End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8557692307692307
+      value: 0.8653846153846154
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4043
-- Accuracy: 0.8558
+- Loss: 0.3938
+- Accuracy: 0.8654
 
 ## Model description
 

all_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 17.77777777777778,
-    "eval_accuracy": 0.8404255319148937,
-    "eval_loss": 0.4538363516330719,
-    "eval_runtime": 0.7115,
-    "eval_samples_per_second": 132.115,
-    "eval_steps_per_second": 4.216,
-    "total_flos": 3.7037909187824026e+17,
-    "train_loss": 0.427582456668218,
-    "train_runtime": 256.3024,
-    "train_samples_per_second": 65.313,
-    "train_steps_per_second": 0.468
+    "epoch": 28.0,
+    "eval_accuracy": 0.8653846153846154,
+    "eval_loss": 0.39384937286376953,
+    "eval_runtime": 0.7571,
+    "eval_samples_per_second": 137.371,
+    "eval_steps_per_second": 5.283,
+    "total_flos": 6.51425759341314e+17,
+    "train_loss": 0.4042152370725359,
+    "train_runtime": 453.861,
+    "train_samples_per_second": 61.869,
+    "train_steps_per_second": 0.463
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 17.77777777777778,
-    "eval_accuracy": 0.8404255319148937,
-    "eval_loss": 0.4538363516330719,
-    "eval_runtime": 0.7115,
-    "eval_samples_per_second": 132.115,
-    "eval_steps_per_second": 4.216
+    "epoch": 28.0,
+    "eval_accuracy": 0.8653846153846154,
+    "eval_loss": 0.39384937286376953,
+    "eval_runtime": 0.7571,
+    "eval_samples_per_second": 137.371,
+    "eval_steps_per_second": 5.283
 }

runs/Jun10_17-27-32_8bc7bf2b7b8a/events.out.tfevents.1718041189.8bc7bf2b7b8a.515.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:545a3de2161e6148771024518f458214ec1ef30ed3f1ab27dd7e273d718adf29
+size 411

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 17.77777777777778,
-    "total_flos": 3.7037909187824026e+17,
-    "train_loss": 0.427582456668218,
-    "train_runtime": 256.3024,
-    "train_samples_per_second": 65.313,
-    "train_steps_per_second": 0.468
+    "epoch": 28.0,
+    "total_flos": 6.51425759341314e+17,
+    "train_loss": 0.4042152370725359,
+    "train_runtime": 453.861,
+    "train_samples_per_second": 61.869,
+    "train_steps_per_second": 0.463
 }

trainer_state.json

@@ -1,275 +1,440 @@
 {
-  "best_metric": 0.8404255319148937,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-phones/checkpoint-81",
-  "epoch": 17.77777777777778,
+  "best_metric": 0.8653846153846154,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-phones/checkpoint-135",
+  "epoch": 28.0,
   "eval_steps": 500,
-  "global_step": 120,
+  "global_step": 210,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.8888888888888888,
-      "eval_accuracy": 0.6595744680851063,
-      "eval_loss": 0.6158677935600281,
-      "eval_runtime": 0.616,
-      "eval_samples_per_second": 152.588,
-      "eval_steps_per_second": 4.87,
-      "step": 6
+      "epoch": 0.9333333333333333,
+      "eval_accuracy": 0.5673076923076923,
+      "eval_loss": 0.6742563247680664,
+      "eval_runtime": 1.0496,
+      "eval_samples_per_second": 99.088,
+      "eval_steps_per_second": 3.811,
+      "step": 7
     },
     {
-      "epoch": 1.4814814814814814,
-      "grad_norm": 8.271566390991211,
-      "learning_rate": 4.166666666666667e-05,
-      "loss": 0.5542,
+      "epoch": 1.3333333333333333,
+      "grad_norm": 5.86643123626709,
