End of training

README.md

@@ -0,0 +1,96 @@
+---
+license: apache-2.0
+base_model: microsoft/swinv2-tiny-patch4-window8-256
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: swinv2-tiny-patch4-window8-256-finetuned-gardner-te-max
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: imagefolder
+      type: imagefolder
+      config: default
+      split: train
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.594017094017094
+---
+
+<!-- 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. -->
+
+# swinv2-tiny-patch4-window8-256-finetuned-gardner-te-max
+
+This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8795
+- Accuracy: 0.5940
+
+## 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: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.0943        | 0.94  | 11   | 1.0750          | 0.6325   |
+| 0.9996        | 1.96  | 23   | 0.8011          | 0.6325   |
+| 0.7731        | 2.98  | 35   | 0.7182          | 0.6325   |
+| 0.7564        | 4.0   | 47   | 0.7109          | 0.6325   |
+| 0.7331        | 4.94  | 58   | 0.7026          | 0.6325   |
+| 0.7336        | 5.96  | 70   | 0.6848          | 0.6325   |
+| 0.7305        | 6.98  | 82   | 0.6938          | 0.6325   |
+| 0.7314        | 8.0   | 94   | 0.6549          | 0.6325   |
+| 0.6905        | 8.94  | 105  | 0.6364          | 0.6867   |
+| 0.7315        | 9.96  | 117  | 0.6223          | 0.6687   |
+| 0.6839        | 10.98 | 129  | 0.6528          | 0.7530   |
+| 0.6931        | 12.0  | 141  | 0.6209          | 0.7410   |
+| 0.6705        | 12.94 | 152  | 0.6296          | 0.7169   |
+| 0.7227        | 13.96 | 164  | 0.6039          | 0.7108   |
+| 0.6695        | 14.98 | 176  | 0.6049          | 0.7530   |
+| 0.6981        | 16.0  | 188  | 0.5965          | 0.7048   |
+| 0.6566        | 16.94 | 199  | 0.6111          | 0.7410   |
+| 0.6828        | 17.96 | 211  | 0.5969          | 0.7530   |
+| 0.6632        | 18.72 | 220  | 0.5947          | 0.7530   |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.2
+- Datasets 2.16.0
+- Tokenizers 0.15.0

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 18.72,
+    "eval_accuracy": 0.594017094017094,
+    "eval_loss": 0.8794776201248169,
+    "eval_runtime": 9.1281,
+    "eval_samples_per_second": 25.635,
+    "eval_steps_per_second": 0.876,
+    "train_loss": 0.7387422084808349,
+    "train_runtime": 1241.7001,
+    "train_samples_per_second": 23.935,
+    "train_steps_per_second": 0.177
+}

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "microsoft/swinv2-tiny-patch4-window8-256",
+  "architectures": [
+    "Swinv2ForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "depths": [
+    2,
+    2,
+    6,
+    2
+  ],
+  "drop_path_rate": 0.1,
+  "embed_dim": 96,
+  "encoder_stride": 32,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "0",
+    "1": "1",
+    "2": "2"
+  },
+  "image_size": 256,
+  "initializer_range": 0.02,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "mlp_ratio": 4.0,
+  "model_type": "swinv2",
+  "num_channels": 3,
+  "num_heads": [
+    3,
+    6,
+    12,
+    24
+  ],
+  "num_layers": 4,
+  "patch_size": 4,
+  "path_norm": true,
+  "pretrained_window_sizes": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "use_absolute_embeddings": false,
+  "window_size": 8
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 18.72,
+    "eval_accuracy": 0.594017094017094,
+    "eval_loss": 0.8794776201248169,
+    "eval_runtime": 9.1281,
+    "eval_samples_per_second": 25.635,
+    "eval_steps_per_second": 0.876
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f017e4dde2cebbe0bfae7fcae6fd1f1313ffe61e6972203f394a9836ba4178d8
+size 110353212

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 256,
+    "width": 256
+  }
+}

runs/Dec28_19-33-23_MacBook-Pro-de-Max-2.local/events.out.tfevents.1703788410.MacBook-Pro-de-Max-2.local.35333.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5515db0aa3bc9761b0234811aab7e6acc262c1b3ca63898cf4dc896be6d0b54
+size 14625

runs/Dec28_19-33-23_MacBook-Pro-de-Max-2.local/events.out.tfevents.1703789774.MacBook-Pro-de-Max-2.local.35333.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef90218cbf344cbec1761fdc5ba580a3590e6c937155fcf045d270642347c982
+size 734

