rotated_maps

README.md

@@ -0,0 +1,80 @@
+---
+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-v10
+  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-v10
+
+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: 0.9495
+- 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: 25
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Accuracy |
+|:-------------:|:-------:|:----:|:---------------:|:--------:|
+| 0.3924        | 8.3333  | 100  | 1.0648          | 0.75     |
+| 0.2925        | 16.6667 | 200  | 0.9745          | 0.875    |
+| 0.2696        | 25.0    | 300  | 0.9495          | 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": 25.0,
+    "eval_accuracy": 0.875,
+    "eval_loss": 0.949462890625,
+    "eval_runtime": 0.1295,
+    "eval_samples_per_second": 61.775,
+    "eval_steps_per_second": 7.722,
+    "total_flos": 9.10571681972736e+16,
+    "train_loss": 0.3887536287307739,
+    "train_runtime": 50.4832,
+    "train_samples_per_second": 23.275,
+    "train_steps_per_second": 5.943
+}

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": 25.0,
+    "eval_accuracy": 0.875,
+    "eval_loss": 0.949462890625,
+    "eval_runtime": 0.1295,
+    "eval_samples_per_second": 61.775,
+    "eval_steps_per_second": 7.722
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83fafab7f4e060bcfc378657c677f74b4fc4e050f70271d46f906e25fe6250b2
+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/Nov02_20-16-33_be037f56c5ae/events.out.tfevents.1730578599.be037f56c5ae.1722.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35b6324e1f1f4f9a747605b46c209f55631e6a24907bf7e9b9d527eee38f6861
+size 12846

runs/Nov02_20-16-33_be037f56c5ae/events.out.tfevents.1730578651.be037f56c5ae.1722.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:506da935265e20a570e2b8a0cf1dd9af344bafa3843700ff46084d2f7950fcb5
+size 411

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 25.0,
+    "total_flos": 9.10571681972736e+16,
+    "train_loss": 0.3887536287307739,
+    "train_runtime": 50.4832,
+    "train_samples_per_second": 23.275,
+    "train_steps_per_second": 5.943
+}

