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": 0.15406067664163153,
-    "train_runtime": 2830.5602,
-    "train_samples_per_second": 3.222,
-    "train_steps_per_second": 0.101
+    "train_loss": 0.1663920469451369,
+    "train_runtime": 2889.1333,
+    "train_samples_per_second": 3.157,
+    "train_steps_per_second": 0.099
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a69db0cb14c6e4b1127feefae97c4ad4e6f8d07f8e98e206e12178c38c4edecf
+oid sha256:1234dd0e4cf6e8e986fbba158d52518d89042fcb2e12354de58a3d5f6cbb8529
 size 343223968

runs/Jul19_12-58-59_REDLGLAUCORE01/events.out.tfevents.1721422069.REDLGLAUCORE01.543209.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fb2aca9e8a93e06d8afcddd4be2dec19fe93edc0fee624bfa0dcf78d3dd8f8c
+size 1380

runs/Jul19_14-48-08_REDLGLAUCORE01/events.out.tfevents.1721425689.REDLGLAUCORE01.547362.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:163d3193d6a0ea05f93ee5c0afa542513d2c8919df068031a99b69f72f75cec5
+size 7437

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
     "total_flos": 7.020774259082035e+17,
-    "train_loss": 0.15406067664163153,
-    "train_runtime": 2830.5602,
-    "train_samples_per_second": 3.222,
-    "train_steps_per_second": 0.101
+    "train_loss": 0.1663920469451369,
+    "train_runtime": 2889.1333,
+    "train_samples_per_second": 3.157,
+    "train_steps_per_second": 0.099
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.11733701080083847,
+  "best_metric": 0.10980270802974701,
   "best_model_checkpoint": "/home/projects/Project - Fundus Photo Glaucoma Detection (AI)//model_results/vit-base-gpu/checkpoint-200",
   "epoch": 5.0,
   "eval_steps": 100,
@@ -10,246 +10,246 @@
   "log_history": [
     {
       "epoch": 0.17543859649122806,
-      "grad_norm": 1.1859416961669922,
+      "grad_norm": 1.2453378438949585,
       "learning_rate": 9.649122807017545e-06,
-      "loss": 0.6066,
+      "loss": 0.6386,
       "step": 10
     },
     {
       "epoch": 0.3508771929824561,
-      "grad_norm": 1.6240363121032715,
+      "grad_norm": 1.6582715511322021,
       "learning_rate": 9.298245614035088e-06,
-      "loss": 0.4798,
+      "loss": 0.5038,
       "step": 20
     },
     {
       "epoch": 0.5263157894736842,
-      "grad_norm": 1.196411371231079,
+      "grad_norm": 1.3695889711380005,
       "learning_rate": 8.947368421052632e-06,
-      "loss": 0.3884,
+      "loss": 0.4101,
       "step": 30
     },
     {
       "epoch": 0.7017543859649122,
-      "grad_norm": 1.3352068662643433,
+      "grad_norm": 1.556289792060852,
       "learning_rate": 8.596491228070176e-06,
-      "loss": 0.312,
+      "loss": 0.33,
       "step": 40
     },
     {
       "epoch": 0.8771929824561403,
-      "grad_norm": 1.4265506267547607,
+      "grad_norm": 1.3890976905822754,
       "learning_rate": 8.24561403508772e-06,
-      "loss": 0.2724,
+      "loss": 0.297,
       "step": 50
     },
     {
       "epoch": 1.0526315789473684,
-      "grad_norm": 0.7923513054847717,
+      "grad_norm": 0.8680610656738281,
       "learning_rate": 7.894736842105265e-06,
-      "loss": 0.1841,
+      "loss": 0.2205,
       "step": 60
     },
     {
       "epoch": 1.2280701754385965,
-      "grad_norm": 0.6485021114349365,
+      "grad_norm": 0.6986090540885925,
       "learning_rate": 7.5438596491228074e-06,
-      "loss": 0.1676,
+      "loss": 0.1979,
       "step": 70
     },
     {
       "epoch": 1.4035087719298245,
