Training in progress, step 200

README.md

@@ -1,3 +1,62 @@
 ---
 license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: vit-base-beans
+  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
+
+This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0409
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.0961        | 1.54  | 100  | 0.1920          | 0.9398   |
+| 0.0123        | 3.08  | 200  | 0.0409          | 0.9850   |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.2+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9924812030075187,
+    "eval_loss": 0.03386877477169037,
+    "eval_runtime": 1.7511,
+    "eval_samples_per_second": 75.95,
+    "eval_steps_per_second": 9.708,
+    "total_flos": 3.205097416476426e+17,
+    "train_loss": 0.1224416760297922,
+    "train_runtime": 70.5477,
+    "train_samples_per_second": 58.627,
+    "train_steps_per_second": 3.685
+}

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": "4.38.2"
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9924812030075187,
+    "eval_loss": 0.03386877477169037,
+    "eval_runtime": 1.7511,
+    "eval_samples_per_second": 75.95,
+    "eval_steps_per_second": 9.708
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1411f6eecdaece9588a275e4d5f739de8860e01e5a529c7df1b3e7e0180c548e
+size 343227052

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

runs/Apr16_04-50-38_ip-172-16-49-2.ec2.internal/events.out.tfevents.1713243053.ip-172-16-49-2.ec2.internal.31959.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:234962dd291913efca33f4038053cc6114b65be6361e63be3f92a5e1141c735e
+size 11068

runs/Apr16_04-50-38_ip-172-16-49-2.ec2.internal/events.out.tfevents.1713243146.ip-172-16-49-2.ec2.internal.31959.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1ad2baa0d05b45722dad671f30b213d77ec5f8c791ca3ede874031e8c1b9bfb
+size 411

runs/Apr16_05-10-42_ip-172-16-49-2.ec2.internal/events.out.tfevents.1713244248.ip-172-16-49-2.ec2.internal.19969.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90c2238823c2d5b9a7a06cc143d9b1bf43ea64acd9d722618ae12b0a567d5d65
+size 11088

runs/Apr16_05-18-40_ip-172-16-49-2.ec2.internal/events.out.tfevents.1713244722.ip-172-16-49-2.ec2.internal.28494.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12da4c991fdcbf20683bdbc486dc6827069147327738c08b86b2e2a7b743892f
+size 9468

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "total_flos": 3.205097416476426e+17,
+    "train_loss": 0.1224416760297922,
+    "train_runtime": 70.5477,
+    "train_samples_per_second": 58.627,
+    "train_steps_per_second": 3.685
+}

