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-v3
+  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: 1.0
+---
+
+<!-- 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-v3
+
+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: 0.1515
+- Accuracy: 1.0
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.0386        | 12.5  | 100  | 0.1515          | 1.0      |
+
+
+### 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": 1.0,
+    "eval_loss": 0.1515045166015625,
+    "eval_runtime": 0.092,
+    "eval_samples_per_second": 76.101,
+    "eval_steps_per_second": 10.872,
+    "total_flos": 4.417241350846464e+16,
+    "train_loss": 0.08117741694053014,
+    "train_runtime": 27.1137,
+    "train_samples_per_second": 21.023,
+    "train_steps_per_second": 4.426
+}

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": 1.0,
+    "eval_loss": 0.1515045166015625,
+    "eval_runtime": 0.092,
+    "eval_samples_per_second": 76.101,
+    "eval_steps_per_second": 10.872
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec300bee5b7dde99c4801ee26ecb64e50738f69095e1b8d86fbc34f204f96153
+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/Oct28_19-45-14_5604b9ecc1a6/events.out.tfevents.1730144718.5604b9ecc1a6.1607.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e3eed267378d5ccf2aed36a3c85733a57be652ffcfa6d06468b658a796f9e8c
+size 8394

runs/Oct28_19-45-14_5604b9ecc1a6/events.out.tfevents.1730144746.5604b9ecc1a6.1607.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ab61383cde6ea7b2c066b2425bc9feee57f8d1253120c36c32c3f4423eecd18
+size 405

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 15.0,
+    "total_flos": 4.417241350846464e+16,
+    "train_loss": 0.08117741694053014,
+    "train_runtime": 27.1137,
+    "train_samples_per_second": 21.023,
+    "train_steps_per_second": 4.426
+}

trainer_state.json

@@ -0,0 +1,135 @@
+{
+  "best_metric": 0.1515045166015625,
+  "best_model_checkpoint": "vit-base-patch16-224-in21k-rotated-dungeons-v3/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": 0.588030219078064,
+      "learning_rate": 0.00018333333333333334,
+      "loss": 0.2001,
+      "step": 10
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.40187984704971313,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 0.2121,
+      "step": 20
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 0.26918885111808777,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.1179,
+      "step": 30
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.2864986062049866,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.0755,
+      "step": 40
+    },
+    {
+      "epoch": 6.25,
+      "grad_norm": 0.20267005264759064,
+      "learning_rate": 0.00011666666666666668,
+      "loss": 0.0641,
+      "step": 50
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 0.24064351618289948,
+      "learning_rate": 0.0001,
+      "loss": 0.0523,
+      "step": 60
+    },
+    {
+      "epoch": 8.75,
+      "grad_norm": 0.15450333058834076,
+      "learning_rate": 8.333333333333334e-05,
+      "loss": 0.0487,
+      "step": 70
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.3064187467098236,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.0447,
+      "step": 80
+    },
+    {
+      "epoch": 11.25,
+      "grad_norm": 0.23561660945415497,
+      "learning_rate": 5e-05,
+      "loss": 0.043,
+      "step": 90
+    },
+    {
+      "epoch": 12.5,
+      "grad_norm": 0.19291207194328308,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.0386,
+      "step": 100
+    },
+    {
+      "epoch": 12.5,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.1515045166015625,
+      "eval_runtime": 0.0635,
+      "eval_samples_per_second": 110.175,
+      "eval_steps_per_second": 15.739,
+      "step": 100
+    },
+    {
+      "epoch": 13.75,
+      "grad_norm": 0.14135047793388367,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.0402,
+      "step": 110
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 0.2867968678474426,
+      "learning_rate": 0.0,
+      "loss": 0.037,
+      "step": 120
+    },
+    {
+      "epoch": 15.0,
+      "step": 120,
+      "total_flos": 4.417241350846464e+16,
+      "train_loss": 0.08117741694053014,
+      "train_runtime": 27.1137,
+      "train_samples_per_second": 21.023,
+      "train_steps_per_second": 4.426
+    }
+  ],
+  "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": 4.417241350846464e+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:c92f29ff6847d0e143af11ce92e7c695b999cab35edef2863bd027c51ded0a06
+size 5240