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": "!  \u0630\u0648\u0642\u0643 \u0631\u0627\u0626\u0639",
+    "1": "\u0623\u0631\u062c\u0648\u062d\u0629",
+    "2": "\u0625\u062d\u0631\u0627\u062c",
+    "3": "\u0627\u062f\u0639\u0649",
+    "4": "\u0627\u0633\u062a\u064a\u0631\u0627\u062f",
+    "5": "\u0627\u0633\u0637\u0648\u0644",
+    "6": "\u0627\u0639\u0627\u0642\u0629 \u0630\u0647\u0646\u064a\u0629",
+    "7": "\u0627\u0643\u062a\u0626\u0627\u0628",
+    "8": "\u0627\u0644\u062b\u0627\u0646\u064a",
+    "9": "\u0627\u0644\u062b\u0644\u0627\u062b\u0627\u0621",
+    "10": "\u0627\u0644\u0633\u0627\u0628\u0639",
+    "11": "\u0627\u0644\u0633\u0645\u0627\u0639\u0629",
+    "12": "\u0628\u0637\u0627\u0644\u0629",
+    "13": "\u062a\u064a\u0646",
+    "14": "\u062e\u0641\u0636",
+    "15": "\u0635\u0628\u0627\u062d \u0627\u0644\u0646\u0648\u0631",
+    "16": "\u063a\u064a\u0631 \u0645\u0644\u0632\u0645",
+    "17": "\u0646\u0627\u062f\u064a \u0627\u0644\u062a\u0639\u0627\u0648\u0646",
+    "18": "\u0646\u0627\u062f\u064a \u0627\u0644\u0634\u0628\u0627\u0628",
+    "19": "\u0646\u0627\u062f\u064a \u0627\u0644\u0639\u0631\u0628\u064a"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "!  \u0630\u0648\u0642\u0643 \u0631\u0627\u0626\u0639": 0,
+    "\u0623\u0631\u062c\u0648\u062d\u0629": 1,
+    "\u0625\u062d\u0631\u0627\u062c": 2,
+    "\u0627\u062f\u0639\u0649": 3,
+    "\u0627\u0633\u062a\u064a\u0631\u0627\u062f": 4,
+    "\u0627\u0633\u0637\u0648\u0644": 5,
+    "\u0627\u0639\u0627\u0642\u0629 \u0630\u0647\u0646\u064a\u0629": 6,
+    "\u0627\u0643\u062a\u0626\u0627\u0628": 7,
+    "\u0627\u0644\u062b\u0627\u0646\u064a": 8,
+    "\u0627\u0644\u062b\u0644\u0627\u062b\u0627\u0621": 9,
+    "\u0627\u0644\u0633\u0627\u0628\u0639": 10,
+    "\u0627\u0644\u0633\u0645\u0627\u0639\u0629": 11,
+    "\u0628\u0637\u0627\u0644\u0629": 12,
+    "\u062a\u064a\u0646": 13,
+    "\u062e\u0641\u0636": 14,
+    "\u0635\u0628\u0627\u062d \u0627\u0644\u0646\u0648\u0631": 15,
+    "\u063a\u064a\u0631 \u0645\u0644\u0632\u0645": 16,
+    "\u0646\u0627\u062f\u064a \u0627\u0644\u062a\u0639\u0627\u0648\u0646": 17,
+    "\u0646\u0627\u062f\u064a \u0627\u0644\u0634\u0628\u0627\u0628": 18,
+    "\u0646\u0627\u062f\u064a \u0627\u0644\u0639\u0631\u0628\u064a": 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:ac3f4fc825aa8108d38cd536ca7f572d299573644cc63087ad0d419a9c58f36e
+size 345031733

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5039752e5400a1fce8088bfbe92c9f0f8e4107572e22076a0f2b9a15814df97
+size 4091