+      "learning_rate": 2.380952380952381e-05,
+      "loss": 0.6763,
       "step": 10
     },
     {
-      "epoch": 1.925925925925926,
-      "eval_accuracy": 0.7127659574468085,
-      "eval_loss": 0.5690343379974365,
-      "eval_runtime": 0.5828,
-      "eval_samples_per_second": 161.284,
-      "eval_steps_per_second": 5.147,
-      "step": 13
+      "epoch": 2.0,
+      "eval_accuracy": 0.6923076923076923,
+      "eval_loss": 0.6165803670883179,
+      "eval_runtime": 0.6494,
+      "eval_samples_per_second": 160.146,
+      "eval_steps_per_second": 6.159,
+      "step": 15
     },
     {
-      "epoch": 2.962962962962963,
-      "grad_norm": 9.217803001403809,
-      "learning_rate": 4.62962962962963e-05,
-      "loss": 0.5334,
+      "epoch": 2.6666666666666665,
+      "grad_norm": 6.109733581542969,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 0.635,
       "step": 20
     },
     {
-      "epoch": 2.962962962962963,
-      "eval_accuracy": 0.7127659574468085,
-      "eval_loss": 0.5524399280548096,
-      "eval_runtime": 0.6208,
-      "eval_samples_per_second": 151.413,
-      "eval_steps_per_second": 4.832,
-      "step": 20
+      "epoch": 2.9333333333333336,
+      "eval_accuracy": 0.7403846153846154,
+      "eval_loss": 0.5646082758903503,
+      "eval_runtime": 0.7406,
+      "eval_samples_per_second": 140.428,
+      "eval_steps_per_second": 5.401,
+      "step": 22
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.7021276595744681,
-      "eval_loss": 0.5923256874084473,
-      "eval_runtime": 0.6139,
-      "eval_samples_per_second": 153.118,
-      "eval_steps_per_second": 4.887,
-      "step": 27
-    },
-    {
-      "epoch": 4.444444444444445,
-      "grad_norm": 8.293265342712402,
-      "learning_rate": 4.166666666666667e-05,
-      "loss": 0.4658,
+      "grad_norm": 14.055779457092285,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 0.5724,
       "step": 30
     },
     {
-      "epoch": 4.888888888888889,
-      "eval_accuracy": 0.7659574468085106,
-      "eval_loss": 0.4978613257408142,
-      "eval_runtime": 0.7172,
-      "eval_samples_per_second": 131.065,
-      "eval_steps_per_second": 4.183,
-      "step": 33
+      "epoch": 4.0,
+      "eval_accuracy": 0.7307692307692307,
+      "eval_loss": 0.5073935985565186,
+      "eval_runtime": 0.6701,
+      "eval_samples_per_second": 155.19,
+      "eval_steps_per_second": 5.969,
+      "step": 30
     },
     {
-      "epoch": 5.925925925925926,
-      "grad_norm": 7.5387701988220215,
-      "learning_rate": 3.7037037037037037e-05,
-      "loss": 0.469,
-      "step": 40
+      "epoch": 4.933333333333334,
+      "eval_accuracy": 0.7692307692307693,
+      "eval_loss": 0.48087915778160095,
+      "eval_runtime": 0.6729,
+      "eval_samples_per_second": 154.555,
+      "eval_steps_per_second": 5.944,
+      "step": 37
     },
     {
-      "epoch": 5.925925925925926,
-      "eval_accuracy": 0.776595744680851,
-      "eval_loss": 0.4834465980529785,
-      "eval_runtime": 0.6072,
-      "eval_samples_per_second": 154.816,
-      "eval_steps_per_second": 4.941,
+      "epoch": 5.333333333333333,
+      "grad_norm": 8.836523056030273,
+      "learning_rate": 4.4973544973544974e-05,
+      "loss": 0.527,
       "step": 40
     },
     {
-      "epoch": 6.962962962962963,
-      "eval_accuracy": 0.7446808510638298,
-      "eval_loss": 0.5267057418823242,
