be2be2

README.md

@@ -0,0 +1,65 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- image-classification
+- ViT
+- 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: 0.2048
+- Accuracy: 0.9375
+
+## 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: 16
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 4
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 0.0814        | 1.5385 | 100  | 0.2125          | 0.9098   |
+| 0.0127        | 3.0769 | 200  | 0.0274          | 0.9925   |
+
+
+### Framework versions
+
+- Transformers 4.54.1
+- Pytorch 2.6.0+cu124
+- Datasets 4.0.0
+- Tokenizers 0.21.4

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9375,
+    "eval_loss": 0.204814612865448,
+    "eval_runtime": 1.5577,
+    "eval_samples_per_second": 82.171,
+    "eval_steps_per_second": 5.136,
+    "total_flos": 3.205097416476426e+17,
+    "train_loss": 0.12112718929465001,
+    "train_runtime": 104.2153,
+    "train_samples_per_second": 39.687,
+    "train_steps_per_second": 2.495
+}

config.json

@@ -0,0 +1,35 @@
+{
+  "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,
+  "pooler_act": "tanh",
+  "pooler_output_size": 768,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.54.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7386c30881d27e4a7595d17aff5d421b8ec0cd922e3b46128ebc79172c21433
+size 343227052

preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_convert_rgb": null,
+  "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/Aug01_02-09-02_0edff376c966/events.out.tfevents.1754014146.0edff376c966.531.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dc738a20296c188de618e23d145c94264574eabc3a03fedccd79276b67448ad
+size 11515

runs/Aug01_02-09-02_0edff376c966/events.out.tfevents.1754014254.0edff376c966.531.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96b44628bd89b446998faaff33e081e780bcc0da7c526b6bd50c71545d06ee1a
+size 411

test_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9375,
+    "eval_loss": 0.204814612865448,
+    "eval_runtime": 1.5577,
+    "eval_samples_per_second": 82.171,
+    "eval_steps_per_second": 5.136
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "total_flos": 3.205097416476426e+17,
+    "train_loss": 0.12112718929465001,
+    "train_runtime": 104.2153,
+    "train_samples_per_second": 39.687,
+    "train_steps_per_second": 2.495
+}

