Training in progress, epoch 0

config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "MCG-NJU/videomae-small-finetuned-kinetics",
+  "architectures": [
+    "VideoMAEForVideoClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "decoder_hidden_size": 192,
+  "decoder_intermediate_size": 768,
+  "decoder_num_attention_heads": 3,
+  "decoder_num_hidden_layers": 12,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "WORD1501",
+    "1": "WORD1502",
+    "2": "WORD1503",
+    "3": "WORD1504",
+    "4": "WORD1505",
+    "5": "WORD1506",
+    "6": "WORD1507",
+    "7": "WORD1508",
+    "8": "WORD1509",
+    "9": "WORD1510",
+    "10": "WORD1511",
+    "11": "WORD1512",
+    "12": "WORD1513",
+    "13": "WORD1514",
+    "14": "WORD1515",
+    "15": "WORD1516",
+    "16": "WORD1517",
+    "17": "WORD1518",
+    "18": "WORD1519",
+    "19": "WORD1520"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "WORD1501": 0,
+    "WORD1502": 1,
+    "WORD1503": 2,
+    "WORD1504": 3,
+    "WORD1505": 4,
+    "WORD1506": 5,
+    "WORD1507": 6,
+    "WORD1508": 7,
+    "WORD1509": 8,
+    "WORD1510": 9,
+    "WORD1511": 10,
+    "WORD1512": 11,
+    "WORD1513": 12,
+    "WORD1514": 13,
+    "WORD1515": 14,
+    "WORD1516": 15,
+    "WORD1517": 16,
+    "WORD1518": 17,
+    "WORD1519": 18,
+    "WORD1520": 19
+  },
+  "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": 12,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.32.0",
+  "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 sha256:1c1aa3b4fc3ee71fb7404fa419fb4fb8afef87309585aa6d87c64bcd19470b78
+size 87614517

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72e9b635f69ce86175f1f63c3de1e6364ac924f361e230473b6758e34f6c35ed
+size 4155