End of training

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 39.86,
     "eval_accuracy": 1.0,
-    "eval_loss": 0.062098320573568344,
-    "eval_runtime": 3.1556,
-    "eval_samples_per_second": 14.894,
-    "eval_steps_per_second": 0.634,
-    "total_flos": 4.138238964234977e+17,
-    "train_loss": 0.19912103215853375,
-    "train_runtime": 1848.5966,
-    "train_samples_per_second": 9.023,
-    "train_steps_per_second": 0.065
+    "eval_loss": 0.026065116748213768,
+    "eval_runtime": 3.2422,
+    "eval_samples_per_second": 14.805,
+    "eval_steps_per_second": 0.617,
+    "total_flos": 4.264272913587241e+17,
+    "train_loss": 0.1722367246945699,
+    "train_runtime": 1999.9903,
+    "train_samples_per_second": 8.6,
+    "train_steps_per_second": 0.06
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 39.86,
     "eval_accuracy": 1.0,
-    "eval_loss": 0.062098320573568344,
-    "eval_runtime": 3.1556,
-    "eval_samples_per_second": 14.894,
-    "eval_steps_per_second": 0.634
+    "eval_loss": 0.026065116748213768,
+    "eval_runtime": 3.2422,
+    "eval_samples_per_second": 14.805,
+    "eval_steps_per_second": 0.617
 }

runs/Oct21_11-39-35_643e08dfd987/events.out.tfevents.1666354649.643e08dfd987.72.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96500e4dcf356bd7897eacca656e34bcb5e6fa98831930bd67c01902cf0e604a
+size 357

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 39.86,
-    "total_flos": 4.138238964234977e+17,
-    "train_loss": 0.19912103215853375,
-    "train_runtime": 1848.5966,
-    "train_samples_per_second": 9.023,
-    "train_steps_per_second": 0.065
+    "total_flos": 4.264272913587241e+17,
+    "train_loss": 0.1722367246945699,
+    "train_runtime": 1999.9903,
+    "train_samples_per_second": 8.6,
+    "train_steps_per_second": 0.06
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_metric": 1.0,
-  "best_model_checkpoint": "delivery_truck_classification/checkpoint-9",
+  "best_model_checkpoint": "delivery_truck_classification/checkpoint-3",
   "epoch": 39.857142857142854,
   "global_step": 120,
   "is_hyper_param_search": false,
@@ -9,413 +9,413 @@
   "log_history": [
     {
       "epoch": 0.86,
-      "eval_accuracy": 0.9574468085106383,
-      "eval_loss": 0.14558981359004974,
-      "eval_runtime": 3.0797,
-      "eval_samples_per_second": 15.261,
-      "eval_steps_per_second": 0.649,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.026065116748213768,
+      "eval_runtime": 3.4495,
+      "eval_samples_per_second": 13.915,
+      "eval_steps_per_second": 0.58,
       "step": 3
     },
     {
       "epoch": 1.86,
-      "eval_accuracy": 0.9787234042553191,
-      "eval_loss": 0.08996303379535675,
-      "eval_runtime": 3.5219,
-      "eval_samples_per_second": 13.345,
-      "eval_steps_per_second": 0.568,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.024647483602166176,
+      "eval_runtime": 3.9431,
+      "eval_samples_per_second": 12.173,
+      "eval_steps_per_second": 0.507,
       "step": 6
     },
     {
       "epoch": 2.86,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.062098320573568344,
-      "eval_runtime": 3.3535,
-      "eval_samples_per_second": 14.015,
-      "eval_steps_per_second": 0.596,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.035011451691389084,
+      "eval_runtime": 3.4736,
+      "eval_samples_per_second": 13.818,
+      "eval_steps_per_second": 0.576,
       "step": 9
     },
     {
       "epoch": 3.86,
-      "eval_accuracy": 0.9787234042553191,
-      "eval_loss": 0.06347361207008362,
-      "eval_runtime": 3.0769,
-      "eval_samples_per_second": 15.275,
-      "eval_steps_per_second": 0.65,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.029779432341456413,
+      "eval_runtime": 3.1788,
+      "eval_samples_per_second": 15.1,
+      "eval_steps_per_second": 0.629,
       "step": 12
     },
     {
       "epoch": 4.86,
-      "eval_accuracy": 0.9787234042553191,
-      "eval_loss": 0.05354984849691391,
-      "eval_runtime": 3.0814,
-      "eval_samples_per_second": 15.253,
-      "eval_steps_per_second": 0.649,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.036166682839393616,
