End of training

README.md

@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.9849058122685558
+      value: 0.9560060081137611
     - name: F1
       type: f1
-      value: 0.9916590671500701
+      value: 0.9749764456013159
     - name: Precision
       type: precision
-      value: 0.9836297048051891
+      value: 0.995013037809648
     - name: Recall
       type: recall
-      value: 0.9998205956225332
+      value: 0.9557308788078018
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -44,11 +44,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 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 imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1042
-- Accuracy: 0.9849
-- F1: 0.9917
-- Precision: 0.9836
-- Recall: 0.9998
+- Loss: 0.2115
+- Accuracy: 0.9560
+- F1: 0.9750
+- Precision: 0.9950
+- Recall: 0.9557
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9560060081137611,
+    "eval_f1": 0.9749764456013159,
+    "eval_loss": 0.21150292456150055,
+    "eval_precision": 0.995013037809648,
+    "eval_recall": 0.9557308788078018,
+    "eval_runtime": 1892.414,
+    "eval_samples_per_second": 37.643,
+    "eval_steps_per_second": 4.706,
+    "train_loss": 0.03190612774814858,
+    "train_runtime": 4007.5201,
+    "train_samples_per_second": 18.999,
+    "train_steps_per_second": 2.375
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9888101754950893,
+    "eval_f1": 0.993782429772768,
+    "eval_loss": 0.050547029823064804,
+    "eval_precision": 0.9911224125624554,
+    "eval_recall": 0.9964567635450305,
+    "eval_runtime": 651.5312,
+    "eval_samples_per_second": 38.132,
+    "eval_steps_per_second": 4.767
+}

runs/Dec21_21-05-11_Phoenix/events.out.tfevents.1703197863.Phoenix.7120.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76da4b9240958f9ded76c1e490f136c544bb0ffb0f3c76b2d57f7bf3fc41752f
+size 1032

test_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9560060081137611,
+    "eval_f1": 0.9749764456013159,
+    "eval_loss": 0.21150292456150055,
+    "eval_precision": 0.995013037809648,
+    "eval_recall": 0.9557308788078018,
+    "eval_runtime": 1892.414,
+    "eval_samples_per_second": 37.643,
+    "eval_steps_per_second": 4.706
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.03190612774814858,
+    "train_runtime": 4007.5201,
+    "train_samples_per_second": 18.999,
+    "train_steps_per_second": 2.375
+}

trainer_state.json

@@ -0,0 +1,180 @@
+{
+  "best_metric": 0.050547029823064804,
+  "best_model_checkpoint": "W:/res/Transformers/VIT-ConstantQ-Synthetic-Voice-Detection\\checkpoint-6346",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 9519,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.7373673705221136e-05,
+      "loss": 0.2039,
+      "step": 500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.4747347410442276e-05,
+      "loss": 0.0976,
+      "step": 1000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.212102111566341e-05,
+      "loss": 0.0627,
+      "step": 1500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 3.949469482088455e-05,
+      "loss": 0.046,
+      "step": 2000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.686836852610568e-05,
+      "loss": 0.0461,
+      "step": 2500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.424204223132682e-05,
+      "loss": 0.0383,
+      "step": 3000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9752857832877153,
+      "eval_f1": 0.9864141257689073,
+      "eval_loss": 0.11920787394046783,
+      "eval_precision": 0.9734474626604943,
+      "eval_recall": 0.9997308934337998,
+      "eval_runtime": 647.2762,
+      "eval_samples_per_second": 38.382,
+      "eval_steps_per_second": 4.799,
+      "step": 3173
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 3.1615715936547956e-05,
+      "loss": 0.0195,
+      "step": 3500
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 2.8989389641769092e-05,
+      "loss": 0.0133,
+      "step": 4000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 2.636306334699023e-05,
+      "loss": 0.0132,
+      "step": 4500
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 2.373673705221137e-05,
+      "loss": 0.0147,
+      "step": 5000
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 2.1110410757432505e-05,
+      "loss": 0.0178,
+      "step": 5500
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.8484084462653642e-05,
+      "loss": 0.0158,
+      "step": 6000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9888101754950893,
+      "eval_f1": 0.993782429772768,
+      "eval_loss": 0.050547029823064804,
+      "eval_precision": 0.9911224125624554,
+      "eval_recall": 0.9964567635450305,
+      "eval_runtime": 652.5276,
+      "eval_samples_per_second": 38.073,
+      "eval_steps_per_second": 4.76,
+      "step": 6346
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.585775816787478e-05,
+      "loss": 0.0103,
+      "step": 6500
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 1.3231431873095915e-05,
+      "loss": 0.0034,
+      "step": 7000
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 1.060510557831705e-05,
+      "loss": 0.0007,
+      "step": 7500
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 7.978779283538187e-06,
+      "loss": 0.0017,
+      "step": 8000
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 5.352452988759324e-06,
+      "loss": 0.0001,
+      "step": 8500
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 2.7261266939804603e-06,
+      "loss": 0.0005,
+      "step": 9000
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 9.98003992015968e-08,
+      "loss": 0.0021,
+      "step": 9500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9849058122685558,
+      "eval_f1": 0.9916590671500701,
+      "eval_loss": 0.10420931875705719,
+      "eval_precision": 0.9836297048051891,
+      "eval_recall": 0.9998205956225332,
+      "eval_runtime": 641.7351,
+      "eval_samples_per_second": 38.714,
+      "eval_steps_per_second": 4.84,
+      "step": 9519
+    },
+    {
+      "epoch": 3.0,
+      "step": 9519,
+      "total_flos": 5.900240089255035e+18,
+      "train_loss": 0.03190612774814858,
+      "train_runtime": 4007.5201,
+      "train_samples_per_second": 18.999,
+      "train_steps_per_second": 2.375
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9519,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 5.900240089255035e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}