Training in progress, step 200

config.json

@@ -0,0 +1,114 @@
+{
+  "_name_or_path": "google/owlvit-base-patch32",
+  "architectures": [
+    "OwlViTForObjectDetection"
+  ],
+  "id2label": {
+    "0": 6,
+    "1": 7,
+    "10": 16,
+    "11": 17,
+    "12": 18,
+    "13": 19,
+    "14": 20,
+    "15": 21,
+    "16": 22,
+    "17": 23,
+    "18": 24,
+    "19": 25,
+    "2": 8,
+    "20": 26,
+    "21": 27,
+    "22": 28,
+    "23": 29,
+    "24": 30,
+    "25": 31,
+    "26": 32,
+    "27": 33,
+    "28": 34,
+    "29": 35,
+    "3": 9,
+    "30": 36,
+    "31": 37,
+    "32": 38,
+    "33": 40,
+    "34": 41,
+    "35": 42,
+    "36": 43,
+    "37": 44,
+    "38": 45,
+    "39": 46,
+    "4": 10,
+    "40": 47,
+    "41": 48,
+    "5": 11,
+    "6": 12,
+    "7": 13,
+    "8": 14,
+    "9": 15
+  },
+  "initializer_factor": 1.0,
+  "label2id": {
+    "6": "0",
+    "7": "1",
+    "8": "2",
+    "9": "3",
+    "10": "4",
+    "11": "5",
+    "12": "6",
+    "13": "7",
+    "14": "8",
+    "15": "9",
+    "16": "10",
+    "17": "11",
+    "18": "12",
+    "19": "13",
+    "20": "14",
+    "21": "15",
+    "22": "16",
+    "23": "17",
+    "24": "18",
+    "25": "19",
+    "26": "20",
+    "27": "21",
+    "28": "22",
+    "29": "23",
+    "30": "24",
+    "31": "25",
+    "32": "26",
+    "33": "27",
+    "34": "28",
+    "35": "29",
+    "36": "30",
+    "37": "31",
+    "38": "32",
+    "40": "33",
+    "41": "34",
+    "42": "35",
+    "43": "36",
+    "44": "37",
+    "45": "38",
+    "46": "39",
+    "47": "40",
+    "48": "41"
+  },
+  "logit_scale_init_value": 2.6592,
+  "model_type": "owlvit",
+  "projection_dim": 512,
+  "text_config": {
+    "bos_token_id": 0,
+    "dropout": 0.0,
+    "eos_token_id": 2,
+    "max_length": 16,
+    "model_type": "owlvit_text_model",
+    "pad_token_id": 1
+  },
+  "text_config_dict": null,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "vision_config": {
+    "dropout": 0.0,
+    "model_type": "owlvit_vision_model"
+  },
+  "vision_config_dict": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40b0fbb7b18a468417dd1786d035d993a8414706bb4b16098cfc1edbdba6031e
+size 612978988

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "crop_size": {
+    "height": 768,
+    "width": 768
+  },
+  "do_center_crop": false,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "OwlViTImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "OwlViTProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 768,
+    "width": 768
+  }
+}

runs/Apr16_20-32-20_e94151ae2d81/events.out.tfevents.1713299582.e94151ae2d81.3412.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7247a4251a3dedbae95e8befc9731a84a326d5e5553f110577b2d8f92902d527
+size 6639

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "!",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "!",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 16,
+  "pad_token": "!",
+  "processor_class": "OwlViTProcessor",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47f404dc1a7e9c7cb0fcd57cc51a7940606b909824c75c0d37f7f4d414120e6e
+size 4920