running_log.txt

[INFO|2024-12-01 18:24:23] parser.py:355 >> Process rank: 1, device: cuda:1, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16

[WARNING|2024-12-01 18:24:23] logging.py:162 >> We recommend enable `upcast_layernorm` in quantized training.

[WARNING|2024-12-01 18:24:23] logging.py:162 >> `ddp_find_unused_parameters` needs to be set as False for LoRA in DDP training.

[INFO|2024-12-01 18:24:23] parser.py:355 >> Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16

[INFO|2024-12-01 18:24:23] configuration_utils.py:679 >> loading configuration file config.json from cache at /home/dl/.cache/huggingface/hub/models--llava-hf--LLaVA-NeXT-Video-7B-hf/snapshots/b3b624d0915bb487ef1abb15255aaa2cd5581205/config.json

[INFO|2024-12-01 18:24:23] configuration_utils.py:746 >> Model config LlavaNextVideoConfig {
  "_name_or_path": "llava-hf/LLaVA-NeXT-Video-7B-hf",
  "architectures": [
    "LlavaNextVideoForConditionalGeneration"
  ],
  "ignore_index": -100,
  "image_grid_pinpoints": [
    [
      336,
      672
    ],
    [
      672,
      336
    ],
    [
      672,
      672
    ],
    [
      1008,
      336
    ],
    [
      336,
      1008
    ]
  ],
  "image_seq_length": 576,
  "image_token_index": 32001,
  "model_type": "llava_next_video",
  "projector_hidden_act": "gelu",
  "spatial_pool_mode": "average",
  "spatial_pool_out_channels": 1024,
  "spatial_pool_stride": 2,
  "text_config": {
    "_attn_implementation_autoset": false,
    "_name_or_path": "lmsys/vicuna-7b-v1.5",
    "add_cross_attention": false,
    "architectures": [
      "LlamaForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": 1,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": 2,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "intermediate_size": 11008,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "length_penalty": 1.0,
    "max_length": 20,
    "max_position_embeddings": 4096,
    "min_length": 0,
    "mlp_bias": false,
    "model_type": "llama",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 32,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 32,
    "num_key_value_heads": 32,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": 0,
    "prefix": null,
    "pretraining_tp": 1,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "rms_norm_eps": 1e-05,
    "rope_scaling": {
      "factor": 2.5,
      "rope_type": "linear",
      "type": "linear"
    },
    "rope_theta": 10000.0,
    "sep_token_id": null,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": false,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": "float16",
    "torchscript": false,
    "type": "linear",
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_cache": true,
    "vocab_size": 32064
  },
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.46.1",
  "use_image_newline_parameter": true,
  "video_seq_length": 288,
  "video_token_index": 32000,
  "vision_config": {
    "_attn_implementation_autoset": false,
    "_name_or_path": "",
    "add_cross_attention": false,
    "architectures": null,
    "attention_dropout": 0.0,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": null,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": null,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "hidden_act": "quick_gelu",
    "hidden_size": 1024,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "image_size": 336,
    "initializer_factor": 1.0,
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-05,
    "length_penalty": 1.0,
    "max_length": 20,
    "min_length": 0,
    "model_type": "clip_vision_model",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 16,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_channels": 3,
    "num_hidden_layers": 24,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": null,
    "patch_size": 14,
    "prefix": null,
    "problem_type": null,
    "projection_dim": 768,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "sep_token_id": null,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": null,
    "torchscript": false,
    "typical_p": 1.0,
    "use_bfloat16": false,
    "vocab_size": 32000
  },
  "vision_feature_layer": -2,
  "vision_feature_select_strategy": "default"
}


[INFO|2024-12-01 18:24:23] tokenization_utils_base.py:2211 >> loading file tokenizer.model from cache at /home/dl/.cache/huggingface/hub/models--llava-hf--LLaVA-NeXT-Video-7B-hf/snapshots/b3b624d0915bb487ef1abb15255aaa2cd5581205/tokenizer.model

[INFO|2024-12-01 18:24:23] tokenization_utils_base.py:2211 >> loading file tokenizer.json from cache at /home/dl/.cache/huggingface/hub/models--llava-hf--LLaVA-NeXT-Video-7B-hf/snapshots/b3b624d0915bb487ef1abb15255aaa2cd5581205/tokenizer.json

