End of training

all_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 15.0,
+    "epoch": 10.0,
     "eval_accuracy": 0.7647058823529411,
-    "eval_loss": 0.6537247896194458,
-    "eval_runtime": 0.209,
-    "eval_samples_per_second": 81.348,
-    "eval_steps_per_second": 23.926,
-    "total_flos": 2.412253290037248e+16,
-    "train_loss": 0.5445812543233236,
-    "train_runtime": 64.3122,
-    "train_samples_per_second": 14.927,
-    "train_steps_per_second": 0.933
+    "eval_loss": 0.6600015163421631,
+    "eval_runtime": 0.2093,
+    "eval_samples_per_second": 81.21,
+    "eval_steps_per_second": 23.885,
+    "total_flos": 1.608168860024832e+16,
+    "train_loss": 0.36969062089920046,
+    "train_runtime": 46.5,
+    "train_samples_per_second": 13.763,
+    "train_steps_per_second": 0.86
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 15.0,
+    "epoch": 10.0,
     "eval_accuracy": 0.7647058823529411,
-    "eval_loss": 0.6537247896194458,
-    "eval_runtime": 0.209,
-    "eval_samples_per_second": 81.348,
-    "eval_steps_per_second": 23.926
+    "eval_loss": 0.6600015163421631,
+    "eval_runtime": 0.2093,
+    "eval_samples_per_second": 81.21,
+    "eval_steps_per_second": 23.885
 }

runs/May27_20-27-48_0922109e5cf6/events.out.tfevents.1685219354.0922109e5cf6.8213.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:155880a25fda563ab545e7166d6aae8a78cbc15ac5646252293d7fd0f050a813
+size 405

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 15.0,
-    "total_flos": 2.412253290037248e+16,
-    "train_loss": 0.5445812543233236,
-    "train_runtime": 64.3122,
-    "train_samples_per_second": 14.927,
-    "train_steps_per_second": 0.933
+    "epoch": 10.0,
+    "total_flos": 1.608168860024832e+16,
+    "train_loss": 0.36969062089920046,
+    "train_runtime": 46.5,
+    "train_samples_per_second": 13.763,
+    "train_steps_per_second": 0.86
 }

