End of training

all_results.json

@@ -2,12 +2,12 @@
     "epoch": 59.94,
     "eval_accuracy": 1.0,
     "eval_loss": 0.028991766273975372,
-    "eval_runtime": 3.8464,
-    "eval_samples_per_second": 15.339,
-    "eval_steps_per_second": 0.52,
+    "eval_runtime": 3.8287,
+    "eval_samples_per_second": 15.41,
+    "eval_steps_per_second": 0.522,
     "total_flos": 7.88616702456404e+17,
-    "train_loss": 0.4937874893347422,
-    "train_runtime": 3820.3512,
-    "train_samples_per_second": 8.308,
-    "train_steps_per_second": 0.063
+    "train_loss": 0.267316605647405,
+    "train_runtime": 6314.82,
+    "train_samples_per_second": 5.026,
+    "train_steps_per_second": 0.038
 }

eval_results.json

@@ -2,7 +2,7 @@
     "epoch": 59.94,
     "eval_accuracy": 1.0,
     "eval_loss": 0.028991766273975372,
-    "eval_runtime": 3.8464,
-    "eval_samples_per_second": 15.339,
-    "eval_steps_per_second": 0.52
+    "eval_runtime": 3.8287,
+    "eval_samples_per_second": 15.41,
+    "eval_steps_per_second": 0.522
 }

runs/Dec21_12-30-01_93f77f96eef0/events.out.tfevents.1671637263.93f77f96eef0.928.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cb4b4e90866e8ccdf05e317e90024e36123d8d6458ae5a0243d9aed1df8e133
+size 363

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 59.94,
     "total_flos": 7.88616702456404e+17,
-    "train_loss": 0.4937874893347422,
-    "train_runtime": 3820.3512,
-    "train_samples_per_second": 8.308,
-    "train_steps_per_second": 0.063
+    "train_loss": 0.267316605647405,
+    "train_runtime": 6314.82,
+    "train_samples_per_second": 5.026,
+    "train_steps_per_second": 0.038
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_metric": 1.0,
-  "best_model_checkpoint": "delivery_truck_classification/checkpoint-172",
+  "best_model_checkpoint": "delivery_truck_classification/checkpoint-4",
   "epoch": 59.94117647058823,
   "global_step": 240,
   "is_hyper_param_search": false,
@@ -9,624 +9,624 @@
   "log_history": [
     {
       "epoch": 0.94,
-      "eval_accuracy": 0.1864406779661017,
-      "eval_loss": 1.9123966693878174,
-      "eval_runtime": 3.7131,
-      "eval_samples_per_second": 15.89,
-      "eval_steps_per_second": 0.539,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7584,
+      "eval_samples_per_second": 15.698,
+      "eval_steps_per_second": 0.532,
       "step": 4
     },
     {
       "epoch": 1.94,
-      "eval_accuracy": 0.23728813559322035,
-      "eval_loss": 1.8094592094421387,
-      "eval_runtime": 4.4625,
-      "eval_samples_per_second": 13.221,
-      "eval_steps_per_second": 0.448,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.805,
+      "eval_samples_per_second": 15.506,
+      "eval_steps_per_second": 0.526,
       "step": 8
     },
     {
       "epoch": 2.94,
-      "eval_accuracy": 0.3898305084745763,
-      "eval_loss": 1.6757333278656006,
-      "eval_runtime": 3.88,
-      "eval_samples_per_second": 15.206,
-      "eval_steps_per_second": 0.515,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7489,
+      "eval_samples_per_second": 15.738,
+      "eval_steps_per_second": 0.533,
       "step": 12
     },
     {
       "epoch": 3.94,
-      "eval_accuracy": 0.5254237288135594,
-      "eval_loss": 1.4906411170959473,
-      "eval_runtime": 3.788,
-      "eval_samples_per_second": 15.576,
-      "eval_steps_per_second": 0.528,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.8228,
+      "eval_samples_per_second": 15.434,
+      "eval_steps_per_second": 0.523,
       "step": 16
     },
     {
       "epoch": 4.94,
-      "learning_rate": 4.166666666666667e-05,
-      "loss": 1.8286,
+      "learning_rate": 0.0,
+      "loss": 0.2595,
       "step": 20
     },
     {
       "epoch": 4.94,
-      "eval_accuracy": 0.6440677966101694,
-      "eval_loss": 1.2703886032104492,
-      "eval_runtime": 4.208,
-      "eval_samples_per_second": 14.021,