[INFO|2024-12-01 18:24:23] tokenization_utils_base.py:2211 >> loading file added_tokens.json from cache at /home/dl/.cache/huggingface/hub/models--llava-hf--LLaVA-NeXT-Video-7B-hf/snapshots/b3b624d0915bb487ef1abb15255aaa2cd5581205/added_tokens.json

[INFO|2024-12-01 18:24:23] tokenization_utils_base.py:2211 >> loading file special_tokens_map.json from cache at /home/dl/.cache/huggingface/hub/models--llava-hf--LLaVA-NeXT-Video-7B-hf/snapshots/b3b624d0915bb487ef1abb15255aaa2cd5581205/special_tokens_map.json

[INFO|2024-12-01 18:24:23] tokenization_utils_base.py:2211 >> loading file tokenizer_config.json from cache at /home/dl/.cache/huggingface/hub/models--llava-hf--LLaVA-NeXT-Video-7B-hf/snapshots/b3b624d0915bb487ef1abb15255aaa2cd5581205/tokenizer_config.json

[INFO|2024-12-01 18:24:23] tokenization_utils_base.py:2475 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.

[INFO|2024-12-01 18:24:24] processing_utils.py:695 >> loading configuration file processor_config.json from cache at /home/dl/.cache/huggingface/hub/models--llava-hf--LLaVA-NeXT-Video-7B-hf/snapshots/b3b624d0915bb487ef1abb15255aaa2cd5581205/processor_config.json

[INFO|2024-12-01 18:24:24] image_processing_base.py:375 >> loading configuration file preprocessor_config.json from cache at /home/dl/.cache/huggingface/hub/models--llava-hf--LLaVA-NeXT-Video-7B-hf/snapshots/b3b624d0915bb487ef1abb15255aaa2cd5581205/preprocessor_config.json

[INFO|2024-12-01 18:24:24] image_processing_base.py:429 >> Image processor LlavaNextVideoImageProcessor {
  "crop_size": {
    "height": 336,
    "width": 336
  },
  "do_center_crop": true,
  "do_convert_rgb": true,
  "do_normalize": true,
  "do_pad": true,
  "do_rescale": true,
  "do_resize": true,
  "image_grid_pinpoints": [
    [
      336,
      672
    ],
    [
      672,
      336
    ],
    [
      672,
      672
    ],
    [
      1008,
      336
    ],
    [
      336,
      1008
    ]
  ],
  "image_mean": [
    0.48145466,
    0.4578275,
    0.40821073
  ],
  "image_processor_type": "LlavaNextVideoImageProcessor",
  "image_std": [
    0.26862954,
    0.26130258,
    0.27577711
  ],
  "processor_class": "LlavaNextVideoProcessor",
  "resample": 3,
  "rescale_factor": 0.00392156862745098,
  "size": {
    "shortest_edge": 336
  }
}


[INFO|2024-12-01 18:24:24] image_processing_base.py:375 >> loading configuration file preprocessor_config.json from cache at /home/dl/.cache/huggingface/hub/models--llava-hf--LLaVA-NeXT-Video-7B-hf/snapshots/b3b624d0915bb487ef1abb15255aaa2cd5581205/preprocessor_config.json

[INFO|2024-12-01 18:24:24] image_processing_base.py:429 >> Image processor LlavaNextImageProcessor {
  "crop_size": {
    "height": 336,
    "width": 336
  },
  "do_center_crop": true,
  "do_convert_rgb": true,
  "do_normalize": true,
  "do_pad": true,
  "do_rescale": true,
  "do_resize": true,
  "image_grid_pinpoints": [
    [
      336,
      672
    ],
    [
      672,
      336
    ],
    [
      672,
      672
    ],
    [
      1008,
      336
    ],
    [
      336,
      1008
    ]
  ],
  "image_mean": [
    0.48145466,
    0.4578275,
    0.40821073
  ],
  "image_processor_type": "LlavaNextImageProcessor",
  "image_std": [
    0.26862954,
    0.26130258,
    0.27577711
  ],
  "processor_class": "LlavaNextVideoProcessor",
  "resample": 3,
  "rescale_factor": 0.00392156862745098,
  "size": {
    "shortest_edge": 336
  }
}


[INFO|2024-12-01 18:24:25] tokenization_utils_base.py:2211 >> loading file tokenizer.model from cache at /home/dl/.cache/huggingface/hub/models--llava-hf--LLaVA-NeXT-Video-7B-hf/snapshots/b3b624d0915bb487ef1abb15255aaa2cd5581205/tokenizer.model

