{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9957679860592482,
  "eval_steps": 250,
  "global_step": 3500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0028450513887407092,
      "grad_norm": 0.30044543743133545,
      "learning_rate": 7.113007913221304e-08,
      "loss": 0.0216,
      "step": 10
    },
    {
      "epoch": 0.0056901027774814185,
      "grad_norm": 0.22410444915294647,
      "learning_rate": 1.4226015826442608e-07,
      "loss": 0.0204,
      "step": 20
    },
    {
      "epoch": 0.008535154166222128,
      "grad_norm": 0.29121559858322144,
      "learning_rate": 2.1339023739663913e-07,
      "loss": 0.0194,
      "step": 30
    },
    {
      "epoch": 0.011380205554962837,
      "grad_norm": 0.3065185248851776,
      "learning_rate": 2.8452031652885216e-07,
      "loss": 0.0195,
      "step": 40
    },
    {
      "epoch": 0.014225256943703546,
      "grad_norm": 0.26153531670570374,
      "learning_rate": 3.5565039566106516e-07,
      "loss": 0.0182,
      "step": 50
    },
    {
      "epoch": 0.017070308332444255,
      "grad_norm": 0.268179327249527,
      "learning_rate": 4.2678047479327826e-07,
      "loss": 0.0161,
      "step": 60
    },
    {
      "epoch": 0.019915359721184963,
      "grad_norm": 0.26602137088775635,
      "learning_rate": 4.979105539254913e-07,
      "loss": 0.015,
      "step": 70
    },
    {
      "epoch": 0.022760411109925674,
      "grad_norm": 0.20688457787036896,
      "learning_rate": 5.690406330577043e-07,
      "loss": 0.0153,
      "step": 80
    },
    {
      "epoch": 0.02560546249866638,
      "grad_norm": 0.19044898450374603,
      "learning_rate": 6.401707121899174e-07,
      "loss": 0.0137,
      "step": 90
    },
    {
      "epoch": 0.028450513887407092,
      "grad_norm": 0.22615332901477814,
      "learning_rate": 7.113007913221303e-07,
      "loss": 0.014,
      "step": 100
    },
    {
      "epoch": 0.0312955652761478,
      "grad_norm": 0.20191101729869843,
      "learning_rate": 7.824308704543435e-07,
      "loss": 0.0122,
      "step": 110
    },
    {
      "epoch": 0.03414061666488851,
      "grad_norm": 0.19718502461910248,
      "learning_rate": 8.535609495865565e-07,
      "loss": 0.0114,
      "step": 120
    },
    {
      "epoch": 0.03698566805362922,
      "grad_norm": 0.1824241578578949,
      "learning_rate": 9.246910287187695e-07,
      "loss": 0.0109,
      "step": 130
    },
    {
      "epoch": 0.039830719442369926,
      "grad_norm": 0.13791899383068085,
      "learning_rate": 9.958211078509825e-07,
      "loss": 0.0097,
      "step": 140
    },
    {
      "epoch": 0.04267577083111064,
      "grad_norm": 0.11571934819221497,
      "learning_rate": 1.0669511869831955e-06,
      "loss": 0.0085,
      "step": 150
    },
    {
      "epoch": 0.04552082221985135,
      "grad_norm": 0.13633102178573608,
      "learning_rate": 1.1380812661154086e-06,
      "loss": 0.0084,
      "step": 160
    },
    {
      "epoch": 0.048365873608592055,
      "grad_norm": 0.08016248047351837,
      "learning_rate": 1.2092113452476218e-06,
      "loss": 0.0083,
      "step": 170
    },
    {
      "epoch": 0.05121092499733276,
      "grad_norm": 0.10402435064315796,
      "learning_rate": 1.2803414243798347e-06,
      "loss": 0.0078,
      "step": 180
    },
    {
      "epoch": 0.05405597638607347,
      "grad_norm": 0.10400915145874023,
      "learning_rate": 1.3514715035120477e-06,
      "loss": 0.008,
      "step": 190
    },
    {
      "epoch": 0.056901027774814185,
      "grad_norm": 0.05126596987247467,
      "learning_rate": 1.4226015826442606e-06,
      "loss": 0.0073,
      "step": 200
    },
    {
      "epoch": 0.05974607916355489,
      "grad_norm": 0.09815330803394318,
      "learning_rate": 1.4937316617764738e-06,
      "loss": 0.0079,
      "step": 210
    },
    {
      "epoch": 0.0625911305522956,
      "grad_norm": 0.07512035965919495,
      "learning_rate": 1.564861740908687e-06,
      "loss": 0.0073,
      "step": 220
    },
    {
      "epoch": 0.06543618194103631,
      "grad_norm": 0.0874195247888565,
      "learning_rate": 1.6359918200409001e-06,
      "loss": 0.0079,
      "step": 230
    },
    {
      "epoch": 0.06828123332977702,
      "grad_norm": 0.05660032480955124,
      "learning_rate": 1.707121899173113e-06,
      "loss": 0.0068,
      "step": 240
    },
    {
      "epoch": 0.07112628471851773,
      "grad_norm": 0.06961371004581451,
      "learning_rate": 1.778251978305326e-06,
      "loss": 0.0068,
      "step": 250
    },
    {
      "epoch": 0.07112628471851773,
      "eval_loss": 0.03334415331482887,
      "eval_runtime": 9.3985,
      "eval_samples_per_second": 159.599,
      "eval_steps_per_second": 10.002,
      "eval_sts_dev_pearson_cosine": 0.8139279991578542,
      "eval_sts_dev_pearson_dot": 0.750640851965511,
      "eval_sts_dev_pearson_euclidean": 0.7813827425904325,
      "eval_sts_dev_pearson_manhattan": 0.7825586268743923,
      "eval_sts_dev_pearson_max": 0.8139279991578542,
      "eval_sts_dev_spearman_cosine": 0.8228542044736794,
      "eval_sts_dev_spearman_dot": 0.7341843393391922,
      "eval_sts_dev_spearman_euclidean": 0.7859707213660079,
      "eval_sts_dev_spearman_manhattan": 0.7886657735697056,
      "eval_sts_dev_spearman_max": 0.8228542044736794,
      "step": 250
    },
    {
      "epoch": 0.07397133610725844,
      "grad_norm": 0.05404730886220932,
      "learning_rate": 1.849382057437539e-06,
      "loss": 0.0073,
      "step": 260
    },
    {
      "epoch": 0.07681638749599914,
      "grad_norm": 0.07932556420564651,
      "learning_rate": 1.920512136569752e-06,
      "loss": 0.0077,
      "step": 270
    },
    {
      "epoch": 0.07966143888473985,
      "grad_norm": 0.055235493928194046,
      "learning_rate": 1.991642215701965e-06,
      "loss": 0.0067,
      "step": 280
    },
    {
      "epoch": 0.08250649027348056,
      "grad_norm": 0.06954500079154968,
      "learning_rate": 2.0627722948341784e-06,
      "loss": 0.007,
      "step": 290
    },
    {
      "epoch": 0.08535154166222128,
      "grad_norm": 0.08223138749599457,
      "learning_rate": 2.133902373966391e-06,
      "loss": 0.0065,
      "step": 300
    },
    {
      "epoch": 0.08819659305096199,
      "grad_norm": 0.06235595792531967,
      "learning_rate": 2.2050324530986043e-06,
      "loss": 0.0072,
      "step": 310
    },
    {
      "epoch": 0.0910416444397027,
      "grad_norm": 0.06472361832857132,
      "learning_rate": 2.2761625322308173e-06,
      "loss": 0.0068,
      "step": 320
    },
    {
      "epoch": 0.0938866958284434,
      "grad_norm": 0.06870505958795547,
      "learning_rate": 2.3472926113630302e-06,
      "loss": 0.0064,
      "step": 330
    },
    {
      "epoch": 0.09673174721718411,
      "grad_norm": 0.07072167843580246,
      "learning_rate": 2.4184226904952436e-06,
      "loss": 0.0074,
      "step": 340
    },
    {
      "epoch": 0.09957679860592482,
      "grad_norm": 0.065520741045475,
      "learning_rate": 2.489552769627456e-06,
      "loss": 0.0071,
      "step": 350
    },
    {
      "epoch": 0.10242184999466553,
      "grad_norm": 0.06320654600858688,
      "learning_rate": 2.5606828487596695e-06,
      "loss": 0.0065,
      "step": 360
    },
    {
      "epoch": 0.10526690138340623,
      "grad_norm": 0.08099081367254257,
      "learning_rate": 2.6318129278918824e-06,
      "loss": 0.0067,
      "step": 370
    },
    {
      "epoch": 0.10811195277214694,
      "grad_norm": 0.06201442331075668,
      "learning_rate": 2.7029430070240954e-06,
      "loss": 0.0063,
      "step": 380
    },
    {
      "epoch": 0.11095700416088766,
      "grad_norm": 0.06379993259906769,
      "learning_rate": 2.7740730861563087e-06,
      "loss": 0.0062,
      "step": 390
    },
    {
      "epoch": 0.11380205554962837,
      "grad_norm": 0.05820363759994507,
      "learning_rate": 2.8452031652885213e-06,
      "loss": 0.0068,
      "step": 400
    },
    {
      "epoch": 0.11664710693836908,
      "grad_norm": 0.05578601360321045,
      "learning_rate": 2.9163332444207346e-06,
      "loss": 0.0064,
      "step": 410
    },
    {
      "epoch": 0.11949215832710978,
      "grad_norm": 0.06488487124443054,
      "learning_rate": 2.9874633235529476e-06,
      "loss": 0.0064,
      "step": 420
    },
    {
      "epoch": 0.12233720971585049,
      "grad_norm": 0.06347406655550003,
      "learning_rate": 3.0585934026851605e-06,
      "loss": 0.0064,
      "step": 430
    },
    {
      "epoch": 0.1251822611045912,
      "grad_norm": 0.07820002734661102,
      "learning_rate": 3.129723481817374e-06,
      "loss": 0.0074,
      "step": 440
    },
    {
      "epoch": 0.1280273124933319,
      "grad_norm": 0.052174266427755356,
      "learning_rate": 3.200853560949587e-06,
      "loss": 0.0069,
      "step": 450
    },
    {
      "epoch": 0.13087236388207263,
      "grad_norm": 0.0655951127409935,
      "learning_rate": 3.2719836400818002e-06,
      "loss": 0.0065,
      "step": 460
    },
    {
      "epoch": 0.13371741527081332,
      "grad_norm": 0.07082219421863556,
