Training in progress, step 200

config.json

@@ -1,241 +1,40 @@
 {
-  "_name_or_path": "facebook/detr-resnet-50",
-  "activation_dropout": 0.0,
-  "activation_function": "relu",
+  "_name_or_path": "hustvl/yolos-tiny",
   "architectures": [
-    "DetrForObjectDetection"
+    "YolosForObjectDetection"
   ],
-  "attention_dropout": 0.0,
+  "attention_probs_dropout_prob": 0.0,
   "auxiliary_loss": false,
-  "backbone": "resnet50",
-  "backbone_config": null,
-  "backbone_kwargs": {
-    "in_chans": 3,
-    "out_indices": [
-      1,
-      2,
-      3,
-      4
-    ]
-  },
   "bbox_cost": 5,
   "bbox_loss_coefficient": 5,
   "class_cost": 1,
-  "classifier_dropout": 0.0,
-  "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,
-  "encoder_attention_heads": 8,
-  "encoder_ffn_dim": 2048,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 6,
   "eos_coefficient": 0.1,
   "giou_cost": 2,
   "giou_loss_coefficient": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 192,
   "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": "kangaroo"
   },
-  "init_std": 0.02,
-  "init_xavier_std": 1.0,
-  "is_encoder_decoder": true,
+  "image_size": [
+    800,
+    1333
+  ],
+  "initializer_range": 0.02,
+  "intermediate_size": 768,
   "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
+    "kangaroo": 0
   },
-  "mask_loss_coefficient": 1,
-  "max_position_embeddings": 1024,
-  "model_type": "detr",
+  "layer_norm_eps": 1e-12,
+  "model_type": "yolos",
+  "num_attention_heads": 3,
   "num_channels": 3,
-  "num_hidden_layers": 6,
-  "num_queries": 100,
-  "position_embedding_type": "sine",
-  "scale_embedding": false,
+  "num_detection_tokens": 100,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "qkv_bias": true,
   "torch_dtype": "float32",
   "transformers_version": "4.48.3",
-  "use_pretrained_backbone": true,
-  "use_timm_backbone": true
+  "use_mid_position_embeddings": false
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d185c7881e4283d66d32d67894f10de691ec9a2d825fbe90d9260fb56afa40a
-size 166587352
+oid sha256:0e69747ddc3ee36d6d05cb8525914bf52ce5a1f5472294727574c9a1c686c4fc
+size 25909400

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50b5b0f7bb28dc6b4326b87b372fdde6f76880ffed6f0711cfb70457bb648fbb
+oid sha256:03c681f67d5d621a2c74c4680a74c26fbcc4263accda3c5b28fa48ecfbd9c7c4
 size 5304