{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "eval_steps": 250,
  "global_step": 8536,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004686035613870665,
      "grad_norm": 0.5978041887283325,
      "learning_rate": 1.999707122774133e-05,
      "loss": 3.4332,
      "step": 10
    },
    {
      "epoch": 0.00937207122774133,
      "grad_norm": 1.5130422115325928,
      "learning_rate": 1.9994142455482664e-05,
      "loss": 3.2454,
      "step": 20
    },
    {
      "epoch": 0.014058106841611996,
      "grad_norm": 1.607094168663025,
      "learning_rate": 1.9991213683223994e-05,
      "loss": 2.9102,
      "step": 30
    },
    {
      "epoch": 0.01874414245548266,
      "grad_norm": 2.6665945053100586,
      "learning_rate": 1.9988284910965326e-05,
      "loss": 2.7066,
      "step": 40
    },
    {
      "epoch": 0.023430178069353328,
      "grad_norm": 3.212167978286743,
      "learning_rate": 1.9985356138706656e-05,
      "loss": 2.5895,
      "step": 50
    },
    {
      "epoch": 0.028116213683223992,
      "grad_norm": 3.8364155292510986,
      "learning_rate": 1.998242736644799e-05,
      "loss": 2.4215,
      "step": 60
    },
    {
      "epoch": 0.03280224929709466,
      "grad_norm": 3.560389280319214,
      "learning_rate": 1.9979498594189318e-05,
      "loss": 2.0972,
      "step": 70
    },
    {
      "epoch": 0.03748828491096532,
      "grad_norm": 4.126266956329346,
      "learning_rate": 1.9976569821930648e-05,
      "loss": 1.8428,
      "step": 80
    },
    {
      "epoch": 0.04217432052483599,
      "grad_norm": 4.506312370300293,
      "learning_rate": 1.997364104967198e-05,
      "loss": 1.5853,
      "step": 90
    },
    {
      "epoch": 0.046860356138706656,
      "grad_norm": 4.499500751495361,
      "learning_rate": 1.997071227741331e-05,
      "loss": 1.4429,
      "step": 100
    },
    {
      "epoch": 0.05154639175257732,
      "grad_norm": 4.746804237365723,
      "learning_rate": 1.996778350515464e-05,
      "loss": 1.3275,
      "step": 110
    },
    {
      "epoch": 0.056232427366447985,
      "grad_norm": 4.36592435836792,
      "learning_rate": 1.996485473289597e-05,
      "loss": 1.0965,
      "step": 120
    },
    {
      "epoch": 0.06091846298031865,
      "grad_norm": 4.177589416503906,
      "learning_rate": 1.9961925960637302e-05,
      "loss": 1.0654,
      "step": 130
    },
    {
      "epoch": 0.06560449859418932,
      "grad_norm": 4.377724647521973,
      "learning_rate": 1.995899718837863e-05,
      "loss": 0.9687,
      "step": 140
    },
    {
      "epoch": 0.07029053420805999,
      "grad_norm": 3.9814295768737793,
      "learning_rate": 1.9956068416119964e-05,
      "loss": 1.043,
      "step": 150
    },
    {
      "epoch": 0.07497656982193064,
      "grad_norm": 3.938041925430298,
      "learning_rate": 1.9953139643861294e-05,
      "loss": 0.9639,
      "step": 160
    },
    {
      "epoch": 0.07966260543580131,
      "grad_norm": 4.323759078979492,
      "learning_rate": 1.9950210871602627e-05,
      "loss": 0.9344,
      "step": 170
    },
    {
      "epoch": 0.08434864104967198,
      "grad_norm": 4.037902355194092,
      "learning_rate": 1.9947282099343956e-05,
      "loss": 0.8302,
      "step": 180
    },
    {
      "epoch": 0.08903467666354264,
      "grad_norm": 3.9691343307495117,
      "learning_rate": 1.994435332708529e-05,
      "loss": 0.8573,
      "step": 190
    },
    {
      "epoch": 0.09372071227741331,
      "grad_norm": 3.8372201919555664,
      "learning_rate": 1.994142455482662e-05,
      "loss": 0.808,
      "step": 200
    },
    {
      "epoch": 0.09840674789128398,
      "grad_norm": 4.224605083465576,
      "learning_rate": 1.9938495782567948e-05,
      "loss": 0.8942,
      "step": 210
    },
    {
      "epoch": 0.10309278350515463,
      "grad_norm": 3.7245891094207764,
      "learning_rate": 1.993556701030928e-05,
      "loss": 0.8321,
      "step": 220
    },
    {
      "epoch": 0.1077788191190253,
      "grad_norm": 4.344135761260986,
      "learning_rate": 1.993263823805061e-05,
      "loss": 0.8035,
      "step": 230
    },
    {
      "epoch": 0.11246485473289597,
      "grad_norm": 3.6320858001708984,
      "learning_rate": 1.9929709465791943e-05,
      "loss": 0.723,
      "step": 240
    },
    {
      "epoch": 0.11715089034676664,
      "grad_norm": 2.934122085571289,
      "learning_rate": 1.9926780693533273e-05,
      "loss": 0.761,
      "step": 250
    },
    {
      "epoch": 0.11715089034676664,
      "eval_loss": 0.13966944813728333,
      "eval_pearson_cosine": 0.7191493566389795,
      "eval_pearson_dot": 0.43422507697410495,
      "eval_pearson_euclidean": 0.7135360350736899,
      "eval_pearson_manhattan": 0.7129270627309872,
      "eval_runtime": 3.3956,
      "eval_samples_per_second": 441.749,
      "eval_spearman_cosine": 0.7365500082397669,
      "eval_spearman_dot": 0.43017280395518565,
      "eval_spearman_euclidean": 0.7209662281529704,
      "eval_spearman_manhattan": 0.720539010106817,
      "eval_steps_per_second": 27.683,
      "step": 250
    },
    {
      "epoch": 0.1218369259606373,
      "grad_norm": 3.1349332332611084,
      "learning_rate": 1.9923851921274602e-05,
      "loss": 0.7916,
      "step": 260
    },
    {
      "epoch": 0.12652296157450796,
      "grad_norm": 4.0211286544799805,
