trained on 1371 images from the Met for 10 epochs

***** train metrics *****
epoch = 10.0
train_loss = 0.8552
train_runtime = 1:11:30.94
train_samples_per_second = 3.225
train_steps_per_second = 0.033

config.json

@@ -0,0 +1,22 @@
+{
+  "_name_or_path": "openai/clip-vit-base-patch32",
+  "architectures": [
+    "CLIPModel"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "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": "4.35.0.dev0",
+  "vision_config": {
+    "dropout": 0.0,
+    "model_type": "clip_vision_model"
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b21f784f4b57697ba0c977c2bc9e890ab8c992157fcbc4f9cc573484783fc03
+size 605240770