Training in progress, epoch 0

config.json

@@ -1,13 +1,20 @@
 {
-  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "_name_or_path": "shi-labs/nat-mini-in1k-224",
   "architectures": [
-    "ViTForImageClassification"
+    "NatForImageClassification"
   ],
   "attention_probs_dropout_prob": 0.0,
-  "encoder_stride": 16,
+  "depths": [
+    3,
+    4,
+    6,
+    5
+  ],
+  "drop_path_rate": 0.2,
+  "embed_dim": 64,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.0,
-  "hidden_size": 768,
+  "hidden_size": 512,
   "id2label": {
     "0": "apple_pie",
     "1": "baby_back_ribs",
@@ -111,9 +118,8 @@
     "98": "tiramisu",
     "99": "tuna_tartare"
   },
-  "image_size": 224,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "kernel_size": 7,
   "label2id": {
     "apple_pie": "0",
     "baby_back_ribs": "1",
@@ -217,14 +223,35 @@
     "tuna_tartare": "99",
     "waffles": "100"
   },
-  "layer_norm_eps": 1e-12,
-  "model_type": "vit",
-  "num_attention_heads": 12,
+  "layer_norm_eps": 1e-05,
+  "layer_scale_init_value": 0.0,
+  "mlp_ratio": 3.0,
+  "model_type": "nat",
   "num_channels": 3,
-  "num_hidden_layers": 12,
-  "patch_size": 16,
+  "num_heads": [
+    2,
+    4,
+    8,
+    16
+  ],
+  "num_layers": 4,
+  "out_features": [
+    "stage4"
+  ],
+  "out_indices": [
+    4
+  ],
+  "patch_size": 4,
+  "path_norm": true,
   "problem_type": "single_label_classification",
   "qkv_bias": true,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4"
+  ],
   "torch_dtype": "float32",
   "transformers_version": "4.35.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dac0325cc49bda023ab0368bd01058903ec6135648f0d3c05d3ba7349da1ba49
-size 343528508
+oid sha256:f2421f3149ca7c94e720fa8193b928373aa6bc9e856713e21e5cd1a798fbaff4
+size 78131212

preprocessor_config.json

@@ -3,17 +3,17 @@
   "do_rescale": true,
   "do_resize": true,
   "image_mean": [
-    0.5,
-    0.5,
-    0.5
+    0.485,
+    0.456,
+    0.406
   ],
   "image_processor_type": "ViTImageProcessor",
   "image_std": [
-    0.5,
-    0.5,
-    0.5
+    0.229,
+    0.224,
+    0.225
   ],
-  "resample": 2,
+  "resample": 3,
   "rescale_factor": 0.00392156862745098,
   "size": {
     "height": 224,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8df2f963698bca357cedcfcb68cdea4925d5b131032bd50d9987486dc9151830
+oid sha256:d6422a2bcfcd68bcb3ec0785875ef3b3f62fe47d5134196d3db38a278361218e
 size 4155