      "learning_rate": 1.9920923149015935e-05,
      "loss": 0.7147,
      "step": 270
    },
    {
      "epoch": 0.13120899718837864,
      "grad_norm": 3.262589693069458,
      "learning_rate": 1.9917994376757265e-05,
      "loss": 0.7689,
      "step": 280
    },
    {
      "epoch": 0.1358950328022493,
      "grad_norm": 4.0925397872924805,
      "learning_rate": 1.9915065604498594e-05,
      "loss": 0.7556,
      "step": 290
    },
    {
      "epoch": 0.14058106841611998,
      "grad_norm": 3.7041923999786377,
      "learning_rate": 1.9912136832239924e-05,
      "loss": 0.7239,
      "step": 300
    },
    {
      "epoch": 0.14526710402999063,
      "grad_norm": 3.712703227996826,
      "learning_rate": 1.9909208059981257e-05,
      "loss": 0.6685,
      "step": 310
    },
    {
      "epoch": 0.14995313964386128,
      "grad_norm": 3.6240854263305664,
      "learning_rate": 1.9906279287722586e-05,
      "loss": 0.7263,
      "step": 320
    },
    {
      "epoch": 0.15463917525773196,
      "grad_norm": 4.013660907745361,
      "learning_rate": 1.990335051546392e-05,
      "loss": 0.7287,
      "step": 330
    },
    {
      "epoch": 0.15932521087160262,
      "grad_norm": 2.8780667781829834,
      "learning_rate": 1.990042174320525e-05,
      "loss": 0.6709,
      "step": 340
    },
    {
      "epoch": 0.1640112464854733,
      "grad_norm": 3.035186290740967,
      "learning_rate": 1.989749297094658e-05,
      "loss": 0.6977,
      "step": 350
    },
    {
      "epoch": 0.16869728209934395,
      "grad_norm": 3.433403491973877,
      "learning_rate": 1.989456419868791e-05,
      "loss": 0.6656,
      "step": 360
    },
    {
      "epoch": 0.1733833177132146,
      "grad_norm": 3.8357644081115723,
      "learning_rate": 1.9891635426429244e-05,
      "loss": 0.6192,
      "step": 370
    },
    {
      "epoch": 0.1780693533270853,
      "grad_norm": 3.506263494491577,
      "learning_rate": 1.9888706654170573e-05,
      "loss": 0.6516,
      "step": 380
    },
    {
      "epoch": 0.18275538894095594,
      "grad_norm": 2.839836835861206,
      "learning_rate": 1.9885777881911906e-05,
      "loss": 0.6056,
      "step": 390
    },
    {
      "epoch": 0.18744142455482662,
      "grad_norm": 3.2694239616394043,
      "learning_rate": 1.9882849109653236e-05,
      "loss": 0.6753,
      "step": 400
    },
    {
      "epoch": 0.19212746016869728,
      "grad_norm": 3.5731680393218994,
      "learning_rate": 1.9879920337394565e-05,
      "loss": 0.6848,
      "step": 410
    },
    {
      "epoch": 0.19681349578256796,
      "grad_norm": 2.8836023807525635,
      "learning_rate": 1.9876991565135898e-05,
      "loss": 0.659,
      "step": 420
    },
    {
      "epoch": 0.2014995313964386,
      "grad_norm": 3.5604217052459717,
      "learning_rate": 1.9874062792877228e-05,
      "loss": 0.6745,
      "step": 430
    },
    {
      "epoch": 0.20618556701030927,
      "grad_norm": 2.7834393978118896,
      "learning_rate": 1.9871134020618557e-05,
      "loss": 0.623,
      "step": 440
    },
    {
      "epoch": 0.21087160262417995,
      "grad_norm": 3.5130224227905273,
      "learning_rate": 1.986820524835989e-05,
      "loss": 0.579,
      "step": 450
    },
    {
      "epoch": 0.2155576382380506,
      "grad_norm": 2.9537723064422607,
      "learning_rate": 1.986527647610122e-05,
      "loss": 0.6042,
      "step": 460
    },
    {
      "epoch": 0.22024367385192128,
      "grad_norm": 2.926415205001831,
      "learning_rate": 1.986234770384255e-05,
      "loss": 0.5785,
      "step": 470
    },
    {
      "epoch": 0.22492970946579194,
      "grad_norm": 4.53303861618042,
      "learning_rate": 1.9859418931583882e-05,
      "loss": 0.5957,
      "step": 480
    },
    {
      "epoch": 0.2296157450796626,
      "grad_norm": 2.5960335731506348,
      "learning_rate": 1.985649015932521e-05,
      "loss": 0.6223,
      "step": 490
    },
    {
      "epoch": 0.23430178069353327,
      "grad_norm": 2.509232997894287,
      "learning_rate": 1.985356138706654e-05,
      "loss": 0.6275,
      "step": 500
    },
    {
      "epoch": 0.23430178069353327,
      "eval_loss": 0.12402218580245972,
      "eval_pearson_cosine": 0.7535085617332911,
      "eval_pearson_dot": 0.4526570980382658,
      "eval_pearson_euclidean": 0.7442016683051946,
      "eval_pearson_manhattan": 0.7442320131099294,
      "eval_runtime": 3.5327,
      "eval_samples_per_second": 424.602,
      "eval_spearman_cosine": 0.7638158285362802,
      "eval_spearman_dot": 0.4533334110281352,
      "eval_spearman_euclidean": 0.7505934110060137,
      "eval_spearman_manhattan": 0.7505444222182343,
      "eval_steps_per_second": 26.608,
      "step": 500
    },
    {
      "epoch": 0.23898781630740393,
      "grad_norm": 3.2064850330352783,
      "learning_rate": 1.9850632614807874e-05,
      "loss": 0.6257,
      "step": 510
    },
    {
      "epoch": 0.2436738519212746,
      "grad_norm": 3.235630512237549,
      "learning_rate": 1.9847703842549203e-05,
      "loss": 0.6069,
      "step": 520
    },
    {
      "epoch": 0.24835988753514526,
      "grad_norm": 2.8067846298217773,
      "learning_rate": 1.9844775070290536e-05,
      "loss": 0.6137,
      "step": 530
    },
    {
      "epoch": 0.2530459231490159,
      "grad_norm": 3.6333608627319336,
