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": 0.16534085315570496,
-    "train_runtime": 2881.0155,
-    "train_samples_per_second": 3.166,
+    "train_loss": 0.1656334604087629,
+    "train_runtime": 2889.8629,
+    "train_samples_per_second": 3.156,
     "train_steps_per_second": 0.099
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb5929be228688edfb47cac0edbc4d0a48269639dc17047c66141e0186d347de
+oid sha256:42c69d6d3c969d364c985ba4aef7324f92c91fb0bdc63a9ed518604757cef22e
 size 343223968

runs/Jul23_16-54-06_REDLGLAUCORE01/events.out.tfevents.1721781780.REDLGLAUCORE01.547362.27

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aec619a9592916052aa286c887dbc432b59dfbce58848ec2759e1d3e5dec694
+size 1057

runs/Jul24_12-35-53_REDLGLAUCORE01/events.out.tfevents.1721849754.REDLGLAUCORE01.547362.29

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09e91d65c6b37dec73fdb48a7c7c44eef0a54454e999c3607a59bdec31512694
+size 7437

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
     "total_flos": 7.020774259082035e+17,
-    "train_loss": 0.16534085315570496,
-    "train_runtime": 2881.0155,
-    "train_samples_per_second": 3.166,
+    "train_loss": 0.1656334604087629,
+    "train_runtime": 2889.8629,
+    "train_samples_per_second": 3.156,
     "train_steps_per_second": 0.099
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.1165604442358017,
+  "best_metric": 0.11656656116247177,
   "best_model_checkpoint": "/home/projects/Project - Fundus Photo Glaucoma Detection (AI)//model_results/vit-base-gpu/checkpoint-200",
   "epoch": 5.0,
   "eval_steps": 100,
@@ -10,72 +10,72 @@
   "log_history": [
     {
       "epoch": 0.17543859649122806,
-      "grad_norm": 1.276576280593872,
+      "grad_norm": 1.2793735265731812,
       "learning_rate": 9.649122807017545e-06,
       "loss": 0.6232,
       "step": 10
     },
     {
       "epoch": 0.3508771929824561,
-      "grad_norm": 1.7653321027755737,
+      "grad_norm": 1.7450703382492065,
       "learning_rate": 9.298245614035088e-06,
-      "loss": 0.4728,
+      "loss": 0.4729,
       "step": 20
     },
     {
       "epoch": 0.5263157894736842,
-      "grad_norm": 1.3592791557312012,
+      "grad_norm": 1.4280253648757935,
       "learning_rate": 8.947368421052632e-06,
-      "loss": 0.3828,
+      "loss": 0.3831,
       "step": 30
     },
     {
       "epoch": 0.7017543859649122,
-      "grad_norm": 1.5831280946731567,
+      "grad_norm": 1.5422084331512451,
       "learning_rate": 8.596491228070176e-06,
-      "loss": 0.3042,
+      "loss": 0.3052,
       "step": 40
     },
     {
       "epoch": 0.8771929824561403,
-      "grad_norm": 1.1694388389587402,
+      "grad_norm": 1.118567943572998,
       "learning_rate": 8.24561403508772e-06,
-      "loss": 0.2862,
+      "loss": 0.2872,
       "step": 50
     },
     {
       "epoch": 1.0526315789473684,
-      "grad_norm": 0.819071888923645,
+      "grad_norm": 0.8227060437202454,
       "learning_rate": 7.894736842105265e-06,
-      "loss": 0.2171,
+      "loss": 0.2179,
       "step": 60
     },
     {
       "epoch": 1.2280701754385965,
-      "grad_norm": 0.6716095805168152,
+      "grad_norm": 0.6690755486488342,
       "learning_rate": 7.5438596491228074e-06,
-      "loss": 0.2047,
+      "loss": 0.2056,
       "step": 70
     },
     {