-      "eval_runtime": 0.604,
-      "eval_samples_per_second": 155.621,
-      "eval_steps_per_second": 4.967,
-      "step": 47
+      "epoch": 6.0,
+      "eval_accuracy": 0.7692307692307693,
+      "eval_loss": 0.45965665578842163,
+      "eval_runtime": 0.6926,
+      "eval_samples_per_second": 150.153,
+      "eval_steps_per_second": 5.775,
+      "step": 45
     },
     {
-      "epoch": 7.407407407407407,
-      "grad_norm": 7.728250026702881,
-      "learning_rate": 3.240740740740741e-05,
-      "loss": 0.4469,
+      "epoch": 6.666666666666667,
+      "grad_norm": 6.653749465942383,
+      "learning_rate": 4.232804232804233e-05,
+      "loss": 0.5304,
       "step": 50
     },
+    {
+      "epoch": 6.933333333333334,
+      "eval_accuracy": 0.7596153846153846,
+      "eval_loss": 0.47583022713661194,
+      "eval_runtime": 0.681,
+      "eval_samples_per_second": 152.716,
+      "eval_steps_per_second": 5.874,
+      "step": 52
+    },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.723404255319149,
-      "eval_loss": 0.5309192538261414,
-      "eval_runtime": 0.6111,
-      "eval_samples_per_second": 153.821,
-      "eval_steps_per_second": 4.909,
-      "step": 54
-    },
-    {
-      "epoch": 8.88888888888889,
-      "grad_norm": 12.034634590148926,
-      "learning_rate": 2.777777777777778e-05,
-      "loss": 0.436,
+      "grad_norm": 13.230646133422852,
+      "learning_rate": 3.968253968253968e-05,
+      "loss": 0.4597,
       "step": 60
     },
     {
-      "epoch": 8.88888888888889,
-      "eval_accuracy": 0.7872340425531915,
-      "eval_loss": 0.4591914117336273,
-      "eval_runtime": 0.6041,
-      "eval_samples_per_second": 155.611,
-      "eval_steps_per_second": 4.966,
+      "epoch": 8.0,
+      "eval_accuracy": 0.7884615384615384,
+      "eval_loss": 0.43429186940193176,
+      "eval_runtime": 0.7692,
+      "eval_samples_per_second": 135.213,
+      "eval_steps_per_second": 5.2,
       "step": 60
     },
     {
-      "epoch": 9.925925925925926,
-      "eval_accuracy": 0.8191489361702128,
-      "eval_loss": 0.4601520001888275,
-      "eval_runtime": 0.6315,
-      "eval_samples_per_second": 148.848,
-      "eval_steps_per_second": 4.75,
+      "epoch": 8.933333333333334,
+      "eval_accuracy": 0.7980769230769231,
+      "eval_loss": 0.42488300800323486,
+      "eval_runtime": 0.6816,
+      "eval_samples_per_second": 152.578,
+      "eval_steps_per_second": 5.868,
       "step": 67
     },
     {
-      "epoch": 10.37037037037037,
-      "grad_norm": 8.522727012634277,
-      "learning_rate": 2.314814814814815e-05,
-      "loss": 0.3978,
+      "epoch": 9.333333333333334,
+      "grad_norm": 8.930418968200684,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 0.4606,
       "step": 70
     },
     {
-      "epoch": 10.962962962962964,
-      "eval_accuracy": 0.8085106382978723,
-      "eval_loss": 0.479958176612854,
-      "eval_runtime": 0.7165,
-      "eval_samples_per_second": 131.191,
-      "eval_steps_per_second": 4.187,
-      "step": 74
+      "epoch": 10.0,
+      "eval_accuracy": 0.7980769230769231,
+      "eval_loss": 0.42358094453811646,
+      "eval_runtime": 0.6708,
+      "eval_samples_per_second": 155.044,
+      "eval_steps_per_second": 5.963,
+      "step": 75
     },
     {
-      "epoch": 11.851851851851851,
-      "grad_norm": 8.708232879638672,
-      "learning_rate": 1.8518518518518518e-05,
