End of training

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 2.99,
-    "eval_accuracy": 0.9064,
-    "eval_loss": 0.2777732014656067,
-    "eval_runtime": 126.0372,
-    "eval_samples_per_second": 119.013,
-    "eval_steps_per_second": 3.721,
+    "eval_accuracy": 0.10166666666666667,
+    "eval_loss": NaN,
+    "eval_runtime": 135.6867,
+    "eval_samples_per_second": 110.549,
+    "eval_steps_per_second": 3.456,
     "total_flos": 1.0585264325663785e+18,
-    "train_loss": 0.9103804560371371,
-    "train_runtime": 753.233,
-    "train_samples_per_second": 139.399,
-    "train_steps_per_second": 1.087
+    "train_loss": 0.0,
+    "train_runtime": 811.0273,
+    "train_samples_per_second": 129.465,
+    "train_steps_per_second": 1.01
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.99,
-    "eval_accuracy": 0.9064,
-    "eval_loss": 0.2777732014656067,
-    "eval_runtime": 126.0372,
-    "eval_samples_per_second": 119.013,
-    "eval_steps_per_second": 3.721
+    "eval_accuracy": 0.10166666666666667,
+    "eval_loss": NaN,
+    "eval_runtime": 135.6867,
+    "eval_samples_per_second": 110.549,
+    "eval_steps_per_second": 3.456
 }

runs/Apr07_14-53-27_9b51f9451925/events.out.tfevents.1712502568.9b51f9451925.6697.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:936dea077f72a96abdf489ed31dba84951ee3bac2625c560dbeca6a6348ccae9
+size 411

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.99,
     "total_flos": 1.0585264325663785e+18,
-    "train_loss": 0.9103804560371371,
-    "train_runtime": 753.233,
-    "train_samples_per_second": 139.399,
-    "train_steps_per_second": 1.087
+    "train_loss": 0.0,
+    "train_runtime": 811.0273,
+    "train_samples_per_second": 129.465,
+    "train_steps_per_second": 1.01
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.9064,
-  "best_model_checkpoint": "resnet-18-finetuned-cifar10/checkpoint-819",
+  "best_metric": 0.10166666666666667,
+  "best_model_checkpoint": "resnet-18-finetuned-cifar10/checkpoint-273",
   "epoch": 2.9945155393053016,
   "eval_steps": 500,
   "global_step": 819,
@@ -10,606 +10,606 @@
   "log_history": [
     {
       "epoch": 0.04,
-      "grad_norm": 16.46918296813965,
+      "grad_norm": NaN,
       "learning_rate": 6.0975609756097564e-06,
-      "loss": 3.2109,
+      "loss": 0.0,
       "step": 10
     },
     {
       "epoch": 0.07,
-      "grad_norm": 22.162967681884766,
+      "grad_norm": NaN,
       "learning_rate": 1.2195121951219513e-05,
-      "loss": 2.929,
+      "loss": 0.0,
       "step": 20
     },
     {
       "epoch": 0.11,
-      "grad_norm": 18.4061336517334,
+      "grad_norm": NaN,
       "learning_rate": 1.8292682926829268e-05,
-      "loss": 2.6339,
+      "loss": 0.0,
       "step": 30
     },
     {
       "epoch": 0.15,
-      "grad_norm": 14.292740821838379,
+      "grad_norm": NaN,
       "learning_rate": 2.4390243902439026e-05,
-      "loss": 2.2668,
+      "loss": 0.0,
       "step": 40
     },
     {
       "epoch": 0.18,
-      "grad_norm": 15.263444900512695,
+      "grad_norm": NaN,
       "learning_rate": 3.048780487804878e-05,
-      "loss": 1.947,
+      "loss": 0.0,
       "step": 50
     },
     {
       "epoch": 0.22,
-      "grad_norm": 18.372751235961914,
+      "grad_norm": NaN,
       "learning_rate": 3.6585365853658535e-05,
-      "loss": 1.7001,
+      "loss": 0.0,
       "step": 60
     },
     {
       "epoch": 0.26,
-      "grad_norm": 14.107364654541016,
+      "grad_norm": NaN,
