End of training

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7686
-- Accuracy: 0.6538
+- Loss: 1.0154
+- Accuracy: 0.7115
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 80.0,
+    "eval_accuracy": 0.7115384615384616,
+    "eval_loss": 1.015413522720337,
+    "eval_runtime": 0.8987,
+    "eval_samples_per_second": 57.863,
+    "eval_steps_per_second": 2.226,
+    "train_loss": 1.0117311209440232,
+    "train_runtime": 462.6508,
+    "train_samples_per_second": 41.154,
+    "train_steps_per_second": 0.346
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 80.0,
+    "eval_accuracy": 0.7115384615384616,
+    "eval_loss": 1.015413522720337,
+    "eval_runtime": 0.8987,
+    "eval_samples_per_second": 57.863,
+    "eval_steps_per_second": 2.226
+}

runs/Jun16_14-59-28_DESKTOP-SKBE9FB/events.out.tfevents.1718572048.DESKTOP-SKBE9FB.10988.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fcccf17b129dc71b0e0298bb21e5e484547311dca8d83fc363edf5d5bec7bd2
+size 411

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 80.0,
+    "train_loss": 1.0117311209440232,
+    "train_runtime": 462.6508,
+    "train_samples_per_second": 41.154,
+    "train_steps_per_second": 0.346
+}

trainer_state.json

@@ -0,0 +1,846 @@
+{
+  "best_metric": 0.7115384615384616,
+  "best_model_checkpoint": "swinv2-tiny-patch4-window8-256-ve-UH\\checkpoint-74",
+  "epoch": 80.0,
+  "eval_steps": 500,
+  "global_step": 160,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.40384615384615385,
+      "eval_loss": 1.609152913093567,
+      "eval_runtime": 0.6177,
+      "eval_samples_per_second": 84.178,
+      "eval_steps_per_second": 3.238,
+      "step": 2
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4230769230769231,
+      "eval_loss": 1.607539415359497,
+      "eval_runtime": 0.6151,
+      "eval_samples_per_second": 84.537,
+      "eval_steps_per_second": 3.251,
+      "step": 4
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.40384615384615385,
+      "eval_loss": 1.6036603450775146,
+      "eval_runtime": 0.6452,
+      "eval_samples_per_second": 80.598,
+      "eval_steps_per_second": 3.1,
+      "step": 6
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.40384615384615385,
+      "eval_loss": 1.5960490703582764,
+      "eval_runtime": 0.6216,
+      "eval_samples_per_second": 83.658,
+      "eval_steps_per_second": 3.218,
+      "step": 8
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.5e-05,
+      "loss": 1.6041,
+      "step": 10
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.40384615384615385,
+      "eval_loss": 1.5820420980453491,
+      "eval_runtime": 0.6018,
+      "eval_samples_per_second": 86.403,
+      "eval_steps_per_second": 3.323,
+      "step": 10
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.40384615384615385,
+      "eval_loss": 1.557769536972046,
+      "eval_runtime": 0.6002,
+      "eval_samples_per_second": 86.637,
+      "eval_steps_per_second": 3.332,
+      "step": 12
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.40384615384615385,
+      "eval_loss": 1.5217629671096802,
+      "eval_runtime": 0.5994,
+      "eval_samples_per_second": 86.756,
+      "eval_steps_per_second": 3.337,
+      "step": 14
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.40384615384615385,
+      "eval_loss": 1.4849278926849365,
+      "eval_runtime": 0.5916,
+      "eval_samples_per_second": 87.892,