-      "loss": 0.3916,
+      "epoch": 10.666666666666666,
+      "grad_norm": 10.609027862548828,
+      "learning_rate": 3.439153439153439e-05,
+      "loss": 0.4286,
       "step": 80
     },
     {
-      "epoch": 12.0,
-      "eval_accuracy": 0.8404255319148937,
-      "eval_loss": 0.4538363516330719,
-      "eval_runtime": 0.7058,
-      "eval_samples_per_second": 133.179,
-      "eval_steps_per_second": 4.25,
-      "step": 81
+      "epoch": 10.933333333333334,
+      "eval_accuracy": 0.8461538461538461,
+      "eval_loss": 0.4054819643497467,
+      "eval_runtime": 0.6768,
+      "eval_samples_per_second": 153.664,
+      "eval_steps_per_second": 5.91,
+      "step": 82
     },
     {
-      "epoch": 12.88888888888889,
-      "eval_accuracy": 0.7872340425531915,
-      "eval_loss": 0.4807003438472748,
-      "eval_runtime": 0.7274,
-      "eval_samples_per_second": 129.222,
-      "eval_steps_per_second": 4.124,
-      "step": 87
+      "epoch": 12.0,
+      "grad_norm": 5.532287120819092,
+      "learning_rate": 3.1746031746031745e-05,
+      "loss": 0.3857,
+      "step": 90
     },
     {
-      "epoch": 13.333333333333334,
-      "grad_norm": 10.32046127319336,
-      "learning_rate": 1.388888888888889e-05,
-      "loss": 0.3932,
+      "epoch": 12.0,
+      "eval_accuracy": 0.8269230769230769,
+      "eval_loss": 0.4144248962402344,
+      "eval_runtime": 0.7584,
+      "eval_samples_per_second": 137.132,
+      "eval_steps_per_second": 5.274,
       "step": 90
     },
     {
-      "epoch": 13.925925925925926,
-      "eval_accuracy": 0.8297872340425532,
-      "eval_loss": 0.4472525715827942,
-      "eval_runtime": 0.6791,
-      "eval_samples_per_second": 138.408,
-      "eval_steps_per_second": 4.417,
-      "step": 94
+      "epoch": 12.933333333333334,
+      "eval_accuracy": 0.7980769230769231,
+      "eval_loss": 0.4293949007987976,
+      "eval_runtime": 0.6743,
+      "eval_samples_per_second": 154.239,
+      "eval_steps_per_second": 5.932,
+      "step": 97
     },
     {
-      "epoch": 14.814814814814815,
-      "grad_norm": 7.876950263977051,
-      "learning_rate": 9.259259259259259e-06,
-      "loss": 0.3362,
+      "epoch": 13.333333333333334,
+      "grad_norm": 11.760865211486816,
+      "learning_rate": 2.91005291005291e-05,
+      "loss": 0.3801,
       "step": 100
     },
     {
-      "epoch": 14.962962962962964,
-      "eval_accuracy": 0.8085106382978723,
-      "eval_loss": 0.4526437520980835,
-      "eval_runtime": 0.6231,
-      "eval_samples_per_second": 150.861,
-      "eval_steps_per_second": 4.815,
-      "step": 101
+      "epoch": 14.0,
+      "eval_accuracy": 0.8461538461538461,
+      "eval_loss": 0.40805691480636597,
+      "eval_runtime": 0.6845,
+      "eval_samples_per_second": 151.929,
+      "eval_steps_per_second": 5.843,
+      "step": 105
     },
     {
-      "epoch": 16.0,
-      "eval_accuracy": 0.8191489361702128,
-      "eval_loss": 0.4435100257396698,
-      "eval_runtime": 0.6246,
-      "eval_samples_per_second": 150.502,
-      "eval_steps_per_second": 4.803,
-      "step": 108
-    },
-    {
-      "epoch": 16.296296296296298,
-      "grad_norm": 7.970451354980469,
-      "learning_rate": 4.6296296296296296e-06,
-      "loss": 0.3631,
+      "epoch": 14.666666666666666,
+      "grad_norm": 11.491521835327148,
+      "learning_rate": 2.6455026455026456e-05,
+      "loss": 0.3538,
       "step": 110
