Training in progress, epoch 1

config.json

@@ -1,8 +1,13 @@
 {
-  "_name_or_path": "openai/clip-vit-base-patch32",
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
   "architectures": [
-    "CLIPForImageClassification"
+    "ViTForImageClassification"
   ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
   "id2label": {
     "0": "1",
     "1": "2",
@@ -10,7 +15,9 @@
     "3": "4",
     "4": "5"
   },
-  "initializer_factor": 1.0,
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "1": "0",
     "2": "1",
@@ -18,20 +25,14 @@
     "4": "3",
     "5": "4"
   },
-  "logit_scale_init_value": 2.6592,
-  "model_type": "clip",
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
   "problem_type": "single_label_classification",
-  "projection_dim": 512,
-  "text_config": {
-    "bos_token_id": 0,
-    "dropout": 0.0,
-    "eos_token_id": 2,
-    "model_type": "clip_text_model"
-  },
+  "qkv_bias": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
-  "vision_config": {
-    "dropout": 0.0,
-    "model_type": "clip_vision_model"
-  }
+  "transformers_version": "4.38.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a927c47ccbc08e092240e73f6209a329d03b931595f95a6c5a7715a3919cf5c
-size 349863356
+oid sha256:ba8ee0630f38c9e73d3bea8b75ad378c4fd0c5c1a5b58c6a4c170f8aaf12e946
+size 343233204

preprocessor_config.json

@@ -1,27 +1,22 @@
 {
-  "crop_size": {
-    "height": 224,
-    "width": 224
-  },
-  "do_center_crop": true,
-  "do_convert_rgb": true,
   "do_normalize": true,
   "do_rescale": true,
   "do_resize": true,
   "image_mean": [
-    0.48145466,
-    0.4578275,
-    0.40821073
+    0.5,
+    0.5,
+    0.5
   ],
-  "image_processor_type": "CLIPImageProcessor",
+  "image_processor_type": "ViTImageProcessor",
   "image_std": [
-    0.26862954,
-    0.26130258,
-    0.27577711
+    0.5,
+    0.5,
+    0.5
   ],
-  "resample": 3,
+  "resample": 2,
   "rescale_factor": 0.00392156862745098,
   "size": {
-    "shortest_edge": 224
+    "height": 224,
+    "width": 224
   }
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a33aac535eb9f5e368f575fb343655a1b2e93c13844ab491e88bf73edccb6b27
+oid sha256:7a38ed0a85f960927299f85e1092ab6dc9785c56bf33721a23bdba4d9d3c3c5e
 size 4856