+      "eval_steps_per_second": 3.38,
+      "step": 16
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.40384615384615385,
+      "eval_loss": 1.4459120035171509,
+      "eval_runtime": 0.631,
+      "eval_samples_per_second": 82.411,
+      "eval_steps_per_second": 3.17,
+      "step": 18
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 3.888888888888889e-05,
+      "loss": 1.4962,
+      "step": 20
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.40384615384615385,
+      "eval_loss": 1.4108681678771973,
+      "eval_runtime": 0.6792,
+      "eval_samples_per_second": 76.559,
+      "eval_steps_per_second": 2.945,
+      "step": 20
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.40384615384615385,
+      "eval_loss": 1.3940582275390625,
+      "eval_runtime": 0.6563,
+      "eval_samples_per_second": 79.237,
+      "eval_steps_per_second": 3.048,
+      "step": 22
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.40384615384615385,
+      "eval_loss": 1.3864620923995972,
+      "eval_runtime": 0.6095,
+      "eval_samples_per_second": 85.32,
+      "eval_steps_per_second": 3.282,
+      "step": 24
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.40384615384615385,
+      "eval_loss": 1.3753844499588013,
+      "eval_runtime": 0.5989,
+      "eval_samples_per_second": 86.825,
+      "eval_steps_per_second": 3.339,
+      "step": 26
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.40384615384615385,
+      "eval_loss": 1.3655123710632324,
+      "eval_runtime": 0.7862,
+      "eval_samples_per_second": 66.14,
+      "eval_steps_per_second": 2.544,
+      "step": 28
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 3.6111111111111116e-05,
+      "loss": 1.3392,
+      "step": 30
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 0.40384615384615385,
+      "eval_loss": 1.3794106245040894,
+      "eval_runtime": 0.6509,
+      "eval_samples_per_second": 79.893,
+      "eval_steps_per_second": 3.073,
+      "step": 30
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.40384615384615385,
+      "eval_loss": 1.3799992799758911,
+      "eval_runtime": 0.6103,
+      "eval_samples_per_second": 85.198,
+      "eval_steps_per_second": 3.277,
+      "step": 32
+    },
+    {
+      "epoch": 17.0,
+      "eval_accuracy": 0.40384615384615385,
+      "eval_loss": 1.3404345512390137,
+      "eval_runtime": 0.6343,
+      "eval_samples_per_second": 81.985,
+      "eval_steps_per_second": 3.153,
+      "step": 34
+    },
+    {
+      "epoch": 18.0,
+      "eval_accuracy": 0.40384615384615385,
+      "eval_loss": 1.333656907081604,
+      "eval_runtime": 0.5981,
+      "eval_samples_per_second": 86.938,
+      "eval_steps_per_second": 3.344,
+      "step": 36
+    },
+    {
+      "epoch": 19.0,
+      "eval_accuracy": 0.40384615384615385,
+      "eval_loss": 1.360221028327942,
+      "eval_runtime": 0.6045,
+      "eval_samples_per_second": 86.016,
+      "eval_steps_per_second": 3.308,
+      "step": 38
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.2738,
+      "step": 40
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.40384615384615385,
+      "eval_loss": 1.3383551836013794,
+      "eval_runtime": 0.606,
+      "eval_samples_per_second": 85.809,
+      "eval_steps_per_second": 3.3,
+      "step": 40
+    },
+    {
+      "epoch": 21.0,
