Training in progress, epoch 0

config.json

@@ -1,13 +1,26 @@
 {
-  "_name_or_path": "WinKawaks/vit-tiny-patch16-224",
+  "_name_or_path": "apple/deeplabv3-mobilevit-xx-small",
   "architectures": [
-    "ViTForImageClassification"
+    "MobileViTForImageClassification"
+  ],
+  "aspp_dropout_prob": 0.1,
+  "aspp_out_channels": 256,
+  "atrous_rates": [
+    6,
+    12,
+    18
   ],
   "attention_probs_dropout_prob": 0.0,
-  "encoder_stride": 16,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.0,
-  "hidden_size": 192,
+  "classifier_dropout_prob": 0.1,
+  "conv_kernel_size": 3,
+  "expand_ratio": 2.0,
+  "hidden_act": "silu",
+  "hidden_dropout_prob": 0.05,
+  "hidden_sizes": [
+    64,
+    80,
+    96
+  ],
   "id2label": {
     "0": "burn through",
     "1": "contamination",
@@ -16,9 +29,8 @@
     "4": "lack of penetration",
     "5": "misalignment"
   },
-  "image_size": 224,
+  "image_size": 512,
   "initializer_range": 0.02,
-  "intermediate_size": 768,
   "label2id": {
     "burn through": "0",
     "contamination": "1",
@@ -27,14 +39,25 @@
     "lack of penetration": "4",
     "misalignment": "5"
   },
-  "layer_norm_eps": 1e-12,
-  "model_type": "vit",
-  "num_attention_heads": 3,
+  "layer_norm_eps": 1e-05,
+  "mlp_ratio": 2.0,
+  "model_type": "mobilevit",
+  "neck_hidden_sizes": [
+    16,
+    16,
+    24,
+    48,
+    64,
+    80,
+    320
+  ],
+  "num_attention_heads": 4,
   "num_channels": 3,
-  "num_hidden_layers": 12,
-  "patch_size": 16,
+  "output_stride": 16,
+  "patch_size": 2,
   "problem_type": "single_label_classification",
   "qkv_bias": true,
+  "semantic_loss_ignore_index": 255,
   "torch_dtype": "float32",
   "transformers_version": "4.45.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d8846cdfb537f1aafe224fc3fa258ce1f3709a8ee90a4db8af0148d6eb186aa
-size 22125008
+oid sha256:370c569b883e322bd60f7babe8790bd8ffd21fef7e0b2027d39baa859bf94ce2
+size 3874488

preprocessor_config.json

@@ -1,22 +1,17 @@
 {
-  "do_normalize": true,
+  "crop_size": {
+    "height": 512,
+    "width": 512
+  },
+  "do_center_crop": true,
+  "do_flip_channel_order": true,
+  "do_flip_channels": true,
   "do_rescale": true,
   "do_resize": true,
-  "image_mean": [
-    0.5,
-    0.5,
-    0.5
-  ],
-  "image_processor_type": "ViTImageProcessor",
-  "image_std": [
-    0.5,
-    0.5,
-    0.5
-  ],
+  "image_processor_type": "MobileViTImageProcessor",
   "resample": 2,
   "rescale_factor": 0.00392156862745098,
   "size": {
-    "height": 224,
-    "width": 224
+    "shortest_edge": 544
   }
 }

runs/Jan10_23-59-12_95fa96068200/events.out.tfevents.1736553553.95fa96068200.30.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b939774e0c029fc7d23bf44a65e11d88416cdd6297abadf63d8b99deb7589795
+size 6038

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e48c5b7028114e04c7debc876fa5da117900004aed39042aa8994bee0faaa1d1
+oid sha256:793f43ac6003b831510c6b23cc0f18a3686e81399d0c83d049dfd18a90455c07
 size 5240