      "learning_rate": 3.3431137192140127e-06,
      "loss": 0.0067,
      "step": 470
    },
    {
      "epoch": 0.13656246665955404,
      "grad_norm": 0.05722203105688095,
      "learning_rate": 3.414243798346226e-06,
      "loss": 0.0068,
      "step": 480
    },
    {
      "epoch": 0.13940751804829474,
      "grad_norm": 0.042512740939855576,
      "learning_rate": 3.485373877478439e-06,
      "loss": 0.0057,
      "step": 490
    },
    {
      "epoch": 0.14225256943703546,
      "grad_norm": 0.07777195423841476,
      "learning_rate": 3.556503956610652e-06,
      "loss": 0.0065,
      "step": 500
    },
    {
      "epoch": 0.14225256943703546,
      "eval_loss": 0.034268368035554886,
      "eval_runtime": 9.4571,
      "eval_samples_per_second": 158.611,
      "eval_steps_per_second": 9.94,
      "eval_sts_dev_pearson_cosine": 0.8181914244558982,
      "eval_sts_dev_pearson_dot": 0.7449626401674933,
      "eval_sts_dev_pearson_euclidean": 0.7912044446283607,
      "eval_sts_dev_pearson_manhattan": 0.7922858740750306,
      "eval_sts_dev_pearson_max": 0.8181914244558982,
      "eval_sts_dev_spearman_cosine": 0.828420839653431,
      "eval_sts_dev_spearman_dot": 0.7263741357918354,
      "eval_sts_dev_spearman_euclidean": 0.7977480260329146,
      "eval_sts_dev_spearman_manhattan": 0.800148774872662,
      "eval_sts_dev_spearman_max": 0.828420839653431,
      "step": 500
    },
    {
      "epoch": 0.14509762082577615,
      "grad_norm": 0.06219501420855522,
      "learning_rate": 3.6276340357428654e-06,
      "loss": 0.0069,
      "step": 510
    },
    {
      "epoch": 0.14794267221451687,
      "grad_norm": 0.06601779162883759,
      "learning_rate": 3.698764114875078e-06,
      "loss": 0.0068,
      "step": 520
    },
    {
      "epoch": 0.1507877236032576,
      "grad_norm": 0.06005557253956795,
      "learning_rate": 3.7698941940072913e-06,
      "loss": 0.0065,
      "step": 530
    },
    {
      "epoch": 0.1536327749919983,
      "grad_norm": 0.05748499929904938,
      "learning_rate": 3.841024273139504e-06,
      "loss": 0.0065,
      "step": 540
    },
    {
      "epoch": 0.156477826380739,
      "grad_norm": 0.06991992145776749,
      "learning_rate": 3.912154352271717e-06,
      "loss": 0.0063,
      "step": 550
    },
    {
      "epoch": 0.1593228777694797,
      "grad_norm": 0.04834827408194542,
      "learning_rate": 3.98328443140393e-06,
      "loss": 0.0058,
      "step": 560
    },
    {
      "epoch": 0.16216792915822043,
      "grad_norm": 0.05604851618409157,
      "learning_rate": 4.054414510536143e-06,
      "loss": 0.0064,
      "step": 570
    },
    {
      "epoch": 0.16501298054696112,
      "grad_norm": 0.05394286289811134,
      "learning_rate": 4.125544589668357e-06,
      "loss": 0.0062,
      "step": 580
    },
    {
      "epoch": 0.16785803193570184,
      "grad_norm": 0.0512845516204834,
      "learning_rate": 4.19667466880057e-06,
      "loss": 0.0061,
      "step": 590
    },
    {
      "epoch": 0.17070308332444256,
      "grad_norm": 0.0574568510055542,
      "learning_rate": 4.267804747932782e-06,
      "loss": 0.0062,
      "step": 600
    },
    {
      "epoch": 0.17354813471318326,
      "grad_norm": 0.06107944995164871,
      "learning_rate": 4.338934827064996e-06,
      "loss": 0.0057,
      "step": 610
    },
    {
      "epoch": 0.17639318610192398,
      "grad_norm": 0.06508038192987442,
      "learning_rate": 4.410064906197209e-06,
      "loss": 0.0066,
      "step": 620
    },
    {
      "epoch": 0.17923823749066467,
      "grad_norm": 0.0429425947368145,
      "learning_rate": 4.481194985329422e-06,
      "loss": 0.0061,
      "step": 630
    },
    {
      "epoch": 0.1820832888794054,
      "grad_norm": 0.07746722549200058,
      "learning_rate": 4.5523250644616345e-06,
      "loss": 0.0054,
      "step": 640
    },
    {
      "epoch": 0.18492834026814609,
      "grad_norm": 0.05604277178645134,
      "learning_rate": 4.6234551435938475e-06,
      "loss": 0.0066,
      "step": 650
    },
    {
      "epoch": 0.1877733916568868,
      "grad_norm": 0.04747707024216652,
      "learning_rate": 4.6945852227260604e-06,
      "loss": 0.0059,
      "step": 660
    },
    {
      "epoch": 0.1906184430456275,
      "grad_norm": 0.049124643206596375,
      "learning_rate": 4.765715301858273e-06,
      "loss": 0.0063,
      "step": 670
    },
    {
      "epoch": 0.19346349443436822,
      "grad_norm": 0.05432770773768425,
      "learning_rate": 4.836845380990487e-06,
      "loss": 0.0065,
      "step": 680
    },
    {
      "epoch": 0.19630854582310894,
      "grad_norm": 0.04070006310939789,
      "learning_rate": 4.9079754601227e-06,
      "loss": 0.0065,
      "step": 690
    },
    {
      "epoch": 0.19915359721184964,
      "grad_norm": 0.05693609267473221,
      "learning_rate": 4.979105539254912e-06,
      "loss": 0.0058,
      "step": 700
    },
    {
      "epoch": 0.20199864860059036,
      "grad_norm": 0.051310617476701736,
      "learning_rate": 5.050235618387126e-06,
      "loss": 0.006,
      "step": 710
    },
    {
      "epoch": 0.20484369998933105,
      "grad_norm": 0.0512520931661129,
      "learning_rate": 5.121365697519339e-06,
      "loss": 0.0062,
      "step": 720
    },
    {
      "epoch": 0.20768875137807177,
      "grad_norm": 0.06032096594572067,
      "learning_rate": 5.192495776651552e-06,
      "loss": 0.0058,
      "step": 730
    },
    {
      "epoch": 0.21053380276681247,
      "grad_norm": 0.05407226085662842,
      "learning_rate": 5.263625855783765e-06,
      "loss": 0.0058,
      "step": 740
    },
    {
      "epoch": 0.2133788541555532,
      "grad_norm": 0.04472426697611809,
      "learning_rate": 5.334755934915979e-06,
      "loss": 0.0056,
      "step": 750
    },
    {
      "epoch": 0.2133788541555532,
      "eval_loss": 0.035597361624240875,
      "eval_runtime": 9.4023,
      "eval_samples_per_second": 159.536,
      "eval_steps_per_second": 9.998,
      "eval_sts_dev_pearson_cosine": 0.8192166641007746,
      "eval_sts_dev_pearson_dot": 0.7403343789875012,
      "eval_sts_dev_pearson_euclidean": 0.7962870902346526,
      "eval_sts_dev_pearson_manhattan": 0.7970902993298804,
      "eval_sts_dev_pearson_max": 0.8192166641007746,
      "eval_sts_dev_spearman_cosine": 0.8301874075212713,
      "eval_sts_dev_spearman_dot": 0.7214281718521472,
      "eval_sts_dev_spearman_euclidean": 0.8028538594956929,
      "eval_sts_dev_spearman_manhattan": 0.805293771786166,
      "eval_sts_dev_spearman_max": 0.8301874075212713,
      "step": 750
    },
    {
      "epoch": 0.21622390554429388,
      "grad_norm": 0.06494403630495071,
      "learning_rate": 5.405886014048191e-06,
      "loss": 0.0067,
      "step": 760
    },
    {
      "epoch": 0.2190689569330346,
      "grad_norm": 0.06772973388433456,
      "learning_rate": 5.477016093180404e-06,
      "loss": 0.0063,
      "step": 770
    },
    {
      "epoch": 0.22191400832177532,
      "grad_norm": 0.051205262541770935,
      "learning_rate": 5.5481461723126175e-06,
      "loss": 0.0063,
      "step": 780
    },
    {
      "epoch": 0.22475905971051602,
      "grad_norm": 0.057035986334085464,
      "learning_rate": 5.6192762514448304e-06,
      "loss": 0.0063,
      "step": 790
    },
    {
      "epoch": 0.22760411109925674,
      "grad_norm": 0.048164695501327515,
      "learning_rate": 5.6904063305770425e-06,
      "loss": 0.0056,
      "step": 800
    },
    {
      "epoch": 0.23044916248799743,
      "grad_norm": 0.05380985513329506,
      "learning_rate": 5.761536409709256e-06,
      "loss": 0.0058,
      "step": 810
    },
    {
      "epoch": 0.23329421387673815,
      "grad_norm": 0.03878633305430412,
      "learning_rate": 5.832666488841469e-06,
      "loss": 0.0053,
      "step": 820
    },
    {
      "epoch": 0.23613926526547885,
      "grad_norm": 0.04493873938918114,
      "learning_rate": 5.903796567973682e-06,
      "loss": 0.0057,
      "step": 830
    },
    {
      "epoch": 0.23898431665421957,
      "grad_norm": 0.03924809396266937,
      "learning_rate": 5.974926647105895e-06,
      "loss": 0.0055,
      "step": 840
    },
    {
      "epoch": 0.24182936804296026,
      "grad_norm": 0.058627255260944366,
      "learning_rate": 6.046056726238109e-06,
      "loss": 0.0054,
      "step": 850
    },
    {
      "epoch": 0.24467441943170098,
      "grad_norm": 0.068621426820755,
      "learning_rate": 6.117186805370321e-06,
      "loss": 0.0065,
      "step": 860
    },
    {
      "epoch": 0.2475194708204417,
      "grad_norm": 0.05066554993391037,
      "learning_rate": 6.188316884502534e-06,
      "loss": 0.0054,
      "step": 870
    },
    {
      "epoch": 0.2503645222091824,
      "grad_norm": 0.05321214348077774,
      "learning_rate": 6.259446963634748e-06,
      "loss": 0.0051,
      "step": 880
    },
    {
      "epoch": 0.2532095735979231,
      "grad_norm": 0.054955266416072845,
      "learning_rate": 6.330577042766961e-06,
      "loss": 0.0057,
      "step": 890
    },
    {
      "epoch": 0.2560546249866638,
      "grad_norm": 0.05507129430770874,
