Training in progress, epoch 0

config.json

@@ -1,13 +1,14 @@
 {
-  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "_name_or_path": "facebook/dinov2-large",
+  "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,
+  "hidden_size": 1024,
   "id2label": {
     "0": "DR",
     "1": "G",
@@ -15,9 +16,8 @@
     "3": "WD",
     "4": "other"
   },
-  "image_size": 224,
+  "image_size": 518,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "DR": 0,
     "G": 1,
@@ -25,14 +25,51 @@
     "WD": 3,
     "other": 4
   },
-  "layer_norm_eps": 1e-12,
-  "model_type": "vit",
-  "num_attention_heads": 12,
+  "layer_norm_eps": 1e-06,
+  "layerscale_value": 1.0,
+  "mlp_ratio": 4,
+  "model_type": "dinov2",
+  "num_attention_heads": 16,
   "num_channels": 3,
-  "num_hidden_layers": 12,
-  "patch_size": 16,
+  "num_hidden_layers": 24,
+  "out_features": [
+    "stage24"
+  ],
+  "out_indices": [
+    24
+  ],
+  "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",
+    "stage13",
+    "stage14",
+    "stage15",
+    "stage16",
+    "stage17",
+    "stage18",
+    "stage19",
+    "stage20",
+    "stage21",
+    "stage22",
+    "stage23",
+    "stage24"
+  ],
   "torch_dtype": "float32",
-  "transformers_version": "4.36.2"
+  "transformers_version": "4.35.2",
+  "use_swiglu_ffn": false
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e96567d5a698fe395078487f536178c594712539ac50e4be2a9589e15603a2da
-size 343233204
+oid sha256:4f16d0a90b7c2f366de617fa7b4dfd5332ec29c5949956e63483af4a1d2b8fc6
+size 1217567100

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
   }
 }

runs/Jan22_22-37-20_424f285bbf23/events.out.tfevents.1705963057.424f285bbf23.6619.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be8cb0bf3dcd7a9063f9bd95033543d44fe4045d393a67a01586bbcf15785187
+size 4980

runs/Jan22_22-37-54_424f285bbf23/events.out.tfevents.1705963085.424f285bbf23.6619.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a55cf65ca5c056dcbd8a5fee55ec92471c7c426cc42428c5a381fbc379b4e70f
+size 12985

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e86f796c1e3b5f959f41580a83e4304522c568c21e78d5086d958eaedb79a86f
-size 4792
+oid sha256:5b447bd1c48a551e59eb0af020b63b4b16fd1924c0d7ba6bb7de8cd4304e92bc
+size 4664