{
  "best_metric": 0.7373271889400922,
  "best_model_checkpoint": "videomae-base-finetuned-subset\\checkpoint-1770",
  "epoch": 17.016809116809117,
  "eval_steps": 500,
  "global_step": 2124,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 7.122507122507123e-07,
      "loss": 1.6298,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.4245014245014246e-06,
      "loss": 1.6341,
      "step": 20
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.136752136752137e-06,
      "loss": 1.6059,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.8490028490028492e-06,
      "loss": 1.6036,
      "step": 40
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.5612535612535615e-06,
      "loss": 1.6528,
      "step": 50
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.273504273504274e-06,
      "loss": 1.62,
      "step": 60
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.985754985754986e-06,
      "loss": 1.6109,
      "step": 70
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.6980056980056985e-06,
      "loss": 1.6268,
      "step": 80
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.41025641025641e-06,
      "loss": 1.6502,
      "step": 90
    },
    {
      "epoch": 0.01,
      "learning_rate": 7.122507122507123e-06,
      "loss": 1.5551,
      "step": 100
    },
    {
      "epoch": 0.02,
      "learning_rate": 7.834757834757835e-06,
      "loss": 1.6277,
      "step": 110
    },
    {
      "epoch": 0.02,
      "eval_accuracy": 0.08755760368663594,
      "eval_loss": 1.579700231552124,
      "eval_runtime": 293.8716,
      "eval_samples_per_second": 0.738,
      "eval_steps_per_second": 0.187,
      "step": 118
    },
    {
      "epoch": 1.0,
      "learning_rate": 8.547008547008548e-06,
      "loss": 1.6441,
      "step": 120
    },
    {
      "epoch": 1.0,
      "learning_rate": 9.259259259259259e-06,
      "loss": 1.6682,
      "step": 130
    },
    {
      "epoch": 1.0,
      "learning_rate": 9.971509971509972e-06,
      "loss": 1.5708,
      "step": 140
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.0683760683760684e-05,
      "loss": 1.5522,
      "step": 150
    },
    {
      "epoch": 1.01,
      "learning_rate": 1.1396011396011397e-05,
      "loss": 1.5703,
      "step": 160
    },
    {
      "epoch": 1.01,
      "learning_rate": 1.2108262108262108e-05,
      "loss": 1.6537,
      "step": 170
    },
    {
      "epoch": 1.01,
      "learning_rate": 1.282051282051282e-05,
      "loss": 1.6126,
      "step": 180
    },
    {
      "epoch": 1.01,
      "learning_rate": 1.3532763532763535e-05,
      "loss": 1.6827,
      "step": 190
    },
    {
      "epoch": 1.01,
      "learning_rate": 1.4245014245014246e-05,
      "loss": 1.5872,
      "step": 200
    },
    {
      "epoch": 1.01,
      "learning_rate": 1.4957264957264958e-05,
      "loss": 1.5702,
      "step": 210
    },
    {
      "epoch": 1.01,
      "learning_rate": 1.566951566951567e-05,
      "loss": 1.5971,
      "step": 220
    },
    {
      "epoch": 1.02,
      "learning_rate": 1.6381766381766382e-05,
      "loss": 1.6542,
      "step": 230
    },
    {
      "epoch": 1.02,
      "eval_accuracy": 0.1336405529953917,
      "eval_loss": 1.654339075088501,
      "eval_runtime": 264.9103,
      "eval_samples_per_second": 0.819,
      "eval_steps_per_second": 0.208,
      "step": 236
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.7094017094017095e-05,
      "loss": 1.5755,
      "step": 240
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.7806267806267805e-05,
      "loss": 1.6276,
      "step": 250
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 1.6158,
      "step": 260
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.923076923076923e-05,
      "loss": 1.5842,
      "step": 270
    },
