Training in progress, epoch 0

config.json

@@ -1,26 +1,18 @@
 {
-  "_name_or_path": "apple/deeplabv3-mobilevit-xx-small",
+  "_name_or_path": "microsoft/beit-base-patch16-224-pt22k-ft22k",
+  "add_fpn": false,
   "architectures": [
-    "MobileViTForImageClassification"
-  ],
-  "aspp_dropout_prob": 0.1,
-  "aspp_out_channels": 256,
-  "atrous_rates": [
-    6,
-    12,
-    18
+    "BeitForImageClassification"
   ],
   "attention_probs_dropout_prob": 0.0,
-  "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
-  ],
+  "auxiliary_channels": 256,
+  "auxiliary_concat_input": false,
+  "auxiliary_loss_weight": 0.4,
+  "auxiliary_num_convs": 1,
+  "drop_path_rate": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
   "id2label": {
     "0": "burn through",
     "1": "contamination",
@@ -29,8 +21,9 @@
     "4": "lack of penetration",
     "5": "misalignment"
   },
-  "image_size": 512,
+  "image_size": 224,
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "burn through": "0",
     "contamination": "1",
@@ -39,25 +32,50 @@
     "lack of penetration": "4",
     "misalignment": "5"
   },
-  "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,
+  "layer_norm_eps": 1e-12,
+  "layer_scale_init_value": 0.1,
+  "model_type": "beit",
+  "num_attention_heads": 12,
   "num_channels": 3,
-  "output_stride": 16,
-  "patch_size": 2,
+  "num_hidden_layers": 12,
+  "out_features": [
+    "stage12"
+  ],
+  "out_indices": [
+    12
+  ],
+  "patch_size": 16,
+  "pool_scales": [
+    1,
+    2,
+    3,
+    6
+  ],
   "problem_type": "single_label_classification",
-  "qkv_bias": true,
+  "reshape_hidden_states": true,
   "semantic_loss_ignore_index": 255,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4",
+    "stage5",
+    "stage6",
+    "stage7",
+    "stage8",
+    "stage9",
+    "stage10",
+    "stage11",
+    "stage12"
+  ],
   "torch_dtype": "float32",
-  "transformers_version": "4.45.1"
+  "transformers_version": "4.45.1",
+  "use_absolute_position_embeddings": false,
+  "use_auxiliary_head": true,
+  "use_mask_token": false,
+  "use_mean_pooling": true,
+  "use_relative_position_bias": true,
+  "use_shared_relative_position_bias": false,
+  "vocab_size": 8192
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:370c569b883e322bd60f7babe8790bd8ffd21fef7e0b2027d39baa859bf94ce2
-size 3874488
+oid sha256:e9fad10b25aefbda1df347e9517d862671c6c7d3faa0618cd5bf4e7bc7eca7d2
+size 343092632

preprocessor_config.json

@@ -1,17 +1,28 @@
 {
   "crop_size": {
-    "height": 512,
-    "width": 512
+    "height": 224,
+    "width": 224
   },
-  "do_center_crop": true,
-  "do_flip_channel_order": true,
-  "do_flip_channels": true,
+  "do_center_crop": false,
+  "do_normalize": true,
+  "do_reduce_labels": false,
   "do_rescale": true,
   "do_resize": true,
-  "image_processor_type": "MobileViTImageProcessor",
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "BeitImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
   "resample": 2,
   "rescale_factor": 0.00392156862745098,
   "size": {
-    "shortest_edge": 544
+    "height": 224,
+    "width": 224
   }
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:793f43ac6003b831510c6b23cc0f18a3686e81399d0c83d049dfd18a90455c07
-size 5240
+oid sha256:d91cbe3d74aadbf0ee0fa5e86525d7a236c9b8a5ec2c3ed82c6856d89c7a7b61
+size 5176