-      "eval_steps_per_second": 0.475,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7534,
+      "eval_samples_per_second": 15.719,
+      "eval_steps_per_second": 0.533,
       "step": 20
     },
     {
       "epoch": 5.94,
-      "eval_accuracy": 0.6779661016949152,
-      "eval_loss": 1.0685124397277832,
-      "eval_runtime": 3.8096,
-      "eval_samples_per_second": 15.487,
-      "eval_steps_per_second": 0.525,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7496,
+      "eval_samples_per_second": 15.735,
+      "eval_steps_per_second": 0.533,
       "step": 24
     },
     {
       "epoch": 6.94,
-      "eval_accuracy": 0.7457627118644068,
-      "eval_loss": 0.8031855225563049,
-      "eval_runtime": 4.1542,
-      "eval_samples_per_second": 14.203,
-      "eval_steps_per_second": 0.481,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.798,
+      "eval_samples_per_second": 15.534,
+      "eval_steps_per_second": 0.527,
       "step": 28
     },
     {
       "epoch": 7.94,
-      "eval_accuracy": 0.7627118644067796,
-      "eval_loss": 0.6308717131614685,
-      "eval_runtime": 3.7602,
-      "eval_samples_per_second": 15.691,
-      "eval_steps_per_second": 0.532,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7322,
+      "eval_samples_per_second": 15.808,
+      "eval_steps_per_second": 0.536,
       "step": 32
     },
     {
       "epoch": 8.94,
-      "eval_accuracy": 0.847457627118644,
-      "eval_loss": 0.49890831112861633,
-      "eval_runtime": 4.1569,
-      "eval_samples_per_second": 14.193,
-      "eval_steps_per_second": 0.481,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7416,
+      "eval_samples_per_second": 15.769,
+      "eval_steps_per_second": 0.535,
       "step": 36
     },
     {
       "epoch": 9.94,
-      "learning_rate": 4.62962962962963e-05,
-      "loss": 0.9342,
+      "learning_rate": 0.0,
+      "loss": 0.2679,
       "step": 40
     },
     {
       "epoch": 9.94,
-      "eval_accuracy": 0.847457627118644,
-      "eval_loss": 0.40634387731552124,
-      "eval_runtime": 3.8202,
-      "eval_samples_per_second": 15.444,
-      "eval_steps_per_second": 0.524,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7284,
+      "eval_samples_per_second": 15.824,
+      "eval_steps_per_second": 0.536,
       "step": 40
     },
     {
       "epoch": 10.94,
-      "eval_accuracy": 0.9152542372881356,
-      "eval_loss": 0.26924625039100647,
-      "eval_runtime": 4.1384,
-      "eval_samples_per_second": 14.257,
-      "eval_steps_per_second": 0.483,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.726,
+      "eval_samples_per_second": 15.835,
+      "eval_steps_per_second": 0.537,
       "step": 44
     },
     {
       "epoch": 11.94,
-      "eval_accuracy": 0.8983050847457628,
-      "eval_loss": 0.27362605929374695,
-      "eval_runtime": 3.707,
-      "eval_samples_per_second": 15.916,
-      "eval_steps_per_second": 0.54,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7864,
+      "eval_samples_per_second": 15.582,
+      "eval_steps_per_second": 0.528,
       "step": 48
     },
     {
       "epoch": 12.94,
-      "eval_accuracy": 0.9322033898305084,
-      "eval_loss": 0.21159349381923676,
-      "eval_runtime": 4.0712,
-      "eval_samples_per_second": 14.492,
-      "eval_steps_per_second": 0.491,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.8076,
+      "eval_samples_per_second": 15.495,
+      "eval_steps_per_second": 0.525,
       "step": 52
     },
     {
       "epoch": 13.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.1497751921415329,
-      "eval_runtime": 3.629,
-      "eval_samples_per_second": 16.258,
-      "eval_steps_per_second": 0.551,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7937,
+      "eval_samples_per_second": 15.552,
+      "eval_steps_per_second": 0.527,
       "step": 56
     },
     {
       "epoch": 14.94,
-      "learning_rate": 4.166666666666667e-05,
