Training in progress, epoch 1

all_results.json

@@ -6,8 +6,8 @@
     "eval_samples_per_second": 86.013,
     "eval_steps_per_second": 21.503,
     "total_flos": 1.583041221586944e+16,
-    "train_loss": 0.4837726652622223,
-    "train_runtime": 41.4007,
-    "train_samples_per_second": 15.217,
-    "train_steps_per_second": 0.966
+    "train_loss": 0.6278304576873779,
+    "train_runtime": 51.4123,
+    "train_samples_per_second": 12.254,
+    "train_steps_per_second": 0.778
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76aac07035d0bf55a59bc86f0420629de8ae74dc673ea5ea8e907d1ed9d7fc31
+oid sha256:727d603ceea024febde4faa0e6f92c89f481fbe52fa4402e540dc402c70a5baf
 size 111349029

runs/May27_21-05-28_0922109e5cf6/1685221531.0906715/events.out.tfevents.1685221531.0922109e5cf6.8213.25

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a36c00322078dda0181539359e2e4372e180f9004ea74d928274fc0a74d5dfe7
+size 5949

runs/May27_21-05-28_0922109e5cf6/events.out.tfevents.1685221531.0922109e5cf6.8213.24

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48d016292dd9e2c7916bc06dd1c00bb224c4381a5d804f3d62344be44208a527
+size 4531

