End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.7614213197969543
+      value: 0.7715736040609137
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/swin-base-patch4-window7-224-in22k](https://huggingface.co/microsoft/swin-base-patch4-window7-224-in22k) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3081
-- Accuracy: 0.7614
+- Loss: 1.1390
+- Accuracy: 0.7716
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.7715736040609137,
+    "eval_loss": 1.139024019241333,
+    "eval_runtime": 26.9374,
+    "eval_samples_per_second": 14.627,
+    "eval_steps_per_second": 0.928,
+    "total_flos": 1.1242852922068992e+18,
+    "train_loss": 0.37599817170037164,
+    "train_runtime": 5634.9759,
+    "train_samples_per_second": 2.547,
+    "train_steps_per_second": 0.04
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.7715736040609137,
+    "eval_loss": 1.139024019241333,
+    "eval_runtime": 26.9374,
+    "eval_samples_per_second": 14.627,
+    "eval_steps_per_second": 0.928
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 1.1242852922068992e+18,
+    "train_loss": 0.37599817170037164,
+    "train_runtime": 5634.9759,
+    "train_samples_per_second": 2.547,
+    "train_steps_per_second": 0.04
+}

trainer_state.json

@@ -0,0 +1,229 @@
+{
+  "best_metric": 0.7715736040609137,
+  "best_model_checkpoint": "swin-base-patch4-window7-224-in22k-finetuned-CT\\checkpoint-180",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 225,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 4.816601276397705,
+      "learning_rate": 1.3043478260869566e-05,
+      "loss": 1.515,
+      "step": 10
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 4.57719087600708,
+      "learning_rate": 2.608695652173913e-05,
+      "loss": 1.2094,
+      "step": 20
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 22.845544815063477,
+      "learning_rate": 2.896039603960396e-05,
+      "loss": 0.8499,
+      "step": 30
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 22.14103126525879,
+      "learning_rate": 2.747524752475248e-05,
+      "loss": 0.5901,
+      "step": 40
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5685279187817259,
+      "eval_loss": 1.2601628303527832,
+      "eval_runtime": 25.1222,
+      "eval_samples_per_second": 15.683,
+      "eval_steps_per_second": 0.995,
+      "step": 45
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 13.752126693725586,
+      "learning_rate": 2.599009900990099e-05,
+      "loss": 0.4871,
+      "step": 50
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 20.15511131286621,
+      "learning_rate": 2.4504950495049504e-05,
+      "loss": 0.375,
+      "step": 60
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 7.8009490966796875,
+      "learning_rate": 2.301980198019802e-05,
+      "loss": 0.333,
+      "step": 70
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 6.6323957443237305,
+      "learning_rate": 2.1534653465346535e-05,
+      "loss": 0.2945,
+      "step": 80
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.815214157104492,
+      "learning_rate": 2.004950495049505e-05,
+      "loss": 0.2771,
+      "step": 90
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7106598984771574,
+      "eval_loss": 1.1592636108398438,
+      "eval_runtime": 26.3129,
+      "eval_samples_per_second": 14.974,
+      "eval_steps_per_second": 0.95,
+      "step": 90
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 7.441839694976807,
+      "learning_rate": 1.8564356435643564e-05,
+      "loss": 0.2747,
+      "step": 100
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 16.264951705932617,
+      "learning_rate": 1.7079207920792078e-05,
+      "loss": 0.2465,
+      "step": 110
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 51.40734100341797,
+      "learning_rate": 1.5594059405940596e-05,
+      "loss": 0.2113,
+      "step": 120
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 9.421001434326172,
+      "learning_rate": 1.4108910891089108e-05,
+      "loss": 0.2341,
+      "step": 130
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7233502538071066,
+      "eval_loss": 1.2320008277893066,
+      "eval_runtime": 25.3627,
+      "eval_samples_per_second": 15.535,
+      "eval_steps_per_second": 0.986,
+      "step": 135
+    },
+    {
+      "epoch": 3.111111111111111,
+      "grad_norm": 4.912576675415039,
+      "learning_rate": 1.2623762376237624e-05,
+      "loss": 0.2227,
+      "step": 140
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 35.091007232666016,
+      "learning_rate": 1.1138613861386138e-05,
+      "loss": 0.1684,
+      "step": 150
+    },
+    {
+      "epoch": 3.5555555555555554,
+      "grad_norm": 7.606155872344971,
+      "learning_rate": 9.653465346534654e-06,
+      "loss": 0.1606,
+      "step": 160
+    },
+    {
+      "epoch": 3.7777777777777777,
+      "grad_norm": 8.227788925170898,
+      "learning_rate": 8.168316831683168e-06,
+      "loss": 0.1323,
+      "step": 170
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 9.39113712310791,
+      "learning_rate": 6.6831683168316835e-06,
+      "loss": 0.1879,
+      "step": 180
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7715736040609137,
+      "eval_loss": 1.139024019241333,
+      "eval_runtime": 25.2262,
+      "eval_samples_per_second": 15.619,
+      "eval_steps_per_second": 0.991,
+      "step": 180
+    },
+    {
+      "epoch": 4.222222222222222,
+      "grad_norm": 8.584113121032715,
+      "learning_rate": 5.198019801980198e-06,
+      "loss": 0.1653,
+      "step": 190
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 9.124540328979492,
+      "learning_rate": 3.7128712871287128e-06,
+      "loss": 0.1394,
+      "step": 200
+    },
+    {
+      "epoch": 4.666666666666667,
+      "grad_norm": 6.846659183502197,
+      "learning_rate": 2.227722772277228e-06,
+      "loss": 0.1275,
+      "step": 210
+    },
+    {
+      "epoch": 4.888888888888889,
+      "grad_norm": 9.12004280090332,
+      "learning_rate": 7.425742574257426e-07,
+      "loss": 0.1765,
+      "step": 220
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7614213197969543,
+      "eval_loss": 1.3080726861953735,
+      "eval_runtime": 27.2127,
+      "eval_samples_per_second": 14.479,
+      "eval_steps_per_second": 0.919,
+      "step": 225
+    },
+    {
+      "epoch": 5.0,
+      "step": 225,
+      "total_flos": 1.1242852922068992e+18,
+      "train_loss": 0.37599817170037164,
+      "train_runtime": 5634.9759,
+      "train_samples_per_second": 2.547,
+      "train_steps_per_second": 0.04
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 225,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 1.1242852922068992e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}