add model

.gitignore

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

README.md

@@ -0,0 +1,76 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- beans
+metrics:
+- accuracy
+model-index:
+- name: vit-base-beans
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: beans
+      type: beans
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9774436090225563
+---
+
+<!-- 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
+
+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: 0.0942
+- Accuracy: 0.9774
+
+## 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: 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: 5.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.2809        | 1.0   | 130  | 0.2287          | 0.9699   |
+| 0.1097        | 2.0   | 260  | 0.1676          | 0.9624   |
+| 0.1027        | 3.0   | 390  | 0.0942          | 0.9774   |
+| 0.0923        | 4.0   | 520  | 0.1104          | 0.9699   |
+| 0.1726        | 5.0   | 650  | 0.1030          | 0.9699   |
+
+
+### Framework versions
+
+- Transformers 4.10.0.dev0
+- Pytorch 1.9.0+cu102
+- Datasets 1.11.1.dev0
+- Tokenizers 0.10.3

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9774436090225563,
+    "eval_loss": 0.09423530101776123,
+    "eval_runtime": 1.7062,
+    "eval_samples_per_second": 77.951,
+    "eval_steps_per_second": 9.964,
+    "train_loss": 0.23702784006412211,
+    "train_runtime": 124.7505,
+    "train_samples_per_second": 41.443,
+    "train_steps_per_second": 5.21
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "finetuning_task": "image-classification",
+  "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"
+}

emissions.csv

@@ -0,0 +1,2 @@
+timestamp,experiment_id,project_name,duration,emissions,energy_consumed,country_name,country_iso_code,region,on_cloud,cloud_provider,cloud_region
+2021-08-31T12:54:49,a4449492-67ee-4738-a85d-5ac4861bcb29,codecarbon,124.76043105125427,0.005462426324374648,0.009645817277723201,USA,USA,Iowa,Y,gcp,us-central1

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9774436090225563,
+    "eval_loss": 0.09423530101776123,
+    "eval_runtime": 1.7062,
+    "eval_samples_per_second": 77.951,
+    "eval_steps_per_second": 9.964
+}

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:fc443b145fcc3a09cf07eb28b94e9a989ec3f0e8f7255e1fa08c0953ed4bae91
+size 343282929

runs/Aug31_12-52-34_nate-gpu-2/1630414364.999114/events.out.tfevents.1630414364.nate-gpu-2.12898.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0518be0bbb187145974df13bed88d402be8eb609cabf1527c4a09df057b7a1ef
+size 4216

runs/Aug31_12-52-34_nate-gpu-2/events.out.tfevents.1630414364.nate-gpu-2.12898.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d838680fe881c3f25f235ece74982927b314f580b29d1224c44a3df042bd64b4
+size 15187

runs/Aug31_12-52-34_nate-gpu-2/events.out.tfevents.1630414491.nate-gpu-2.12898.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aaee3d3e039b4a6e840ad05b41b11c749918c7925d1c19fa4524e0423d179d7
+size 363

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.23702784006412211,
+    "train_runtime": 124.7505,
+    "train_samples_per_second": 41.443,
+    "train_steps_per_second": 5.21
+}