[INFO|2024-12-01 18:24:25] tokenization_utils_base.py:2211 >> loading file tokenizer.json from cache at /home/dl/.cache/huggingface/hub/models--llava-hf--LLaVA-NeXT-Video-7B-hf/snapshots/b3b624d0915bb487ef1abb15255aaa2cd5581205/tokenizer.json

[INFO|2024-12-01 18:24:25] tokenization_utils_base.py:2211 >> loading file added_tokens.json from cache at /home/dl/.cache/huggingface/hub/models--llava-hf--LLaVA-NeXT-Video-7B-hf/snapshots/b3b624d0915bb487ef1abb15255aaa2cd5581205/added_tokens.json

[INFO|2024-12-01 18:24:25] tokenization_utils_base.py:2211 >> loading file special_tokens_map.json from cache at /home/dl/.cache/huggingface/hub/models--llava-hf--LLaVA-NeXT-Video-7B-hf/snapshots/b3b624d0915bb487ef1abb15255aaa2cd5581205/special_tokens_map.json

[INFO|2024-12-01 18:24:25] tokenization_utils_base.py:2211 >> loading file tokenizer_config.json from cache at /home/dl/.cache/huggingface/hub/models--llava-hf--LLaVA-NeXT-Video-7B-hf/snapshots/b3b624d0915bb487ef1abb15255aaa2cd5581205/tokenizer_config.json

[INFO|2024-12-01 18:24:25] tokenization_utils_base.py:2475 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.

[INFO|2024-12-01 18:24:25] processing_utils.py:695 >> loading configuration file processor_config.json from cache at /home/dl/.cache/huggingface/hub/models--llava-hf--LLaVA-NeXT-Video-7B-hf/snapshots/b3b624d0915bb487ef1abb15255aaa2cd5581205/processor_config.json

[WARNING|2024-12-01 18:24:25] processing_utils.py:1005 >> Some kwargs in processor config are unused and will not have any effect: num_additional_image_tokens. 

[INFO|2024-12-01 18:24:25] processing_utils.py:755 >> Processor LlavaNextVideoProcessor:
- video_processor: LlavaNextVideoImageProcessor {
  "crop_size": {
    "height": 336,
    "width": 336
  },
  "do_center_crop": true,
  "do_convert_rgb": true,
  "do_normalize": true,
  "do_pad": true,
  "do_rescale": true,
  "do_resize": true,
  "image_grid_pinpoints": [
    [
      336,
      672
    ],
    [
      672,
      336
    ],
    [
      672,
      672
    ],
    [
      1008,
      336
    ],
    [
      336,
      1008
    ]
  ],
  "image_mean": [
    0.48145466,
    0.4578275,
    0.40821073
  ],
  "image_processor_type": "LlavaNextVideoImageProcessor",
  "image_std": [
    0.26862954,
    0.26130258,
    0.27577711
  ],
  "processor_class": "LlavaNextVideoProcessor",
  "resample": 3,
  "rescale_factor": 0.00392156862745098,
  "size": {
    "shortest_edge": 336
  }
}

- image_processor: LlavaNextImageProcessor {
  "crop_size": {
    "height": 336,
    "width": 336
  },
  "do_center_crop": true,
  "do_convert_rgb": true,
  "do_normalize": true,
  "do_pad": true,
  "do_rescale": true,
  "do_resize": true,
  "image_grid_pinpoints": [
    [
      336,
      672
    ],
    [
      672,
      336
    ],
    [
      672,
      672
    ],
    [
      1008,
      336
    ],
    [
      336,
      1008
    ]
  ],
  "image_mean": [
    0.48145466,
    0.4578275,
    0.40821073
  ],
  "image_processor_type": "LlavaNextImageProcessor",
  "image_std": [
    0.26862954,
    0.26130258,
    0.27577711
  ],
  "processor_class": "LlavaNextVideoProcessor",
  "resample": 3,
  "rescale_factor": 0.00392156862745098,
  "size": {
    "shortest_edge": 336
  }
}

- tokenizer: LlamaTokenizerFast(name_or_path='llava-hf/LLaVA-NeXT-Video-7B-hf', vocab_size=32000, model_max_length=4096, is_fast=True, padding_side='left', truncation_side='right', special_tokens={'bos_token': '<s>', 'eos_token': '</s>', 'unk_token': '<unk>', 'pad_token': '<unk>'}, clean_up_tokenization_spaces=False),  added_tokens_decoder={
	0: AddedToken("<unk>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
	1: AddedToken("<s>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
	2: AddedToken("</s>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
	32000: AddedToken("<video>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
	32001: AddedToken("<image>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
}

{
  "image_token": "<image>",
  "patch_size": 14,
  "processor_class": "LlavaNextVideoProcessor",
  "video_token": "<video>",
  "vision_feature_select_strategy": "default"
}


[INFO|2024-12-01 18:24:25] logging.py:157 >> Loading dataset merger500.json...