+      "eval_runtime": 3.497,
+      "eval_samples_per_second": 13.726,
+      "eval_steps_per_second": 0.572,
       "step": 15
     },
     {
       "epoch": 5.86,
-      "eval_accuracy": 0.9574468085106383,
-      "eval_loss": 0.06630665063858032,
-      "eval_runtime": 3.3475,
-      "eval_samples_per_second": 14.04,
-      "eval_steps_per_second": 0.597,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.05407286807894707,
+      "eval_runtime": 3.4858,
+      "eval_samples_per_second": 13.77,
+      "eval_steps_per_second": 0.574,
       "step": 18
     },
     {
       "epoch": 6.57,
       "learning_rate": 4.62962962962963e-05,
-      "loss": 0.3029,
+      "loss": 0.2214,
       "step": 20
     },
     {
       "epoch": 6.86,
-      "eval_accuracy": 0.9787234042553191,
-      "eval_loss": 0.04919619858264923,
-      "eval_runtime": 3.3837,
-      "eval_samples_per_second": 13.89,
-      "eval_steps_per_second": 0.591,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.03632530942559242,
+      "eval_runtime": 3.1393,
+      "eval_samples_per_second": 15.29,
+      "eval_steps_per_second": 0.637,
       "step": 21
     },
     {
       "epoch": 7.86,
-      "eval_accuracy": 0.9787234042553191,
-      "eval_loss": 0.05591897666454315,
-      "eval_runtime": 3.0774,
-      "eval_samples_per_second": 15.273,
-      "eval_steps_per_second": 0.65,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.02213350497186184,
+      "eval_runtime": 3.7451,
+      "eval_samples_per_second": 12.817,
+      "eval_steps_per_second": 0.534,
       "step": 24
     },
     {
       "epoch": 8.86,
-      "eval_accuracy": 0.9787234042553191,
-      "eval_loss": 0.0664142519235611,
-      "eval_runtime": 3.4113,
-      "eval_samples_per_second": 13.778,
-      "eval_steps_per_second": 0.586,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.03659434616565704,
+      "eval_runtime": 3.4556,
+      "eval_samples_per_second": 13.89,
+      "eval_steps_per_second": 0.579,
       "step": 27
     },
     {
       "epoch": 9.86,
-      "eval_accuracy": 0.9787234042553191,
-      "eval_loss": 0.06434692442417145,
-      "eval_runtime": 3.3792,
-      "eval_samples_per_second": 13.908,
-      "eval_steps_per_second": 0.592,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.05018351972103119,
+      "eval_runtime": 3.2792,
+      "eval_samples_per_second": 14.638,
+      "eval_steps_per_second": 0.61,
       "step": 30
     },
     {
       "epoch": 10.86,
-      "eval_accuracy": 0.9787234042553191,
-      "eval_loss": 0.05577840283513069,
-      "eval_runtime": 3.3341,
-      "eval_samples_per_second": 14.097,
-      "eval_steps_per_second": 0.6,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.03546701744198799,
+      "eval_runtime": 3.4963,
+      "eval_samples_per_second": 13.729,
+      "eval_steps_per_second": 0.572,
       "step": 33
     },
     {
       "epoch": 11.86,
       "eval_accuracy": 1.0,
-      "eval_loss": 0.03647231683135033,
-      "eval_runtime": 3.076,
-      "eval_samples_per_second": 15.28,
-      "eval_steps_per_second": 0.65,
+      "eval_loss": 0.021759234368801117,
+      "eval_runtime": 3.5458,
+      "eval_samples_per_second": 13.537,
+      "eval_steps_per_second": 0.564,
       "step": 36
     },
     {
       "epoch": 12.86,
-      "eval_accuracy": 0.9787234042553191,
-      "eval_loss": 0.043758317828178406,
-      "eval_runtime": 3.3173,
-      "eval_samples_per_second": 14.168,
-      "eval_steps_per_second": 0.603,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.014033220708370209,
+      "eval_runtime": 3.2728,
+      "eval_samples_per_second": 14.666,
+      "eval_steps_per_second": 0.611,
       "step": 39
     },
     {
       "epoch": 13.29,
       "learning_rate": 3.7037037037037037e-05,
-      "loss": 0.2212,
+      "loss": 0.183,
       "step": 40
     },
     {
       "epoch": 13.86,
-      "eval_accuracy": 0.9787234042553191,
-      "eval_loss": 0.045602452009916306,
-      "eval_runtime": 3.3351,
-      "eval_samples_per_second": 14.093,
-      "eval_steps_per_second": 0.6,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.017221327871084213,
