End of training

README.md

@@ -0,0 +1,84 @@
+---
+license: apache-2.0
+base_model: google/vit-base-patch16-224
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: UL_base_classification
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: imagefolder
+      type: imagefolder
+      config: default
+      split: validation
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8921161825726142
+---
+
+<!-- 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. -->
+
+# UL_base_classification
+
+This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3125
+- Accuracy: 0.8921
+
+## 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: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 7
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 0.8296        | 0.9756 | 20   | 0.5683          | 0.8230   |
+| 0.4462        | 2.0    | 41   | 0.3949          | 0.8603   |
+| 0.3588        | 2.9756 | 61   | 0.3633          | 0.8575   |
+| 0.3196        | 4.0    | 82   | 0.3247          | 0.8852   |
+| 0.2921        | 4.9756 | 102  | 0.3374          | 0.8728   |
+| 0.2688        | 6.0    | 123  | 0.3125          | 0.8921   |
+| 0.2366        | 6.8293 | 140  | 0.3137          | 0.8866   |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 6.829268292682927,
+    "eval_accuracy": 0.8921161825726142,
+    "eval_loss": 0.3124912977218628,
+    "eval_runtime": 28.6771,
+    "eval_samples_per_second": 25.212,
+    "eval_steps_per_second": 0.802,
+    "total_flos": 1.3849740766444585e+18,
+    "train_loss": 0.4427596058164324,
+    "train_runtime": 1849.9588,
+    "train_samples_per_second": 9.899,
+    "train_steps_per_second": 0.076
+}

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "bedrooms",
+    "1": "exterior",
+    "2": "floorPlans",
+    "3": "interior",
+    "4": "others"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "bedrooms": 0,
+    "exterior": 1,
+    "floorPlans": 2,
+    "interior": 3,
+    "others": 4
+  },
+  "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"
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.829268292682927,
+    "eval_accuracy": 0.8921161825726142,
+    "eval_loss": 0.3124912977218628,
+    "eval_runtime": 28.6771,
+    "eval_samples_per_second": 25.212,
+    "eval_steps_per_second": 0.802
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cfcf2240c8df96c8db1c45765ba0c91c35b180eb30355fec033e10b801fe97f
+size 343233204

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": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

runs/Jun11_09-29-23_c706598b3e1f/events.out.tfevents.1718098183.c706598b3e1f.1099.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61cc4d8868079102a6a3a6873b6fe5f183b4a642deffa18f9020118593ccec55
+size 10445

runs/Jun11_09-29-23_c706598b3e1f/events.out.tfevents.1718100119.c706598b3e1f.1099.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed8b46fc875b3e564b25bf115eeda139794baca4954cddf66085701e6df25693
+size 411

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.829268292682927,
+    "total_flos": 1.3849740766444585e+18,
+    "train_loss": 0.4427596058164324,
+    "train_runtime": 1849.9588,
+    "train_samples_per_second": 9.899,
+    "train_steps_per_second": 0.076
+}