trainer_state.json

@@ -0,0 +1,460 @@
+{
+  "best_metric": 0.09423530101776123,
+  "best_model_checkpoint": "./beans_outputs/checkpoint-390",
+  "epoch": 5.0,
+  "global_step": 650,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9692307692307696e-05,
+      "loss": 1.0801,
+      "step": 10
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9384615384615386e-05,
+      "loss": 1.0047,
+      "step": 20
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.907692307692308e-05,
+      "loss": 0.9106,
+      "step": 30
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.876923076923077e-05,
+      "loss": 0.7891,
+      "step": 40
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.8461538461538465e-05,
+      "loss": 0.7158,
+      "step": 50
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.8153846153846155e-05,
+      "loss": 0.6401,
+      "step": 60
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.784615384615385e-05,
+      "loss": 0.5135,
+      "step": 70
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.753846153846154e-05,
+      "loss": 0.4501,
+      "step": 80
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.7230769230769234e-05,
+      "loss": 0.4603,
+      "step": 90
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.6923076923076924e-05,
+      "loss": 0.2978,
+      "step": 100
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.6615384615384618e-05,
+      "loss": 0.3313,
+      "step": 110
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.630769230769231e-05,
+      "loss": 0.3273,
+      "step": 120
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.2809,
+      "step": 130
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9699248120300752,
+      "eval_loss": 0.2287006974220276,
+      "eval_runtime": 1.6228,
+      "eval_samples_per_second": 81.958,
+      "eval_steps_per_second": 10.476,
+      "step": 130
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.5692307692307693e-05,
+      "loss": 0.2246,
+      "step": 140
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 0.184,
+      "step": 150
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.5076923076923078e-05,
+      "loss": 0.2474,
+      "step": 160
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.4769230769230772e-05,
+      "loss": 0.2246,
+      "step": 170
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.4461538461538462e-05,
+      "loss": 0.1846,
+      "step": 180
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.4153846153846156e-05,
+      "loss": 0.2743,
+      "step": 190
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.3846153846153847e-05,
+      "loss": 0.1205,
+      "step": 200
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.353846153846154e-05,
+      "loss": 0.249,
+      "step": 210
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.3230769230769231e-05,
+      "loss": 0.1794,
+      "step": 220
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.2923076923076925e-05,
+      "loss": 0.0964,
+      "step": 230
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 1.2615384615384616e-05,
+      "loss": 0.2207,
+      "step": 240
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.230769230769231e-05,
+      "loss": 0.167,
+      "step": 250
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.2e-05,
+      "loss": 0.1097,
+      "step": 260
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9624060150375939,
+      "eval_loss": 0.1675739735364914,
+      "eval_runtime": 1.6333,
+      "eval_samples_per_second": 81.431,
+      "eval_steps_per_second": 10.408,
+      "step": 260
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 1.1692307692307694e-05,
+      "loss": 0.1882,
+      "step": 270
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 1.1384615384615385e-05,
+      "loss": 0.1248,
+      "step": 280
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 1.1076923076923079e-05,
+      "loss": 0.1261,
+      "step": 290
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 1.076923076923077e-05,
+      "loss": 0.1816,
+      "step": 300
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 1.0461538461538463e-05,
+      "loss": 0.1997,
+      "step": 310
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 1.0153846153846154e-05,
+      "loss": 0.0846,
+      "step": 320
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 9.846153846153848e-06,
+      "loss": 0.2028,
+      "step": 330
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 9.53846153846154e-06,
+      "loss": 0.2454,
+      "step": 340
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 9.230769230769232e-06,
+      "loss": 0.1636,
+      "step": 350
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 8.923076923076925e-06,
+      "loss": 0.2061,
+      "step": 360
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 8.615384615384617e-06,
+      "loss": 0.163,
+      "step": 370
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 8.307692307692309e-06,
+      "loss": 0.0696,
+      "step": 380
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.1027,
+      "step": 390
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9774436090225563,
+      "eval_loss": 0.09423530101776123,
+      "eval_runtime": 1.6148,
+      "eval_samples_per_second": 82.363,
+      "eval_steps_per_second": 10.528,
+      "step": 390
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 0.1679,
+      "step": 400
+    },
+    {
+      "epoch": 3.15,
+      "learning_rate": 7.384615384615386e-06,
+      "loss": 0.1548,
+      "step": 410
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 7.076923076923078e-06,
+      "loss": 0.1519,
+      "step": 420
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 6.76923076923077e-06,
+      "loss": 0.0835,
+      "step": 430
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 6.461538461538463e-06,
+      "loss": 0.2056,
+      "step": 440
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 6.153846153846155e-06,
+      "loss": 0.1459,
+      "step": 450
+    },
+    {
+      "epoch": 3.54,
+      "learning_rate": 5.846153846153847e-06,
+      "loss": 0.1141,
+      "step": 460
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 5.538461538461539e-06,
+      "loss": 0.0742,
+      "step": 470
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 5.230769230769232e-06,
+      "loss": 0.1156,
+      "step": 480
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 4.923076923076924e-06,
+      "loss": 0.1143,
+      "step": 490
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 4.615384615384616e-06,
+      "loss": 0.0908,
+      "step": 500
+    },
+    {
+      "epoch": 3.92,
+      "learning_rate": 4.307692307692308e-06,
+      "loss": 0.0621,
+      "step": 510
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.0923,
+      "step": 520
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9699248120300752,
+      "eval_loss": 0.11044816672801971,
+      "eval_runtime": 1.6172,
+      "eval_samples_per_second": 82.239,
+      "eval_steps_per_second": 10.512,
+      "step": 520
+    },
+    {
+      "epoch": 4.08,
+      "learning_rate": 3.692307692307693e-06,
+      "loss": 0.1789,
+      "step": 530
+    },
+    {
+      "epoch": 4.15,
+      "learning_rate": 3.384615384615385e-06,
+      "loss": 0.1695,
+      "step": 540
+    },
+    {
+      "epoch": 4.23,
+      "learning_rate": 3.0769230769230774e-06,
+      "loss": 0.1273,
+      "step": 550
+    },
+    {
+      "epoch": 4.31,
+      "learning_rate": 2.7692307692307697e-06,
+      "loss": 0.0729,
+      "step": 560
+    },
+    {
+      "epoch": 4.38,
+      "learning_rate": 2.461538461538462e-06,
+      "loss": 0.0598,
+      "step": 570
+    },
+    {
+      "epoch": 4.46,
+      "learning_rate": 2.153846153846154e-06,
+      "loss": 0.0919,
+      "step": 580
+    },
+    {
+      "epoch": 4.54,
+      "learning_rate": 1.8461538461538465e-06,
+      "loss": 0.0685,
+      "step": 590
+    },
+    {
+      "epoch": 4.62,
+      "learning_rate": 1.5384615384615387e-06,
+      "loss": 0.088,
+      "step": 600
+    },
+    {
+      "epoch": 4.69,
+      "learning_rate": 1.230769230769231e-06,
+      "loss": 0.1753,
+      "step": 610
+    },
+    {
+      "epoch": 4.77,
+      "learning_rate": 9.230769230769232e-07,
+      "loss": 0.0791,
+      "step": 620
+    },
+    {
+      "epoch": 4.85,
+      "learning_rate": 6.153846153846155e-07,
+      "loss": 0.1131,
+      "step": 630
+    },
+    {
+      "epoch": 4.92,
+      "learning_rate": 3.0769230769230774e-07,
+      "loss": 0.0949,
+      "step": 640
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 0.1726,
+      "step": 650
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9699248120300752,
+      "eval_loss": 0.10300374776124954,
+      "eval_runtime": 1.6531,
+      "eval_samples_per_second": 80.453,
+      "eval_steps_per_second": 10.284,
+      "step": 650
+    },
+    {
+      "epoch": 5.0,
+      "step": 650,
+      "total_flos": 0.0,
+      "train_loss": 0.23702784006412211,
+      "train_runtime": 124.7505,
+      "train_samples_per_second": 41.443,
+      "train_steps_per_second": 5.21
+    }
+  ],
+  "max_steps": 650,
+  "num_train_epochs": 5,
+  "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:dbfebeca32be1d102a71d29619d0db0783df335f73af946dd488cfac20c644ec
+size 2671