      "learning_rate": 1.9841846298031866e-05,
      "loss": 0.6111,
      "step": 540
    },
    {
      "epoch": 0.25773195876288657,
      "grad_norm": 2.410837411880493,
      "learning_rate": 1.98389175257732e-05,
      "loss": 0.5463,
      "step": 550
    },
    {
      "epoch": 0.2624179943767573,
      "grad_norm": 3.0617260932922363,
      "learning_rate": 1.9835988753514528e-05,
      "loss": 0.5571,
      "step": 560
    },
    {
      "epoch": 0.26710402999062793,
      "grad_norm": 2.576580762863159,
      "learning_rate": 1.983305998125586e-05,
      "loss": 0.5428,
      "step": 570
    },
    {
      "epoch": 0.2717900656044986,
      "grad_norm": 3.412797451019287,
      "learning_rate": 1.983013120899719e-05,
      "loss": 0.5541,
      "step": 580
    },
    {
      "epoch": 0.27647610121836924,
      "grad_norm": 2.929755210876465,
      "learning_rate": 1.9827202436738523e-05,
      "loss": 0.5941,
      "step": 590
    },
    {
      "epoch": 0.28116213683223995,
      "grad_norm": 2.80749773979187,
      "learning_rate": 1.9824273664479853e-05,
      "loss": 0.5702,
      "step": 600
    },
    {
      "epoch": 0.2858481724461106,
      "grad_norm": 2.91896390914917,
      "learning_rate": 1.9821344892221182e-05,
      "loss": 0.5971,
      "step": 610
    },
    {
      "epoch": 0.29053420805998126,
      "grad_norm": 2.754328727722168,
      "learning_rate": 1.9818416119962512e-05,
      "loss": 0.5544,
      "step": 620
    },
    {
      "epoch": 0.2952202436738519,
      "grad_norm": 3.4075613021850586,
      "learning_rate": 1.9815487347703845e-05,
      "loss": 0.5981,
      "step": 630
    },
    {
      "epoch": 0.29990627928772257,
      "grad_norm": 2.6344642639160156,
      "learning_rate": 1.9812558575445174e-05,
      "loss": 0.5539,
      "step": 640
    },
    {
      "epoch": 0.3045923149015933,
      "grad_norm": 2.417914867401123,
      "learning_rate": 1.9809629803186504e-05,
      "loss": 0.5078,
      "step": 650
    },
    {
      "epoch": 0.30927835051546393,
      "grad_norm": 2.52506685256958,
      "learning_rate": 1.9806701030927837e-05,
      "loss": 0.532,
      "step": 660
    },
    {
      "epoch": 0.3139643861293346,
      "grad_norm": 2.830923557281494,
      "learning_rate": 1.9803772258669166e-05,
      "loss": 0.5537,
      "step": 670
    },
    {
      "epoch": 0.31865042174320524,
      "grad_norm": 3.1638379096984863,
      "learning_rate": 1.98008434864105e-05,
      "loss": 0.5375,
      "step": 680
    },
    {
      "epoch": 0.3233364573570759,
      "grad_norm": 3.447112798690796,
      "learning_rate": 1.979791471415183e-05,
      "loss": 0.5755,
      "step": 690
    },
    {
      "epoch": 0.3280224929709466,
      "grad_norm": 2.3407933712005615,
      "learning_rate": 1.9794985941893158e-05,
      "loss": 0.514,
      "step": 700
    },
    {
      "epoch": 0.33270852858481725,
      "grad_norm": 3.226551055908203,
      "learning_rate": 1.979205716963449e-05,
      "loss": 0.5167,
      "step": 710
    },
    {
      "epoch": 0.3373945641986879,
      "grad_norm": 3.1462602615356445,
      "learning_rate": 1.978912839737582e-05,
      "loss": 0.5431,
      "step": 720
    },
    {
      "epoch": 0.34208059981255856,
      "grad_norm": 3.051692008972168,
      "learning_rate": 1.9786199625117153e-05,
      "loss": 0.5129,
      "step": 730
    },
    {
      "epoch": 0.3467666354264292,
      "grad_norm": 2.5202085971832275,
      "learning_rate": 1.9783270852858483e-05,
      "loss": 0.5752,
      "step": 740
    },
    {
      "epoch": 0.3514526710402999,
      "grad_norm": 2.6891393661499023,
      "learning_rate": 1.9780342080599816e-05,
      "loss": 0.5326,
      "step": 750
    },
    {
      "epoch": 0.3514526710402999,
      "eval_loss": 0.11494184285402298,
      "eval_pearson_cosine": 0.7539853173929743,
      "eval_pearson_dot": 0.47863358738842976,
      "eval_pearson_euclidean": 0.7326912597509363,
      "eval_pearson_manhattan": 0.7320283236539638,
      "eval_runtime": 3.5674,
      "eval_samples_per_second": 420.478,
      "eval_spearman_cosine": 0.7697587773995457,
      "eval_spearman_dot": 0.47367550293168154,
      "eval_spearman_euclidean": 0.7466430705786936,
      "eval_spearman_manhattan": 0.7460682347775467,
      "eval_steps_per_second": 26.35,
      "step": 750
    },
    {
      "epoch": 0.3561387066541706,
      "grad_norm": 2.9754297733306885,
      "learning_rate": 1.9777413308341145e-05,
      "loss": 0.4959,
      "step": 760
    },
    {
      "epoch": 0.36082474226804123,
      "grad_norm": 3.2427656650543213,
      "learning_rate": 1.9774484536082478e-05,
      "loss": 0.539,
      "step": 770
    },
    {
      "epoch": 0.3655107778819119,
      "grad_norm": 2.6402335166931152,
      "learning_rate": 1.9771555763823808e-05,
      "loss": 0.5328,
      "step": 780
    },
    {
      "epoch": 0.3701968134957826,
      "grad_norm": 2.9217915534973145,
      "learning_rate": 1.9768626991565137e-05,
      "loss": 0.4895,
      "step": 790
    },
    {
      "epoch": 0.37488284910965325,
      "grad_norm": 2.363999128341675,
      "learning_rate": 1.976569821930647e-05,
      "loss": 0.4805,
      "step": 800
    },
    {
      "epoch": 0.3795688847235239,
      "grad_norm": 2.491255044937134,
      "learning_rate": 1.97627694470478e-05,