-      "grad_norm": 0.5704644322395325,
+      "grad_norm": 0.7257100343704224,
       "learning_rate": 7.192982456140352e-06,
-      "loss": 0.1413,
+      "loss": 0.1698,
       "step": 80
     },
     {
       "epoch": 1.5789473684210527,
-      "grad_norm": 1.0736716985702515,
+      "grad_norm": 0.6503203511238098,
       "learning_rate": 6.842105263157896e-06,
-      "loss": 0.117,
+      "loss": 0.1392,
       "step": 90
     },
     {
       "epoch": 1.7543859649122808,
-      "grad_norm": 2.145616292953491,
+      "grad_norm": 0.7091914415359497,
       "learning_rate": 6.491228070175439e-06,
-      "loss": 0.1265,
+      "loss": 0.1364,
       "step": 100
     },
     {
       "epoch": 1.7543859649122808,
-      "eval_accuracy": 0.960352422907489,
+      "eval_accuracy": 0.9691629955947136,
       "eval_confusion_matrix": [
         [
-          57,
-          9
+          59,
+          7
         ],
         [
           0,
           161
         ]
       ],
-      "eval_loss": 0.16849496960639954,
-      "eval_runtime": 25.1005,
-      "eval_samples_per_second": 9.044,
-      "eval_steps_per_second": 0.319,
+      "eval_loss": 0.15967673063278198,
+      "eval_runtime": 25.6843,
+      "eval_samples_per_second": 8.838,
+      "eval_steps_per_second": 0.311,
       "step": 100
     },
     {
       "epoch": 1.9298245614035088,
-      "grad_norm": 5.284341335296631,
+      "grad_norm": 2.2813637256622314,
       "learning_rate": 6.140350877192983e-06,
-      "loss": 0.1298,
+      "loss": 0.1366,
       "step": 110
     },
     {
       "epoch": 2.1052631578947367,
-      "grad_norm": 0.568046510219574,
+      "grad_norm": 0.6449915170669556,
       "learning_rate": 5.789473684210527e-06,
-      "loss": 0.1032,
+      "loss": 0.1141,
       "step": 120
     },
     {
       "epoch": 2.280701754385965,
-      "grad_norm": 0.4078410863876343,
+      "grad_norm": 0.4561377763748169,
       "learning_rate": 5.438596491228071e-06,
-      "loss": 0.1142,
+      "loss": 0.123,
       "step": 130
     },
     {
       "epoch": 2.456140350877193,
-      "grad_norm": 0.33205288648605347,
+      "grad_norm": 0.4450923502445221,
       "learning_rate": 5.087719298245615e-06,
-      "loss": 0.0794,
+      "loss": 0.0885,
       "step": 140
     },
     {
       "epoch": 2.6315789473684212,
-      "grad_norm": 0.3029208183288574,
+      "grad_norm": 0.3755855858325958,
       "learning_rate": 4.736842105263158e-06,
-      "loss": 0.0904,
+      "loss": 0.0962,
       "step": 150
     },
     {
       "epoch": 2.807017543859649,
-      "grad_norm": 0.3194632828235626,
+      "grad_norm": 0.3571043610572815,
       "learning_rate": 4.385964912280702e-06,
-      "loss": 0.0827,
+      "loss": 0.0904,
       "step": 160
     },
     {
       "epoch": 2.982456140350877,
-      "grad_norm": 2.0402252674102783,
+      "grad_norm": 1.4378596544265747,
       "learning_rate": 4.035087719298246e-06,
-      "loss": 0.084,
+      "loss": 0.0885,
       "step": 170
     },
     {
       "epoch": 3.1578947368421053,
-      "grad_norm": 0.3052498400211334,
+      "grad_norm": 0.3472326397895813,
       "learning_rate": 3.6842105263157896e-06,
-      "loss": 0.0868,
+      "loss": 0.0921,
       "step": 180
     },
     {
       "epoch": 3.3333333333333335,
-      "grad_norm": 0.28064411878585815,
+      "grad_norm": 0.3223017752170563,
       "learning_rate": 3.3333333333333333e-06,
-      "loss": 0.0822,
