{
  "best_global_step": 876,
  "best_metric": 0.9277850539806721,
  "best_model_checkpoint": "./saved_best/sst2_BERT-20000/full_text/checkpoint-876",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1314,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0228310502283105,
      "grad_norm": 127786.96875,
      "learning_rate": 1.9863013698630137e-05,
      "loss": 0.7128,
      "step": 10
    },
    {
      "epoch": 0.045662100456621,
      "grad_norm": 288305.125,
      "learning_rate": 1.971080669710807e-05,
      "loss": 0.6404,
      "step": 20
    },
    {
      "epoch": 0.0684931506849315,
      "grad_norm": 372462.9375,
      "learning_rate": 1.9558599695585997e-05,
      "loss": 0.5327,
      "step": 30
    },
    {
      "epoch": 0.091324200913242,
      "grad_norm": 602445.375,
      "learning_rate": 1.940639269406393e-05,
      "loss": 0.432,
      "step": 40
    },
    {
      "epoch": 0.1141552511415525,
      "grad_norm": 358026.8125,
      "learning_rate": 1.9254185692541858e-05,
      "loss": 0.3758,
      "step": 50
    },
    {
      "epoch": 0.136986301369863,
      "grad_norm": 402071.21875,
      "learning_rate": 1.910197869101979e-05,
      "loss": 0.3234,
      "step": 60
    },
    {
      "epoch": 0.1598173515981735,
      "grad_norm": 352748.53125,
      "learning_rate": 1.8949771689497718e-05,
      "loss": 0.3151,
      "step": 70
    },
    {
      "epoch": 0.182648401826484,
      "grad_norm": 905835.5625,
      "learning_rate": 1.879756468797565e-05,
      "loss": 0.3166,
      "step": 80
    },
    {
      "epoch": 0.2054794520547945,
      "grad_norm": 466547.9375,
      "learning_rate": 1.8645357686453578e-05,
      "loss": 0.3419,
      "step": 90
    },
    {
      "epoch": 0.228310502283105,
      "grad_norm": 423154.84375,
      "learning_rate": 1.849315068493151e-05,
      "loss": 0.3481,
      "step": 100
    },
    {
      "epoch": 0.2511415525114155,
      "grad_norm": 297082.96875,
      "learning_rate": 1.8340943683409438e-05,
      "loss": 0.3115,
      "step": 110
    },
    {
      "epoch": 0.273972602739726,
      "grad_norm": 369912.21875,
      "learning_rate": 1.818873668188737e-05,
      "loss": 0.316,
      "step": 120
    },
    {
      "epoch": 0.2968036529680365,
      "grad_norm": 197489.21875,
      "learning_rate": 1.80365296803653e-05,
      "loss": 0.295,
      "step": 130
    },
    {
      "epoch": 0.319634703196347,
      "grad_norm": 557747.25,
      "learning_rate": 1.788432267884323e-05,
      "loss": 0.2646,
      "step": 140
    },
    {
      "epoch": 0.3424657534246575,
      "grad_norm": 1081537.125,
      "learning_rate": 1.773211567732116e-05,
      "loss": 0.2154,
      "step": 150
    },
    {
      "epoch": 0.365296803652968,
      "grad_norm": 468382.625,
      "learning_rate": 1.757990867579909e-05,
      "loss": 0.3291,
      "step": 160
    },
    {
      "epoch": 0.3881278538812785,
      "grad_norm": 1200675.625,
      "learning_rate": 1.742770167427702e-05,
      "loss": 0.3015,
      "step": 170
    },
    {
      "epoch": 0.410958904109589,
      "grad_norm": 290634.03125,
      "learning_rate": 1.727549467275495e-05,
      "loss": 0.2645,
      "step": 180
    },
    {
      "epoch": 0.4337899543378995,
      "grad_norm": 785782.75,
      "learning_rate": 1.712328767123288e-05,
      "loss": 0.3038,
      "step": 190
    },
    {
