Training in progress, epoch 1

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "finetuning_task": "image-classification",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "model",
+    "1": "pack-accessory",
+    "2": "pack-bottom-l0",
+    "3": "pack-bottom-l1",
+    "4": "pack-one-piece-l1",
+    "5": "pack-shoes",
+    "6": "pack-top-l1",
+    "7": "pack-top-l2",
+    "8": "pack-top-l3"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "model": "0",
+    "pack-accessory": "1",
+    "pack-bottom-l0": "2",
+    "pack-bottom-l1": "3",
+    "pack-one-piece-l1": "4",
+    "pack-shoes": "5",
+    "pack-top-l1": "6",
+    "pack-top-l2": "7",
+    "pack-top-l3": "8"
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.0.dev0"
+}

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b93f7fb523ce23e611b5fe748176cb8c04a5036f53e51628cc0d8a6c7b8ccf8
+size 343290221

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92d6f2f83d01f23544fe3c23b64bf0f8b27b5c4b808c36d7be5de9a3786457c7
+size 4091