-      "loss": 0.5151,
+      "learning_rate": 0.0,
+      "loss": 0.275,
       "step": 60
     },
     {
       "epoch": 14.94,
-      "eval_accuracy": 0.9152542372881356,
-      "eval_loss": 0.1906394362449646,
-      "eval_runtime": 4.159,
-      "eval_samples_per_second": 14.186,
-      "eval_steps_per_second": 0.481,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7461,
+      "eval_samples_per_second": 15.75,
+      "eval_steps_per_second": 0.534,
       "step": 60
     },
     {
       "epoch": 15.94,
-      "eval_accuracy": 0.9491525423728814,
-      "eval_loss": 0.16975143551826477,
-      "eval_runtime": 3.7313,
-      "eval_samples_per_second": 15.812,
-      "eval_steps_per_second": 0.536,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.8277,
+      "eval_samples_per_second": 15.414,
+      "eval_steps_per_second": 0.523,
       "step": 64
     },
     {
       "epoch": 16.94,
-      "eval_accuracy": 0.9491525423728814,
-      "eval_loss": 0.1431875377893448,
-      "eval_runtime": 4.1272,
-      "eval_samples_per_second": 14.295,
-      "eval_steps_per_second": 0.485,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.764,
+      "eval_samples_per_second": 15.675,
+      "eval_steps_per_second": 0.531,
       "step": 68
     },
     {
       "epoch": 17.94,
-      "eval_accuracy": 0.9322033898305084,
-      "eval_loss": 0.16815055906772614,
-      "eval_runtime": 3.6724,
-      "eval_samples_per_second": 16.066,
-      "eval_steps_per_second": 0.545,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7719,
+      "eval_samples_per_second": 15.642,
+      "eval_steps_per_second": 0.53,
       "step": 72
     },
     {
       "epoch": 18.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.10692509263753891,
-      "eval_runtime": 4.1232,
-      "eval_samples_per_second": 14.309,
-      "eval_steps_per_second": 0.485,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.826,
+      "eval_samples_per_second": 15.421,
+      "eval_steps_per_second": 0.523,
       "step": 76
     },
     {
       "epoch": 19.94,
-      "learning_rate": 3.7037037037037037e-05,
-      "loss": 0.4009,
+      "learning_rate": 0.0,
+      "loss": 0.248,
       "step": 80
     },
     {
       "epoch": 19.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.08214119076728821,
-      "eval_runtime": 3.6886,
-      "eval_samples_per_second": 15.995,
-      "eval_steps_per_second": 0.542,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7289,
+      "eval_samples_per_second": 15.822,
+      "eval_steps_per_second": 0.536,
       "step": 80
     },
     {
       "epoch": 20.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.09025811403989792,
-      "eval_runtime": 4.3053,
-      "eval_samples_per_second": 13.704,
-      "eval_steps_per_second": 0.465,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7427,
+      "eval_samples_per_second": 15.764,
+      "eval_steps_per_second": 0.534,
       "step": 84
     },
     {
       "epoch": 21.94,
-      "eval_accuracy": 0.9661016949152542,
-      "eval_loss": 0.12810270488262177,
-      "eval_runtime": 3.7203,
-      "eval_samples_per_second": 15.859,
-      "eval_steps_per_second": 0.538,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.6831,
+      "eval_samples_per_second": 16.019,
+      "eval_steps_per_second": 0.543,
       "step": 88
     },
     {
       "epoch": 22.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.09356144815683365,
-      "eval_runtime": 4.118,
-      "eval_samples_per_second": 14.328,
-      "eval_steps_per_second": 0.486,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.764,
+      "eval_samples_per_second": 15.675,
+      "eval_steps_per_second": 0.531,
       "step": 92
     },
     {
       "epoch": 23.94,
-      "eval_accuracy": 0.9661016949152542,
-      "eval_loss": 0.10591834783554077,
-      "eval_runtime": 3.6933,
-      "eval_samples_per_second": 15.975,