      "epoch": 0.45662100456621,
      "grad_norm": 454525.84375,
      "learning_rate": 1.6971080669710807e-05,
      "loss": 0.2706,
      "step": 200
    },
    {
      "epoch": 0.4794520547945205,
      "grad_norm": 366387.75,
      "learning_rate": 1.681887366818874e-05,
      "loss": 0.2778,
      "step": 210
    },
    {
      "epoch": 0.502283105022831,
      "grad_norm": 213485.28125,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.2431,
      "step": 220
    },
    {
      "epoch": 0.5251141552511416,
      "grad_norm": 434280.5625,
      "learning_rate": 1.65144596651446e-05,
      "loss": 0.2712,
      "step": 230
    },
    {
      "epoch": 0.547945205479452,
      "grad_norm": 444368.0625,
      "learning_rate": 1.6362252663622528e-05,
      "loss": 0.2257,
      "step": 240
    },
    {
      "epoch": 0.5707762557077626,
      "grad_norm": 325988.9375,
      "learning_rate": 1.6210045662100456e-05,
      "loss": 0.2046,
      "step": 250
    },
    {
      "epoch": 0.593607305936073,
      "grad_norm": 376345.3125,
      "learning_rate": 1.6057838660578388e-05,
      "loss": 0.2685,
      "step": 260
    },
    {
      "epoch": 0.6164383561643836,
      "grad_norm": 596176.125,
      "learning_rate": 1.5905631659056316e-05,
      "loss": 0.2729,
      "step": 270
    },
    {
      "epoch": 0.639269406392694,
      "grad_norm": 650678.25,
      "learning_rate": 1.5753424657534248e-05,
      "loss": 0.2352,
      "step": 280
    },
    {
      "epoch": 0.6621004566210046,
      "grad_norm": 688517.5,
      "learning_rate": 1.5601217656012176e-05,
      "loss": 0.2395,
      "step": 290
    },
    {
      "epoch": 0.684931506849315,
      "grad_norm": 550269.5625,
      "learning_rate": 1.5449010654490108e-05,
      "loss": 0.2338,
      "step": 300
    },
    {
      "epoch": 0.7077625570776256,
      "grad_norm": 382038.0625,
      "learning_rate": 1.5296803652968037e-05,
      "loss": 0.2819,
      "step": 310
    },
    {
      "epoch": 0.730593607305936,
      "grad_norm": 413848.71875,
      "learning_rate": 1.5144596651445968e-05,
      "loss": 0.182,
      "step": 320
    },
    {
      "epoch": 0.7534246575342466,
      "grad_norm": 833068.375,
      "learning_rate": 1.4992389649923897e-05,
      "loss": 0.237,
      "step": 330
    },
    {
      "epoch": 0.776255707762557,
      "grad_norm": 249349.609375,
      "learning_rate": 1.4840182648401829e-05,
      "loss": 0.2295,
      "step": 340
    },
    {
      "epoch": 0.7990867579908676,
      "grad_norm": 195666.703125,
      "learning_rate": 1.4687975646879757e-05,
      "loss": 0.1964,
      "step": 350
    },
    {
      "epoch": 0.821917808219178,
      "grad_norm": 526547.625,
      "learning_rate": 1.4535768645357689e-05,
      "loss": 0.3156,
      "step": 360
    },
    {
      "epoch": 0.8447488584474886,
      "grad_norm": 733883.0,
      "learning_rate": 1.4383561643835617e-05,
      "loss": 0.2027,
      "step": 370
    },
    {
      "epoch": 0.867579908675799,
      "grad_norm": 299320.78125,
      "learning_rate": 1.4231354642313549e-05,
      "loss": 0.2713,
      "step": 380
    },
    {
      "epoch": 0.8904109589041096,
      "grad_norm": 440281.78125,
      "learning_rate": 1.4079147640791477e-05,
      "loss": 0.2047,
      "step": 390
    },
    {
      "epoch": 0.91324200913242,
      "grad_norm": 462590.125,