+      "eval_runtime": 3.4953,
+      "eval_samples_per_second": 13.733,
+      "eval_steps_per_second": 0.572,
       "step": 42
     },
     {
       "epoch": 14.86,
-      "eval_accuracy": 0.9787234042553191,
-      "eval_loss": 0.040249306708574295,
-      "eval_runtime": 3.0799,
-      "eval_samples_per_second": 15.26,
-      "eval_steps_per_second": 0.649,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.03003031760454178,
+      "eval_runtime": 3.4946,
+      "eval_samples_per_second": 13.735,
+      "eval_steps_per_second": 0.572,
       "step": 45
     },
     {
       "epoch": 15.86,
-      "eval_accuracy": 0.9787234042553191,
-      "eval_loss": 0.03505050763487816,
-      "eval_runtime": 3.2192,
-      "eval_samples_per_second": 14.6,
-      "eval_steps_per_second": 0.621,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.058922749012708664,
+      "eval_runtime": 3.184,
+      "eval_samples_per_second": 15.075,
+      "eval_steps_per_second": 0.628,
       "step": 48
     },
     {
       "epoch": 16.86,
-      "eval_accuracy": 0.9787234042553191,
-      "eval_loss": 0.03594408929347992,
-      "eval_runtime": 3.2905,
-      "eval_samples_per_second": 14.284,
-      "eval_steps_per_second": 0.608,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.06934068351984024,
+      "eval_runtime": 3.4776,
+      "eval_samples_per_second": 13.803,
+      "eval_steps_per_second": 0.575,
       "step": 51
     },
     {
       "epoch": 17.86,
-      "eval_accuracy": 0.9787234042553191,
-      "eval_loss": 0.04266700521111488,
-      "eval_runtime": 3.4643,
-      "eval_samples_per_second": 13.567,
-      "eval_steps_per_second": 0.577,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.04955345392227173,
+      "eval_runtime": 3.6895,
+      "eval_samples_per_second": 13.01,
+      "eval_steps_per_second": 0.542,
       "step": 54
     },
     {
       "epoch": 18.86,
-      "eval_accuracy": 0.9574468085106383,
-      "eval_loss": 0.04897385463118553,
-      "eval_runtime": 3.0853,
-      "eval_samples_per_second": 15.234,
-      "eval_steps_per_second": 0.648,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.03155900537967682,
+      "eval_runtime": 3.1541,
+      "eval_samples_per_second": 15.218,
+      "eval_steps_per_second": 0.634,
       "step": 57
     },
     {
       "epoch": 19.86,
       "learning_rate": 2.777777777777778e-05,
-      "loss": 0.186,
+      "loss": 0.1706,
       "step": 60
     },
     {
       "epoch": 19.86,
-      "eval_accuracy": 0.9787234042553191,
-      "eval_loss": 0.039550021290779114,
-      "eval_runtime": 3.1131,
-      "eval_samples_per_second": 15.097,
-      "eval_steps_per_second": 0.642,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.03406331315636635,
+      "eval_runtime": 4.5532,
+      "eval_samples_per_second": 10.542,
+      "eval_steps_per_second": 0.439,
       "step": 60
     },
     {
       "epoch": 20.86,
-      "eval_accuracy": 0.9787234042553191,
-      "eval_loss": 0.029103364795446396,
-      "eval_runtime": 3.3495,
-      "eval_samples_per_second": 14.032,
-      "eval_steps_per_second": 0.597,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.03481491655111313,
+      "eval_runtime": 3.4718,
+      "eval_samples_per_second": 13.826,
+      "eval_steps_per_second": 0.576,
       "step": 63
     },
     {
       "epoch": 21.86,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.015161500312387943,
-      "eval_runtime": 3.3942,
-      "eval_samples_per_second": 13.847,
-      "eval_steps_per_second": 0.589,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.03439461812376976,
+      "eval_runtime": 3.2108,
+      "eval_samples_per_second": 14.949,
+      "eval_steps_per_second": 0.623,
       "step": 66
     },
     {
       "epoch": 22.86,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.014185278676450253,
-      "eval_runtime": 3.0833,
-      "eval_samples_per_second": 15.244,
-      "eval_steps_per_second": 0.649,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.04687784984707832,
+      "eval_runtime": 3.5128,
+      "eval_samples_per_second": 13.664,
+      "eval_steps_per_second": 0.569,
