rotated_maps

README.md

@@ -0,0 +1,78 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- image-classification
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: vit-base-patch16-224-in21k-rotated-dungeons-v4
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: rotated_maps
+      type: imagefolder
+      config: default
+      split: validation
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.875
+---
+
+<!-- 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-patch16-224-in21k-rotated-dungeons-v4
+
+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 rotated_maps dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5276
+- Accuracy: 0.875
+
+## 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: 5
+- eval_batch_size: 8
+- seed: 1024
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 15
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.028         | 12.5  | 100  | 0.5276          | 0.875    |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.5.0+cu121
+- Datasets 3.0.2
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 15.0,
+    "eval_accuracy": 0.875,
+    "eval_loss": 0.5275640487670898,
+    "eval_runtime": 0.0981,
+    "eval_samples_per_second": 81.548,
+    "eval_steps_per_second": 10.194,
+    "total_flos": 4.64972773773312e+16,
+    "train_loss": 0.05409030864636103,
+    "train_runtime": 24.6133,
+    "train_samples_per_second": 24.377,
+    "train_steps_per_second": 4.875
+}

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": "five",
+    "1": "four",
+    "2": "one",
+    "3": "three",
+    "4": "twelve",
+    "5": "two",
+    "6": "zero"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "five": "0",
+    "four": "1",
+    "one": "2",
+    "three": "3",
+    "twelve": "4",
+    "two": "5",
+    "zero": "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": "4.44.2"
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 15.0,
+    "eval_accuracy": 0.875,
+    "eval_loss": 0.5275640487670898,
+    "eval_runtime": 0.0981,
+    "eval_samples_per_second": 81.548,
+    "eval_steps_per_second": 10.194
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb0cf0f495927d34227664f8d251a66c6bdc09c1fc0811c8ebb6bcdedf35a59b
+size 343239356

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

runs/Oct29_20-27-24_3e04bab4dd1f/events.out.tfevents.1730233649.3e04bab4dd1f.943.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b6ae88845330efe40182f660a351f6278e53c5494af6281ab5b276521564255
+size 8394

runs/Oct29_20-27-24_3e04bab4dd1f/events.out.tfevents.1730233675.3e04bab4dd1f.943.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8583364743c4384c1950bdcaa55fbfa703456a744504f2d5b9ef49f5896a79b6
+size 405

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 15.0,
+    "total_flos": 4.64972773773312e+16,
+    "train_loss": 0.05409030864636103,
+    "train_runtime": 24.6133,
+    "train_samples_per_second": 24.377,
+    "train_steps_per_second": 4.875
+}

trainer_state.json

@@ -0,0 +1,135 @@
+{
+  "best_metric": 0.5275640487670898,
+  "best_model_checkpoint": "vit-base-patch16-224-in21k-rotated-dungeons-v4/checkpoint-100",
+  "epoch": 15.0,
+  "eval_steps": 100,
+  "global_step": 120,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.5645539164543152,
+      "learning_rate": 0.00018333333333333334,
+      "loss": 0.1955,
+      "step": 10
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.22394521534442902,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 0.0944,
+      "step": 20
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 0.37107622623443604,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.0686,
+      "step": 30
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.1673012524843216,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.0459,
+      "step": 40
+    },
+    {
+      "epoch": 6.25,
+      "grad_norm": 0.12259427458047867,
+      "learning_rate": 0.00011666666666666668,
+      "loss": 0.042,
+      "step": 50
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 0.1604679673910141,
+      "learning_rate": 0.0001,
+      "loss": 0.0327,
+      "step": 60
+    },
+    {
+      "epoch": 8.75,
+      "grad_norm": 0.121036596596241,
+      "learning_rate": 8.333333333333334e-05,
+      "loss": 0.0336,
+      "step": 70
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.12557414174079895,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.0295,
+      "step": 80
+    },
+    {
+      "epoch": 11.25,
+      "grad_norm": 0.10457774996757507,
+      "learning_rate": 5e-05,
+      "loss": 0.0266,
+      "step": 90
+    },
+    {
+      "epoch": 12.5,
+      "grad_norm": 0.10654424130916595,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.028,
+      "step": 100
+    },
+    {
+      "epoch": 12.5,
+      "eval_accuracy": 0.875,
+      "eval_loss": 0.5275640487670898,
+      "eval_runtime": 0.0716,
+      "eval_samples_per_second": 111.698,
+      "eval_steps_per_second": 13.962,
+      "step": 100
+    },
+    {
+      "epoch": 13.75,
+      "grad_norm": 0.17629727721214294,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.028,
+      "step": 110
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 0.14613842964172363,
+      "learning_rate": 0.0,
+      "loss": 0.0244,
+      "step": 120
+    },
+    {
+      "epoch": 15.0,
+      "step": 120,
+      "total_flos": 4.64972773773312e+16,
+      "train_loss": 0.05409030864636103,
+      "train_runtime": 24.6133,
+      "train_samples_per_second": 24.377,
+      "train_steps_per_second": 4.875
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 120,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 15,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.64972773773312e+16,
+  "train_batch_size": 5,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8837f7d15b1a74cb7e26c6402883f6bfb19863add42fb26f90acd5371813d8ff
+size 5240