      "learning_rate": 1.3926940639269409e-05,
      "loss": 0.2395,
      "step": 400
    },
    {
      "epoch": 0.9360730593607306,
      "grad_norm": 1140073.75,
      "learning_rate": 1.3774733637747338e-05,
      "loss": 0.216,
      "step": 410
    },
    {
      "epoch": 0.958904109589041,
      "grad_norm": 197822.625,
      "learning_rate": 1.3622526636225268e-05,
      "loss": 0.2449,
      "step": 420
    },
    {
      "epoch": 0.9817351598173516,
      "grad_norm": 638955.5625,
      "learning_rate": 1.3470319634703198e-05,
      "loss": 0.253,
      "step": 430
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9223333333333333,
      "eval_f1_macro": 0.9212113479103987,
      "eval_f1_weighted": 0.9221891676085987,
      "eval_loss": 0.2171599268913269,
      "eval_runtime": 14.7894,
      "eval_samples_per_second": 405.695,
      "eval_steps_per_second": 12.712,
      "step": 438
    },
    {
      "epoch": 1.004566210045662,
      "grad_norm": 654569.875,
      "learning_rate": 1.3318112633181128e-05,
      "loss": 0.18,
      "step": 440
    },
    {
      "epoch": 1.0273972602739727,
      "grad_norm": 182483.90625,
      "learning_rate": 1.3165905631659058e-05,
      "loss": 0.1107,
      "step": 450
    },
    {
      "epoch": 1.0502283105022832,
      "grad_norm": 185298.140625,
      "learning_rate": 1.3013698630136988e-05,
      "loss": 0.1458,
      "step": 460
    },
    {
      "epoch": 1.0730593607305936,
      "grad_norm": 21770.05078125,
      "learning_rate": 1.2861491628614916e-05,
      "loss": 0.1592,
      "step": 470
    },
    {
      "epoch": 1.095890410958904,
      "grad_norm": 851453.125,
      "learning_rate": 1.2709284627092848e-05,
      "loss": 0.1383,
      "step": 480
    },
    {
      "epoch": 1.1187214611872145,
      "grad_norm": 348289.34375,
      "learning_rate": 1.2557077625570777e-05,
      "loss": 0.1205,
      "step": 490
    },
    {
      "epoch": 1.1415525114155252,
      "grad_norm": 510975.78125,
      "learning_rate": 1.2404870624048708e-05,
      "loss": 0.1321,
      "step": 500
    },
    {
      "epoch": 1.1643835616438356,
      "grad_norm": 1570861.375,
      "learning_rate": 1.2252663622526637e-05,
      "loss": 0.221,
      "step": 510
    },
    {
      "epoch": 1.187214611872146,
      "grad_norm": 948502.5625,
      "learning_rate": 1.2100456621004569e-05,
      "loss": 0.1814,
      "step": 520
    },
    {
      "epoch": 1.2100456621004567,
      "grad_norm": 597450.25,
      "learning_rate": 1.1948249619482497e-05,
      "loss": 0.0911,
      "step": 530
    },
    {
      "epoch": 1.2328767123287672,
      "grad_norm": 397320.8125,
      "learning_rate": 1.1796042617960429e-05,
      "loss": 0.1649,
      "step": 540
    },
    {
      "epoch": 1.2557077625570776,
      "grad_norm": 513346.84375,
      "learning_rate": 1.1643835616438357e-05,
      "loss": 0.1953,
      "step": 550
    },
    {
      "epoch": 1.278538812785388,
      "grad_norm": 504690.0625,
      "learning_rate": 1.1491628614916289e-05,
      "loss": 0.14,
      "step": 560
    },
    {
      "epoch": 1.3013698630136985,
      "grad_norm": 1110943.625,
      "learning_rate": 1.1339421613394217e-05,
      "loss": 0.1191,
      "step": 570
    },
    {
      "epoch": 1.3242009132420092,
      "grad_norm": 200145.484375,
      "learning_rate": 1.1187214611872147e-05,
      "loss": 0.1339,
      "step": 580