      "learning_rate": 6.401707121899174e-06,
      "loss": 0.0056,
      "step": 900
    },
    {
      "epoch": 0.2588996763754045,
      "grad_norm": 0.05375712364912033,
      "learning_rate": 6.472837201031387e-06,
      "loss": 0.0055,
      "step": 910
    },
    {
      "epoch": 0.26174472776414526,
      "grad_norm": 0.04651631414890289,
      "learning_rate": 6.5439672801636004e-06,
      "loss": 0.0051,
      "step": 920
    },
    {
      "epoch": 0.26458977915288595,
      "grad_norm": 0.042346760630607605,
      "learning_rate": 6.6150973592958125e-06,
      "loss": 0.0055,
      "step": 930
    },
    {
      "epoch": 0.26743483054162664,
      "grad_norm": 0.04895606264472008,
      "learning_rate": 6.6862274384280255e-06,
      "loss": 0.0059,
      "step": 940
    },
    {
      "epoch": 0.2702798819303674,
      "grad_norm": 0.04482842609286308,
      "learning_rate": 6.757357517560239e-06,
      "loss": 0.005,
      "step": 950
    },
    {
      "epoch": 0.2731249333191081,
      "grad_norm": 0.041253965348005295,
      "learning_rate": 6.828487596692452e-06,
      "loss": 0.0058,
      "step": 960
    },
    {
      "epoch": 0.2759699847078488,
      "grad_norm": 0.034503597766160965,
      "learning_rate": 6.899617675824664e-06,
      "loss": 0.005,
      "step": 970
    },
    {
      "epoch": 0.2788150360965895,
      "grad_norm": 0.06278059631586075,
      "learning_rate": 6.970747754956878e-06,
      "loss": 0.0055,
      "step": 980
    },
    {
      "epoch": 0.2816600874853302,
      "grad_norm": 0.04181290045380592,
      "learning_rate": 7.041877834089091e-06,
      "loss": 0.0054,
      "step": 990
    },
    {
      "epoch": 0.2845051388740709,
      "grad_norm": 0.051747649908065796,
      "learning_rate": 7.113007913221304e-06,
      "loss": 0.0055,
      "step": 1000
    },
    {
      "epoch": 0.2845051388740709,
      "eval_loss": 0.03596724942326546,
      "eval_runtime": 9.3729,
      "eval_samples_per_second": 160.036,
      "eval_steps_per_second": 10.029,
      "eval_sts_dev_pearson_cosine": 0.82172548616974,
      "eval_sts_dev_pearson_dot": 0.7364892222173365,
      "eval_sts_dev_pearson_euclidean": 0.8020381417699484,
      "eval_sts_dev_pearson_manhattan": 0.8025412567249582,
      "eval_sts_dev_pearson_max": 0.82172548616974,
      "eval_sts_dev_spearman_cosine": 0.8319127997746368,
      "eval_sts_dev_spearman_dot": 0.7174649408827799,
      "eval_sts_dev_spearman_euclidean": 0.8094012861546513,
      "eval_sts_dev_spearman_manhattan": 0.8112845636960319,
      "eval_sts_dev_spearman_max": 0.8319127997746368,
      "step": 1000
    },
    {
      "epoch": 0.2873501902628116,
      "grad_norm": 0.041287198662757874,
      "learning_rate": 7.184137992353517e-06,
      "loss": 0.0059,
      "step": 1010
    },
    {
      "epoch": 0.2901952416515523,
      "grad_norm": 0.04565191641449928,
      "learning_rate": 7.255268071485731e-06,
      "loss": 0.0049,
      "step": 1020
    },
    {
      "epoch": 0.29304029304029305,
      "grad_norm": 0.049692653119564056,
      "learning_rate": 7.326398150617943e-06,
      "loss": 0.0052,
      "step": 1030
    },
    {
      "epoch": 0.29588534442903375,
      "grad_norm": 0.04820411652326584,
      "learning_rate": 7.397528229750156e-06,
      "loss": 0.0051,
      "step": 1040
    },
    {
      "epoch": 0.29873039581777444,
      "grad_norm": 0.05799231678247452,
      "learning_rate": 7.46865830888237e-06,
      "loss": 0.006,
      "step": 1050
    },
    {
      "epoch": 0.3015754472065152,
      "grad_norm": 0.039241332560777664,
      "learning_rate": 7.5397883880145825e-06,
      "loss": 0.0048,
      "step": 1060
    },
    {
      "epoch": 0.3044204985952559,
      "grad_norm": 0.04567272588610649,
      "learning_rate": 7.610918467146795e-06,
      "loss": 0.0055,
      "step": 1070
    },
    {
      "epoch": 0.3072655499839966,
      "grad_norm": 0.05523727089166641,
      "learning_rate": 7.682048546279008e-06,
      "loss": 0.0052,
      "step": 1080
    },
    {
      "epoch": 0.31011060137273727,
      "grad_norm": 0.046325985342264175,
      "learning_rate": 7.753178625411222e-06,
      "loss": 0.0051,
      "step": 1090
    },
    {
      "epoch": 0.312955652761478,
      "grad_norm": 0.048398926854133606,
      "learning_rate": 7.824308704543434e-06,
      "loss": 0.0051,
      "step": 1100
    },
    {
      "epoch": 0.3158007041502187,
      "grad_norm": 0.04315317049622536,
      "learning_rate": 7.895438783675648e-06,
      "loss": 0.005,
      "step": 1110
    },
    {
      "epoch": 0.3186457555389594,
      "grad_norm": 0.04845454543828964,
      "learning_rate": 7.96656886280786e-06,
      "loss": 0.0054,
      "step": 1120
    },
    {
      "epoch": 0.32149080692770016,
      "grad_norm": 0.049591273069381714,
      "learning_rate": 8.037698941940072e-06,
      "loss": 0.0051,
      "step": 1130
    },
    {
      "epoch": 0.32433585831644085,
      "grad_norm": 0.036491356790065765,
      "learning_rate": 8.108829021072286e-06,
      "loss": 0.0054,
      "step": 1140
    },
    {
      "epoch": 0.32718090970518154,
      "grad_norm": 0.032174497842788696,
      "learning_rate": 8.1799591002045e-06,
      "loss": 0.0056,
      "step": 1150
    },
    {
      "epoch": 0.33002596109392224,
      "grad_norm": 0.050426822155714035,
      "learning_rate": 8.251089179336714e-06,
      "loss": 0.0053,
      "step": 1160
    },
    {
      "epoch": 0.332871012482663,
      "grad_norm": 0.03973342478275299,
      "learning_rate": 8.322219258468926e-06,
      "loss": 0.0052,
      "step": 1170
    },
    {
      "epoch": 0.3357160638714037,
      "grad_norm": 0.051343441009521484,
      "learning_rate": 8.39334933760114e-06,
      "loss": 0.0051,
      "step": 1180
    },
    {
      "epoch": 0.3385611152601444,
      "grad_norm": 0.04074539989233017,
      "learning_rate": 8.464479416733352e-06,
      "loss": 0.0051,
      "step": 1190
    },
    {
      "epoch": 0.3414061666488851,
      "grad_norm": 0.040065567940473557,
      "learning_rate": 8.535609495865564e-06,
      "loss": 0.0048,
      "step": 1200
    },
    {
      "epoch": 0.3442512180376258,
      "grad_norm": 0.054492607712745667,
      "learning_rate": 8.606739574997778e-06,
      "loss": 0.005,
      "step": 1210
    },
    {
      "epoch": 0.3470962694263665,
      "grad_norm": 0.048747118562459946,
      "learning_rate": 8.677869654129991e-06,
      "loss": 0.0055,
      "step": 1220
    },
    {
      "epoch": 0.3499413208151072,
      "grad_norm": 0.03102809563279152,
      "learning_rate": 8.748999733262203e-06,
      "loss": 0.0049,
      "step": 1230
    },
    {
      "epoch": 0.35278637220384795,
      "grad_norm": 0.046874821186065674,
      "learning_rate": 8.820129812394417e-06,
      "loss": 0.0053,
      "step": 1240
    },
    {
      "epoch": 0.35563142359258865,
      "grad_norm": 0.04343179240822792,
      "learning_rate": 8.89125989152663e-06,
      "loss": 0.0052,
      "step": 1250
    },
    {
      "epoch": 0.35563142359258865,
      "eval_loss": 0.036384228616952896,
      "eval_runtime": 9.2709,
      "eval_samples_per_second": 161.796,
      "eval_steps_per_second": 10.139,
      "eval_sts_dev_pearson_cosine": 0.8227235713076437,
      "eval_sts_dev_pearson_dot": 0.7352421859428611,
      "eval_sts_dev_pearson_euclidean": 0.8053003746237307,
      "eval_sts_dev_pearson_manhattan": 0.805677081921409,
      "eval_sts_dev_pearson_max": 0.8227235713076437,
      "eval_sts_dev_spearman_cosine": 0.8330328864427068,
      "eval_sts_dev_spearman_dot": 0.715812823875112,
      "eval_sts_dev_spearman_euclidean": 0.8129674308880657,
      "eval_sts_dev_spearman_manhattan": 0.814635019437101,
      "eval_sts_dev_spearman_max": 0.8330328864427068,
      "step": 1250
    },
    {
      "epoch": 0.35847647498132934,
      "grad_norm": 0.043001964688301086,
      "learning_rate": 8.962389970658843e-06,
      "loss": 0.0051,
      "step": 1260
    },
    {
      "epoch": 0.36132152637007003,
      "grad_norm": 0.03615862876176834,
      "learning_rate": 9.033520049791055e-06,
      "loss": 0.005,
      "step": 1270
    },
    {
      "epoch": 0.3641665777588108,
      "grad_norm": 0.039267782121896744,
      "learning_rate": 9.104650128923269e-06,
      "loss": 0.005,
      "step": 1280
    },
    {
      "epoch": 0.3670116291475515,
      "grad_norm": 0.04287976399064064,
      "learning_rate": 9.175780208055483e-06,
      "loss": 0.0045,
      "step": 1290
    },
    {
      "epoch": 0.36985668053629217,
      "grad_norm": 0.04853058233857155,
      "learning_rate": 9.246910287187695e-06,
      "loss": 0.0055,
      "step": 1300
    },
    {
      "epoch": 0.3727017319250329,
      "grad_norm": 0.044756922870874405,
      "learning_rate": 9.318040366319909e-06,
      "loss": 0.0049,
      "step": 1310
    },
    {
      "epoch": 0.3755467833137736,
      "grad_norm": 0.04728604108095169,
      "learning_rate": 9.389170445452121e-06,
      "loss": 0.0049,
      "step": 1320
    },
    {
      "epoch": 0.3783918347025143,
      "grad_norm": 0.05135470628738403,
