Duplicate from autoevaluate/image-multi-class-classification

Co-authored-by: Lewis Tunstall <[email protected]>

.gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,77 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- mnist
+- autoevaluate/mnist-sample
+metrics:
+- accuracy
+model-index:
+- name: image-classification
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: mnist
+      type: mnist
+      args: mnist
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9833333333333333
+duplicated_from: autoevaluate/image-multi-class-classification
+---
+
+<!-- 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. -->
+
+# image-classification
+
+This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the mnist dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0556
+- Accuracy: 0.9833
+
+## 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: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.3743        | 1.0   | 422  | 0.0556          | 0.9833   |
+
+
+### Framework versions
+
+- Transformers 4.20.0
+- Pytorch 1.11.0+cu113
+- Datasets 2.3.2
+- Tokenizers 0.12.1

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.9833333333333333,
+    "eval_loss": 0.05558411777019501,
+    "eval_runtime": 38.4928,
+    "eval_samples_per_second": 155.873,
+    "eval_steps_per_second": 4.884,
+    "total_flos": 1.342523444871168e+18,
+    "train_loss": 0.6594652506694975,
+    "train_runtime": 822.8009,
+    "train_samples_per_second": 65.629,
+    "train_steps_per_second": 0.513
+}

config.json

@@ -0,0 +1,64 @@
+{
+  "_name_or_path": "microsoft/swin-tiny-patch4-window7-224",
+  "architectures": [
+    "SwinForImageClassification"
+  ],
+  "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",
+    "3": "3",
+    "4": "4",
+    "5": "5",
+    "6": "6",
+    "7": "7",
+    "8": "8",
+    "9": "9"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3,
+    "4": 4,
+    "5": 5,
+    "6": 6,
+    "7": 7,
+    "8": 8,
+    "9": 9
+  },
+  "layer_norm_eps": 1e-05,
+  "mlp_ratio": 4.0,
+  "model_type": "swin",
+  "num_channels": 3,
+  "num_heads": [
+    3,
+    6,
+    12,
+    24
+  ],
+  "num_layers": 4,
+  "patch_size": 4,
+  "path_norm": true,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.0",
+  "use_absolute_embeddings": false,
+  "window_size": 7
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.9833333333333333,
+    "eval_loss": 0.05558411777019501,
+    "eval_runtime": 38.4928,
+    "eval_samples_per_second": 155.873,
+    "eval_steps_per_second": 4.884
+}

preprocessor_config.json

@@ -0,0 +1,17 @@
+{
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "ViTFeatureExtractor",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "size": 224
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:611bf6c977a11e8ecd3ca5f56d694dca8769e5bbd6510d3280968528eb4f47c2
+size 110417455

runs/Jun21_08-52-13_15d408464ff9/1655801577.142551/events.out.tfevents.1655801577.15d408464ff9.75.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc9ea6892fc914f58a13bd743e83935fc218594efeb5324ce45c26bd83b69b11
+size 5365

runs/Jun21_08-52-13_15d408464ff9/events.out.tfevents.1655801577.15d408464ff9.75.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97ab8cd1d74c5c6a815e9cbbc63b2065b52be1ef314270daf6ac411af8fea034
+size 4205

runs/Jun21_08-53-46_15d408464ff9/1655801639.1869574/events.out.tfevents.1655801639.15d408464ff9.75.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:993782d56ac79b6cee4e96074c8fac867793e4e852a9b97c86db0a2c9b581ac2
+size 5365

runs/Jun21_08-53-46_15d408464ff9/events.out.tfevents.1655801639.15d408464ff9.75.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4c4fa32ccbef8fcbb820c8410492e70c87050e5cc761e8cb6b1e37ac9eabb4a
+size 4051

runs/Jun21_08-55-37_15d408464ff9/1655801747.2972329/events.out.tfevents.1655801747.15d408464ff9.75.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:791e1e41bb3f8adcbf45d32cbe639a70d2d35ebda46f530b98fc579073d480ec
+size 5365

runs/Jun21_08-55-37_15d408464ff9/events.out.tfevents.1655801747.15d408464ff9.75.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c830b24b3492654f9c80e58ca1cb3004aa1bafa9a5f731dcba7c50c2a58c7319
+size 3842

runs/Jun21_08-56-34_15d408464ff9/1655801813.5448782/events.out.tfevents.1655801813.15d408464ff9.75.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4012a50925ced1eb5006e819b96a73343aecfddb645d4883b15810f1a77b9b68
+size 5365

runs/Jun21_08-56-34_15d408464ff9/events.out.tfevents.1655801813.15d408464ff9.75.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18204d0799e7348765e34fb8bdb4c1edc27ac1d4588dcea55312a8fac54e364f
+size 11286