    {
      "epoch": 2.01,
      "learning_rate": 1.9943019943019945e-05,
      "loss": 1.5915,
      "step": 280
    },
    {
      "epoch": 2.01,
      "learning_rate": 2.0655270655270654e-05,
      "loss": 1.4263,
      "step": 290
    },
    {
      "epoch": 2.01,
      "learning_rate": 2.1367521367521368e-05,
      "loss": 1.4421,
      "step": 300
    },
    {
      "epoch": 2.01,
      "learning_rate": 2.207977207977208e-05,
      "loss": 1.2551,
      "step": 310
    },
    {
      "epoch": 2.01,
      "learning_rate": 2.2792022792022794e-05,
      "loss": 1.3329,
      "step": 320
    },
    {
      "epoch": 2.01,
      "learning_rate": 2.3504273504273504e-05,
      "loss": 1.1874,
      "step": 330
    },
    {
      "epoch": 2.01,
      "learning_rate": 2.4216524216524217e-05,
      "loss": 1.3141,
      "step": 340
    },
    {
      "epoch": 2.02,
      "learning_rate": 2.492877492877493e-05,
      "loss": 1.522,
      "step": 350
    },
    {
      "epoch": 2.02,
      "eval_accuracy": 0.3271889400921659,
      "eval_loss": 1.3541377782821655,
      "eval_runtime": 259.8187,
      "eval_samples_per_second": 0.835,
      "eval_steps_per_second": 0.212,
      "step": 354
    },
    {
      "epoch": 3.0,
      "learning_rate": 2.564102564102564e-05,
      "loss": 1.3559,
      "step": 360
    },
    {
      "epoch": 3.0,
      "learning_rate": 2.6353276353276356e-05,
      "loss": 1.4339,
      "step": 370
    },
    {
      "epoch": 3.0,
      "learning_rate": 2.706552706552707e-05,
      "loss": 1.1016,
      "step": 380
    },
    {
      "epoch": 3.01,
      "learning_rate": 2.777777777777778e-05,
      "loss": 1.1426,
      "step": 390
    },
    {
      "epoch": 3.01,
      "learning_rate": 2.8490028490028492e-05,
      "loss": 1.5716,
      "step": 400
    },
    {
      "epoch": 3.01,
      "learning_rate": 2.9202279202279202e-05,
      "loss": 1.201,
      "step": 410
    },
    {
      "epoch": 3.01,
      "learning_rate": 2.9914529914529915e-05,
      "loss": 1.3309,
      "step": 420
    },
    {
      "epoch": 3.01,
      "learning_rate": 3.0626780626780625e-05,
      "loss": 1.3621,
      "step": 430
    },
    {
      "epoch": 3.01,
      "learning_rate": 3.133903133903134e-05,
      "loss": 1.3497,
      "step": 440
    },
    {
      "epoch": 3.01,
      "learning_rate": 3.205128205128206e-05,
      "loss": 1.3392,
      "step": 450
    },
    {
      "epoch": 3.02,
      "learning_rate": 3.2763532763532764e-05,
      "loss": 1.1704,
      "step": 460
    },
    {
      "epoch": 3.02,
      "learning_rate": 3.347578347578348e-05,
      "loss": 1.2632,
      "step": 470
    },
    {
      "epoch": 3.02,
      "eval_accuracy": 0.3640552995391705,
      "eval_loss": 1.2103053331375122,
      "eval_runtime": 269.6766,
      "eval_samples_per_second": 0.805,
      "eval_steps_per_second": 0.204,
      "step": 472
    },
    {
      "epoch": 4.0,
      "learning_rate": 3.418803418803419e-05,
      "loss": 1.2155,
      "step": 480
    },
    {
      "epoch": 4.0,
      "learning_rate": 3.4900284900284904e-05,
      "loss": 1.1909,
      "step": 490
    },
    {
      "epoch": 4.0,
      "learning_rate": 3.561253561253561e-05,
      "loss": 1.355,
      "step": 500
    },
    {
      "epoch": 4.01,
      "learning_rate": 3.6324786324786323e-05,
      "loss": 1.4403,
      "step": 510
    },
    {
      "epoch": 4.01,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 1.2344,
      "step": 520
    },
    {
      "epoch": 4.01,
      "learning_rate": 3.774928774928775e-05,
      "loss": 1.1599,
      "step": 530
    },
    {
      "epoch": 4.01,
      "learning_rate": 3.846153846153846e-05,
      "loss": 1.0906,
      "step": 540
    },
    {
      "epoch": 4.01,
      "learning_rate": 3.9173789173789176e-05,
