Training in progress, epoch 0

config.json

@@ -0,0 +1,71 @@
+{
+  "_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": "SK",
+    "1": "lupper",
+    "2": "LBRound",
+    "3": "rhook",
+    "4": "LElbow",
+    "5": "Teep",
+    "6": "rupper",
+    "7": "cross",
+    "8": "HM",
+    "9": "LKnee",
+    "10": "lhook",
+    "11": "jab",
+    "12": "RKnee",
+    "13": "Check",
+    "14": "RLRound",
+    "15": "RElbow",
+    "16": "RBRound",
+    "17": "Sidekick"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Check": 13,
+    "HM": 8,
+    "LBRound": 2,
+    "LElbow": 4,
+    "LKnee": 9,
+    "RBRound": 16,
+    "RElbow": 15,
+    "RKnee": 12,
+    "RLRound": 14,
+    "SK": 0,
+    "Sidekick": 17,
+    "Teep": 5,
+    "cross": 7,
+    "jab": 11,
+    "lhook": 10,
+    "lupper": 1,
+    "rhook": 3,
+    "rupper": 6
+  },
+  "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": "4.47.0.dev0",
+  "tubelet_size": 2,
+  "use_mean_pooling": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00169acb29d1c7516603ad484808b32e7d65783af58d365794f5b3620ad6411e
+size 344986552

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "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/Nov26_23-49-10_29fc5810b4c5/events.out.tfevents.1732664956.29fc5810b4c5.15852.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99bff24da57b56b07e681862a90a774fce9c311233b4f2ec2a00991ea662430a
+size 13956

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20dce62242fa34746ff23485a45f87cbeaba438b56a90ccc88d08e736fc19210
+size 5432