Training in progress, epoch 0

config.json

@@ -0,0 +1,75 @@
+{
+  "_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": "\u0623\u0628\u0648 \u0642\u0631\u0648\u0629",
+    "1": "\u0625\u0628\u0642\u0627\u0621",
+    "2": "\u0625\u062c\u0647\u0627\u062f",
+    "3": "\u0625\u0633\u0643\u0627\u0646",
+    "4": "\u0627\u0628\u062a\u0639\u0627\u062b",
+    "5": "\u0627\u062e\u062a\u0631\u0627\u0642",
+    "6": "\u0627\u0634\u0627\u0631\u0629 \u062d\u0645\u0631\u0627\u0621",
+    "7": "\u0627\u0644\u0627\u0631\u062f\u0646",
+    "8": "\u0627\u0644\u0639\u0635\u0631",
+    "9": "\u0627\u0646\u062a\u0634\u0627\u0631",
+    "10": "\u0628\u064a\u062c\u0648",
+    "11": "\u062b\u0631\u064a\u0627",
+    "12": "\u062c\u0627\u0643\u0648\u0627\u0631",
+    "13": "\u062f\u0627\u0626\u0631\u064a",
+    "14": "\u0631\u0633\u0627\u0645",
+    "15": "\u0632\u062d\u0644",
+    "16": "\u0641\u0631\u062f\u064a",
+    "17": "\u0645\u0644\u0627\u062d\u0638\u0629",
+    "18": "\u0646\u0627\u062f\u064a \u0627\u0644\u0627\u062a\u0641\u0627\u0642",
+    "19": "\u0648\u0639\u0644\u064a\u0643\u0645 \u0627\u0644\u0633\u0644\u0627\u0645"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "\u0623\u0628\u0648 \u0642\u0631\u0648\u0629": 0,
+    "\u0625\u0628\u0642\u0627\u0621": 1,
+    "\u0625\u062c\u0647\u0627\u062f": 2,
+    "\u0625\u0633\u0643\u0627\u0646": 3,
+    "\u0627\u0628\u062a\u0639\u0627\u062b": 4,
+    "\u0627\u062e\u062a\u0631\u0627\u0642": 5,
+    "\u0627\u0634\u0627\u0631\u0629 \u062d\u0645\u0631\u0627\u0621": 6,
+    "\u0627\u0644\u0627\u0631\u062f\u0646": 7,
+    "\u0627\u0644\u0639\u0635\u0631": 8,
+    "\u0627\u0646\u062a\u0634\u0627\u0631": 9,
+    "\u0628\u064a\u062c\u0648": 10,
+    "\u062b\u0631\u064a\u0627": 11,
+    "\u062c\u0627\u0643\u0648\u0627\u0631": 12,
+    "\u062f\u0627\u0626\u0631\u064a": 13,
+    "\u0631\u0633\u0627\u0645": 14,
+    "\u0632\u062d\u0644": 15,
+    "\u0641\u0631\u062f\u064a": 16,
+    "\u0645\u0644\u0627\u062d\u0638\u0629": 17,
+    "\u0646\u0627\u062f\u064a \u0627\u0644\u0627\u062a\u0641\u0627\u0642": 18,
+    "\u0648\u0639\u0644\u064a\u0643\u0645 \u0627\u0644\u0633\u0644\u0627\u0645": 19
+  },
+  "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": "4.33.0",
+  "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 sha256:5197bbfdb6802187e72f54c61eb7d73bd783eac499f4b3eabd121ec6584cfd44
+size 345031733

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:451b1ba17a0a38864612eec6ab3acc09afa7da73ebf45b5c69a7a828d3bd975f
+size 4091