attn.k_proj.weight', 'text_model.encoder.layers.24.self_attn.out_proj.bias', 'text_model.encoder.layers.24.self_attn.out_proj.weight', 'text_model.encoder.layers.24.self_attn.q_proj.bias', 'text_model.encoder.layers.24.self_attn.q_proj.weight', 'text_model.encoder.layers.24.self_attn.v_proj.bias', 'text_model.encoder.layers.24.self_attn.v_proj.weight', 'text_model.encoder.layers.25.layer_norm1.bias', 'text_model.encoder.layers.25.layer_norm1.weight', 'text_model.encoder.layers.25.layer_norm2.bias', 'text_model.encoder.layers.25.layer_norm2.weight', 'text_model.encoder.layers.25.mlp.fc1.bias', 'text_model.encoder.layers.25.mlp.fc1.weight', 'text_model.encoder.layers.25.mlp.fc2.bias', 'text_model.encoder.layers.25.mlp.fc2.weight', 'text_model.encoder.layers.25.self_attn.k_proj.bias', 'text_model.encoder.layers.25.self_attn.k_proj.weight', 'text_model.encoder.layers.25.self_attn.out_proj.bias', 'text_model.encoder.layers.25.self_attn.out_proj.weight', 'text_model.encoder.layers.25.self_attn.q_proj.bias', 'text_model.encoder.layers.25.self_attn.q_proj.weight', 'text_model.encoder.layers.25.self_attn.v_proj.bias', 'text_model.encoder.layers.25.self_attn.v_proj.weight', 'text_model.encoder.layers.26.layer_norm1.bias', 'text_model.encoder.layers.26.layer_norm1.weight', 'text_model.encoder.layers.26.layer_norm2.bias', 'text_model.encoder.layers.26.layer_norm2.weight', 'text_model.encoder.layers.26.mlp.fc1.bias', 'text_model.encoder.layers.26.mlp.fc1.weight', 'text_model.encoder.layers.26.mlp.fc2.bias', 'text_model.encoder.layers.26.mlp.fc2.weight', 'text_model.encoder.layers.26.self_attn.k_proj.bias', 'text_model.encoder.layers.26.self_attn.k_proj.weight', 'text_model.encoder.layers.26.self_attn.out_proj.bias', 'text_model.encoder.layers.26.self_attn.out_proj.weight', 'text_model.encoder.layers.26.self_attn.q_proj.bias', 'text_model.encoder.layers.26.self_attn.q_proj.weight', 'text_model.encoder.layers.26.self_attn.v_proj.bias', 'text_model.encoder.layers.26.self_attn.v_proj.weight', 'text_model.encoder.layers.3.layer_norm1.bias', 'text_model.encoder.layers.3.layer_norm1.weight', 'text_model.encoder.layers.3.layer_norm2.bias', 'text_model.encoder.layers.3.layer_norm2.weight', 'text_model.encoder.layers.3.mlp.fc1.bias', 'text_model.encoder.layers.3.mlp.fc1.weight', 'text_model.encoder.layers.3.mlp.fc2.bias', 'text_model.encoder.layers.3.mlp.fc2.weight', 'text_model.encoder.layers.3.self_attn.k_proj.bias', 'text_model.encoder.layers.3.self_attn.k_proj.weight', 'text_model.encoder.layers.3.self_attn.out_proj.bias', 'text_model.encoder.layers.3.self_attn.out_proj.weight', 'text_model.encoder.layers.3.self_attn.q_proj.bias', 'text_model.encoder.layers.3.self_attn.q_proj.weight', 'text_model.encoder.layers.3.self_attn.v_proj.bias', 'text_model.encoder.layers.3.self_attn.v_proj.weight', 'text_model.encoder.layers.4.layer_norm1.bias', 'text_model.encoder.layers.4.layer_norm1.weight', 'text_model.encoder.layers.4.layer_norm2.bias', 'text_model.encoder.layers.4.layer_norm2.weight', 'text_model.encoder.layers.4.mlp.fc1.bias', 'text_model.encoder.layers.4.mlp.fc1.weight', 'text_model.encoder.layers.4.mlp.fc2.bias', 'text_model.encoder.layers.4.mlp.fc2.weight', 'text_model.encoder.layers.4.self_attn.k_proj.bias', 'text_model.encoder.layers.4.self_attn.k_proj.weight', 'text_model.encoder.layers.4.self_attn.out_proj.bias', 'text_model.encoder.layers.4.self_attn.out_proj.weight', 'text_model.encoder.layers.4.self_attn.q_proj.bias', 'text_model.encoder.layers.4.self_attn.q_proj.weight', 'text_model.encoder.layers.4.self_attn.v_proj.bias', 'text_model.encoder.layers.4.self_attn.v_proj.weight', 'text_model.encoder.layers.5.layer_norm1.bias', 'text_model.encoder.layers.5.layer_norm1.weight', 'text_model.encoder.layers.5.layer_norm2.bias', 'text_model.encoder.layers.5.layer_norm2.weight', 'text_model.encoder.layers.5.mlp.fc1.bias', 'text_model.encoder.layers.5.mlp.fc1.weight', 'text_model.encoder.layers.5.mlp.fc2.bias', 'text_model.encoder.layers.5.mlp.fc2.weight', 'text_model.encoder.layers.5.self_attn.k_proj.bias', 'text_model.encoder.layers.5.self_attn.k_proj.weight', 