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": 0.16874999728119164,
-    "train_runtime": 2873.7083,
-    "train_samples_per_second": 3.174,
+    "train_loss": 0.16588184833526612,
+    "train_runtime": 2879.0892,
+    "train_samples_per_second": 3.168,
     "train_steps_per_second": 0.099
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dbe5e90e3a9f0bc236ed5c40ef4d5e950f040bbd05a831f7dcc85910e5cac76
+oid sha256:c4fbf56a3eb9967811c68c02b4b9235dcc15365969ded188f015114e8643f60b
 size 343223968

runs/Jul25_14-48-19_REDLGLAUCORE01/events.out.tfevents.1721947025.REDLGLAUCORE01.848854.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fe1bc598f8864d3a0ac574378e193ddacf0ad9a40249fefda6c070594fcf521
+size 1057

runs/Sep05_19-26-29_REDLGLAUCORE01/events.out.tfevents.1725589589.REDLGLAUCORE01.848854.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5bacdcbdab63c0e5231fd40c61fd5e22abeee02027db4f78d75e3b3e013c2d5
+size 5050

runs/Sep05_19-26-51_REDLGLAUCORE01/events.out.tfevents.1725589611.REDLGLAUCORE01.848854.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e665a6c9e2c82ed8c32830d2bb87d7beac7644dcaadd14f2ba6de885b347bc6a
+size 5050

runs/Sep05_20-01-33_REDLGLAUCORE01/events.out.tfevents.1725591693.REDLGLAUCORE01.848854.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9903d81b3a6ab98eefb3fc505e8c5e1e8f36c70a401ded55d8b8cae14b90000
+size 7437

