🍻 cheers

README.md

@@ -0,0 +1,63 @@
+---
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- image-classification
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: vit-base-beans-demo-v5
+  results: []
+---
+
+<!-- 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-v5
+
+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: 0.0395
+- 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: 4
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 0.0879        | 1.5385 | 100  | 0.0950          | 0.9774   |
+| 0.0243        | 3.0769 | 200  | 0.0395          | 0.9850   |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9849624060150376,
+    "eval_loss": 0.039455611258745193,
+    "eval_runtime": 1.3415,
+    "eval_samples_per_second": 99.143,
+    "eval_steps_per_second": 12.672,
+    "total_flos": 3.205097416476426e+17,
+    "train_loss": 0.12025929483083578,
+    "train_runtime": 94.3031,
+    "train_samples_per_second": 43.859,
+    "train_steps_per_second": 2.757
+}

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "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,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2"
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9849624060150376,
+    "eval_loss": 0.039455611258745193,
+    "eval_runtime": 1.3415,
+    "eval_samples_per_second": 99.143,
+    "eval_steps_per_second": 12.672
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da23118451465ef10341a98aa766e4137db222474ee4f6002366b8a02de2d1d4
+size 343227052

preprocessor_config.json

@@ -0,0 +1,36 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTFeatureExtractor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

runs/Jun27_17-42-01_5895515150a4/events.out.tfevents.1719510122.5895515150a4.1406.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d125f1e0310a98e0828ef5c701d32311e8310b22e02a05b169d3d360099a8c75
+size 11323

runs/Jun27_17-42-01_5895515150a4/events.out.tfevents.1719510219.5895515150a4.1406.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb6174d27fecdf7901c5281858c7e1695ffb9f5a8c005703fd582eb92444d21f
+size 411

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "total_flos": 3.205097416476426e+17,
+    "train_loss": 0.12025929483083578,
+    "train_runtime": 94.3031,
+    "train_samples_per_second": 43.859,
+    "train_steps_per_second": 2.757
+}

