Training in progress, epoch 1

config.json

@@ -1,13 +1,21 @@
 {
   "architectures": [
-    "ViTForImageClassification"
+    "SwinForImageClassification"
   ],
   "attention_probs_dropout_prob": 0.0,
+  "depths": [
+    2,
+    2,
+    18,
+    2
+  ],
+  "drop_path_rate": 0.1,
   "dtype": "float32",
-  "encoder_stride": 16,
+  "embed_dim": 128,
+  "encoder_stride": 32,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.0,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "id2label": {
     "0": "Altocumulus",
     "1": "Cirrocumulus",
@@ -22,7 +30,6 @@
   },
   "image_size": 224,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "Altocumulus": "0",
     "Cirrocumulus": "1",
@@ -35,15 +42,35 @@
     "stratiform clouds": "8",
     "stratocumulus clouds": "9"
   },
-  "layer_norm_eps": 1e-12,
-  "model_type": "vit",
-  "num_attention_heads": 12,
+  "layer_norm_eps": 1e-05,
+  "mlp_ratio": 4.0,
+  "model_type": "swin",
   "num_channels": 3,
-  "num_hidden_layers": 12,
-  "patch_size": 16,
-  "pooler_act": "tanh",
-  "pooler_output_size": 768,
+  "num_heads": [
+    4,
+    8,
+    16,
+    32
+  ],
+  "num_layers": 4,
+  "out_features": [
+    "stage4"
+  ],
+  "out_indices": [
+    4
+  ],
+  "patch_size": 4,
+  "path_norm": true,
   "problem_type": "single_label_classification",
   "qkv_bias": true,
-  "transformers_version": "4.57.1"
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4"
+  ],
+  "transformers_version": "4.57.1",
+  "use_absolute_embeddings": false,
+  "window_size": 7
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bcc51ad354351adaaf786d09e5ff4f7b7019284dc0c65cb844510a1882d8c50
-size 343248584
+oid sha256:dc5aac912f28a8ef644f613256241face62f78619127b67b8718eb2f49811878
+size 347531616

preprocessor_config.json

@@ -4,17 +4,17 @@
   "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:e61182265f93a8d45b69756a0b9c9ecdf796247cc5695e5e90690cdc75e57379
+oid sha256:388c67f880ef800dab4ff2387418cf69e12d667dd9aa32f53525d8a782532d99
 size 5841