End of training

README.md

@@ -2,6 +2,8 @@
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
+- image-classification
+- vision
 - generated_from_trainer
 metrics:
 - accuracy
@@ -15,7 +17,7 @@ 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.
+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: 0.3437
 - Accuracy: 0.9699

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9699248120300752,
+    "eval_loss": 0.3437380790710449,
+    "eval_runtime": 1.6166,
+    "eval_samples_per_second": 82.274,
+    "eval_steps_per_second": 1.856,
+    "total_flos": 4.006371770595533e+17,
+    "train_loss": 0.5857037207659553,
+    "train_runtime": 120.9483,
+    "train_samples_per_second": 42.746,
+    "train_steps_per_second": 0.703
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9699248120300752,
+    "eval_loss": 0.3437380790710449,
+    "eval_runtime": 1.6166,
+    "eval_samples_per_second": 82.274,
+    "eval_steps_per_second": 1.856
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 4.006371770595533e+17,
+    "train_loss": 0.5857037207659553,
+    "train_runtime": 120.9483,
+    "train_samples_per_second": 42.746,
+    "train_steps_per_second": 0.703
+}

trainer_state.json

@@ -0,0 +1,143 @@
+{
+  "best_metric": 0.3437380790710449,
+  "best_model_checkpoint": "./beans_outputs/checkpoint-85",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 85,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 1.3447251319885254,
+      "learning_rate": 1.7647058823529414e-05,
+      "loss": 0.9867,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.924812030075188,
+      "eval_loss": 0.7572891116142273,
+      "eval_runtime": 2.5634,
+      "eval_samples_per_second": 51.884,
+      "eval_steps_per_second": 1.17,
+      "step": 17
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 1.191501259803772,
+      "learning_rate": 1.5294117647058822e-05,
+      "loss": 0.8137,
+      "step": 20
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 1.1548258066177368,
+      "learning_rate": 1.2941176470588238e-05,
+      "loss": 0.6901,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9624060150375939,
+      "eval_loss": 0.5546020269393921,
+      "eval_runtime": 1.7725,
+      "eval_samples_per_second": 75.037,
+      "eval_steps_per_second": 1.693,
+      "step": 34
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 1.2297497987747192,
+      "learning_rate": 1.0588235294117648e-05,
+      "loss": 0.5758,
+      "step": 40
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 1.0743614435195923,
+      "learning_rate": 8.23529411764706e-06,
+      "loss": 0.4983,
+      "step": 50
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9699248120300752,
+      "eval_loss": 0.4202447533607483,
+      "eval_runtime": 1.5463,
+      "eval_samples_per_second": 86.01,
+      "eval_steps_per_second": 1.94,
+      "step": 51
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "grad_norm": 1.227348804473877,
+      "learning_rate": 5.882352941176471e-06,
+      "loss": 0.454,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9624060150375939,
+      "eval_loss": 0.36091482639312744,
+      "eval_runtime": 1.5527,
+      "eval_samples_per_second": 85.658,
+      "eval_steps_per_second": 1.932,
+      "step": 68
+    },
+    {
+      "epoch": 4.117647058823529,
+      "grad_norm": 1.0482817888259888,
+      "learning_rate": 3.529411764705883e-06,
+      "loss": 0.391,
+      "step": 70
+    },
+    {
+      "epoch": 4.705882352941177,
+      "grad_norm": 1.1002055406570435,
+      "learning_rate": 1.1764705882352942e-06,
+      "loss": 0.3921,
+      "step": 80
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9699248120300752,
+      "eval_loss": 0.3437380790710449,
+      "eval_runtime": 1.5995,
+      "eval_samples_per_second": 83.153,
+      "eval_steps_per_second": 1.876,
+      "step": 85
+    },
+    {
+      "epoch": 5.0,
+      "step": 85,
+      "total_flos": 4.006371770595533e+17,
+      "train_loss": 0.5857037207659553,
+      "train_runtime": 120.9483,
+      "train_samples_per_second": 42.746,
+      "train_steps_per_second": 0.703
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 85,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "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": 64,
+  "trial_name": null,
+  "trial_params": null
+}