End of training

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 10.0,
     "eval_accuracy": 0.875,
-    "eval_loss": 0.4960244596004486,
-    "eval_runtime": 0.186,
-    "eval_samples_per_second": 86.013,
-    "eval_steps_per_second": 21.503,
+    "eval_loss": 0.6159822940826416,
+    "eval_runtime": 0.1862,
+    "eval_samples_per_second": 85.94,
+    "eval_steps_per_second": 21.485,
     "total_flos": 1.583041221586944e+16,
-    "train_loss": 0.6278304576873779,
-    "train_runtime": 51.4123,
-    "train_samples_per_second": 12.254,
-    "train_steps_per_second": 0.778
+    "train_loss": 0.6517677068710327,
+    "train_runtime": 52.1182,
+    "train_samples_per_second": 12.088,
+    "train_steps_per_second": 0.767
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 10.0,
     "eval_accuracy": 0.875,
-    "eval_loss": 0.4960244596004486,
-    "eval_runtime": 0.186,
-    "eval_samples_per_second": 86.013,
-    "eval_steps_per_second": 21.503
+    "eval_loss": 0.6159822940826416,
+    "eval_runtime": 0.1862,
+    "eval_samples_per_second": 85.94,
+    "eval_steps_per_second": 21.485
 }

runs/May27_21-05-28_0922109e5cf6/events.out.tfevents.1685221613.0922109e5cf6.8213.26

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7e0f98f4622ab933de81d619471a51423cd30564f75ef0467ce5c633c2927ac
+size 405