'text_model.encoder.layers.5.self_attn.out_proj.bias', 'text_model.encoder.layers.5.self_attn.out_proj.weight', 'text_model.encoder.layers.5.self_attn.q_proj.bias', 'text_model.encoder.layers.5.self_attn.q_proj.weight', 'text_model.encoder.layers.5.self_attn.v_proj.bias', 'text_model.encoder.layers.5.self_attn.v_proj.weight', 'text_model.encoder.layers.6.layer_norm1.bias', 'text_model.encoder.layers.6.layer_norm1.weight', 'text_model.encoder.layers.6.layer_norm2.bias', 'text_model.encoder.layers.6.layer_norm2.weight', 'text_model.encoder.layers.6.mlp.fc1.bias', 'text_model.encoder.layers.6.mlp.fc1.weight', 'text_model.encoder.layers.6.mlp.fc2.bias', 'text_model.encoder.layers.6.mlp.fc2.weight', 'text_model.encoder.layers.6.self_attn.k_proj.bias', 'text_model.encoder.layers.6.self_attn.k_proj.weight', 'text_model.encoder.layers.6.self_attn.out_proj.bias', 'text_model.encoder.layers.6.self_attn.out_proj.weight', 'text_model.encoder.layers.6.self_attn.q_proj.bias', 'text_model.encoder.layers.6.self_attn.q_proj.weight', 'text_model.encoder.layers.6.self_attn.v_proj.bias', 'text_model.encoder.layers.6.self_attn.v_proj.weight', 'text_model.encoder.layers.7.layer_norm1.bias', 'text_model.encoder.layers.7.layer_norm1.weight', 'text_model.encoder.layers.7.layer_norm2.bias', 'text_model.encoder.layers.7.layer_norm2.weight', 'text_model.encoder.layers.7.mlp.fc1.bias', 'text_model.encoder.layers.7.mlp.fc1.weight', 'text_model.encoder.layers.7.mlp.fc2.bias', 'text_model.encoder.layers.7.mlp.fc2.weight', 'text_model.encoder.layers.7.self_attn.k_proj.bias', 'text_model.encoder.layers.7.self_attn.k_proj.weight', 'text_model.encoder.layers.7.self_attn.out_proj.bias', 'text_model.encoder.layers.7.self_attn.out_proj.weight', 'text_model.encoder.layers.7.self_attn.q_proj.bias', 'text_model.encoder.layers.7.self_attn.q_proj.weight', 'text_model.encoder.layers.7.self_attn.v_proj.bias', 'text_model.encoder.layers.7.self_attn.v_proj.weight', 'text_model.encoder.layers.8.layer_norm1.bias', 'text_model.encoder.layers.8.layer_norm1.weight', 'text_model.encoder.layers.8.layer_norm2.bias', 'text_model.encoder.layers.8.layer_norm2.weight', 'text_model.encoder.layers.8.mlp.fc1.bias', 'text_model.encoder.layers.8.mlp.fc1.weight', 'text_model.encoder.layers.8.mlp.fc2.bias', 'text_model.encoder.layers.8.mlp.fc2.weight', 'text_model.encoder.layers.8.self_attn.k_proj.bias', 'text_model.encoder.layers.8.self_attn.k_proj.weight', 'text_model.encoder.layers.8.self_attn.out_proj.bias', 'text_model.encoder.layers.8.self_attn.out_proj.weight', 'text_model.encoder.layers.8.self_attn.q_proj.bias', 'text_model.encoder.layers.8.self_attn.q_proj.weight', 'text_model.encoder.layers.8.self_attn.v_proj.bias', 'text_model.encoder.layers.8.self_attn.v_proj.weight', 'text_model.encoder.layers.9.layer_norm1.bias', 'text_model.encoder.layers.9.layer_norm1.weight', 'text_model.encoder.layers.9.layer_norm2.bias', 'text_model.encoder.layers.9.layer_norm2.weight', 'text_model.encoder.layers.9.mlp.fc1.bias', 'text_model.encoder.layers.9.mlp.fc1.weight', 'text_model.encoder.layers.9.mlp.fc2.bias', 'text_model.encoder.layers.9.mlp.fc2.weight', 'text_model.encoder.layers.9.self_attn.k_proj.bias', 'text_model.encoder.layers.9.self_attn.k_proj.weight', 'text_model.encoder.layers.9.self_attn.out_proj.bias', 'text_model.encoder.layers.9.self_attn.out_proj.weight', 'text_model.encoder.layers.9.self_attn.q_proj.bias', 'text_model.encoder.layers.9.self_attn.q_proj.weight', 'text_model.encoder.layers.9.self_attn.v_proj.bias', 'text_model.encoder.layers.9.self_attn.v_proj.weight', 'text_model.final_layer_norm.bias', 'text_model.final_layer_norm.weight', 'text_model.head.bias', 'text_model.head.weight']
-- This IS expected if you are initializing SiglipVisionModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
-- This IS NOT expected if you are initializing SiglipVisionModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
-2025-02-15 03:02:47,668 - modeling_utils.py:4458 - _load_pretrained_model - INFO - All the weights of SiglipVisionModel were initialized from the model checkpoint at google/siglip-so400m-patch14-384.