      "loss": 0.5281,
      "step": 810
    },
    {
      "epoch": 0.38425492033739456,
      "grad_norm": 2.595560312271118,
      "learning_rate": 1.975984067478913e-05,
      "loss": 0.5104,
      "step": 820
    },
    {
      "epoch": 0.3889409559512652,
      "grad_norm": 2.991326332092285,
      "learning_rate": 1.975691190253046e-05,
      "loss": 0.508,
      "step": 830
    },
    {
      "epoch": 0.3936269915651359,
      "grad_norm": 2.6440255641937256,
      "learning_rate": 1.975398313027179e-05,
      "loss": 0.5643,
      "step": 840
    },
    {
      "epoch": 0.3983130271790066,
      "grad_norm": 3.06538987159729,
      "learning_rate": 1.975105435801312e-05,
      "loss": 0.4944,
      "step": 850
    },
    {
      "epoch": 0.4029990627928772,
      "grad_norm": 2.751331329345703,
      "learning_rate": 1.9748125585754454e-05,
      "loss": 0.5215,
      "step": 860
    },
    {
      "epoch": 0.4076850984067479,
      "grad_norm": 3.2387125492095947,
      "learning_rate": 1.9745196813495783e-05,
      "loss": 0.5925,
      "step": 870
    },
    {
      "epoch": 0.41237113402061853,
      "grad_norm": 2.5455057621002197,
      "learning_rate": 1.9742268041237116e-05,
      "loss": 0.4956,
      "step": 880
    },
    {
      "epoch": 0.41705716963448924,
      "grad_norm": 2.864497423171997,
      "learning_rate": 1.9739339268978446e-05,
      "loss": 0.4855,
      "step": 890
    },
    {
      "epoch": 0.4217432052483599,
      "grad_norm": 2.6306967735290527,
      "learning_rate": 1.9736410496719775e-05,
      "loss": 0.4542,
      "step": 900
    },
    {
      "epoch": 0.42642924086223055,
      "grad_norm": 2.294090747833252,
      "learning_rate": 1.9733481724461108e-05,
      "loss": 0.4247,
      "step": 910
    },
    {
      "epoch": 0.4311152764761012,
      "grad_norm": 2.9401843547821045,
      "learning_rate": 1.9730552952202438e-05,
      "loss": 0.5219,
      "step": 920
    },
    {
      "epoch": 0.43580131208997186,
      "grad_norm": 2.5331194400787354,
      "learning_rate": 1.972762417994377e-05,
      "loss": 0.5193,
      "step": 930
    },
    {
      "epoch": 0.44048734770384257,
      "grad_norm": 3.265944719314575,
      "learning_rate": 1.97246954076851e-05,
      "loss": 0.4733,
      "step": 940
    },
    {
      "epoch": 0.4451733833177132,
      "grad_norm": 2.6586129665374756,
      "learning_rate": 1.9721766635426433e-05,
      "loss": 0.4939,
      "step": 950
    },
    {
      "epoch": 0.4498594189315839,
      "grad_norm": 2.126664638519287,
      "learning_rate": 1.9718837863167762e-05,
      "loss": 0.5149,
      "step": 960
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 2.8597347736358643,
      "learning_rate": 1.9715909090909092e-05,
      "loss": 0.5089,
      "step": 970
    },
    {
      "epoch": 0.4592314901593252,
      "grad_norm": 2.5802338123321533,
      "learning_rate": 1.9712980318650425e-05,
      "loss": 0.5264,
      "step": 980
    },
    {
      "epoch": 0.4639175257731959,
      "grad_norm": 2.4247639179229736,
      "learning_rate": 1.9710051546391754e-05,
      "loss": 0.5416,
      "step": 990
    },
    {
      "epoch": 0.46860356138706655,
      "grad_norm": 2.6614298820495605,
      "learning_rate": 1.9707122774133084e-05,
      "loss": 0.4917,
      "step": 1000
    },
    {
      "epoch": 0.46860356138706655,
      "eval_loss": 0.1028011292219162,
      "eval_pearson_cosine": 0.7630335129215418,
      "eval_pearson_dot": 0.5427640329363896,
      "eval_pearson_euclidean": 0.7394698860945113,
      "eval_pearson_manhattan": 0.7395035409540256,
      "eval_runtime": 3.2727,
      "eval_samples_per_second": 458.333,
      "eval_spearman_cosine": 0.7777749785163052,
      "eval_spearman_dot": 0.5403903388556195,
      "eval_spearman_euclidean": 0.7530551416243708,
      "eval_spearman_manhattan": 0.753178994867466,
      "eval_steps_per_second": 28.722,
      "step": 1000
    },
    {
      "epoch": 0.4732895970009372,
      "grad_norm": 2.8377857208251953,
      "learning_rate": 1.9704194001874417e-05,
      "loss": 0.4806,
      "step": 1010
    },
    {
      "epoch": 0.47797563261480785,
      "grad_norm": 2.3730361461639404,
      "learning_rate": 1.9701265229615746e-05,
      "loss": 0.4946,
      "step": 1020
    },
    {
      "epoch": 0.48266166822867856,
      "grad_norm": 3.101628541946411,
      "learning_rate": 1.9698336457357076e-05,
      "loss": 0.4958,
      "step": 1030
    },
    {
      "epoch": 0.4873477038425492,
      "grad_norm": 2.4200384616851807,
      "learning_rate": 1.969540768509841e-05,
      "loss": 0.5231,
      "step": 1040
    },
    {
      "epoch": 0.49203373945641987,
      "grad_norm": 2.9535088539123535,
      "learning_rate": 1.9692478912839738e-05,
      "loss": 0.4952,
      "step": 1050
    },
    {
      "epoch": 0.4967197750702905,
      "grad_norm": 2.3175110816955566,
      "learning_rate": 1.968955014058107e-05,
      "loss": 0.4845,
      "step": 1060
    },
    {
      "epoch": 0.5014058106841612,
      "grad_norm": 2.934502124786377,
      "learning_rate": 1.96866213683224e-05,
      "loss": 0.5229,
      "step": 1070
    },
    {
      "epoch": 0.5060918462980318,
      "grad_norm": 2.5961878299713135,
      "learning_rate": 1.9683692596063733e-05,
      "loss": 0.5111,
