commit files to HF hub

.gitignore

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

README.md

@@ -0,0 +1,92 @@
+---
+license: apache-2.0
+tags:
+- huggingpics
+- image-classification
+- generated_from_trainer
+metrics:
+- accuracy
+model_index:
+- name: planes-trains-automobiles
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    metric:
+      name: Accuracy
+      type: accuracy
+      value: 0.9850746268656716
+---
+
+<!-- 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. -->
+
+# planes-trains-automobiles
+
+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 huggingpics dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0534
+- Accuracy: 0.9851
+
+
+## Model description
+
+Autogenerated by HuggingPics🤗🖼️
+
+Create your own image classifier for **anything** by running [the demo on Google Colab](https://colab.research.google.com/github/nateraw/huggingpics/blob/main/HuggingPics.ipynb).
+
+Report any issues with the demo at the [github repo](https://github.com/nateraw/huggingpics).
+## Example Images
+
+
+#### automobiles
+
+![automobiles](images/automobiles.jpg)
+
+#### planes
+
+![planes](images/planes.jpg)
+
+#### trains
+
+![trains](images/trains.jpg)
+
+
+## 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: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 1337
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.0283        | 1.0   | 48   | 0.0434          | 0.9851   |
+| 0.0224        | 2.0   | 96   | 0.0548          | 0.9851   |
+| 0.0203        | 3.0   | 144  | 0.0445          | 0.9851   |
+| 0.0195        | 4.0   | 192  | 0.0534          | 0.9851   |
+
+
+### Framework versions
+
+- Transformers 4.9.2
+- Pytorch 1.9.0+cu102
+- Datasets 1.11.0
+- Tokenizers 0.10.3

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "total_flos": 0.0,
+    "train_loss": 0.023352553563502926,
+    "train_runtime": 233.1724,
+    "train_samples_per_second": 6.57,
+    "train_steps_per_second": 0.823
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "automobiles",
+    "1": "planes",
+    "2": "trains"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "automobiles": "0",
+    "planes": "1",
+    "trains": "2"
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.2"
+}

preprocessor_config.json

@@ -0,0 +1,17 @@
+{
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "ViTFeatureExtractor",
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "size": 224
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbe3c77709d39b188d1840940951756659a5cb58e13b92935d33d69b3a229a49
+size 343282929

runs/Aug23_21-37-56_90489a400d03/1629754680.1882749/events.out.tfevents.1629754680.90489a400d03.658.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fffa4466850b15eb210b2cee8eccea0227990f8fb4491a6619d01a82663d6d7
+size 4323

runs/Aug23_21-37-56_90489a400d03/events.out.tfevents.1629754680.90489a400d03.658.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f47398f622806d914d00ced1979145c7167cf3aeeeb76e029ba20da5e04ced71
+size 7707

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "total_flos": 0.0,
+    "train_loss": 0.023352553563502926,
+    "train_runtime": 233.1724,
+    "train_samples_per_second": 6.57,
+    "train_steps_per_second": 0.823
+}

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": 0.9850746268656716,
+  "best_model_checkpoint": "./outputs/checkpoint-48",
+  "epoch": 4.0,
+  "global_step": 192,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8958333333333334e-05,
+      "loss": 0.0325,
+      "step": 10
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.7916666666666667e-05,
+      "loss": 0.031,
+      "step": 20
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.6875e-05,
+      "loss": 0.0295,
+      "step": 30
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.5833333333333333e-05,
+      "loss": 0.0283,
+      "step": 40
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9850746268656716,
+      "eval_loss": 0.04340995103120804,
+      "eval_runtime": 1.9606,
+      "eval_samples_per_second": 34.174,
+      "eval_steps_per_second": 4.59,
+      "step": 48
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.479166666666667e-05,
+      "loss": 0.0268,
+      "step": 50
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.375e-05,
+      "loss": 0.0249,
+      "step": 60
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.2708333333333333e-05,
+      "loss": 0.0236,
+      "step": 70
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.1666666666666668e-05,
+      "loss": 0.023,
+      "step": 80
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.0625e-05,
+      "loss": 0.0224,
+      "step": 90
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9850746268656716,
+      "eval_loss": 0.05477194860577583,
+      "eval_runtime": 1.9694,
+      "eval_samples_per_second": 34.021,
+      "eval_steps_per_second": 4.57,
+      "step": 96
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 9.583333333333335e-06,
+      "loss": 0.0216,
+      "step": 100
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 8.541666666666666e-06,
+      "loss": 0.0213,
+      "step": 110
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.0205,
+      "step": 120
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 6.458333333333334e-06,
+      "loss": 0.0206,
+      "step": 130
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 5.416666666666667e-06,
+      "loss": 0.0203,
+      "step": 140
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9850746268656716,
+      "eval_loss": 0.04450145736336708,
+      "eval_runtime": 1.9416,
+      "eval_samples_per_second": 34.507,
+      "eval_steps_per_second": 4.635,
+      "step": 144
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 4.3750000000000005e-06,
+      "loss": 0.02,
+      "step": 150
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.0196,
+      "step": 160
+    },
+    {
+      "epoch": 3.54,
+      "learning_rate": 2.2916666666666666e-06,
+      "loss": 0.0196,
+      "step": 170
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 1.25e-06,
+      "loss": 0.0194,
+      "step": 180
+    },
+    {
+      "epoch": 3.96,
+      "learning_rate": 2.0833333333333333e-07,
+      "loss": 0.0195,
+      "step": 190
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9850746268656716,
+      "eval_loss": 0.053447265177965164,
+      "eval_runtime": 1.9698,
+      "eval_samples_per_second": 34.013,
+      "eval_steps_per_second": 4.569,
+      "step": 192
+    },
+    {
+      "epoch": 4.0,
+      "step": 192,
+      "total_flos": 0.0,
+      "train_loss": 0.023352553563502926,
+      "train_runtime": 233.1724,
+      "train_samples_per_second": 6.57,
+      "train_steps_per_second": 0.823
+    }
+  ],
+  "max_steps": 192,
+  "num_train_epochs": 4,
+  "total_flos": 0.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f59fb11a6ea363b68fd3296567eb3a86f2116a225e3fdb842fc90800d6332673
+size 2799