Training in progress, epoch 0

config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "MCG-NJU/videomae-huge-finetuned-kinetics",
+  "architectures": [
+    "VideoMAEForVideoClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "decoder_hidden_size": 640,
+  "decoder_intermediate_size": 2560,
+  "decoder_num_attention_heads": 8,
+  "decoder_num_hidden_layers": 12,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1280,
+  "id2label": {
+    "0": "badminton",
+    "1": "clap",
+    "2": "dance",
+    "3": "drinking",
+    "4": "football",
+    "5": "handshake",
+    "6": "handwave",
+    "7": "jogging",
+    "8": "jumping",
+    "9": "pouring",
+    "10": "pt_exercise",
+    "11": "punching",
+    "12": "pushups",
+    "13": "rotating",
+    "14": "running",
+    "15": "situps",
+    "16": "swirling",
+    "17": "swirling_umbrella",
+    "18": "volleyball",
+    "19": "walking"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "label2id": {
+    "badminton": 0,
+    "clap": 1,
+    "dance": 2,
+    "drinking": 3,
+    "football": 4,
+    "handshake": 5,
+    "handwave": 6,
+    "jogging": 7,
+    "jumping": 8,
+    "pouring": 9,
+    "pt_exercise": 10,
+    "punching": 11,
+    "pushups": 12,
+    "rotating": 13,
+    "running": 14,
+    "situps": 15,
+    "swirling": 16,
+    "swirling_umbrella": 17,
+    "volleyball": 18,
+    "walking": 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": 32,
+  "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 sha256:187eea57a47264e6c39adf553d43d9a482d7827fc5670d8af4f94f939fc11250
+size 2526692197

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f07ae16d548a39484cd4ecb1ca297582a6d465891e03e50eb45c357157d0c7a3
+size 4155