+      "eval_accuracy": 0.40384615384615385,
+      "eval_loss": 1.324778437614441,
+      "eval_runtime": 0.6288,
+      "eval_samples_per_second": 82.703,
+      "eval_steps_per_second": 3.181,
+      "step": 42
+    },
+    {
+      "epoch": 22.0,
+      "eval_accuracy": 0.40384615384615385,
+      "eval_loss": 1.2693126201629639,
+      "eval_runtime": 0.649,
+      "eval_samples_per_second": 80.121,
+      "eval_steps_per_second": 3.082,
+      "step": 44
+    },
+    {
+      "epoch": 23.0,
+      "eval_accuracy": 0.40384615384615385,
+      "eval_loss": 1.2394922971725464,
+      "eval_runtime": 0.6309,
+      "eval_samples_per_second": 82.421,
+      "eval_steps_per_second": 3.17,
+      "step": 46
+    },
+    {
+      "epoch": 24.0,
+      "eval_accuracy": 0.40384615384615385,
+      "eval_loss": 1.2427353858947754,
+      "eval_runtime": 0.5994,
+      "eval_samples_per_second": 86.758,
+      "eval_steps_per_second": 3.337,
+      "step": 48
+    },
+    {
+      "epoch": 25.0,
+      "learning_rate": 3.0555555555555554e-05,
+      "loss": 1.2283,
+      "step": 50
+    },
+    {
+      "epoch": 25.0,
+      "eval_accuracy": 0.40384615384615385,
+      "eval_loss": 1.2884917259216309,
+      "eval_runtime": 0.6483,
+      "eval_samples_per_second": 80.212,
+      "eval_steps_per_second": 3.085,
+      "step": 50
+    },
+    {
+      "epoch": 26.0,
+      "eval_accuracy": 0.40384615384615385,
+      "eval_loss": 1.2916259765625,
+      "eval_runtime": 0.6262,
+      "eval_samples_per_second": 83.039,
+      "eval_steps_per_second": 3.194,
+      "step": 52
+    },
+    {
+      "epoch": 27.0,
+      "eval_accuracy": 0.40384615384615385,
+      "eval_loss": 1.2353298664093018,
+      "eval_runtime": 0.6205,
+      "eval_samples_per_second": 83.797,
+      "eval_steps_per_second": 3.223,
+      "step": 54
+    },
+    {
+      "epoch": 28.0,
+      "eval_accuracy": 0.40384615384615385,
+      "eval_loss": 1.2031632661819458,
+      "eval_runtime": 0.6285,
+      "eval_samples_per_second": 82.735,
+      "eval_steps_per_second": 3.182,
+      "step": 56
+    },
+    {
+      "epoch": 29.0,
+      "eval_accuracy": 0.5576923076923077,
+      "eval_loss": 1.209951639175415,
+      "eval_runtime": 0.6191,
+      "eval_samples_per_second": 83.997,
+      "eval_steps_per_second": 3.231,
+      "step": 58
+    },
+    {
+      "epoch": 30.0,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 1.1804,
+      "step": 60
+    },
+    {
+      "epoch": 30.0,
+      "eval_accuracy": 0.6153846153846154,
+      "eval_loss": 1.210994005203247,
+      "eval_runtime": 0.6216,
+      "eval_samples_per_second": 83.653,
+      "eval_steps_per_second": 3.217,
+      "step": 60
+    },
+    {
+      "epoch": 31.0,
+      "eval_accuracy": 0.6346153846153846,
+      "eval_loss": 1.17095947265625,
+      "eval_runtime": 0.6376,
+      "eval_samples_per_second": 81.553,
+      "eval_steps_per_second": 3.137,
+      "step": 62
+    },
+    {
+      "epoch": 32.0,
+      "eval_accuracy": 0.6153846153846154,
+      "eval_loss": 1.132305383682251,
+      "eval_runtime": 0.6381,
+      "eval_samples_per_second": 81.492,
+      "eval_steps_per_second": 3.134,
+      "step": 64
+    },
+    {
+      "epoch": 33.0,
+      "eval_accuracy": 0.5961538461538461,
+      "eval_loss": 1.1082764863967896,
+      "eval_runtime": 0.6131,
+      "eval_samples_per_second": 84.813,
