🍻 cheers

all_results.json

@@ -1,8 +1,13 @@
 {
     "epoch": 4.0,
+    "eval_accuracy": 0.8987341772151899,
+    "eval_loss": 0.3074355721473694,
+    "eval_runtime": 3.6489,
+    "eval_samples_per_second": 64.952,
+    "eval_steps_per_second": 8.222,
     "total_flos": 4.156707577848054e+17,
-    "train_loss": 0.5616364919003987,
-    "train_runtime": 127.6942,
-    "train_samples_per_second": 42.007,
-    "train_steps_per_second": 2.631
+    "train_loss": 0.4933107083752042,
+    "train_runtime": 131.5099,
+    "train_samples_per_second": 40.788,
+    "train_steps_per_second": 2.555
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.8987341772151899,
+    "eval_loss": 0.3074355721473694,
+    "eval_runtime": 3.6489,
+    "eval_samples_per_second": 64.952,
+    "eval_steps_per_second": 8.222
+}

runs/May13_10-04-37_4c49d2f8bc77/events.out.tfevents.1715595788.4c49d2f8bc77.7570.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcca50447cb9a1fe982032537d4e8eca1f3d40793978ac82a795ddcd015b90d6
+size 411

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
     "total_flos": 4.156707577848054e+17,
-    "train_loss": 0.5616364919003987,
-    "train_runtime": 127.6942,
-    "train_samples_per_second": 42.007,
-    "train_steps_per_second": 2.631
+    "train_loss": 0.4933107083752042,
+    "train_runtime": 131.5099,
+    "train_samples_per_second": 40.788,
+    "train_steps_per_second": 2.555
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_metric": 0.3074355721473694,
-  "best_model_checkpoint": "finetuned-breast_cancer_images/checkpoint-200",
+  "best_model_checkpoint": "finetuned-breast_cancer_images/checkpoint-100",
   "epoch": 4.0,
   "global_step": 336,
   "is_hyper_param_search": false,
@@ -9,237 +9,237 @@
   "log_history": [
     {
       "epoch": 0.12,
-      "learning_rate": 0.00019404761904761905,
-      "loss": 0.9428,
+      "learning_rate": 0.0,
+      "loss": 0.4362,
       "step": 10
     },
     {
       "epoch": 0.24,
-      "learning_rate": 0.0001880952380952381,
-      "loss": 0.7846,
+      "learning_rate": 0.0,
+      "loss": 0.4081,
       "step": 20
     },
     {
       "epoch": 0.36,
-      "learning_rate": 0.00018214285714285714,
-      "loss": 0.6764,
+      "learning_rate": 0.0,
+      "loss": 0.5069,
       "step": 30
     },
     {
       "epoch": 0.48,
-      "learning_rate": 0.0001761904761904762,
-      "loss": 0.616,
+      "learning_rate": 0.0,
+      "loss": 0.4546,
       "step": 40
     },
     {
       "epoch": 0.6,
-      "learning_rate": 0.00017023809523809523,
-      "loss": 0.713,
+      "learning_rate": 0.0,
+      "loss": 0.4799,
       "step": 50
     },
     {
       "epoch": 0.71,
-      "learning_rate": 0.00016428571428571428,
-      "loss": 0.6676,
+      "learning_rate": 0.0,
+      "loss": 0.5819,
       "step": 60
     },
     {
       "epoch": 0.83,
-      "learning_rate": 0.00015833333333333332,
-      "loss": 0.6025,
+      "learning_rate": 0.0,
+      "loss": 0.4704,
       "step": 70
     },
     {
       "epoch": 0.95,
-      "learning_rate": 0.00015238095238095237,
-      "loss": 0.7843,
+      "learning_rate": 0.0,
+      "loss": 0.5476,
       "step": 80
     },
     {
       "epoch": 1.07,
-      "learning_rate": 0.00014642857142857141,
-      "loss": 0.5945,
+      "learning_rate": 0.0,
+      "loss": 0.5506,
       "step": 90
     },
     {
       "epoch": 1.19,
-      "learning_rate": 0.00014047619047619049,
-      "loss": 0.5578,
+      "learning_rate": 0.0,
+      "loss": 0.4716,
       "step": 100
     },
     {
       "epoch": 1.19,
-      "eval_accuracy": 0.8776371308016878,
-      "eval_loss": 0.3928695321083069,
-      "eval_runtime": 2.5752,
-      "eval_samples_per_second": 92.033,
-      "eval_steps_per_second": 11.65,
+      "eval_accuracy": 0.8987341772151899,
+      "eval_loss": 0.3074355721473694,
+      "eval_runtime": 2.4007,
+      "eval_samples_per_second": 98.722,
+      "eval_steps_per_second": 12.496,
       "step": 100
     },
     {
       "epoch": 1.31,
-      "learning_rate": 0.00013452380952380953,
-      "loss": 0.5636,
+      "learning_rate": 0.0,
+      "loss": 0.4972,
       "step": 110
     },
     {
       "epoch": 1.43,
-      "learning_rate": 0.00012857142857142858,
-      "loss": 0.6501,
+      "learning_rate": 0.0,
+      "loss": 0.5508,
       "step": 120
     },
     {
       "epoch": 1.55,
-      "learning_rate": 0.00012261904761904762,
-      "loss": 0.6229,
+      "learning_rate": 0.0,
+      "loss": 0.3687,
       "step": 130
     },
     {
       "epoch": 1.67,
-      "learning_rate": 0.00011666666666666668,
-      "loss": 0.6096,
+      "learning_rate": 0.0,
