Training in progress, epoch 0

config.json

@@ -0,0 +1,56 @@
+{
+  "_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": "\u1100\u1161\u1105\u1167\u11b8\u1103\u1161",
+    "1": "\u1100\u1169\u11af\u110c\u1165\u11af",
+    "2": "\u1100\u116e\u1100\u1173\u11b8\u110e\u1161",
+    "3": "\u1103\u1161\u1105\u1175",
+    "4": "\u1107\u1162\u1100\u1169\u1111\u1173\u1103\u1161",
+    "5": "\u1107\u1167\u11bc\u110b\u116f\u11ab",
+    "6": "\u1107\u116e\u11bc\u1103\u1162",
+    "7": "\u110a\u1173\u1105\u1165\u110c\u1175\u1103\u1161",
+    "8": "\u110b\u1174\u1109\u1161",
+    "9": "\u110e\u1175\u11ab\u1100\u116e"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "\u1100\u1161\u1105\u1167\u11b8\u1103\u1161": 0,
+    "\u1100\u1169\u11af\u110c\u1165\u11af": 1,
+    "\u1100\u116e\u1100\u1173\u11b8\u110e\u1161": 2,
+    "\u1103\u1161\u1105\u1175": 3,
+    "\u1107\u1162\u1100\u1169\u1111\u1173\u1103\u1161": 4,
+    "\u1107\u1167\u11bc\u110b\u116f\u11ab": 5,
+    "\u1107\u116e\u11bc\u1103\u1162": 6,
+    "\u110a\u1173\u1105\u1165\u110c\u1175\u1103\u1161": 7,
+    "\u110b\u1174\u1109\u1161": 8,
+    "\u110e\u1175\u11ab\u1100\u116e": 9
+  },
+  "layer_norm_eps": 1e-06,
+  "model_type": "vivit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_frames": 32,
+  "num_hidden_layers": 12,
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "tubelet_size": [
+    2,
+    16,
+    16
+  ],
+  "video_size": [
+    32,
+    224,
+    224
+  ]
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:927084a62ddd95ed103956ebe3f01a32aeb0e30ad8cf5026dc2f6cccfce3418c
+size 354639992

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
+  }
+}

runs/May05_11-43-42_d18d1efa833b/events.out.tfevents.1714909451.d18d1efa833b.4611.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81c5ea90684aa8aa2582e292a151e9d4ec283d5f79ef6559e5c6c10c48acd78a
+size 7124

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f31e6ae186cab0a307f0fe13e2c033872f6d33eeb96228031167c943155d1ba
+size 5048