Training in progress, epoch 0

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 4.938271604938271,
-    "eval_accuracy": 0.9477351916376306,
-    "eval_loss": 0.11578787863254547,
-    "eval_runtime": 2.7445,
-    "eval_samples_per_second": 104.573,
-    "eval_steps_per_second": 6.559,
+    "eval_accuracy": 0.9368950832365467,
+    "eval_loss": 0.16935844719409943,
+    "eval_runtime": 25.4894,
+    "eval_samples_per_second": 101.336,
+    "eval_steps_per_second": 6.356,
     "total_flos": 3.1727957353537536e+17,
-    "train_loss": 0.41540566325187683,
-    "train_runtime": 248.6508,
-    "train_samples_per_second": 51.94,
-    "train_steps_per_second": 0.804
+    "train_loss": 0.4196511161327362,
+    "train_runtime": 246.9642,
+    "train_samples_per_second": 52.295,
+    "train_steps_per_second": 0.81
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.938271604938271,
-    "eval_accuracy": 0.9477351916376306,
-    "eval_loss": 0.11578787863254547,
-    "eval_runtime": 2.7445,
-    "eval_samples_per_second": 104.573,
-    "eval_steps_per_second": 6.559
+    "eval_accuracy": 0.9547038327526133,
+    "eval_loss": 0.12142720818519592,
+    "eval_runtime": 2.5284,
+    "eval_samples_per_second": 113.511,
+    "eval_steps_per_second": 7.119
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3066a6576511f8b1883aff008c864835f27728376c417b4e508e6b0db03602f
+oid sha256:0d741f951e705b7ffa0e757168f7ac730981b0e25bf7c8a91391460719849e34
 size 110348984

runs/Oct17_04-14-12_05a7a6f58592/events.out.tfevents.1729138717.05a7a6f58592.1707.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66e53f1758ef5ff11dc93dac058e52d0c707f49c1188eb6bc2e971f24210601e
+size 1057

runs/Oct17_04-44-59_05a7a6f58592/events.out.tfevents.1729140379.05a7a6f58592.1707.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:417035168be3584c04a8684f64e4ddd6945d2541033bb9d11c01b15789908fc4
+size 6581

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.938271604938271,
-    "total_flos": 3.1727957353537536e+17,
-    "train_loss": 0.41540566325187683,
-    "train_runtime": 248.6508,
-    "train_samples_per_second": 51.94,
-    "train_steps_per_second": 0.804
+    "eval_accuracy": 0.9368950832365467,
+    "eval_loss": 0.16935844719409943,
+    "eval_runtime": 25.4894,
+    "eval_samples_per_second": 101.336,
+    "eval_steps_per_second": 6.356
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.9477351916376306,
+  "best_metric": 0.9547038327526133,
   "best_model_checkpoint": "brain-tumor-classification/checkpoint-200",
   "epoch": 4.938271604938271,
   "eval_steps": 500,
@@ -10,197 +10,224 @@
   "log_history": [
     {
       "epoch": 0.24691358024691357,
-      "grad_norm": 11.865983009338379,
+      "grad_norm": 8.300398826599121,
       "learning_rate": 2.5e-05,
-      "loss": 1.335,
+      "loss": 1.3599,
       "step": 10
     },
     {
       "epoch": 0.49382716049382713,
-      "grad_norm": 14.611420631408691,
+      "grad_norm": 11.234930992126465,
       "learning_rate": 5e-05,
-      "loss": 1.0649,
+      "loss": 1.0545,
       "step": 20
     },
     {
       "epoch": 0.7407407407407407,
-      "grad_norm": 14.365787506103516,
+      "grad_norm": 12.957039833068848,
       "learning_rate": 4.722222222222222e-05,
-      "loss": 0.7611,
+      "loss": 0.7446,
       "step": 30
     },
     {
       "epoch": 0.9876543209876543,
-      "grad_norm": 16.896533966064453,
+      "grad_norm": 13.77059268951416,
       "learning_rate": 4.4444444444444447e-05,
-      "loss": 0.5761,
+      "loss": 0.6001,
       "step": 40
     },
     {
       "epoch": 0.9876543209876543,
-      "eval_accuracy": 0.8432055749128919,
-      "eval_loss": 0.41130325198173523,