+      "eval_steps_per_second": 3.262,
+      "step": 66
+    },
+    {
+      "epoch": 34.0,
+      "eval_accuracy": 0.5961538461538461,
+      "eval_loss": 1.09354829788208,
+      "eval_runtime": 0.6605,
+      "eval_samples_per_second": 78.734,
+      "eval_steps_per_second": 3.028,
+      "step": 68
+    },
+    {
+      "epoch": 35.0,
+      "learning_rate": 2.5e-05,
+      "loss": 1.0925,
+      "step": 70
+    },
+    {
+      "epoch": 35.0,
+      "eval_accuracy": 0.6346153846153846,
+      "eval_loss": 1.0853270292282104,
+      "eval_runtime": 0.6707,
+      "eval_samples_per_second": 77.535,
+      "eval_steps_per_second": 2.982,
+      "step": 70
+    },
+    {
+      "epoch": 36.0,
+      "eval_accuracy": 0.6730769230769231,
+      "eval_loss": 1.0622206926345825,
+      "eval_runtime": 0.6098,
+      "eval_samples_per_second": 85.28,
+      "eval_steps_per_second": 3.28,
+      "step": 72
+    },
+    {
+      "epoch": 37.0,
+      "eval_accuracy": 0.7115384615384616,
+      "eval_loss": 1.015413522720337,
+      "eval_runtime": 0.6146,
+      "eval_samples_per_second": 84.601,
+      "eval_steps_per_second": 3.254,
+      "step": 74
+    },
+    {
+      "epoch": 38.0,
+      "eval_accuracy": 0.7115384615384616,
+      "eval_loss": 0.9900897145271301,
+      "eval_runtime": 0.6263,
+      "eval_samples_per_second": 83.028,
+      "eval_steps_per_second": 3.193,
+      "step": 76
+    },
+    {
+      "epoch": 39.0,
+      "eval_accuracy": 0.6923076923076923,
+      "eval_loss": 0.992486834526062,
+      "eval_runtime": 0.6363,
+      "eval_samples_per_second": 81.717,
+      "eval_steps_per_second": 3.143,
+      "step": 78
+    },
+    {
+      "epoch": 40.0,
+      "learning_rate": 2.2222222222222227e-05,
+      "loss": 0.9981,
+      "step": 80
+    },
+    {
+      "epoch": 40.0,
+      "eval_accuracy": 0.6730769230769231,
+      "eval_loss": 0.9864760041236877,
+      "eval_runtime": 0.61,
+      "eval_samples_per_second": 85.242,
+      "eval_steps_per_second": 3.279,
+      "step": 80
+    },
+    {
+      "epoch": 41.0,
+      "eval_accuracy": 0.6730769230769231,
+      "eval_loss": 0.9539706110954285,
+      "eval_runtime": 0.6046,
+      "eval_samples_per_second": 86.003,
+      "eval_steps_per_second": 3.308,
+      "step": 82
+    },
+    {
+      "epoch": 42.0,
+      "eval_accuracy": 0.7115384615384616,
+      "eval_loss": 0.931605875492096,
+      "eval_runtime": 0.61,
+      "eval_samples_per_second": 85.247,
+      "eval_steps_per_second": 3.279,
+      "step": 84
+    },
+    {
+      "epoch": 43.0,
+      "eval_accuracy": 0.7115384615384616,
+      "eval_loss": 0.9304342269897461,
+      "eval_runtime": 0.6185,
+      "eval_samples_per_second": 84.076,
+      "eval_steps_per_second": 3.234,
+      "step": 86
+    },
+    {
+      "epoch": 44.0,
+      "eval_accuracy": 0.6923076923076923,
+      "eval_loss": 0.9246343970298767,
+      "eval_runtime": 0.6813,
+      "eval_samples_per_second": 76.322,
+      "eval_steps_per_second": 2.935,
+      "step": 88
+    },
+    {
+      "epoch": 45.0,
+      "learning_rate": 1.9444444444444445e-05,
+      "loss": 0.9102,
+      "step": 90
+    },
+    {
+      "epoch": 45.0,
+      "eval_accuracy": 0.7115384615384616,
+      "eval_loss": 0.8784506916999817,
+      "eval_runtime": 0.6181,
+      "eval_samples_per_second": 84.124,