      "loss": 1.4037,
      "step": 550
    },
    {
      "epoch": 4.01,
      "learning_rate": 3.988603988603989e-05,
      "loss": 1.015,
      "step": 560
    },
    {
      "epoch": 4.01,
      "learning_rate": 4.05982905982906e-05,
      "loss": 1.1146,
      "step": 570
    },
    {
      "epoch": 4.02,
      "learning_rate": 4.131054131054131e-05,
      "loss": 1.3183,
      "step": 580
    },
    {
      "epoch": 4.02,
      "learning_rate": 4.202279202279202e-05,
      "loss": 1.094,
      "step": 590
    },
    {
      "epoch": 4.02,
      "eval_accuracy": 0.6682027649769585,
      "eval_loss": 1.0165023803710938,
      "eval_runtime": 285.7344,
      "eval_samples_per_second": 0.759,
      "eval_steps_per_second": 0.192,
      "step": 590
    },
    {
      "epoch": 5.0,
      "learning_rate": 4.2735042735042735e-05,
      "loss": 1.0792,
      "step": 600
    },
    {
      "epoch": 5.0,
      "learning_rate": 4.344729344729345e-05,
      "loss": 0.9429,
      "step": 610
    },
    {
      "epoch": 5.0,
      "learning_rate": 4.415954415954416e-05,
      "loss": 1.1575,
      "step": 620
    },
    {
      "epoch": 5.01,
      "learning_rate": 4.4871794871794874e-05,
      "loss": 1.03,
      "step": 630
    },
    {
      "epoch": 5.01,
      "learning_rate": 4.558404558404559e-05,
      "loss": 1.2668,
      "step": 640
    },
    {
      "epoch": 5.01,
      "learning_rate": 4.62962962962963e-05,
      "loss": 1.4121,
      "step": 650
    },
    {
      "epoch": 5.01,
      "learning_rate": 4.700854700854701e-05,
      "loss": 1.3624,
      "step": 660
    },
    {
      "epoch": 5.01,
      "learning_rate": 4.772079772079772e-05,
      "loss": 1.0479,
      "step": 670
    },
    {
      "epoch": 5.01,
      "learning_rate": 4.8433048433048433e-05,
      "loss": 1.3261,
      "step": 680
    },
    {
      "epoch": 5.01,
      "learning_rate": 4.9145299145299147e-05,
      "loss": 1.0643,
      "step": 690
    },
    {
      "epoch": 5.02,
      "learning_rate": 4.985754985754986e-05,
      "loss": 1.183,
      "step": 700
    },
    {
      "epoch": 5.02,
      "eval_accuracy": 0.6082949308755761,
      "eval_loss": 1.023329496383667,
      "eval_runtime": 286.9179,
      "eval_samples_per_second": 0.756,
      "eval_steps_per_second": 0.192,
      "step": 708
    },
    {
      "epoch": 6.0,
      "learning_rate": 4.993668882557772e-05,
      "loss": 1.0286,
      "step": 710
    },
    {
      "epoch": 6.0,
      "learning_rate": 4.985754985754986e-05,
      "loss": 1.2985,
      "step": 720
    },
    {
      "epoch": 6.0,
      "learning_rate": 4.9778410889522e-05,
      "loss": 1.3161,
      "step": 730
    },
    {
      "epoch": 6.0,
      "learning_rate": 4.9699271921494144e-05,
      "loss": 1.2498,
      "step": 740
    },
    {
      "epoch": 6.01,
      "learning_rate": 4.962013295346629e-05,
      "loss": 1.0488,
      "step": 750
    },
    {
      "epoch": 6.01,
      "learning_rate": 4.9540993985438435e-05,
      "loss": 1.1916,
      "step": 760
    },
    {
      "epoch": 6.01,
      "learning_rate": 4.946185501741058e-05,
      "loss": 1.3807,
      "step": 770
    },
    {
      "epoch": 6.01,
      "learning_rate": 4.938271604938271e-05,
      "loss": 1.1852,
      "step": 780
    },
    {
      "epoch": 6.01,
      "learning_rate": 4.930357708135486e-05,
      "loss": 1.3454,
      "step": 790
    },
    {
      "epoch": 6.01,
      "learning_rate": 4.9224438113327004e-05,
      "loss": 1.1208,
      "step": 800
    },
    {
      "epoch": 6.01,
      "learning_rate": 4.9145299145299147e-05,
      "loss": 1.0341,
      "step": 810
    },
    {
      "epoch": 6.02,
      "learning_rate": 4.906616017727129e-05,
      "loss": 1.1543,
      "step": 820
    },
