Training in progress, epoch 0

config.json

@@ -0,0 +1,88 @@
+{
+  "_name_or_path": "openai/clip-vit-large-patch14-336",
+  "architectures": [
+    "CLIPForImageClassification"
+  ],
+  "id2label": {
+    "0": "A",
+    "1": "B",
+    "2": "C",
+    "3": "D",
+    "4": "E",
+    "5": "F",
+    "6": "G",
+    "7": "H",
+    "8": "I",
+    "9": "J",
+    "10": "K",
+    "11": "L",
+    "12": "M",
+    "13": "N",
+    "14": "O",
+    "15": "P",
+    "16": "Q",
+    "17": "R",
+    "18": "S",
+    "19": "T",
+    "20": "U",
+    "21": "V",
+    "22": "W",
+    "23": "X",
+    "24": "Y",
+    "25": "Z"
+  },
+  "initializer_factor": 1.0,
+  "label2id": {
+    "A": 0,
+    "B": 1,
+    "C": 2,
+    "D": 3,
+    "E": 4,
+    "F": 5,
+    "G": 6,
+    "H": 7,
+    "I": 8,
+    "J": 9,
+    "K": 10,
+    "L": 11,
+    "M": 12,
+    "N": 13,
+    "O": 14,
+    "P": 15,
+    "Q": 16,
+    "R": 17,
+    "S": 18,
+    "T": 19,
+    "U": 20,
+    "V": 21,
+    "W": 22,
+    "X": 23,
+    "Y": 24,
+    "Z": 25
+  },
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "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
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "vision_config": {
+    "dropout": 0.0,
+    "hidden_size": 1024,
+    "image_size": 336,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c48e33a100e65665733b23f5787f86e6312c583d40c4b0d498e70a3a808b5b7
+size 1214184376

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "crop_size": {
+    "height": 336,
+    "width": 336
+  },
+  "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
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 336
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2d0fde872d8f684517b334c32434f429de6731f29aa55012d2e89b21c67e5ee
+size 5304