End of training

README.md

@@ -32,7 +32,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0730
+- Loss: 0.0786
 - Accuracy: 0.9809
 
 ## Model description

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9809264305177112,
+    "eval_loss": 0.07860878109931946,
+    "eval_runtime": 5.4221,
+    "eval_samples_per_second": 67.687,
+    "eval_steps_per_second": 2.213,
+    "total_flos": 7.678887715683717e+17,
+    "train_loss": 0.36344620203360534,
+    "train_runtime": 415.1296,
+    "train_samples_per_second": 23.87,
+    "train_steps_per_second": 0.188
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9809264305177112,
+    "eval_loss": 0.07860878109931946,
+    "eval_runtime": 5.4221,
+    "eval_samples_per_second": 67.687,
+    "eval_steps_per_second": 2.213
+}

runs/Nov29_14-11-28_6450fb237299/events.out.tfevents.1701267939.6450fb237299.5032.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45c638858befd9ba63016867799a49f17ea47e72973d7a4b6662a9876c6a695a
+size 405

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 7.678887715683717e+17,
+    "train_loss": 0.36344620203360534,
+    "train_runtime": 415.1296,
+    "train_samples_per_second": 23.87,
+    "train_steps_per_second": 0.188
+}

trainer_state.json

@@ -0,0 +1,97 @@
+{
+  "best_metric": 0.9809264305177112,
+  "best_model_checkpoint": "vit-base-patch16-224-finetuned/checkpoint-52",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 78,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.8571428571428576e-05,
+      "loss": 1.5192,
+      "step": 10
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 4.1428571428571437e-05,
+      "loss": 0.5888,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9700272479564033,
+      "eval_loss": 0.17195835709571838,
+      "eval_runtime": 5.5957,
+      "eval_samples_per_second": 65.586,
+      "eval_steps_per_second": 2.145,
+      "step": 26
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 3.428571428571429e-05,
+      "loss": 0.2357,
+      "step": 30
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 2.714285714285714e-05,
+      "loss": 0.1499,
+      "step": 40
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 2e-05,
+      "loss": 0.1027,
+      "step": 50
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9809264305177112,
+      "eval_loss": 0.07860878109931946,
+      "eval_runtime": 5.4987,
+      "eval_samples_per_second": 66.743,
+      "eval_steps_per_second": 2.182,
+      "step": 52
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 1.2857142857142857e-05,
+      "loss": 0.0989,
+      "step": 60
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 0.0809,
+      "step": 70
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9809264305177112,
+      "eval_loss": 0.07304801046848297,
+      "eval_runtime": 5.4275,
+      "eval_samples_per_second": 67.619,
+      "eval_steps_per_second": 2.211,
+      "step": 78
+    },
+    {
+      "epoch": 3.0,
+      "step": 78,
+      "total_flos": 7.678887715683717e+17,
+      "train_loss": 0.36344620203360534,
+      "train_runtime": 415.1296,
+      "train_samples_per_second": 23.87,
+      "train_steps_per_second": 0.188
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 78,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 7.678887715683717e+17,
+  "trial_name": null,
+  "trial_params": null
+}