Training in progress, epoch 1

config.json

@@ -1,13 +1,21 @@
 {
-  "_name_or_path": "trpakov/vit-face-expression",
+  "_name_or_path": "microsoft/swin-base-patch4-window7-224-in22k",
   "architectures": [
-    "ViTForImageClassification"
+    "SwinForImageClassification"
   ],
   "attention_probs_dropout_prob": 0.0,
-  "encoder_stride": 16,
+  "depths": [
+    2,
+    2,
+    18,
+    2
+  ],
+  "drop_path_rate": 0.1,
+  "embed_dim": 128,
+  "encoder_stride": 32,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.0,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "id2label": {
     "0": "anger",
     "1": "contempt",
@@ -20,7 +28,6 @@
   },
   "image_size": 224,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "anger": "0",
     "contempt": "1",
@@ -31,14 +38,36 @@
     "sad": "6",
     "surprise": "7"
   },
-  "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,
+  "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,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4"
+  ],
   "torch_dtype": "float32",
-  "transformers_version": "4.44.2"
+  "transformers_version": "4.44.2",
+  "use_absolute_embeddings": false,
+  "window_size": 7
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bd264f6e22f11fb96123ee30facaf700e2127658a88cabe0278858968b7540a
-size 343242432
+oid sha256:368697a802d97193f16bd1a4dcc13c6fab998e472cc6c0bba583dc66e00007fb
+size 347523416

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,

runs/Sep06_10-50-45_b5b5a316ba07/events.out.tfevents.1725619858.b5b5a316ba07.1210.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:024df5aaca6521d01615e8788ac74ce94e6766672ef541e0e531d343d58e10e5
+size 6074

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2497623d1e769419aaaf6a573a444e096fabd72f605828f2118668cf07b8d23
+oid sha256:8b4dcf0cea76ed6e515dd351c4afabdfcf2f51c785ae6a1c6dda93d38844072d
 size 5240