     },
     {
-      "epoch": 16.88888888888889,
-      "eval_accuracy": 0.8297872340425532,
-      "eval_loss": 0.4465709328651428,
-      "eval_runtime": 0.6157,
-      "eval_samples_per_second": 152.667,
-      "eval_steps_per_second": 4.872,
-      "step": 114
+      "epoch": 14.933333333333334,
+      "eval_accuracy": 0.8461538461538461,
+      "eval_loss": 0.4194793403148651,
+      "eval_runtime": 0.674,
+      "eval_samples_per_second": 154.298,
+      "eval_steps_per_second": 5.935,
+      "step": 112
     },
     {
-      "epoch": 17.77777777777778,
-      "grad_norm": 7.780444622039795,
-      "learning_rate": 0.0,
-      "loss": 0.3441,
+      "epoch": 16.0,
+      "grad_norm": 11.567109107971191,
+      "learning_rate": 2.380952380952381e-05,
+      "loss": 0.3585,
       "step": 120
     },
     {
-      "epoch": 17.77777777777778,
-      "eval_accuracy": 0.8297872340425532,
-      "eval_loss": 0.45035284757614136,
-      "eval_runtime": 0.6091,
-      "eval_samples_per_second": 154.338,
-      "eval_steps_per_second": 4.926,
+      "epoch": 16.0,
+      "eval_accuracy": 0.8557692307692307,
+      "eval_loss": 0.4068710207939148,
+      "eval_runtime": 0.7839,
+      "eval_samples_per_second": 132.667,
+      "eval_steps_per_second": 5.103,
       "step": 120
     },
     {
-      "epoch": 17.77777777777778,
-      "step": 120,
-      "total_flos": 3.7037909187824026e+17,
-      "train_loss": 0.427582456668218,
-      "train_runtime": 256.3024,
-      "train_samples_per_second": 65.313,
-      "train_steps_per_second": 0.468
+      "epoch": 16.933333333333334,
+      "eval_accuracy": 0.8557692307692307,
+      "eval_loss": 0.3970623016357422,
+      "eval_runtime": 0.6669,
+      "eval_samples_per_second": 155.948,
+      "eval_steps_per_second": 5.998,
+      "step": 127
+    },
+    {
+      "epoch": 17.333333333333332,
+      "grad_norm": 12.216808319091797,
+      "learning_rate": 2.1164021164021164e-05,
+      "loss": 0.3258,
+      "step": 130
+    },
+    {
+      "epoch": 18.0,
+      "eval_accuracy": 0.8653846153846154,
+      "eval_loss": 0.39384937286376953,
+      "eval_runtime": 0.6899,
+      "eval_samples_per_second": 150.747,
+      "eval_steps_per_second": 5.798,
+      "step": 135
+    },
+    {
+      "epoch": 18.666666666666668,
+      "grad_norm": 15.223637580871582,
+      "learning_rate": 1.8518518518518518e-05,
+      "loss": 0.3288,
+      "step": 140
+    },
+    {
+      "epoch": 18.933333333333334,
+      "eval_accuracy": 0.8461538461538461,
+      "eval_loss": 0.396359384059906,
+      "eval_runtime": 0.6861,
+      "eval_samples_per_second": 151.574,
+      "eval_steps_per_second": 5.83,
+      "step": 142
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 25.446683883666992,
+      "learning_rate": 1.5873015873015872e-05,
+      "loss": 0.3276,
+      "step": 150
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.8557692307692307,
+      "eval_loss": 0.44233372807502747,
+      "eval_runtime": 0.6969,
+      "eval_samples_per_second": 149.226,
+      "eval_steps_per_second": 5.739,
+      "step": 150
+    },
+    {
+      "epoch": 20.933333333333334,
+      "eval_accuracy": 0.8365384615384616,
+      "eval_loss": 0.40670448541641235,
+      "eval_runtime": 0.7625,
+      "eval_samples_per_second": 136.392,
+      "eval_steps_per_second": 5.246,
+      "step": 157
+    },
+    {
+      "epoch": 21.333333333333332,