       "learning_rate": 4.26829268292683e-05,
-      "loss": 1.4365,
+      "loss": 0.0,
       "step": 70
     },
     {
       "epoch": 0.29,
-      "grad_norm": 11.996474266052246,
+      "grad_norm": NaN,
       "learning_rate": 4.878048780487805e-05,
-      "loss": 1.3653,
+      "loss": 0.0,
       "step": 80
     },
     {
       "epoch": 0.33,
-      "grad_norm": 13.601606369018555,
+      "grad_norm": NaN,
       "learning_rate": 4.94572591587517e-05,
-      "loss": 1.2311,
+      "loss": 0.0,
       "step": 90
     },
     {
       "epoch": 0.37,
-      "grad_norm": 12.406356811523438,
+      "grad_norm": NaN,
       "learning_rate": 4.877883310719132e-05,
-      "loss": 1.2409,
+      "loss": 0.0,
       "step": 100
     },
     {
       "epoch": 0.4,
-      "grad_norm": 10.42392349243164,
+      "grad_norm": NaN,
       "learning_rate": 4.810040705563094e-05,
-      "loss": 1.1009,
+      "loss": 0.0,
       "step": 110
     },
     {
       "epoch": 0.44,
-      "grad_norm": 11.649271011352539,
+      "grad_norm": NaN,
       "learning_rate": 4.742198100407056e-05,
-      "loss": 1.1132,
+      "loss": 0.0,
       "step": 120
     },
     {
       "epoch": 0.48,
-      "grad_norm": 10.590466499328613,
+      "grad_norm": NaN,
       "learning_rate": 4.674355495251018e-05,
-      "loss": 1.0677,
+      "loss": 0.0,
       "step": 130
     },
     {
       "epoch": 0.51,
-      "grad_norm": 10.409879684448242,
+      "grad_norm": NaN,
       "learning_rate": 4.60651289009498e-05,
-      "loss": 1.0262,
+      "loss": 0.0,
       "step": 140
     },
     {
       "epoch": 0.55,
-      "grad_norm": 11.766679763793945,
+      "grad_norm": NaN,
       "learning_rate": 4.5386702849389416e-05,
-      "loss": 1.0399,
+      "loss": 0.0,
       "step": 150
     },
     {
       "epoch": 0.59,
-      "grad_norm": 10.652596473693848,
+      "grad_norm": NaN,
       "learning_rate": 4.470827679782904e-05,
-      "loss": 1.0203,
+      "loss": 0.0,
       "step": 160
     },
     {
       "epoch": 0.62,
-      "grad_norm": 10.809771537780762,
+      "grad_norm": NaN,
       "learning_rate": 4.402985074626866e-05,
-      "loss": 0.9633,
+      "loss": 0.0,
       "step": 170
     },
     {
       "epoch": 0.66,
-      "grad_norm": 12.764290809631348,
+      "grad_norm": NaN,
       "learning_rate": 4.335142469470828e-05,
-      "loss": 0.9355,
+      "loss": 0.0,
       "step": 180
     },
     {
       "epoch": 0.69,
-      "grad_norm": 10.757213592529297,
+      "grad_norm": NaN,
       "learning_rate": 4.26729986431479e-05,
-      "loss": 0.9337,
+      "loss": 0.0,
       "step": 190
     },
     {
       "epoch": 0.73,
-      "grad_norm": 11.284212112426758,
+      "grad_norm": NaN,
       "learning_rate": 4.199457259158752e-05,
-      "loss": 0.9314,
+      "loss": 0.0,
       "step": 200
     },
     {
       "epoch": 0.77,
-      "grad_norm": 11.635641098022461,
+      "grad_norm": NaN,
       "learning_rate": 4.131614654002714e-05,
-      "loss": 0.8976,
+      "loss": 0.0,
       "step": 210
     },
     {
       "epoch": 0.8,
-      "grad_norm": 10.869036674499512,
+      "grad_norm": NaN,
       "learning_rate": 4.063772048846676e-05,
-      "loss": 0.9065,
+      "loss": 0.0,
       "step": 220
     },
     {
       "epoch": 0.84,
-      "grad_norm": 11.703560829162598,
+      "grad_norm": NaN,
       "learning_rate": 3.995929443690638e-05,
-      "loss": 0.8444,
+      "loss": 0.0,
