Upload folder using huggingface_hub

README.md

@@ -0,0 +1,22 @@
+---
+base_model:
+- openai/clip-vit-base-patch16
+datasets:
+- ethz/food101
+metrics:
+- accuracy
+---
+
+# Model Card
+
+## Training Details
+
+Adam Optimizer with a constant learning rate 1e-5 for 4000 steps training (batch_size=128).
+Only the vision encoder is fine-tuned.
+
+## Evaluation Results
+
+Test set accuracy:
+
+- pre-trained: 0.8701385855674744
+- fine-tuned: 0.9186534881591797

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "openai/clip-vit-base-patch16",
+  "architectures": [
+    "CLIPVisionModel"
+  ],
+  "attention_dropout": 0.0,
+  "dropout": 0.0,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "image_size": 224,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "model_type": "clip_vision_model",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "projection_dim": 512,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0"
+}

events.out.tfevents.1734027056.amax.1841026.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9428f6bdc1ab5c452cf9e117578ac1aa2b478eac0593718e6e5f11247aefcf7
+size 195958

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a3fd32dec4f45c4dea1a10c96b592c6a4206939ef8c4ffa497c181f3b118db5
+size 343221512