Training in progress, epoch 0

config.json

@@ -0,0 +1,164 @@
+{
+  "_name_or_path": "google/vivit-b-16x2-kinetics400",
+  "architectures": [
+    "VivitForVideoClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "hidden_act": "gelu_fast",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "W1",
+    "1": "W10",
+    "2": "W11",
+    "3": "W12",
+    "4": "W13",
+    "5": "W14",
+    "6": "W15",
+    "7": "W16",
+    "8": "W17",
+    "9": "W18",
+    "10": "W19",
+    "11": "W2",
+    "12": "W20",
+    "13": "W21",
+    "14": "W22",
+    "15": "W23",
+    "16": "W24",
+    "17": "W25",
+    "18": "W26",
+    "19": "W27",
+    "20": "W28",
+    "21": "W29",
+    "22": "W3",
+    "23": "W30",
+    "24": "W31",
+    "25": "W32",
+    "26": "W33",
+    "27": "W34",
+    "28": "W35",
+    "29": "W36",
+    "30": "W37",
+    "31": "W38",
+    "32": "W39",
+    "33": "W4",
+    "34": "W40",
+    "35": "W41",
+    "36": "W42",
+    "37": "W43",
+    "38": "W44",
+    "39": "W45",
+    "40": "W46",
+    "41": "W47",
+    "42": "W48",
+    "43": "W49",
+    "44": "W5",
+    "45": "W50",
+    "46": "W51",
+    "47": "W52",
+    "48": "W53",
+    "49": "W54",
+    "50": "W55",
+    "51": "W56",
+    "52": "W57",
+    "53": "W58",
+    "54": "W59",
+    "55": "W6",
+    "56": "W60",
+    "57": "W61",
+    "58": "W62",
+    "59": "W63",
+    "60": "W64",
+    "61": "W7",
+    "62": "W8",
+    "63": "W9"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "W1": 0,
+    "W10": 1,
+    "W11": 2,
+    "W12": 3,
+    "W13": 4,
+    "W14": 5,
+    "W15": 6,
+    "W16": 7,
+    "W17": 8,
+    "W18": 9,
+    "W19": 10,
+    "W2": 11,
+    "W20": 12,
+    "W21": 13,
+    "W22": 14,
+    "W23": 15,
+    "W24": 16,
+    "W25": 17,
+    "W26": 18,
+    "W27": 19,
+    "W28": 20,
+    "W29": 21,
+    "W3": 22,
+    "W30": 23,
+    "W31": 24,
+    "W32": 25,
+    "W33": 26,
+    "W34": 27,
+    "W35": 28,
+    "W36": 29,
+    "W37": 30,
+    "W38": 31,
+    "W39": 32,
+    "W4": 33,
+    "W40": 34,
+    "W41": 35,
+    "W42": 36,
+    "W43": 37,
+    "W44": 38,
+    "W45": 39,
+    "W46": 40,
+    "W47": 41,
+    "W48": 42,
+    "W49": 43,
+    "W5": 44,
+    "W50": 45,
+    "W51": 46,
+    "W52": 47,
+    "W53": 48,
+    "W54": 49,
+    "W55": 50,
+    "W56": 51,
+    "W57": 52,
+    "W58": 53,
+    "W59": 54,
+    "W6": 55,
+    "W60": 56,
+    "W61": 57,
+    "W62": 58,
+    "W63": 59,
+    "W64": 60,
+    "W7": 61,
+    "W8": 62,
+    "W9": 63
+  },
+  "layer_norm_eps": 1e-06,
+  "model_type": "vivit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_frames": 32,
+  "num_hidden_layers": 12,
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.1",
+  "tubelet_size": [
+    2,
+    16,
+    16
+  ],
+  "video_size": [
+    32,
+    224,
+    224
+  ]
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ab9722d8d8179a719b671f92317ce26b3a57fff2eb37f06b26eabee3c61e6d5
+size 354806104

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,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "VivitImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "offset": true,
+  "resample": 2,
+  "rescale_factor": 0.00784313725490196,
+  "size": {
+    "shortest_edge": 224
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54638c7f8b2e67c8f7ce7d94dd4ddff45de9f6e8681b8001028557be23cccea2
+size 5304