+      "grad_norm": 10.679701805114746,
+      "learning_rate": 1.3227513227513228e-05,
+      "loss": 0.317,
+      "step": 160
+    },
+    {
+      "epoch": 22.0,
+      "eval_accuracy": 0.8653846153846154,
+      "eval_loss": 0.4178958535194397,
+      "eval_runtime": 0.6933,
+      "eval_samples_per_second": 150.017,
+      "eval_steps_per_second": 5.77,
+      "step": 165
+    },
+    {
+      "epoch": 22.666666666666668,
+      "grad_norm": 12.451942443847656,
+      "learning_rate": 1.0582010582010582e-05,
+      "loss": 0.288,
+      "step": 170
+    },
+    {
+      "epoch": 22.933333333333334,
+      "eval_accuracy": 0.8557692307692307,
+      "eval_loss": 0.3881677985191345,
+      "eval_runtime": 0.6592,
+      "eval_samples_per_second": 157.766,
+      "eval_steps_per_second": 6.068,
+      "step": 172
+    },
+    {
+      "epoch": 24.0,
+      "grad_norm": 11.666213989257812,
+      "learning_rate": 7.936507936507936e-06,
+      "loss": 0.2735,
+      "step": 180
+    },
+    {
+      "epoch": 24.0,
+      "eval_accuracy": 0.8557692307692307,
+      "eval_loss": 0.42146697640419006,
+      "eval_runtime": 0.6742,
+      "eval_samples_per_second": 154.246,
+      "eval_steps_per_second": 5.933,
+      "step": 180
+    },
+    {
+      "epoch": 24.933333333333334,
+      "eval_accuracy": 0.8461538461538461,
+      "eval_loss": 0.3971670866012573,
+      "eval_runtime": 0.7934,
+      "eval_samples_per_second": 131.085,
+      "eval_steps_per_second": 5.042,
+      "step": 187
+    },
+    {
+      "epoch": 25.333333333333332,
+      "grad_norm": 7.033930778503418,
+      "learning_rate": 5.291005291005291e-06,
+      "loss": 0.2805,
+      "step": 190
+    },
+    {
+      "epoch": 26.0,
+      "eval_accuracy": 0.8557692307692307,
+      "eval_loss": 0.3943334221839905,
+      "eval_runtime": 0.6986,
+      "eval_samples_per_second": 148.874,
+      "eval_steps_per_second": 5.726,
+      "step": 195
+    },
+    {
+      "epoch": 26.666666666666668,
+      "grad_norm": 5.698335647583008,
+      "learning_rate": 2.6455026455026455e-06,
+      "loss": 0.2961,
+      "step": 200
+    },
+    {
+      "epoch": 26.933333333333334,
+      "eval_accuracy": 0.8557692307692307,
+      "eval_loss": 0.39985355734825134,
+      "eval_runtime": 0.691,
+      "eval_samples_per_second": 150.514,
+      "eval_steps_per_second": 5.789,
+      "step": 202
+    },
+    {
+      "epoch": 28.0,
+      "grad_norm": 9.678221702575684,
+      "learning_rate": 0.0,
+      "loss": 0.2832,
+      "step": 210
+    },
+    {
+      "epoch": 28.0,
+      "eval_accuracy": 0.8557692307692307,
+      "eval_loss": 0.4042527377605438,
+      "eval_runtime": 0.6919,
+      "eval_samples_per_second": 150.307,
+      "eval_steps_per_second": 5.781,
+      "step": 210
+    },
+    {
+      "epoch": 28.0,
+      "step": 210,
+      "total_flos": 6.51425759341314e+17,
+      "train_loss": 0.4042152370725359,
+      "train_runtime": 453.861,
+      "train_samples_per_second": 61.869,
+      "train_steps_per_second": 0.463
     }
   ],
   "logging_steps": 10,
-  "max_steps": 120,
+  "max_steps": 210,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 20,
+  "num_train_epochs": 30,
   "save_steps": 500,
-  "total_flos": 3.7037909187824026e+17,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.51425759341314e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null