🍻 cheers

.gitignore

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

README.md

@@ -0,0 +1,75 @@
+---
+license: apache-2.0
+tags:
+- image-classification
+- other-image-classification
+- generated_from_trainer
+datasets:
+- beans
+metrics:
+- accuracy
+model-index:
+- name: vit-base-beans-demo-v3
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: beans
+      type: beans
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9849624060150376
+---
+
+<!-- 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-beans-demo-v3
+
+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 beans dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0645
+- Accuracy: 0.9850
+
+## 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: 0.0002
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.0397        | 1.54  | 100  | 0.0645          | 0.9850   |
+
+
+### Framework versions
+
+- Transformers 4.10.0.dev0
+- Pytorch 1.9.0+cu102
+- Datasets 1.11.0
+- Tokenizers 0.10.3

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.9849624060150376,
+    "eval_loss": 0.0645078495144844,
+    "eval_runtime": 4.4101,
+    "eval_samples_per_second": 30.158,
+    "eval_steps_per_second": 3.855,
+    "total_flos": 0.0,
+    "train_loss": 0.22280787963133591,
+    "train_runtime": 105.6076,
+    "train_samples_per_second": 19.582,
+    "train_steps_per_second": 1.231
+}

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": "angular_leaf_spot",
+    "1": "bean_rust",
+    "2": "healthy"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "angular_leaf_spot": "0",
+    "bean_rust": "1",
+    "healthy": "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": "4.10.0.dev0"
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.9849624060150376,
+    "eval_loss": 0.0645078495144844,
+    "eval_runtime": 4.4101,
+    "eval_samples_per_second": 30.158,
+    "eval_steps_per_second": 3.855
+}

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 sha256:95242172659c30362be995bbbd33238d1d6d2661d0a2af6dd10ac6867575c9dc
+size 343282929

runs/Aug27_17-49-35_8aef211896cd/1630086610.446651/events.out.tfevents.1630086610.8aef211896cd.77.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:211af9c8f1d6329784891431b44841ec61844f09a0af591edef74a9b3018b591
+size 4240

runs/Aug27_17-49-35_8aef211896cd/events.out.tfevents.1630086610.8aef211896cd.77.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9521b3119e81dfe6480ad59ea0d99761673457954b4482286436cbf076f3977
+size 5693

runs/Aug27_17-49-35_8aef211896cd/events.out.tfevents.1630086722.8aef211896cd.77.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d6ba4450844676431c5283ef7accfd3f7b1de2b13b7ba2b9de4b44ac696cc08
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 0.0,
+    "train_loss": 0.22280787963133591,
+    "train_runtime": 105.6076,
+    "train_samples_per_second": 19.582,
+    "train_steps_per_second": 1.231
+}

trainer_state.json

@@ -0,0 +1,112 @@
+{
+  "best_metric": 0.0645078495144844,
+  "best_model_checkpoint": "./vit-base-beans-demo-v3/checkpoint-100",
+  "epoch": 2.0,
+  "global_step": 130,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00018461538461538463,
+      "loss": 0.8806,
+      "step": 10
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00016923076923076923,
+      "loss": 0.4438,
+      "step": 20
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00015384615384615385,
+      "loss": 0.3464,
+      "step": 30
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00013846153846153847,
+      "loss": 0.3524,
+      "step": 40
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0001230769230769231,
+      "loss": 0.2376,
+      "step": 50
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0001076923076923077,
+      "loss": 0.1484,
+      "step": 60
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 9.230769230769232e-05,
+      "loss": 0.0672,
+      "step": 70
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 7.692307692307693e-05,
+      "loss": 0.1207,
+      "step": 80
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 6.153846153846155e-05,
+      "loss": 0.0542,
+      "step": 90
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 4.615384615384616e-05,
+      "loss": 0.0397,
+      "step": 100
+    },
+    {
+      "epoch": 1.54,
+      "eval_accuracy": 0.9849624060150376,
+      "eval_loss": 0.0645078495144844,
+      "eval_runtime": 4.5427,
+      "eval_samples_per_second": 29.278,
+      "eval_steps_per_second": 3.742,
+      "step": 100
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 3.0769230769230774e-05,
+      "loss": 0.0978,
+      "step": 110
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 0.0357,
+      "step": 120
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0,
+      "loss": 0.0721,
+      "step": 130
+    },
+    {
+      "epoch": 2.0,
+      "step": 130,
+      "total_flos": 0.0,
+      "train_loss": 0.22280787963133591,
+      "train_runtime": 105.6076,
+      "train_samples_per_second": 19.582,
+      "train_steps_per_second": 1.231
+    }
+  ],
+  "max_steps": 130,
+  "num_train_epochs": 2,
+  "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:a77c3c293c2992c1db7fd3161a6d6788254a0d9e50d0fef014531adac39df67b
+size 2671