Training in progress, epoch 0

config.json

@@ -1,23 +1,7 @@
 {
-  "_name_or_path": "microsoft/resnet-50",
+  "_name_or_path": "openai/clip-vit-base-patch32",
   "architectures": [
-    "ResNetForImageClassification"
-  ],
-  "depths": [
-    3,
-    4,
-    6,
-    3
-  ],
-  "downsample_in_bottleneck": false,
-  "downsample_in_first_stage": false,
-  "embedding_size": 64,
-  "hidden_act": "relu",
-  "hidden_sizes": [
-    256,
-    512,
-    1024,
-    2048
+    "CLIPForImageClassification"
   ],
   "id2label": {
     "0": "1",
@@ -123,6 +107,7 @@
     "98": "96",
     "99": "97"
   },
+  "initializer_factor": 1.0,
   "label2id": {
     "1": "0",
     "10": "1",
@@ -227,23 +212,20 @@
     "98": "100",
     "99": "101"
   },
-  "layer_type": "bottleneck",
-  "model_type": "resnet",
-  "num_channels": 3,
-  "out_features": [
-    "stage4"
-  ],
-  "out_indices": [
-    4
-  ],
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
   "problem_type": "single_label_classification",
-  "stage_names": [
-    "stem",
-    "stage1",
-    "stage2",
-    "stage3",
-    "stage4"
-  ],
+  "projection_dim": 512,
+  "text_config": {
+    "bos_token_id": 0,
+    "dropout": 0.0,
+    "eos_token_id": 2,
+    "model_type": "clip_text_model"
+  },
   "torch_dtype": "float32",
-  "transformers_version": "4.39.3"
+  "transformers_version": "4.39.3",
+  "vision_config": {
+    "dropout": 0.0,
+    "model_type": "clip_vision_model"
+  }
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b0175ebf100ecd7de16e9c1d1c86fbba50a61088aaebce3133cf66a059de2f8
-size 95122680
+oid sha256:565a010ab321d34925d7f1bd22accf4d24f6f5172e839744a2391c123c98ea4a
+size 350161736

preprocessor_config.json

@@ -3,31 +3,38 @@
     "images",
     "do_resize",
     "size",
-    "crop_pct",
     "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_pct": 0.875,
+  "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": [
-    0.485,
-    0.456,
-    0.406
+    0.48145466,
+    0.4578275,
+    0.40821073
   ],
-  "image_processor_type": "ConvNextImageProcessor",
+  "image_processor_type": "CLIPImageProcessor",
   "image_std": [
-    0.229,
-    0.224,
-    0.225
+    0.26862954,
+    0.26130258,
+    0.27577711
   ],
   "resample": 3,
   "rescale_factor": 0.00392156862745098,

runs/Apr13_22-50-57_25bc6b3f9b19/events.out.tfevents.1713048658.25bc6b3f9b19.4236.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0388f9571627f93eb0cd488d9a0ed174f2d12d1018c01db63d7cbda4487a9689
-size 23219
+oid sha256:523598959927eac70f5c4366bb7938b9e763e968b0a0529a241f21b5bff2b502
+size 24274

runs/Apr13_22-59-55_25bc6b3f9b19/events.out.tfevents.1713049196.25bc6b3f9b19.4236.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:279492ecee0d4647a0eb46421fb3496f0248f68ca880409daf034353e70625fa
+size 9880

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30d598f5643b23089d495fc7e12117109d83de6142a0c71c0953e35ab5fd6d1d
+oid sha256:3bac924eb8937ac9a2673b33459d06c96478405d4c996111924d33da39f86779
 size 4920