       "step": 230
     },
     {
       "epoch": 0.88,
-      "grad_norm": 10.33545207977295,
+      "grad_norm": NaN,
       "learning_rate": 3.9280868385345995e-05,
-      "loss": 0.825,
+      "loss": 0.0,
       "step": 240
     },
     {
       "epoch": 0.91,
-      "grad_norm": 7.844155311584473,
+      "grad_norm": NaN,
       "learning_rate": 3.860244233378562e-05,
-      "loss": 0.8369,
+      "loss": 0.0,
       "step": 250
     },
     {
       "epoch": 0.95,
-      "grad_norm": 9.158990859985352,
+      "grad_norm": NaN,
       "learning_rate": 3.792401628222524e-05,
-      "loss": 0.8422,
+      "loss": 0.0,
       "step": 260
     },
     {
       "epoch": 0.99,
-      "grad_norm": 9.740525245666504,
+      "grad_norm": NaN,
       "learning_rate": 3.724559023066486e-05,
-      "loss": 0.8502,
+      "loss": 0.0,
       "step": 270
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.8632,
-      "eval_loss": 0.4063829481601715,
-      "eval_runtime": 123.7138,
-      "eval_samples_per_second": 121.248,
-      "eval_steps_per_second": 3.791,
+      "eval_accuracy": 0.10166666666666667,
+      "eval_loss": NaN,
+      "eval_runtime": 135.8532,
+      "eval_samples_per_second": 110.413,
+      "eval_steps_per_second": 3.452,
       "step": 273
     },
     {
       "epoch": 1.02,
-      "grad_norm": 7.927298069000244,
+      "grad_norm": NaN,
       "learning_rate": 3.656716417910448e-05,
-      "loss": 0.847,
+      "loss": 0.0,
       "step": 280
     },
     {
       "epoch": 1.06,
-      "grad_norm": 9.951263427734375,
+      "grad_norm": NaN,
       "learning_rate": 3.58887381275441e-05,
-      "loss": 0.8189,
+      "loss": 0.0,
       "step": 290
     },
     {
       "epoch": 1.1,
-      "grad_norm": 7.741189479827881,
+      "grad_norm": NaN,
       "learning_rate": 3.521031207598372e-05,
-      "loss": 0.804,
+      "loss": 0.0,
       "step": 300
     },
     {
       "epoch": 1.13,
-      "grad_norm": 8.110347747802734,
+      "grad_norm": NaN,
       "learning_rate": 3.453188602442334e-05,
-      "loss": 0.7829,
+      "loss": 0.0,
       "step": 310
     },
     {
       "epoch": 1.17,
-      "grad_norm": 8.17768669128418,
+      "grad_norm": NaN,
       "learning_rate": 3.385345997286296e-05,
-      "loss": 0.8124,
+      "loss": 0.0,
       "step": 320
     },
     {
       "epoch": 1.21,
-      "grad_norm": 8.95181655883789,
+      "grad_norm": NaN,
       "learning_rate": 3.3175033921302575e-05,
-      "loss": 0.7392,
+      "loss": 0.0,
       "step": 330
     },
     {
       "epoch": 1.24,
-      "grad_norm": 9.440756797790527,
+      "grad_norm": NaN,
       "learning_rate": 3.24966078697422e-05,
-      "loss": 0.8488,
+      "loss": 0.0,
       "step": 340
     },
     {
       "epoch": 1.28,
-      "grad_norm": 8.526937484741211,
+      "grad_norm": NaN,
       "learning_rate": 3.181818181818182e-05,
-      "loss": 0.7525,
+      "loss": 0.0,
       "step": 350
     },
     {
       "epoch": 1.32,
-      "grad_norm": 8.15047836303711,
+      "grad_norm": NaN,
       "learning_rate": 3.113975576662144e-05,
-      "loss": 0.7966,
+      "loss": 0.0,
       "step": 360
     },
     {
       "epoch": 1.35,
-      "grad_norm": 8.909910202026367,
+      "grad_norm": NaN,
       "learning_rate": 3.046132971506106e-05,
-      "loss": 0.7682,
+      "loss": 0.0,
       "step": 370
     },
     {
       "epoch": 1.39,
-      "grad_norm": 9.869742393493652,
+      "grad_norm": NaN,