-      "eval_steps_per_second": 0.542,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7309,
+      "eval_samples_per_second": 15.814,
+      "eval_steps_per_second": 0.536,
       "step": 96
     },
     {
       "epoch": 24.94,
-      "learning_rate": 3.240740740740741e-05,
-      "loss": 0.3482,
+      "learning_rate": 0.0,
+      "loss": 0.2669,
       "step": 100
     },
     {
       "epoch": 24.94,
-      "eval_accuracy": 0.9491525423728814,
-      "eval_loss": 0.14312368631362915,
-      "eval_runtime": 4.1639,
-      "eval_samples_per_second": 14.169,
-      "eval_steps_per_second": 0.48,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7661,
+      "eval_samples_per_second": 15.666,
+      "eval_steps_per_second": 0.531,
       "step": 100
     },
     {
       "epoch": 25.94,
-      "eval_accuracy": 0.9661016949152542,
-      "eval_loss": 0.08986904472112656,
-      "eval_runtime": 3.7088,
-      "eval_samples_per_second": 15.908,
-      "eval_steps_per_second": 0.539,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.682,
+      "eval_samples_per_second": 16.024,
+      "eval_steps_per_second": 0.543,
       "step": 104
     },
     {
       "epoch": 26.94,
-      "eval_accuracy": 0.9661016949152542,
-      "eval_loss": 0.06888163089752197,
-      "eval_runtime": 4.1304,
-      "eval_samples_per_second": 14.284,
-      "eval_steps_per_second": 0.484,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7339,
+      "eval_samples_per_second": 15.801,
+      "eval_steps_per_second": 0.536,
       "step": 108
     },
     {
       "epoch": 27.94,
-      "eval_accuracy": 0.9661016949152542,
-      "eval_loss": 0.07510155439376831,
-      "eval_runtime": 3.7462,
-      "eval_samples_per_second": 15.749,
-      "eval_steps_per_second": 0.534,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.8015,
+      "eval_samples_per_second": 15.52,
+      "eval_steps_per_second": 0.526,
       "step": 112
     },
     {
       "epoch": 28.94,
-      "eval_accuracy": 0.9661016949152542,
-      "eval_loss": 0.08912018686532974,
-      "eval_runtime": 3.7992,
-      "eval_samples_per_second": 15.53,
-      "eval_steps_per_second": 0.526,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7232,
+      "eval_samples_per_second": 15.846,
+      "eval_steps_per_second": 0.537,
       "step": 116
     },
     {
       "epoch": 29.94,
-      "learning_rate": 2.777777777777778e-05,
-      "loss": 0.3306,
+      "learning_rate": 0.0,
+      "loss": 0.2589,
       "step": 120
     },
     {
       "epoch": 29.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.05226200073957443,
-      "eval_runtime": 4.2109,
-      "eval_samples_per_second": 14.011,
-      "eval_steps_per_second": 0.475,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7329,
+      "eval_samples_per_second": 15.805,
+      "eval_steps_per_second": 0.536,
       "step": 120
     },
     {
       "epoch": 30.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.07344209402799606,
-      "eval_runtime": 3.9025,
-      "eval_samples_per_second": 15.118,
-      "eval_steps_per_second": 0.512,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7815,
+      "eval_samples_per_second": 15.602,
+      "eval_steps_per_second": 0.529,
       "step": 124
     },
     {
       "epoch": 31.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.07462318241596222,
-      "eval_runtime": 4.1592,
-      "eval_samples_per_second": 14.185,
-      "eval_steps_per_second": 0.481,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7496,
+      "eval_samples_per_second": 15.735,
+      "eval_steps_per_second": 0.533,
       "step": 128
     },
     {
       "epoch": 32.94,
-      "eval_accuracy": 0.9661016949152542,
-      "eval_loss": 0.04742526262998581,
-      "eval_runtime": 3.8091,
-      "eval_samples_per_second": 15.489,
-      "eval_steps_per_second": 0.525,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7126,