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 10.0,
     "total_flos": 1.583041221586944e+16,
-    "train_loss": 0.6278304576873779,
-    "train_runtime": 51.4123,
-    "train_samples_per_second": 12.254,
-    "train_steps_per_second": 0.778
+    "train_loss": 0.6517677068710327,
+    "train_runtime": 52.1182,
+    "train_samples_per_second": 12.088,
+    "train_steps_per_second": 0.767
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.625,
-  "best_model_checkpoint": "convnext-tiny-224-drfx-surgery-classifier/checkpoint-16",
+  "best_metric": 0.875,
+  "best_model_checkpoint": "convnext-tiny-224-drfx-surgery-classifier/checkpoint-28",
   "epoch": 10.0,
   "global_step": 40,
   "is_hyper_param_search": false,
@@ -9,126 +9,126 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5625,
-      "eval_loss": 0.6742807626724243,
-      "eval_runtime": 0.1742,
-      "eval_samples_per_second": 91.859,
-      "eval_steps_per_second": 22.965,
+      "eval_accuracy": 0.375,
+      "eval_loss": 0.7140131592750549,
+      "eval_runtime": 0.1678,
+      "eval_samples_per_second": 95.342,
+      "eval_steps_per_second": 23.836,
       "step": 4
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.5625,
-      "eval_loss": 0.6683036088943481,
-      "eval_runtime": 0.2648,
-      "eval_samples_per_second": 60.432,
-      "eval_steps_per_second": 15.108,
+      "eval_accuracy": 0.5,
+      "eval_loss": 0.6876102685928345,
+      "eval_runtime": 0.2806,
+      "eval_samples_per_second": 57.029,
+      "eval_steps_per_second": 14.257,
       "step": 8
     },
     {
       "epoch": 2.5,
-      "learning_rate": 8.333333333333333e-07,
-      "loss": 0.649,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.7104,
       "step": 10
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.5625,
-      "eval_loss": 0.6634215116500854,
-      "eval_runtime": 0.1434,
-      "eval_samples_per_second": 111.587,
-      "eval_steps_per_second": 27.897,
+      "eval_accuracy": 0.625,
+      "eval_loss": 0.6665950417518616,
+      "eval_runtime": 0.1311,
+      "eval_samples_per_second": 122.003,
+      "eval_steps_per_second": 30.501,
       "step": 12
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.625,
-      "eval_loss": 0.6593766808509827,
-      "eval_runtime": 0.1368,
-      "eval_samples_per_second": 116.941,
-      "eval_steps_per_second": 29.235,
+      "eval_accuracy": 0.6875,
+      "eval_loss": 0.6494508981704712,
+      "eval_runtime": 0.1354,
+      "eval_samples_per_second": 118.202,
+      "eval_steps_per_second": 29.55,
       "step": 16
     },
     {
       "epoch": 5.0,
-      "learning_rate": 5.555555555555555e-07,
-      "loss": 0.6178,
+      "learning_rate": 2.7777777777777783e-06,
+      "loss": 0.6567,
       "step": 20
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.625,
-      "eval_loss": 0.656198263168335,
-      "eval_runtime": 0.2701,
-      "eval_samples_per_second": 59.234,
-      "eval_steps_per_second": 14.808,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.6359503865242004,
+      "eval_runtime": 0.1374,
+      "eval_samples_per_second": 116.463,
+      "eval_steps_per_second": 29.116,
       "step": 20
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.625,
-      "eval_loss": 0.6535187363624573,
-      "eval_runtime": 0.1357,
-      "eval_samples_per_second": 117.874,
-      "eval_steps_per_second": 29.468,
+      "eval_accuracy": 0.8125,
+      "eval_loss": 0.6247015595436096,
+      "eval_runtime": 0.139,
+      "eval_samples_per_second": 115.068,
+      "eval_steps_per_second": 28.767,
       "step": 24
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.5625,
-      "eval_loss": 0.6514049768447876,
-      "eval_runtime": 0.1802,
-      "eval_samples_per_second": 88.8,
-      "eval_steps_per_second": 22.2,
+      "eval_accuracy": 0.875,
+      "eval_loss": 0.6159822940826416,
+      "eval_runtime": 0.1357,
+      "eval_samples_per_second": 117.933,
+      "eval_steps_per_second": 29.483,
       "step": 28
     },
     {
       "epoch": 7.5,
-      "learning_rate": 2.7777777777777776e-07,
-      "loss": 0.6236,
+      "learning_rate": 1.3888888888888892e-06,
+      "loss": 0.6277,
       "step": 30
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.5625,
-      "eval_loss": 0.649865448474884,
-      "eval_runtime": 0.1601,
-      "eval_samples_per_second": 99.945,
-      "eval_steps_per_second": 24.986,
+      "eval_accuracy": 0.875,
+      "eval_loss": 0.6097759008407593,
+      "eval_runtime": 0.1545,
+      "eval_samples_per_second": 103.542,
+      "eval_steps_per_second": 25.886,
       "step": 32
     },
     {
       "epoch": 9.0,
-      "eval_accuracy": 0.5625,
-      "eval_loss": 0.648896336555481,
-      "eval_runtime": 0.2183,
-      "eval_samples_per_second": 73.288,
-      "eval_steps_per_second": 18.322,
+      "eval_accuracy": 0.875,
+      "eval_loss": 0.6058341264724731,
+      "eval_runtime": 0.1381,
+      "eval_samples_per_second": 115.852,
+      "eval_steps_per_second": 28.963,
       "step": 36
     },
     {
       "epoch": 10.0,
       "learning_rate": 0.0,
-      "loss": 0.621,
+      "loss": 0.6122,
       "step": 40
     },
     {
       "epoch": 10.0,
-      "eval_accuracy": 0.5625,
-      "eval_loss": 0.6485264897346497,
-      "eval_runtime": 0.1395,
-      "eval_samples_per_second": 114.686,
-      "eval_steps_per_second": 28.672,
+      "eval_accuracy": 0.875,
+      "eval_loss": 0.6043429374694824,
+      "eval_runtime": 0.1712,
+      "eval_samples_per_second": 93.452,
+      "eval_steps_per_second": 23.363,
       "step": 40
     },
     {
       "epoch": 10.0,
       "step": 40,
       "total_flos": 1.583041221586944e+16,
-      "train_loss": 0.6278304576873779,
-      "train_runtime": 51.4123,
-      "train_samples_per_second": 12.254,
-      "train_steps_per_second": 0.778
+      "train_loss": 0.6517677068710327,
+      "train_runtime": 52.1182,
+      "train_samples_per_second": 12.088,
+      "train_steps_per_second": 0.767
     }
   ],
   "max_steps": 40,