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 18.72,
+    "train_loss": 0.7387422084808349,
+    "train_runtime": 1241.7001,
+    "train_samples_per_second": 23.935,
+    "train_steps_per_second": 0.177
+}

trainer_state.json

@@ -0,0 +1,333 @@
+{
+  "best_metric": 0.7530120481927711,
+  "best_model_checkpoint": "swinv2-tiny-patch4-window8-256-finetuned-gardner-te-max/checkpoint-129",
+  "epoch": 18.72340425531915,
+  "eval_steps": 500,
+  "global_step": 220,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.272727272727273e-05,
+      "loss": 1.0943,
+      "step": 10
+    },
+    {
+      "epoch": 0.94,
+      "eval_accuracy": 0.6325301204819277,
+      "eval_loss": 1.0749578475952148,
+      "eval_runtime": 8.5945,
+      "eval_samples_per_second": 19.315,
+      "eval_steps_per_second": 0.698,
+      "step": 11
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 4.545454545454546e-05,
+      "loss": 0.9996,
+      "step": 20
+    },
+    {
+      "epoch": 1.96,
+      "eval_accuracy": 0.6325301204819277,
+      "eval_loss": 0.8011154532432556,
+      "eval_runtime": 2.9146,
+      "eval_samples_per_second": 56.955,
+      "eval_steps_per_second": 2.059,
+      "step": 23
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 4.797979797979798e-05,
+      "loss": 0.7731,
+      "step": 30
+    },
+    {
+      "epoch": 2.98,
+      "eval_accuracy": 0.6325301204819277,
+      "eval_loss": 0.7181705236434937,
+      "eval_runtime": 2.8916,
+      "eval_samples_per_second": 57.408,
+      "eval_steps_per_second": 2.075,
+      "step": 35
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 4.545454545454546e-05,
+      "loss": 0.7564,
+      "step": 40
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6325301204819277,
+      "eval_loss": 0.7109255790710449,
+      "eval_runtime": 2.8917,
+      "eval_samples_per_second": 57.405,
+      "eval_steps_per_second": 2.075,
+      "step": 47
+    },
+    {
+      "epoch": 4.26,
+      "learning_rate": 4.292929292929293e-05,
+      "loss": 0.7331,
+      "step": 50
+    },
+    {
+      "epoch": 4.94,
+      "eval_accuracy": 0.6325301204819277,
+      "eval_loss": 0.7025781869888306,
+      "eval_runtime": 2.9658,
+      "eval_samples_per_second": 55.972,
+      "eval_steps_per_second": 2.023,
+      "step": 58
+    },
+    {
+      "epoch": 5.11,
+      "learning_rate": 4.0404040404040405e-05,
+      "loss": 0.743,
+      "step": 60
+    },
+    {
+      "epoch": 5.96,
+      "learning_rate": 3.787878787878788e-05,
+      "loss": 0.7336,
+      "step": 70
+    },
+    {
+      "epoch": 5.96,
+      "eval_accuracy": 0.6325301204819277,
+      "eval_loss": 0.6847715973854065,
+      "eval_runtime": 2.9186,
+      "eval_samples_per_second": 56.877,
+      "eval_steps_per_second": 2.056,
+      "step": 70
+    },
+    {
+      "epoch": 6.81,
+      "learning_rate": 3.535353535353535e-05,
+      "loss": 0.7305,
+      "step": 80
+    },
+    {
+      "epoch": 6.98,
+      "eval_accuracy": 0.6325301204819277,
+      "eval_loss": 0.6938183307647705,
+      "eval_runtime": 2.945,
+      "eval_samples_per_second": 56.367,
+      "eval_steps_per_second": 2.037,
+      "step": 82
+    },
+    {
+      "epoch": 7.66,
+      "learning_rate": 3.282828282828283e-05,
+      "loss": 0.7314,
+      "step": 90
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6325301204819277,
+      "eval_loss": 0.654893696308136,
+      "eval_runtime": 2.8829,
+      "eval_samples_per_second": 57.58,
+      "eval_steps_per_second": 2.081,
+      "step": 94
+    },
+    {
+      "epoch": 8.51,
+      "learning_rate": 3.0303030303030306e-05,
+      "loss": 0.6905,
+      "step": 100
+    },
+    {
+      "epoch": 8.94,
+      "eval_accuracy": 0.6867469879518072,
+      "eval_loss": 0.6364297270774841,
+      "eval_runtime": 2.9426,
+      "eval_samples_per_second": 56.413,
+      "eval_steps_per_second": 2.039,
+      "step": 105
+    },
+    {
+      "epoch": 9.36,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 0.7315,
+      "step": 110
+    },
+    {
+      "epoch": 9.96,
+      "eval_accuracy": 0.6686746987951807,
+      "eval_loss": 0.6223430037498474,
+      "eval_runtime": 2.8889,
+      "eval_samples_per_second": 57.46,