-If your task is similar to the task the model of the checkpoint was trained on, you can already use SiglipVisionModel for predictions without further training.
-2025-02-15 03:02:47,864 - image_processing_base.py:375 - get_image_processor_dict - INFO - loading configuration file preprocessor_config.json from cache at /root/.cache/huggingface/hub/models--google--siglip-so400m-patch14-384/snapshots/9fdffc58afc957d1a03a25b10dba0329ab15c2a3/preprocessor_config.json
-2025-02-15 03:02:47,865 - image_processing_base.py:429 - from_dict - INFO - Image processor SiglipImageProcessor {
-  "do_convert_rgb": null,
-  "do_normalize": true,
-  "do_rescale": true,
-  "do_resize": true,
-  "image_mean": [
-    0.5,
-    0.5,
-    0.5
-  ],
-  "image_processor_type": "SiglipImageProcessor",
-  "image_std": [
-    0.5,
-    0.5,
-    0.5
-  ],
-  "processor_class": "SiglipProcessor",
-  "resample": 3,
-  "rescale_factor": 0.00392156862745098,
-  "size": {
-    "height": 384,
-    "width": 384
-  }
-}
-
-2025-02-15 03:02:48,307 - configuration_utils.py:733 - _get_config_dict - INFO - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--facebook--dinov2-giant/snapshots/611a9d42f2335e0f921f1e313ad3c1b7178d206d/config.json
-2025-02-15 03:02:48,310 - configuration_utils.py:800 - from_dict - INFO - Model config Dinov2Config {
-  "apply_layernorm": true,
-  "architectures": [
-    "Dinov2Model"
-  ],
-  "attention_probs_dropout_prob": 0.0,
-  "drop_path_rate": 0.0,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.0,
-  "hidden_size": 1536,
-  "image_size": 518,
-  "initializer_range": 0.02,
-  "layer_norm_eps": 1e-06,
-  "layerscale_value": 1.0,
-  "mlp_ratio": 4,
-  "model_type": "dinov2",
-  "num_attention_heads": 24,
-  "num_channels": 3,
-  "num_hidden_layers": 40,
-  "out_features": [
-    "stage40"
-  ],
-  "out_indices": [
-    40
-  ],
-  "patch_size": 14,
-  "qkv_bias": true,
-  "reshape_hidden_states": true,
-  "stage_names": [
-    "stem",
-    "stage1",
-    "stage2",
-    "stage3",
-    "stage4",
-    "stage5",
-    "stage6",
-    "stage7",
-    "stage8",
-    "stage9",
-    "stage10",
-    "stage11",
-    "stage12",
-    "stage13",
-    "stage14",
-    "stage15",
-    "stage16",
-    "stage17",
-    "stage18",
-    "stage19",
-    "stage20",
-    "stage21",
-    "stage22",
-    "stage23",
-    "stage24",
-    "stage25",
-    "stage26",
-    "stage27",
-    "stage28",
-    "stage29",
-    "stage30",
-    "stage31",
-    "stage32",
-    "stage33",
-    "stage34",
-    "stage35",
-    "stage36",
-    "stage37",
-    "stage38",
-    "stage39",
-    "stage40"
-  ],
-  "torch_dtype": "float32",
-  "transformers_version": "4.43.1",
-  "use_swiglu_ffn": true
-}
-
-2025-02-15 03:02:48,310 - modeling_utils.py:3621 - from_pretrained - INFO - loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--facebook--dinov2-giant/snapshots/611a9d42f2335e0f921f1e313ad3c1b7178d206d/model.safetensors
-2025-02-15 03:02:48,895 - modeling_utils.py:4450 - _load_pretrained_model - INFO - All model checkpoint weights were used when initializing Dinov2Model.