+      "eval_steps_per_second": 3.236,
+      "step": 90
+    },
+    {
+      "epoch": 46.0,
+      "eval_accuracy": 0.7115384615384616,
+      "eval_loss": 0.8422226309776306,
+      "eval_runtime": 0.6163,
+      "eval_samples_per_second": 84.379,
+      "eval_steps_per_second": 3.245,
+      "step": 92
+    },
+    {
+      "epoch": 47.0,
+      "eval_accuracy": 0.7115384615384616,
+      "eval_loss": 0.8381490707397461,
+      "eval_runtime": 0.6224,
+      "eval_samples_per_second": 83.552,
+      "eval_steps_per_second": 3.214,
+      "step": 94
+    },
+    {
+      "epoch": 48.0,
+      "eval_accuracy": 0.7115384615384616,
+      "eval_loss": 0.8359355926513672,
+      "eval_runtime": 0.7117,
+      "eval_samples_per_second": 73.061,
+      "eval_steps_per_second": 2.81,
+      "step": 96
+    },
+    {
+      "epoch": 49.0,
+      "eval_accuracy": 0.7115384615384616,
+      "eval_loss": 0.8444095253944397,
+      "eval_runtime": 0.6236,
+      "eval_samples_per_second": 83.381,
+      "eval_steps_per_second": 3.207,
+      "step": 98
+    },
+    {
+      "epoch": 50.0,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.8496,
+      "step": 100
+    },
+    {
+      "epoch": 50.0,
+      "eval_accuracy": 0.6730769230769231,
+      "eval_loss": 0.8286628127098083,
+      "eval_runtime": 0.6989,
+      "eval_samples_per_second": 74.398,
+      "eval_steps_per_second": 2.861,
+      "step": 100
+    },
+    {
+      "epoch": 51.0,
+      "eval_accuracy": 0.6923076923076923,
+      "eval_loss": 0.7973195314407349,
+      "eval_runtime": 0.6329,
+      "eval_samples_per_second": 82.162,
+      "eval_steps_per_second": 3.16,
+      "step": 102
+    },
+    {
+      "epoch": 52.0,
+      "eval_accuracy": 0.6923076923076923,
+      "eval_loss": 0.779899537563324,
+      "eval_runtime": 0.6256,
+      "eval_samples_per_second": 83.126,
+      "eval_steps_per_second": 3.197,
+      "step": 104
+    },
+    {
+      "epoch": 53.0,
+      "eval_accuracy": 0.6923076923076923,
+      "eval_loss": 0.7779891490936279,
+      "eval_runtime": 0.6343,
+      "eval_samples_per_second": 81.978,
+      "eval_steps_per_second": 3.153,
+      "step": 106
+    },
+    {
+      "epoch": 54.0,
+      "eval_accuracy": 0.7115384615384616,
+      "eval_loss": 0.7819709181785583,
+      "eval_runtime": 0.6007,
+      "eval_samples_per_second": 86.573,
+      "eval_steps_per_second": 3.33,
+      "step": 108
+    },
+    {
+      "epoch": 55.0,
+      "learning_rate": 1.388888888888889e-05,
+      "loss": 0.7808,
+      "step": 110
+    },
+    {
+      "epoch": 55.0,
+      "eval_accuracy": 0.7115384615384616,
+      "eval_loss": 0.7896474599838257,
+      "eval_runtime": 0.6289,
+      "eval_samples_per_second": 82.683,
+      "eval_steps_per_second": 3.18,
+      "step": 110
+    },
+    {
+      "epoch": 56.0,
+      "eval_accuracy": 0.6923076923076923,
+      "eval_loss": 0.7737353444099426,
+      "eval_runtime": 0.6167,
+      "eval_samples_per_second": 84.318,
+      "eval_steps_per_second": 3.243,
+      "step": 112
+    },
+    {
+      "epoch": 57.0,
+      "eval_accuracy": 0.6730769230769231,
+      "eval_loss": 0.763085663318634,
+      "eval_runtime": 0.6137,
+      "eval_samples_per_second": 84.73,
+      "eval_steps_per_second": 3.259,
+      "step": 114
+    },
+    {
+      "epoch": 58.0,
+      "eval_accuracy": 0.6538461538461539,
