Training in progress, step 100

all_results.json

@@ -5,8 +5,8 @@
     "eval_samples_per_second": 9.337,
     "eval_steps_per_second": 0.294,
     "total_flos": 7.020774259082035e+17,
-    "train_loss": 0.1656212309996287,
-    "train_runtime": 2867.8524,
-    "train_samples_per_second": 3.18,
-    "train_steps_per_second": 0.099
+    "train_loss": 0.16555590545921994,
+    "train_runtime": 2847.4829,
+    "train_samples_per_second": 3.203,
+    "train_steps_per_second": 0.1
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05fd49c6037d2f62dd8489eba979b382b8825dc0beaa8e8f5cad144d4d674681
+oid sha256:62d7bce78b668077b9aa0e60ee9b69b9447194a5837ad3b8c4280f26ba859cac
 size 343223968

runs/Sep11_08-54-13_REDLGLAUCORE01/events.out.tfevents.1726072954.REDLGLAUCORE01.3667144.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:882a42db644ab9bef877cf9401b6527a4173959dcb196921d31ba94b4970b546
+size 1057

runs/Sep18_11-12-19_REDLGLAUCORE01/events.out.tfevents.1726683139.REDLGLAUCORE01.3667144.19

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76050df0eca0ece6ae93c898b216320730b9810e4049870de306396e577763ef
+size 7437

