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": 0.1523371622227786,
-    "train_runtime": 2876.4334,
-    "train_samples_per_second": 3.171,
+    "train_loss": 0.15312039318837617,
+    "train_runtime": 2880.1419,
+    "train_samples_per_second": 3.167,
     "train_steps_per_second": 0.099
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66f7c51971db0d9e7dc12bd50d2a1b91503b1456c24af0c7f6e182963f2b9147
+oid sha256:591988df34c16164a1078c56597b03e0714a91106f956ecb2b09c1ef03fa245a
 size 343223968

runs/Jul22_13-10-21_REDLGLAUCORE01/events.out.tfevents.1721681943.REDLGLAUCORE01.547362.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deffca7aeffc3169bf84c9a801c6a0e2d63089ea58d249e61741806987a4ec93
+size 1380

runs/Jul22_15-39-52_REDLGLAUCORE01/events.out.tfevents.1721687993.REDLGLAUCORE01.547362.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07b7285932a9e7e891a21fc7ed83c8812b6d2cce3921cb974cb6d2df0489a0ab
+size 7437

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
     "total_flos": 7.020774259082035e+17,
-    "train_loss": 0.1523371622227786,
-    "train_runtime": 2876.4334,
-    "train_samples_per_second": 3.171,
+    "train_loss": 0.15312039318837617,
+    "train_runtime": 2880.1419,
+    "train_samples_per_second": 3.167,
     "train_steps_per_second": 0.099
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.11359766870737076,
+  "best_metric": 0.1123642697930336,
   "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": 1.4138859510421753,
+      "grad_norm": 1.4138169288635254,
       "learning_rate": 9.649122807017545e-06,
       "loss": 0.5957,
       "step": 10
     },
     {
       "epoch": 0.3508771929824561,
-      "grad_norm": 1.6238865852355957,
+      "grad_norm": 1.6343547105789185,
       "learning_rate": 9.298245614035088e-06,
       "loss": 0.4704,
       "step": 20
     },
     {
       "epoch": 0.5263157894736842,
-      "grad_norm": 1.1839267015457153,
+      "grad_norm": 1.1984628438949585,
       "learning_rate": 8.947368421052632e-06,
-      "loss": 0.3787,
+      "loss": 0.3792,
       "step": 30
     },
     {
       "epoch": 0.7017543859649122,
-      "grad_norm": 1.2619974613189697,
+      "grad_norm": 1.2228361368179321,
       "learning_rate": 8.596491228070176e-06,
-      "loss": 0.2969,
+      "loss": 0.3013,
       "step": 40
     },
     {
       "epoch": 0.8771929824561403,
-      "grad_norm": 1.7304680347442627,
+      "grad_norm": 1.6350319385528564,
       "learning_rate": 8.24561403508772e-06,
-      "loss": 0.2624,
+      "loss": 0.267,
       "step": 50
     },
     {
       "epoch": 1.0526315789473684,
-      "grad_norm": 0.7326079607009888,
+      "grad_norm": 0.7450676560401917,
       "learning_rate": 7.894736842105265e-06,
-      "loss": 0.1852,
+      "loss": 0.189,
       "step": 60
     },
     {
       "epoch": 1.2280701754385965,
-      "grad_norm": 0.6521451473236084,
+      "grad_norm": 0.6679130792617798,
       "learning_rate": 7.5438596491228074e-06,
-      "loss": 0.1707,
+      "loss": 0.1731,
       "step": 70
     },
     {
       "epoch": 1.4035087719298245,
-      "grad_norm": 0.6134852170944214,
+      "grad_norm": 0.6309726238250732,
       "learning_rate": 7.192982456140352e-06,
-      "loss": 0.146,
+      "loss": 0.1479,
       "step": 80
     },
     {
       "epoch": 1.5789473684210527,
-      "grad_norm": 0.5536946654319763,
+      "grad_norm": 0.5439296960830688,
       "learning_rate": 6.842105263157896e-06,
-      "loss": 0.118,
+      "loss": 0.1194,
       "step": 90
     },
     {
       "epoch": 1.7543859649122808,
-      "grad_norm": 2.3261914253234863,
+      "grad_norm": 2.2208399772644043,
       "learning_rate": 6.491228070175439e-06,
-      "loss": 0.1251,
+      "loss": 0.1265,
       "step": 100
     },
     {
@@ -91,80 +91,80 @@
           161
         ]
       ],
-      "eval_loss": 0.15179260075092316,
-      "eval_runtime": 23.7153,
-      "eval_samples_per_second": 9.572,
-      "eval_steps_per_second": 0.337,
+      "eval_loss": 0.15117686986923218,
+      "eval_runtime": 24.8749,
+      "eval_samples_per_second": 9.126,
+      "eval_steps_per_second": 0.322,
       "step": 100
     },
     {
       "epoch": 1.9298245614035088,
-      "grad_norm": 2.69319748878479,
+      "grad_norm": 4.325542449951172,
       "learning_rate": 6.140350877192983e-06,
-      "loss": 0.1267,
+      "loss": 0.1281,
       "step": 110
     },
     {
       "epoch": 2.1052631578947367,
-      "grad_norm": 0.406830370426178,
+      "grad_norm": 0.43080058693885803,
       "learning_rate": 5.789473684210527e-06,
-      "loss": 0.0962,
+      "loss": 0.0971,
       "step": 120
     },
     {
       "epoch": 2.280701754385965,
-      "grad_norm": 0.38751837611198425,