+      "eval_loss": 0.7635093927383423,
+      "eval_runtime": 0.6433,
+      "eval_samples_per_second": 80.831,
+      "eval_steps_per_second": 3.109,
+      "step": 116
+    },
+    {
+      "epoch": 59.0,
+      "eval_accuracy": 0.6538461538461539,
+      "eval_loss": 0.7779039144515991,
+      "eval_runtime": 0.6338,
+      "eval_samples_per_second": 82.04,
+      "eval_steps_per_second": 3.155,
+      "step": 118
+    },
+    {
+      "epoch": 60.0,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 0.757,
+      "step": 120
+    },
+    {
+      "epoch": 60.0,
+      "eval_accuracy": 0.6730769230769231,
+      "eval_loss": 0.7990029454231262,
+      "eval_runtime": 0.6164,
+      "eval_samples_per_second": 84.361,
+      "eval_steps_per_second": 3.245,
+      "step": 120
+    },
+    {
+      "epoch": 61.0,
+      "eval_accuracy": 0.6538461538461539,
+      "eval_loss": 0.8221505880355835,
+      "eval_runtime": 0.7222,
+      "eval_samples_per_second": 72.007,
+      "eval_steps_per_second": 2.769,
+      "step": 122
+    },
+    {
+      "epoch": 62.0,
+      "eval_accuracy": 0.6538461538461539,
+      "eval_loss": 0.8203845620155334,
+      "eval_runtime": 0.6138,
+      "eval_samples_per_second": 84.723,
+      "eval_steps_per_second": 3.259,
+      "step": 124
+    },
+    {
+      "epoch": 63.0,
+      "eval_accuracy": 0.6730769230769231,
+      "eval_loss": 0.7964361906051636,
+      "eval_runtime": 0.6279,
+      "eval_samples_per_second": 82.819,
+      "eval_steps_per_second": 3.185,
+      "step": 126
+    },
+    {
+      "epoch": 64.0,
+      "eval_accuracy": 0.6538461538461539,
+      "eval_loss": 0.7818092107772827,
+      "eval_runtime": 0.6388,
+      "eval_samples_per_second": 81.404,
+      "eval_steps_per_second": 3.131,
+      "step": 128
+    },
+    {
+      "epoch": 65.0,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.6919,
+      "step": 130
+    },
+    {
+      "epoch": 65.0,
+      "eval_accuracy": 0.6346153846153846,
+      "eval_loss": 0.7795537710189819,
+      "eval_runtime": 0.6964,
+      "eval_samples_per_second": 74.666,
+      "eval_steps_per_second": 2.872,
+      "step": 130
+    },
+    {
+      "epoch": 66.0,
+      "eval_accuracy": 0.6346153846153846,
+      "eval_loss": 0.7831135392189026,
+      "eval_runtime": 0.6247,
+      "eval_samples_per_second": 83.245,
+      "eval_steps_per_second": 3.202,
+      "step": 132
+    },
+    {
+      "epoch": 67.0,
+      "eval_accuracy": 0.6346153846153846,
+      "eval_loss": 0.7866898775100708,
+      "eval_runtime": 0.6084,
+      "eval_samples_per_second": 85.464,
+      "eval_steps_per_second": 3.287,
+      "step": 134
+    },
+    {
+      "epoch": 68.0,
+      "eval_accuracy": 0.6346153846153846,
+      "eval_loss": 0.785628080368042,
+      "eval_runtime": 0.6378,
+      "eval_samples_per_second": 81.531,
+      "eval_steps_per_second": 3.136,
+      "step": 136
+    },
+    {
+      "epoch": 69.0,
+      "eval_accuracy": 0.6538461538461539,
+      "eval_loss": 0.7793223857879639,
+      "eval_runtime": 0.6338,
+      "eval_samples_per_second": 82.043,
+      "eval_steps_per_second": 3.156,
+      "step": 138
+    },
+    {
+      "epoch": 70.0,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 0.6722,
+      "step": 140
+    },
+    {
+      "epoch": 70.0,
+      "eval_accuracy": 0.6538461538461539,
+      "eval_loss": 0.7736176252365112,