      "learning_rate": 9.460300524584335e-06,
      "loss": 0.0053,
      "step": 1330
    },
    {
      "epoch": 0.381236886091255,
      "grad_norm": 0.05084382742643356,
      "learning_rate": 9.531430603716547e-06,
      "loss": 0.005,
      "step": 1340
    },
    {
      "epoch": 0.38408193747999575,
      "grad_norm": 0.04461762309074402,
      "learning_rate": 9.60256068284876e-06,
      "loss": 0.0048,
      "step": 1350
    },
    {
      "epoch": 0.38692698886873644,
      "grad_norm": 0.04691236838698387,
      "learning_rate": 9.673690761980974e-06,
      "loss": 0.0049,
      "step": 1360
    },
    {
      "epoch": 0.38977204025747714,
      "grad_norm": 0.05038540065288544,
      "learning_rate": 9.744820841113186e-06,
      "loss": 0.0046,
      "step": 1370
    },
    {
      "epoch": 0.3926170916462179,
      "grad_norm": 0.037911634892225266,
      "learning_rate": 9.8159509202454e-06,
      "loss": 0.0049,
      "step": 1380
    },
    {
      "epoch": 0.3954621430349586,
      "grad_norm": 0.03995656967163086,
      "learning_rate": 9.887080999377612e-06,
      "loss": 0.0052,
      "step": 1390
    },
    {
      "epoch": 0.3983071944236993,
      "grad_norm": 0.03694682940840721,
      "learning_rate": 9.958211078509824e-06,
      "loss": 0.005,
      "step": 1400
    },
    {
      "epoch": 0.40115224581243997,
      "grad_norm": 0.04984055832028389,
      "learning_rate": 1.0029341157642038e-05,
      "loss": 0.0052,
      "step": 1410
    },
    {
      "epoch": 0.4039972972011807,
      "grad_norm": 0.045273568481206894,
      "learning_rate": 1.0100471236774252e-05,
      "loss": 0.0052,
      "step": 1420
    },
    {
      "epoch": 0.4068423485899214,
      "grad_norm": 0.04406927153468132,
      "learning_rate": 1.0171601315906466e-05,
      "loss": 0.0045,
      "step": 1430
    },
    {
      "epoch": 0.4096873999786621,
      "grad_norm": 0.04544726386666298,
      "learning_rate": 1.0242731395038678e-05,
      "loss": 0.0046,
      "step": 1440
    },
    {
      "epoch": 0.4125324513674028,
      "grad_norm": 0.05660213530063629,
      "learning_rate": 1.031386147417089e-05,
      "loss": 0.0056,
      "step": 1450
    },
    {
      "epoch": 0.41537750275614355,
      "grad_norm": 0.03915410116314888,
      "learning_rate": 1.0384991553303104e-05,
      "loss": 0.0056,
      "step": 1460
    },
    {
      "epoch": 0.41822255414488424,
      "grad_norm": 0.04316354915499687,
      "learning_rate": 1.0456121632435316e-05,
      "loss": 0.005,
      "step": 1470
    },
    {
      "epoch": 0.42106760553362493,
      "grad_norm": 0.03962288424372673,
      "learning_rate": 1.052725171156753e-05,
      "loss": 0.0051,
      "step": 1480
    },
    {
      "epoch": 0.4239126569223657,
      "grad_norm": 0.05906355381011963,
      "learning_rate": 1.0598381790699743e-05,
      "loss": 0.0049,
      "step": 1490
    },
    {
      "epoch": 0.4267577083111064,
      "grad_norm": 0.048688966780900955,
      "learning_rate": 1.0669511869831957e-05,
      "loss": 0.0048,
      "step": 1500
    },
    {
      "epoch": 0.4267577083111064,
      "eval_loss": 0.037407051771879196,
      "eval_runtime": 9.34,
      "eval_samples_per_second": 160.6,
      "eval_steps_per_second": 10.064,
      "eval_sts_dev_pearson_cosine": 0.8235580009492447,
      "eval_sts_dev_pearson_dot": 0.7304409388102885,
      "eval_sts_dev_pearson_euclidean": 0.80850209692844,
      "eval_sts_dev_pearson_manhattan": 0.8086421345574696,
      "eval_sts_dev_pearson_max": 0.8235580009492447,
      "eval_sts_dev_spearman_cosine": 0.8334282731331559,
      "eval_sts_dev_spearman_dot": 0.7108658935799598,
      "eval_sts_dev_spearman_euclidean": 0.8172139025761608,
      "eval_sts_dev_spearman_manhattan": 0.8184702685018853,
      "eval_sts_dev_spearman_max": 0.8334282731331559,
      "step": 1500
    },
    {
      "epoch": 0.42960275969984707,
      "grad_norm": 0.06282392889261246,
      "learning_rate": 1.074064194896417e-05,
      "loss": 0.0053,
      "step": 1510
    },
    {
      "epoch": 0.43244781108858776,
      "grad_norm": 0.04287637770175934,
      "learning_rate": 1.0811772028096381e-05,
      "loss": 0.0054,
      "step": 1520
    },
    {
      "epoch": 0.4352928624773285,
      "grad_norm": 0.03431074693799019,
      "learning_rate": 1.0882902107228595e-05,
      "loss": 0.0048,
      "step": 1530
    },
    {
      "epoch": 0.4381379138660692,
      "grad_norm": 0.04143288731575012,
      "learning_rate": 1.0954032186360807e-05,
      "loss": 0.005,
      "step": 1540
    },
    {
      "epoch": 0.4409829652548099,
      "grad_norm": 0.03329918906092644,
      "learning_rate": 1.1025162265493021e-05,
      "loss": 0.0045,
      "step": 1550
    },
    {
      "epoch": 0.44382801664355065,
      "grad_norm": 0.040052179247140884,
      "learning_rate": 1.1096292344625235e-05,
      "loss": 0.0046,
      "step": 1560
    },
    {
      "epoch": 0.44667306803229134,
      "grad_norm": 0.03860851004719734,
      "learning_rate": 1.1167422423757449e-05,
      "loss": 0.0045,
      "step": 1570
    },
    {
      "epoch": 0.44951811942103204,
      "grad_norm": 0.04196810722351074,
      "learning_rate": 1.1238552502889661e-05,
      "loss": 0.0049,
      "step": 1580
    },
    {
      "epoch": 0.45236317080977273,
      "grad_norm": 0.039289627224206924,
      "learning_rate": 1.1309682582021873e-05,
      "loss": 0.0048,
      "step": 1590
    },
    {
      "epoch": 0.4552082221985135,
      "grad_norm": 0.0410202331840992,
      "learning_rate": 1.1380812661154085e-05,
      "loss": 0.005,
      "step": 1600
    },
    {
      "epoch": 0.4580532735872542,
      "grad_norm": 0.042857419699430466,
      "learning_rate": 1.1451942740286299e-05,
      "loss": 0.0045,
      "step": 1610
    },
    {
      "epoch": 0.46089832497599487,
      "grad_norm": 0.05660340189933777,
      "learning_rate": 1.1523072819418513e-05,
      "loss": 0.0049,
      "step": 1620
    },
    {
      "epoch": 0.4637433763647356,
      "grad_norm": 0.03311100974678993,
      "learning_rate": 1.1594202898550726e-05,
      "loss": 0.0044,
      "step": 1630
    },
    {
      "epoch": 0.4665884277534763,
      "grad_norm": 0.040902819484472275,
      "learning_rate": 1.1665332977682939e-05,
      "loss": 0.0048,
      "step": 1640
    },
    {
      "epoch": 0.469433479142217,
      "grad_norm": 0.03882967308163643,
      "learning_rate": 1.1736463056815152e-05,
      "loss": 0.0049,
      "step": 1650
    },
    {
      "epoch": 0.4722785305309577,
      "grad_norm": 0.03872678056359291,
      "learning_rate": 1.1807593135947364e-05,
      "loss": 0.0048,
      "step": 1660
    },
    {
      "epoch": 0.47512358191969845,
      "grad_norm": 0.04378141462802887,
      "learning_rate": 1.1878723215079577e-05,
      "loss": 0.0051,
      "step": 1670
    },
    {
      "epoch": 0.47796863330843914,
      "grad_norm": 0.03466705232858658,
      "learning_rate": 1.194985329421179e-05,
      "loss": 0.0047,
      "step": 1680
    },
    {
      "epoch": 0.48081368469717983,
      "grad_norm": 0.03464537858963013,
      "learning_rate": 1.2020983373344004e-05,
      "loss": 0.0048,
      "step": 1690
    },
    {
      "epoch": 0.4836587360859205,
      "grad_norm": 0.03331427648663521,
      "learning_rate": 1.2092113452476218e-05,
      "loss": 0.0047,
      "step": 1700
    },
    {
      "epoch": 0.4865037874746613,
      "grad_norm": 0.03817320987582207,
      "learning_rate": 1.216324353160843e-05,
      "loss": 0.0044,
      "step": 1710
    },
    {
      "epoch": 0.48934883886340197,
      "grad_norm": 0.03969097137451172,
      "learning_rate": 1.2234373610740642e-05,
      "loss": 0.0049,
      "step": 1720
    },
    {
      "epoch": 0.49219389025214266,
      "grad_norm": 0.035453908145427704,
      "learning_rate": 1.2305503689872856e-05,
      "loss": 0.0049,
      "step": 1730
    },
    {
      "epoch": 0.4950389416408834,
      "grad_norm": 0.05088822916150093,
      "learning_rate": 1.2376633769005068e-05,
      "loss": 0.0051,
      "step": 1740
    },
    {
      "epoch": 0.4978839930296241,
      "grad_norm": 0.0713745728135109,
      "learning_rate": 1.2447763848137282e-05,
      "loss": 0.0043,
      "step": 1750
    },
    {
      "epoch": 0.4978839930296241,
      "eval_loss": 0.039244912564754486,
      "eval_runtime": 9.3246,
      "eval_samples_per_second": 160.865,
      "eval_steps_per_second": 10.081,
      "eval_sts_dev_pearson_cosine": 0.8238186946290151,
      "eval_sts_dev_pearson_dot": 0.7239411623613566,
      "eval_sts_dev_pearson_euclidean": 0.8121715578027333,
      "eval_sts_dev_pearson_manhattan": 0.8120907547694739,
      "eval_sts_dev_pearson_max": 0.8238186946290151,
      "eval_sts_dev_spearman_cosine": 0.835172641675273,
      "eval_sts_dev_spearman_dot": 0.7062934262157234,
      "eval_sts_dev_spearman_euclidean": 0.8213874307893159,
      "eval_sts_dev_spearman_manhattan": 0.8223449132950557,
      "eval_sts_dev_spearman_max": 0.835172641675273,
      "step": 1750
    },
    {
      "epoch": 0.5007290444183649,