+      "loss": 0.5155,
       "step": 140
     },
     {
       "epoch": 1.79,
-      "learning_rate": 0.00011071428571428572,
-      "loss": 0.618,
+      "learning_rate": 0.0,
+      "loss": 0.4511,
       "step": 150
     },
     {
       "epoch": 1.9,
-      "learning_rate": 0.00010476190476190477,
-      "loss": 0.5657,
+      "learning_rate": 0.0,
+      "loss": 0.4943,
       "step": 160
     },
     {
       "epoch": 2.02,
-      "learning_rate": 9.880952380952381e-05,
-      "loss": 0.6101,
+      "learning_rate": 0.0,
+      "loss": 0.4756,
       "step": 170
     },
     {
       "epoch": 2.14,
-      "learning_rate": 9.285714285714286e-05,
-      "loss": 0.5271,
+      "learning_rate": 0.0,
+      "loss": 0.4893,
       "step": 180
     },
     {
       "epoch": 2.26,
-      "learning_rate": 8.690476190476192e-05,
-      "loss": 0.5345,
+      "learning_rate": 0.0,
+      "loss": 0.553,
       "step": 190
     },
     {
       "epoch": 2.38,
-      "learning_rate": 8.095238095238096e-05,
-      "loss": 0.5322,
+      "learning_rate": 0.0,
+      "loss": 0.5523,
       "step": 200
     },
     {
       "epoch": 2.38,
       "eval_accuracy": 0.8987341772151899,
       "eval_loss": 0.3074355721473694,
-      "eval_runtime": 2.419,
-      "eval_samples_per_second": 97.975,
-      "eval_steps_per_second": 12.402,
+      "eval_runtime": 2.4171,
+      "eval_samples_per_second": 98.05,
+      "eval_steps_per_second": 12.411,
       "step": 200
     },
     {
       "epoch": 2.5,
-      "learning_rate": 7.500000000000001e-05,
-      "loss": 0.5904,
+      "learning_rate": 0.0,
+      "loss": 0.5049,
       "step": 210
     },
     {
       "epoch": 2.62,
-      "learning_rate": 6.904761904761905e-05,
-      "loss": 0.4328,
+      "learning_rate": 0.0,
+      "loss": 0.4306,
       "step": 220
     },
     {
       "epoch": 2.74,
-      "learning_rate": 6.30952380952381e-05,
-      "loss": 0.4631,
+      "learning_rate": 0.0,
+      "loss": 0.4699,
       "step": 230
     },
     {
       "epoch": 2.86,
-      "learning_rate": 5.714285714285714e-05,
-      "loss": 0.5723,
+      "learning_rate": 0.0,
+      "loss": 0.5013,
       "step": 240
     },
     {
       "epoch": 2.98,
-      "learning_rate": 5.119047619047619e-05,
-      "loss": 0.4674,
+      "learning_rate": 0.0,
+      "loss": 0.509,
       "step": 250
     },
     {
       "epoch": 3.1,
-      "learning_rate": 4.523809523809524e-05,
-      "loss": 0.3898,
+      "learning_rate": 0.0,
+      "loss": 0.4949,
       "step": 260
     },
     {
       "epoch": 3.21,
-      "learning_rate": 3.928571428571429e-05,
-      "loss": 0.4035,
+      "learning_rate": 0.0,
+      "loss": 0.5185,
       "step": 270
     },
     {
       "epoch": 3.33,
-      "learning_rate": 3.3333333333333335e-05,
-      "loss": 0.3686,
+      "learning_rate": 0.0,
+      "loss": 0.469,
       "step": 280
     },
     {
       "epoch": 3.45,
-      "learning_rate": 2.7380952380952383e-05,
-      "loss": 0.4226,
+      "learning_rate": 0.0,
+      "loss": 0.5256,
       "step": 290
     },
     {
       "epoch": 3.57,
-      "learning_rate": 2.1428571428571428e-05,
-      "loss": 0.458,
+      "learning_rate": 0.0,
+      "loss": 0.4472,
       "step": 300
     },
     {
       "epoch": 3.57,
-      "eval_accuracy": 0.8776371308016878,
-      "eval_loss": 0.34819480776786804,
-      "eval_runtime": 2.3929,
-      "eval_samples_per_second": 99.042,
-      "eval_steps_per_second": 12.537,
+      "eval_accuracy": 0.8987341772151899,
+      "eval_loss": 0.3074355721473694,
+      "eval_runtime": 2.4655,
+      "eval_samples_per_second": 96.127,
+      "eval_steps_per_second": 12.168,
       "step": 300
     },
     {
       "epoch": 3.69,
-      "learning_rate": 1.5476190476190476e-05,
-      "loss": 0.506,
+      "learning_rate": 0.0,
+      "loss": 0.4371,
       "step": 310
     },
     {
       "epoch": 3.81,
-      "learning_rate": 9.523809523809523e-06,
-      "loss": 0.3503,
+      "learning_rate": 0.0,
+      "loss": 0.5614,
       "step": 320
     },
     {
       "epoch": 3.93,
-      "learning_rate": 3.5714285714285714e-06,
-      "loss": 0.416,
+      "learning_rate": 0.0,
+      "loss": 0.4989,
       "step": 330
     },
     {
       "epoch": 4.0,
       "step": 336,
       "total_flos": 4.156707577848054e+17,
-      "train_loss": 0.5616364919003987,
-      "train_runtime": 127.6942,
-      "train_samples_per_second": 42.007,
-      "train_steps_per_second": 2.631
+      "train_loss": 0.4933107083752042,
+      "train_runtime": 131.5099,
+      "train_samples_per_second": 40.788,
+      "train_steps_per_second": 2.555
     }
   ],
   "max_steps": 336,