[WARNING|2024-12-01 18:24:25] processing_utils.py:1005 >> Some kwargs in processor config are unused and will not have any effect: num_additional_image_tokens. 

[INFO|2024-12-01 18:24:27] logging.py:157 >> Loading dataset LLM_dataset(4o).json...

[INFO|2024-12-01 18:24:27] logging.py:157 >> Loading dataset LLM_dataset(4mini).json...

[INFO|2024-12-01 18:25:48] configuration_utils.py:679 >> loading configuration file config.json from cache at /home/dl/.cache/huggingface/hub/models--llava-hf--LLaVA-NeXT-Video-7B-hf/snapshots/b3b624d0915bb487ef1abb15255aaa2cd5581205/config.json

[INFO|2024-12-01 18:25:48] configuration_utils.py:746 >> Model config LlavaNextVideoConfig {
  "_name_or_path": "llava-hf/LLaVA-NeXT-Video-7B-hf",
  "architectures": [
    "LlavaNextVideoForConditionalGeneration"
  ],
  "ignore_index": -100,
  "image_grid_pinpoints": [
    [
      336,
      672
    ],
    [
      672,
      336
    ],
    [
      672,
      672
    ],
    [
      1008,
      336
    ],
    [
      336,
      1008
    ]
  ],
  "image_seq_length": 576,
  "image_token_index": 32001,
  "model_type": "llava_next_video",
  "projector_hidden_act": "gelu",
  "spatial_pool_mode": "average",
  "spatial_pool_out_channels": 1024,
  "spatial_pool_stride": 2,
  "text_config": {
    "_attn_implementation_autoset": false,
    "_name_or_path": "lmsys/vicuna-7b-v1.5",
    "add_cross_attention": false,
    "architectures": [
      "LlamaForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": 1,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": 2,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "intermediate_size": 11008,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "length_penalty": 1.0,
    "max_length": 20,
    "max_position_embeddings": 4096,
    "min_length": 0,
    "mlp_bias": false,
    "model_type": "llama",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 32,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 32,
    "num_key_value_heads": 32,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": 0,
    "prefix": null,
    "pretraining_tp": 1,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "rms_norm_eps": 1e-05,
    "rope_scaling": {
      "factor": 2.5,
      "rope_type": "linear",
      "type": "linear"
    },
    "rope_theta": 10000.0,
    "sep_token_id": null,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": false,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": "float16",
    "torchscript": false,
    "type": "linear",
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_cache": true,
    "vocab_size": 32064
  },
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.46.1",
  "use_image_newline_parameter": true,
  "video_seq_length": 288,
  "video_token_index": 32000,
  "vision_config": {
    "_attn_implementation_autoset": false,
    "_name_or_path": "",
    "add_cross_attention": false,
    "architectures": null,
    "attention_dropout": 0.0,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": null,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": null,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "hidden_act": "quick_gelu",
    "hidden_size": 1024,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "image_size": 336,
    "initializer_factor": 1.0,
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-05,
    "length_penalty": 1.0,
    "max_length": 20,
    "min_length": 0,
    "model_type": "clip_vision_model",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 16,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_channels": 3,
    "num_hidden_layers": 24,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": null,
    "patch_size": 14,
    "prefix": null,
    "problem_type": null,
    "projection_dim": 768,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "sep_token_id": null,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": null,
    "torchscript": false,
    "typical_p": 1.0,
    "use_bfloat16": false,
    "vocab_size": 32000
  },
  "vision_feature_layer": -2,
  "vision_feature_select_strategy": "default"
}


[INFO|2024-12-01 18:25:48] logging.py:157 >> Quantizing model to 4 bit with bitsandbytes.

