Juhyang

README.md

@@ -0,0 +1,68 @@
+---
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- 3_class
+- multi_labels
+- generated_from_trainer
+model-index:
+- name: ViT_face
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# ViT_face
+
+This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the face dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2038
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 38   | 0.8817          |
+| No log        | 2.0   | 76   | 0.6110          |
+| No log        | 3.0   | 114  | 0.4243          |
+| No log        | 4.0   | 152  | 0.3180          |
+| No log        | 5.0   | 190  | 0.2811          |
+| No log        | 6.0   | 228  | 0.2286          |
+| No log        | 7.0   | 266  | 0.2133          |
+| No log        | 8.0   | 304  | 0.2082          |
+| No log        | 9.0   | 342  | 0.2050          |
+| No log        | 10.0  | 380  | 0.2038          |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "\u110c\u1169\u110b\u1175",
+    "1": "\u110f\u1161\u1105\u1175\u1102\u1161",
+    "2": "\u1110\u1162\u110b\u1167\u11ab"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "\u110c\u1169\u110b\u1175": "0",
+    "\u110f\u1161\u1105\u1175\u1102\u1161": "1",
+    "\u1110\u1162\u110b\u1167\u11ab": "2"
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44ca1e171cd1f69eb803a5344ac3c9be29242ca916c062678e8bbef3e8dbe19c
+size 343227052

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTFeatureExtractor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

runs/Sep03_02-20-40_c59c53a4c351/events.out.tfevents.1725330072.c59c53a4c351.1141.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d47812b65e4be0f1f0601a6beb1274e7e25901ccf0acee6105fadfc94b7ddea3
+size 8044

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc65e462787003847159b7208d97d08a43f252eb311b14ee3b5f5609993c71a1
+size 5112