    },
    {
      "epoch": 1.3470319634703196,
      "grad_norm": 221766.21875,
      "learning_rate": 1.1035007610350078e-05,
      "loss": 0.1427,
      "step": 590
    },
    {
      "epoch": 1.36986301369863,
      "grad_norm": 881168.3125,
      "learning_rate": 1.0882800608828008e-05,
      "loss": 0.1089,
      "step": 600
    },
    {
      "epoch": 1.3926940639269407,
      "grad_norm": 854495.5625,
      "learning_rate": 1.0730593607305938e-05,
      "loss": 0.1368,
      "step": 610
    },
    {
      "epoch": 1.4155251141552512,
      "grad_norm": 115748.078125,
      "learning_rate": 1.0578386605783868e-05,
      "loss": 0.15,
      "step": 620
    },
    {
      "epoch": 1.4383561643835616,
      "grad_norm": 334710.25,
      "learning_rate": 1.0426179604261796e-05,
      "loss": 0.2423,
      "step": 630
    },
    {
      "epoch": 1.461187214611872,
      "grad_norm": 972609.8125,
      "learning_rate": 1.0273972602739728e-05,
      "loss": 0.093,
      "step": 640
    },
    {
      "epoch": 1.4840182648401825,
      "grad_norm": 519533.71875,
      "learning_rate": 1.0121765601217656e-05,
      "loss": 0.217,
      "step": 650
    },
    {
      "epoch": 1.5068493150684932,
      "grad_norm": 156004.296875,
      "learning_rate": 9.969558599695586e-06,
      "loss": 0.1424,
      "step": 660
    },
    {
      "epoch": 1.5296803652968036,
      "grad_norm": 398576.53125,
      "learning_rate": 9.817351598173517e-06,
      "loss": 0.1404,
      "step": 670
    },
    {
      "epoch": 1.5525114155251143,
      "grad_norm": 648208.25,
      "learning_rate": 9.665144596651447e-06,
      "loss": 0.1277,
      "step": 680
    },
    {
      "epoch": 1.5753424657534247,
      "grad_norm": 71873.3046875,
      "learning_rate": 9.512937595129377e-06,
      "loss": 0.1247,
      "step": 690
    },
    {
      "epoch": 1.5981735159817352,
      "grad_norm": 349757.6875,
      "learning_rate": 9.360730593607307e-06,
      "loss": 0.1786,
      "step": 700
    },
    {
      "epoch": 1.6210045662100456,
      "grad_norm": 395071.59375,
      "learning_rate": 9.208523592085237e-06,
      "loss": 0.1687,
      "step": 710
    },
    {
      "epoch": 1.643835616438356,
      "grad_norm": 689678.75,
      "learning_rate": 9.056316590563167e-06,
      "loss": 0.1239,
      "step": 720
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 609217.75,
      "learning_rate": 8.904109589041097e-06,
      "loss": 0.1193,
      "step": 730
    },
    {
      "epoch": 1.6894977168949772,
      "grad_norm": 429054.15625,
      "learning_rate": 8.751902587519027e-06,
      "loss": 0.0972,
      "step": 740
    },
    {
      "epoch": 1.7123287671232876,
      "grad_norm": 658631.0,
      "learning_rate": 8.599695585996957e-06,
      "loss": 0.2026,
      "step": 750
    },
    {
      "epoch": 1.7351598173515983,
      "grad_norm": 696978.75,
      "learning_rate": 8.447488584474887e-06,
      "loss": 0.2093,
      "step": 760
    },
    {
      "epoch": 1.7579908675799087,
      "grad_norm": 1273698.5,
      "learning_rate": 8.295281582952816e-06,
      "loss": 0.131,
      "step": 770
    },
    {
      "epoch": 1.7808219178082192,
      "grad_norm": 381059.125,
      "learning_rate": 8.143074581430746e-06,
      "loss": 0.0753,
      "step": 780
    },
    {
      "epoch": 1.8036529680365296,
      "grad_norm": 760526.8125,
