🍻 cheers

README.md

@@ -2,6 +2,7 @@
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
+- image-classification
 - generated_from_trainer
 metrics:
 - accuracy
@@ -16,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/salmamoori/vit-beans-image-classification-2/runs/5fik93zr)
 # vit-fine-tuned-image-classification-beans_2
 
-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.
+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: 0.0170
 - Accuracy: 1.0

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 1.0,
+    "eval_loss": 0.017028138041496277,
+    "eval_runtime": 17.5441,
+    "eval_samples_per_second": 7.581,
+    "eval_steps_per_second": 0.969,
+    "total_flos": 4.006371770595533e+17,
+    "train_loss": 0.10399184557107778,
+    "train_runtime": 4370.2022,
+    "train_samples_per_second": 1.183,
+    "train_steps_per_second": 0.074
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 1.0,
+    "eval_loss": 0.017028138041496277,
+    "eval_runtime": 17.5441,
+    "eval_samples_per_second": 7.581,
+    "eval_steps_per_second": 0.969
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 4.006371770595533e+17,
+    "train_loss": 0.10399184557107778,
+    "train_runtime": 4370.2022,
+    "train_samples_per_second": 1.183,
+    "train_steps_per_second": 0.074
+}

trainer_state.json

@@ -0,0 +1,293 @@
+{
+  "best_metric": 0.017028138041496277,
+  "best_model_checkpoint": "vit-fine-tuned-image-classification-beans_2\\checkpoint-300",
+  "epoch": 5.0,
+  "eval_steps": 100,
+  "global_step": 325,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 1.838330626487732,
+      "learning_rate": 0.00019384615384615385,
+      "loss": 0.9029,
+      "step": 10
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 0.8585432767868042,
+      "learning_rate": 0.0001876923076923077,
+      "loss": 0.3239,
+      "step": 20
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 2.5284998416900635,
+      "learning_rate": 0.00018153846153846155,
+      "loss": 0.2423,
+      "step": 30
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 5.096222877502441,
+      "learning_rate": 0.0001753846153846154,
+      "loss": 0.3654,
+      "step": 40
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 2.209157943725586,
+      "learning_rate": 0.00016923076923076923,
+      "loss": 0.1337,
+      "step": 50
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 1.0063344240188599,
+      "learning_rate": 0.0001630769230769231,
+      "loss": 0.2958,
+      "step": 60
+    },
+    {
+      "epoch": 1.0769230769230769,
+      "grad_norm": 5.1612725257873535,
+      "learning_rate": 0.00015692307692307693,
+      "loss": 0.2864,
+      "step": 70
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 0.8443673253059387,
+      "learning_rate": 0.00015076923076923077,
+      "loss": 0.1165,
+      "step": 80
+    },
+    {
+      "epoch": 1.3846153846153846,
+      "grad_norm": 0.1971602886915207,
+      "learning_rate": 0.0001446153846153846,
+      "loss": 0.0356,
+      "step": 90
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 0.22484387457370758,
+      "learning_rate": 0.00013846153846153847,
+      "loss": 0.0648,
+      "step": 100
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "eval_accuracy": 0.9924812030075187,
+      "eval_loss": 0.0420377217233181,
+      "eval_runtime": 30.8858,
+      "eval_samples_per_second": 4.306,
+      "eval_steps_per_second": 0.55,
+      "step": 100
+    },
+    {
+      "epoch": 1.6923076923076923,
+      "grad_norm": 0.10582908987998962,
+      "learning_rate": 0.0001323076923076923,
+      "loss": 0.0537,
+      "step": 110
+    },
+    {
+      "epoch": 1.8461538461538463,
+      "grad_norm": 0.09471665322780609,
+      "learning_rate": 0.00012615384615384615,
+      "loss": 0.1001,
+      "step": 120
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.08882123231887817,
+      "learning_rate": 0.00012,
+      "loss": 0.0386,
+      "step": 130
+    },
+    {
+      "epoch": 2.1538461538461537,
+      "grad_norm": 2.4845492839813232,
+      "learning_rate": 0.00011384615384615384,
+      "loss": 0.0227,
