Training in progress, epoch 0

config.json

@@ -0,0 +1,63 @@
+{
+  "_name_or_path": "shossain11/videomae-base-finetuned-inhard-finetuned-inhard2",
+  "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": "Assemble_system",
+    "1": "Consult_sheets",
+    "2": "No_action",
+    "3": "Picking_in_front",
+    "4": "Picking_left",
+    "5": "Put_down_component",
+    "6": "Put_down_measuring_rod",
+    "7": "Put_down_screwdriver",
+    "8": "Put_down_subsystem",
+    "9": "Take_component",
+    "10": "Take_measuring_rod",
+    "11": "Take_screwdriver",
+    "12": "Take_subsystem",
+    "13": "Turn_sheets"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Assemble_system": 0,
+    "Consult_sheets": 1,
+    "No_action": 2,
+    "Picking_in_front": 3,
+    "Picking_left": 4,
+    "Put_down_component": 5,
+    "Put_down_measuring_rod": 6,
+    "Put_down_screwdriver": 7,
+    "Put_down_subsystem": 8,
+    "Take_component": 9,
+    "Take_measuring_rod": 10,
+    "Take_screwdriver": 11,
+    "Take_subsystem": 12,
+    "Turn_sheets": 13
+  },
+  "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": "4.35.2",
+  "tubelet_size": 2,
+  "use_mean_pooling": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92f79bab7b498361cbf2dd927891d2152b40eedad97738f9b30ae4a7f289a608
+size 344974288

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
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43cb2de0de756fb91ceb761184bf8591a2ddf59a6c166ef7359ccd809c7c7c58
+size 4664