       "step": 69
     },
     {
       "epoch": 23.86,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.01784444786608219,
-      "eval_runtime": 3.3662,
-      "eval_samples_per_second": 13.962,
-      "eval_steps_per_second": 0.594,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.05970446392893791,
+      "eval_runtime": 3.7464,
+      "eval_samples_per_second": 12.812,
+      "eval_steps_per_second": 0.534,
       "step": 72
     },
     {
       "epoch": 24.86,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.017597978934645653,
-      "eval_runtime": 3.4018,
-      "eval_samples_per_second": 13.816,
-      "eval_steps_per_second": 0.588,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.05298614129424095,
+      "eval_runtime": 3.1637,
+      "eval_samples_per_second": 15.172,
+      "eval_steps_per_second": 0.632,
       "step": 75
     },
     {
       "epoch": 25.86,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.015114851295948029,
-      "eval_runtime": 3.1308,
-      "eval_samples_per_second": 15.012,
-      "eval_steps_per_second": 0.639,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.040230389684438705,
+      "eval_runtime": 3.5114,
+      "eval_samples_per_second": 13.67,
+      "eval_steps_per_second": 0.57,
       "step": 78
     },
     {
       "epoch": 26.57,
       "learning_rate": 1.8518518518518518e-05,
-      "loss": 0.1751,
+      "loss": 0.1644,
       "step": 80
     },
     {
       "epoch": 26.86,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.011016697622835636,
-      "eval_runtime": 3.366,
-      "eval_samples_per_second": 13.963,
-      "eval_steps_per_second": 0.594,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.03619036078453064,
+      "eval_runtime": 3.7338,
+      "eval_samples_per_second": 12.856,
+      "eval_steps_per_second": 0.536,
       "step": 81
     },
     {
       "epoch": 27.86,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.012051686644554138,
-      "eval_runtime": 3.3303,
-      "eval_samples_per_second": 14.113,
-      "eval_steps_per_second": 0.601,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.038440290838479996,
+      "eval_runtime": 3.2337,
+      "eval_samples_per_second": 14.844,
+      "eval_steps_per_second": 0.618,
       "step": 84
     },
     {
       "epoch": 28.86,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.01581379771232605,
-      "eval_runtime": 3.3324,
-      "eval_samples_per_second": 14.104,
-      "eval_steps_per_second": 0.6,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.03096356801688671,
+      "eval_runtime": 3.4785,
+      "eval_samples_per_second": 13.799,
+      "eval_steps_per_second": 0.575,
       "step": 87
     },
     {
       "epoch": 29.86,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.02497912012040615,
-      "eval_runtime": 3.1285,
-      "eval_samples_per_second": 15.023,
-      "eval_steps_per_second": 0.639,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.02927880547940731,
+      "eval_runtime": 3.5018,
+      "eval_samples_per_second": 13.707,
+      "eval_steps_per_second": 0.571,
       "step": 90
     },
     {
       "epoch": 30.86,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.02920253947377205,
-      "eval_runtime": 3.3575,
-      "eval_samples_per_second": 13.999,
-      "eval_steps_per_second": 0.596,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.03753955289721489,
+      "eval_runtime": 3.2739,
+      "eval_samples_per_second": 14.662,
+      "eval_steps_per_second": 0.611,
       "step": 93
     },
     {
       "epoch": 31.86,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.025970185175538063,
-      "eval_runtime": 3.3707,
-      "eval_samples_per_second": 13.944,
-      "eval_steps_per_second": 0.593,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.04604535177350044,
+      "eval_runtime": 3.9083,
+      "eval_samples_per_second": 12.282,
+      "eval_steps_per_second": 0.512,
       "step": 96
     },
     {
       "epoch": 32.86,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.020575150847434998,
-      "eval_runtime": 3.152,
-      "eval_samples_per_second": 14.911,
