Training in progress, epoch 1

config.json

@@ -1,8 +1,13 @@
 {
-  "_name_or_path": "openai/clip-vit-large-patch14",
+  "_name_or_path": "google/vit-base-patch32-224-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": "T - shirt / top",
     "1": "Trouser",
@@ -15,7 +20,9 @@
     "8": "Bag",
     "9": "Ankle boot"
   },
-  "initializer_factor": 1.0,
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "Ankle boot": "9",
     "Bag": "8",
@@ -28,28 +35,14 @@
     "T - shirt / top": "0",
     "Trouser": "1"
   },
-  "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": 32,
   "problem_type": "single_label_classification",
-  "projection_dim": 768,
-  "text_config": {
-    "dropout": 0.0,
-    "hidden_size": 768,
-    "intermediate_size": 3072,
-    "model_type": "clip_text_model",
-    "num_attention_heads": 12,
-    "projection_dim": 768
-  },
+  "qkv_bias": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.40.1",
-  "vision_config": {
-    "dropout": 0.0,
-    "hidden_size": 1024,
-    "intermediate_size": 4096,
-    "model_type": "clip_vision_model",
-    "num_attention_heads": 16,
-    "num_hidden_layers": 24,
-    "patch_size": 14,
-    "projection_dim": 768
-  }
+  "transformers_version": "4.40.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b17376300f470619db67a6d721eb61e1cc5bb9dfa3d74b514bcf431143c8a29
-size 1212808056
+oid sha256:93ff5a3abdc9dc015ada0757a65b1124b6b939020cc92ee1b049376559e3f365
+size 349874904

preprocessor_config.json

@@ -4,41 +4,33 @@
     "do_resize",
     "size",
     "resample",
-    "do_center_crop",
-    "crop_size",
     "do_rescale",
     "rescale_factor",
     "do_normalize",
     "image_mean",
     "image_std",
-    "do_convert_rgb",
     "return_tensors",
     "data_format",
     "input_data_format"
   ],
-  "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
   }
 }

runs/May04_02-07-45_tron53.umiacs.umd.edu/events.out.tfevents.1714802866.tron53.umiacs.umd.edu.3706292.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aca9c64df105daf06060083fc904bb3665a40b0e17cd359921f61e9d1c87134
+size 6079

runs/May04_02-11-43_tron53.umiacs.umd.edu/events.out.tfevents.1714803104.tron53.umiacs.umd.edu.3707341.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:961a00019fbe471a46b64b22bc2a4cf13f9d8083d6f280911b1185c16d7103c8
+size 8795

runs/May04_02-14-37_tron53.umiacs.umd.edu/events.out.tfevents.1714803278.tron53.umiacs.umd.edu.3708970.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ede0c8956da7fb7008bf20da3921a4d75d50c6797f7abb8f8757609e12801482
+size 13760

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:686189be16b394f2cea6dd364d97575f2d95d1c28a54e0f3e8e71a052d6952f8
+oid sha256:04b7afaf73fcc63e9a0b0ecb1626af44e99df729fe8b8fbc6868a361997d6680
 size 5048