+      "loss": 0.0859,
       "step": 190
     },
     {
       "epoch": 3.5087719298245617,
-      "grad_norm": 1.4272339344024658,
+      "grad_norm": 0.8092898726463318,
       "learning_rate": 2.9824561403508774e-06,
-      "loss": 0.091,
+      "loss": 0.097,
       "step": 200
     },
     {
       "epoch": 3.5087719298245617,
-      "eval_accuracy": 0.973568281938326,
+      "eval_accuracy": 0.9779735682819384,
       "eval_confusion_matrix": [
         [
-          60,
-          6
+          61,
+          5
         ],
         [
           0,
           161
         ]
       ],
-      "eval_loss": 0.11733701080083847,
-      "eval_runtime": 24.7946,
-      "eval_samples_per_second": 9.155,
+      "eval_loss": 0.10980270802974701,
+      "eval_runtime": 24.737,
+      "eval_samples_per_second": 9.177,
       "eval_steps_per_second": 0.323,
       "step": 200
     },
     {
       "epoch": 3.6842105263157894,
-      "grad_norm": 0.2653508484363556,
+      "grad_norm": 0.32260850071907043,
       "learning_rate": 2.631578947368421e-06,
-      "loss": 0.1048,
+      "loss": 0.1055,
       "step": 210
     },
     {
       "epoch": 3.8596491228070176,
-      "grad_norm": 0.35800936818122864,
+      "grad_norm": 0.4265308976173401,
       "learning_rate": 2.280701754385965e-06,
-      "loss": 0.0679,
+      "loss": 0.0725,
       "step": 220
     },
     {
       "epoch": 4.035087719298246,
-      "grad_norm": 0.5756603479385376,
+      "grad_norm": 0.5623507499694824,
       "learning_rate": 1.929824561403509e-06,
-      "loss": 0.105,
+      "loss": 0.1134,
       "step": 230
     },
     {
       "epoch": 4.2105263157894735,
-      "grad_norm": 0.2936393916606903,
+      "grad_norm": 0.34324246644973755,
       "learning_rate": 1.5789473684210526e-06,
-      "loss": 0.0762,
+      "loss": 0.0772,
       "step": 240
     },
     {
       "epoch": 4.385964912280702,
-      "grad_norm": 0.25113916397094727,
+      "grad_norm": 0.3174402415752411,
       "learning_rate": 1.2280701754385965e-06,
-      "loss": 0.0554,
+      "loss": 0.0612,
       "step": 250
     },
     {
       "epoch": 4.56140350877193,
-      "grad_norm": 0.2507961690425873,
+      "grad_norm": 0.3045223653316498,
       "learning_rate": 8.771929824561404e-07,
-      "loss": 0.0546,
+      "loss": 0.0587,
       "step": 260
     },
     {
       "epoch": 4.7368421052631575,
-      "grad_norm": 0.23755021393299103,
+      "grad_norm": 0.2865180969238281,
       "learning_rate": 5.263157894736843e-07,
-      "loss": 0.0439,
+      "loss": 0.0499,
       "step": 270
     },
     {
       "epoch": 4.912280701754386,
-      "grad_norm": 0.27338671684265137,
+      "grad_norm": 0.34900176525115967,
       "learning_rate": 1.7543859649122808e-07,
-      "loss": 0.0969,
+      "loss": 0.0987,
       "step": 280
     },
     {
       "epoch": 5.0,
       "step": 285,
       "total_flos": 7.020774259082035e+17,
-      "train_loss": 0.15406067664163153,
-      "train_runtime": 2830.5602,
-      "train_samples_per_second": 3.222,
-      "train_steps_per_second": 0.101
+      "train_loss": 0.1663920469451369,
+      "train_runtime": 2889.1333,
+      "train_samples_per_second": 3.157,
+      "train_steps_per_second": 0.099
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fe7d7ebdefb05823bfd18e0fc815f9a7be5abc9c04fc742bf55224f4b0e55f5
+oid sha256:60588ccbd71fc71556664c117afd2cb6b1cae526cbee7550d97c3e153cbeb3ff
 size 5240