-      "eval_runtime": 2.4201,
-      "eval_samples_per_second": 118.592,
-      "eval_steps_per_second": 7.438,
+      "eval_accuracy": 0.8466898954703833,
+      "eval_loss": 0.4058869779109955,
+      "eval_runtime": 2.3913,
+      "eval_samples_per_second": 120.016,
+      "eval_steps_per_second": 7.527,
       "step": 40
     },
     {
       "epoch": 1.2345679012345678,
-      "grad_norm": 9.885971069335938,
+      "grad_norm": 12.874049186706543,
       "learning_rate": 4.166666666666667e-05,
-      "loss": 0.5027,
+      "loss": 0.4598,
       "step": 50
     },
     {
       "epoch": 1.4814814814814814,
-      "grad_norm": 19.173418045043945,
+      "grad_norm": 15.899703979492188,
       "learning_rate": 3.888888888888889e-05,
-      "loss": 0.4857,
+      "loss": 0.4362,
       "step": 60
     },
     {
       "epoch": 1.7283950617283952,
-      "grad_norm": 10.684455871582031,
+      "grad_norm": 14.211153030395508,
       "learning_rate": 3.611111111111111e-05,
-      "loss": 0.4252,
+      "loss": 0.4013,
       "step": 70
     },
     {
       "epoch": 1.9753086419753085,
-      "grad_norm": 11.967300415039062,
+      "grad_norm": 14.76016902923584,
       "learning_rate": 3.3333333333333335e-05,
-      "loss": 0.3871,
+      "loss": 0.3615,
       "step": 80
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.9024390243902439,
-      "eval_loss": 0.25702860951423645,
-      "eval_runtime": 3.0171,
-      "eval_samples_per_second": 95.125,
-      "eval_steps_per_second": 5.966,
+      "eval_accuracy": 0.9128919860627178,
+      "eval_loss": 0.2405817061662674,
+      "eval_runtime": 4.5171,
+      "eval_samples_per_second": 63.537,
+      "eval_steps_per_second": 3.985,
       "step": 81
     },
     {
       "epoch": 2.2222222222222223,
-      "grad_norm": 7.449192047119141,
+      "grad_norm": 10.028989791870117,
       "learning_rate": 3.055555555555556e-05,
-      "loss": 0.294,
+      "loss": 0.3202,
       "step": 90
     },
     {
       "epoch": 2.4691358024691357,
-      "grad_norm": 15.003212928771973,
+      "grad_norm": 8.175374984741211,
       "learning_rate": 2.777777777777778e-05,
-      "loss": 0.3583,
+      "loss": 0.2769,
       "step": 100
     },
     {
       "epoch": 2.7160493827160495,
-      "grad_norm": 12.026302337646484,
+      "grad_norm": 7.94071102142334,
       "learning_rate": 2.5e-05,
-      "loss": 0.2584,
+      "loss": 0.2848,
       "step": 110
     },
     {
       "epoch": 2.962962962962963,
-      "grad_norm": 10.30452823638916,
+      "grad_norm": 14.77879524230957,
       "learning_rate": 2.2222222222222223e-05,
-      "loss": 0.2586,
+      "loss": 0.2619,
       "step": 120
     },
     {
       "epoch": 2.9876543209876543,
-      "eval_accuracy": 0.9407665505226481,
-      "eval_loss": 0.1910204291343689,
-      "eval_runtime": 2.8228,
-      "eval_samples_per_second": 101.672,
-      "eval_steps_per_second": 6.377,
+      "eval_accuracy": 0.9372822299651568,
+      "eval_loss": 0.18160930275917053,
+      "eval_runtime": 2.3852,
+      "eval_samples_per_second": 120.323,
+      "eval_steps_per_second": 7.546,
       "step": 121
     },
     {
       "epoch": 3.2098765432098766,
-      "grad_norm": 9.547262191772461,
+      "grad_norm": 5.213917255401611,
       "learning_rate": 1.9444444444444445e-05,
-      "loss": 0.1965,
+      "loss": 0.2809,
       "step": 130
     },
     {
       "epoch": 3.45679012345679,
-      "grad_norm": 8.193156242370605,
+      "grad_norm": 9.913806915283203,
       "learning_rate": 1.6666666666666667e-05,
-      "loss": 0.2272,
+      "loss": 0.2239,
       "step": 140
     },
     {
       "epoch": 3.7037037037037037,
