Training in progress, epoch 0

config.json

@@ -1,15 +1,24 @@
 {
-  "_name_or_path": "google/mobilenet_v2_1.4_224",
+  "_name_or_path": "microsoft/resnet-50",
   "architectures": [
-    "MobileNetV2ForImageClassification"
+    "ResNetForImageClassification"
+  ],
+  "depths": [
+    3,
+    4,
+    6,
+    3
+  ],
+  "downsample_in_bottleneck": false,
+  "downsample_in_first_stage": false,
+  "embedding_size": 64,
+  "hidden_act": "relu",
+  "hidden_sizes": [
+    256,
+    512,
+    1024,
+    2048
   ],
-  "classifier_dropout_prob": 0.2,
-  "depth_divisible_by": 8,
-  "depth_multiplier": 1.4,
-  "expand_ratio": 6,
-  "finegrained_output": true,
-  "first_layer_is_expansion": true,
-  "hidden_act": "relu6",
   "id2label": {
     "0": "apple_pie",
     "1": "baby_back_ribs",
@@ -113,8 +122,6 @@
     "98": "tiramisu",
     "99": "tuna_tartare"
   },
-  "image_size": 224,
-  "initializer_range": 0.02,
   "label2id": {
     "apple_pie": "0",
     "baby_back_ribs": "1",
@@ -218,14 +225,23 @@
     "tuna_tartare": "99",
     "waffles": "100"
   },
-  "layer_norm_eps": 0.001,
-  "min_depth": 8,
-  "model_type": "mobilenet_v2",
+  "layer_type": "bottleneck",
+  "model_type": "resnet",
   "num_channels": 3,
-  "output_stride": 32,
+  "out_features": [
+    "stage4"
+  ],
+  "out_indices": [
+    4
+  ],
   "problem_type": "single_label_classification",
-  "semantic_loss_ignore_index": 255,
-  "tf_padding": true,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4"
+  ],
   "torch_dtype": "float32",
   "transformers_version": "4.41.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acc22f00a578715e08904ee3405cdb8b23fa681fa356097870f8c791b5f9b854
-size 18217604
+oid sha256:79831bb3a6d35a094cf05c79c7ea9d007b59310a6348755bfe54a687538bab83
+size 95114484

preprocessor_config.json

@@ -3,9 +3,8 @@
     "images",
     "do_resize",
     "size",
+    "crop_pct",
     "resample",
-    "do_center_crop",
-    "crop_size",
     "do_rescale",
     "rescale_factor",
     "do_normalize",
@@ -15,28 +14,24 @@
     "data_format",
     "input_data_format"
   ],
-  "crop_size": {
-    "height": 224,
-    "width": 224
-  },
-  "do_center_crop": true,
+  "crop_pct": 0.875,
   "do_normalize": true,
   "do_rescale": true,
   "do_resize": true,
   "image_mean": [
-    0.5,
-    0.5,
-    0.5
+    0.485,
+    0.456,
+    0.406
   ],
-  "image_processor_type": "MobileNetV2ImageProcessor",
+  "image_processor_type": "ConvNextImageProcessor",
   "image_std": [
-    0.5,
-    0.5,
-    0.5
+    0.229,
+    0.224,
+    0.225
   ],
-  "resample": 2,
+  "resample": 3,
   "rescale_factor": 0.00392156862745098,
   "size": {
-    "shortest_edge": 256
+    "shortest_edge": 224
   }
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:644757217992f5de88a431d32ba529047a80649d178210bda8ccae9685ed15ce
+oid sha256:e209e09331227110b8ec9939c2502dd5de9c9e5b1a80bf66605f8dfbd80357d0
 size 5112