      "learning_rate": 7.990867579908676e-06,
      "loss": 0.1004,
      "step": 790
    },
    {
      "epoch": 1.82648401826484,
      "grad_norm": 197580.625,
      "learning_rate": 7.838660578386606e-06,
      "loss": 0.1652,
      "step": 800
    },
    {
      "epoch": 1.8493150684931505,
      "grad_norm": 1663549.75,
      "learning_rate": 7.686453576864536e-06,
      "loss": 0.1465,
      "step": 810
    },
    {
      "epoch": 1.8721461187214612,
      "grad_norm": 517745.75,
      "learning_rate": 7.534246575342466e-06,
      "loss": 0.1703,
      "step": 820
    },
    {
      "epoch": 1.8949771689497716,
      "grad_norm": 680767.5625,
      "learning_rate": 7.382039573820396e-06,
      "loss": 0.1623,
      "step": 830
    },
    {
      "epoch": 1.9178082191780823,
      "grad_norm": 697195.1875,
      "learning_rate": 7.2298325722983265e-06,
      "loss": 0.1733,
      "step": 840
    },
    {
      "epoch": 1.9406392694063928,
      "grad_norm": 263220.8125,
      "learning_rate": 7.077625570776257e-06,
      "loss": 0.116,
      "step": 850
    },
    {
      "epoch": 1.9634703196347032,
      "grad_norm": 336279.6875,
      "learning_rate": 6.925418569254187e-06,
      "loss": 0.1565,
      "step": 860
    },
    {
      "epoch": 1.9863013698630136,
      "grad_norm": 230299.015625,
      "learning_rate": 6.773211567732117e-06,
      "loss": 0.1184,
      "step": 870
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9285,
      "eval_f1_macro": 0.9277850539806721,
      "eval_f1_weighted": 0.92853233424208,
      "eval_loss": 0.2250971645116806,
      "eval_runtime": 15.009,
      "eval_samples_per_second": 399.76,
      "eval_steps_per_second": 12.526,
      "step": 876
    },
    {
      "epoch": 2.009132420091324,
      "grad_norm": 105916.703125,
      "learning_rate": 6.621004566210046e-06,
      "loss": 0.1208,
      "step": 880
    },
    {
      "epoch": 2.0319634703196345,
      "grad_norm": 231579.703125,
      "learning_rate": 6.468797564687976e-06,
      "loss": 0.0994,
      "step": 890
    },
    {
      "epoch": 2.0547945205479454,
      "grad_norm": 226497.375,
      "learning_rate": 6.316590563165906e-06,
      "loss": 0.0713,
      "step": 900
    },
    {
      "epoch": 2.077625570776256,
      "grad_norm": 275743.15625,
      "learning_rate": 6.164383561643836e-06,
      "loss": 0.0873,
      "step": 910
    },
    {
      "epoch": 2.1004566210045663,
      "grad_norm": 28719.689453125,
      "learning_rate": 6.012176560121766e-06,
      "loss": 0.1131,
      "step": 920
    },
    {
      "epoch": 2.1232876712328768,
      "grad_norm": 947971.3125,
      "learning_rate": 5.8599695585996965e-06,
      "loss": 0.0514,
      "step": 930
    },
    {
      "epoch": 2.146118721461187,
      "grad_norm": 768273.125,
      "learning_rate": 5.7077625570776266e-06,
      "loss": 0.0813,
      "step": 940
    },
    {
      "epoch": 2.1689497716894977,
      "grad_norm": 202898.15625,
      "learning_rate": 5.555555555555557e-06,
      "loss": 0.0813,
      "step": 950
    },
    {
      "epoch": 2.191780821917808,
      "grad_norm": 481656.03125,
      "learning_rate": 5.403348554033486e-06,
      "loss": 0.1004,
      "step": 960
    },
    {
      "epoch": 2.2146118721461185,
      "grad_norm": 250803.953125,
      "learning_rate": 5.251141552511416e-06,
      "loss": 0.1432,
      "step": 970
