Training in progress, epoch 1

config.json

@@ -1,13 +1,8 @@
 {
-  "_name_or_path": "google/vit-huge-patch14-224-in21k",
+  "_name_or_path": "openai/clip-vit-large-patch14",
   "architectures": [
-    "ViTForImageClassification"
+    "CLIPForImageClassification"
   ],
-  "attention_probs_dropout_prob": 0.0,
-  "encoder_stride": 16,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.0,
-  "hidden_size": 1280,
   "id2label": {
     "0": "T - shirt / top",
     "1": "Trouser",
@@ -20,9 +15,7 @@
     "8": "Bag",
     "9": "Ankle boot"
   },
-  "image_size": 224,
-  "initializer_range": 0.02,
-  "intermediate_size": 5120,
+  "initializer_factor": 1.0,
   "label2id": {
     "Ankle boot": "9",
     "Bag": "8",
@@ -35,14 +28,28 @@
     "T - shirt / top": "0",
     "Trouser": "1"
   },
-  "layer_norm_eps": 1e-12,
-  "model_type": "vit",
-  "num_attention_heads": 16,
-  "num_channels": 3,
-  "num_hidden_layers": 32,
-  "patch_size": 14,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
   "problem_type": "single_label_classification",
-  "qkv_bias": true,
+  "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
+  },
   "torch_dtype": "float32",
-  "transformers_version": "4.40.1"
+  "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
+  }
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba03e37f14b905521bd0492ec29cc1cc4c5f68a441e08575c43823990eed48d8
-size 2523172784
+oid sha256:4b17376300f470619db67a6d721eb61e1cc5bb9dfa3d74b514bcf431143c8a29
+size 1212808056

preprocessor_config.json

@@ -4,33 +4,41 @@
     "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": [
-    0.5,
-    0.5,
-    0.5
+    0.48145466,
+    0.4578275,
+    0.40821073
   ],
-  "image_processor_type": "ViTImageProcessor",
+  "image_processor_type": "CLIPImageProcessor",
   "image_std": [
-    0.5,
-    0.5,
-    0.5
+    0.26862954,
+    0.26130258,
+    0.27577711
   ],
-  "resample": 2,
+  "resample": 3,
   "rescale_factor": 0.00392156862745098,
   "size": {
-    "height": 224,
-    "width": 224
+    "shortest_edge": 224
   }
 }

runs/May04_00-26-56_tron60.umiacs.umd.edu/events.out.tfevents.1714796818.tron60.umiacs.umd.edu.188383.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b41e905342b4a52f7a25128670d3efc797ca080c68db2b1f9bfaae1f9fcf41be
+size 13675

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f8793ffc32dbae6f2b33dad465b4561a1516d90336345731faae32e44945f9e
+oid sha256:686189be16b394f2cea6dd364d97575f2d95d1c28a54e0f3e8e71a052d6952f8
 size 5048