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\u0639\u0627\u062f",
+    "1": "\u0623\u0628\u0646 \u0627\u0644\u0623\u062e",
+    "2": "\u0623\u062d\u0627\u0637",
+    "3": "\u0623\u062e\u062a",
+    "4": "\u0623\u062e\u0635\u0627\u0626\u064a\u0629",
+    "5": "\u0625\u0639\u0644\u0627\u0645",
+    "6": "\u0627\u0628\u0631\u0627\u0647\u064a\u0645",
+    "7": "\u0627\u062d\u062a\u0645\u0627\u0644",
+    "8": "\u0627\u0633\u062a\u0641\u0627\u062f\u0629",
+    "9": "\u0627\u0635\u063a\u0631 \u0645\u0646",
+    "10": "\u0627\u0639\u0627\u0642\u0629",
+    "11": "\u0627\u0644 \u062c\u064a",
+    "12": "\u0627\u0644\u062e\u0644\u064a\u062c \u0627\u0644\u0639\u0631\u0628\u064a",
+    "13": "\u0627\u0644\u0630\u0627\u0643\u0631\u0629",
+    "14": "\u0628\u0646\u0641\u0633\u062c\u064a",
+    "15": "\u0628\u0648\u0646\u062a \u0633\u0646\u062a\u0631",
+    "16": "\u062a\u0623\u0645\u064a\u0646 \u0634\u0627\u0645\u0644",
+    "17": "\u062e\u0627\u0635",
+    "18": "\u0645\u0628\u0631\u0648\u0643 \u0627\u0644\u0645\u0648\u0644\u0648\u062f",
+    "19": "\u0645\u062a\u0631 \u0645\u0631\u0628\u0639 - \u06452"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "\u0623\u0628\u0639\u0627\u062f": 0,
+    "\u0623\u0628\u0646 \u0627\u0644\u0623\u062e": 1,
+    "\u0623\u062d\u0627\u0637": 2,
+    "\u0623\u062e\u062a": 3,
+    "\u0623\u062e\u0635\u0627\u0626\u064a\u0629": 4,
+    "\u0625\u0639\u0644\u0627\u0645": 5,
+    "\u0627\u0628\u0631\u0627\u0647\u064a\u0645": 6,
+    "\u0627\u062d\u062a\u0645\u0627\u0644": 7,
+    "\u0627\u0633\u062a\u0641\u0627\u062f\u0629": 8,
+    "\u0627\u0635\u063a\u0631 \u0645\u0646": 9,
+    "\u0627\u0639\u0627\u0642\u0629": 10,
+    "\u0627\u0644 \u062c\u064a": 11,
+    "\u0627\u0644\u062e\u0644\u064a\u062c \u0627\u0644\u0639\u0631\u0628\u064a": 12,
+    "\u0627\u0644\u0630\u0627\u0643\u0631\u0629": 13,
+    "\u0628\u0646\u0641\u0633\u062c\u064a": 14,
+    "\u0628\u0648\u0646\u062a \u0633\u0646\u062a\u0631": 15,
+    "\u062a\u0623\u0645\u064a\u0646 \u0634\u0627\u0645\u0644": 16,
+    "\u062e\u0627\u0635": 17,
+    "\u0645\u0628\u0631\u0648\u0643 \u0627\u0644\u0645\u0648\u0644\u0648\u062f": 18,
+    "\u0645\u062a\u0631 \u0645\u0631\u0628\u0639 - \u06452": 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 sha256:85e567d79342a32dcdcc065c006cc543b35b9cc42d363d71a4f38773a667dd67
+size 345034293

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b984e202bc47e5fabfc74b695ee68dbca00293465b88719a8c243615b670cddf
+size 4091