-
-2025-02-15 03:02:48,895 - modeling_utils.py:4458 - _load_pretrained_model - INFO - All the weights of Dinov2Model were initialized from the model checkpoint at facebook/dinov2-giant.
-If your task is similar to the task the model of the checkpoint was trained on, you can already use Dinov2Model for predictions without further training.
-2025-02-15 03:02:49,091 - image_processing_base.py:375 - get_image_processor_dict - INFO - loading configuration file preprocessor_config.json from cache at /root/.cache/huggingface/hub/models--facebook--dinov2-giant/snapshots/611a9d42f2335e0f921f1e313ad3c1b7178d206d/preprocessor_config.json
-2025-02-15 03:02:49,094 - image_processing_base.py:429 - from_dict - INFO - Image processor BitImageProcessor {
-  "crop_size": {
-    "height": 378,
-    "width": 378
-  },
-  "do_center_crop": true,
-  "do_convert_rgb": true,
-  "do_normalize": true,
-  "do_rescale": true,
-  "do_resize": true,
-  "image_mean": [
-    0.485,
-    0.456,
-    0.406
-  ],
-  "image_processor_type": "BitImageProcessor",
-  "image_std": [
-    0.229,
-    0.224,
-    0.225
-  ],
-  "resample": 3,
-  "rescale_factor": 0.00392156862745098,
-  "size": {
-    "shortest_edge": 378
-  }
-}
-
-2025-02-15 03:02:50,031 - finetune_llama.py:1239 - train - INFO - Total params: 3264865280
-2025-02-15 03:02:50,031 - finetune_llama.py:1240 - train - INFO - Trainable params: 12589056
-2025-02-15 03:02:50,031 - finetune_llama.py:1241 - train - INFO - LM head params: 394002432
-2025-02-15 03:02:52,464 - trainer_callback.py:423 - add_callback - WARNING - You are adding a <class 'transformers.integrations.integration_utils.TensorBoardCallback'> to the callbacks of this Trainer, but there is already one. The currentlist of callbacks is
-:DefaultFlowCallback
-TensorBoardCallback
-2025-02-15 03:02:52,464 - trainer.py:648 - __init__ - INFO - Using auto half precision backend
-2025-02-15 03:02:52,465 - trainer.py:2526 - _load_from_checkpoint - INFO - Loading model from ./checkpoints/cambrian_llama3_2/checkpoint-4.
-2025-02-15 03:02:55,358 - trainer.py:2134 - _inner_training_loop - INFO - ***** Running training *****
-2025-02-15 03:02:55,358 - trainer.py:2135 - _inner_training_loop - INFO -   Num examples = 540
-2025-02-15 03:02:55,358 - trainer.py:2136 - _inner_training_loop - INFO -   Num Epochs = 2
-2025-02-15 03:02:55,358 - trainer.py:2137 - _inner_training_loop - INFO -   Instantaneous batch size per device = 1
-2025-02-15 03:02:55,358 - trainer.py:2140 - _inner_training_loop - INFO -   Total train batch size (w. parallel, distributed & accumulation) = 1
-2025-02-15 03:02:55,358 - trainer.py:2141 - _inner_training_loop - INFO -   Gradient Accumulation steps = 1
-2025-02-15 03:02:55,358 - trainer.py:2142 - _inner_training_loop - INFO -   Total optimization steps = 1,080
-2025-02-15 03:02:55,359 - trainer.py:2143 - _inner_training_loop - INFO -   Number of trainable parameters = 406,591,488
-2025-02-15 03:02:55,359 - trainer.py:2165 - _inner_training_loop - INFO -   Continuing training from checkpoint, will skip to saved global_step
-2025-02-15 03:02:55,359 - trainer.py:2166 - _inner_training_loop - INFO -   Continuing training from epoch 0
-2025-02-15 03:02:55,359 - trainer.py:2167 - _inner_training_loop - INFO -   Continuing training from global step 4
-2025-02-15 03:02:55,359 - trainer.py:2169 - _inner_training_loop - INFO -   Will skip the first 0 epochs then the first 4 batches in the first epoch.
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8ca82d50a27c49e4b6b579372386820290395eb6a9384bbeba1d94c653c460a
+size 37091