trainer_state.json

@@ -0,0 +1,279 @@
+{
+  "best_metric": 0.949462890625,
+  "best_model_checkpoint": "vit-base-patch16-224-in21k-rotated-dungeons-v10/checkpoint-300",
+  "epoch": 25.0,
+  "eval_steps": 100,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 2.3087613582611084,
+      "learning_rate": 9.666666666666667e-06,
+      "loss": 0.6636,
+      "step": 10
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 2.7166261672973633,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 0.6662,
+      "step": 20
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 3.353682279586792,
+      "learning_rate": 9e-06,
+      "loss": 0.5914,
+      "step": 30
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 2.8412413597106934,
+      "learning_rate": 8.666666666666668e-06,
+      "loss": 0.5596,
+      "step": 40
+    },
+    {
+      "epoch": 4.166666666666667,
+      "grad_norm": 1.754184603691101,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.5065,
+      "step": 50
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.479107141494751,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.4977,
+      "step": 60
+    },
+    {
+      "epoch": 5.833333333333333,
+      "grad_norm": 2.0364372730255127,
+      "learning_rate": 7.666666666666667e-06,
+      "loss": 0.4746,
+      "step": 70
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 2.4275097846984863,
+      "learning_rate": 7.333333333333333e-06,
+      "loss": 0.4526,
+      "step": 80
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 2.7387607097625732,
+      "learning_rate": 7e-06,
+      "loss": 0.4602,
+      "step": 90
+    },
+    {
+      "epoch": 8.333333333333334,
+      "grad_norm": 1.6016734838485718,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.3924,
+      "step": 100
+    },
+    {
+      "epoch": 8.333333333333334,
+      "eval_accuracy": 0.75,
+      "eval_loss": 1.0648193359375,
+      "eval_runtime": 0.1023,
+      "eval_samples_per_second": 78.165,
+      "eval_steps_per_second": 9.771,
+      "step": 100
+    },
+    {
+      "epoch": 9.166666666666666,
+      "grad_norm": 1.6682934761047363,
+      "learning_rate": 6.333333333333333e-06,
+      "loss": 0.4078,
+      "step": 110
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.6906030178070068,
+      "learning_rate": 6e-06,
+      "loss": 0.3954,
+      "step": 120
+    },
+    {
+      "epoch": 10.833333333333334,
+      "grad_norm": 2.5330770015716553,
+      "learning_rate": 5.666666666666667e-06,
+      "loss": 0.3856,
+      "step": 130
+    },
+    {
+      "epoch": 11.666666666666666,
+      "grad_norm": 1.7529984712600708,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 0.3603,
+      "step": 140
+    },
+    {
+      "epoch": 12.5,
+      "grad_norm": 1.7168235778808594,
+      "learning_rate": 5e-06,
+      "loss": 0.3493,
+      "step": 150
+    },
+    {
+      "epoch": 13.333333333333334,
+      "grad_norm": 1.144932508468628,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 0.3555,
+      "step": 160
+    },
+    {
+      "epoch": 14.166666666666666,
+      "grad_norm": 1.3627619743347168,
+      "learning_rate": 4.333333333333334e-06,
+      "loss": 0.3087,
+      "step": 170
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 1.25572669506073,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.3354,
+      "step": 180
+    },
+    {
+      "epoch": 15.833333333333334,
+      "grad_norm": 1.3966418504714966,
+      "learning_rate": 3.6666666666666666e-06,
+      "loss": 0.3254,
+      "step": 190
+    },
+    {
+      "epoch": 16.666666666666668,
+      "grad_norm": 1.105637550354004,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.2925,
+      "step": 200
+    },
+    {
+      "epoch": 16.666666666666668,
+      "eval_accuracy": 0.875,
+      "eval_loss": 0.97454833984375,
+      "eval_runtime": 0.078,
+      "eval_samples_per_second": 102.592,
+      "eval_steps_per_second": 12.824,
+      "step": 200
+    },
+    {
+      "epoch": 17.5,
+      "grad_norm": 1.1144015789031982,
+      "learning_rate": 3e-06,
+      "loss": 0.323,
+      "step": 210
+    },
+    {
+      "epoch": 18.333333333333332,
+      "grad_norm": 1.1320604085922241,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 0.2966,
+      "step": 220
+    },
+    {
+      "epoch": 19.166666666666668,
+      "grad_norm": 0.9238783717155457,
+      "learning_rate": 2.3333333333333336e-06,
+      "loss": 0.2717,
+      "step": 230
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 1.6188000440597534,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.3051,
+      "step": 240
+    },
+    {
+      "epoch": 20.833333333333332,
+      "grad_norm": 1.2386761903762817,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.2758,
+      "step": 250
+    },
+    {
+      "epoch": 21.666666666666668,
+      "grad_norm": 1.056011438369751,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 0.3078,
+      "step": 260
+    },
+    {
+      "epoch": 22.5,
+      "grad_norm": 0.9684665203094482,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.2861,
+      "step": 270
+    },
+    {
+      "epoch": 23.333333333333332,
+      "grad_norm": 0.9503129720687866,
+      "learning_rate": 6.666666666666667e-07,
+      "loss": 0.2708,
+      "step": 280
+    },
+    {
+      "epoch": 24.166666666666668,
+      "grad_norm": 0.9533663392066956,
+      "learning_rate": 3.3333333333333335e-07,
+      "loss": 0.2753,
+      "step": 290
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 1.1195876598358154,
+      "learning_rate": 0.0,
+      "loss": 0.2696,
+      "step": 300
+    },
+    {
+      "epoch": 25.0,
+      "eval_accuracy": 0.875,
+      "eval_loss": 0.949462890625,
+      "eval_runtime": 0.0772,
+      "eval_samples_per_second": 103.628,
+      "eval_steps_per_second": 12.953,
+      "step": 300
+    },
+    {
+      "epoch": 25.0,
+      "step": 300,
+      "total_flos": 9.10571681972736e+16,
+      "train_loss": 0.3887536287307739,
+      "train_runtime": 50.4832,
+      "train_samples_per_second": 23.275,
+      "train_steps_per_second": 5.943
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 25,
+  "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": 9.10571681972736e+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 sha256:4963f901fc34067afa2a7e3064f7e15d34d4867b4437145155f6b4821a07d872
+size 5240