    {
      "epoch": 6.02,
      "eval_accuracy": 0.5391705069124424,
      "eval_loss": 1.108931064605713,
      "eval_runtime": 273.7329,
      "eval_samples_per_second": 0.793,
      "eval_steps_per_second": 0.201,
      "step": 826
    },
    {
      "epoch": 7.0,
      "learning_rate": 4.898702120924343e-05,
      "loss": 1.1723,
      "step": 830
    },
    {
      "epoch": 7.0,
      "learning_rate": 4.890788224121557e-05,
      "loss": 1.0579,
      "step": 840
    },
    {
      "epoch": 7.0,
      "learning_rate": 4.882874327318772e-05,
      "loss": 0.9805,
      "step": 850
    },
    {
      "epoch": 7.0,
      "learning_rate": 4.8749604305159865e-05,
      "loss": 1.1434,
      "step": 860
    },
    {
      "epoch": 7.01,
      "learning_rate": 4.867046533713201e-05,
      "loss": 1.2956,
      "step": 870
    },
    {
      "epoch": 7.01,
      "learning_rate": 4.859132636910415e-05,
      "loss": 1.1865,
      "step": 880
    },
    {
      "epoch": 7.01,
      "learning_rate": 4.851218740107629e-05,
      "loss": 1.226,
      "step": 890
    },
    {
      "epoch": 7.01,
      "learning_rate": 4.8433048433048433e-05,
      "loss": 0.9409,
      "step": 900
    },
    {
      "epoch": 7.01,
      "learning_rate": 4.835390946502058e-05,
      "loss": 1.05,
      "step": 910
    },
    {
      "epoch": 7.01,
      "learning_rate": 4.8274770496992725e-05,
      "loss": 1.0455,
      "step": 920
    },
    {
      "epoch": 7.01,
      "learning_rate": 4.819563152896486e-05,
      "loss": 0.8294,
      "step": 930
    },
    {
      "epoch": 7.02,
      "learning_rate": 4.811649256093701e-05,
      "loss": 1.1015,
      "step": 940
    },
    {
      "epoch": 7.02,
      "eval_accuracy": 0.45161290322580644,
      "eval_loss": 1.171296238899231,
      "eval_runtime": 263.2049,
      "eval_samples_per_second": 0.824,
      "eval_steps_per_second": 0.209,
      "step": 944
    },
    {
      "epoch": 8.0,
      "learning_rate": 4.803735359290915e-05,
      "loss": 0.7604,
      "step": 950
    },
    {
      "epoch": 8.0,
      "learning_rate": 4.7958214624881294e-05,
      "loss": 1.3654,
      "step": 960
    },
    {
      "epoch": 8.0,
      "learning_rate": 4.787907565685344e-05,
      "loss": 1.0182,
      "step": 970
    },
    {
      "epoch": 8.01,
      "learning_rate": 4.779993668882558e-05,
      "loss": 1.007,
      "step": 980
    },
    {
      "epoch": 8.01,
      "learning_rate": 4.772079772079772e-05,
      "loss": 0.9339,
      "step": 990
    },
    {
      "epoch": 8.01,
      "learning_rate": 4.764165875276987e-05,
      "loss": 0.8832,
      "step": 1000
    },
    {
      "epoch": 8.01,
      "learning_rate": 4.756251978474201e-05,
      "loss": 0.8878,
      "step": 1010
    },
    {
      "epoch": 8.01,
      "learning_rate": 4.7483380816714154e-05,
      "loss": 1.038,
      "step": 1020
    },
    {
      "epoch": 8.01,
      "learning_rate": 4.7404241848686296e-05,
      "loss": 1.0377,
      "step": 1030
    },
    {
      "epoch": 8.01,
      "learning_rate": 4.732510288065844e-05,
      "loss": 1.1283,
      "step": 1040
    },
    {
      "epoch": 8.02,
      "learning_rate": 4.724596391263058e-05,
      "loss": 0.845,
      "step": 1050
    },
    {
      "epoch": 8.02,
      "learning_rate": 4.716682494460272e-05,
      "loss": 1.012,
      "step": 1060
    },
    {
      "epoch": 8.02,
      "eval_accuracy": 0.6175115207373272,
      "eval_loss": 1.0352449417114258,
      "eval_runtime": 279.9204,
      "eval_samples_per_second": 0.775,
      "eval_steps_per_second": 0.196,
      "step": 1062
    },
    {
      "epoch": 9.0,
      "learning_rate": 4.708768597657487e-05,
      "loss": 1.3229,
      "step": 1070
    },
    {
      "epoch": 9.0,
      "learning_rate": 4.700854700854701e-05,