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
     "total_flos": 7.020774259082035e+17,
-    "train_loss": 0.1656212309996287,
-    "train_runtime": 2867.8524,
-    "train_samples_per_second": 3.18,
-    "train_steps_per_second": 0.099
+    "train_loss": 0.16555590545921994,
+    "train_runtime": 2847.4829,
+    "train_samples_per_second": 3.203,
+    "train_steps_per_second": 0.1
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.11660724878311157,
+  "best_metric": 0.1169881522655487,
   "best_model_checkpoint": "/home/projects/Project - Fundus Photo Glaucoma Detection (AI)//model_results/vit-base-gpu/checkpoint-200",
   "epoch": 5.0,
   "eval_steps": 100,
@@ -24,58 +24,58 @@
     },
     {
       "epoch": 0.5263157894736842,
-      "grad_norm": 1.3600224256515503,
+      "grad_norm": 1.360029697418213,
       "learning_rate": 8.947368421052632e-06,
       "loss": 0.3828,
       "step": 30
     },
     {
       "epoch": 0.7017543859649122,
-      "grad_norm": 1.4679501056671143,
+      "grad_norm": 1.4675012826919556,
       "learning_rate": 8.596491228070176e-06,
       "loss": 0.3044,
       "step": 40
     },
     {
       "epoch": 0.8771929824561403,
-      "grad_norm": 1.1724063158035278,
+      "grad_norm": 1.1715320348739624,
       "learning_rate": 8.24561403508772e-06,
       "loss": 0.2862,
       "step": 50
     },
     {
       "epoch": 1.0526315789473684,
-      "grad_norm": 0.8161798715591431,
+      "grad_norm": 0.816554844379425,
       "learning_rate": 7.894736842105265e-06,
-      "loss": 0.217,
+      "loss": 0.2171,
       "step": 60
     },
     {
       "epoch": 1.2280701754385965,
-      "grad_norm": 0.6667922735214233,
+      "grad_norm": 0.7754776477813721,
       "learning_rate": 7.5438596491228074e-06,
-      "loss": 0.2047,
+      "loss": 0.2057,
       "step": 70
     },
     {
       "epoch": 1.4035087719298245,
-      "grad_norm": 1.1511715650558472,
+      "grad_norm": 1.184274435043335,
       "learning_rate": 7.192982456140352e-06,
-      "loss": 0.1821,
+      "loss": 0.1824,
       "step": 80
     },
     {
       "epoch": 1.5789473684210527,
-      "grad_norm": 0.8299317359924316,
+      "grad_norm": 0.7909060716629028,
       "learning_rate": 6.842105263157896e-06,
-      "loss": 0.1556,
+      "loss": 0.156,
       "step": 90
     },
     {
       "epoch": 1.7543859649122808,
-      "grad_norm": 0.4476878046989441,
+      "grad_norm": 0.45461058616638184,
       "learning_rate": 6.491228070175439e-06,
-      "loss": 0.1493,
+      "loss": 0.1494,
       "step": 100
     },
     {
@@ -91,165 +91,165 @@
           161
         ]
       ],
-      "eval_loss": 0.1793680638074875,
-      "eval_runtime": 24.285,
-      "eval_samples_per_second": 9.347,
-      "eval_steps_per_second": 0.329,
+      "eval_loss": 0.17945599555969238,
+      "eval_runtime": 25.2577,
+      "eval_samples_per_second": 8.987,
+      "eval_steps_per_second": 0.317,
       "step": 100
     },
     {
       "epoch": 1.9298245614035088,
-      "grad_norm": 5.393967151641846,
+      "grad_norm": 5.456608295440674,
       "learning_rate": 6.140350877192983e-06,
-      "loss": 0.1456,
+      "loss": 0.1443,
       "step": 110
     },
     {
       "epoch": 2.1052631578947367,
-      "grad_norm": 0.469459593296051,
+      "grad_norm": 0.4778239130973816,
       "learning_rate": 5.789473684210527e-06,
-      "loss": 0.1277,
+      "loss": 0.1275,
       "step": 120
     },
     {
       "epoch": 2.280701754385965,
-      "grad_norm": 0.42347291111946106,
+      "grad_norm": 0.427962064743042,
       "learning_rate": 5.438596491228071e-06,
-      "loss": 0.1297,
+      "loss": 0.1289,
       "step": 130
     },
     {
       "epoch": 2.456140350877193,
-      "grad_norm": 0.490871787071228,
+      "grad_norm": 0.49317681789398193,
       "learning_rate": 5.087719298245615e-06,
-      "loss": 0.0897,
+      "loss": 0.0903,
       "step": 140
     },
     {
       "epoch": 2.6315789473684212,
-      "grad_norm": 0.3595890402793884,
+      "grad_norm": 0.36226317286491394,
       "learning_rate": 4.736842105263158e-06,
-      "loss": 0.0999,
+      "loss": 0.1,
       "step": 150
     },
     {
       "epoch": 2.807017543859649,
-      "grad_norm": 0.4167119562625885,
+      "grad_norm": 0.4284095764160156,
       "learning_rate": 4.385964912280702e-06,
-      "loss": 0.0926,
+      "loss": 0.0927,
       "step": 160
     },
     {
       "epoch": 2.982456140350877,
-      "grad_norm": 2.0740127563476562,
+      "grad_norm": 2.2354979515075684,
       "learning_rate": 4.035087719298246e-06,
       "loss": 0.0909,
       "step": 170
     },
     {
       "epoch": 3.1578947368421053,
-      "grad_norm": 0.34823891520500183,
+      "grad_norm": 0.33503246307373047,
       "learning_rate": 3.6842105263157896e-06,
-      "loss": 0.0983,
+      "loss": 0.0981,
       "step": 180
     },
     {
       "epoch": 3.3333333333333335,
-      "grad_norm": 0.3568525016307831,
+      "grad_norm": 0.3614230155944824,
       "learning_rate": 3.3333333333333333e-06,
-      "loss": 0.0895,
+      "loss": 0.0889,
       "step": 190
     },
     {
       "epoch": 3.5087719298245617,
-      "grad_norm": 0.5340443849563599,
+      "grad_norm": 0.48562532663345337,
       "learning_rate": 2.9824561403508774e-06,
-      "loss": 0.1001,
+      "loss": 0.1006,
       "step": 200
     },
     {
       "epoch": 3.5087719298245617,
-      "eval_accuracy": 0.9779735682819384,
+      "eval_accuracy": 0.973568281938326,
       "eval_confusion_matrix": [
         [
-          61,
-          5
+          60,
+          6
         ],
         [
           0,
           161
         ]
       ],
-      "eval_loss": 0.11660724878311157,
-      "eval_runtime": 24.305,
-      "eval_samples_per_second": 9.34,
-      "eval_steps_per_second": 0.329,
+      "eval_loss": 0.1169881522655487,
+      "eval_runtime": 25.5218,
+      "eval_samples_per_second": 8.894,
+      "eval_steps_per_second": 0.313,
       "step": 200
     },
     {
       "epoch": 3.6842105263157894,
-      "grad_norm": 0.38332486152648926,
+      "grad_norm": 0.38694825768470764,
       "learning_rate": 2.631578947368421e-06,
       "loss": 0.103,
       "step": 210
     },
     {
       "epoch": 3.8596491228070176,
-      "grad_norm": 0.661551296710968,
+      "grad_norm": 0.4382840096950531,
       "learning_rate": 2.280701754385965e-06,
-      "loss": 0.0742,
+      "loss": 0.0743,
       "step": 220
     },
     {
       "epoch": 4.035087719298246,
-      "grad_norm": 0.7470467686653137,
+      "grad_norm": 0.756301999092102,
       "learning_rate": 1.929824561403509e-06,
-      "loss": 0.1082,
+      "loss": 0.1059,
       "step": 230
     },
     {
       "epoch": 4.2105263157894735,
-      "grad_norm": 0.360360324382782,
+      "grad_norm": 0.3622179925441742,
       "learning_rate": 1.5789473684210526e-06,
-      "loss": 0.078,
+      "loss": 0.0779,
       "step": 240
     },
     {
       "epoch": 4.385964912280702,
-      "grad_norm": 0.29448771476745605,
+      "grad_norm": 0.2922267019748688,
       "learning_rate": 1.2280701754385965e-06,
       "loss": 0.0614,
       "step": 250
     },
     {
       "epoch": 4.56140350877193,
-      "grad_norm": 0.29900696873664856,
+      "grad_norm": 0.29758143424987793,
       "learning_rate": 8.771929824561404e-07,
-      "loss": 0.0602,
+      "loss": 0.0603,
       "step": 260
     },
     {
       "epoch": 4.7368421052631575,
-      "grad_norm": 0.2832123339176178,
+      "grad_norm": 0.28573909401893616,
       "learning_rate": 5.263157894736843e-07,
-      "loss": 0.0529,
+      "loss": 0.0538,
       "step": 270
     },
     {
       "epoch": 4.912280701754386,
-      "grad_norm": 0.5533156991004944,
+      "grad_norm": 0.556418240070343,
       "learning_rate": 1.7543859649122808e-07,
-      "loss": 0.0906,
+      "loss": 0.0902,
       "step": 280
     },
     {
       "epoch": 5.0,
       "step": 285,
       "total_flos": 7.020774259082035e+17,
-      "train_loss": 0.1656212309996287,
-      "train_runtime": 2867.8524,
-      "train_samples_per_second": 3.18,
-      "train_steps_per_second": 0.099
+      "train_loss": 0.16555590545921994,
+      "train_runtime": 2847.4829,
+      "train_samples_per_second": 3.203,
+      "train_steps_per_second": 0.1
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73efdb6ee7ebf7b3727fc9398858b9ed1c22d8e58088a72231906727d5570500
+oid sha256:0a9cbfda4497da1135d2849b838bca022560bd69b7ee12748bbd45d4341ce28a
 size 5240