trainer_state.json

@@ -0,0 +1,243 @@
+{
+  "best_global_step": 200,
+  "best_metric": 0.9924812030075187,
+  "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": 1.8465008735656738,
+      "learning_rate": 0.0001930769230769231,
+      "loss": 0.8272,
+      "step": 10
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 2.3152756690979004,
+      "learning_rate": 0.0001853846153846154,
+      "loss": 0.3076,
+      "step": 20
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 1.462149977684021,
+      "learning_rate": 0.0001776923076923077,
+      "loss": 0.2484,
+      "step": 30
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 1.5601600408554077,
+      "learning_rate": 0.00017,
+      "loss": 0.3078,
+      "step": 40
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 1.7110002040863037,
+      "learning_rate": 0.0001623076923076923,
+      "loss": 0.2375,
+      "step": 50
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 1.6433830261230469,
+      "learning_rate": 0.00015461538461538464,
+      "loss": 0.2519,
+      "step": 60
+    },
+    {
+      "epoch": 1.0769230769230769,
+      "grad_norm": 0.5108979940414429,
+      "learning_rate": 0.00014692307692307693,
+      "loss": 0.1594,
+      "step": 70
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 0.17463286221027374,
+      "learning_rate": 0.00013923076923076923,
+      "loss": 0.0964,
+      "step": 80
+    },
+    {
+      "epoch": 1.3846153846153846,
+      "grad_norm": 6.128848552703857,
+      "learning_rate": 0.00013153846153846156,
+      "loss": 0.0696,
+      "step": 90
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 0.13578061759471893,
+      "learning_rate": 0.00012384615384615385,
+      "loss": 0.0814,
+      "step": 100
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "eval_accuracy": 0.9097744360902256,
+      "eval_loss": 0.21250881254673004,
+      "eval_runtime": 1.2493,
+      "eval_samples_per_second": 106.461,
+      "eval_steps_per_second": 7.204,
+      "step": 100
+    },
+    {
+      "epoch": 1.6923076923076923,
+      "grad_norm": 1.2079147100448608,
+      "learning_rate": 0.00011615384615384617,
+      "loss": 0.1222,
+      "step": 110
+    },
+    {
+      "epoch": 1.8461538461538463,
+      "grad_norm": 2.105736255645752,
+      "learning_rate": 0.00010846153846153846,
+      "loss": 0.0689,
+      "step": 120
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.0425434112548828,
+      "learning_rate": 0.00010076923076923077,
+      "loss": 0.0689,
+      "step": 130
+    },
+    {
+      "epoch": 2.1538461538461537,
+      "grad_norm": 0.09185847640037537,
+      "learning_rate": 9.307692307692309e-05,
+      "loss": 0.0353,
+      "step": 140
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 9.617168426513672,
+      "learning_rate": 8.538461538461538e-05,
+      "loss": 0.0381,
+      "step": 150
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 0.08445341140031815,
+      "learning_rate": 7.76923076923077e-05,
+      "loss": 0.017,
+      "step": 160
+    },
+    {
+      "epoch": 2.6153846153846154,
+      "grad_norm": 0.07447629421949387,
+      "learning_rate": 7e-05,
+      "loss": 0.0163,
+      "step": 170
+    },
+    {
+      "epoch": 2.769230769230769,
+      "grad_norm": 2.2068941593170166,
+      "learning_rate": 6.23076923076923e-05,
+      "loss": 0.0237,
+      "step": 180
+    },
+    {
+      "epoch": 2.9230769230769234,
+      "grad_norm": 1.7057480812072754,
+      "learning_rate": 5.461538461538461e-05,
+      "loss": 0.0683,
+      "step": 190
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 0.06541252136230469,
+      "learning_rate": 4.692307692307693e-05,
+      "loss": 0.0127,
+      "step": 200
+    },
+    {
+      "epoch": 3.076923076923077,
+      "eval_accuracy": 0.9924812030075187,
+      "eval_loss": 0.027433352544903755,
+      "eval_runtime": 1.2357,
+      "eval_samples_per_second": 107.631,
+      "eval_steps_per_second": 7.283,
+      "step": 200
+    },
+    {
+      "epoch": 3.230769230769231,
+      "grad_norm": 0.06294204294681549,
+      "learning_rate": 3.923076923076923e-05,
+      "loss": 0.0124,
+      "step": 210
+    },
+    {
+      "epoch": 3.3846153846153846,
+      "grad_norm": 0.06276626139879227,
+      "learning_rate": 3.153846153846154e-05,
+      "loss": 0.0125,
+      "step": 220
+    },
+    {
+      "epoch": 3.5384615384615383,
+      "grad_norm": 7.931839466094971,
+      "learning_rate": 2.384615384615385e-05,
+      "loss": 0.0306,
+      "step": 230
+    },
+    {
+      "epoch": 3.6923076923076925,
+      "grad_norm": 0.061203066259622574,
+      "learning_rate": 1.6153846153846154e-05,
+      "loss": 0.0115,
+      "step": 240
+    },
+    {
+      "epoch": 3.8461538461538463,
+      "grad_norm": 0.07784971594810486,
+      "learning_rate": 8.461538461538462e-06,
+      "loss": 0.0117,
+      "step": 250
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.05536546930670738,
+      "learning_rate": 7.692307692307694e-07,
+      "loss": 0.0118,
+      "step": 260
+    },
+    {
+      "epoch": 4.0,
+      "step": 260,
+      "total_flos": 3.205097416476426e+17,
+      "train_loss": 0.12112718929465001,
+      "train_runtime": 104.2153,
+      "train_samples_per_second": 39.687,
+      "train_steps_per_second": 2.495
+    }
+  ],
+  "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": true
+      },
+      "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 sha256:0cbc7ccec2a843284484f9c33528000c14a02bf25c12e2b34b4b4636ad722375
+size 5368