      "step": 1080
    },
    {
      "epoch": 0.5107778819119025,
      "grad_norm": 2.9093525409698486,
      "learning_rate": 1.9680763823805063e-05,
      "loss": 0.545,
      "step": 1090
    },
    {
      "epoch": 0.5154639175257731,
      "grad_norm": 2.733900547027588,
      "learning_rate": 1.9677835051546392e-05,
      "loss": 0.4589,
      "step": 1100
    },
    {
      "epoch": 0.5201499531396439,
      "grad_norm": 2.3905482292175293,
      "learning_rate": 1.9674906279287725e-05,
      "loss": 0.5197,
      "step": 1110
    },
    {
      "epoch": 0.5248359887535146,
      "grad_norm": 2.5557029247283936,
      "learning_rate": 1.9671977507029055e-05,
      "loss": 0.5089,
      "step": 1120
    },
    {
      "epoch": 0.5295220243673852,
      "grad_norm": 2.3789846897125244,
      "learning_rate": 1.9669048734770388e-05,
      "loss": 0.5373,
      "step": 1130
    },
    {
      "epoch": 0.5342080599812559,
      "grad_norm": 2.848998785018921,
      "learning_rate": 1.9666119962511717e-05,
      "loss": 0.5321,
      "step": 1140
    },
    {
      "epoch": 0.5388940955951266,
      "grad_norm": 2.2063546180725098,
      "learning_rate": 1.9663191190253047e-05,
      "loss": 0.4809,
      "step": 1150
    },
    {
      "epoch": 0.5435801312089972,
      "grad_norm": 2.7333438396453857,
      "learning_rate": 1.966026241799438e-05,
      "loss": 0.4615,
      "step": 1160
    },
    {
      "epoch": 0.5482661668228679,
      "grad_norm": 3.124687671661377,
      "learning_rate": 1.965733364573571e-05,
      "loss": 0.5177,
      "step": 1170
    },
    {
      "epoch": 0.5529522024367385,
      "grad_norm": 2.726681709289551,
      "learning_rate": 1.965440487347704e-05,
      "loss": 0.4891,
      "step": 1180
    },
    {
      "epoch": 0.5576382380506092,
      "grad_norm": 2.9802463054656982,
      "learning_rate": 1.965147610121837e-05,
      "loss": 0.5018,
      "step": 1190
    },
    {
      "epoch": 0.5623242736644799,
      "grad_norm": 2.844006299972534,
      "learning_rate": 1.96485473289597e-05,
      "loss": 0.5149,
      "step": 1200
    },
    {
      "epoch": 0.5670103092783505,
      "grad_norm": 2.442472219467163,
      "learning_rate": 1.964561855670103e-05,
      "loss": 0.4808,
      "step": 1210
    },
    {
      "epoch": 0.5716963448922212,
      "grad_norm": 1.9972388744354248,
      "learning_rate": 1.9642689784442363e-05,
      "loss": 0.4743,
      "step": 1220
    },
    {
      "epoch": 0.5763823805060918,
      "grad_norm": 2.6430776119232178,
      "learning_rate": 1.9639761012183693e-05,
      "loss": 0.5057,
      "step": 1230
    },
    {
      "epoch": 0.5810684161199625,
      "grad_norm": 2.37652850151062,
      "learning_rate": 1.9636832239925026e-05,
      "loss": 0.4851,
      "step": 1240
    },
    {
      "epoch": 0.5857544517338332,
      "grad_norm": 2.755315065383911,
      "learning_rate": 1.9633903467666355e-05,
      "loss": 0.4451,
      "step": 1250
    },
    {
      "epoch": 0.5857544517338332,
      "eval_loss": 0.09590280055999756,
      "eval_pearson_cosine": 0.7634019154373535,
      "eval_pearson_dot": 0.5909367397822605,
      "eval_pearson_euclidean": 0.7507597414427352,
      "eval_pearson_manhattan": 0.7505103943331619,
      "eval_runtime": 3.3916,
      "eval_samples_per_second": 442.267,
      "eval_spearman_cosine": 0.7803407693262222,
      "eval_spearman_dot": 0.592884901593322,
      "eval_spearman_euclidean": 0.7652017734526011,
      "eval_spearman_manhattan": 0.7648713625602643,
      "eval_steps_per_second": 27.715,
      "step": 1250
    },
    {
      "epoch": 0.5904404873477038,
      "grad_norm": 3.0767931938171387,
      "learning_rate": 1.9630974695407688e-05,
      "loss": 0.5093,
      "step": 1260
    },
    {
      "epoch": 0.5951265229615745,
      "grad_norm": 3.0984067916870117,
      "learning_rate": 1.9628045923149017e-05,
      "loss": 0.4888,
      "step": 1270
    },
    {
      "epoch": 0.5998125585754451,
      "grad_norm": 2.496957778930664,
      "learning_rate": 1.962511715089035e-05,
      "loss": 0.5005,
      "step": 1280
    },
    {
      "epoch": 0.6044985941893158,
      "grad_norm": 2.1109137535095215,
      "learning_rate": 1.962218837863168e-05,
      "loss": 0.4729,
      "step": 1290
    },
    {
      "epoch": 0.6091846298031866,
      "grad_norm": 2.663804054260254,
      "learning_rate": 1.961925960637301e-05,
      "loss": 0.4454,
      "step": 1300
    },
    {
      "epoch": 0.6138706654170571,
      "grad_norm": 1.8708107471466064,
      "learning_rate": 1.9616330834114342e-05,
      "loss": 0.4949,
      "step": 1310
    },
    {
      "epoch": 0.6185567010309279,
      "grad_norm": 2.9178926944732666,
      "learning_rate": 1.9613402061855672e-05,
      "loss": 0.4438,
      "step": 1320
    },
    {
      "epoch": 0.6232427366447985,
      "grad_norm": 2.1928579807281494,
      "learning_rate": 1.9610473289597005e-05,
      "loss": 0.4483,
      "step": 1330
    },
    {
      "epoch": 0.6279287722586692,
      "grad_norm": 2.3122403621673584,
      "learning_rate": 1.9607544517338334e-05,
      "loss": 0.4677,
      "step": 1340
    },
    {
      "epoch": 0.6326148078725399,
      "grad_norm": 2.5242831707000732,
      "learning_rate": 1.9604615745079664e-05,
      "loss": 0.4822,