       "epoch": 1.4035087719298245,
-      "grad_norm": 1.2074573040008545,
+      "grad_norm": 1.198415756225586,
       "learning_rate": 7.192982456140352e-06,
-      "loss": 0.1821,
+      "loss": 0.1825,
       "step": 80
     },
     {
       "epoch": 1.5789473684210527,
-      "grad_norm": 0.7754034399986267,
+      "grad_norm": 0.763924777507782,
       "learning_rate": 6.842105263157896e-06,
-      "loss": 0.1557,
+      "loss": 0.1564,
       "step": 90
     },
     {
       "epoch": 1.7543859649122808,
-      "grad_norm": 0.45100048184394836,
+      "grad_norm": 0.4554818570613861,
       "learning_rate": 6.491228070175439e-06,
-      "loss": 0.1492,
+      "loss": 0.1496,
       "step": 100
     },
     {
@@ -91,164 +91,164 @@
           161
         ]
       ],
-      "eval_loss": 0.17834381759166718,
-      "eval_runtime": 25.1043,
-      "eval_samples_per_second": 9.042,
-      "eval_steps_per_second": 0.319,
+      "eval_loss": 0.17874090373516083,
+      "eval_runtime": 24.3384,
+      "eval_samples_per_second": 9.327,
+      "eval_steps_per_second": 0.329,
       "step": 100
     },
     {
       "epoch": 1.9298245614035088,
-      "grad_norm": 4.859443664550781,
+      "grad_norm": 4.51282262802124,
       "learning_rate": 6.140350877192983e-06,
-      "loss": 0.1439,
+      "loss": 0.1444,
       "step": 110
     },
     {
       "epoch": 2.1052631578947367,
-      "grad_norm": 0.47108176350593567,
+      "grad_norm": 0.47525253891944885,
       "learning_rate": 5.789473684210527e-06,
-      "loss": 0.1275,
+      "loss": 0.1274,
       "step": 120
     },
     {
       "epoch": 2.280701754385965,
-      "grad_norm": 0.4304533898830414,
+      "grad_norm": 0.4660364091396332,
       "learning_rate": 5.438596491228071e-06,
       "loss": 0.1291,
       "step": 130
     },
     {
       "epoch": 2.456140350877193,
-      "grad_norm": 0.5671774744987488,
+      "grad_norm": 0.5069414973258972,
       "learning_rate": 5.087719298245615e-06,
-      "loss": 0.0898,
+      "loss": 0.0901,
       "step": 140
     },
     {
       "epoch": 2.6315789473684212,
-      "grad_norm": 0.36146485805511475,
+      "grad_norm": 0.36069270968437195,
       "learning_rate": 4.736842105263158e-06,
-      "loss": 0.0999,
+      "loss": 0.0998,
       "step": 150
     },
     {
       "epoch": 2.807017543859649,
-      "grad_norm": 0.4231085777282715,
+      "grad_norm": 0.4235830008983612,
       "learning_rate": 4.385964912280702e-06,
-      "loss": 0.0927,
+      "loss": 0.0929,
       "step": 160
     },
     {
       "epoch": 2.982456140350877,
-      "grad_norm": 2.568676471710205,
+      "grad_norm": 1.640547275543213,
       "learning_rate": 4.035087719298246e-06,
-      "loss": 0.0907,
+      "loss": 0.0905,
       "step": 170
     },
     {
       "epoch": 3.1578947368421053,
-      "grad_norm": 0.3344823718070984,
+      "grad_norm": 0.33297139406204224,
       "learning_rate": 3.6842105263157896e-06,
-      "loss": 0.0977,
+      "loss": 0.0982,
       "step": 180
     },
     {
       "epoch": 3.3333333333333335,
-      "grad_norm": 0.36377760767936707,
+      "grad_norm": 0.3522562086582184,
       "learning_rate": 3.3333333333333333e-06,
-      "loss": 0.0885,
+      "loss": 0.0889,
       "step": 190
     },
     {
       "epoch": 3.5087719298245617,