-      "grad_norm": 6.964083671569824,
+      "grad_norm": 9.552595138549805,
       "learning_rate": 1.388888888888889e-05,
-      "loss": 0.237,
+      "loss": 0.2331,
       "step": 150
     },
     {
       "epoch": 3.950617283950617,
-      "grad_norm": 15.732324600219727,
+      "grad_norm": 13.436369895935059,
       "learning_rate": 1.1111111111111112e-05,
-      "loss": 0.2164,
+      "loss": 0.2262,
       "step": 160
     },
     {
       "epoch": 4.0,
       "eval_accuracy": 0.9442508710801394,
-      "eval_loss": 0.13123387098312378,
-      "eval_runtime": 2.4291,
-      "eval_samples_per_second": 118.153,
-      "eval_steps_per_second": 7.41,
+      "eval_loss": 0.14013153314590454,
+      "eval_runtime": 2.3881,
+      "eval_samples_per_second": 120.178,
+      "eval_steps_per_second": 7.537,
       "step": 162
     },
     {
       "epoch": 4.197530864197531,
-      "grad_norm": 7.277712821960449,
+      "grad_norm": 5.0693039894104,
       "learning_rate": 8.333333333333334e-06,
-      "loss": 0.1614,
+      "loss": 0.2334,
       "step": 170
     },
     {
       "epoch": 4.444444444444445,
-      "grad_norm": 13.366209030151367,
+      "grad_norm": 9.17518424987793,
       "learning_rate": 5.555555555555556e-06,
-      "loss": 0.1978,
+      "loss": 0.2374,
       "step": 180
     },
     {
       "epoch": 4.6913580246913575,
-      "grad_norm": 9.085039138793945,
+      "grad_norm": 7.441468715667725,
       "learning_rate": 2.777777777777778e-06,
-      "loss": 0.189,
+      "loss": 0.2173,
       "step": 190
     },
     {
       "epoch": 4.938271604938271,
-      "grad_norm": 7.736137866973877,
+      "grad_norm": 3.2817890644073486,
       "learning_rate": 0.0,
-      "loss": 0.1757,
+      "loss": 0.179,
       "step": 200
     },
     {
       "epoch": 4.938271604938271,
-      "eval_accuracy": 0.9477351916376306,
-      "eval_loss": 0.11578787863254547,
-      "eval_runtime": 2.7368,
-      "eval_samples_per_second": 104.868,
-      "eval_steps_per_second": 6.577,
+      "eval_accuracy": 0.9547038327526133,
+      "eval_loss": 0.12142720818519592,
+      "eval_runtime": 3.0543,
+      "eval_samples_per_second": 93.966,
+      "eval_steps_per_second": 5.893,
       "step": 200
     },
     {
       "epoch": 4.938271604938271,
       "step": 200,
       "total_flos": 3.1727957353537536e+17,
-      "train_loss": 0.41540566325187683,
-      "train_runtime": 248.6508,
-      "train_samples_per_second": 51.94,
-      "train_steps_per_second": 0.804
+      "train_loss": 0.4196511161327362,
+      "train_runtime": 246.9642,
+      "train_samples_per_second": 52.295,
+      "train_steps_per_second": 0.81
+    },
+    {
+      "epoch": 4.938271604938271,
+      "eval_accuracy": 0.9547038327526133,
+      "eval_loss": 0.12142720818519592,
+      "eval_runtime": 2.5284,
+      "eval_samples_per_second": 113.511,
+      "eval_steps_per_second": 7.119,
+      "step": 200
+    },
+    {
+      "epoch": 4.938271604938271,
+      "eval_accuracy": 0.9407665505226481,
+      "eval_loss": 0.16431476175785065,
+      "eval_runtime": 26.8879,
+      "eval_samples_per_second": 96.066,
+      "eval_steps_per_second": 6.025,
+      "step": 200
+    },
+    {
+      "epoch": 4.938271604938271,
+      "eval_accuracy": 0.9368950832365467,
+      "eval_loss": 0.16935844719409943,
+      "eval_runtime": 25.4894,
+      "eval_samples_per_second": 101.336,
+      "eval_steps_per_second": 6.356,
+      "step": 200
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78ef78e2dad428c020819d09e1b5c0caf3c6c577718dbcd3c1403929d220398d
+oid sha256:5a88135003244a417dc1864deba9655d21aa0384efab8f780d6cd82423fa59d4
 size 5240