Training in progress, step 200

config.json

@@ -29,193 +29,27 @@
   "giou_cost": 2,
   "giou_loss_coefficient": 2,
   "id2label": {
-    "0": "N/A",
-    "1": "person",
-    "2": "bicycle",
-    "3": "car",
-    "4": "motorcycle",
-    "5": "airplane",
-    "6": "bus",
-    "7": "train",
-    "8": "truck",
-    "9": "boat",
-    "10": "traffic light",
-    "11": "fire hydrant",
-    "12": "street sign",
-    "13": "stop sign",
-    "14": "parking meter",
-    "15": "bench",
-    "16": "bird",
-    "17": "cat",
-    "18": "dog",
-    "19": "horse",
-    "20": "sheep",
-    "21": "cow",
-    "22": "elephant",
-    "23": "bear",
-    "24": "zebra",
-    "25": "giraffe",
-    "26": "hat",
-    "27": "backpack",
-    "28": "umbrella",
-    "29": "shoe",
-    "30": "eye glasses",
-    "31": "handbag",
-    "32": "tie",
-    "33": "suitcase",
-    "34": "frisbee",
-    "35": "skis",
-    "36": "snowboard",
-    "37": "sports ball",
-    "38": "kite",
-    "39": "baseball bat",
-    "40": "baseball glove",
-    "41": "skateboard",
-    "42": "surfboard",
-    "43": "tennis racket",
-    "44": "bottle",
-    "45": "plate",
-    "46": "wine glass",
-    "47": "cup",
-    "48": "fork",
-    "49": "knife",
-    "50": "spoon",
-    "51": "bowl",
-    "52": "banana",
-    "53": "apple",
-    "54": "sandwich",
-    "55": "orange",
-    "56": "broccoli",
-    "57": "carrot",
-    "58": "hot dog",
-    "59": "pizza",
-    "60": "donut",
-    "61": "cake",
-    "62": "chair",
-    "63": "couch",
-    "64": "potted plant",
-    "65": "bed",
-    "66": "mirror",
-    "67": "dining table",
-    "68": "window",
-    "69": "desk",
-    "70": "toilet",
-    "71": "door",
-    "72": "tv",
-    "73": "laptop",
-    "74": "mouse",
-    "75": "remote",
-    "76": "keyboard",
-    "77": "cell phone",
-    "78": "microwave",
-    "79": "oven",
-    "80": "toaster",
-    "81": "sink",
-    "82": "refrigerator",
-    "83": "blender",
-    "84": "book",
-    "85": "clock",
-    "86": "vase",
-    "87": "scissors",
-    "88": "teddy bear",
-    "89": "hair drier",
-    "90": "toothbrush"
+    "0": "road-traffic",
+    "1": "bicycles",
+    "2": "buses",
+    "3": "crosswalks",
+    "4": "fire hydrants",
+    "5": "motorcycles",
+    "6": "traffic lights",
+    "7": "vehicles"
   },
   "init_std": 0.02,
   "init_xavier_std": 1.0,
   "is_encoder_decoder": true,
   "label2id": {
-    "N/A": 0,
-    "airplane": 5,
-    "apple": 53,
-    "backpack": 27,
-    "banana": 52,
-    "baseball bat": 39,
-    "baseball glove": 40,
-    "bear": 23,
-    "bed": 65,
-    "bench": 15,
-    "bicycle": 2,
-    "bird": 16,
-    "blender": 83,
-    "boat": 9,
-    "book": 84,
-    "bottle": 44,
-    "bowl": 51,
-    "broccoli": 56,
-    "bus": 6,
-    "cake": 61,
-    "car": 3,
-    "carrot": 57,
-    "cat": 17,
-    "cell phone": 77,
-    "chair": 62,
-    "clock": 85,
-    "couch": 63,
-    "cow": 21,
-    "cup": 47,
-    "desk": 69,
-    "dining table": 67,
-    "dog": 18,
-    "donut": 60,
-    "door": 71,
-    "elephant": 22,
-    "eye glasses": 30,
-    "fire hydrant": 11,
-    "fork": 48,
-    "frisbee": 34,
-    "giraffe": 25,
-    "hair drier": 89,
-    "handbag": 31,
-    "hat": 26,
-    "horse": 19,
-    "hot dog": 58,
-    "keyboard": 76,
-    "kite": 38,
-    "knife": 49,
-    "laptop": 73,
-    "microwave": 78,
-    "mirror": 66,
-    "motorcycle": 4,
-    "mouse": 74,
-    "orange": 55,
-    "oven": 79,
-    "parking meter": 14,
-    "person": 1,
-    "pizza": 59,
-    "plate": 45,
-    "potted plant": 64,
-    "refrigerator": 82,
-    "remote": 75,
-    "sandwich": 54,
-    "scissors": 87,
-    "sheep": 20,
-    "shoe": 29,
-    "sink": 81,
-    "skateboard": 41,
-    "skis": 35,
-    "snowboard": 36,
-    "spoon": 50,
-    "sports ball": 37,
-    "stop sign": 13,
-    "street sign": 12,
-    "suitcase": 33,
-    "surfboard": 42,
-    "teddy bear": 88,
-    "tennis racket": 43,
-    "tie": 32,
-    "toaster": 80,
-    "toilet": 70,
-    "toothbrush": 90,
-    "traffic light": 10,
-    "train": 7,
-    "truck": 8,
-    "tv": 72,
-    "umbrella": 28,
-    "vase": 86,
-    "window": 68,
-    "wine glass": 46,
-    "zebra": 24
+    "bicycles": 1,
+    "buses": 2,
+    "crosswalks": 3,
+    "fire hydrants": 4,
+    "motorcycles": 5,
+    "road-traffic": 0,
+    "traffic lights": 6,
+    "vehicles": 7
   },
   "mask_loss_coefficient": 1,
   "max_position_embeddings": 1024,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aea975f18d5b875db77dc7c782ac65bc698c44bba45ce4efe9a6e718762f3b3f
-size 166587352
+oid sha256:ca70d8203e931e5c4b24852d68af4feddc8f1394909405a741ba8029b83889ca
+size 166502020

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d503eeeed3cc51bef9f073251b6c0de2a006924d76ecdc67c271c0da131a98a
+oid sha256:a6cc1a68e84aaaf43e778f5a3f81a67e05eb1a193aad3d84fd400ae4a109d36d
 size 4600