Training in progress, epoch 0

config.json

@@ -0,0 +1,283 @@
+{
+  "_name_or_path": "MCG-NJU/videomae-base",
+  "architectures": [
+    "VideoMAEForVideoClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "decoder_hidden_size": 384,
+  "decoder_intermediate_size": 1536,
+  "decoder_num_attention_heads": 6,
+  "decoder_num_hidden_layers": 4,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "001",
+    "1": "002",
+    "2": "003",
+    "3": "004",
+    "4": "005",
+    "5": "006",
+    "6": "007",
+    "7": "008",
+    "8": "009",
+    "9": "010",
+    "10": "011",
+    "11": "012",
+    "12": "013",
+    "13": "014",
+    "14": "015",
+    "15": "016",
+    "16": "017",
+    "17": "018",
+    "18": "019",
+    "19": "020",
+    "20": "021",
+    "21": "022",
+    "22": "023",
+    "23": "024",
+    "24": "025",
+    "25": "026",
+    "26": "027",
+    "27": "028",
+    "28": "029",
+    "29": "030",
+    "30": "031",
+    "31": "032",
+    "32": "033",
+    "33": "034",
+    "34": "035",
+    "35": "036",
+    "36": "037",
+    "37": "038",
+    "38": "039",
+    "39": "040",
+    "40": "041",
+    "41": "042",
+    "42": "043",
+    "43": "044",
+    "44": "045",
+    "45": "046",
+    "46": "047",
+    "47": "048",
+    "48": "049",
+    "49": "050",
+    "50": "051",
+    "51": "052",
+    "52": "053",
+    "53": "054",
+    "54": "055",
+    "55": "056",
+    "56": "057",
+    "57": "058",
+    "58": "059",
+    "59": "060",
+    "60": "061",
+    "61": "062",
+    "62": "063",
+    "63": "064",
+    "64": "065",
+    "65": "066",
+    "66": "067",
+    "67": "068",
+    "68": "069",
+    "69": "070",
+    "70": "071",
+    "71": "072",
+    "72": "073",
+    "73": "074",
+    "74": "075",
+    "75": "076",
+    "76": "077",
+    "77": "078",
+    "78": "079",
+    "79": "080",
+    "80": "081",
+    "81": "082",
+    "82": "083",
+    "83": "084",
+    "84": "085",
+    "85": "086",
+    "86": "087",
+    "87": "088",
+    "88": "089",
+    "89": "090",
+    "90": "091",
+    "91": "092",
+    "92": "093",
+    "93": "094",
+    "94": "095",
+    "95": "096",
+    "96": "097",
+    "97": "098",
+    "98": "099",
+    "99": "100",
+    "100": "101",
+    "101": "102",
+    "102": "103",
+    "103": "104",
+    "104": "105",
+    "105": "106",
+    "106": "107",
+    "107": "108",
+    "108": "109",
+    "109": "110",
+    "110": "111",
+    "111": "112",
+    "112": "113",
+    "113": "114",
+    "114": "115",
+    "115": "116",
+    "116": "117",
+    "117": "118",
+    "118": "119",
+    "119": "120",
+    "120": "121",
+    "121": "122",
+    "122": "123",
+    "123": "124"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "001": 0,
+    "002": 1,
+    "003": 2,
+    "004": 3,
+    "005": 4,
+    "006": 5,
+    "007": 6,
+    "008": 7,
+    "009": 8,
+    "010": 9,
+    "011": 10,
+    "012": 11,
+    "013": 12,
+    "014": 13,
+    "015": 14,
+    "016": 15,
+    "017": 16,
+    "018": 17,
+    "019": 18,
+    "020": 19,
+    "021": 20,
+    "022": 21,
+    "023": 22,
+    "024": 23,
+    "025": 24,
+    "026": 25,
+    "027": 26,
+    "028": 27,
+    "029": 28,
+    "030": 29,
+    "031": 30,
+    "032": 31,
+    "033": 32,
+    "034": 33,
+    "035": 34,
+    "036": 35,
+    "037": 36,
+    "038": 37,
+    "039": 38,
+    "040": 39,
+    "041": 40,
+    "042": 41,
+    "043": 42,
+    "044": 43,
+    "045": 44,
+    "046": 45,
+    "047": 46,
+    "048": 47,
+    "049": 48,
+    "050": 49,
+    "051": 50,
+    "052": 51,
+    "053": 52,
+    "054": 53,
+    "055": 54,
+    "056": 55,
+    "057": 56,
+    "058": 57,
+    "059": 58,
+    "060": 59,
+    "061": 60,
+    "062": 61,
+    "063": 62,
+    "064": 63,
+    "065": 64,
+    "066": 65,
+    "067": 66,
+    "068": 67,
+    "069": 68,
+    "070": 69,
+    "071": 70,
+    "072": 71,
+    "073": 72,
+    "074": 73,
+    "075": 74,
+    "076": 75,
+    "077": 76,
+    "078": 77,
+    "079": 78,
+    "080": 79,
+    "081": 80,
+    "082": 81,
+    "083": 82,
+    "084": 83,
+    "085": 84,
+    "086": 85,
+    "087": 86,
+    "088": 87,
+    "089": 88,
+    "090": 89,
+    "091": 90,
+    "092": 91,
+    "093": 92,
+    "094": 93,
+    "095": 94,
+    "096": 95,
+    "097": 96,
+    "098": 97,
+    "099": 98,
+    "100": 99,
+    "101": 100,
+    "102": 101,
+    "103": 102,
+    "104": 103,
+    "105": 104,
+    "106": 105,
+    "107": 106,
+    "108": 107,
+    "109": 108,
+    "110": 109,
+    "111": 110,
+    "112": 111,
+    "113": 112,
+    "114": 113,
+    "115": 114,
+    "116": 115,
+    "117": 116,
+    "118": 117,
+    "119": 118,
+    "120": 119,
+    "121": 120,
+    "122": 121,
+    "123": 122,
+    "124": 123
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "videomae",
+  "norm_pix_loss": true,
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_frames": 16,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.2",
+  "tubelet_size": 2,
+  "use_mean_pooling": false
+}

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "VideoMAEFeatureExtractor",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "VideoMAEImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94f941960e1c98bca726e16ab3f425ab4cf5ff48147c4025ce06f534c232c741
+size 345354165

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:141b2cab80ea6b970668d574c6857353056ebc89e666c8e938591a03bfe35196
+size 4091