trainer_state.json

@@ -0,0 +1,242 @@
+{
+  "best_metric": 0.039455611258745193,
+  "best_model_checkpoint": "./vit-base-beans-demo-v5/checkpoint-200",
+  "epoch": 4.0,
+  "eval_steps": 100,
+  "global_step": 260,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 1.5127050876617432,
+      "learning_rate": 0.00019230769230769233,
+      "loss": 0.832,
+      "step": 10
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 2.9642956256866455,
+      "learning_rate": 0.00018461538461538463,
+      "loss": 0.3281,
+      "step": 20
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 1.479327917098999,
+      "learning_rate": 0.00017692307692307693,
+      "loss": 0.1852,
+      "step": 30
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 4.251507759094238,
+      "learning_rate": 0.00016923076923076923,
+      "loss": 0.2552,
+      "step": 40
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 2.2233493328094482,
+      "learning_rate": 0.00016153846153846155,
+      "loss": 0.173,
+      "step": 50
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 1.1962614059448242,
+      "learning_rate": 0.00015384615384615385,
+      "loss": 0.2716,
+      "step": 60
+    },
+    {
+      "epoch": 1.0769230769230769,
+      "grad_norm": 2.2528934478759766,
+      "learning_rate": 0.00014615384615384615,
+      "loss": 0.3024,
+      "step": 70
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 0.2029009759426117,
+      "learning_rate": 0.00013846153846153847,
+      "loss": 0.1413,
+      "step": 80
+    },
+    {
+      "epoch": 1.3846153846153846,
+      "grad_norm": 0.16266554594039917,
+      "learning_rate": 0.00013076923076923077,
+      "loss": 0.0459,
+      "step": 90
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 3.4238033294677734,
+      "learning_rate": 0.0001230769230769231,
+      "loss": 0.0879,
+      "step": 100
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "eval_accuracy": 0.9774436090225563,
+      "eval_loss": 0.09501739591360092,
+      "eval_runtime": 1.6492,
+      "eval_samples_per_second": 80.643,
+      "eval_steps_per_second": 10.308,
+      "step": 100
+    },
+    {
+      "epoch": 1.6923076923076923,
+      "grad_norm": 4.021958827972412,
+      "learning_rate": 0.00011538461538461538,
+      "loss": 0.0663,
+      "step": 110
+    },
+    {
+      "epoch": 1.8461538461538463,
+      "grad_norm": 0.8424084186553955,
+      "learning_rate": 0.0001076923076923077,
+      "loss": 0.0762,
+      "step": 120
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.11821229010820389,
+      "learning_rate": 0.0001,
+      "loss": 0.068,
+      "step": 130
+    },
+    {
+      "epoch": 2.1538461538461537,
+      "grad_norm": 0.11869572848081589,
+      "learning_rate": 9.230769230769232e-05,
+      "loss": 0.0463,
+      "step": 140
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 5.829068660736084,
+      "learning_rate": 8.461538461538461e-05,
+      "loss": 0.0358,
+      "step": 150
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 0.09531725943088531,
+      "learning_rate": 7.692307692307693e-05,
+      "loss": 0.0459,
+      "step": 160
+    },
+    {
+      "epoch": 2.6153846153846154,
+      "grad_norm": 0.13866978883743286,
+      "learning_rate": 6.923076923076924e-05,
+      "loss": 0.0309,
+      "step": 170
+    },
+    {
+      "epoch": 2.769230769230769,
+      "grad_norm": 0.18827354907989502,
+      "learning_rate": 6.153846153846155e-05,
+      "loss": 0.0156,
+      "step": 180
+    },
+    {
+      "epoch": 2.9230769230769234,
+      "grad_norm": 0.07095403224229813,
+      "learning_rate": 5.384615384615385e-05,
+      "loss": 0.0169,
+      "step": 190
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 0.06902670115232468,
+      "learning_rate": 4.615384615384616e-05,
+      "loss": 0.0243,
+      "step": 200
+    },
+    {
+      "epoch": 3.076923076923077,
+      "eval_accuracy": 0.9849624060150376,
+      "eval_loss": 0.039455611258745193,
+      "eval_runtime": 1.1868,
+      "eval_samples_per_second": 112.071,
+      "eval_steps_per_second": 14.325,
+      "step": 200
+    },
+    {
+      "epoch": 3.230769230769231,
+      "grad_norm": 0.6385956406593323,
+      "learning_rate": 3.846153846153846e-05,
+      "loss": 0.0133,
+      "step": 210
+    },
+    {
+      "epoch": 3.3846153846153846,
+      "grad_norm": 0.0793854370713234,
+      "learning_rate": 3.0769230769230774e-05,
+      "loss": 0.0124,
+      "step": 220
+    },
+    {
+      "epoch": 3.5384615384615383,
+      "grad_norm": 0.06871400028467178,
+      "learning_rate": 2.307692307692308e-05,
+      "loss": 0.0122,
+      "step": 230
+    },
+    {
+      "epoch": 3.6923076923076925,
+      "grad_norm": 0.10652589797973633,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 0.0124,
+      "step": 240
+    },
+    {
+      "epoch": 3.8461538461538463,
+      "grad_norm": 0.059241101145744324,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 0.0118,
+      "step": 250
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.1098334938287735,
+      "learning_rate": 0.0,
+      "loss": 0.0156,
+      "step": 260
+    },
+    {
+      "epoch": 4.0,
+      "step": 260,
+      "total_flos": 3.205097416476426e+17,
+      "train_loss": 0.12025929483083578,
+      "train_runtime": 94.3031,
+      "train_samples_per_second": 43.859,
+      "train_steps_per_second": 2.757
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 260,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.205097416476426e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8baf81fe96f98069659da52bd60eddef3e6c99293239ad3b6032cfe3637bc378
+size 5112