Training in progress, epoch 0

config.json

@@ -0,0 +1,67 @@
+{
+  "_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": "Normal Forward Driving",
+    "1": "Drinking",
+    "2": "Phone Call(right)",
+    "3": "Phone Call(left)",
+    "4": "Eating",
+    "5": "Text (Right)",
+    "6": "Text (Left)",
+    "7": "Reaching behind",
+    "8": "Adjust control panel",
+    "9": "Pick up from floor (Driver)",
+    "10": "Pick up from floor (Passenger)",
+    "11": "Talk to passenger at the right",
+    "12": "Talk to passenger at backseat",
+    "13": "yawning",
+    "14": "Hand on head",
+    "15": "Singing or dancing with music"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Adjust control panel": 8,
+    "Drinking": 1,
+    "Eating": 4,
+    "Hand on head": 14,
+    "Normal Forward Driving": 0,
+    "Phone Call(left)": 3,
+    "Phone Call(right)": 2,
+    "Pick up from floor (Driver)": 9,
+    "Pick up from floor (Passenger)": 10,
+    "Reaching behind": 7,
+    "Singing or dancing with music": 15,
+    "Talk to passenger at backseat": 12,
+    "Talk to passenger at the right": 11,
+    "Text (Left)": 6,
+    "Text (Right)": 5,
+    "yawning": 13
+  },
+  "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": "4.35.2",
+  "tubelet_size": 2,
+  "use_mean_pooling": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da0fc54fbd3fed8561a846c0e3365250b8e13bf9c070ec6b69b10ba2184e9314
+size 344980440

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
+  }
+}

runs/Nov29_20-51-40_ca9043fffaa6/events.out.tfevents.1701291113.ca9043fffaa6.3627.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5abdaf6b4b0807eaaea315cc87486cfa4667933eb93f1488f2f4d15387800ac2
+size 7986

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c9b0805b3d5290ad51406215a1694ac61a0733098695e454775c1773071634d
+size 4664