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": 0.15240513682365417,
-    "train_runtime": 2873.599,
-    "train_samples_per_second": 3.174,
+    "train_loss": 0.1523371622227786,
+    "train_runtime": 2876.4334,
+    "train_samples_per_second": 3.171,
     "train_steps_per_second": 0.099
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44c6f5577965ea9cdc919a8b64bd7b1f3c19a5cdffbc561c8dfab4c7a28d1b67
+oid sha256:d7c58f278cf5a22e10d742e72ac3e6d0851553b0a47dd7bd860a6be11e447f3d
 size 343223968

runs/Jul22_11-42-32_REDLGLAUCORE01/events.out.tfevents.1721676674.REDLGLAUCORE01.547362.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5fa36bf51aa26e129ce23dc1cb5aec2f2e0d4f7980816f7995cf9643ea32dc7
+size 1380

runs/Jul22_13-10-21_REDLGLAUCORE01/events.out.tfevents.1721679021.REDLGLAUCORE01.547362.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec8ee1be7a6580af08226d13e1e3a7ca20df67ec706ec29262560975b892e6e8
+size 7437

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
     "total_flos": 7.020774259082035e+17,
-    "train_loss": 0.15240513682365417,
-    "train_runtime": 2873.599,
-    "train_samples_per_second": 3.174,
+    "train_loss": 0.1523371622227786,
+    "train_runtime": 2876.4334,
+    "train_samples_per_second": 3.171,
     "train_steps_per_second": 0.099
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.11360067874193192,
+  "best_metric": 0.11359766870737076,
   "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": 1.413887858390808,
+      "grad_norm": 1.4138859510421753,
       "learning_rate": 9.649122807017545e-06,
       "loss": 0.5957,
       "step": 10
     },
     {
       "epoch": 0.3508771929824561,
-      "grad_norm": 1.629610300064087,
+      "grad_norm": 1.6238865852355957,
       "learning_rate": 9.298245614035088e-06,
       "loss": 0.4704,
       "step": 20
     },
     {
       "epoch": 0.5263157894736842,
-      "grad_norm": 1.1828052997589111,
+      "grad_norm": 1.1839267015457153,
       "learning_rate": 8.947368421052632e-06,
-      "loss": 0.3788,
+      "loss": 0.3787,
       "step": 30
     },
     {
       "epoch": 0.7017543859649122,
-      "grad_norm": 1.2675493955612183,
+      "grad_norm": 1.2619974613189697,
       "learning_rate": 8.596491228070176e-06,
       "loss": 0.2969,
       "step": 40
     },
     {
       "epoch": 0.8771929824561403,
-      "grad_norm": 1.6942648887634277,
+      "grad_norm": 1.7304680347442627,
       "learning_rate": 8.24561403508772e-06,
-      "loss": 0.2623,
+      "loss": 0.2624,
       "step": 50
     },
     {
       "epoch": 1.0526315789473684,
-      "grad_norm": 0.7355015277862549,
+      "grad_norm": 0.7326079607009888,
       "learning_rate": 7.894736842105265e-06,
-      "loss": 0.1859,
+      "loss": 0.1852,
       "step": 60
     },
     {
       "epoch": 1.2280701754385965,
-      "grad_norm": 0.6509683132171631,
+      "grad_norm": 0.6521451473236084,
       "learning_rate": 7.5438596491228074e-06,
-      "loss": 0.1712,
+      "loss": 0.1707,
       "step": 70
     },
     {
       "epoch": 1.4035087719298245,
-      "grad_norm": 0.6213608384132385,
+      "grad_norm": 0.6134852170944214,
       "learning_rate": 7.192982456140352e-06,
-      "loss": 0.1466,
+      "loss": 0.146,
       "step": 80
     },
     {
       "epoch": 1.5789473684210527,
-      "grad_norm": 0.5607940554618835,
+      "grad_norm": 0.5536946654319763,
       "learning_rate": 6.842105263157896e-06,
-      "loss": 0.1181,
+      "loss": 0.118,
       "step": 90
     },
     {
       "epoch": 1.7543859649122808,
-      "grad_norm": 2.426992416381836,
+      "grad_norm": 2.3261914253234863,
       "learning_rate": 6.491228070175439e-06,
-      "loss": 0.1254,
+      "loss": 0.1251,
       "step": 100
     },
     {
@@ -91,80 +91,80 @@
           161
         ]
       ],
-      "eval_loss": 0.15184630453586578,
-      "eval_runtime": 24.5664,
-      "eval_samples_per_second": 9.24,
-      "eval_steps_per_second": 0.326,
+      "eval_loss": 0.15179260075092316,
+      "eval_runtime": 23.7153,
+      "eval_samples_per_second": 9.572,
+      "eval_steps_per_second": 0.337,
       "step": 100
     },
     {
       "epoch": 1.9298245614035088,
-      "grad_norm": 2.1420822143554688,
+      "grad_norm": 2.69319748878479,
       "learning_rate": 6.140350877192983e-06,
-      "loss": 0.1274,
+      "loss": 0.1267,
       "step": 110
     },
     {
       "epoch": 2.1052631578947367,
-      "grad_norm": 0.4402596950531006,
+      "grad_norm": 0.406830370426178,
       "learning_rate": 5.789473684210527e-06,
-      "loss": 0.0958,
+      "loss": 0.0962,
       "step": 120
     },
     {
       "epoch": 2.280701754385965,
-      "grad_norm": 0.3711773157119751,