      "grad_norm": 0.04352276772260666,
      "learning_rate": 1.2518893927269496e-05,
      "loss": 0.0043,
      "step": 1760
    },
    {
      "epoch": 0.5035740958071055,
      "grad_norm": 0.03687438368797302,
      "learning_rate": 1.259002400640171e-05,
      "loss": 0.0045,
      "step": 1770
    },
    {
      "epoch": 0.5064191471958462,
      "grad_norm": 0.03907119855284691,
      "learning_rate": 1.2661154085533921e-05,
      "loss": 0.0046,
      "step": 1780
    },
    {
      "epoch": 0.5092641985845869,
      "grad_norm": 0.04670177772641182,
      "learning_rate": 1.2732284164666134e-05,
      "loss": 0.0042,
      "step": 1790
    },
    {
      "epoch": 0.5121092499733276,
      "grad_norm": 0.042154308408498764,
      "learning_rate": 1.2803414243798347e-05,
      "loss": 0.0047,
      "step": 1800
    },
    {
      "epoch": 0.5149543013620683,
      "grad_norm": 0.049788545817136765,
      "learning_rate": 1.287454432293056e-05,
      "loss": 0.0047,
      "step": 1810
    },
    {
      "epoch": 0.517799352750809,
      "grad_norm": 0.030743401497602463,
      "learning_rate": 1.2945674402062773e-05,
      "loss": 0.0046,
      "step": 1820
    },
    {
      "epoch": 0.5206444041395498,
      "grad_norm": 0.03050127439200878,
      "learning_rate": 1.3016804481194987e-05,
      "loss": 0.0044,
      "step": 1830
    },
    {
      "epoch": 0.5234894555282905,
      "grad_norm": 0.04552179202437401,
      "learning_rate": 1.3087934560327201e-05,
      "loss": 0.0046,
      "step": 1840
    },
    {
      "epoch": 0.5263345069170312,
      "grad_norm": 0.035957857966423035,
      "learning_rate": 1.3159064639459413e-05,
      "loss": 0.0047,
      "step": 1850
    },
    {
      "epoch": 0.5291795583057719,
      "grad_norm": 0.042550280690193176,
      "learning_rate": 1.3230194718591625e-05,
      "loss": 0.0044,
      "step": 1860
    },
    {
      "epoch": 0.5320246096945126,
      "grad_norm": 0.046532485634088516,
      "learning_rate": 1.3301324797723837e-05,
      "loss": 0.0047,
      "step": 1870
    },
    {
      "epoch": 0.5348696610832533,
      "grad_norm": 0.06353285163640976,
      "learning_rate": 1.3372454876856051e-05,
      "loss": 0.0049,
      "step": 1880
    },
    {
      "epoch": 0.537714712471994,
      "grad_norm": 0.06265376508235931,
      "learning_rate": 1.3443584955988265e-05,
      "loss": 0.0049,
      "step": 1890
    },
    {
      "epoch": 0.5405597638607348,
      "grad_norm": 0.03437663987278938,
      "learning_rate": 1.3514715035120479e-05,
      "loss": 0.0047,
      "step": 1900
    },
    {
      "epoch": 0.5434048152494755,
      "grad_norm": 0.0506511814892292,
      "learning_rate": 1.358584511425269e-05,
      "loss": 0.0045,
      "step": 1910
    },
    {
      "epoch": 0.5462498666382162,
      "grad_norm": 0.041182588785886765,
      "learning_rate": 1.3656975193384904e-05,
      "loss": 0.0044,
      "step": 1920
    },
    {
      "epoch": 0.5490949180269569,
      "grad_norm": 0.0319492369890213,
      "learning_rate": 1.3728105272517117e-05,
      "loss": 0.0048,
      "step": 1930
    },
    {
      "epoch": 0.5519399694156976,
      "grad_norm": 0.03551415726542473,
      "learning_rate": 1.3799235351649329e-05,
      "loss": 0.0041,
      "step": 1940
    },
    {
      "epoch": 0.5547850208044383,
      "grad_norm": 0.0385081022977829,
      "learning_rate": 1.3870365430781542e-05,
      "loss": 0.004,
      "step": 1950
    },
    {
      "epoch": 0.557630072193179,
      "grad_norm": 0.03801606595516205,
      "learning_rate": 1.3941495509913756e-05,
      "loss": 0.0048,
      "step": 1960
    },
    {
      "epoch": 0.5604751235819196,
      "grad_norm": 0.0409582257270813,
      "learning_rate": 1.401262558904597e-05,
      "loss": 0.0042,
      "step": 1970
    },
    {
      "epoch": 0.5633201749706604,
      "grad_norm": 0.040966786444187164,
      "learning_rate": 1.4083755668178182e-05,
      "loss": 0.0048,
      "step": 1980
    },
    {
      "epoch": 0.5661652263594011,
      "grad_norm": 0.045747336000204086,
      "learning_rate": 1.4154885747310394e-05,
      "loss": 0.0045,
      "step": 1990
    },
    {
      "epoch": 0.5690102777481418,
      "grad_norm": 0.04319002479314804,
      "learning_rate": 1.4226015826442608e-05,
      "loss": 0.0043,
      "step": 2000
    },
    {
      "epoch": 0.5690102777481418,
      "eval_loss": 0.03749217092990875,
      "eval_runtime": 9.2357,
      "eval_samples_per_second": 162.414,
      "eval_steps_per_second": 10.178,
      "eval_sts_dev_pearson_cosine": 0.8261085791313695,
      "eval_sts_dev_pearson_dot": 0.7313352904564399,
      "eval_sts_dev_pearson_euclidean": 0.8139794096198416,
      "eval_sts_dev_pearson_manhattan": 0.8137749296469377,
      "eval_sts_dev_pearson_max": 0.8261085791313695,
      "eval_sts_dev_spearman_cosine": 0.835855895733968,
      "eval_sts_dev_spearman_dot": 0.7134011062715361,
      "eval_sts_dev_spearman_euclidean": 0.8230230911277879,
      "eval_sts_dev_spearman_manhattan": 0.8237999277944462,
      "eval_sts_dev_spearman_max": 0.835855895733968,
      "step": 2000
    },
    {
      "epoch": 0.5718553291368825,
      "grad_norm": 0.04026263579726219,
      "learning_rate": 1.429714590557482e-05,
      "loss": 0.005,
      "step": 2010
    },
    {
      "epoch": 0.5747003805256232,
      "grad_norm": 0.035753291100263596,
      "learning_rate": 1.4368275984707034e-05,
      "loss": 0.0049,
      "step": 2020
    },
    {
      "epoch": 0.5775454319143639,
      "grad_norm": 0.047706492245197296,
      "learning_rate": 1.4439406063839248e-05,
      "loss": 0.0044,
      "step": 2030
    },
    {
      "epoch": 0.5803904833031046,
      "grad_norm": 0.0450417585670948,
      "learning_rate": 1.4510536142971462e-05,
      "loss": 0.0045,
      "step": 2040
    },
    {
      "epoch": 0.5832355346918454,
      "grad_norm": 0.040127743035554886,
      "learning_rate": 1.4581666222103674e-05,
      "loss": 0.0043,
      "step": 2050
    },
    {
      "epoch": 0.5860805860805861,
      "grad_norm": 0.03849497064948082,
      "learning_rate": 1.4652796301235886e-05,
      "loss": 0.0045,
      "step": 2060
    },
    {
      "epoch": 0.5889256374693268,
      "grad_norm": 0.03406572341918945,
      "learning_rate": 1.47239263803681e-05,
      "loss": 0.004,
      "step": 2070
    },
    {
      "epoch": 0.5917706888580675,
      "grad_norm": 0.03106602467596531,
      "learning_rate": 1.4795056459500312e-05,
      "loss": 0.0042,
      "step": 2080
    },
    {
      "epoch": 0.5946157402468082,
      "grad_norm": 0.0420919694006443,
      "learning_rate": 1.4866186538632525e-05,
      "loss": 0.0044,
      "step": 2090
    },
    {
      "epoch": 0.5974607916355489,
      "grad_norm": 0.03017972595989704,
      "learning_rate": 1.493731661776474e-05,
      "loss": 0.0043,
      "step": 2100
    },
    {
      "epoch": 0.6003058430242896,
      "grad_norm": 0.036625951528549194,
      "learning_rate": 1.5008446696896953e-05,
      "loss": 0.0041,
      "step": 2110
    },
    {
      "epoch": 0.6031508944130304,
      "grad_norm": 0.043762583285570145,
      "learning_rate": 1.5079576776029165e-05,
      "loss": 0.0046,
      "step": 2120
    },
    {
      "epoch": 0.6059959458017711,
      "grad_norm": 0.04011479392647743,
      "learning_rate": 1.5150706855161377e-05,
      "loss": 0.0048,
      "step": 2130
    },
    {
      "epoch": 0.6088409971905118,
      "grad_norm": 0.038334403187036514,
      "learning_rate": 1.522183693429359e-05,
      "loss": 0.0048,
      "step": 2140
    },
    {
      "epoch": 0.6116860485792525,
      "grad_norm": 0.031101884320378304,
      "learning_rate": 1.5292967013425805e-05,
      "loss": 0.0041,
      "step": 2150
    },
    {
      "epoch": 0.6145310999679932,
      "grad_norm": 0.03326570242643356,
      "learning_rate": 1.5364097092558017e-05,
      "loss": 0.0044,
      "step": 2160
    },
    {
      "epoch": 0.6173761513567338,
      "grad_norm": 0.03964686393737793,
      "learning_rate": 1.543522717169023e-05,
      "loss": 0.0045,
      "step": 2170
    },
    {
      "epoch": 0.6202212027454745,
      "grad_norm": 0.03298981860280037,
      "learning_rate": 1.5506357250822444e-05,
      "loss": 0.0044,
      "step": 2180
    },
    {
      "epoch": 0.6230662541342153,
      "grad_norm": 0.03743202984333038,
      "learning_rate": 1.5577487329954657e-05,
      "loss": 0.0044,
      "step": 2190
    },
    {
      "epoch": 0.625911305522956,
      "grad_norm": 0.04800928011536598,
      "learning_rate": 1.564861740908687e-05,
      "loss": 0.0046,
      "step": 2200
    },
    {
      "epoch": 0.6287563569116967,
      "grad_norm": 0.03906644880771637,
      "learning_rate": 1.571974748821908e-05,
      "loss": 0.0048,
      "step": 2210
    },
    {
      "epoch": 0.6316014083004374,
      "grad_norm": 0.037462957203388214,
      "learning_rate": 1.5790877567351296e-05,
      "loss": 0.0045,
      "step": 2220
    },
    {
      "epoch": 0.6344464596891781,
      "grad_norm": 0.037155114114284515,
