Training in progress, epoch 0

config.json

@@ -1,39 +1,39 @@
-{
-  "_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": 0,
-    "1": 1
-  },
-  "image_size": 224,
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "label2id": {
-    "0": 0,
-    "1": 1
-  },
-  "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": "4.41.2",
-  "tubelet_size": 2,
-  "use_mean_pooling": false
-}
+{
+  "_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": 0,
+    "1": 1
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "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": "4.44.2",
+  "tubelet_size": 2,
+  "use_mean_pooling": false
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a350e6f8e506d79fc0d319c33d171d25ab69e8078bdcc63d1ae3848c1e9b452
+oid sha256:61f1dea9cf49ac0caa8bfdf8429c8b17fae06dd87d9399ecd331f370b766ecb2
 size 344937368

preprocessor_config.json

@@ -1,42 +1,26 @@
-{
-  "_valid_processor_keys": [
-    "videos",
-    "do_resize",
-    "size",
-    "resample",
-    "do_center_crop",
-    "crop_size",
-    "do_rescale",
-    "rescale_factor",
-    "do_normalize",
-    "image_mean",
-    "image_std",
-    "return_tensors",
-    "data_format",
-    "input_data_format"
-  ],
-  "crop_size": {
-    "height": 224,
-    "width": 224
-  },
-  "do_center_crop": true,
-  "do_normalize": true,
-  "do_rescale": true,
-  "do_resize": true,
-  "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
-  }
-}
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "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
+  }
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50485af7937a6c0d6b4f063bf200b0ee5aaa9df06e80fe9921377cb981c73499
-size 5112
+oid sha256:8c6a2435043e09b34b4957a466379bf0f8057c5e1d27c1181a6e2aff065753d1
+size 5304