+      "eval_samples_per_second": 15.892,
+      "eval_steps_per_second": 0.539,
       "step": 132
     },
     {
       "epoch": 33.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.044318120926618576,
-      "eval_runtime": 3.7853,
-      "eval_samples_per_second": 15.587,
-      "eval_steps_per_second": 0.528,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.6855,
+      "eval_samples_per_second": 16.009,
+      "eval_steps_per_second": 0.543,
       "step": 136
     },
     {
       "epoch": 34.94,
-      "learning_rate": 2.314814814814815e-05,
-      "loss": 0.2871,
+      "learning_rate": 0.0,
+      "loss": 0.278,
       "step": 140
     },
     {
       "epoch": 34.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.08141448348760605,
-      "eval_runtime": 4.1875,
-      "eval_samples_per_second": 14.09,
-      "eval_steps_per_second": 0.478,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7784,
+      "eval_samples_per_second": 15.615,
+      "eval_steps_per_second": 0.529,
       "step": 140
     },
     {
       "epoch": 35.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.0690697729587555,
-      "eval_runtime": 3.7869,
-      "eval_samples_per_second": 15.58,
-      "eval_steps_per_second": 0.528,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7189,
+      "eval_samples_per_second": 15.865,
+      "eval_steps_per_second": 0.538,
       "step": 144
     },
     {
       "epoch": 36.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.053145911544561386,
-      "eval_runtime": 4.1845,
-      "eval_samples_per_second": 14.1,
-      "eval_steps_per_second": 0.478,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7865,
+      "eval_samples_per_second": 15.582,
+      "eval_steps_per_second": 0.528,
       "step": 148
     },
     {
       "epoch": 37.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.06143573671579361,
-      "eval_runtime": 3.7811,
-      "eval_samples_per_second": 15.604,
-      "eval_steps_per_second": 0.529,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7161,
+      "eval_samples_per_second": 15.877,
+      "eval_steps_per_second": 0.538,
       "step": 152
     },
     {
       "epoch": 38.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.057755034416913986,
-      "eval_runtime": 4.2237,
-      "eval_samples_per_second": 13.969,
-      "eval_steps_per_second": 0.474,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7413,
+      "eval_samples_per_second": 15.77,
+      "eval_steps_per_second": 0.535,
       "step": 156
     },
     {
       "epoch": 39.94,
-      "learning_rate": 1.8518518518518518e-05,
-      "loss": 0.2754,
+      "learning_rate": 0.0,
+      "loss": 0.273,
       "step": 160
     },
     {
       "epoch": 39.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.05201863497495651,
-      "eval_runtime": 3.7528,
-      "eval_samples_per_second": 15.722,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7504,
+      "eval_samples_per_second": 15.732,
       "eval_steps_per_second": 0.533,
       "step": 160
     },
     {
       "epoch": 40.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.05365251377224922,
-      "eval_runtime": 3.7906,
-      "eval_samples_per_second": 15.565,
-      "eval_steps_per_second": 0.528,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7301,
+      "eval_samples_per_second": 15.817,
+      "eval_steps_per_second": 0.536,
       "step": 164
     },
     {
       "epoch": 41.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.04466838762164116,
-      "eval_runtime": 4.0883,
-      "eval_samples_per_second": 14.432,
-      "eval_steps_per_second": 0.489,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.6896,
+      "eval_samples_per_second": 15.991,
+      "eval_steps_per_second": 0.542,
       "step": 168
     },
     {
       "epoch": 42.94,
       "eval_accuracy": 1.0,
       "eval_loss": 0.028991766273975372,