       "learning_rate": 2.9782903663500678e-05,
-      "loss": 0.7143,
+      "loss": 0.0,
       "step": 380
     },
     {
       "epoch": 1.43,
-      "grad_norm": 9.056320190429688,
+      "grad_norm": NaN,
       "learning_rate": 2.91044776119403e-05,
-      "loss": 0.7467,
+      "loss": 0.0,
       "step": 390
     },
     {
       "epoch": 1.46,
-      "grad_norm": 8.215534210205078,
+      "grad_norm": NaN,
       "learning_rate": 2.842605156037992e-05,
-      "loss": 0.7589,
+      "loss": 0.0,
       "step": 400
     },
     {
       "epoch": 1.5,
-      "grad_norm": 8.56048583984375,
+      "grad_norm": NaN,
       "learning_rate": 2.7747625508819542e-05,
-      "loss": 0.786,
+      "loss": 0.0,
       "step": 410
     },
     {
       "epoch": 1.54,
-      "grad_norm": 7.839065074920654,
+      "grad_norm": NaN,
       "learning_rate": 2.7069199457259158e-05,
-      "loss": 0.7033,
+      "loss": 0.0,
       "step": 420
     },
     {
       "epoch": 1.57,
-      "grad_norm": 8.194784164428711,
+      "grad_norm": NaN,
       "learning_rate": 2.639077340569878e-05,
-      "loss": 0.6867,
+      "loss": 0.0,
       "step": 430
     },
     {
       "epoch": 1.61,
-      "grad_norm": 7.5709547996521,
+      "grad_norm": NaN,
       "learning_rate": 2.57123473541384e-05,
-      "loss": 0.7555,
+      "loss": 0.0,
       "step": 440
     },
     {
       "epoch": 1.65,
-      "grad_norm": 8.456563949584961,
+      "grad_norm": NaN,
       "learning_rate": 2.5033921302578023e-05,
-      "loss": 0.6939,
+      "loss": 0.0,
       "step": 450
     },
     {
       "epoch": 1.68,
-      "grad_norm": 8.453351020812988,
+      "grad_norm": NaN,
       "learning_rate": 2.4355495251017642e-05,
-      "loss": 0.6965,
+      "loss": 0.0,
       "step": 460
     },
     {
       "epoch": 1.72,
-      "grad_norm": 7.400697231292725,
+      "grad_norm": NaN,
       "learning_rate": 2.367706919945726e-05,
-      "loss": 0.7067,
+      "loss": 0.0,
       "step": 470
     },
     {
       "epoch": 1.76,
-      "grad_norm": 8.554298400878906,
+      "grad_norm": NaN,
       "learning_rate": 2.299864314789688e-05,
-      "loss": 0.712,
+      "loss": 0.0,
       "step": 480
     },
     {
       "epoch": 1.79,
-      "grad_norm": 8.703104972839355,
+      "grad_norm": NaN,
       "learning_rate": 2.2320217096336503e-05,
-      "loss": 0.7176,
+      "loss": 0.0,
       "step": 490
     },
     {
       "epoch": 1.83,
-      "grad_norm": 8.274211883544922,
+      "grad_norm": NaN,
       "learning_rate": 2.164179104477612e-05,
-      "loss": 0.7214,
+      "loss": 0.0,
       "step": 500
     },
     {
       "epoch": 1.86,
-      "grad_norm": 10.009110450744629,
+      "grad_norm": NaN,
       "learning_rate": 2.0963364993215738e-05,
-      "loss": 0.7518,
+      "loss": 0.0,
       "step": 510
     },
     {
       "epoch": 1.9,
-      "grad_norm": 9.217292785644531,
+      "grad_norm": NaN,
       "learning_rate": 2.028493894165536e-05,
-      "loss": 0.7125,
+      "loss": 0.0,
       "step": 520
     },
     {
       "epoch": 1.94,
-      "grad_norm": 7.580327987670898,
+      "grad_norm": NaN,
       "learning_rate": 1.960651289009498e-05,
-      "loss": 0.6731,
+      "loss": 0.0,
       "step": 530
     },
     {
       "epoch": 1.97,
-      "grad_norm": 7.33704137802124,
+      "grad_norm": NaN,
       "learning_rate": 1.89280868385346e-05,
-      "loss": 0.6924,
+      "loss": 0.0,
       "step": 540
