Training in progress, epoch 0

config.json

@@ -0,0 +1,117 @@
+{
+  "_name_or_path": "MCG-NJU/videomae-large-finetuned-kinetics",
+  "architectures": [
+    "VideoMAEForVideoClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "decoder_hidden_size": 512,
+  "decoder_intermediate_size": 2048,
+  "decoder_num_attention_heads": 8,
+  "decoder_num_hidden_layers": 12,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "C_1",
+    "1": "C_2",
+    "2": "C_3",
+    "3": "C_4",
+    "4": "C_5",
+    "5": "C_6",
+    "6": "C_7",
+    "7": "C_8",
+    "8": "O_1",
+    "9": "O_2",
+    "10": "O_3",
+    "11": "O_4",
+    "12": "O_5",
+    "13": "O_6",
+    "14": "O_7",
+    "15": "P_1",
+    "16": "P_10",
+    "17": "P_11",
+    "18": "P_12",
+    "19": "P_2",
+    "20": "P_3",
+    "21": "P_4",
+    "22": "P_5",
+    "23": "P_6",
+    "24": "P_7",
+    "25": "P_8",
+    "26": "P_9",
+    "27": "Q_1",
+    "28": "Q_2",
+    "29": "Q_3",
+    "30": "Q_4",
+    "31": "Q_5",
+    "32": "Q_6",
+    "33": "Q_7",
+    "34": "T_1",
+    "35": "T_2",
+    "36": "T_3",
+    "37": "T_4",
+    "38": "T_5",
+    "39": "T_6",
+    "40": "T_7"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "C_1": 0,
+    "C_2": 1,
+    "C_3": 2,
+    "C_4": 3,
+    "C_5": 4,
+    "C_6": 5,
+    "C_7": 6,
+    "C_8": 7,
+    "O_1": 8,
+    "O_2": 9,
+    "O_3": 10,
+    "O_4": 11,
+    "O_5": 12,
+    "O_6": 13,
+    "O_7": 14,
+    "P_1": 15,
+    "P_10": 16,
+    "P_11": 17,
+    "P_12": 18,
+    "P_2": 19,
+    "P_3": 20,
+    "P_4": 21,
+    "P_5": 22,
+    "P_6": 23,
+    "P_7": 24,
+    "P_8": 25,
+    "P_9": 26,
+    "Q_1": 27,
+    "Q_2": 28,
+    "Q_3": 29,
+    "Q_4": 30,
+    "Q_5": 31,
+    "Q_6": 32,
+    "Q_7": 33,
+    "T_1": 34,
+    "T_2": 35,
+    "T_3": 36,
+    "T_4": 37,
+    "T_5": 38,
+    "T_6": 39,
+    "T_7": 40
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "videomae",
+  "norm_pix_loss": true,
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_frames": 16,
+  "num_hidden_layers": 24,
+  "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": true
+}

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 sha256:9c2c3bd99341dea45fdbac674e90dc03573bb73270b18128c96a2a98ce6b4b73
+size 1215734821

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5b5a20c74a096bd41e7d27a9fc2469b54a0eb0c1ffeb4190c0e5558f6e8e14f
+size 4079