End of training

README.md

@@ -0,0 +1,72 @@
+---
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: image-categories-2023-08-28-08-43-770487
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: imagefolder
+      type: imagefolder
+      config: default
+      split: train
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6764705882352942
+---
+
+<!-- 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. -->
+
+# image-categories-2023-08-28-08-43-770487
+
+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 imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9626
+- Accuracy: 0.6765
+
+## 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: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.32.0
+- Pytorch 2.0.1
+- Datasets 2.14.4
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.6764705882352942,
+    "eval_loss": 0.9626137018203735,
+    "eval_runtime": 2.8865,
+    "eval_samples_per_second": 47.116,
+    "eval_steps_per_second": 5.889,
+    "train_loss": 1.1862452450920553,
+    "train_runtime": 62.578,
+    "train_samples_per_second": 17.258,
+    "train_steps_per_second": 1.087
+}

config.json

@@ -0,0 +1,42 @@
+{
+  "_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": "architectural",
+    "1": "blurry",
+    "2": "fashion",
+    "3": "graphic_design",
+    "4": "illustration_and_sketches",
+    "5": "movie",
+    "6": "photography"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "architectural": 0,
+    "blurry": 1,
+    "fashion": 2,
+    "graphic_design": 3,
+    "illustration_and_sketches": 4,
+    "movie": 5,
+    "photography": 6
+  },
+  "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": "4.32.0"
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.6764705882352942,
+    "eval_loss": 0.9626137018203735,
+    "eval_runtime": 2.8865,
+    "eval_samples_per_second": 47.116,
+    "eval_steps_per_second": 5.889
+}

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
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a79739603e799a0a1b3013b1b2dd8024027baaea90de63b4ff0696d17e21093f
+size 343281325

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.1862452450920553,
+    "train_runtime": 62.578,
+    "train_samples_per_second": 17.258,
+    "train_steps_per_second": 1.087
+}

trainer_state.json

@@ -0,0 +1,64 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 100,
+  "global_step": 68,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00017058823529411766,
+      "loss": 1.7833,
+      "step": 10
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0001411764705882353,
+      "loss": 1.4406,
+      "step": 20
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00011176470588235294,
+      "loss": 1.1285,
+      "step": 30
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.23529411764706e-05,
+      "loss": 1.0222,
+      "step": 40
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 5.294117647058824e-05,
+      "loss": 0.9368,
+      "step": 50
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2.3529411764705884e-05,
+      "loss": 0.9278,
+      "step": 60
+    },
+    {
+      "epoch": 1.0,
+      "step": 68,
+      "total_flos": 8.369509927919616e+16,
+      "train_loss": 1.1862452450920553,
+      "train_runtime": 62.578,
+      "train_samples_per_second": 17.258,
+      "train_steps_per_second": 1.087
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 68,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 8.369509927919616e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:955050fdcb5268bef141c4ab89eed7007a75ba6fc074977417042bd7e25bbf4e
+size 4091