      "loss": 1.2021,
      "step": 1080
    },
    {
      "epoch": 9.0,
      "learning_rate": 4.692940804051915e-05,
      "loss": 1.2585,
      "step": 1090
    },
    {
      "epoch": 9.01,
      "learning_rate": 4.68502690724913e-05,
      "loss": 1.0603,
      "step": 1100
    },
    {
      "epoch": 9.01,
      "learning_rate": 4.677113010446344e-05,
      "loss": 0.9872,
      "step": 1110
    },
    {
      "epoch": 9.01,
      "learning_rate": 4.669199113643558e-05,
      "loss": 1.0278,
      "step": 1120
    },
    {
      "epoch": 9.01,
      "learning_rate": 4.6612852168407725e-05,
      "loss": 0.8111,
      "step": 1130
    },
    {
      "epoch": 9.01,
      "learning_rate": 4.653371320037987e-05,
      "loss": 1.0985,
      "step": 1140
    },
    {
      "epoch": 9.01,
      "learning_rate": 4.645457423235201e-05,
      "loss": 0.6293,
      "step": 1150
    },
    {
      "epoch": 9.01,
      "learning_rate": 4.637543526432416e-05,
      "loss": 1.0005,
      "step": 1160
    },
    {
      "epoch": 9.02,
      "learning_rate": 4.62962962962963e-05,
      "loss": 1.0029,
      "step": 1170
    },
    {
      "epoch": 9.02,
      "learning_rate": 4.621715732826844e-05,
      "loss": 0.7159,
      "step": 1180
    },
    {
      "epoch": 9.02,
      "eval_accuracy": 0.5622119815668203,
      "eval_loss": 1.004241704940796,
      "eval_runtime": 302.8171,
      "eval_samples_per_second": 0.717,
      "eval_steps_per_second": 0.182,
      "step": 1180
    },
    {
      "epoch": 10.0,
      "learning_rate": 4.6138018360240585e-05,
      "loss": 0.86,
      "step": 1190
    },
    {
      "epoch": 10.0,
      "learning_rate": 4.605887939221273e-05,
      "loss": 0.9204,
      "step": 1200
    },
    {
      "epoch": 10.0,
      "learning_rate": 4.597974042418487e-05,
      "loss": 0.9883,
      "step": 1210
    },
    {
      "epoch": 10.01,
      "learning_rate": 4.590060145615702e-05,
      "loss": 0.9755,
      "step": 1220
    },
    {
      "epoch": 10.01,
      "learning_rate": 4.582146248812916e-05,
      "loss": 0.8854,
      "step": 1230
    },
    {
      "epoch": 10.01,
      "learning_rate": 4.5742323520101296e-05,
      "loss": 1.1736,
      "step": 1240
    },
    {
      "epoch": 10.01,
      "learning_rate": 4.5663184552073445e-05,
      "loss": 0.8579,
      "step": 1250
    },
    {
      "epoch": 10.01,
      "learning_rate": 4.558404558404559e-05,
      "loss": 0.8537,
      "step": 1260
    },
    {
      "epoch": 10.01,
      "learning_rate": 4.550490661601773e-05,
      "loss": 0.8163,
      "step": 1270
    },
    {
      "epoch": 10.01,
      "learning_rate": 4.542576764798987e-05,
      "loss": 0.8938,
      "step": 1280
    },
    {
      "epoch": 10.02,
      "learning_rate": 4.5346628679962014e-05,
      "loss": 0.9417,
      "step": 1290
    },
    {
      "epoch": 10.02,
      "eval_accuracy": 0.5023041474654378,
      "eval_loss": 1.1916040182113647,
      "eval_runtime": 290.3991,
      "eval_samples_per_second": 0.747,
      "eval_steps_per_second": 0.189,
      "step": 1298
    },
    {
      "epoch": 11.0,
      "learning_rate": 4.5267489711934157e-05,
      "loss": 0.7397,
      "step": 1300
    },
    {
      "epoch": 11.0,
      "learning_rate": 4.51883507439063e-05,
      "loss": 0.9699,
      "step": 1310
    },
    {
      "epoch": 11.0,
      "learning_rate": 4.510921177587845e-05,
      "loss": 1.0963,
      "step": 1320
    },
    {
      "epoch": 11.0,
      "learning_rate": 4.503007280785059e-05,
      "loss": 0.6996,
      "step": 1330
    },
    {
      "epoch": 11.01,
      "learning_rate": 4.4950933839822725e-05,
      "loss": 0.878,
      "step": 1340
    },
    {
      "epoch": 11.01,
      "learning_rate": 4.4871794871794874e-05,