      "learning_rate": 1.586200764648351e-05,
      "loss": 0.004,
      "step": 2230
    },
    {
      "epoch": 0.6372915110779188,
      "grad_norm": 0.034092146903276443,
      "learning_rate": 1.593313772561572e-05,
      "loss": 0.0041,
      "step": 2240
    },
    {
      "epoch": 0.6401365624666595,
      "grad_norm": 0.03896261751651764,
      "learning_rate": 1.6004267804747936e-05,
      "loss": 0.0044,
      "step": 2250
    },
    {
      "epoch": 0.6401365624666595,
      "eval_loss": 0.039099473506212234,
      "eval_runtime": 9.2514,
      "eval_samples_per_second": 162.137,
      "eval_steps_per_second": 10.161,
      "eval_sts_dev_pearson_cosine": 0.8272187422275056,
      "eval_sts_dev_pearson_dot": 0.7283947785380285,
      "eval_sts_dev_pearson_euclidean": 0.815899998489852,
      "eval_sts_dev_pearson_manhattan": 0.81565618483905,
      "eval_sts_dev_pearson_max": 0.8272187422275056,
      "eval_sts_dev_spearman_cosine": 0.836903996661572,
      "eval_sts_dev_spearman_dot": 0.7095745027354784,
      "eval_sts_dev_spearman_euclidean": 0.8251814652974586,
      "eval_sts_dev_spearman_manhattan": 0.8261966578035025,
      "eval_sts_dev_spearman_max": 0.836903996661572,
      "step": 2250
    },
    {
      "epoch": 0.6429816138554003,
      "grad_norm": 0.03634743019938469,
      "learning_rate": 1.6075397883880145e-05,
      "loss": 0.0044,
      "step": 2260
    },
    {
      "epoch": 0.645826665244141,
      "grad_norm": 0.04395711049437523,
      "learning_rate": 1.614652796301236e-05,
      "loss": 0.0045,
      "step": 2270
    },
    {
      "epoch": 0.6486717166328817,
      "grad_norm": 0.0334044024348259,
      "learning_rate": 1.6217658042144572e-05,
      "loss": 0.0041,
      "step": 2280
    },
    {
      "epoch": 0.6515167680216224,
      "grad_norm": 0.03832104057073593,
      "learning_rate": 1.6288788121276788e-05,
      "loss": 0.0042,
      "step": 2290
    },
    {
      "epoch": 0.6543618194103631,
      "grad_norm": 0.04635302349925041,
      "learning_rate": 1.6359918200409e-05,
      "loss": 0.0043,
      "step": 2300
    },
    {
      "epoch": 0.6572068707991038,
      "grad_norm": 0.03036418743431568,
      "learning_rate": 1.6431048279541212e-05,
      "loss": 0.004,
      "step": 2310
    },
    {
      "epoch": 0.6600519221878445,
      "grad_norm": 0.025319894775748253,
      "learning_rate": 1.6502178358673427e-05,
      "loss": 0.0042,
      "step": 2320
    },
    {
      "epoch": 0.6628969735765853,
      "grad_norm": 0.03628432750701904,
      "learning_rate": 1.6573308437805636e-05,
      "loss": 0.0041,
      "step": 2330
    },
    {
      "epoch": 0.665742024965326,
      "grad_norm": 0.03586098179221153,
      "learning_rate": 1.664443851693785e-05,
      "loss": 0.0045,
      "step": 2340
    },
    {
      "epoch": 0.6685870763540667,
      "grad_norm": 0.03873738646507263,
      "learning_rate": 1.6715568596070064e-05,
      "loss": 0.0045,
      "step": 2350
    },
    {
      "epoch": 0.6714321277428074,
      "grad_norm": 0.038827184587717056,
      "learning_rate": 1.678669867520228e-05,
      "loss": 0.0042,
      "step": 2360
    },
    {
      "epoch": 0.674277179131548,
      "grad_norm": 0.03740520030260086,
      "learning_rate": 1.685782875433449e-05,
      "loss": 0.0045,
      "step": 2370
    },
    {
      "epoch": 0.6771222305202887,
      "grad_norm": 0.03753795102238655,
      "learning_rate": 1.6928958833466703e-05,
      "loss": 0.0044,
      "step": 2380
    },
    {
      "epoch": 0.6799672819090294,
      "grad_norm": 0.04462343081831932,
      "learning_rate": 1.700008891259892e-05,
      "loss": 0.0044,
      "step": 2390
    },
    {
      "epoch": 0.6828123332977702,
      "grad_norm": 0.0419158972799778,
      "learning_rate": 1.7071218991731128e-05,
      "loss": 0.0041,
      "step": 2400
    },
    {
      "epoch": 0.6856573846865109,
      "grad_norm": 0.04727786406874657,
      "learning_rate": 1.7142349070863343e-05,
      "loss": 0.0045,
      "step": 2410
    },
    {
      "epoch": 0.6885024360752516,
      "grad_norm": 0.03223787620663643,
      "learning_rate": 1.7213479149995555e-05,
      "loss": 0.0046,
      "step": 2420
    },
    {
      "epoch": 0.6913474874639923,
      "grad_norm": 0.04408884793519974,
      "learning_rate": 1.7284609229127767e-05,
      "loss": 0.0041,
      "step": 2430
    },
    {
      "epoch": 0.694192538852733,
      "grad_norm": 0.039247192442417145,
      "learning_rate": 1.7355739308259983e-05,
      "loss": 0.0048,
      "step": 2440
    },
    {
      "epoch": 0.6970375902414737,
      "grad_norm": 0.032358501106500626,
      "learning_rate": 1.7426869387392195e-05,
      "loss": 0.0041,
      "step": 2450
    },
    {
      "epoch": 0.6998826416302144,
      "grad_norm": 0.039968185126781464,
      "learning_rate": 1.7497999466524407e-05,
      "loss": 0.0043,
      "step": 2460
    },
    {
      "epoch": 0.7027276930189551,
      "grad_norm": 0.038930464535951614,
      "learning_rate": 1.756912954565662e-05,
      "loss": 0.0043,
      "step": 2470
    },
    {
      "epoch": 0.7055727444076959,
      "grad_norm": 0.03470390662550926,
      "learning_rate": 1.7640259624788835e-05,
      "loss": 0.0037,
      "step": 2480
    },
    {
      "epoch": 0.7084177957964366,
      "grad_norm": 0.03886763006448746,
      "learning_rate": 1.7711389703921047e-05,
      "loss": 0.0042,
      "step": 2490
    },
    {
      "epoch": 0.7112628471851773,
      "grad_norm": 0.032276757061481476,
      "learning_rate": 1.778251978305326e-05,
      "loss": 0.0043,
      "step": 2500
    },
    {
      "epoch": 0.7112628471851773,
      "eval_loss": 0.04045585170388222,
      "eval_runtime": 9.2659,
      "eval_samples_per_second": 161.885,
      "eval_steps_per_second": 10.145,
      "eval_sts_dev_pearson_cosine": 0.8260847942632407,
      "eval_sts_dev_pearson_dot": 0.7260943559708607,
      "eval_sts_dev_pearson_euclidean": 0.8155324932216388,
      "eval_sts_dev_pearson_manhattan": 0.8152500275551733,
      "eval_sts_dev_pearson_max": 0.8260847942632407,
      "eval_sts_dev_spearman_cosine": 0.8365382060177997,
      "eval_sts_dev_spearman_dot": 0.7099426230017294,
      "eval_sts_dev_spearman_euclidean": 0.8247320291703734,
      "eval_sts_dev_spearman_manhattan": 0.8257079061230801,
      "eval_sts_dev_spearman_max": 0.8365382060177997,
      "step": 2500
    },
    {
      "epoch": 0.714107898573918,
      "grad_norm": 0.04151437059044838,
      "learning_rate": 1.7853649862185474e-05,
      "loss": 0.0045,
      "step": 2510
    },
    {
      "epoch": 0.7169529499626587,
      "grad_norm": 0.04570092633366585,
      "learning_rate": 1.7924779941317686e-05,
      "loss": 0.0044,
      "step": 2520
    },
    {
      "epoch": 0.7197980013513994,
      "grad_norm": 0.03871253505349159,
      "learning_rate": 1.79959100204499e-05,
      "loss": 0.0042,
      "step": 2530
    },
    {
      "epoch": 0.7226430527401401,
      "grad_norm": 0.04794856533408165,
      "learning_rate": 1.806704009958211e-05,
      "loss": 0.0042,
      "step": 2540
    },
    {
      "epoch": 0.7254881041288809,
      "grad_norm": 0.03689658269286156,
      "learning_rate": 1.8138170178714326e-05,
      "loss": 0.0041,
      "step": 2550
    },
    {
      "epoch": 0.7283331555176216,
      "grad_norm": 0.04062201827764511,
      "learning_rate": 1.8209300257846538e-05,
      "loss": 0.0042,
      "step": 2560
    },
    {
      "epoch": 0.7311782069063623,
      "grad_norm": 0.04463518038392067,
      "learning_rate": 1.828043033697875e-05,
      "loss": 0.0041,
      "step": 2570
    },
    {
      "epoch": 0.734023258295103,
      "grad_norm": 0.040007706731557846,
      "learning_rate": 1.8351560416110966e-05,
      "loss": 0.0042,
      "step": 2580
    },
    {
      "epoch": 0.7368683096838436,
      "grad_norm": 0.0314442440867424,
      "learning_rate": 1.8422690495243178e-05,
      "loss": 0.0041,
      "step": 2590
    },
    {
      "epoch": 0.7397133610725843,
      "grad_norm": 0.0411388985812664,
      "learning_rate": 1.849382057437539e-05,
      "loss": 0.0047,
      "step": 2600
    },
    {
      "epoch": 0.742558412461325,
      "grad_norm": 0.04951240494847298,
      "learning_rate": 1.8564950653507602e-05,
      "loss": 0.0038,
      "step": 2610
    },
    {
      "epoch": 0.7454034638500658,
      "grad_norm": 0.06948298215866089,
      "learning_rate": 1.8636080732639818e-05,
      "loss": 0.0041,
      "step": 2620
    },
    {
      "epoch": 0.7482485152388065,
      "grad_norm": 0.0375785268843174,
      "learning_rate": 1.870721081177203e-05,
      "loss": 0.0042,
      "step": 2630
    },
    {
      "epoch": 0.7510935666275472,
      "grad_norm": 0.04124037176370621,
      "learning_rate": 1.8778340890904242e-05,
      "loss": 0.0042,
      "step": 2640
    },
    {
      "epoch": 0.7539386180162879,
      "grad_norm": 0.03421395272016525,
      "learning_rate": 1.8849470970036457e-05,
      "loss": 0.0042,
      "step": 2650
    },
    {
      "epoch": 0.7567836694050286,
