Training in progress, epoch 0

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "MCG-NJU/videomae-base",
+  "architectures": [
+    "VideoMAEForVideoClassification"
+  ],
+  "attention_probs_dropout_prob": 0.2,
+  "decoder_hidden_size": 384,
+  "decoder_intermediate_size": 1536,
+  "decoder_num_attention_heads": 6,
+  "decoder_num_hidden_layers": 4,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.2,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "nonpunch",
+    "1": "punch"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "nonpunch": 0,
+    "punch": 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": "4.48.1",
+  "tubelet_size": 2,
+  "use_mean_pooling": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f53450b236aed87c018e1e0ab0e3016e125b7571f4b770436eb3c29c4a425644
+size 344937368

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d162f4634385177062eda8fb58ef7848f4f3d106954428283898d1be1cc86cde
+size 5304