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 10.0,
     "total_flos": 1.583041221586944e+16,
-    "train_loss": 0.4837726652622223,
-    "train_runtime": 41.4007,
-    "train_samples_per_second": 15.217,
-    "train_steps_per_second": 0.966
+    "train_loss": 0.6278304576873779,
+    "train_runtime": 51.4123,
+    "train_samples_per_second": 12.254,
+    "train_steps_per_second": 0.778
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.875,
-  "best_model_checkpoint": "convnext-tiny-224-drfx-surgery-classifier/checkpoint-8",
+  "best_metric": 0.625,
+  "best_model_checkpoint": "convnext-tiny-224-drfx-surgery-classifier/checkpoint-16",
   "epoch": 10.0,
   "global_step": 40,
   "is_hyper_param_search": false,
@@ -9,126 +9,126 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6875,
-      "eval_loss": 0.6467709541320801,
-      "eval_runtime": 0.1396,
-      "eval_samples_per_second": 114.574,
-      "eval_steps_per_second": 28.643,
+      "eval_accuracy": 0.5625,
+      "eval_loss": 0.6742807626724243,
+      "eval_runtime": 0.1742,
+      "eval_samples_per_second": 91.859,
+      "eval_steps_per_second": 22.965,
       "step": 4
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.875,
-      "eval_loss": 0.4960244596004486,
-      "eval_runtime": 0.2812,
-      "eval_samples_per_second": 56.9,
-      "eval_steps_per_second": 14.225,
+      "eval_accuracy": 0.5625,
+      "eval_loss": 0.6683036088943481,
+      "eval_runtime": 0.2648,
+      "eval_samples_per_second": 60.432,
+      "eval_steps_per_second": 15.108,
       "step": 8
     },
     {
       "epoch": 2.5,
-      "learning_rate": 4.166666666666667e-05,
-      "loss": 0.6461,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 0.649,
       "step": 10
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.875,
-      "eval_loss": 0.4355894923210144,
-      "eval_runtime": 0.2068,
-      "eval_samples_per_second": 77.351,
-      "eval_steps_per_second": 19.338,
+      "eval_accuracy": 0.5625,
+      "eval_loss": 0.6634215116500854,
+      "eval_runtime": 0.1434,
+      "eval_samples_per_second": 111.587,
+      "eval_steps_per_second": 27.897,
       "step": 12
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.875,
-      "eval_loss": 0.3915722072124481,
-      "eval_runtime": 0.1349,
-      "eval_samples_per_second": 118.579,
-      "eval_steps_per_second": 29.645,
+      "eval_accuracy": 0.625,
+      "eval_loss": 0.6593766808509827,
+      "eval_runtime": 0.1368,
+      "eval_samples_per_second": 116.941,
+      "eval_steps_per_second": 29.235,
       "step": 16
     },
     {
       "epoch": 5.0,
-      "learning_rate": 2.777777777777778e-05,
-      "loss": 0.4586,
+      "learning_rate": 5.555555555555555e-07,
+      "loss": 0.6178,
       "step": 20
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.875,
-      "eval_loss": 0.3885435461997986,
-      "eval_runtime": 0.1295,
-      "eval_samples_per_second": 123.544,
-      "eval_steps_per_second": 30.886,
+      "eval_accuracy": 0.625,
+      "eval_loss": 0.656198263168335,
+      "eval_runtime": 0.2701,
+      "eval_samples_per_second": 59.234,
+      "eval_steps_per_second": 14.808,
       "step": 20
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.875,
-      "eval_loss": 0.38064631819725037,
-      "eval_runtime": 0.1351,
-      "eval_samples_per_second": 118.447,
-      "eval_steps_per_second": 29.612,
+      "eval_accuracy": 0.625,
+      "eval_loss": 0.6535187363624573,
+      "eval_runtime": 0.1357,
+      "eval_samples_per_second": 117.874,
+      "eval_steps_per_second": 29.468,
       "step": 24
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.875,
-      "eval_loss": 0.3729676604270935,
-      "eval_runtime": 0.1372,
-      "eval_samples_per_second": 116.595,
-      "eval_steps_per_second": 29.149,
+      "eval_accuracy": 0.5625,
+      "eval_loss": 0.6514049768447876,
+      "eval_runtime": 0.1802,
+      "eval_samples_per_second": 88.8,
+      "eval_steps_per_second": 22.2,
       "step": 28
     },
     {
       "epoch": 7.5,
-      "learning_rate": 1.388888888888889e-05,
-      "loss": 0.3969,
+      "learning_rate": 2.7777777777777776e-07,
+      "loss": 0.6236,
       "step": 30
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.875,
-      "eval_loss": 0.3685373067855835,
-      "eval_runtime": 0.1332,
-      "eval_samples_per_second": 120.143,
-      "eval_steps_per_second": 30.036,
+      "eval_accuracy": 0.5625,
+      "eval_loss": 0.649865448474884,
+      "eval_runtime": 0.1601,
+      "eval_samples_per_second": 99.945,
+      "eval_steps_per_second": 24.986,
       "step": 32
     },
     {
       "epoch": 9.0,
-      "eval_accuracy": 0.875,
-      "eval_loss": 0.3655328154563904,
-      "eval_runtime": 0.169,
-      "eval_samples_per_second": 94.697,
-      "eval_steps_per_second": 23.674,
+      "eval_accuracy": 0.5625,
+      "eval_loss": 0.648896336555481,
+      "eval_runtime": 0.2183,
+      "eval_samples_per_second": 73.288,
+      "eval_steps_per_second": 18.322,
       "step": 36
     },
     {
       "epoch": 10.0,
       "learning_rate": 0.0,
-      "loss": 0.4335,
+      "loss": 0.621,
       "step": 40
     },
     {
       "epoch": 10.0,
-      "eval_accuracy": 0.875,
-      "eval_loss": 0.36532726883888245,
-      "eval_runtime": 0.1343,
-      "eval_samples_per_second": 119.146,
-      "eval_steps_per_second": 29.786,
+      "eval_accuracy": 0.5625,
+      "eval_loss": 0.6485264897346497,
+      "eval_runtime": 0.1395,
+      "eval_samples_per_second": 114.686,
+      "eval_steps_per_second": 28.672,
       "step": 40
     },
     {
       "epoch": 10.0,
       "step": 40,
       "total_flos": 1.583041221586944e+16,
-      "train_loss": 0.4837726652622223,
-      "train_runtime": 41.4007,
-      "train_samples_per_second": 15.217,
-      "train_steps_per_second": 0.966
+      "train_loss": 0.6278304576873779,
+      "train_runtime": 51.4123,
+      "train_samples_per_second": 12.254,
+      "train_steps_per_second": 0.778
     }
   ],
   "max_steps": 40,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95a73c2826fec298fed7b5f439180d56cf54d9ed76f341d9b98001a39889bed6
+oid sha256:af67709ce9988745a26b4af07d220b26aed77bc68e74c8007253fca9ee38f462
 size 3643