rotated_maps

README.md

@@ -0,0 +1,79 @@
+---
+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-v8
+  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-v8
+
+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: 0.8643
+- 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: 1e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 1024
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 22
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Accuracy |
+|:-------------:|:-------:|:----:|:---------------:|:--------:|
+| 0.1574        | 8.3333  | 100  | 0.8765          | 0.875    |
+| 0.1364        | 16.6667 | 200  | 0.8643          | 0.875    |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.5.0+cu121
+- Datasets 3.1.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 22.0,
+    "eval_accuracy": 0.875,
+    "eval_loss": 0.864288330078125,
+    "eval_runtime": 0.133,
+    "eval_samples_per_second": 60.169,
+    "eval_steps_per_second": 7.521,
+    "total_flos": 8.013030801360077e+16,
+    "train_loss": 0.16366353608442075,
+    "train_runtime": 97.5562,
+    "train_samples_per_second": 10.599,
+    "train_steps_per_second": 2.706
+}

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": 22.0,
+    "eval_accuracy": 0.875,
+    "eval_loss": 0.864288330078125,
+    "eval_runtime": 0.133,
+    "eval_samples_per_second": 60.169,
+    "eval_steps_per_second": 7.521
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e20e702b54aeeed692141acb24f7a99c058ad4ce6328b401110a8e2f9237b79
+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/Oct31_15-36-40_e244556ed756/events.out.tfevents.1730389003.e244556ed756.183.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1847b3d5c1b26b2c03217f6d19ccc5537f2f6358c6b43b152266d07912c428f4
+size 11676

runs/Oct31_15-36-40_e244556ed756/events.out.tfevents.1730389108.e244556ed756.183.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c7166de179d2d5057c389ebde77db85de9f79053d1ec2203599adaf09177a6d
+size 411

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 22.0,
+    "total_flos": 8.013030801360077e+16,
+    "train_loss": 0.16366353608442075,
+    "train_runtime": 97.5562,
+    "train_samples_per_second": 10.599,
+    "train_steps_per_second": 2.706
+}