      "step": 1350
    },
    {
      "epoch": 0.6373008434864105,
      "grad_norm": 2.572446346282959,
      "learning_rate": 1.9601686972820993e-05,
      "loss": 0.46,
      "step": 1360
    },
    {
      "epoch": 0.6419868791002812,
      "grad_norm": 2.6114673614501953,
      "learning_rate": 1.9598758200562326e-05,
      "loss": 0.4606,
      "step": 1370
    },
    {
      "epoch": 0.6466729147141518,
      "grad_norm": 2.6151556968688965,
      "learning_rate": 1.9595829428303655e-05,
      "loss": 0.459,
      "step": 1380
    },
    {
      "epoch": 0.6513589503280225,
      "grad_norm": 2.9040744304656982,
      "learning_rate": 1.959290065604499e-05,
      "loss": 0.4994,
      "step": 1390
    },
    {
      "epoch": 0.6560449859418932,
      "grad_norm": 2.9549591541290283,
      "learning_rate": 1.9589971883786318e-05,
      "loss": 0.4335,
      "step": 1400
    },
    {
      "epoch": 0.6607310215557638,
      "grad_norm": 2.2790753841400146,
      "learning_rate": 1.9587043111527647e-05,
      "loss": 0.4642,
      "step": 1410
    },
    {
      "epoch": 0.6654170571696345,
      "grad_norm": 2.265308141708374,
      "learning_rate": 1.958411433926898e-05,
      "loss": 0.4654,
      "step": 1420
    },
    {
      "epoch": 0.6701030927835051,
      "grad_norm": 2.1528425216674805,
      "learning_rate": 1.958118556701031e-05,
      "loss": 0.4983,
      "step": 1430
    },
    {
      "epoch": 0.6747891283973758,
      "grad_norm": 2.840533494949341,
      "learning_rate": 1.9578256794751643e-05,
      "loss": 0.4989,
      "step": 1440
    },
    {
      "epoch": 0.6794751640112465,
      "grad_norm": 2.4118032455444336,
      "learning_rate": 1.9575328022492972e-05,
      "loss": 0.4207,
      "step": 1450
    },
    {
      "epoch": 0.6841611996251171,
      "grad_norm": 2.845712900161743,
      "learning_rate": 1.9572399250234305e-05,
      "loss": 0.4219,
      "step": 1460
    },
    {
      "epoch": 0.6888472352389878,
      "grad_norm": 2.6068544387817383,
      "learning_rate": 1.9569470477975635e-05,
      "loss": 0.4618,
      "step": 1470
    },
    {
      "epoch": 0.6935332708528584,
      "grad_norm": 2.6239466667175293,
      "learning_rate": 1.9566541705716967e-05,
      "loss": 0.4613,
      "step": 1480
    },
    {
      "epoch": 0.6982193064667291,
      "grad_norm": 2.417541742324829,
      "learning_rate": 1.9563612933458297e-05,
      "loss": 0.4457,
      "step": 1490
    },
    {
      "epoch": 0.7029053420805998,
      "grad_norm": 2.444243907928467,
      "learning_rate": 1.9560684161199626e-05,
      "loss": 0.4682,
      "step": 1500
    },
    {
      "epoch": 0.7029053420805998,
      "eval_loss": 0.10573244839906693,
      "eval_pearson_cosine": 0.7687240391174335,
      "eval_pearson_dot": 0.52706539661569,
      "eval_pearson_euclidean": 0.7544794171981408,
      "eval_pearson_manhattan": 0.7540749762273435,
      "eval_runtime": 3.5044,
      "eval_samples_per_second": 428.028,
      "eval_spearman_cosine": 0.7854868415020917,
      "eval_spearman_dot": 0.5189687789236848,
      "eval_spearman_euclidean": 0.7685180176151998,
      "eval_spearman_manhattan": 0.7680518081256867,
      "eval_steps_per_second": 26.823,
      "step": 1500
    },
    {
      "epoch": 0.7075913776944704,
      "grad_norm": 2.4107391834259033,
      "learning_rate": 1.955775538894096e-05,
      "loss": 0.4231,
      "step": 1510
    },
    {
      "epoch": 0.7122774133083412,
      "grad_norm": 2.2897465229034424,
      "learning_rate": 1.955482661668229e-05,
      "loss": 0.495,
      "step": 1520
    },
    {
      "epoch": 0.7169634489222118,
      "grad_norm": 2.1320059299468994,
      "learning_rate": 1.9551897844423618e-05,
      "loss": 0.4362,
      "step": 1530
    },
    {
      "epoch": 0.7216494845360825,
      "grad_norm": 2.1766531467437744,
      "learning_rate": 1.9548969072164948e-05,
      "loss": 0.4324,
      "step": 1540
    },
    {
      "epoch": 0.7263355201499532,
      "grad_norm": 2.1343445777893066,
      "learning_rate": 1.954604029990628e-05,
      "loss": 0.4356,
      "step": 1550
    },
    {
      "epoch": 0.7310215557638238,
      "grad_norm": 2.6357688903808594,
      "learning_rate": 1.954311152764761e-05,
      "loss": 0.4617,
      "step": 1560
    },
    {
      "epoch": 0.7357075913776945,
      "grad_norm": 2.2863566875457764,
      "learning_rate": 1.9540182755388943e-05,
      "loss": 0.4444,
      "step": 1570
    },
    {
      "epoch": 0.7403936269915652,
      "grad_norm": 1.9845598936080933,
      "learning_rate": 1.9537253983130273e-05,
      "loss": 0.4459,
      "step": 1580
    },
    {
      "epoch": 0.7450796626054358,
      "grad_norm": 2.3808443546295166,
      "learning_rate": 1.9534325210871605e-05,
      "loss": 0.4664,
      "step": 1590
    },
    {
      "epoch": 0.7497656982193065,
      "grad_norm": 2.976896286010742,
      "learning_rate": 1.9531396438612935e-05,
      "loss": 0.4317,
      "step": 1600
    },
    {
      "epoch": 0.7544517338331771,
      "grad_norm": 3.114450693130493,
      "learning_rate": 1.9528467666354264e-05,
      "loss": 0.4365,
      "step": 1610
    },
    {
      "epoch": 0.7591377694470478,
      "grad_norm": 2.208798408508301,
      "learning_rate": 1.9525538894095597e-05,
      "loss": 0.4357,