[INFO|2024-12-01 18:25:48] modeling_utils.py:3937 >> loading weights file model.safetensors from cache at /home/dl/.cache/huggingface/hub/models--llava-hf--LLaVA-NeXT-Video-7B-hf/snapshots/b3b624d0915bb487ef1abb15255aaa2cd5581205/model.safetensors.index.json

[INFO|2024-12-01 18:25:48] modeling_utils.py:1670 >> Instantiating LlavaNextVideoForConditionalGeneration model under default dtype torch.bfloat16.

[INFO|2024-12-01 18:25:48] configuration_utils.py:1096 >> Generate config GenerationConfig {}


[INFO|2024-12-01 18:25:48] modeling_utils.py:1670 >> Instantiating CLIPVisionModel model under default dtype torch.bfloat16.

[INFO|2024-12-01 18:25:48] modeling_utils.py:1670 >> Instantiating LlamaForCausalLM model under default dtype torch.bfloat16.

[INFO|2024-12-01 18:25:48] configuration_utils.py:1096 >> Generate config GenerationConfig {
  "bos_token_id": 1,
  "eos_token_id": 2,
  "pad_token_id": 0
}


[INFO|2024-12-01 18:25:52] modeling_utils.py:4800 >> All model checkpoint weights were used when initializing LlavaNextVideoForConditionalGeneration.


[INFO|2024-12-01 18:25:52] modeling_utils.py:4808 >> All the weights of LlavaNextVideoForConditionalGeneration were initialized from the model checkpoint at llava-hf/LLaVA-NeXT-Video-7B-hf.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlavaNextVideoForConditionalGeneration for predictions without further training.

[INFO|2024-12-01 18:25:52] configuration_utils.py:1051 >> loading configuration file generation_config.json from cache at /home/dl/.cache/huggingface/hub/models--llava-hf--LLaVA-NeXT-Video-7B-hf/snapshots/b3b624d0915bb487ef1abb15255aaa2cd5581205/generation_config.json

[INFO|2024-12-01 18:25:52] configuration_utils.py:1096 >> Generate config GenerationConfig {
  "bos_token_id": 1,
  "eos_token_id": 2,
  "pad_token_id": 0
}


[INFO|2024-12-01 18:25:53] logging.py:157 >> Gradient checkpointing enabled.

[INFO|2024-12-01 18:25:53] logging.py:157 >> Casting multimodal projector outputs in torch.bfloat16.

[INFO|2024-12-01 18:25:53] logging.py:157 >> Using FlashAttention-2 for faster training and inference.

[INFO|2024-12-01 18:25:53] logging.py:157 >> Upcasting trainable params to float32.

[INFO|2024-12-01 18:25:53] logging.py:157 >> Fine-tuning method: LoRA

[INFO|2024-12-01 18:25:53] logging.py:157 >> Found linear modules: down_proj,v_proj,k_proj,q_proj,up_proj,o_proj,gate_proj

[INFO|2024-12-01 18:25:53] logging.py:157 >> trainable params: 19,988,480 || all params: 7,083,419,648 || trainable%: 0.2822

[INFO|2024-12-01 18:25:53] trainer.py:698 >> Using auto half precision backend

[INFO|2024-12-01 18:25:55] trainer.py:2313 >> ***** Running training *****

[INFO|2024-12-01 18:25:55] trainer.py:2314 >>   Num examples = 714

[INFO|2024-12-01 18:25:55] trainer.py:2315 >>   Num Epochs = 1

[INFO|2024-12-01 18:25:55] trainer.py:2316 >>   Instantaneous batch size per device = 2

[INFO|2024-12-01 18:25:55] trainer.py:2319 >>   Total train batch size (w. parallel, distributed & accumulation) = 32

[INFO|2024-12-01 18:25:55] trainer.py:2320 >>   Gradient Accumulation steps = 8

[INFO|2024-12-01 18:25:55] trainer.py:2321 >>   Total optimization steps = 22

[INFO|2024-12-01 18:25:55] trainer.py:2322 >>   Number of trainable parameters = 19,988,480

[WARNING|2024-12-01 18:25:59] logging.py:168 >> `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`.