-      "grad_norm": 0.5525999665260315,
+      "grad_norm": 0.5093055367469788,
       "learning_rate": 2.9824561403508774e-06,
-      "loss": 0.1,
+      "loss": 0.1002,
       "step": 200
     },
     {
       "epoch": 3.5087719298245617,
-      "eval_accuracy": 0.973568281938326,
+      "eval_accuracy": 0.9779735682819384,
       "eval_confusion_matrix": [
         [
-          60,
-          6
+          61,
+          5
         ],
         [
           0,
           161
         ]
       ],
-      "eval_loss": 0.1165604442358017,
-      "eval_runtime": 23.3236,
-      "eval_samples_per_second": 9.733,
-      "eval_steps_per_second": 0.343,
+      "eval_loss": 0.11656656116247177,
+      "eval_runtime": 24.5633,
+      "eval_samples_per_second": 9.241,
+      "eval_steps_per_second": 0.326,
       "step": 200
     },
     {
       "epoch": 3.6842105263157894,
-      "grad_norm": 0.3867160677909851,
+      "grad_norm": 0.3924790918827057,
       "learning_rate": 2.631578947368421e-06,
-      "loss": 0.1027,
+      "loss": 0.1029,
       "step": 210
     },
     {
       "epoch": 3.8596491228070176,
-      "grad_norm": 0.4372801184654236,
+      "grad_norm": 0.43185240030288696,
       "learning_rate": 2.280701754385965e-06,
       "loss": 0.0743,
       "step": 220
     },
     {
       "epoch": 4.035087719298246,
-      "grad_norm": 0.7543017268180847,
+      "grad_norm": 0.7460317015647888,
       "learning_rate": 1.929824561403509e-06,
-      "loss": 0.1059,
+      "loss": 0.1062,
       "step": 230
     },
     {
       "epoch": 4.2105263157894735,
-      "grad_norm": 0.36244213581085205,
+      "grad_norm": 0.36178895831108093,
       "learning_rate": 1.5789473684210526e-06,
-      "loss": 0.0776,
+      "loss": 0.0778,
       "step": 240
     },
     {
       "epoch": 4.385964912280702,
-      "grad_norm": 0.29121342301368713,
+      "grad_norm": 0.2968393862247467,
       "learning_rate": 1.2280701754385965e-06,
-      "loss": 0.0614,
+      "loss": 0.0613,
       "step": 250
     },
     {
       "epoch": 4.56140350877193,
-      "grad_norm": 0.3036610186100006,
+      "grad_norm": 0.3041611611843109,
       "learning_rate": 8.771929824561404e-07,
       "loss": 0.0602,
       "step": 260
     },
     {
       "epoch": 4.7368421052631575,
-      "grad_norm": 0.2852645516395569,
+      "grad_norm": 0.2833913564682007,
       "learning_rate": 5.263157894736843e-07,
-      "loss": 0.0532,
+      "loss": 0.053,
       "step": 270
     },
     {
       "epoch": 4.912280701754386,
-      "grad_norm": 0.5596099495887756,
+      "grad_norm": 0.5582696199417114,
       "learning_rate": 1.7543859649122808e-07,
-      "loss": 0.0899,
+      "loss": 0.0901,
       "step": 280
     },
     {
       "epoch": 5.0,
       "step": 285,
       "total_flos": 7.020774259082035e+17,
-      "train_loss": 0.16534085315570496,
-      "train_runtime": 2881.0155,
-      "train_samples_per_second": 3.166,
+      "train_loss": 0.1656334604087629,
+      "train_runtime": 2889.8629,
+      "train_samples_per_second": 3.156,
       "train_steps_per_second": 0.099
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f722bf575f9d519538deb54363d1d2401de40d4e1b128427423cee166d775fea
+oid sha256:3ae01540031eccadd869cba94e0ff0b917defb0cce7137089796e57281614c9f
 size 5240