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
     "total_flos": 7.020774259082035e+17,
-    "train_loss": 0.16874999728119164,
-    "train_runtime": 2873.7083,
-    "train_samples_per_second": 3.174,
+    "train_loss": 0.16588184833526612,
+    "train_runtime": 2879.0892,
+    "train_samples_per_second": 3.168,
     "train_steps_per_second": 0.099
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.11347667127847672,
+  "best_metric": 0.11670097708702087,
   "best_model_checkpoint": "/home/projects/Project - Fundus Photo Glaucoma Detection (AI)//model_results/vit-base-gpu/checkpoint-200",
   "epoch": 5.0,
   "eval_steps": 100,
@@ -10,161 +10,161 @@
   "log_history": [
     {
       "epoch": 0.17543859649122806,
-      "grad_norm": 1.0130871534347534,
+      "grad_norm": 1.2752189636230469,
       "learning_rate": 9.649122807017545e-06,
-      "loss": 0.6237,
+      "loss": 0.6232,
       "step": 10
     },
     {
       "epoch": 0.3508771929824561,
-      "grad_norm": 1.5061233043670654,
+      "grad_norm": 1.752753496170044,
       "learning_rate": 9.298245614035088e-06,
-      "loss": 0.5133,
+      "loss": 0.473,
       "step": 20
     },
     {
       "epoch": 0.5263157894736842,
-      "grad_norm": 1.1895650625228882,
+      "grad_norm": 1.3884831666946411,
       "learning_rate": 8.947368421052632e-06,
-      "loss": 0.4212,
+      "loss": 0.3834,
       "step": 30
     },
     {
       "epoch": 0.7017543859649122,
-      "grad_norm": 1.2210878133773804,
+      "grad_norm": 1.6439697742462158,
       "learning_rate": 8.596491228070176e-06,
-      "loss": 0.3366,
+      "loss": 0.305,
       "step": 40
     },
     {
       "epoch": 0.8771929824561403,
-      "grad_norm": 0.8089302182197571,
+      "grad_norm": 1.1231735944747925,
       "learning_rate": 8.24561403508772e-06,
-      "loss": 0.2959,
+      "loss": 0.2869,
       "step": 50
     },
     {
       "epoch": 1.0526315789473684,
-      "grad_norm": 0.8888680338859558,
+      "grad_norm": 0.8180190324783325,
       "learning_rate": 7.894736842105265e-06,
-      "loss": 0.2143,
+      "loss": 0.2178,
       "step": 60
     },
     {
       "epoch": 1.2280701754385965,
-      "grad_norm": 0.553264319896698,
+      "grad_norm": 0.6753518581390381,
       "learning_rate": 7.5438596491228074e-06,
-      "loss": 0.187,
+      "loss": 0.206,
       "step": 70
     },
     {
       "epoch": 1.4035087719298245,
-      "grad_norm": 0.6764554381370544,
+      "grad_norm": 1.176467776298523,
       "learning_rate": 7.192982456140352e-06,
-      "loss": 0.161,
+      "loss": 0.1828,
       "step": 80
     },
     {
       "epoch": 1.5789473684210527,
-      "grad_norm": 0.9164976477622986,
+      "grad_norm": 0.7861670255661011,
       "learning_rate": 6.842105263157896e-06,
-      "loss": 0.1341,
+      "loss": 0.1564,
       "step": 90
     },
     {
       "epoch": 1.7543859649122808,
-      "grad_norm": 0.4016127288341522,
+      "grad_norm": 0.4661114811897278,
       "learning_rate": 6.491228070175439e-06,
-      "loss": 0.1269,
+      "loss": 0.1497,
       "step": 100
     },
     {
       "epoch": 1.7543859649122808,
-      "eval_accuracy": 0.9691629955947136,
+      "eval_accuracy": 0.9647577092511013,
       "eval_confusion_matrix": [
         [
-          59,
-          7
+          58,
+          8
         ],
         [
           0,
           161
         ]
       ],
-      "eval_loss": 0.15991853177547455,
-      "eval_runtime": 24.3978,
-      "eval_samples_per_second": 9.304,
-      "eval_steps_per_second": 0.328,
+      "eval_loss": 0.1807878464460373,
+      "eval_runtime": 24.5815,
+      "eval_samples_per_second": 9.235,
+      "eval_steps_per_second": 0.325,
       "step": 100
     },
     {
       "epoch": 1.9298245614035088,
-      "grad_norm": 2.8858230113983154,
+      "grad_norm": 5.353541851043701,
       "learning_rate": 6.140350877192983e-06,
-      "loss": 0.1424,
+      "loss": 0.1463,
       "step": 110
     },
     {
       "epoch": 2.1052631578947367,
-      "grad_norm": 1.5411401987075806,
+      "grad_norm": 0.47052720189094543,
       "learning_rate": 5.789473684210527e-06,
-      "loss": 0.121,
+      "loss": 0.1291,
       "step": 120
     },
     {
       "epoch": 2.280701754385965,
-      "grad_norm": 0.32339081168174744,
+      "grad_norm": 0.43008866906166077,
       "learning_rate": 5.438596491228071e-06,
-      "loss": 0.1263,
+      "loss": 0.1294,
       "step": 130
     },
     {
       "epoch": 2.456140350877193,
-      "grad_norm": 0.4499027132987976,