+      "eval_steps_per_second": 2.077,
+      "step": 117
+    },
+    {
+      "epoch": 10.21,
+      "learning_rate": 2.5252525252525256e-05,
+      "loss": 0.6839,
+      "step": 120
+    },
+    {
+      "epoch": 10.98,
+      "eval_accuracy": 0.7530120481927711,
+      "eval_loss": 0.6527661085128784,
+      "eval_runtime": 2.9492,
+      "eval_samples_per_second": 56.286,
+      "eval_steps_per_second": 2.034,
+      "step": 129
+    },
+    {
+      "epoch": 11.06,
+      "learning_rate": 2.272727272727273e-05,
+      "loss": 0.7044,
+      "step": 130
+    },
+    {
+      "epoch": 11.91,
+      "learning_rate": 2.0202020202020203e-05,
+      "loss": 0.6931,
+      "step": 140
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.7409638554216867,
+      "eval_loss": 0.6209445595741272,
+      "eval_runtime": 2.9113,
+      "eval_samples_per_second": 57.019,
+      "eval_steps_per_second": 2.061,
+      "step": 141
+    },
+    {
+      "epoch": 12.77,
+      "learning_rate": 1.7676767676767676e-05,
+      "loss": 0.6705,
+      "step": 150
+    },
+    {
+      "epoch": 12.94,
+      "eval_accuracy": 0.7168674698795181,
+      "eval_loss": 0.6295837759971619,
+      "eval_runtime": 2.9661,
+      "eval_samples_per_second": 55.965,
+      "eval_steps_per_second": 2.023,
+      "step": 152
+    },
+    {
+      "epoch": 13.62,
+      "learning_rate": 1.5151515151515153e-05,
+      "loss": 0.7227,
+      "step": 160
+    },
+    {
+      "epoch": 13.96,
+      "eval_accuracy": 0.7108433734939759,
+      "eval_loss": 0.6039193272590637,
+      "eval_runtime": 2.9739,
+      "eval_samples_per_second": 55.819,
+      "eval_steps_per_second": 2.018,
+      "step": 164
+    },
+    {
+      "epoch": 14.47,
+      "learning_rate": 1.2626262626262628e-05,
+      "loss": 0.6695,
+      "step": 170
+    },
+    {
+      "epoch": 14.98,
+      "eval_accuracy": 0.7530120481927711,
+      "eval_loss": 0.6048843264579773,
+      "eval_runtime": 2.9528,
+      "eval_samples_per_second": 56.217,
+      "eval_steps_per_second": 2.032,
+      "step": 176
+    },
+    {
+      "epoch": 15.32,
+      "learning_rate": 1.0101010101010101e-05,
+      "loss": 0.6981,
+      "step": 180
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.7048192771084337,
+      "eval_loss": 0.5965093374252319,
+      "eval_runtime": 2.9154,
+      "eval_samples_per_second": 56.938,
+      "eval_steps_per_second": 2.058,
+      "step": 188
+    },
+    {
+      "epoch": 16.17,
+      "learning_rate": 7.5757575757575764e-06,
+      "loss": 0.6566,
+      "step": 190
+    },
+    {
+      "epoch": 16.94,
+      "eval_accuracy": 0.7409638554216867,
+      "eval_loss": 0.6111359000205994,
+      "eval_runtime": 2.8973,
+      "eval_samples_per_second": 57.294,
+      "eval_steps_per_second": 2.071,
+      "step": 199
+    },
+    {
+      "epoch": 17.02,
+      "learning_rate": 5.050505050505051e-06,
+      "loss": 0.6908,
+      "step": 200
+    },
+    {
+      "epoch": 17.87,
+      "learning_rate": 2.5252525252525253e-06,
+      "loss": 0.6828,
+      "step": 210
+    },
+    {
+      "epoch": 17.96,
+      "eval_accuracy": 0.7530120481927711,
+      "eval_loss": 0.5969204902648926,
+      "eval_runtime": 2.8702,
+      "eval_samples_per_second": 57.835,
+      "eval_steps_per_second": 2.09,
+      "step": 211
+    },
+    {
+      "epoch": 18.72,
+      "learning_rate": 0.0,
+      "loss": 0.6632,
+      "step": 220
+    },
+    {
+      "epoch": 18.72,
+      "eval_accuracy": 0.7530120481927711,
+      "eval_loss": 0.5946705937385559,
+      "eval_runtime": 2.8876,
+      "eval_samples_per_second": 57.486,
+      "eval_steps_per_second": 2.078,
+      "step": 220
+    },
+    {
+      "epoch": 18.72,
+      "step": 220,
+      "total_flos": 9.056508197685166e+17,
+      "train_loss": 0.7387422084808349,
+      "train_runtime": 1241.7001,
+      "train_samples_per_second": 23.935,
+      "train_steps_per_second": 0.177
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 220,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "total_flos": 9.056508197685166e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26b19098430cb115d57b6fb341f1938bf6892ca1a936bc224ddbee8be17e1460
+size 4792