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8956,
-      "eval_loss": 0.3149263858795166,
-      "eval_runtime": 128.5203,
-      "eval_samples_per_second": 116.713,
-      "eval_steps_per_second": 3.649,
+      "eval_accuracy": 0.10166666666666667,
+      "eval_loss": NaN,
+      "eval_runtime": 132.0195,
+      "eval_samples_per_second": 113.62,
+      "eval_steps_per_second": 3.553,
       "step": 547
     },
     {
       "epoch": 2.01,
-      "grad_norm": 8.008723258972168,
+      "grad_norm": NaN,
       "learning_rate": 1.824966078697422e-05,
-      "loss": 0.7104,
+      "loss": 0.0,
       "step": 550
     },
     {
       "epoch": 2.05,
-      "grad_norm": 6.283710479736328,
+      "grad_norm": NaN,
       "learning_rate": 1.757123473541384e-05,
-      "loss": 0.6671,
+      "loss": 0.0,
       "step": 560
     },
     {
       "epoch": 2.08,
-      "grad_norm": 7.36352014541626,
+      "grad_norm": NaN,
       "learning_rate": 1.689280868385346e-05,
-      "loss": 0.6464,
+      "loss": 0.0,
       "step": 570
     },
     {
       "epoch": 2.12,
-      "grad_norm": 8.875202178955078,
+      "grad_norm": NaN,
       "learning_rate": 1.6214382632293083e-05,
-      "loss": 0.6495,
+      "loss": 0.0,
       "step": 580
     },
     {
       "epoch": 2.16,
-      "grad_norm": 8.145440101623535,
+      "grad_norm": NaN,
       "learning_rate": 1.55359565807327e-05,
-      "loss": 0.6609,
+      "loss": 0.0,
       "step": 590
     },
     {
       "epoch": 2.19,
-      "grad_norm": 8.108186721801758,
+      "grad_norm": NaN,
       "learning_rate": 1.485753052917232e-05,
-      "loss": 0.7062,
+      "loss": 0.0,
       "step": 600
     },
     {
       "epoch": 2.23,
-      "grad_norm": 7.363587856292725,
+      "grad_norm": NaN,
       "learning_rate": 1.417910447761194e-05,
-      "loss": 0.6395,
+      "loss": 0.0,
       "step": 610
     },
     {
       "epoch": 2.27,
-      "grad_norm": 7.521917343139648,
+      "grad_norm": NaN,
       "learning_rate": 1.3500678426051561e-05,
-      "loss": 0.657,
+      "loss": 0.0,
       "step": 620
     },
     {
       "epoch": 2.3,
-      "grad_norm": 7.513711452484131,
+      "grad_norm": NaN,
       "learning_rate": 1.282225237449118e-05,
-      "loss": 0.6638,
+      "loss": 0.0,
       "step": 630
     },
     {
       "epoch": 2.34,
-      "grad_norm": 8.112990379333496,
+      "grad_norm": NaN,
       "learning_rate": 1.2143826322930801e-05,
-      "loss": 0.6968,
+      "loss": 0.0,
       "step": 640
     },
     {
       "epoch": 2.38,
-      "grad_norm": 7.811177730560303,
+      "grad_norm": NaN,
       "learning_rate": 1.1465400271370422e-05,
-      "loss": 0.7007,
+      "loss": 0.0,
       "step": 650
     },
     {
       "epoch": 2.41,
-      "grad_norm": 7.438766956329346,
+      "grad_norm": NaN,
       "learning_rate": 1.0786974219810041e-05,
-      "loss": 0.6458,
+      "loss": 0.0,
       "step": 660
     },
     {
       "epoch": 2.45,
-      "grad_norm": 9.478456497192383,
+      "grad_norm": NaN,
       "learning_rate": 1.010854816824966e-05,
-      "loss": 0.6534,
+      "loss": 0.0,
       "step": 670
     },
     {
       "epoch": 2.49,
-      "grad_norm": 7.470586776733398,
+      "grad_norm": NaN,
       "learning_rate": 9.430122116689281e-06,
-      "loss": 0.6625,
+      "loss": 0.0,
       "step": 680
     },
     {
       "epoch": 2.52,
-      "grad_norm": 7.3036956787109375,
+      "grad_norm": NaN,