-      "eval_steps_per_second": 0.635,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.05220605805516243,
+      "eval_runtime": 3.4983,
+      "eval_samples_per_second": 13.721,
+      "eval_steps_per_second": 0.572,
       "step": 99
     },
     {
       "epoch": 33.29,
       "learning_rate": 9.259259259259259e-06,
-      "loss": 0.1614,
+      "loss": 0.1539,
       "step": 100
     },
     {
       "epoch": 33.86,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.018124328926205635,
-      "eval_runtime": 3.4042,
-      "eval_samples_per_second": 13.807,
-      "eval_steps_per_second": 0.588,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.05513928830623627,
+      "eval_runtime": 3.1674,
+      "eval_samples_per_second": 15.154,
+      "eval_steps_per_second": 0.631,
       "step": 102
     },
     {
       "epoch": 34.86,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.017009548842906952,
-      "eval_runtime": 3.4107,
-      "eval_samples_per_second": 13.78,
-      "eval_steps_per_second": 0.586,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.05517812445759773,
+      "eval_runtime": 3.4831,
+      "eval_samples_per_second": 13.781,
+      "eval_steps_per_second": 0.574,
       "step": 105
     },
     {
       "epoch": 35.86,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.0170438252389431,
-      "eval_runtime": 3.0972,
-      "eval_samples_per_second": 15.175,
-      "eval_steps_per_second": 0.646,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.054359838366508484,
+      "eval_runtime": 3.6987,
+      "eval_samples_per_second": 12.977,
+      "eval_steps_per_second": 0.541,
       "step": 108
     },
     {
       "epoch": 36.86,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.017739199101924896,
-      "eval_runtime": 3.4084,
-      "eval_samples_per_second": 13.789,
-      "eval_steps_per_second": 0.587,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.05520467087626457,
+      "eval_runtime": 3.1659,
+      "eval_samples_per_second": 15.162,
+      "eval_steps_per_second": 0.632,
       "step": 111
     },
     {
       "epoch": 37.86,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.018777411431074142,
-      "eval_runtime": 3.4191,
-      "eval_samples_per_second": 13.746,
-      "eval_steps_per_second": 0.585,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.054130103439092636,
+      "eval_runtime": 3.4868,
+      "eval_samples_per_second": 13.766,
+      "eval_steps_per_second": 0.574,
       "step": 114
     },
     {
       "epoch": 38.86,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.01889665052294731,
-      "eval_runtime": 3.0931,
-      "eval_samples_per_second": 15.195,
-      "eval_steps_per_second": 0.647,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.0525875948369503,
+      "eval_runtime": 3.4473,
+      "eval_samples_per_second": 13.924,
+      "eval_steps_per_second": 0.58,
       "step": 117
     },
     {
       "epoch": 39.86,
       "learning_rate": 0.0,
-      "loss": 0.1483,
+      "loss": 0.1401,
       "step": 120
     },
     {
       "epoch": 39.86,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.018766822293400764,
-      "eval_runtime": 3.369,
-      "eval_samples_per_second": 13.951,
-      "eval_steps_per_second": 0.594,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.05150062218308449,
+      "eval_runtime": 3.1357,
+      "eval_samples_per_second": 15.308,
+      "eval_steps_per_second": 0.638,
       "step": 120
     },
     {
       "epoch": 39.86,
       "step": 120,
-      "total_flos": 4.138238964234977e+17,
-      "train_loss": 0.19912103215853375,
-      "train_runtime": 1848.5966,
-      "train_samples_per_second": 9.023,
-      "train_steps_per_second": 0.065
+      "total_flos": 4.264272913587241e+17,
+      "train_loss": 0.1722367246945699,
+      "train_runtime": 1999.9903,
+      "train_samples_per_second": 8.6,
+      "train_steps_per_second": 0.06
     }
   ],
   "max_steps": 120,
   "num_train_epochs": 40,
-  "total_flos": 4.138238964234977e+17,
+  "total_flos": 4.264272913587241e+17,
   "trial_name": null,
   "trial_params": null
 }