      "loss": 1.1484,
      "step": 1350
    },
    {
      "epoch": 11.01,
      "learning_rate": 4.479265590376702e-05,
      "loss": 1.0544,
      "step": 1360
    },
    {
      "epoch": 11.01,
      "learning_rate": 4.471351693573916e-05,
      "loss": 0.9162,
      "step": 1370
    },
    {
      "epoch": 11.01,
      "learning_rate": 4.463437796771131e-05,
      "loss": 0.8283,
      "step": 1380
    },
    {
      "epoch": 11.01,
      "learning_rate": 4.455523899968344e-05,
      "loss": 1.0451,
      "step": 1390
    },
    {
      "epoch": 11.01,
      "learning_rate": 4.4476100031655586e-05,
      "loss": 1.1554,
      "step": 1400
    },
    {
      "epoch": 11.02,
      "learning_rate": 4.4396961063627735e-05,
      "loss": 1.0331,
      "step": 1410
    },
    {
      "epoch": 11.02,
      "eval_accuracy": 0.6359447004608295,
      "eval_loss": 0.9247654676437378,
      "eval_runtime": 279.9164,
      "eval_samples_per_second": 0.775,
      "eval_steps_per_second": 0.196,
      "step": 1416
    },
    {
      "epoch": 12.0,
      "learning_rate": 4.431782209559988e-05,
      "loss": 0.7141,
      "step": 1420
    },
    {
      "epoch": 12.0,
      "learning_rate": 4.423868312757202e-05,
      "loss": 0.6275,
      "step": 1430
    },
    {
      "epoch": 12.0,
      "learning_rate": 4.415954415954416e-05,
      "loss": 0.8072,
      "step": 1440
    },
    {
      "epoch": 12.0,
      "learning_rate": 4.4080405191516304e-05,
      "loss": 0.9574,
      "step": 1450
    },
    {
      "epoch": 12.01,
      "learning_rate": 4.4001266223488446e-05,
      "loss": 1.0716,
      "step": 1460
    },
    {
      "epoch": 12.01,
      "learning_rate": 4.3922127255460595e-05,
      "loss": 1.2938,
      "step": 1470
    },
    {
      "epoch": 12.01,
      "learning_rate": 4.384298828743274e-05,
      "loss": 1.0527,
      "step": 1480
    },
    {
      "epoch": 12.01,
      "learning_rate": 4.376384931940488e-05,
      "loss": 0.9223,
      "step": 1490
    },
    {
      "epoch": 12.01,
      "learning_rate": 4.368471035137702e-05,
      "loss": 0.9105,
      "step": 1500
    },
    {
      "epoch": 12.01,
      "learning_rate": 4.3605571383349164e-05,
      "loss": 0.8926,
      "step": 1510
    },
    {
      "epoch": 12.01,
      "learning_rate": 4.3526432415321306e-05,
      "loss": 0.7864,
      "step": 1520
    },
    {
      "epoch": 12.02,
      "learning_rate": 4.344729344729345e-05,
      "loss": 1.208,
      "step": 1530
    },
    {
      "epoch": 12.02,
      "eval_accuracy": 0.7096774193548387,
      "eval_loss": 0.7162204384803772,
      "eval_runtime": 253.0914,
      "eval_samples_per_second": 0.857,
      "eval_steps_per_second": 0.217,
      "step": 1534
    },
    {
      "epoch": 13.0,
      "learning_rate": 4.336815447926559e-05,
      "loss": 0.5751,
      "step": 1540
    },
    {
      "epoch": 13.0,
      "learning_rate": 4.328901551123773e-05,
      "loss": 0.892,
      "step": 1550
    },
    {
      "epoch": 13.0,
      "learning_rate": 4.3209876543209875e-05,
      "loss": 0.8127,
      "step": 1560
    },
    {
      "epoch": 13.01,
      "learning_rate": 4.3130737575182024e-05,
      "loss": 0.7734,
      "step": 1570
    },
    {
      "epoch": 13.01,
      "learning_rate": 4.3051598607154166e-05,
      "loss": 0.6491,
      "step": 1580
    },
    {
      "epoch": 13.01,
      "learning_rate": 4.297245963912631e-05,
      "loss": 1.2019,
      "step": 1590
    },
    {
      "epoch": 13.01,
      "learning_rate": 4.289332067109845e-05,
      "loss": 0.8835,
      "step": 1600
    },
    {
      "epoch": 13.01,
      "learning_rate": 4.281418170307059e-05,
      "loss": 1.1494,
      "step": 1610
    },
    {
      "epoch": 13.01,
      "learning_rate": 4.2735042735042735e-05,
