Upload folder using huggingface_hub

README.md

@@ -0,0 +1,22 @@
+---
+base_model:
+- openai/clip-vit-large-patch14
+datasets:
+- nateraw/rendered-sst2
+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: 0.6891817450523376
+- fine-tuned: 0.8045030236244202

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "openai/clip-vit-large-patch14",
+  "architectures": [
+    "CLIPVisionModel"
+  ],
+  "attention_dropout": 0.0,
+  "dropout": 0.0,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 1024,
+  "image_size": 224,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "model_type": "clip_vision_model",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 24,
+  "patch_size": 14,
+  "projection_dim": 768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0"
+}

events.out.tfevents.1734023946.amax.82915.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc8548f223702431e8b85b7071fc565bf0fd44f6ee9d45615127b1a1fd7336d7
+size 195958

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ae0c693ec0101bdbce5c4fa332a9c372c3f0cdc39d8f5752f79744d5e56e687
+size 1212766896