trainer_state.json

@@ -0,0 +1,230 @@
+{
+  "best_metric": 0.03386877477169037,
+  "best_model_checkpoint": "./vit-base-beans/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": 0.15,
+      "grad_norm": 2.295685052871704,
+      "learning_rate": 0.00019230769230769233,
+      "loss": 0.8646,
+      "step": 10
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 1.1776849031448364,
+      "learning_rate": 0.00018461538461538463,
+      "loss": 0.3374,
+      "step": 20
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.9071102738380432,
+      "learning_rate": 0.00017692307692307693,
+      "loss": 0.2223,
+      "step": 30
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.580019474029541,
+      "learning_rate": 0.00016923076923076923,
+      "loss": 0.2125,
+      "step": 40
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 9.19766902923584,
+      "learning_rate": 0.00016153846153846155,
+      "loss": 0.1555,
+      "step": 50
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 2.0074708461761475,
+      "learning_rate": 0.00015384615384615385,
+      "loss": 0.2388,
+      "step": 60
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.7031182050704956,
+      "learning_rate": 0.00014615384615384615,
+      "loss": 0.1481,
+      "step": 70
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 6.785604953765869,
+      "learning_rate": 0.00013846153846153847,
+      "loss": 0.1322,
+      "step": 80
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.13774830102920532,
+      "learning_rate": 0.00013076923076923077,
+      "loss": 0.0722,
+      "step": 90
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 0.8483244776725769,
+      "learning_rate": 0.0001230769230769231,
+      "loss": 0.0517,
+      "step": 100
+    },
+    {
+      "epoch": 1.54,
+      "eval_accuracy": 0.9849624060150376,
+      "eval_loss": 0.05896018445491791,
+      "eval_runtime": 1.8056,
+      "eval_samples_per_second": 73.661,
+      "eval_steps_per_second": 9.415,
+      "step": 100
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 0.10988904535770416,
+      "learning_rate": 0.00011538461538461538,
+      "loss": 0.0433,
+      "step": 110
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.3253529369831085,
+      "learning_rate": 0.00010846153846153846,
+      "loss": 0.1515,
+      "step": 120
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.0863533690571785,
+      "learning_rate": 0.00010076923076923077,
+      "loss": 0.1029,
+      "step": 130
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 0.2501890957355499,
+      "learning_rate": 9.307692307692309e-05,
+      "loss": 0.071,
+      "step": 140
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 0.09559178352355957,
+      "learning_rate": 8.538461538461538e-05,
+      "loss": 0.0328,
+      "step": 150
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 0.08136636763811111,
+      "learning_rate": 7.76923076923077e-05,
+      "loss": 0.0154,
+      "step": 160
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 1.6561012268066406,
+      "learning_rate": 7e-05,
+      "loss": 0.0145,
+      "step": 170
+    },
+    {
+      "epoch": 2.77,
+      "grad_norm": 9.944978713989258,
+      "learning_rate": 6.23076923076923e-05,
+      "loss": 0.0785,
+      "step": 180
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 0.1309250295162201,
+      "learning_rate": 5.461538461538461e-05,
+      "loss": 0.0327,
+      "step": 190
+    },
+    {
+      "epoch": 3.08,
+      "grad_norm": 0.0702584758400917,
+      "learning_rate": 4.692307692307693e-05,
+      "loss": 0.0723,
+      "step": 200
+    },
+    {
+      "epoch": 3.08,
+      "eval_accuracy": 0.9924812030075187,
+      "eval_loss": 0.03386877477169037,
+      "eval_runtime": 1.7639,
+      "eval_samples_per_second": 75.402,
+      "eval_steps_per_second": 9.638,
+      "step": 200
+    },
+    {
+      "epoch": 3.23,
+      "grad_norm": 0.05829323083162308,
+      "learning_rate": 3.923076923076923e-05,
+      "loss": 0.0117,
+      "step": 210
+    },
+    {
+      "epoch": 3.38,
+      "grad_norm": 0.06120636686682701,
+      "learning_rate": 3.153846153846154e-05,
+      "loss": 0.0119,
+      "step": 220
+    },
+    {
+      "epoch": 3.54,
+      "grad_norm": 0.06219624727964401,
+      "learning_rate": 2.384615384615385e-05,
+      "loss": 0.0519,
+      "step": 230
+    },
+    {
+      "epoch": 3.69,
+      "grad_norm": 0.9760288596153259,
+      "learning_rate": 1.6153846153846154e-05,
+      "loss": 0.0174,
+      "step": 240
+    },
+    {
+      "epoch": 3.85,
+      "grad_norm": 0.06477300822734833,
+      "learning_rate": 8.461538461538462e-06,
+      "loss": 0.0116,
+      "step": 250
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.05689156800508499,
+      "learning_rate": 7.692307692307694e-07,
+      "loss": 0.0287,
+      "step": 260
+    },
+    {
+      "epoch": 4.0,
+      "step": 260,
+      "total_flos": 3.205097416476426e+17,
+      "train_loss": 0.1224416760297922,
+      "train_runtime": 70.5477,
+      "train_samples_per_second": 58.627,
+      "train_steps_per_second": 3.685
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 260,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 100,
+  "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:b9a33359196376f74ad592a08a8668e2cc8e5ed9185ec9dd636d12fd9f450909
+size 4920