      "loss": 0.8985,
      "step": 1620
    },
    {
      "epoch": 13.01,
      "learning_rate": 4.2655903767014884e-05,
      "loss": 0.6637,
      "step": 1630
    },
    {
      "epoch": 13.02,
      "learning_rate": 4.2576764798987026e-05,
      "loss": 0.9194,
      "step": 1640
    },
    {
      "epoch": 13.02,
      "learning_rate": 4.249762583095916e-05,
      "loss": 1.0481,
      "step": 1650
    },
    {
      "epoch": 13.02,
      "eval_accuracy": 0.6129032258064516,
      "eval_loss": 1.2836726903915405,
      "eval_runtime": 266.9839,
      "eval_samples_per_second": 0.813,
      "eval_steps_per_second": 0.206,
      "step": 1652
    },
    {
      "epoch": 14.0,
      "learning_rate": 4.241848686293131e-05,
      "loss": 0.8832,
      "step": 1660
    },
    {
      "epoch": 14.0,
      "learning_rate": 4.233934789490345e-05,
      "loss": 0.5931,
      "step": 1670
    },
    {
      "epoch": 14.0,
      "learning_rate": 4.2260208926875595e-05,
      "loss": 0.7721,
      "step": 1680
    },
    {
      "epoch": 14.01,
      "learning_rate": 4.2181069958847744e-05,
      "loss": 0.8753,
      "step": 1690
    },
    {
      "epoch": 14.01,
      "learning_rate": 4.210193099081988e-05,
      "loss": 0.9211,
      "step": 1700
    },
    {
      "epoch": 14.01,
      "learning_rate": 4.202279202279202e-05,
      "loss": 0.8866,
      "step": 1710
    },
    {
      "epoch": 14.01,
      "learning_rate": 4.194365305476417e-05,
      "loss": 0.9061,
      "step": 1720
    },
    {
      "epoch": 14.01,
      "learning_rate": 4.186451408673631e-05,
      "loss": 0.8832,
      "step": 1730
    },
    {
      "epoch": 14.01,
      "learning_rate": 4.1785375118708455e-05,
      "loss": 0.6224,
      "step": 1740
    },
    {
      "epoch": 14.01,
      "learning_rate": 4.17062361506806e-05,
      "loss": 0.752,
      "step": 1750
    },
    {
      "epoch": 14.02,
      "learning_rate": 4.162709718265274e-05,
      "loss": 1.1106,
      "step": 1760
    },
    {
      "epoch": 14.02,
      "learning_rate": 4.154795821462488e-05,
      "loss": 0.7895,
      "step": 1770
    },
    {
      "epoch": 14.02,
      "eval_accuracy": 0.7373271889400922,
      "eval_loss": 0.7213783264160156,
      "eval_runtime": 302.9001,
      "eval_samples_per_second": 0.716,
      "eval_steps_per_second": 0.182,
      "step": 1770
    },
    {
      "epoch": 15.0,
      "learning_rate": 4.1468819246597024e-05,
      "loss": 0.5983,
      "step": 1780
    },
    {
      "epoch": 15.0,
      "learning_rate": 4.138968027856917e-05,
      "loss": 0.7442,
      "step": 1790
    },
    {
      "epoch": 15.0,
      "learning_rate": 4.131054131054131e-05,
      "loss": 0.8338,
      "step": 1800
    },
    {
      "epoch": 15.01,
      "learning_rate": 4.123140234251345e-05,
      "loss": 1.0226,
      "step": 1810
    },
    {
      "epoch": 15.01,
      "learning_rate": 4.11522633744856e-05,
      "loss": 0.8336,
      "step": 1820
    },
    {
      "epoch": 15.01,
      "learning_rate": 4.107312440645774e-05,
      "loss": 0.6392,
      "step": 1830
    },
    {
      "epoch": 15.01,
      "learning_rate": 4.0993985438429884e-05,
      "loss": 0.8357,
      "step": 1840
    },
    {
      "epoch": 15.01,
      "learning_rate": 4.091484647040203e-05,
      "loss": 0.9604,
      "step": 1850
    },
    {
      "epoch": 15.01,
      "learning_rate": 4.083570750237417e-05,
      "loss": 0.7828,
      "step": 1860
    },
    {
      "epoch": 15.01,
      "learning_rate": 4.075656853434631e-05,
      "loss": 0.8063,
      "step": 1870
    },
    {
      "epoch": 15.02,
      "learning_rate": 4.067742956631846e-05,
      "loss": 0.9859,
      "step": 1880
    },
    {
      "epoch": 15.02,
      "eval_accuracy": 0.6866359447004609,