runs/Jun21_08-56-34_15d408464ff9/events.out.tfevents.1655802836.15d408464ff9.75.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6fa3a3eb5bc736a4eccbd43fcdd83150ea5a737aefb417c12a5cbb678d19b64
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1.342523444871168e+18,
+    "train_loss": 0.6594652506694975,
+    "train_runtime": 822.8009,
+    "train_samples_per_second": 65.629,
+    "train_steps_per_second": 0.513
+}

trainer_state.json

@@ -0,0 +1,286 @@
+{
+  "best_metric": 0.9833333333333333,
+  "best_model_checkpoint": "image-classification/checkpoint-422",
+  "epoch": 1.0,
+  "global_step": 422,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.1627906976744187e-05,
+      "loss": 2.3142,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.3255813953488374e-05,
+      "loss": 2.2058,
+      "step": 20
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 3.488372093023256e-05,
+      "loss": 1.893,
+      "step": 30
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.651162790697675e-05,
+      "loss": 1.4224,
+      "step": 40
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.907651715039578e-05,
+      "loss": 1.0782,
+      "step": 50
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.775725593667547e-05,
+      "loss": 0.877,
+      "step": 60
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.6437994722955145e-05,
+      "loss": 0.778,
+      "step": 70
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.511873350923483e-05,
+      "loss": 0.6735,
+      "step": 80
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.379947229551452e-05,
+      "loss": 0.6688,
+      "step": 90
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.2480211081794194e-05,
+      "loss": 0.6841,
+      "step": 100
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.116094986807388e-05,
+      "loss": 0.5935,
+      "step": 110
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 3.984168865435357e-05,
+      "loss": 0.5521,
+      "step": 120
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 3.8522427440633244e-05,
+      "loss": 0.5555,
+      "step": 130
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 3.7203166226912934e-05,
+      "loss": 0.5483,
+      "step": 140
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.588390501319262e-05,
+      "loss": 0.5371,
+      "step": 150
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.456464379947229e-05,
+      "loss": 0.5485,
+      "step": 160
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.324538258575198e-05,
+      "loss": 0.526,
+      "step": 170
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.1926121372031666e-05,
+      "loss": 0.5255,
+      "step": 180
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 3.060686015831134e-05,
+      "loss": 0.5133,
+      "step": 190
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.9287598944591033e-05,
+      "loss": 0.4857,
+      "step": 200
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.7968337730870712e-05,
+      "loss": 0.4806,
+      "step": 210
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.6649076517150396e-05,
+      "loss": 0.4573,
+      "step": 220
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.5329815303430082e-05,
+      "loss": 0.4995,
+      "step": 230
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.4010554089709765e-05,
+      "loss": 0.4744,
+      "step": 240
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 2.269129287598945e-05,
+      "loss": 0.4543,
+      "step": 250
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 2.1372031662269128e-05,
+      "loss": 0.4613,
+      "step": 260
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 2.0052770448548815e-05,
+      "loss": 0.475,
+      "step": 270
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.8733509234828498e-05,
+      "loss": 0.4324,
+      "step": 280
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.741424802110818e-05,
+      "loss": 0.4003,
+      "step": 290
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.6094986807387864e-05,
+      "loss": 0.4409,
+      "step": 300
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.4775725593667547e-05,
+      "loss": 0.492,
+      "step": 310
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.345646437994723e-05,
+      "loss": 0.4541,
+      "step": 320
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.2137203166226914e-05,
+      "loss": 0.4202,
+      "step": 330
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.0817941952506597e-05,
+      "loss": 0.4371,
+      "step": 340
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 9.49868073878628e-06,
+      "loss": 0.4339,
+      "step": 350
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 8.179419525065963e-06,
+      "loss": 0.4083,
+      "step": 360
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6.860158311345646e-06,
+      "loss": 0.4668,
+      "step": 370
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.540897097625329e-06,
+      "loss": 0.4238,
+      "step": 380
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 4.221635883905013e-06,
+      "loss": 0.434,
+      "step": 390
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.9023746701846966e-06,
+      "loss": 0.4309,
+      "step": 400
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.5831134564643801e-06,
+      "loss": 0.4218,
+      "step": 410
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.6385224274406334e-07,
+      "loss": 0.3743,
+      "step": 420
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9833333333333333,
+      "eval_loss": 0.05558411777019501,
+      "eval_runtime": 38.6009,
+      "eval_samples_per_second": 155.437,
+      "eval_steps_per_second": 4.87,
+      "step": 422
+    },
+    {
+      "epoch": 1.0,
+      "step": 422,
+      "total_flos": 1.342523444871168e+18,
+      "train_loss": 0.6594652506694975,
+      "train_runtime": 822.8009,
+      "train_samples_per_second": 65.629,
+      "train_steps_per_second": 0.513
+    }
+  ],
+  "max_steps": 422,
+  "num_train_epochs": 1,
+  "total_flos": 1.342523444871168e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25b3008f2df2db06844e1c7300c08af1eec38c6580f96246ac4dc0758c823eb2
+size 3311