-      "eval_runtime": 3.7894,
-      "eval_samples_per_second": 15.57,
-      "eval_steps_per_second": 0.528,
+      "eval_runtime": 3.8409,
+      "eval_samples_per_second": 15.361,
+      "eval_steps_per_second": 0.521,
       "step": 172
     },
     {
       "epoch": 43.94,
       "eval_accuracy": 1.0,
-      "eval_loss": 0.029105449095368385,
-      "eval_runtime": 4.1829,
-      "eval_samples_per_second": 14.105,
-      "eval_steps_per_second": 0.478,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7381,
+      "eval_samples_per_second": 15.783,
+      "eval_steps_per_second": 0.535,
       "step": 176
     },
     {
       "epoch": 44.94,
-      "learning_rate": 1.388888888888889e-05,
-      "loss": 0.269,
+      "learning_rate": 0.0,
+      "loss": 0.2535,
       "step": 180
     },
     {
       "epoch": 44.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.03256472200155258,
-      "eval_runtime": 3.7585,
-      "eval_samples_per_second": 15.698,
-      "eval_steps_per_second": 0.532,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7521,
+      "eval_samples_per_second": 15.724,
+      "eval_steps_per_second": 0.533,
       "step": 180
     },
     {
       "epoch": 45.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.03297417610883713,
-      "eval_runtime": 4.155,
-      "eval_samples_per_second": 14.2,
-      "eval_steps_per_second": 0.481,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7759,
+      "eval_samples_per_second": 15.625,
+      "eval_steps_per_second": 0.53,
       "step": 184
     },
     {
       "epoch": 46.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.034774668514728546,
-      "eval_runtime": 3.7675,
-      "eval_samples_per_second": 15.66,
-      "eval_steps_per_second": 0.531,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7894,
+      "eval_samples_per_second": 15.57,
+      "eval_steps_per_second": 0.528,
       "step": 188
     },
     {
       "epoch": 47.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.03467889130115509,
-      "eval_runtime": 4.0766,
-      "eval_samples_per_second": 14.473,
-      "eval_steps_per_second": 0.491,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7432,
+      "eval_samples_per_second": 15.762,
+      "eval_steps_per_second": 0.534,
       "step": 192
     },
     {
       "epoch": 48.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.03474270924925804,
-      "eval_runtime": 3.7643,
-      "eval_samples_per_second": 15.674,
-      "eval_steps_per_second": 0.531,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7921,
+      "eval_samples_per_second": 15.559,
+      "eval_steps_per_second": 0.527,
       "step": 196
     },
     {
       "epoch": 49.94,
-      "learning_rate": 9.259259259259259e-06,
-      "loss": 0.2615,
+      "learning_rate": 0.0,
+      "loss": 0.2762,
       "step": 200
     },
     {
       "epoch": 49.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.04243284463882446,
-      "eval_runtime": 4.0985,
-      "eval_samples_per_second": 14.395,
-      "eval_steps_per_second": 0.488,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.8149,
+      "eval_samples_per_second": 15.466,
+      "eval_steps_per_second": 0.524,
       "step": 200
     },
     {
       "epoch": 50.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.04514499008655548,
-      "eval_runtime": 3.9491,
-      "eval_samples_per_second": 14.94,
-      "eval_steps_per_second": 0.506,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7494,
+      "eval_samples_per_second": 15.736,
+      "eval_steps_per_second": 0.533,
       "step": 204
     },
     {
       "epoch": 51.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.043262287974357605,
-      "eval_runtime": 3.6957,
-      "eval_samples_per_second": 15.964,
-      "eval_steps_per_second": 0.541,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.758,
