YangJunyeong

README.md

@@ -0,0 +1,64 @@
+---
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- image-classification
+- ViT
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: vit-base-beans-demo-v5
+  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-base-beans-demo-v5
+
+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 beans dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1306
+- Accuracy: 0.9531
+
+## 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: 0.0002
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 0.0504        | 1.5385 | 100  | 0.1128          | 0.9624   |
+| 0.0308        | 3.0769 | 200  | 0.0529          | 0.9774   |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.953125,
+    "eval_loss": 0.13057941198349,
+    "eval_runtime": 2.377,
+    "eval_samples_per_second": 53.85,
+    "eval_steps_per_second": 6.731,
+    "total_flos": 3.205097416476426e+17,
+    "train_loss": 0.11719392985105515,
+    "train_runtime": 105.1308,
+    "train_samples_per_second": 39.341,
+    "train_steps_per_second": 2.473
+}

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": "angular_leaf_spot",
+    "1": "bean_rust",
+    "2": "healthy"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "angular_leaf_spot": "0",
+    "bean_rust": "1",
+    "healthy": "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": "4.41.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:974f07c1d752e5dcc504613647126811d1972078c2bdc49e78d5bc7d5b119c00
+size 343227052

preprocessor_config.json

@@ -0,0 +1,36 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "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/Jul08_06-49-41_3b4fce3a0fe7/events.out.tfevents.1720422799.3b4fce3a0fe7.184.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6be27574343aaf1141e11965ada5c0e97985e3e29c01ec28361c9b03897f7db2
+size 11323

runs/Jul08_06-49-41_3b4fce3a0fe7/events.out.tfevents.1720423051.3b4fce3a0fe7.184.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c33d6ef02e09d9bc5ee6313341c3b0dd2f4ea6dfa7e10444e78fd031fa91b333
+size 411

test_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.953125,
+    "eval_loss": 0.13057941198349,
+    "eval_runtime": 2.377,
+    "eval_samples_per_second": 53.85,
+    "eval_steps_per_second": 6.731
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "total_flos": 3.205097416476426e+17,
+    "train_loss": 0.11719392985105515,
+    "train_runtime": 105.1308,
+    "train_samples_per_second": 39.341,
+    "train_steps_per_second": 2.473
+}