      "step": 1620
    },
    {
      "epoch": 0.7638238050609185,
      "grad_norm": 3.005563259124756,
      "learning_rate": 1.9522610121836927e-05,
      "loss": 0.4184,
      "step": 1630
    },
    {
      "epoch": 0.7685098406747891,
      "grad_norm": 2.711338758468628,
      "learning_rate": 1.951968134957826e-05,
      "loss": 0.4479,
      "step": 1640
    },
    {
      "epoch": 0.7731958762886598,
      "grad_norm": 1.9399685859680176,
      "learning_rate": 1.951675257731959e-05,
      "loss": 0.4642,
      "step": 1650
    },
    {
      "epoch": 0.7778819119025304,
      "grad_norm": 2.5553548336029053,
      "learning_rate": 1.9513823805060922e-05,
      "loss": 0.4851,
      "step": 1660
    },
    {
      "epoch": 0.7825679475164011,
      "grad_norm": 2.7015600204467773,
      "learning_rate": 1.951089503280225e-05,
      "loss": 0.4294,
      "step": 1670
    },
    {
      "epoch": 0.7872539831302718,
      "grad_norm": 3.027247428894043,
      "learning_rate": 1.950796626054358e-05,
      "loss": 0.4359,
      "step": 1680
    },
    {
      "epoch": 0.7919400187441424,
      "grad_norm": 2.603200674057007,
      "learning_rate": 1.9505037488284914e-05,
      "loss": 0.4833,
      "step": 1690
    },
    {
      "epoch": 0.7966260543580131,
      "grad_norm": 2.2245004177093506,
      "learning_rate": 1.9502108716026243e-05,
      "loss": 0.4633,
      "step": 1700
    },
    {
      "epoch": 0.8013120899718837,
      "grad_norm": 2.1866180896759033,
      "learning_rate": 1.9499179943767573e-05,
      "loss": 0.4465,
      "step": 1710
    },
    {
      "epoch": 0.8059981255857545,
      "grad_norm": 2.464083671569824,
      "learning_rate": 1.9496251171508906e-05,
      "loss": 0.4282,
      "step": 1720
    },
    {
      "epoch": 0.8106841611996252,
      "grad_norm": 2.5016162395477295,
      "learning_rate": 1.9493322399250235e-05,
      "loss": 0.4566,
      "step": 1730
    },
    {
      "epoch": 0.8153701968134958,
      "grad_norm": 2.9877169132232666,
      "learning_rate": 1.9490393626991565e-05,
      "loss": 0.462,
      "step": 1740
    },
    {
      "epoch": 0.8200562324273665,
      "grad_norm": 2.2195188999176025,
      "learning_rate": 1.9487464854732898e-05,
      "loss": 0.4489,
      "step": 1750
    },
    {
      "epoch": 0.8200562324273665,
      "eval_loss": 0.09936515241861343,
      "eval_pearson_cosine": 0.7657869832789288,
      "eval_pearson_dot": 0.576463122226734,
      "eval_pearson_euclidean": 0.7513952467595857,
      "eval_pearson_manhattan": 0.7505485236956133,
      "eval_runtime": 3.3329,
      "eval_samples_per_second": 450.052,
      "eval_spearman_cosine": 0.7800032031654975,
      "eval_spearman_dot": 0.576004160544721,
      "eval_spearman_euclidean": 0.7627214415950069,
      "eval_spearman_manhattan": 0.7623633881575729,
      "eval_steps_per_second": 28.203,
      "step": 1750
    },
    {
      "epoch": 0.8247422680412371,
      "grad_norm": 2.793635606765747,
      "learning_rate": 1.9484536082474227e-05,
      "loss": 0.4434,
      "step": 1760
    },
    {
      "epoch": 0.8294283036551078,
      "grad_norm": 2.403629779815674,
      "learning_rate": 1.948160731021556e-05,
      "loss": 0.4034,
      "step": 1770
    },
    {
      "epoch": 0.8341143392689785,
      "grad_norm": 2.6248741149902344,
      "learning_rate": 1.947867853795689e-05,
      "loss": 0.4328,
      "step": 1780
    },
    {
      "epoch": 0.8388003748828491,
      "grad_norm": 1.8423967361450195,
      "learning_rate": 1.9475749765698223e-05,
      "loss": 0.458,
      "step": 1790
    },
    {
      "epoch": 0.8434864104967198,
      "grad_norm": 2.8771181106567383,
      "learning_rate": 1.9472820993439552e-05,
      "loss": 0.3796,
      "step": 1800
    },
    {
      "epoch": 0.8481724461105904,
      "grad_norm": 2.6302261352539062,
      "learning_rate": 1.946989222118088e-05,
      "loss": 0.4494,
      "step": 1810
    },
    {
      "epoch": 0.8528584817244611,
      "grad_norm": 1.8728386163711548,
      "learning_rate": 1.9466963448922214e-05,
      "loss": 0.4624,
      "step": 1820
    },
    {
      "epoch": 0.8575445173383318,
      "grad_norm": 1.9615451097488403,
      "learning_rate": 1.9464034676663544e-05,
      "loss": 0.4666,
      "step": 1830
    },
    {
      "epoch": 0.8622305529522024,
      "grad_norm": 2.423076629638672,
      "learning_rate": 1.9461105904404877e-05,
      "loss": 0.4659,
      "step": 1840
    },
    {
      "epoch": 0.8669165885660731,
      "grad_norm": 2.1707210540771484,
      "learning_rate": 1.9458177132146206e-05,
      "loss": 0.4536,
      "step": 1850
    },
    {
      "epoch": 0.8716026241799437,
      "grad_norm": 2.3241922855377197,
      "learning_rate": 1.9455248359887536e-05,
      "loss": 0.4589,
      "step": 1860
    },
    {
      "epoch": 0.8762886597938144,
      "grad_norm": 2.628664255142212,
      "learning_rate": 1.945231958762887e-05,
      "loss": 0.4801,
      "step": 1870
    },
    {
      "epoch": 0.8809746954076851,
      "grad_norm": 2.25126314163208,
      "learning_rate": 1.9449390815370198e-05,
      "loss": 0.4127,
      "step": 1880
    },
    {
      "epoch": 0.8856607310215557,
      "grad_norm": 2.988956928253174,
      "learning_rate": 1.9446462043111528e-05,
      "loss": 0.4431,
