Training in progress, step 20

adapter_config.json

@@ -0,0 +1,40 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "LlavaNextVideoForConditionalGeneration",
+    "parent_library": "transformers.models.llava_next_video.modeling_llava_next_video"
+  },
+  "base_model_name_or_path": "llava-hf/LLaVa-NeXT-Video-7b-hf",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": "gaussian",
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "v_proj",
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:908613c797d07da1fb282a6ad8972ef9185d53a68a0d908d76dcfc29d1cf5bd5
+size 84761704

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<image>": 32001,
+  "<video>": 32000
+}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% for message in messages %}{% if message['role'] != 'system' %}{{ message['role'].upper() + ': '}}{% endif %}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>\n' }}{% endfor %}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'video') %}{{ '<video>\n' }}{% endfor %}{# Render all text next #}{% if message['role'] != 'assistant' %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ content['text'] + ' '}}{% endfor %}{% else %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{% generation %}{{ content['text'] + ' '}}{% endgeneration %}{% endfor %}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'ASSISTANT:' }}{% endif %}"
+}

huggingface/video_llava_demo/lightning_logs/version_0/hparams.yaml

@@ -0,0 +1 @@
+{}

huggingface/video_llava_demo/lightning_logs/version_1/hparams.yaml

@@ -0,0 +1 @@
+{}

huggingface/video_llava_demo/lightning_logs/version_10/hparams.yaml

@@ -0,0 +1 @@
+{}

huggingface/video_llava_demo/lightning_logs/version_11/hparams.yaml

@@ -0,0 +1 @@
+{}

huggingface/video_llava_demo/lightning_logs/version_11/metrics.csv

@@ -0,0 +1,9 @@
+epoch,step,train_loss,val_accuracy
+0,49,3.80435848236084,
+0,99,3.7000603675842285,
+0,149,3.7685372829437256,
+0,199,3.7591216564178467,
+0,249,3.6957693099975586,
+0,299,3.69533109664917,
+0,349,3.75651216506958,
+0,359,,0.0

huggingface/video_llava_demo/lightning_logs/version_12/hparams.yaml

@@ -0,0 +1 @@
+{}

huggingface/video_llava_demo/lightning_logs/version_13/hparams.yaml

@@ -0,0 +1 @@
+{}

huggingface/video_llava_demo/lightning_logs/version_13/metrics.csv

@@ -0,0 +1,2 @@
+epoch,step,val_accuracy
+0,23,0.0

huggingface/video_llava_demo/lightning_logs/version_14/checkpoints/epoch=0-step=2.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c9334766203b37308344719867b0ccb6037cc0b55023c2d01522afbe19abe4f
+size 5316278235

huggingface/video_llava_demo/lightning_logs/version_14/hparams.yaml

@@ -0,0 +1 @@
+{}

huggingface/video_llava_demo/lightning_logs/version_14/metrics.csv

@@ -0,0 +1,2 @@
+epoch,step,val_accuracy
+0,1,0.0

huggingface/video_llava_demo/lightning_logs/version_2/hparams.yaml

@@ -0,0 +1 @@
+{}

huggingface/video_llava_demo/lightning_logs/version_3/hparams.yaml

@@ -0,0 +1 @@
+{}

huggingface/video_llava_demo/lightning_logs/version_4/hparams.yaml

@@ -0,0 +1 @@
+{}

huggingface/video_llava_demo/lightning_logs/version_5/hparams.yaml

@@ -0,0 +1 @@
+{}

huggingface/video_llava_demo/lightning_logs/version_6/hparams.yaml

@@ -0,0 +1 @@
+{}

huggingface/video_llava_demo/lightning_logs/version_7/hparams.yaml

@@ -0,0 +1 @@
+{}

huggingface/video_llava_demo/lightning_logs/version_8/hparams.yaml

@@ -0,0 +1 @@
+{}

huggingface/video_llava_demo/lightning_logs/version_9/hparams.yaml

@@ -0,0 +1 @@
+{}

preprocessor_config.json

@@ -0,0 +1,51 @@
+{
+  "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
+  }
+}

processor_config.json

@@ -0,0 +1,8 @@
+{
+  "image_token": "<image>",
+  "num_additional_image_tokens": 1,
+  "patch_size": 14,
+  "processor_class": "LlavaNextVideoProcessor",
+  "video_token": "<video>",
+  "vision_feature_select_strategy": "default"
+}

special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image>",
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "video_token": "<video>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,67 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<video>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {
+    "image_token": "<image>",
+    "video_token": "<video>"
+  },
+  "image_token": "<image>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "processor_class": "LlavaNextVideoProcessor",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": false,
+  "video_token": "<video>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:759992907ff319884cad476736c33b366106cd38315e3a0543aee4e734d8349d
+size 5304