Training in progress, epoch 0

config.json

@@ -1,10 +1,11 @@
 {
-  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "_name_or_path": "facebook/dinov2-base-imagenet1k-1-layer",
+  "apply_layernorm": true,
   "architectures": [
-    "ViTForImageClassification"
+    "Dinov2ForImageClassification"
   ],
   "attention_probs_dropout_prob": 0.0,
-  "encoder_stride": 16,
+  "drop_path_rate": 0.0,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.0,
   "hidden_size": 768,
@@ -111,9 +112,8 @@
     "98": "tiramisu",
     "99": "tuna_tartare"
   },
-  "image_size": 224,
+  "image_size": 518,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "apple_pie": "0",
     "baby_back_ribs": "1",
@@ -217,14 +217,39 @@
     "tuna_tartare": "99",
     "waffles": "100"
   },
-  "layer_norm_eps": 1e-12,
-  "model_type": "vit",
+  "layer_norm_eps": 1e-06,
+  "layerscale_value": 1.0,
+  "mlp_ratio": 4,
+  "model_type": "dinov2",
   "num_attention_heads": 12,
   "num_channels": 3,
   "num_hidden_layers": 12,
-  "patch_size": 16,
+  "out_features": [
+    "stage12"
+  ],
+  "out_indices": [
+    12
+  ],
+  "patch_size": 14,
   "problem_type": "single_label_classification",
   "qkv_bias": true,
+  "reshape_hidden_states": true,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4",
+    "stage5",
+    "stage6",
+    "stage7",
+    "stage8",
+    "stage9",
+    "stage10",
+    "stage11",
+    "stage12"
+  ],
   "torch_dtype": "float32",
-  "transformers_version": "4.45.2"
+  "transformers_version": "4.45.2",
+  "use_swiglu_ffn": false
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba2153f16139dfcebfa9c9950983678896b77424af76370894f90b3fe1839a04
-size 343528508
+oid sha256:05788d610a3673dfd72090b4fa6fa257440732d73dd79e3d2dfab0ad702055a6
+size 346968596

preprocessor_config.json

@@ -1,22 +1,27 @@
 {
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
   "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": "ViTImageProcessor",
+  "image_processor_type": "BitImageProcessor",
   "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,
-    "width": 224
+    "shortest_edge": 256
   }
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a7eca98acfaf2eeb6c6ef33572fe57afbfb453c99f19e123ddda209efef149f
+oid sha256:c671a5fcbe7d16d79076cb4878b8410ccb68849472fbe6b6c0a22edf7d53fabb
 size 5240