[INFO|2024-12-01 18:28:23] logging.py:157 >> {'loss': 0.8615, 'learning_rate': 2.5000e-06, 'epoch': 0.22}

[INFO|2024-12-01 18:30:41] logging.py:157 >> {'loss': 0.8940, 'learning_rate': 5.0000e-06, 'epoch': 0.45}

[INFO|2024-12-01 18:33:04] logging.py:157 >> {'loss': 0.8808, 'learning_rate': 7.5000e-06, 'epoch': 0.67}

[INFO|2024-12-01 18:35:22] logging.py:157 >> {'loss': 0.8746, 'learning_rate': 1.0000e-05, 'epoch': 0.89}

[INFO|2024-12-01 18:36:12] trainer.py:3801 >> Saving model checkpoint to saves/LLaVA-NeXT-Video-7B-Chat/lora/train_2024-12-01-18-22-24/checkpoint-22

[INFO|2024-12-01 18:36:13] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/LLaVA-NeXT-Video-7B-Chat/lora/train_2024-12-01-18-22-24/checkpoint-22/tokenizer_config.json

[INFO|2024-12-01 18:36:13] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/LLaVA-NeXT-Video-7B-Chat/lora/train_2024-12-01-18-22-24/checkpoint-22/special_tokens_map.json

[INFO|2024-12-01 18:36:13] image_processing_base.py:258 >> Image processor saved in saves/LLaVA-NeXT-Video-7B-Chat/lora/train_2024-12-01-18-22-24/checkpoint-22/preprocessor_config.json

[INFO|2024-12-01 18:36:13] image_processing_base.py:258 >> Image processor saved in saves/LLaVA-NeXT-Video-7B-Chat/lora/train_2024-12-01-18-22-24/checkpoint-22/preprocessor_config.json

[INFO|2024-12-01 18:36:13] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/LLaVA-NeXT-Video-7B-Chat/lora/train_2024-12-01-18-22-24/checkpoint-22/tokenizer_config.json

[INFO|2024-12-01 18:36:13] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/LLaVA-NeXT-Video-7B-Chat/lora/train_2024-12-01-18-22-24/checkpoint-22/special_tokens_map.json

[INFO|2024-12-01 18:36:13] processing_utils.py:541 >> chat template saved in saves/LLaVA-NeXT-Video-7B-Chat/lora/train_2024-12-01-18-22-24/checkpoint-22/chat_template.json

[INFO|2024-12-01 18:36:13] processing_utils.py:547 >> processor saved in saves/LLaVA-NeXT-Video-7B-Chat/lora/train_2024-12-01-18-22-24/checkpoint-22/processor_config.json

[INFO|2024-12-01 18:36:13] trainer.py:2584 >> 

Training completed. Do not forget to share your model on huggingface.co/models =)



[INFO|2024-12-01 18:36:13] image_processing_base.py:258 >> Image processor saved in saves/LLaVA-NeXT-Video-7B-Chat/lora/train_2024-12-01-18-22-24/preprocessor_config.json

[INFO|2024-12-01 18:36:13] image_processing_base.py:258 >> Image processor saved in saves/LLaVA-NeXT-Video-7B-Chat/lora/train_2024-12-01-18-22-24/preprocessor_config.json

[INFO|2024-12-01 18:36:13] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/LLaVA-NeXT-Video-7B-Chat/lora/train_2024-12-01-18-22-24/tokenizer_config.json

[INFO|2024-12-01 18:36:13] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/LLaVA-NeXT-Video-7B-Chat/lora/train_2024-12-01-18-22-24/special_tokens_map.json

[INFO|2024-12-01 18:36:14] processing_utils.py:541 >> chat template saved in saves/LLaVA-NeXT-Video-7B-Chat/lora/train_2024-12-01-18-22-24/chat_template.json

[INFO|2024-12-01 18:36:14] processing_utils.py:547 >> processor saved in saves/LLaVA-NeXT-Video-7B-Chat/lora/train_2024-12-01-18-22-24/processor_config.json

[INFO|2024-12-01 18:36:14] trainer.py:3801 >> Saving model checkpoint to saves/LLaVA-NeXT-Video-7B-Chat/lora/train_2024-12-01-18-22-24

[INFO|2024-12-01 18:36:15] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/LLaVA-NeXT-Video-7B-Chat/lora/train_2024-12-01-18-22-24/tokenizer_config.json

[INFO|2024-12-01 18:36:15] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/LLaVA-NeXT-Video-7B-Chat/lora/train_2024-12-01-18-22-24/special_tokens_map.json

[WARNING|2024-12-01 18:36:15] logging.py:162 >> No metric eval_loss to plot.

[WARNING|2024-12-01 18:36:15] logging.py:162 >> No metric eval_accuracy to plot.

[INFO|2024-12-01 18:36:15] modelcard.py:449 >> Dropping the following result as it does not have all the necessary fields:
{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}