Training in progress, epoch 1

config.json

@@ -0,0 +1,219 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "DetrForObjectDetection"
+  ],
+  "attention_dropout": 0.0,
+  "auxiliary_loss": false,
+  "backbone": "timm/vit_large_patch14_dinov2.lvd142m",
+  "backbone_config": null,
+  "backbone_kwargs": {
+    "in_chans": 3,
+    "out_indices": [
+      1,
+      2,
+      3,
+      4
+    ]
+  },
+  "bbox_cost": 5,
+  "bbox_loss_coefficient": 5,
+  "class_cost": 2,
+  "cls_loss_coefficient": 2,
+  "d_model": 256,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "dice_loss_coefficient": 1,
+  "dilation": false,
+  "dropout": 0.1,
+  "dtype": "bfloat16",
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_coefficient": 0.1,
+  "focal_alpha": 0.25,
+  "giou_cost": 2,
+  "giou_loss_coefficient": 2,
+  "id2label": {
+    "0": "person",
+    "1": "bicycle",
+    "2": "car",
+    "3": "motorcycle",
+    "4": "airplane",
+    "5": "bus",
+    "6": "train",
+    "7": "truck",
+    "8": "boat",
+    "9": "traffic light",
+    "10": "fire hydrant",
+    "11": "stop sign",
+    "12": "parking meter",
+    "13": "bench",
+    "14": "bird",
+    "15": "cat",
+    "16": "dog",
+    "17": "horse",
+    "18": "sheep",
+    "19": "cow",
+    "20": "elephant",
+    "21": "bear",
+    "22": "zebra",
+    "23": "giraffe",
+    "24": "backpack",
+    "25": "umbrella",
+    "26": "handbag",
+    "27": "tie",
+    "28": "suitcase",
+    "29": "frisbee",
+    "30": "skis",
+    "31": "snowboard",
+    "32": "sports ball",
+    "33": "kite",
+    "34": "baseball bat",
+    "35": "baseball glove",
+    "36": "skateboard",
+    "37": "surfboard",
+    "38": "tennis racket",
+    "39": "bottle",
+    "40": "wine glass",
+    "41": "cup",
+    "42": "fork",
+    "43": "knife",
+    "44": "spoon",
+    "45": "bowl",
+    "46": "banana",
+    "47": "apple",
+    "48": "sandwich",
+    "49": "orange",
+    "50": "broccoli",
+    "51": "carrot",
+    "52": "hot dog",
+    "53": "pizza",
+    "54": "donut",
+    "55": "cake",
+    "56": "chair",
+    "57": "couch",
+    "58": "potted plant",
+    "59": "bed",
+    "60": "dining table",
+    "61": "toilet",
+    "62": "tv",
+    "63": "laptop",
+    "64": "mouse",
+    "65": "remote",
+    "66": "keyboard",
+    "67": "cell phone",
+    "68": "microwave",
+    "69": "oven",
+    "70": "toaster",
+    "71": "sink",
+    "72": "refrigerator",
+    "73": "book",
+    "74": "clock",
+    "75": "vase",
+    "76": "scissors",
+    "77": "teddy bear",
+    "78": "hair drier",
+    "79": "toothbrush"
+  },
+  "init_std": 0.02,
+  "init_xavier_std": 1.0,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "airplane": 4,
+    "apple": 47,
+    "backpack": 24,
+    "banana": 46,
+    "baseball bat": 34,
+    "baseball glove": 35,
+    "bear": 21,
+    "bed": 59,
+    "bench": 13,
+    "bicycle": 1,
+    "bird": 14,
+    "boat": 8,
+    "book": 73,
+    "bottle": 39,
+    "bowl": 45,
+    "broccoli": 50,
+    "bus": 5,
+    "cake": 55,
+    "car": 2,
+    "carrot": 51,
+    "cat": 15,
+    "cell phone": 67,
+    "chair": 56,
+    "clock": 74,
+    "couch": 57,
+    "cow": 19,
+    "cup": 41,
+    "dining table": 60,
+    "dog": 16,
+    "donut": 54,
+    "elephant": 20,
+    "fire hydrant": 10,
+    "fork": 42,
+    "frisbee": 29,
+    "giraffe": 23,
+    "hair drier": 78,
+    "handbag": 26,
+    "horse": 17,
+    "hot dog": 52,
+    "keyboard": 66,
+    "kite": 33,
+    "knife": 43,
+    "laptop": 63,
+    "microwave": 68,
+    "motorcycle": 3,
+    "mouse": 64,
+    "orange": 49,
+    "oven": 69,
+    "parking meter": 12,
+    "person": 0,
+    "pizza": 53,
+    "potted plant": 58,
+    "refrigerator": 72,
+    "remote": 65,
+    "sandwich": 48,
+    "scissors": 76,
+    "sheep": 18,
+    "sink": 71,
+    "skateboard": 36,
+    "skis": 30,
+    "snowboard": 31,
+    "spoon": 44,
+    "sports ball": 32,
+    "stop sign": 11,
+    "suitcase": 28,
+    "surfboard": 37,
+    "teddy bear": 77,
+    "tennis racket": 38,
+    "tie": 27,
+    "toaster": 70,
+    "toilet": 61,
+    "toothbrush": 79,
+    "traffic light": 9,
+    "train": 6,
+    "truck": 7,
+    "tv": 62,
+    "umbrella": 25,
+    "vase": 75,
+    "wine glass": 40,
+    "zebra": 22
+  },
+  "mask_loss_coefficient": 1,
+  "max_position_embeddings": 1024,
+  "model_type": "detr",
+  "num_channels": 3,
+  "num_hidden_layers": 6,
+  "num_queries": 300,
+  "position_embedding_type": "sine",
+  "scale_embedding": false,
+  "transformers_version": "4.56.0",
+  "use_pretrained_backbone": true,
+  "use_timm_backbone": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a4e4d31ed0c30f5affda00e66922dd050f18d640a7e69beca319d1cdd1ee679
+size 165749546

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_annotations": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "format": "coco_detection",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "ConditionalDetrImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "pad_size": {
+    "height": 518,
+    "width": 518
+  },
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "max_height": 518,
+    "max_width": 518
+  }
+}

runs/Sep05_06-39-27_e24c0136ff07/events.out.tfevents.1757054368.e24c0136ff07.5260.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cdefe392038f444d9587909e3acea0b9893aeb1ba9d5e8cc5fd9576185c27f7
+size 40655

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e40da0bce68376090af241b3cdd2b2cd921d0be2cf3321ba232bccc97c85fb5
+size 5841