trainer_state.json

@@ -0,0 +1,203 @@
+{
+  "best_metric": 0.8921161825726142,
+  "best_model_checkpoint": "UL_base_classification/checkpoint-123",
+  "epoch": 6.829268292682927,
+  "eval_steps": 500,
+  "global_step": 140,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4878048780487805,
+      "grad_norm": 4.009415149688721,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 1.4657,
+      "step": 10
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 1.9595946073532104,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 0.8296,
+      "step": 20
+    },
+    {
+      "epoch": 0.975609756097561,
+      "eval_accuracy": 0.8229598893499308,
+      "eval_loss": 0.5682700872421265,
+      "eval_runtime": 28.9624,
+      "eval_samples_per_second": 24.963,
+      "eval_steps_per_second": 0.794,
+      "step": 20
+    },
+    {
+      "epoch": 1.4634146341463414,
+      "grad_norm": 1.4578920602798462,
+      "learning_rate": 4.3650793650793655e-05,
+      "loss": 0.5174,
+      "step": 30
+    },
+    {
+      "epoch": 1.951219512195122,
+      "grad_norm": 1.6582454442977905,
+      "learning_rate": 3.968253968253968e-05,
+      "loss": 0.4462,
+      "step": 40
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8603042876901799,
+      "eval_loss": 0.3948992192745209,
+      "eval_runtime": 28.607,
+      "eval_samples_per_second": 25.274,
+      "eval_steps_per_second": 0.804,
+      "step": 41
+    },
+    {
+      "epoch": 2.4390243902439024,
+      "grad_norm": 1.9573261737823486,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 0.3861,
+      "step": 50
+    },
+    {
+      "epoch": 2.926829268292683,
+      "grad_norm": 2.927914619445801,
+      "learning_rate": 3.1746031746031745e-05,
+      "loss": 0.3588,
+      "step": 60
+    },
+    {
+      "epoch": 2.975609756097561,
+      "eval_accuracy": 0.8575380359612724,
+      "eval_loss": 0.3632887601852417,
+      "eval_runtime": 27.4966,
+      "eval_samples_per_second": 26.294,
+      "eval_steps_per_second": 0.836,
+      "step": 61
+    },
+    {
+      "epoch": 3.4146341463414633,
+      "grad_norm": 2.270343065261841,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 0.2995,
+      "step": 70
+    },
+    {
+      "epoch": 3.902439024390244,
+      "grad_norm": 2.323387622833252,
+      "learning_rate": 2.380952380952381e-05,
+      "loss": 0.3196,
+      "step": 80
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8852005532503457,
+      "eval_loss": 0.3247418701648712,
+      "eval_runtime": 28.061,
+      "eval_samples_per_second": 25.765,
+      "eval_steps_per_second": 0.82,
+      "step": 82
+    },
+    {
+      "epoch": 4.390243902439025,
+      "grad_norm": 1.6208417415618896,
+      "learning_rate": 1.984126984126984e-05,
+      "loss": 0.2878,
+      "step": 90
+    },
+    {
+      "epoch": 4.878048780487805,
+      "grad_norm": 1.3482733964920044,
+      "learning_rate": 1.5873015873015872e-05,
+      "loss": 0.2921,
+      "step": 100
+    },
+    {
+      "epoch": 4.975609756097561,
+      "eval_accuracy": 0.8727524204702628,
+      "eval_loss": 0.3373877704143524,
+      "eval_runtime": 28.0046,
+      "eval_samples_per_second": 25.817,
+      "eval_steps_per_second": 0.821,
+      "step": 102
+    },
+    {
+      "epoch": 5.365853658536586,
+      "grad_norm": 1.1717610359191895,
+      "learning_rate": 1.1904761904761905e-05,
+      "loss": 0.2319,
+      "step": 110
+    },
+    {
+      "epoch": 5.853658536585366,
+      "grad_norm": 1.3873180150985718,
+      "learning_rate": 7.936507936507936e-06,
+      "loss": 0.2688,
+      "step": 120
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8921161825726142,
+      "eval_loss": 0.3124912977218628,
+      "eval_runtime": 28.2402,
+      "eval_samples_per_second": 25.602,
+      "eval_steps_per_second": 0.814,
+      "step": 123
+    },
+    {
+      "epoch": 6.341463414634147,
+      "grad_norm": 1.7034335136413574,
+      "learning_rate": 3.968253968253968e-06,
+      "loss": 0.2583,
+      "step": 130
+    },
+    {
+      "epoch": 6.829268292682927,
+      "grad_norm": 1.5103542804718018,
+      "learning_rate": 0.0,
+      "loss": 0.2366,
+      "step": 140
+    },
+    {
+      "epoch": 6.829268292682927,
+      "eval_accuracy": 0.8865836791147994,
+      "eval_loss": 0.3137405514717102,
+      "eval_runtime": 28.632,
+      "eval_samples_per_second": 25.251,
+      "eval_steps_per_second": 0.803,
+      "step": 140
+    },
+    {
+      "epoch": 6.829268292682927,
+      "step": 140,
+      "total_flos": 1.3849740766444585e+18,
+      "train_loss": 0.4427596058164324,
+      "train_runtime": 1849.9588,
+      "train_samples_per_second": 9.899,
+      "train_steps_per_second": 0.076
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 140,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "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": 1.3849740766444585e+18,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49fcc8be95a7679d08cb5ed8d357817d085a172e20e8623995fcb4f118f05a6d
+size 5112