+      "eval_samples_per_second": 15.7,
+      "eval_steps_per_second": 0.532,
       "step": 208
     },
     {
       "epoch": 52.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.035157691687345505,
-      "eval_runtime": 4.172,
-      "eval_samples_per_second": 14.142,
-      "eval_steps_per_second": 0.479,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 4.5125,
+      "eval_samples_per_second": 13.075,
+      "eval_steps_per_second": 0.443,
       "step": 212
     },
     {
       "epoch": 53.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.03394060581922531,
-      "eval_runtime": 3.7213,
-      "eval_samples_per_second": 15.855,
-      "eval_steps_per_second": 0.537,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.6913,
+      "eval_samples_per_second": 15.983,
+      "eval_steps_per_second": 0.542,
       "step": 216
     },
     {
       "epoch": 54.94,
-      "learning_rate": 4.6296296296296296e-06,
-      "loss": 0.2386,
+      "learning_rate": 0.0,
+      "loss": 0.2798,
       "step": 220
     },
     {
       "epoch": 54.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.03394594043493271,
-      "eval_runtime": 4.1524,
-      "eval_samples_per_second": 14.208,
-      "eval_steps_per_second": 0.482,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7635,
+      "eval_samples_per_second": 15.677,
+      "eval_steps_per_second": 0.531,
       "step": 220
     },
     {
       "epoch": 55.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.03388730436563492,
-      "eval_runtime": 3.719,
-      "eval_samples_per_second": 15.864,
-      "eval_steps_per_second": 0.538,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7464,
+      "eval_samples_per_second": 15.748,
+      "eval_steps_per_second": 0.534,
       "step": 224
     },
     {
       "epoch": 56.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.034843575209379196,
-      "eval_runtime": 4.1514,
-      "eval_samples_per_second": 14.212,
-      "eval_steps_per_second": 0.482,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7621,
+      "eval_samples_per_second": 15.683,
+      "eval_steps_per_second": 0.532,
       "step": 228
     },
     {
       "epoch": 57.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.03663792461156845,
-      "eval_runtime": 3.7689,
-      "eval_samples_per_second": 15.654,
-      "eval_steps_per_second": 0.531,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7552,
+      "eval_samples_per_second": 15.712,
+      "eval_steps_per_second": 0.533,
       "step": 232
     },
     {
       "epoch": 58.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.03743705153465271,
-      "eval_runtime": 4.1165,
-      "eval_samples_per_second": 14.333,
-      "eval_steps_per_second": 0.486,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.8189,
+      "eval_samples_per_second": 15.449,
+      "eval_steps_per_second": 0.524,
       "step": 236
     },
     {
       "epoch": 59.94,
       "learning_rate": 0.0,
-      "loss": 0.2362,
+      "loss": 0.2709,
       "step": 240
     },
     {
       "epoch": 59.94,
-      "eval_accuracy": 0.9830508474576272,
-      "eval_loss": 0.03746996819972992,
-      "eval_runtime": 3.7404,
-      "eval_samples_per_second": 15.774,
-      "eval_steps_per_second": 0.535,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.028991766273975372,
+      "eval_runtime": 3.7206,
+      "eval_samples_per_second": 15.858,
+      "eval_steps_per_second": 0.538,
       "step": 240
     },
     {
       "epoch": 59.94,
       "step": 240,
       "total_flos": 7.88616702456404e+17,
-      "train_loss": 0.4937874893347422,
-      "train_runtime": 3820.3512,
-      "train_samples_per_second": 8.308,
-      "train_steps_per_second": 0.063
+      "train_loss": 0.267316605647405,
+      "train_runtime": 6314.82,
+      "train_samples_per_second": 5.026,
+      "train_steps_per_second": 0.038
     }
   ],
   "max_steps": 240,