+      "grad_norm": 0.3750275671482086,
       "learning_rate": 5.438596491228071e-06,
-      "loss": 0.1153,
+      "loss": 0.1155,
       "step": 130
     },
     {
       "epoch": 2.456140350877193,
-      "grad_norm": 0.4417078197002411,
+      "grad_norm": 0.42711108922958374,
       "learning_rate": 5.087719298245615e-06,
       "loss": 0.0805,
       "step": 140
     },
     {
       "epoch": 2.6315789473684212,
-      "grad_norm": 0.3169724643230438,
+      "grad_norm": 0.3187861740589142,
       "learning_rate": 4.736842105263158e-06,
-      "loss": 0.0933,
+      "loss": 0.0936,
       "step": 150
     },
     {
       "epoch": 2.807017543859649,
-      "grad_norm": 0.36373934149742126,
+      "grad_norm": 0.36738303303718567,
       "learning_rate": 4.385964912280702e-06,
-      "loss": 0.0838,
+      "loss": 0.084,
       "step": 160
     },
     {
       "epoch": 2.982456140350877,
-      "grad_norm": 1.6546485424041748,
+      "grad_norm": 2.0587196350097656,
       "learning_rate": 4.035087719298246e-06,
-      "loss": 0.0848,
+      "loss": 0.0855,
       "step": 170
     },
     {
       "epoch": 3.1578947368421053,
-      "grad_norm": 0.3156507611274719,
+      "grad_norm": 0.31759971380233765,
       "learning_rate": 3.6842105263157896e-06,
-      "loss": 0.0897,
+      "loss": 0.0896,
       "step": 180
     },
     {
       "epoch": 3.3333333333333335,
-      "grad_norm": 0.281429648399353,
+      "grad_norm": 0.2914780378341675,
       "learning_rate": 3.3333333333333333e-06,
-      "loss": 0.0812,
+      "loss": 0.0814,
       "step": 190
     },
     {
       "epoch": 3.5087719298245617,
-      "grad_norm": 0.41956350207328796,
+      "grad_norm": 0.33958643674850464,
       "learning_rate": 2.9824561403508774e-06,
-      "loss": 0.0895,
+      "loss": 0.0892,
       "step": 200
     },
     {
@@ -180,64 +180,64 @@
           160
         ]
       ],
-      "eval_loss": 0.11359766870737076,
-      "eval_runtime": 24.3098,
-      "eval_samples_per_second": 9.338,
-      "eval_steps_per_second": 0.329,
+      "eval_loss": 0.1123642697930336,
+      "eval_runtime": 24.2578,
+      "eval_samples_per_second": 9.358,
+      "eval_steps_per_second": 0.33,
       "step": 200
     },
     {
       "epoch": 3.6842105263157894,
-      "grad_norm": 0.27489176392555237,
+      "grad_norm": 0.27888378500938416,
       "learning_rate": 2.631578947368421e-06,
-      "loss": 0.1033,
+      "loss": 0.1024,
       "step": 210
     },
     {
       "epoch": 3.8596491228070176,
-      "grad_norm": 0.5211533308029175,
+      "grad_norm": 0.526310920715332,
       "learning_rate": 2.280701754385965e-06,
-      "loss": 0.0669,
+      "loss": 0.067,
       "step": 220
     },
     {
       "epoch": 4.035087719298246,
-      "grad_norm": 0.9696915149688721,
+      "grad_norm": 1.0086055994033813,
       "learning_rate": 1.929824561403509e-06,
-      "loss": 0.1096,
+      "loss": 0.1094,
       "step": 230
     },
     {
       "epoch": 4.2105263157894735,
-      "grad_norm": 0.42894867062568665,
+      "grad_norm": 0.41842520236968994,
       "learning_rate": 1.5789473684210526e-06,
-      "loss": 0.0752,
+      "loss": 0.0748,
       "step": 240
     },
     {
       "epoch": 4.385964912280702,
-      "grad_norm": 0.2832288444042206,
+      "grad_norm": 0.2806910574436188,
       "learning_rate": 1.2280701754385965e-06,
-      "loss": 0.0562,
+      "loss": 0.0563,
       "step": 250
     },
     {
       "epoch": 4.56140350877193,
-      "grad_norm": 0.2721218168735504,
+      "grad_norm": 0.2728028893470764,
       "learning_rate": 8.771929824561404e-07,
-      "loss": 0.0546,
+      "loss": 0.055,
       "step": 260
     },
     {
       "epoch": 4.7368421052631575,
-      "grad_norm": 0.2685583531856537,
+      "grad_norm": 0.2732146978378296,
       "learning_rate": 5.263157894736843e-07,
-      "loss": 0.0433,
+      "loss": 0.0434,
       "step": 270
     },
     {
       "epoch": 4.912280701754386,
-      "grad_norm": 0.36841797828674316,
+      "grad_norm": 0.3774060010910034,
       "learning_rate": 1.7543859649122808e-07,
       "loss": 0.0962,
       "step": 280
@@ -246,9 +246,9 @@
       "epoch": 5.0,
       "step": 285,
       "total_flos": 7.020774259082035e+17,
-      "train_loss": 0.1523371622227786,
-      "train_runtime": 2876.4334,
-      "train_samples_per_second": 3.171,
+      "train_loss": 0.15312039318837617,
+      "train_runtime": 2880.1419,
+      "train_samples_per_second": 3.167,
       "train_steps_per_second": 0.099
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f53320ff1f0e5340294883424520208507e0ade0e2dfc65ff244d276a5f3f6dd
+oid sha256:2223a644ada76b6f513b01ec0fb8c5ab50ebad3da83eb796792c271093fb5ced
 size 5240