trainer_state.json

@@ -0,0 +1,242 @@
+{
+  "best_metric": 0.0528901182115078,
+  "best_model_checkpoint": "./vit-base-beans-demo-v5/checkpoint-200",
+  "epoch": 4.0,
+  "eval_steps": 100,
+  "global_step": 260,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 1.5694985389709473,
+      "learning_rate": 0.00019230769230769233,
+      "loss": 0.779,
+      "step": 10
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 3.1738662719726562,
+      "learning_rate": 0.00018461538461538463,
+      "loss": 0.3121,
+      "step": 20
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 0.6277250051498413,
+      "learning_rate": 0.00017692307692307693,
+      "loss": 0.2458,
+      "step": 30
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 1.249167799949646,
+      "learning_rate": 0.00016923076923076923,
+      "loss": 0.2304,
+      "step": 40
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 0.7504239082336426,
+      "learning_rate": 0.00016153846153846155,
+      "loss": 0.1661,
+      "step": 50
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 1.7937676906585693,
+      "learning_rate": 0.00015384615384615385,
+      "loss": 0.2717,
+      "step": 60
+    },
+    {
+      "epoch": 1.0769230769230769,
+      "grad_norm": 2.10583758354187,
+      "learning_rate": 0.00014615384615384615,
+      "loss": 0.1335,
+      "step": 70
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 0.16493375599384308,
+      "learning_rate": 0.00013846153846153847,
+      "loss": 0.1085,
+      "step": 80
+    },
+    {
+      "epoch": 1.3846153846153846,
+      "grad_norm": 3.5142745971679688,
+      "learning_rate": 0.00013076923076923077,
+      "loss": 0.0776,
+      "step": 90
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 7.79476261138916,
+      "learning_rate": 0.0001230769230769231,
+      "loss": 0.0504,
+      "step": 100
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "eval_accuracy": 0.9624060150375939,
+      "eval_loss": 0.11275270581245422,
+      "eval_runtime": 1.2651,
+      "eval_samples_per_second": 105.131,
+      "eval_steps_per_second": 13.438,
+      "step": 100
+    },
+    {
+      "epoch": 1.6923076923076923,
+      "grad_norm": 1.4835689067840576,
+      "learning_rate": 0.00011538461538461538,
+      "loss": 0.0954,
+      "step": 110
+    },
+    {
+      "epoch": 1.8461538461538463,
+      "grad_norm": 0.34010475873947144,
+      "learning_rate": 0.0001076923076923077,
+      "loss": 0.1372,
+      "step": 120
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.2076033502817154,
+      "learning_rate": 0.0001,
+      "loss": 0.0853,
+      "step": 130
+    },
+    {
+      "epoch": 2.1538461538461537,
+      "grad_norm": 0.09932549297809601,
+      "learning_rate": 9.230769230769232e-05,
+      "loss": 0.0269,
+      "step": 140
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 0.1113138496875763,
+      "learning_rate": 8.461538461538461e-05,
+      "loss": 0.0717,
+      "step": 150
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 0.4321606755256653,
+      "learning_rate": 7.692307692307693e-05,
+      "loss": 0.0429,
+      "step": 160
+    },
+    {
+      "epoch": 2.6153846153846154,
+      "grad_norm": 0.18629103899002075,
+      "learning_rate": 6.923076923076924e-05,
+      "loss": 0.0227,
+      "step": 170
+    },
+    {
+      "epoch": 2.769230769230769,
+      "grad_norm": 0.070466049015522,
+      "learning_rate": 6.153846153846155e-05,
+      "loss": 0.0465,
+      "step": 180
+    },
+    {
+      "epoch": 2.9230769230769234,
+      "grad_norm": 1.3304802179336548,
+      "learning_rate": 5.384615384615385e-05,
+      "loss": 0.0408,
+      "step": 190
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 0.06198474392294884,
+      "learning_rate": 4.615384615384616e-05,
+      "loss": 0.0308,
+      "step": 200
+    },
+    {
+      "epoch": 3.076923076923077,
+      "eval_accuracy": 0.9774436090225563,
+      "eval_loss": 0.0528901182115078,
+      "eval_runtime": 1.8145,
+      "eval_samples_per_second": 73.297,
+      "eval_steps_per_second": 9.369,
+      "step": 200
+    },
+    {
+      "epoch": 3.230769230769231,
+      "grad_norm": 0.08140137046575546,
+      "learning_rate": 3.846153846153846e-05,
+      "loss": 0.0121,
+      "step": 210
+    },
+    {
+      "epoch": 3.3846153846153846,
+      "grad_norm": 0.05991177260875702,
+      "learning_rate": 3.0769230769230774e-05,
+      "loss": 0.0117,
+      "step": 220
+    },
+    {
+      "epoch": 3.5384615384615383,
+      "grad_norm": 0.06039084494113922,
+      "learning_rate": 2.307692307692308e-05,
+      "loss": 0.0114,
+      "step": 230
+    },
+    {
+      "epoch": 3.6923076923076925,
+      "grad_norm": 0.05764195695519447,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 0.0118,
+      "step": 240
+    },
+    {
+      "epoch": 3.8461538461538463,
+      "grad_norm": 0.05695033073425293,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 0.011,
+      "step": 250
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.05573964864015579,
+      "learning_rate": 0.0,
+      "loss": 0.0138,
+      "step": 260
+    },
+    {
+      "epoch": 4.0,
+      "step": 260,
+      "total_flos": 3.205097416476426e+17,
+      "train_loss": 0.11719392985105515,
+      "train_runtime": 105.1308,
+      "train_samples_per_second": 39.341,
+      "train_steps_per_second": 2.473
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 260,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.205097416476426e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ee948b80e564efb0db1f67f01be048dbd8dff338c6399536d031bf60760218f
+size 5112