      "grad_norm": 0.03397843614220619,
      "learning_rate": 1.892060104916867e-05,
      "loss": 0.0041,
      "step": 2660
    },
    {
      "epoch": 0.7596287207937693,
      "grad_norm": 0.039120275527238846,
      "learning_rate": 1.899173112830088e-05,
      "loss": 0.0042,
      "step": 2670
    },
    {
      "epoch": 0.76247377218251,
      "grad_norm": 0.04069869592785835,
      "learning_rate": 1.9062861207433093e-05,
      "loss": 0.0044,
      "step": 2680
    },
    {
      "epoch": 0.7653188235712508,
      "grad_norm": 0.03612830862402916,
      "learning_rate": 1.913399128656531e-05,
      "loss": 0.0039,
      "step": 2690
    },
    {
      "epoch": 0.7681638749599915,
      "grad_norm": 0.034753765910863876,
      "learning_rate": 1.920512136569752e-05,
      "loss": 0.0037,
      "step": 2700
    },
    {
      "epoch": 0.7710089263487322,
      "grad_norm": 0.05360863357782364,
      "learning_rate": 1.9276251444829733e-05,
      "loss": 0.0044,
      "step": 2710
    },
    {
      "epoch": 0.7738539777374729,
      "grad_norm": 0.04032083973288536,
      "learning_rate": 1.934738152396195e-05,
      "loss": 0.0043,
      "step": 2720
    },
    {
      "epoch": 0.7766990291262136,
      "grad_norm": 0.0377604104578495,
      "learning_rate": 1.9418511603094157e-05,
      "loss": 0.0042,
      "step": 2730
    },
    {
      "epoch": 0.7795440805149543,
      "grad_norm": 0.03419530391693115,
      "learning_rate": 1.9489641682226373e-05,
      "loss": 0.0041,
      "step": 2740
    },
    {
      "epoch": 0.782389131903695,
      "grad_norm": 0.040193505585193634,
      "learning_rate": 1.9560771761358585e-05,
      "loss": 0.0039,
      "step": 2750
    },
    {
      "epoch": 0.782389131903695,
      "eval_loss": 0.038744423538446426,
      "eval_runtime": 9.2929,
      "eval_samples_per_second": 161.414,
      "eval_steps_per_second": 10.115,
      "eval_sts_dev_pearson_cosine": 0.8299324608581861,
      "eval_sts_dev_pearson_dot": 0.7176863363076469,
      "eval_sts_dev_pearson_euclidean": 0.8182959597932262,
      "eval_sts_dev_pearson_manhattan": 0.8182320853696063,
      "eval_sts_dev_pearson_max": 0.8299324608581861,
      "eval_sts_dev_spearman_cosine": 0.8375751383739057,
      "eval_sts_dev_spearman_dot": 0.702295742543807,
      "eval_sts_dev_spearman_euclidean": 0.8274009374359347,
      "eval_sts_dev_spearman_manhattan": 0.8284301537034146,
      "eval_sts_dev_spearman_max": 0.8375751383739057,
      "step": 2750
    },
    {
      "epoch": 0.7852341832924358,
      "grad_norm": 0.0465560108423233,
      "learning_rate": 1.96319018404908e-05,
      "loss": 0.0047,
      "step": 2760
    },
    {
      "epoch": 0.7880792346811765,
      "grad_norm": 0.04297973960638046,
      "learning_rate": 1.9703031919623013e-05,
      "loss": 0.004,
      "step": 2770
    },
    {
      "epoch": 0.7909242860699172,
      "grad_norm": 0.03678404539823532,
      "learning_rate": 1.9774161998755225e-05,
      "loss": 0.0039,
      "step": 2780
    },
    {
      "epoch": 0.7937693374586579,
      "grad_norm": 0.05512017384171486,
      "learning_rate": 1.984529207788744e-05,
      "loss": 0.0039,
      "step": 2790
    },
    {
      "epoch": 0.7966143888473985,
      "grad_norm": 0.03251376003026962,
      "learning_rate": 1.991642215701965e-05,
      "loss": 0.0039,
      "step": 2800
    },
    {
      "epoch": 0.7994594402361392,
      "grad_norm": 0.04584107547998428,
      "learning_rate": 1.9987552236151864e-05,
      "loss": 0.0039,
      "step": 2810
    },
    {
      "epoch": 0.8023044916248799,
      "grad_norm": 0.03864232823252678,
      "learning_rate": 2.0058682315284076e-05,
      "loss": 0.0039,
      "step": 2820
    },
    {
      "epoch": 0.8051495430136207,
      "grad_norm": 0.038527827709913254,
      "learning_rate": 2.0129812394416292e-05,
      "loss": 0.0041,
      "step": 2830
    },
    {
      "epoch": 0.8079945944023614,
      "grad_norm": 0.02851305902004242,
      "learning_rate": 2.0200942473548504e-05,
      "loss": 0.0037,
      "step": 2840
    },
    {
      "epoch": 0.8108396457911021,
      "grad_norm": 0.02903963066637516,
      "learning_rate": 2.0272072552680716e-05,
      "loss": 0.0044,
      "step": 2850
    },
    {
      "epoch": 0.8136846971798428,
      "grad_norm": 0.03449387475848198,
      "learning_rate": 2.034320263181293e-05,
      "loss": 0.0043,
      "step": 2860
    },
    {
      "epoch": 0.8165297485685835,
      "grad_norm": 0.03411369025707245,
      "learning_rate": 2.041433271094514e-05,
      "loss": 0.0041,
      "step": 2870
    },
    {
      "epoch": 0.8193747999573242,
      "grad_norm": 0.040192630141973495,
      "learning_rate": 2.0485462790077356e-05,
      "loss": 0.0043,
      "step": 2880
    },
    {
      "epoch": 0.8222198513460649,
      "grad_norm": 0.031003862619400024,
      "learning_rate": 2.0556592869209568e-05,
      "loss": 0.0039,
      "step": 2890
    },
    {
      "epoch": 0.8250649027348056,
      "grad_norm": 0.04759204015135765,
      "learning_rate": 2.062772294834178e-05,
      "loss": 0.0041,
      "step": 2900
    },
    {
      "epoch": 0.8279099541235464,
      "grad_norm": 0.036447394639253616,
      "learning_rate": 2.0698853027473996e-05,
      "loss": 0.0044,
      "step": 2910
    },
    {
      "epoch": 0.8307550055122871,
      "grad_norm": 0.04358125478029251,
      "learning_rate": 2.0769983106606208e-05,
      "loss": 0.004,
      "step": 2920
    },
    {
      "epoch": 0.8336000569010278,
      "grad_norm": 0.038935497403144836,
      "learning_rate": 2.0841113185738423e-05,
      "loss": 0.0042,
      "step": 2930
    },
    {
      "epoch": 0.8364451082897685,
      "grad_norm": 0.03385254368185997,
      "learning_rate": 2.0912243264870632e-05,
      "loss": 0.0039,
      "step": 2940
    },
    {
      "epoch": 0.8392901596785092,
      "grad_norm": 0.030839361250400543,
      "learning_rate": 2.0983373344002847e-05,
      "loss": 0.004,
      "step": 2950
    },
    {
      "epoch": 0.8421352110672499,
      "grad_norm": 0.03932899981737137,
      "learning_rate": 2.105450342313506e-05,
      "loss": 0.0042,
      "step": 2960
    },
    {
      "epoch": 0.8449802624559906,
      "grad_norm": 0.04810210317373276,
      "learning_rate": 2.112563350226727e-05,
      "loss": 0.004,
      "step": 2970
    },
    {
      "epoch": 0.8478253138447314,
      "grad_norm": 0.03614366054534912,
      "learning_rate": 2.1196763581399487e-05,
      "loss": 0.0039,
      "step": 2980
    },
    {
      "epoch": 0.8506703652334721,
      "grad_norm": 0.03652822598814964,
      "learning_rate": 2.12678936605317e-05,
      "loss": 0.0037,
      "step": 2990
    },
    {
      "epoch": 0.8535154166222128,
      "grad_norm": 0.04175693169236183,
      "learning_rate": 2.1339023739663915e-05,
      "loss": 0.0039,
      "step": 3000
    },
    {
      "epoch": 0.8535154166222128,
      "eval_loss": 0.038587357848882675,
      "eval_runtime": 9.2854,
      "eval_samples_per_second": 161.545,
      "eval_steps_per_second": 10.123,
      "eval_sts_dev_pearson_cosine": 0.8307702264806358,
      "eval_sts_dev_pearson_dot": 0.7156790570711026,
      "eval_sts_dev_pearson_euclidean": 0.819779764199181,
      "eval_sts_dev_pearson_manhattan": 0.8197553048460411,
      "eval_sts_dev_pearson_max": 0.8307702264806358,
      "eval_sts_dev_spearman_cosine": 0.8386149894761288,
      "eval_sts_dev_spearman_dot": 0.7013839487919926,
      "eval_sts_dev_spearman_euclidean": 0.8286781992701565,
      "eval_sts_dev_spearman_manhattan": 0.8296307452835905,
      "eval_sts_dev_spearman_max": 0.8386149894761288,
      "step": 3000
    },
    {
      "epoch": 0.8563604680109534,
      "grad_norm": 0.035189032554626465,
      "learning_rate": 2.1410153818796123e-05,
      "loss": 0.0041,
      "step": 3010
    },
    {
      "epoch": 0.8592055193996941,
      "grad_norm": 0.030665524303913116,
      "learning_rate": 2.148128389792834e-05,
      "loss": 0.0043,
      "step": 3020
    },
    {
      "epoch": 0.8620505707884348,
      "grad_norm": 0.03555646166205406,
      "learning_rate": 2.155241397706055e-05,
      "loss": 0.0041,
      "step": 3030
    },
    {
      "epoch": 0.8648956221771755,
      "grad_norm": 0.04289074242115021,
      "learning_rate": 2.1623544056192763e-05,
      "loss": 0.0041,
      "step": 3040
    },
    {
      "epoch": 0.8677406735659163,
      "grad_norm": 0.03874215856194496,
      "learning_rate": 2.169467413532498e-05,
      "loss": 0.0043,
      "step": 3050
    },
    {
      "epoch": 0.870585724954657,
      "grad_norm": 0.040797311812639236,
      "learning_rate": 2.176580421445719e-05,
      "loss": 0.0042,
      "step": 3060
    },
    {
      "epoch": 0.8734307763433977,
      "grad_norm": 0.043382417410612106,
      "learning_rate": 2.1836934293589406e-05,
      "loss": 0.0039,
      "step": 3070
    },
    {
      "epoch": 0.8762758277321384,
      "grad_norm": 0.03589191287755966,
      "learning_rate": 2.1908064372721615e-05,
      "loss": 0.004,
      "step": 3080
    },
    {
