Training in progress, epoch 0

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "google/vivit-b-16x2-kinetics400",
+  "architectures": [
+    "VivitForVideoClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "hidden_act": "gelu_fast",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "b",
+    "1": "p",
+    "2": "s"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "b": 0,
+    "p": 1,
+    "s": 2
+  },
+  "layer_norm_eps": 1e-06,
+  "model_type": "vivit",
+  "num_attention_heads": 3,
+  "num_channels": 3,
+  "num_frames": 38,
+  "num_hidden_layers": 3,
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "tubelet_size": [
+    19,
+    16,
+    16
+  ]
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5dfb39ce732fa9e4791d2fbbcd2a195f21c7f9cf7c5a465e1eb1008ce595191
+size 131116364

preprocessor_config.json

@@ -0,0 +1,44 @@
+{
+  "_valid_processor_keys": [
+    "videos",
+    "do_resize",
+    "size",
+    "resample",
+    "do_center_crop",
+    "crop_size",
+    "do_rescale",
+    "rescale_factor",
+    "offset",
+    "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": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "VivitImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "offset": true,
+  "resample": 2,
+  "rescale_factor": 0.00784313725490196,
+  "size": {
+    "shortest_edge": 224
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77ed0ebd0b860c316d72d0cacb552181a81dc509bcfab2b749ce785e5d14b2dc
+size 4667