Training in progress, step 500

config.json

@@ -1,92 +1,32 @@
 {
-  "_name_or_path": "google/efficientnet-b2",
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
   "architectures": [
-    "EfficientNetForImageClassification"
+    "ViTForImageClassification"
   ],
-  "batch_norm_eps": 0.001,
-  "batch_norm_momentum": 0.99,
-  "depth_coefficient": 1.2,
-  "depth_divisor": 8,
-  "depthwise_padding": [
-    5,
-    8,
-    16
-  ],
-  "drop_connect_rate": 0.2,
-  "dropout_rate": 0.3,
-  "expand_ratios": [
-    1,
-    6,
-    6,
-    6,
-    6,
-    6,
-    6
-  ],
-  "hidden_act": "swish",
-  "hidden_dim": 1408,
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
   "id2label": {
     "0": "f",
     "1": "r"
   },
-  "image_size": 260,
-  "in_channels": [
-    32,
-    16,
-    24,
-    40,
-    80,
-    112,
-    192
-  ],
+  "image_size": 224,
   "initializer_range": 0.02,
-  "kernel_sizes": [
-    3,
-    3,
-    5,
-    3,
-    5,
-    5,
-    3
-  ],
+  "intermediate_size": 3072,
   "label2id": {
     "fake": 0,
     "real": 1
   },
-  "model_type": "efficientnet",
-  "num_block_repeats": [
-    1,
-    2,
-    2,
-    3,
-    3,
-    4,
-    1
-  ],
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
   "num_channels": 3,
-  "num_hidden_layers": 64,
-  "out_channels": [
-    16,
-    24,
-    40,
-    80,
-    112,
-    192,
-    320
-  ],
-  "pooling_type": "mean",
+  "num_hidden_layers": 12,
+  "patch_size": 16,
   "problem_type": "single_label_classification",
-  "squeeze_expansion_ratio": 0.25,
-  "strides": [
-    1,
-    2,
-    2,
-    2,
-    1,
-    2,
-    1
-  ],
+  "qkv_bias": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.41.2",
-  "width_coefficient": 1.1
+  "transformers_version": "4.41.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adb7f140c03b6ee2768e7591c4021b67eb4dd0e853771d7612037ea4e2912734
-size 31151640
+oid sha256:6237e9e6b972fa1f287fc2b6b2c8d293c2d993708971e65f288596f867749cf1
+size 343223968

preprocessor_config.json

@@ -4,44 +4,33 @@
     "do_resize",
     "size",
     "resample",
-    "do_center_crop",
-    "crop_size",
     "do_rescale",
     "rescale_factor",
-    "rescale_offset",
     "do_normalize",
     "image_mean",
     "image_std",
-    "include_top",
     "return_tensors",
     "data_format",
     "input_data_format"
   ],
-  "crop_size": {
-    "height": 289,
-    "width": 289
-  },
-  "do_center_crop": false,
   "do_normalize": true,
   "do_rescale": true,
   "do_resize": true,
   "image_mean": [
-    0.485,
-    0.456,
-    0.406
+    0.5,
+    0.5,
+    0.5
   ],
-  "image_processor_type": "EfficientNetImageProcessor",
+  "image_processor_type": "ViTImageProcessor",
   "image_std": [
-    0.47853944,
-    0.4732864,
-    0.47434163
+    0.5,
+    0.5,
+    0.5
   ],
-  "include_top": true,
-  "resample": 0,
+  "resample": 2,
   "rescale_factor": 0.00392156862745098,
-  "rescale_offset": false,
   "size": {
-    "height": 260,
-    "width": 260
+    "height": 224,
+    "width": 224
   }
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52fd665af48052277f24b015e7be78ebd4aada91efede099a406c6c94d24a7df
+oid sha256:a5c17f05f881acad21066bc021f10d2d464c4d0d37cb53f0392275bbd9309d4f
 size 5048