Upload folder using huggingface_hub

checkpoint-141/config.json

@@ -0,0 +1,58 @@
+{
+  "_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": "Blazer",
+    "1": "Celana_Panjang",
+    "2": "Celana_Pendek",
+    "3": "Gaun",
+    "4": "Hoodie",
+    "5": "Jaket",
+    "6": "Jaket_Denim",
+    "7": "Jaket_Olahraga",
+    "8": "Jeans",
+    "9": "Kaos",
+    "10": "Kemeja",
+    "11": "Mantel",
+    "12": "Polo",
+    "13": "Rok",
+    "14": "Sweter"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Blazer": 0,
+    "Celana_Panjang": 1,
+    "Celana_Pendek": 2,
+    "Gaun": 3,
+    "Hoodie": 4,
+    "Jaket": 5,
+    "Jaket_Denim": 6,
+    "Jaket_Olahraga": 7,
+    "Jeans": 8,
+    "Kaos": 9,
+    "Kemeja": 10,
+    "Mantel": 11,
+    "Polo": 12,
+    "Rok": 13,
+    "Sweter": 14
+  },
+  "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": "4.48.3"
+}

checkpoint-141/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:054400fdfece91390632c9ebde9ad44947fa8682254f29784525e33c868d0fc6
+size 343263964

checkpoint-141/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89d341c0dfece1d5df61c407522d05a1b0daba2c9798aa0d6ae820c5e1e332a5
+size 686648762

checkpoint-141/preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

checkpoint-141/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceb90df3ea8cef16328c39fa75d7f3bf43366a0675c56f951b7e21ff3a8717df
+size 14244

checkpoint-141/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b21759f4a5a2362267c82dd5c799adb6fb491ec501b2e7cf329d797122216433
+size 1064

checkpoint-141/trainer_state.json

@@ -0,0 +1,43 @@
+{
+  "best_metric": 2.6991894245147705,
+  "best_model_checkpoint": "clothes_image_detection/checkpoint-141",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 141,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.08933333333333333,
+      "eval_loss": 2.6991894245147705,
+      "eval_model_preparation_time": 0.0037,
+      "eval_runtime": 60.2612,
+      "eval_samples_per_second": 49.783,
+      "eval_steps_per_second": 6.223,
+      "step": 141
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 141,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.48754583632896e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-141/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a50716a5f1549811f8e769d974bd756fae94eff983c2a6fdcc1629948d4af4b5
+size 5304

config.json

@@ -0,0 +1,58 @@
+{
+  "_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": "Blazer",
+    "1": "Celana_Panjang",
+    "2": "Celana_Pendek",
+    "3": "Gaun",
+    "4": "Hoodie",
+    "5": "Jaket",
+    "6": "Jaket_Denim",
+    "7": "Jaket_Olahraga",
+    "8": "Jeans",
+    "9": "Kaos",
+    "10": "Kemeja",
+    "11": "Mantel",
+    "12": "Polo",
+    "13": "Rok",
+    "14": "Sweter"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Blazer": 0,
+    "Celana_Panjang": 1,
+    "Celana_Pendek": 2,
+    "Gaun": 3,
+    "Hoodie": 4,
+    "Jaket": 5,
+    "Jaket_Denim": 6,
+    "Jaket_Olahraga": 7,
+    "Jeans": 8,
+    "Kaos": 9,
+    "Kemeja": 10,
+    "Mantel": 11,
+    "Polo": 12,
+    "Rok": 13,
+    "Sweter": 14
+  },
+  "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": "4.48.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:054400fdfece91390632c9ebde9ad44947fa8682254f29784525e33c868d0fc6
+size 343263964

preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a50716a5f1549811f8e769d974bd756fae94eff983c2a6fdcc1629948d4af4b5
+size 5304