+      "step": 140
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 4.820040702819824,
+      "learning_rate": 0.0001076923076923077,
+      "loss": 0.0325,
+      "step": 150
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 0.06727772951126099,
+      "learning_rate": 0.00010153846153846153,
+      "loss": 0.0224,
+      "step": 160
+    },
+    {
+      "epoch": 2.6153846153846154,
+      "grad_norm": 6.172357082366943,
+      "learning_rate": 9.53846153846154e-05,
+      "loss": 0.0455,
+      "step": 170
+    },
+    {
+      "epoch": 2.769230769230769,
+      "grad_norm": 0.7179319262504578,
+      "learning_rate": 8.923076923076924e-05,
+      "loss": 0.0756,
+      "step": 180
+    },
+    {
+      "epoch": 2.9230769230769234,
+      "grad_norm": 0.07661673426628113,
+      "learning_rate": 8.307692307692309e-05,
+      "loss": 0.0196,
+      "step": 190
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 0.05913277715444565,
+      "learning_rate": 7.692307692307693e-05,
+      "loss": 0.0422,
+      "step": 200
+    },
+    {
+      "epoch": 3.076923076923077,
+      "eval_accuracy": 0.9924812030075187,
+      "eval_loss": 0.04675745964050293,
+      "eval_runtime": 37.7884,
+      "eval_samples_per_second": 3.52,
+      "eval_steps_per_second": 0.45,
+      "step": 200
+    },
+    {
+      "epoch": 3.230769230769231,
+      "grad_norm": 0.0708017349243164,
+      "learning_rate": 7.076923076923078e-05,
+      "loss": 0.0107,
+      "step": 210
+    },
+    {
+      "epoch": 3.3846153846153846,
+      "grad_norm": 0.05266530439257622,
+      "learning_rate": 6.461538461538462e-05,
+      "loss": 0.0215,
+      "step": 220
+    },
+    {
+      "epoch": 3.5384615384615383,
+      "grad_norm": 0.05381350219249725,
+      "learning_rate": 5.846153846153847e-05,
+      "loss": 0.0329,
+      "step": 230
+    },
+    {
+      "epoch": 3.6923076923076925,
+      "grad_norm": 0.04883628711104393,
+      "learning_rate": 5.230769230769231e-05,
+      "loss": 0.0094,
+      "step": 240
+    },
+    {
+      "epoch": 3.8461538461538463,
+      "grad_norm": 0.04827561974525452,
+      "learning_rate": 4.615384615384616e-05,
+      "loss": 0.0089,
+      "step": 250
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.046552080661058426,
+      "learning_rate": 4e-05,
+      "loss": 0.0094,
+      "step": 260
+    },
+    {
+      "epoch": 4.153846153846154,
+      "grad_norm": 0.04622137174010277,
+      "learning_rate": 3.384615384615385e-05,
+      "loss": 0.0229,
+      "step": 270
+    },
+    {
+      "epoch": 4.3076923076923075,
+      "grad_norm": 0.04905983805656433,
+      "learning_rate": 2.7692307692307694e-05,
+      "loss": 0.0083,
+      "step": 280
+    },
+    {
+      "epoch": 4.461538461538462,
+      "grad_norm": 0.04810818284749985,
+      "learning_rate": 2.1538461538461542e-05,
+      "loss": 0.008,
+      "step": 290
+    },
+    {
+      "epoch": 4.615384615384615,
+      "grad_norm": 0.04192296415567398,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 0.008,
+      "step": 300
+    },
+    {
+      "epoch": 4.615384615384615,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.017028138041496277,
+      "eval_runtime": 28.3225,
+      "eval_samples_per_second": 4.696,
+      "eval_steps_per_second": 0.6,
+      "step": 300
+    },
+    {
+      "epoch": 4.769230769230769,
+      "grad_norm": 0.04521344602108002,
+      "learning_rate": 9.230769230769232e-06,
+      "loss": 0.0078,
+      "step": 310
+    },
+    {
+      "epoch": 4.923076923076923,
+      "grad_norm": 0.04102473333477974,
+      "learning_rate": 3.0769230769230774e-06,
+      "loss": 0.0078,
+      "step": 320
+    },
+    {
+      "epoch": 5.0,
+      "step": 325,
+      "total_flos": 4.006371770595533e+17,
+      "train_loss": 0.10399184557107778,
+      "train_runtime": 4370.2022,
+      "train_samples_per_second": 1.183,
+      "train_steps_per_second": 0.074
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 325,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 4.006371770595533e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}