+      "grad_norm": 0.495709627866745,
       "learning_rate": 5.087719298245615e-06,
-      "loss": 0.0902,
+      "loss": 0.0904,
       "step": 140
     },
     {
       "epoch": 2.6315789473684212,
-      "grad_norm": 0.403751939535141,
+      "grad_norm": 0.36288028955459595,
       "learning_rate": 4.736842105263158e-06,
-      "loss": 0.0983,
+      "loss": 0.1004,
       "step": 150
     },
     {
       "epoch": 2.807017543859649,
-      "grad_norm": 0.35326865315437317,
+      "grad_norm": 0.42618927359580994,
       "learning_rate": 4.385964912280702e-06,
-      "loss": 0.091,
+      "loss": 0.0931,
       "step": 160
     },
     {
       "epoch": 2.982456140350877,
-      "grad_norm": 1.8933607339859009,
+      "grad_norm": 1.7581294775009155,
       "learning_rate": 4.035087719298246e-06,
-      "loss": 0.0917,
+      "loss": 0.0909,
       "step": 170
     },
     {
       "epoch": 3.1578947368421053,
-      "grad_norm": 0.34224092960357666,
+      "grad_norm": 0.3336179554462433,
       "learning_rate": 3.6842105263157896e-06,
-      "loss": 0.0996,
+      "loss": 0.0991,
       "step": 180
     },
     {
       "epoch": 3.3333333333333335,
-      "grad_norm": 0.38210582733154297,
+      "grad_norm": 0.3549640476703644,
       "learning_rate": 3.3333333333333333e-06,
-      "loss": 0.0967,
+      "loss": 0.089,
       "step": 190
     },
     {
       "epoch": 3.5087719298245617,
-      "grad_norm": 3.640868902206421,
+      "grad_norm": 0.6302672624588013,
       "learning_rate": 2.9824561403508774e-06,
-      "loss": 0.1017,
+      "loss": 0.0998,
       "step": 200
     },
     {
@@ -180,75 +180,75 @@
           161
         ]
       ],
-      "eval_loss": 0.11347667127847672,
-      "eval_runtime": 22.6633,
-      "eval_samples_per_second": 10.016,
-      "eval_steps_per_second": 0.353,
+      "eval_loss": 0.11670097708702087,
+      "eval_runtime": 25.3798,
+      "eval_samples_per_second": 8.944,
+      "eval_steps_per_second": 0.315,
       "step": 200
     },
     {
       "epoch": 3.6842105263157894,
-      "grad_norm": 0.3444685935974121,
+      "grad_norm": 0.3984730839729309,
       "learning_rate": 2.631578947368421e-06,
-      "loss": 0.1074,
+      "loss": 0.1028,
       "step": 210
     },
     {
       "epoch": 3.8596491228070176,
-      "grad_norm": 0.29822683334350586,
+      "grad_norm": 0.4672948718070984,
       "learning_rate": 2.280701754385965e-06,
-      "loss": 0.0815,
+      "loss": 0.0746,
       "step": 220
     },
     {
       "epoch": 4.035087719298246,
-      "grad_norm": 0.49087172746658325,
+      "grad_norm": 0.7369114756584167,
       "learning_rate": 1.929824561403509e-06,
-      "loss": 0.1159,
+      "loss": 0.1065,
       "step": 230
     },
     {
       "epoch": 4.2105263157894735,
-      "grad_norm": 0.2734374701976776,
+      "grad_norm": 0.361775666475296,
       "learning_rate": 1.5789473684210526e-06,
-      "loss": 0.0823,
+      "loss": 0.0779,
       "step": 240
     },
     {
       "epoch": 4.385964912280702,
-      "grad_norm": 0.30442044138908386,
+      "grad_norm": 0.29275935888290405,
       "learning_rate": 1.2280701754385965e-06,
-      "loss": 0.0662,
+      "loss": 0.0615,
       "step": 250
     },
     {
       "epoch": 4.56140350877193,
-      "grad_norm": 0.30384954810142517,
+      "grad_norm": 0.30065467953681946,
       "learning_rate": 8.771929824561404e-07,
-      "loss": 0.063,
+      "loss": 0.0603,
       "step": 260
     },
     {
       "epoch": 4.7368421052631575,
-      "grad_norm": 0.3455353081226349,
+      "grad_norm": 0.28486543893814087,
       "learning_rate": 5.263157894736843e-07,
-      "loss": 0.056,
+      "loss": 0.0523,
       "step": 270
     },
     {
       "epoch": 4.912280701754386,
-      "grad_norm": 0.3426889479160309,
+      "grad_norm": 0.5634991526603699,
       "learning_rate": 1.7543859649122808e-07,
-      "loss": 0.1138,
+      "loss": 0.0905,
       "step": 280
     },
     {
       "epoch": 5.0,
       "step": 285,
       "total_flos": 7.020774259082035e+17,
-      "train_loss": 0.16874999728119164,
-      "train_runtime": 2873.7083,
-      "train_samples_per_second": 3.174,
+      "train_loss": 0.16588184833526612,
+      "train_runtime": 2879.0892,
+      "train_samples_per_second": 3.168,
       "train_steps_per_second": 0.099
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c6fb497af13b66bd8a1f0d0ccf863bb8b087bd59e9c975e96a628fb51eb1cc1
+oid sha256:26ad7d3be1e9b00cda37081e9bd1f3b1066347be8b51b2fd04038001c72c8526
 size 5240