trainer_state.json

@@ -1,196 +1,139 @@
 {
   "best_metric": 0.7647058823529411,
-  "best_model_checkpoint": "convnext-tiny-224-drfx-CT-classifier/checkpoint-40",
-  "epoch": 15.0,
-  "global_step": 60,
+  "best_model_checkpoint": "convnext-tiny-224-drfx-CT-classifier/checkpoint-4",
+  "epoch": 10.0,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5882352941176471,
-      "eval_loss": 0.7083577513694763,
-      "eval_runtime": 0.4547,
-      "eval_samples_per_second": 37.384,
-      "eval_steps_per_second": 10.995,
+      "eval_accuracy": 0.7647058823529411,
+      "eval_loss": 0.6600015163421631,
+      "eval_runtime": 0.1838,
+      "eval_samples_per_second": 92.505,
+      "eval_steps_per_second": 27.207,
       "step": 4
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.5294117647058824,
-      "eval_loss": 0.7021164894104004,
-      "eval_runtime": 0.194,
-      "eval_samples_per_second": 87.643,
-      "eval_steps_per_second": 25.777,
+      "eval_accuracy": 0.5882352941176471,
+      "eval_loss": 0.7135058045387268,
+      "eval_runtime": 0.2157,
+      "eval_samples_per_second": 78.8,
+      "eval_steps_per_second": 23.177,
       "step": 8
     },
     {
       "epoch": 2.5,
-      "learning_rate": 4.62962962962963e-05,
-      "loss": 0.6143,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.4055,
       "step": 10
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.4117647058823529,
-      "eval_loss": 0.702375054359436,
-      "eval_runtime": 0.2072,
-      "eval_samples_per_second": 82.045,
-      "eval_steps_per_second": 24.131,
+      "eval_accuracy": 0.6470588235294118,
+      "eval_loss": 0.6851004958152771,
+      "eval_runtime": 0.1807,
+      "eval_samples_per_second": 94.088,
+      "eval_steps_per_second": 27.673,
       "step": 12
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.5294117647058824,
-      "eval_loss": 0.6856038570404053,
-      "eval_runtime": 0.2259,
-      "eval_samples_per_second": 75.262,
-      "eval_steps_per_second": 22.136,
+      "eval_accuracy": 0.6470588235294118,
+      "eval_loss": 0.6512044668197632,
+      "eval_runtime": 0.1486,
+      "eval_samples_per_second": 114.416,
+      "eval_steps_per_second": 33.652,
       "step": 16
     },
     {
       "epoch": 5.0,
-      "learning_rate": 3.7037037037037037e-05,
-      "loss": 0.6154,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 0.3895,
       "step": 20
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.5294117647058824,
-      "eval_loss": 0.6955483555793762,
-      "eval_runtime": 0.1803,
-      "eval_samples_per_second": 94.292,
-      "eval_steps_per_second": 27.733,
+      "eval_accuracy": 0.6470588235294118,
+      "eval_loss": 0.7130866646766663,
+      "eval_runtime": 0.1511,
+      "eval_samples_per_second": 112.526,
+      "eval_steps_per_second": 33.096,
       "step": 20
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.5294117647058824,
-      "eval_loss": 0.7119423747062683,
-      "eval_runtime": 0.1899,
-      "eval_samples_per_second": 89.52,
-      "eval_steps_per_second": 26.329,
+      "eval_accuracy": 0.6470588235294118,
+      "eval_loss": 0.7157571315765381,
+      "eval_runtime": 0.1508,
+      "eval_samples_per_second": 112.708,
+      "eval_steps_per_second": 33.149,
       "step": 24
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.5882352941176471,
-      "eval_loss": 0.7085601091384888,
-      "eval_runtime": 0.1459,
-      "eval_samples_per_second": 116.502,
-      "eval_steps_per_second": 34.265,
+      "eval_accuracy": 0.7647058823529411,
+      "eval_loss": 0.6532735228538513,
+      "eval_runtime": 0.1506,
+      "eval_samples_per_second": 112.877,
+      "eval_steps_per_second": 33.199,
       "step": 28
     },
     {
       "epoch": 7.5,
-      "learning_rate": 2.777777777777778e-05,
-      "loss": 0.5786,
+      "learning_rate": 1.388888888888889e-05,
+      "loss": 0.363,
       "step": 30
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.5882352941176471,
-      "eval_loss": 0.6967045068740845,
-      "eval_runtime": 0.1479,
-      "eval_samples_per_second": 114.916,
-      "eval_steps_per_second": 33.799,
+      "eval_accuracy": 0.7058823529411765,
+      "eval_loss": 0.6210929155349731,
+      "eval_runtime": 0.1672,
+      "eval_samples_per_second": 101.678,
+      "eval_steps_per_second": 29.905,
       "step": 32
     },
     {
       "epoch": 9.0,
-      "eval_accuracy": 0.6470588235294118,
-      "eval_loss": 0.6773281097412109,
-      "eval_runtime": 0.1449,
-      "eval_samples_per_second": 117.312,
-      "eval_steps_per_second": 34.504,
+      "eval_accuracy": 0.7647058823529411,
+      "eval_loss": 0.6221739649772644,
+      "eval_runtime": 0.1853,
+      "eval_samples_per_second": 91.73,
+      "eval_steps_per_second": 26.979,
       "step": 36
     },
     {
       "epoch": 10.0,
-      "learning_rate": 1.8518518518518518e-05,
-      "loss": 0.5026,
+      "learning_rate": 0.0,
+      "loss": 0.3207,
       "step": 40
     },
     {
       "epoch": 10.0,
       "eval_accuracy": 0.7647058823529411,
-      "eval_loss": 0.6537247896194458,
-      "eval_runtime": 0.1787,
-      "eval_samples_per_second": 95.157,
-      "eval_steps_per_second": 27.987,
+      "eval_loss": 0.6255453824996948,
+      "eval_runtime": 0.1847,
+      "eval_samples_per_second": 92.059,
+      "eval_steps_per_second": 27.076,
       "step": 40
     },
     {
-      "epoch": 11.0,
-      "eval_accuracy": 0.7647058823529411,
-      "eval_loss": 0.6439494490623474,
-      "eval_runtime": 0.1774,
-      "eval_samples_per_second": 95.855,
-      "eval_steps_per_second": 28.193,
-      "step": 44
-    },
-    {
-      "epoch": 12.0,
-      "eval_accuracy": 0.7647058823529411,
-      "eval_loss": 0.6389846205711365,
-      "eval_runtime": 0.155,
-      "eval_samples_per_second": 109.699,
-      "eval_steps_per_second": 32.264,
-      "step": 48
-    },
-    {
-      "epoch": 12.5,
-      "learning_rate": 9.259259259259259e-06,
-      "loss": 0.5086,
-      "step": 50
-    },
-    {
-      "epoch": 13.0,
-      "eval_accuracy": 0.7647058823529411,
-      "eval_loss": 0.6434133052825928,
-      "eval_runtime": 0.1482,
-      "eval_samples_per_second": 114.73,
-      "eval_steps_per_second": 33.744,
-      "step": 52
-    },
-    {
-      "epoch": 14.0,
-      "eval_accuracy": 0.7647058823529411,
-      "eval_loss": 0.6424618363380432,
-      "eval_runtime": 0.1541,
-      "eval_samples_per_second": 110.305,
-      "eval_steps_per_second": 32.443,
-      "step": 56
-    },
-    {
-      "epoch": 15.0,
-      "learning_rate": 0.0,
-      "loss": 0.448,
-      "step": 60
-    },
-    {
-      "epoch": 15.0,
-      "eval_accuracy": 0.7647058823529411,
-      "eval_loss": 0.645173192024231,
-      "eval_runtime": 0.1497,
-      "eval_samples_per_second": 113.564,
-      "eval_steps_per_second": 33.401,
-      "step": 60
-    },
-    {
-      "epoch": 15.0,
-      "step": 60,
-      "total_flos": 2.412253290037248e+16,
-      "train_loss": 0.5445812543233236,
-      "train_runtime": 64.3122,
-      "train_samples_per_second": 14.927,
-      "train_steps_per_second": 0.933
+      "epoch": 10.0,
+      "step": 40,
+      "total_flos": 1.608168860024832e+16,
+      "train_loss": 0.36969062089920046,
+      "train_runtime": 46.5,
+      "train_samples_per_second": 13.763,
+      "train_steps_per_second": 0.86
     }
   ],
-  "max_steps": 60,
-  "num_train_epochs": 15,
-  "total_flos": 2.412253290037248e+16,
+  "max_steps": 40,
+  "num_train_epochs": 10,
+  "total_flos": 1.608168860024832e+16,
   "trial_name": null,
   "trial_params": null
 }