       "learning_rate": 8.751696065128902e-06,
-      "loss": 0.6581,
+      "loss": 0.0,
       "step": 690
     },
     {
       "epoch": 2.56,
-      "grad_norm": 7.530010223388672,
+      "grad_norm": NaN,
       "learning_rate": 8.073270013568522e-06,
-      "loss": 0.6214,
+      "loss": 0.0,
       "step": 700
     },
     {
       "epoch": 2.6,
-      "grad_norm": 6.2767333984375,
+      "grad_norm": NaN,
       "learning_rate": 7.394843962008141e-06,
-      "loss": 0.6136,
+      "loss": 0.0,
       "step": 710
     },
     {
       "epoch": 2.63,
-      "grad_norm": 8.302584648132324,
+      "grad_norm": NaN,
       "learning_rate": 6.716417910447762e-06,
-      "loss": 0.6215,
+      "loss": 0.0,
       "step": 720
     },
     {
       "epoch": 2.67,
-      "grad_norm": 7.744215965270996,
+      "grad_norm": NaN,
       "learning_rate": 6.037991858887382e-06,
-      "loss": 0.6382,
+      "loss": 0.0,
       "step": 730
     },
     {
       "epoch": 2.71,
-      "grad_norm": 7.538488864898682,
+      "grad_norm": NaN,
       "learning_rate": 5.359565807327002e-06,
-      "loss": 0.6239,
+      "loss": 0.0,
       "step": 740
     },
     {
       "epoch": 2.74,
-      "grad_norm": 7.9057488441467285,
+      "grad_norm": NaN,
       "learning_rate": 4.681139755766622e-06,
-      "loss": 0.6413,
+      "loss": 0.0,
       "step": 750
     },
     {
       "epoch": 2.78,
-      "grad_norm": 6.213993549346924,
+      "grad_norm": NaN,
       "learning_rate": 4.002713704206242e-06,
-      "loss": 0.6153,
+      "loss": 0.0,
       "step": 760
     },
     {
       "epoch": 2.82,
-      "grad_norm": 6.704429626464844,
+      "grad_norm": NaN,
       "learning_rate": 3.324287652645862e-06,
-      "loss": 0.6502,
+      "loss": 0.0,
       "step": 770
     },
     {
       "epoch": 2.85,
-      "grad_norm": 10.968541145324707,
+      "grad_norm": NaN,
       "learning_rate": 2.645861601085482e-06,
-      "loss": 0.6439,
+      "loss": 0.0,
       "step": 780
     },
     {
       "epoch": 2.89,
-      "grad_norm": 8.878872871398926,
+      "grad_norm": NaN,
       "learning_rate": 1.967435549525102e-06,
-      "loss": 0.6751,
+      "loss": 0.0,
       "step": 790
     },
     {
       "epoch": 2.93,
-      "grad_norm": 8.374876022338867,
+      "grad_norm": NaN,
       "learning_rate": 1.289009497964722e-06,
-      "loss": 0.6586,
+      "loss": 0.0,
       "step": 800
     },
     {
       "epoch": 2.96,
-      "grad_norm": 8.15294075012207,
+      "grad_norm": NaN,
       "learning_rate": 6.10583446404342e-07,
-      "loss": 0.6714,
+      "loss": 0.0,
       "step": 810
     },
     {
       "epoch": 2.99,
-      "eval_accuracy": 0.9064,
-      "eval_loss": 0.2777732014656067,
-      "eval_runtime": 127.5667,
-      "eval_samples_per_second": 117.586,
-      "eval_steps_per_second": 3.677,
+      "eval_accuracy": 0.10166666666666667,
+      "eval_loss": NaN,
+      "eval_runtime": 130.8726,
+      "eval_samples_per_second": 114.615,
+      "eval_steps_per_second": 3.584,
       "step": 819
     },
     {
       "epoch": 2.99,
       "step": 819,
       "total_flos": 1.0585264325663785e+18,
-      "train_loss": 0.9103804560371371,
-      "train_runtime": 753.233,
-      "train_samples_per_second": 139.399,
-      "train_steps_per_second": 1.087
+      "train_loss": 0.0,
+      "train_runtime": 811.0273,
+      "train_samples_per_second": 129.465,
+      "train_steps_per_second": 1.01
     }
   ],
   "logging_steps": 10,