trainer_state.json

@@ -0,0 +1,242 @@
+{
+  "best_metric": 0.864288330078125,
+  "best_model_checkpoint": "vit-base-patch16-224-in21k-rotated-dungeons-v8/checkpoint-200",
+  "epoch": 22.0,
+  "eval_steps": 100,
+  "global_step": 264,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.6725011467933655,
+      "learning_rate": 9.621212121212122e-06,
+      "loss": 0.2014,
+      "step": 10
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 2.3636183738708496,
+      "learning_rate": 9.242424242424244e-06,
+      "loss": 0.2316,
+      "step": 20
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 2.3594517707824707,
+      "learning_rate": 8.863636363636365e-06,
+      "loss": 0.2021,
+      "step": 30
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 2.3623316287994385,
+      "learning_rate": 8.484848484848486e-06,
+      "loss": 0.1999,
+      "step": 40
+    },
+    {
+      "epoch": 4.166666666666667,
+      "grad_norm": 0.8582655191421509,
+      "learning_rate": 8.106060606060606e-06,
+      "loss": 0.1825,
+      "step": 50
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.9432439208030701,
+      "learning_rate": 7.727272727272727e-06,
+      "loss": 0.1832,
+      "step": 60
+    },
+    {
+      "epoch": 5.833333333333333,
+      "grad_norm": 0.9690579175949097,
+      "learning_rate": 7.348484848484849e-06,
+      "loss": 0.1772,
+      "step": 70
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 1.4010443687438965,
+      "learning_rate": 6.969696969696971e-06,
+      "loss": 0.1726,
+      "step": 80
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 0.7616134285926819,
+      "learning_rate": 6.590909090909091e-06,
+      "loss": 0.1767,
+      "step": 90
+    },
+    {
+      "epoch": 8.333333333333334,
+      "grad_norm": 0.641935408115387,
+      "learning_rate": 6.212121212121213e-06,
+      "loss": 0.1574,
+      "step": 100
+    },
+    {
+      "epoch": 8.333333333333334,
+      "eval_accuracy": 0.875,
+      "eval_loss": 0.8765411376953125,
+      "eval_runtime": 0.0757,
+      "eval_samples_per_second": 105.614,
+      "eval_steps_per_second": 13.202,
+      "step": 100
+    },
+    {
+      "epoch": 9.166666666666666,
+      "grad_norm": 0.8502519130706787,
+      "learning_rate": 5.833333333333334e-06,
+      "loss": 0.1655,
+      "step": 110
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.6651738882064819,
+      "learning_rate": 5.4545454545454545e-06,
+      "loss": 0.1611,
+      "step": 120
+    },
+    {
+      "epoch": 10.833333333333334,
+      "grad_norm": 1.1078132390975952,
+      "learning_rate": 5.075757575757576e-06,
+      "loss": 0.1598,
+      "step": 130
+    },
+    {
+      "epoch": 11.666666666666666,
+      "grad_norm": 0.9000115990638733,
+      "learning_rate": 4.696969696969698e-06,
+      "loss": 0.154,
+      "step": 140
+    },
+    {
+      "epoch": 12.5,
+      "grad_norm": 0.6342107057571411,
+      "learning_rate": 4.3181818181818185e-06,
+      "loss": 0.1486,
+      "step": 150
+    },
+    {
+      "epoch": 13.333333333333334,
+      "grad_norm": 0.4974025785923004,
+      "learning_rate": 3.93939393939394e-06,
+      "loss": 0.1547,
+      "step": 160
+    },
+    {
+      "epoch": 14.166666666666666,
+      "grad_norm": 0.6266921162605286,
+      "learning_rate": 3.560606060606061e-06,
+      "loss": 0.1414,
+      "step": 170
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 0.553960382938385,
+      "learning_rate": 3.181818181818182e-06,
+      "loss": 0.1509,
+      "step": 180
+    },
+    {
+      "epoch": 15.833333333333334,
+      "grad_norm": 0.6009966135025024,
+      "learning_rate": 2.803030303030303e-06,
+      "loss": 0.1497,
+      "step": 190
+    },
+    {
+      "epoch": 16.666666666666668,
+      "grad_norm": 0.5110170841217041,
+      "learning_rate": 2.4242424242424244e-06,
+      "loss": 0.1364,
+      "step": 200
+    },
+    {
+      "epoch": 16.666666666666668,
+      "eval_accuracy": 0.875,
+      "eval_loss": 0.864288330078125,
+      "eval_runtime": 0.0706,
+      "eval_samples_per_second": 113.361,
+      "eval_steps_per_second": 14.17,
+      "step": 200
+    },
+    {
+      "epoch": 17.5,
+      "grad_norm": 0.5791155695915222,
+      "learning_rate": 2.0454545454545457e-06,
+      "loss": 0.153,
+      "step": 210
+    },
+    {
+      "epoch": 18.333333333333332,
+      "grad_norm": 0.5752493143081665,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.1413,
+      "step": 220
+    },
+    {
+      "epoch": 19.166666666666668,
+      "grad_norm": 0.4596743881702423,
+      "learning_rate": 1.287878787878788e-06,
+      "loss": 0.1319,
+      "step": 230
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.790753185749054,
+      "learning_rate": 9.090909090909091e-07,
+      "loss": 0.1474,
+      "step": 240
+    },
+    {
+      "epoch": 20.833333333333332,
+      "grad_norm": 0.6762207746505737,
+      "learning_rate": 5.303030303030304e-07,
+      "loss": 0.1368,
+      "step": 250
+    },
+    {
+      "epoch": 21.666666666666668,
+      "grad_norm": 0.559245765209198,
+      "learning_rate": 1.5151515151515152e-07,
+      "loss": 0.1519,
+      "step": 260
+    },
+    {
+      "epoch": 22.0,
+      "step": 264,
+      "total_flos": 8.013030801360077e+16,
+      "train_loss": 0.16366353608442075,
+      "train_runtime": 97.5562,
+      "train_samples_per_second": 10.599,
+      "train_steps_per_second": 2.706
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 264,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 22,
+  "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": 8.013030801360077e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ab0947e02d54eae3369e563133d5cbad906c2699390f0d5be84955a58a089ab
+size 5240