Training in progress, epoch 1

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "MCG-NJU/videomae-base",
+  "architectures": [
+    "VideoMAEForPreTraining"
+  ],
+  "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,
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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,
+  "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 sha256:247e6e5116038dcf1656db6ef898df692178881414814f53992ba4351eb9f94d
+size 376873760

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/Jan08_13-29-52_5a09d8f8faa6/events.out.tfevents.1704720665.5a09d8f8faa6.368.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf1cca6fd7e55ba1538c1bf79b187642ae80a57bb45d61284249acbdf09a63df
+size 14127

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd010b8ec87365a48eed6c0cac6a1f3220dcda07fe816485c2cefd39eaee1c38
+size 4600