    },
    {
      "epoch": 2.237442922374429,
      "grad_norm": 12995.201171875,
      "learning_rate": 5.098934550989346e-06,
      "loss": 0.0464,
      "step": 980
    },
    {
      "epoch": 2.26027397260274,
      "grad_norm": 902957.0625,
      "learning_rate": 4.946727549467275e-06,
      "loss": 0.137,
      "step": 990
    },
    {
      "epoch": 2.2831050228310503,
      "grad_norm": 534876.0,
      "learning_rate": 4.7945205479452054e-06,
      "loss": 0.0922,
      "step": 1000
    },
    {
      "epoch": 2.3059360730593608,
      "grad_norm": 178206.484375,
      "learning_rate": 4.6423135464231355e-06,
      "loss": 0.0705,
      "step": 1010
    },
    {
      "epoch": 2.328767123287671,
      "grad_norm": 40234.16796875,
      "learning_rate": 4.490106544901066e-06,
      "loss": 0.0372,
      "step": 1020
    },
    {
      "epoch": 2.3515981735159817,
      "grad_norm": 251605.671875,
      "learning_rate": 4.337899543378996e-06,
      "loss": 0.0483,
      "step": 1030
    },
    {
      "epoch": 2.374429223744292,
      "grad_norm": 1325790.375,
      "learning_rate": 4.185692541856926e-06,
      "loss": 0.0806,
      "step": 1040
    },
    {
      "epoch": 2.3972602739726026,
      "grad_norm": 793383.375,
      "learning_rate": 4.033485540334856e-06,
      "loss": 0.123,
      "step": 1050
    },
    {
      "epoch": 2.4200913242009134,
      "grad_norm": 626307.3125,
      "learning_rate": 3.881278538812785e-06,
      "loss": 0.117,
      "step": 1060
    },
    {
      "epoch": 2.442922374429224,
      "grad_norm": 390102.96875,
      "learning_rate": 3.7290715372907157e-06,
      "loss": 0.1038,
      "step": 1070
    },
    {
      "epoch": 2.4657534246575343,
      "grad_norm": 965051.0625,
      "learning_rate": 3.5768645357686453e-06,
      "loss": 0.0869,
      "step": 1080
    },
    {
      "epoch": 2.4885844748858448,
      "grad_norm": 81258.328125,
      "learning_rate": 3.4246575342465754e-06,
      "loss": 0.0941,
      "step": 1090
    },
    {
      "epoch": 2.5114155251141552,
      "grad_norm": 707149.125,
      "learning_rate": 3.2724505327245055e-06,
      "loss": 0.0825,
      "step": 1100
    },
    {
      "epoch": 2.5342465753424657,
      "grad_norm": 10573.8984375,
      "learning_rate": 3.120243531202435e-06,
      "loss": 0.0806,
      "step": 1110
    },
    {
      "epoch": 2.557077625570776,
      "grad_norm": 2018027.5,
      "learning_rate": 2.9680365296803653e-06,
      "loss": 0.1719,
      "step": 1120
    },
    {
      "epoch": 2.5799086757990866,
      "grad_norm": 706195.4375,
      "learning_rate": 2.8158295281582954e-06,
      "loss": 0.0954,
      "step": 1130
    },
    {
      "epoch": 2.602739726027397,
      "grad_norm": 230678.828125,
      "learning_rate": 2.6636225266362255e-06,
      "loss": 0.103,
      "step": 1140
    },
    {
      "epoch": 2.625570776255708,
      "grad_norm": 455807.78125,
      "learning_rate": 2.511415525114155e-06,
      "loss": 0.0965,
      "step": 1150
    },
    {
      "epoch": 2.6484018264840183,
      "grad_norm": 38607.32421875,
      "learning_rate": 2.3592085235920852e-06,
      "loss": 0.0381,
      "step": 1160
    },
    {
      "epoch": 2.671232876712329,
      "grad_norm": 449129.09375,
      "learning_rate": 2.2070015220700153e-06,
      "loss": 0.0836,
      "step": 1170
    },
    {
      "epoch": 2.6940639269406392,