+      "eval_runtime": 0.6283,
+      "eval_samples_per_second": 82.765,
+      "eval_steps_per_second": 3.183,
+      "step": 140
+    },
+    {
+      "epoch": 71.0,
+      "eval_accuracy": 0.6538461538461539,
+      "eval_loss": 0.7681865692138672,
+      "eval_runtime": 0.6291,
+      "eval_samples_per_second": 82.652,
+      "eval_steps_per_second": 3.179,
+      "step": 142
+    },
+    {
+      "epoch": 72.0,
+      "eval_accuracy": 0.6538461538461539,
+      "eval_loss": 0.7681340575218201,
+      "eval_runtime": 0.6524,
+      "eval_samples_per_second": 79.701,
+      "eval_steps_per_second": 3.065,
+      "step": 144
+    },
+    {
+      "epoch": 73.0,
+      "eval_accuracy": 0.6538461538461539,
+      "eval_loss": 0.767238199710846,
+      "eval_runtime": 0.7594,
+      "eval_samples_per_second": 68.472,
+      "eval_steps_per_second": 2.634,
+      "step": 146
+    },
+    {
+      "epoch": 74.0,
+      "eval_accuracy": 0.6538461538461539,
+      "eval_loss": 0.7654622793197632,
+      "eval_runtime": 0.667,
+      "eval_samples_per_second": 77.964,
+      "eval_steps_per_second": 2.999,
+      "step": 148
+    },
+    {
+      "epoch": 75.0,
+      "learning_rate": 2.7777777777777783e-06,
+      "loss": 0.6642,
+      "step": 150
+    },
+    {
+      "epoch": 75.0,
+      "eval_accuracy": 0.6538461538461539,
+      "eval_loss": 0.7645394802093506,
+      "eval_runtime": 0.6584,
+      "eval_samples_per_second": 78.985,
+      "eval_steps_per_second": 3.038,
+      "step": 150
+    },
+    {
+      "epoch": 76.0,
+      "eval_accuracy": 0.6538461538461539,
+      "eval_loss": 0.7657662630081177,
+      "eval_runtime": 0.6248,
+      "eval_samples_per_second": 83.227,
+      "eval_steps_per_second": 3.201,
+      "step": 152
+    },
+    {
+      "epoch": 77.0,
+      "eval_accuracy": 0.6538461538461539,
+      "eval_loss": 0.7677300572395325,
+      "eval_runtime": 0.6243,
+      "eval_samples_per_second": 83.292,
+      "eval_steps_per_second": 3.204,
+      "step": 154
+    },
+    {
+      "epoch": 78.0,
+      "eval_accuracy": 0.6538461538461539,
+      "eval_loss": 0.7683091759681702,
+      "eval_runtime": 0.619,
+      "eval_samples_per_second": 84.01,
+      "eval_steps_per_second": 3.231,
+      "step": 156
+    },
+    {
+      "epoch": 79.0,
+      "eval_accuracy": 0.6538461538461539,
+      "eval_loss": 0.7683802247047424,
+      "eval_runtime": 0.6429,
+      "eval_samples_per_second": 80.882,
+      "eval_steps_per_second": 3.111,
+      "step": 158
+    },
+    {
+      "epoch": 80.0,
+      "learning_rate": 0.0,
+      "loss": 0.6491,
+      "step": 160
+    },
+    {
+      "epoch": 80.0,
+      "eval_accuracy": 0.6538461538461539,
+      "eval_loss": 0.7686132192611694,
+      "eval_runtime": 0.7019,
+      "eval_samples_per_second": 74.089,
+      "eval_steps_per_second": 2.85,
+      "step": 160
+    },
+    {
+      "epoch": 80.0,
+      "step": 160,
+      "total_flos": 6.195054311689421e+17,
+      "train_loss": 1.0117311209440232,
+      "train_runtime": 462.6508,
+      "train_samples_per_second": 41.154,
+      "train_steps_per_second": 0.346
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 160,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 80,
+  "save_steps": 500,
+  "total_flos": 6.195054311689421e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}