      "eval_loss": 0.8335953950881958,
      "eval_runtime": 299.0538,
      "eval_samples_per_second": 0.726,
      "eval_steps_per_second": 0.184,
      "step": 1888
    },
    {
      "epoch": 16.0,
      "learning_rate": 4.05982905982906e-05,
      "loss": 0.672,
      "step": 1890
    },
    {
      "epoch": 16.0,
      "learning_rate": 4.0519151630262745e-05,
      "loss": 0.8109,
      "step": 1900
    },
    {
      "epoch": 16.0,
      "learning_rate": 4.044001266223489e-05,
      "loss": 0.6525,
      "step": 1910
    },
    {
      "epoch": 16.0,
      "learning_rate": 4.036087369420703e-05,
      "loss": 0.7089,
      "step": 1920
    },
    {
      "epoch": 16.01,
      "learning_rate": 4.028173472617917e-05,
      "loss": 1.0346,
      "step": 1930
    },
    {
      "epoch": 16.01,
      "learning_rate": 4.020259575815132e-05,
      "loss": 1.1721,
      "step": 1940
    },
    {
      "epoch": 16.01,
      "learning_rate": 4.012345679012346e-05,
      "loss": 0.6268,
      "step": 1950
    },
    {
      "epoch": 16.01,
      "learning_rate": 4.00443178220956e-05,
      "loss": 0.8538,
      "step": 1960
    },
    {
      "epoch": 16.01,
      "learning_rate": 3.996517885406775e-05,
      "loss": 1.0732,
      "step": 1970
    },
    {
      "epoch": 16.01,
      "learning_rate": 3.988603988603989e-05,
      "loss": 0.8913,
      "step": 1980
    },
    {
      "epoch": 16.01,
      "learning_rate": 3.980690091801203e-05,
      "loss": 0.6379,
      "step": 1990
    },
    {
      "epoch": 16.02,
      "learning_rate": 3.9727761949984174e-05,
      "loss": 0.6517,
      "step": 2000
    },
    {
      "epoch": 16.02,
      "eval_accuracy": 0.6405529953917051,
      "eval_loss": 0.8792047500610352,
      "eval_runtime": 289.7798,
      "eval_samples_per_second": 0.749,
      "eval_steps_per_second": 0.19,
      "step": 2006
    },
    {
      "epoch": 17.0,
      "learning_rate": 3.9648622981956316e-05,
      "loss": 0.5995,
      "step": 2010
    },
    {
      "epoch": 17.0,
      "learning_rate": 3.956948401392846e-05,
      "loss": 1.0005,
      "step": 2020
    },
    {
      "epoch": 17.0,
      "learning_rate": 3.94903450459006e-05,
      "loss": 0.7818,
      "step": 2030
    },
    {
      "epoch": 17.0,
      "learning_rate": 3.941120607787275e-05,
      "loss": 0.7927,
      "step": 2040
    },
    {
      "epoch": 17.01,
      "learning_rate": 3.933206710984489e-05,
      "loss": 0.751,
      "step": 2050
    },
    {
      "epoch": 17.01,
      "learning_rate": 3.925292814181703e-05,
      "loss": 1.001,
      "step": 2060
    },
    {
      "epoch": 17.01,
      "learning_rate": 3.9173789173789176e-05,
      "loss": 0.8409,
      "step": 2070
    },
    {
      "epoch": 17.01,
      "learning_rate": 3.909465020576132e-05,
      "loss": 0.6746,
      "step": 2080
    },
    {
      "epoch": 17.01,
      "learning_rate": 3.901551123773346e-05,
      "loss": 0.6879,
      "step": 2090
    },
    {
      "epoch": 17.01,
      "learning_rate": 3.893637226970561e-05,
      "loss": 0.6906,
      "step": 2100
    },
    {
      "epoch": 17.01,
      "learning_rate": 3.8857233301677745e-05,
      "loss": 0.9602,
      "step": 2110
    },
    {
      "epoch": 17.02,
      "learning_rate": 3.877809433364989e-05,
      "loss": 0.7542,
      "step": 2120
    },
    {
      "epoch": 17.02,
      "eval_accuracy": 0.631336405529954,
      "eval_loss": 1.075119137763977,
      "eval_runtime": 259.3934,
      "eval_samples_per_second": 0.837,
      "eval_steps_per_second": 0.212,
      "step": 2124
    }
  ],
  "logging_steps": 10,
  "max_steps": 7020,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "total_flos": 1.051955870149804e+19,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}