      "grad_norm": 334416.4375,
      "learning_rate": 2.0547945205479454e-06,
      "loss": 0.0511,
      "step": 1180
    },
    {
      "epoch": 2.7168949771689497,
      "grad_norm": 490780.5625,
      "learning_rate": 1.9025875190258753e-06,
      "loss": 0.1427,
      "step": 1190
    },
    {
      "epoch": 2.73972602739726,
      "grad_norm": 6038.24072265625,
      "learning_rate": 1.7503805175038052e-06,
      "loss": 0.1099,
      "step": 1200
    },
    {
      "epoch": 2.762557077625571,
      "grad_norm": 202150.234375,
      "learning_rate": 1.5981735159817353e-06,
      "loss": 0.119,
      "step": 1210
    },
    {
      "epoch": 2.7853881278538815,
      "grad_norm": 232674.578125,
      "learning_rate": 1.4459665144596652e-06,
      "loss": 0.181,
      "step": 1220
    },
    {
      "epoch": 2.808219178082192,
      "grad_norm": 1792436.625,
      "learning_rate": 1.2937595129375953e-06,
      "loss": 0.0718,
      "step": 1230
    },
    {
      "epoch": 2.8310502283105023,
      "grad_norm": 2906556.0,
      "learning_rate": 1.1415525114155251e-06,
      "loss": 0.097,
      "step": 1240
    },
    {
      "epoch": 2.853881278538813,
      "grad_norm": 82039.2734375,
      "learning_rate": 9.89345509893455e-07,
      "loss": 0.1275,
      "step": 1250
    },
    {
      "epoch": 2.8767123287671232,
      "grad_norm": 271356.25,
      "learning_rate": 8.371385083713851e-07,
      "loss": 0.1401,
      "step": 1260
    },
    {
      "epoch": 2.8995433789954337,
      "grad_norm": 9588.64453125,
      "learning_rate": 6.849315068493151e-07,
      "loss": 0.1627,
      "step": 1270
    },
    {
      "epoch": 2.922374429223744,
      "grad_norm": 1104557.125,
      "learning_rate": 5.327245053272451e-07,
      "loss": 0.0942,
      "step": 1280
    },
    {
      "epoch": 2.9452054794520546,
      "grad_norm": 31101.583984375,
      "learning_rate": 3.8051750380517503e-07,
      "loss": 0.0714,
      "step": 1290
    },
    {
      "epoch": 2.968036529680365,
      "grad_norm": 740889.8125,
      "learning_rate": 2.2831050228310502e-07,
      "loss": 0.1083,
      "step": 1300
    },
    {
      "epoch": 2.990867579908676,
      "grad_norm": 7040.435546875,
      "learning_rate": 7.6103500761035e-08,
      "loss": 0.1593,
      "step": 1310
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9261666666666667,
      "eval_f1_macro": 0.9252761556296953,
      "eval_f1_weighted": 0.9261245203427795,
      "eval_loss": 0.37234973907470703,
      "eval_runtime": 15.0862,
      "eval_samples_per_second": 397.714,
      "eval_steps_per_second": 12.462,
      "step": 1314
    },
    {
      "epoch": 3.0,
      "step": 1314,
      "total_flos": 1537621007523840.0,
      "train_loss": 0.18048278951118707,
      "train_runtime": 317.0714,
      "train_samples_per_second": 132.462,
      "train_steps_per_second": 4.144
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9285,
      "eval_f1_macro": 0.9277850539806721,
      "eval_f1_weighted": 0.92853233424208,
      "eval_loss": 0.2250971645116806,
      "eval_runtime": 14.8809,
      "eval_samples_per_second": 403.201,
      "eval_steps_per_second": 12.634,
      "step": 1314
    }
  ],
  "logging_steps": 10,
  "max_steps": 1314,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1537621007523840.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}