+      "grad_norm": 0.38751837611198425,
       "learning_rate": 5.438596491228071e-06,
-      "loss": 0.1151,
+      "loss": 0.1153,
       "step": 130
     },
     {
       "epoch": 2.456140350877193,
-      "grad_norm": 0.4589725732803345,
+      "grad_norm": 0.4417078197002411,
       "learning_rate": 5.087719298245615e-06,
-      "loss": 0.0796,
+      "loss": 0.0805,
       "step": 140
     },
     {
       "epoch": 2.6315789473684212,
-      "grad_norm": 0.32596296072006226,
+      "grad_norm": 0.3169724643230438,
       "learning_rate": 4.736842105263158e-06,
-      "loss": 0.0935,
+      "loss": 0.0933,
       "step": 150
     },
     {
       "epoch": 2.807017543859649,
-      "grad_norm": 0.3621123731136322,
+      "grad_norm": 0.36373934149742126,
       "learning_rate": 4.385964912280702e-06,
       "loss": 0.0838,
       "step": 160
     },
     {
       "epoch": 2.982456140350877,
-      "grad_norm": 1.6324498653411865,
+      "grad_norm": 1.6546485424041748,
       "learning_rate": 4.035087719298246e-06,
-      "loss": 0.085,
+      "loss": 0.0848,
       "step": 170
     },
     {
       "epoch": 3.1578947368421053,
-      "grad_norm": 0.31269893050193787,
+      "grad_norm": 0.3156507611274719,
       "learning_rate": 3.6842105263157896e-06,
-      "loss": 0.0898,
+      "loss": 0.0897,
       "step": 180
     },
     {
       "epoch": 3.3333333333333335,
-      "grad_norm": 0.279706209897995,
+      "grad_norm": 0.281429648399353,
       "learning_rate": 3.3333333333333333e-06,
-      "loss": 0.0811,
+      "loss": 0.0812,
       "step": 190
     },
     {
       "epoch": 3.5087719298245617,
-      "grad_norm": 0.41368523240089417,
+      "grad_norm": 0.41956350207328796,
       "learning_rate": 2.9824561403508774e-06,
-      "loss": 0.0894,
+      "loss": 0.0895,
       "step": 200
     },
     {
@@ -180,75 +180,75 @@
           160
         ]
       ],
-      "eval_loss": 0.11360067874193192,
-      "eval_runtime": 24.4641,
-      "eval_samples_per_second": 9.279,
-      "eval_steps_per_second": 0.327,
+      "eval_loss": 0.11359766870737076,
+      "eval_runtime": 24.3098,
+      "eval_samples_per_second": 9.338,
+      "eval_steps_per_second": 0.329,
       "step": 200
     },
     {
       "epoch": 3.6842105263157894,
-      "grad_norm": 0.2807004153728485,
+      "grad_norm": 0.27489176392555237,
       "learning_rate": 2.631578947368421e-06,
-      "loss": 0.1037,
+      "loss": 0.1033,
       "step": 210
     },
     {
       "epoch": 3.8596491228070176,
-      "grad_norm": 0.51247239112854,
+      "grad_norm": 0.5211533308029175,
       "learning_rate": 2.280701754385965e-06,
-      "loss": 0.0667,
+      "loss": 0.0669,
       "step": 220
     },
     {
       "epoch": 4.035087719298246,
-      "grad_norm": 0.9778783321380615,
+      "grad_norm": 0.9696915149688721,
       "learning_rate": 1.929824561403509e-06,
-      "loss": 0.1093,
+      "loss": 0.1096,
       "step": 230
     },
     {
       "epoch": 4.2105263157894735,
-      "grad_norm": 0.43163198232650757,
+      "grad_norm": 0.42894867062568665,
       "learning_rate": 1.5789473684210526e-06,
-      "loss": 0.0753,
+      "loss": 0.0752,
       "step": 240
     },
     {
       "epoch": 4.385964912280702,
-      "grad_norm": 0.2818666994571686,
+      "grad_norm": 0.2832288444042206,
       "learning_rate": 1.2280701754385965e-06,
-      "loss": 0.0563,
+      "loss": 0.0562,
       "step": 250
     },
     {
       "epoch": 4.56140350877193,
-      "grad_norm": 0.26998862624168396,
+      "grad_norm": 0.2721218168735504,
       "learning_rate": 8.771929824561404e-07,
       "loss": 0.0546,
       "step": 260
     },
     {
       "epoch": 4.7368421052631575,
-      "grad_norm": 0.26639774441719055,
+      "grad_norm": 0.2685583531856537,
       "learning_rate": 5.263157894736843e-07,
-      "loss": 0.0431,
+      "loss": 0.0433,
       "step": 270
     },
     {
       "epoch": 4.912280701754386,
-      "grad_norm": 0.36992037296295166,
+      "grad_norm": 0.36841797828674316,
       "learning_rate": 1.7543859649122808e-07,
-      "loss": 0.0964,
+      "loss": 0.0962,
       "step": 280
     },
     {
       "epoch": 5.0,
       "step": 285,
       "total_flos": 7.020774259082035e+17,
-      "train_loss": 0.15240513682365417,
-      "train_runtime": 2873.599,
-      "train_samples_per_second": 3.174,
+      "train_loss": 0.1523371622227786,
+      "train_runtime": 2876.4334,
+      "train_samples_per_second": 3.171,
       "train_steps_per_second": 0.099
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c33af9ddd90354db3d1189fcfac244abcc2bdc08a82d6298a622217e0781cbb
+oid sha256:f53320ff1f0e5340294883424520208507e0ade0e2dfc65ff244d276a5f3f6dd
 size 5240