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-v14
+  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: 0.75
+---
+
+<!-- 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-v14
+
+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: 1.3604
+- Accuracy: 0.75
+
+## 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 |
+|:-------------:|:-------:|:----:|:---------------:|:--------:|
+| 0.9953        | 8.3333  | 100  | 1.5601          | 0.5      |
+| 0.6415        | 16.6667 | 200  | 1.3604          | 0.75     |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.5.0+cu121
+- Datasets 3.1.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 22.0,
+    "total_flos": 8.013030801360077e+16,
+    "train_loss": 0.9863168768810503,
+    "train_runtime": 53.2305,
+    "train_samples_per_second": 19.425,
+    "train_steps_per_second": 4.96
+}

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"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39956a39af56e4ff70710743e1a8225379d551898420c5983f3cf936b91758b5
+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/Nov03_12-27-29_ade8aeba0fd2/events.out.tfevents.1730636863.ade8aeba0fd2.415.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12b658059a3ca1a351740f29a7b10c7f2fb67fa1bbdde6a14336bb1000002b6e
+size 11585

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 22.0,
+    "total_flos": 8.013030801360077e+16,
+    "train_loss": 0.9863168768810503,
+    "train_runtime": 53.2305,
+    "train_samples_per_second": 19.425,
+    "train_steps_per_second": 4.96
+}

trainer_state.json

@@ -0,0 +1,242 @@
+{
+  "best_metric": 1.36041259765625,
+  "best_model_checkpoint": "vit-base-patch16-224-in21k-rotated-dungeons-v14/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": 3.3986947536468506,
+      "learning_rate": 9.621212121212122e-06,
+      "loss": 1.8561,
+      "step": 10
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 2.7316417694091797,
+      "learning_rate": 9.242424242424244e-06,
+      "loss": 1.737,
+      "step": 20
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 2.755110740661621,
+      "learning_rate": 8.863636363636365e-06,
+      "loss": 1.6365,
+      "step": 30
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 3.602980613708496,
+      "learning_rate": 8.484848484848486e-06,
+      "loss": 1.503,
+      "step": 40
+    },
+    {
+      "epoch": 4.166666666666667,
+      "grad_norm": 3.042379379272461,
+      "learning_rate": 8.106060606060606e-06,
+      "loss": 1.4031,
+      "step": 50
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.64223575592041,
+      "learning_rate": 7.727272727272727e-06,
+      "loss": 1.3179,
+      "step": 60
+    },
+    {
+      "epoch": 5.833333333333333,
+      "grad_norm": 2.7679355144500732,
+      "learning_rate": 7.348484848484849e-06,
+      "loss": 1.2421,
+      "step": 70
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 2.9133822917938232,
+      "learning_rate": 6.969696969696971e-06,
+      "loss": 1.1694,
+      "step": 80
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 3.096311569213867,
+      "learning_rate": 6.590909090909091e-06,
+      "loss": 1.0972,
+      "step": 90
+    },
+    {
+      "epoch": 8.333333333333334,
+      "grad_norm": 2.925428867340088,
+      "learning_rate": 6.212121212121213e-06,
+      "loss": 0.9953,
+      "step": 100
+    },
+    {
+      "epoch": 8.333333333333334,
+      "eval_accuracy": 0.5,
+      "eval_loss": 1.56011962890625,
+      "eval_runtime": 0.084,
+      "eval_samples_per_second": 95.205,
+      "eval_steps_per_second": 11.901,
+      "step": 100
+    },
+    {
+      "epoch": 9.166666666666666,
+      "grad_norm": 2.2385735511779785,
+      "learning_rate": 5.833333333333334e-06,
+      "loss": 0.9643,
+      "step": 110
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 3.4153809547424316,
+      "learning_rate": 5.4545454545454545e-06,
+      "loss": 0.9366,
+      "step": 120
+    },
+    {
+      "epoch": 10.833333333333334,
+      "grad_norm": 2.7754604816436768,
+      "learning_rate": 5.075757575757576e-06,
+      "loss": 0.8888,
+      "step": 130
+    },
+    {
+      "epoch": 11.666666666666666,
+      "grad_norm": 2.791471004486084,
+      "learning_rate": 4.696969696969698e-06,
+      "loss": 0.8297,
+      "step": 140
+    },
+    {
+      "epoch": 12.5,
+      "grad_norm": 2.9258711338043213,
+      "learning_rate": 4.3181818181818185e-06,
+      "loss": 0.795,
+      "step": 150
+    },
+    {
+      "epoch": 13.333333333333334,
+      "grad_norm": 2.066309928894043,
+      "learning_rate": 3.93939393939394e-06,
+      "loss": 0.7955,
+      "step": 160
+    },
+    {
+      "epoch": 14.166666666666666,
+      "grad_norm": 5.605708122253418,
+      "learning_rate": 3.560606060606061e-06,
+      "loss": 0.6958,
+      "step": 170
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 2.3019251823425293,
+      "learning_rate": 3.181818181818182e-06,
+      "loss": 0.7313,
+      "step": 180
+    },
+    {
+      "epoch": 15.833333333333334,
+      "grad_norm": 2.301241636276245,
+      "learning_rate": 2.803030303030303e-06,
+      "loss": 0.7144,
+      "step": 190
+    },
+    {
+      "epoch": 16.666666666666668,
+      "grad_norm": 2.3400890827178955,
+      "learning_rate": 2.4242424242424244e-06,
+      "loss": 0.6415,
+      "step": 200
+    },
+    {
+      "epoch": 16.666666666666668,
+      "eval_accuracy": 0.75,
+      "eval_loss": 1.36041259765625,
+      "eval_runtime": 0.0748,
+      "eval_samples_per_second": 106.9,
+      "eval_steps_per_second": 13.363,
+      "step": 200
+    },
+    {
+      "epoch": 17.5,
+      "grad_norm": 2.118030071258545,
+      "learning_rate": 2.0454545454545457e-06,
+      "loss": 0.6993,
+      "step": 210
+    },
+    {
+      "epoch": 18.333333333333332,
+      "grad_norm": 2.083101987838745,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.6416,
+      "step": 220
+    },
+    {
+      "epoch": 19.166666666666668,
+      "grad_norm": 1.6677289009094238,
+      "learning_rate": 1.287878787878788e-06,
+      "loss": 0.5854,
+      "step": 230
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 2.4138357639312744,
+      "learning_rate": 9.090909090909091e-07,
+      "loss": 0.6605,
+      "step": 240
+    },
+    {
+      "epoch": 20.833333333333332,
+      "grad_norm": 2.4232518672943115,
+      "learning_rate": 5.303030303030304e-07,
+      "loss": 0.5998,
+      "step": 250
+    },
+    {
+      "epoch": 21.666666666666668,
+      "grad_norm": 1.9394166469573975,
+      "learning_rate": 1.5151515151515152e-07,
+      "loss": 0.6696,
+      "step": 260
+    },
+    {
+      "epoch": 22.0,
+      "step": 264,
+      "total_flos": 8.013030801360077e+16,
+      "train_loss": 0.9863168768810503,
+      "train_runtime": 53.2305,
+      "train_samples_per_second": 19.425,
+      "train_steps_per_second": 4.96
+    }
+  ],
+  "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 sha256:60b7a8300b8ae6231b3f8b31b673ae0c9a1fddc535344132e464702e8bf6c734
+size 5240