Training in progress, epoch 0

config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "MCG-NJU/videomae-base-finetuned-kinetics",
+  "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": "Alhamdulillah",
+    "1": "Good bye",
+    "2": "Good evening",
+    "3": "Good morning",
+    "4": "How are you",
+    "5": "I am pleased to meet you",
+    "6": "I_m fine",
+    "7": "I_m sorry",
+    "8": "Not bad",
+    "9": "Salam aleikum (peace be upon you)",
+    "10": "Sorry (Excuse me)",
+    "11": "Thanks"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Alhamdulillah": 0,
+    "Good bye": 1,
+    "Good evening": 2,
+    "Good morning": 3,
+    "How are you": 4,
+    "I am pleased to meet you": 5,
+    "I_m fine": 6,
+    "I_m sorry": 7,
+    "Not bad": 8,
+    "Salam aleikum (peace be upon you)": 9,
+    "Sorry (Excuse me)": 10,
+    "Thanks": 11
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "videomae",
+  "norm_pix_loss": false,
+  "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": "4.39.3",
+  "tubelet_size": 2,
+  "use_mean_pooling": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60feed0d2fad6b40a128aa60eccd385b98abb51233dc2b53a58f76e5c1c62cb7
+size 344968096

preprocessor_config.json

@@ -0,0 +1,42 @@
+{
+  "_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
+  }
+}

runs/May14_13-49-43_a29789280118/events.out.tfevents.1715694613.a29789280118.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:721a576c6a6bc2244b43a117fc3e65cdb0168b7d2d0a4fe94e8df1dc454dbe0d
+size 9593

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0460a930d1cf03581240ee255b7c725af1754efc8513e7f791156d80890f4351
+size 5048