      "epoch": 0.8791208791208791,
      "grad_norm": 0.030675871297717094,
      "learning_rate": 2.197919445185383e-05,
      "loss": 0.0039,
      "step": 3090
    },
    {
      "epoch": 0.8819659305096198,
      "grad_norm": 0.03458893299102783,
      "learning_rate": 2.2050324530986042e-05,
      "loss": 0.0039,
      "step": 3100
    },
    {
      "epoch": 0.8848109818983605,
      "grad_norm": 0.03687838092446327,
      "learning_rate": 2.2121454610118254e-05,
      "loss": 0.004,
      "step": 3110
    },
    {
      "epoch": 0.8876560332871013,
      "grad_norm": 0.03154761716723442,
      "learning_rate": 2.219258468925047e-05,
      "loss": 0.0039,
      "step": 3120
    },
    {
      "epoch": 0.890501084675842,
      "grad_norm": 0.036181699484586716,
      "learning_rate": 2.2263714768382682e-05,
      "loss": 0.0038,
      "step": 3130
    },
    {
      "epoch": 0.8933461360645827,
      "grad_norm": 0.036393746733665466,
      "learning_rate": 2.2334844847514898e-05,
      "loss": 0.0036,
      "step": 3140
    },
    {
      "epoch": 0.8961911874533234,
      "grad_norm": 0.04613763466477394,
      "learning_rate": 2.2405974926647106e-05,
      "loss": 0.0039,
      "step": 3150
    },
    {
      "epoch": 0.8990362388420641,
      "grad_norm": 0.028627606108784676,
      "learning_rate": 2.2477105005779322e-05,
      "loss": 0.0039,
      "step": 3160
    },
    {
      "epoch": 0.9018812902308048,
      "grad_norm": 0.03881096839904785,
      "learning_rate": 2.2548235084911534e-05,
      "loss": 0.0038,
      "step": 3170
    },
    {
      "epoch": 0.9047263416195455,
      "grad_norm": 0.030927816405892372,
      "learning_rate": 2.2619365164043746e-05,
      "loss": 0.0039,
      "step": 3180
    },
    {
      "epoch": 0.9075713930082863,
      "grad_norm": 0.033624544739723206,
      "learning_rate": 2.269049524317596e-05,
      "loss": 0.0041,
      "step": 3190
    },
    {
      "epoch": 0.910416444397027,
      "grad_norm": 0.03509572893381119,
      "learning_rate": 2.276162532230817e-05,
      "loss": 0.004,
      "step": 3200
    },
    {
      "epoch": 0.9132614957857677,
      "grad_norm": 0.03826339542865753,
      "learning_rate": 2.283275540144039e-05,
      "loss": 0.0041,
      "step": 3210
    },
    {
      "epoch": 0.9161065471745083,
      "grad_norm": 0.033389002084732056,
      "learning_rate": 2.2903885480572598e-05,
      "loss": 0.0042,
      "step": 3220
    },
    {
      "epoch": 0.918951598563249,
      "grad_norm": 0.03484668210148811,
      "learning_rate": 2.2975015559704813e-05,
      "loss": 0.004,
      "step": 3230
    },
    {
      "epoch": 0.9217966499519897,
      "grad_norm": 0.0346749946475029,
      "learning_rate": 2.3046145638837025e-05,
      "loss": 0.0041,
      "step": 3240
    },
    {
      "epoch": 0.9246417013407304,
      "grad_norm": 0.031990326941013336,
      "learning_rate": 2.3117275717969237e-05,
      "loss": 0.0041,
      "step": 3250
    },
    {
      "epoch": 0.9246417013407304,
      "eval_loss": 0.04199736937880516,
      "eval_runtime": 9.3223,
      "eval_samples_per_second": 160.904,
      "eval_steps_per_second": 10.083,
      "eval_sts_dev_pearson_cosine": 0.8329326037706698,
      "eval_sts_dev_pearson_dot": 0.7244653232060949,
      "eval_sts_dev_pearson_euclidean": 0.8208614363276345,
      "eval_sts_dev_pearson_manhattan": 0.8208271942763237,
      "eval_sts_dev_pearson_max": 0.8329326037706698,
      "eval_sts_dev_spearman_cosine": 0.8408210792535609,
      "eval_sts_dev_spearman_dot": 0.7059199525474262,
      "eval_sts_dev_spearman_euclidean": 0.8293341205092732,
      "eval_sts_dev_spearman_manhattan": 0.8305099059292741,
      "eval_sts_dev_spearman_max": 0.8408210792535609,
      "step": 3250
    },
    {
      "epoch": 0.9274867527294712,
      "grad_norm": 0.04185841232538223,
      "learning_rate": 2.3188405797101453e-05,
      "loss": 0.0041,
      "step": 3260
    },
    {
      "epoch": 0.9303318041182119,
      "grad_norm": 0.035076793283224106,
      "learning_rate": 2.325953587623366e-05,
      "loss": 0.004,
      "step": 3270
    },
    {
      "epoch": 0.9331768555069526,
      "grad_norm": 0.038307491689920425,
      "learning_rate": 2.3330665955365877e-05,
      "loss": 0.0042,
      "step": 3280
    },
    {
      "epoch": 0.9360219068956933,
      "grad_norm": 0.03905055299401283,
      "learning_rate": 2.340179603449809e-05,
      "loss": 0.004,
      "step": 3290
    },
    {
      "epoch": 0.938866958284434,
      "grad_norm": 0.03548280894756317,
      "learning_rate": 2.3472926113630305e-05,
      "loss": 0.0037,
      "step": 3300
    },
    {
      "epoch": 0.9417120096731747,
      "grad_norm": 0.031215885654091835,
      "learning_rate": 2.3544056192762517e-05,
      "loss": 0.0038,
      "step": 3310
    },
    {
      "epoch": 0.9445570610619154,
      "grad_norm": 0.03097504749894142,
      "learning_rate": 2.361518627189473e-05,
      "loss": 0.0039,
      "step": 3320
    },
    {
      "epoch": 0.9474021124506561,
      "grad_norm": 0.027599211782217026,
      "learning_rate": 2.3686316351026944e-05,
      "loss": 0.004,
      "step": 3330
    },
    {
      "epoch": 0.9502471638393969,
      "grad_norm": 0.028425293043255806,
      "learning_rate": 2.3757446430159153e-05,
      "loss": 0.0037,
      "step": 3340
    },
    {
      "epoch": 0.9530922152281376,
      "grad_norm": 0.048545658588409424,
      "learning_rate": 2.382857650929137e-05,
      "loss": 0.0038,
      "step": 3350
    },
    {
      "epoch": 0.9559372666168783,
      "grad_norm": 0.031001316383481026,
      "learning_rate": 2.389970658842358e-05,
      "loss": 0.0037,
      "step": 3360
    },
    {
      "epoch": 0.958782318005619,
      "grad_norm": 0.032509058713912964,
      "learning_rate": 2.3970836667555793e-05,
      "loss": 0.0042,
      "step": 3370
    },
    {
      "epoch": 0.9616273693943597,
      "grad_norm": 0.044801611453294754,
      "learning_rate": 2.4041966746688008e-05,
      "loss": 0.0042,
      "step": 3380
    },
    {
      "epoch": 0.9644724207831004,
      "grad_norm": 0.03758518770337105,
      "learning_rate": 2.411309682582022e-05,
      "loss": 0.0042,
      "step": 3390
    },
    {
      "epoch": 0.967317472171841,
      "grad_norm": 0.0497860424220562,
      "learning_rate": 2.4184226904952436e-05,
      "loss": 0.0037,
      "step": 3400
    },
    {
      "epoch": 0.9701625235605819,
      "grad_norm": 0.029705649241805077,
      "learning_rate": 2.4255356984084645e-05,
      "loss": 0.0038,
      "step": 3410
    },
    {
      "epoch": 0.9730075749493226,
      "grad_norm": 0.034794483333826065,
      "learning_rate": 2.432648706321686e-05,
      "loss": 0.0039,
      "step": 3420
    },
    {
      "epoch": 0.9758526263380632,
      "grad_norm": 0.03679205849766731,
      "learning_rate": 2.4397617142349072e-05,
      "loss": 0.0038,
      "step": 3430
    },
    {
      "epoch": 0.9786976777268039,
      "grad_norm": 0.03937937691807747,
      "learning_rate": 2.4468747221481284e-05,
      "loss": 0.0041,
      "step": 3440
    },
    {
      "epoch": 0.9815427291155446,
      "grad_norm": 0.0480770580470562,
      "learning_rate": 2.45398773006135e-05,
      "loss": 0.004,
      "step": 3450
    },
    {
      "epoch": 0.9843877805042853,
      "grad_norm": 0.0545036643743515,
      "learning_rate": 2.4611007379745712e-05,
      "loss": 0.0039,
      "step": 3460
    },
    {
      "epoch": 0.987232831893026,
      "grad_norm": 0.02787315472960472,
      "learning_rate": 2.4682137458877927e-05,
      "loss": 0.0036,
      "step": 3470
    },
    {
      "epoch": 0.9900778832817668,
      "grad_norm": 0.026936234906315804,
      "learning_rate": 2.4753267538010136e-05,
      "loss": 0.0037,
      "step": 3480
    },
    {
      "epoch": 0.9929229346705075,
      "grad_norm": 0.04028989002108574,
      "learning_rate": 2.482439761714235e-05,
      "loss": 0.0039,
      "step": 3490
    },
    {
      "epoch": 0.9957679860592482,
      "grad_norm": 0.036293208599090576,
      "learning_rate": 2.4895527696274564e-05,
      "loss": 0.0036,
      "step": 3500
    },
    {
      "epoch": 0.9957679860592482,
      "eval_loss": 0.04033274203538895,
      "eval_runtime": 9.5163,
      "eval_samples_per_second": 157.625,
      "eval_steps_per_second": 9.878,
      "eval_sts_dev_pearson_cosine": 0.8319192467999278,
      "eval_sts_dev_pearson_dot": 0.7234705763545461,
      "eval_sts_dev_pearson_euclidean": 0.8198226408074469,
      "eval_sts_dev_pearson_manhattan": 0.8199114649719743,
      "eval_sts_dev_pearson_max": 0.8319192467999278,
      "eval_sts_dev_spearman_cosine": 0.8396159085327265,
      "eval_sts_dev_spearman_dot": 0.7094397491074207,
      "eval_sts_dev_spearman_euclidean": 0.8285927601564604,
      "eval_sts_dev_spearman_manhattan": 0.8295556212626334,
      "eval_sts_dev_spearman_max": 0.8396159085327265,
      "step": 3500
    }
  ],
  "logging_steps": 10,
  "max_steps": 7028,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 3500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}