      "step": 1890
    },
    {
      "epoch": 0.8903467666354264,
      "grad_norm": 2.3071420192718506,
      "learning_rate": 1.944353327085286e-05,
      "loss": 0.4606,
      "step": 1900
    },
    {
      "epoch": 0.895032802249297,
      "grad_norm": 2.712460517883301,
      "learning_rate": 1.944060449859419e-05,
      "loss": 0.4853,
      "step": 1910
    },
    {
      "epoch": 0.8997188378631678,
      "grad_norm": 2.555626153945923,
      "learning_rate": 1.943767572633552e-05,
      "loss": 0.4187,
      "step": 1920
    },
    {
      "epoch": 0.9044048734770385,
      "grad_norm": 2.3509678840637207,
      "learning_rate": 1.9434746954076852e-05,
      "loss": 0.4144,
      "step": 1930
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 2.63004994392395,
      "learning_rate": 1.9431818181818182e-05,
      "loss": 0.399,
      "step": 1940
    },
    {
      "epoch": 0.9137769447047798,
      "grad_norm": 2.8148534297943115,
      "learning_rate": 1.9428889409559515e-05,
      "loss": 0.4309,
      "step": 1950
    },
    {
      "epoch": 0.9184629803186504,
      "grad_norm": 2.594778537750244,
      "learning_rate": 1.9425960637300844e-05,
      "loss": 0.4753,
      "step": 1960
    },
    {
      "epoch": 0.9231490159325211,
      "grad_norm": 2.4502975940704346,
      "learning_rate": 1.9423031865042177e-05,
      "loss": 0.4317,
      "step": 1970
    },
    {
      "epoch": 0.9278350515463918,
      "grad_norm": 2.335707664489746,
      "learning_rate": 1.9420103092783507e-05,
      "loss": 0.405,
      "step": 1980
    },
    {
      "epoch": 0.9325210871602624,
      "grad_norm": 2.0419764518737793,
      "learning_rate": 1.941717432052484e-05,
      "loss": 0.4669,
      "step": 1990
    },
    {
      "epoch": 0.9372071227741331,
      "grad_norm": 2.2041420936584473,
      "learning_rate": 1.941424554826617e-05,
      "loss": 0.4696,
      "step": 2000
    },
    {
      "epoch": 0.9372071227741331,
      "eval_loss": 0.10549145191907883,
      "eval_pearson_cosine": 0.7617707450696116,
      "eval_pearson_dot": 0.5909647410786931,
      "eval_pearson_euclidean": 0.7526201710813609,
      "eval_pearson_manhattan": 0.7514050722082715,
      "eval_runtime": 3.4394,
      "eval_samples_per_second": 436.124,
      "eval_spearman_cosine": 0.7834635716420068,
      "eval_spearman_dot": 0.5835376546734291,
      "eval_spearman_euclidean": 0.7675113486625056,
      "eval_spearman_manhattan": 0.7668717701506194,
      "eval_steps_per_second": 27.33,
      "step": 2000
    },
    {
      "epoch": 0.9418931583880038,
      "grad_norm": 1.7690527439117432,
      "learning_rate": 1.94113167760075e-05,
      "loss": 0.39,
      "step": 2010
    },
    {
      "epoch": 0.9465791940018744,
      "grad_norm": 2.247870683670044,
      "learning_rate": 1.940838800374883e-05,
      "loss": 0.4283,
      "step": 2020
    },
    {
      "epoch": 0.9512652296157451,
      "grad_norm": 2.7865118980407715,
      "learning_rate": 1.940545923149016e-05,
      "loss": 0.4041,
      "step": 2030
    },
    {
      "epoch": 0.9559512652296157,
      "grad_norm": 2.7173750400543213,
      "learning_rate": 1.9402530459231494e-05,
      "loss": 0.428,
      "step": 2040
    },
    {
      "epoch": 0.9606373008434864,
      "grad_norm": 2.4290664196014404,
      "learning_rate": 1.9399601686972823e-05,
      "loss": 0.4363,
      "step": 2050
    },
    {
      "epoch": 0.9653233364573571,
      "grad_norm": 2.9478437900543213,
      "learning_rate": 1.9396672914714153e-05,
      "loss": 0.4341,
      "step": 2060
    },
    {
      "epoch": 0.9700093720712277,
      "grad_norm": 2.5642406940460205,
      "learning_rate": 1.9393744142455482e-05,
      "loss": 0.4402,
      "step": 2070
    },
    {
      "epoch": 0.9746954076850984,
      "grad_norm": 2.622969388961792,
      "learning_rate": 1.9390815370196815e-05,
      "loss": 0.4415,
      "step": 2080
    },
    {
      "epoch": 0.979381443298969,
      "grad_norm": 1.8864187002182007,
      "learning_rate": 1.9387886597938145e-05,
      "loss": 0.421,
      "step": 2090
    },
    {
      "epoch": 0.9840674789128397,
      "grad_norm": 2.145385503768921,
      "learning_rate": 1.9384957825679474e-05,
      "loss": 0.4142,
      "step": 2100
    },
    {
      "epoch": 0.9887535145267105,
      "grad_norm": 2.5870542526245117,
      "learning_rate": 1.9382029053420807e-05,
      "loss": 0.4701,
      "step": 2110
    },
    {
      "epoch": 0.993439550140581,
      "grad_norm": 2.5176923274993896,
      "learning_rate": 1.9379100281162137e-05,
      "loss": 0.3776,
      "step": 2120
    },
    {
      "epoch": 0.9981255857544518,
      "grad_norm": 2.8260464668273926,
      "learning_rate": 1.937617150890347e-05,
      "loss": 0.4453,
      "step": 2130
    },
    {
      "epoch": 1.0028116213683225,
      "grad_norm": 2.2735579013824463,
      "learning_rate": 1.93732427366448e-05,
      "loss": 0.3617,
      "step": 2140
    },
    {
      "epoch": 1.007497656982193,
      "grad_norm": 1.9802652597427368,
      "learning_rate": 1.9370313964386132e-05,
      "loss": 0.3103,
      "step": 2150
    },
    {
      "epoch": 1.0121836925960637,
      "grad_norm": 2.4149436950683594,
      "learning_rate": 1.936738519212746e-05,
      "loss": 0.3183,
      "step": 2160
    },
    {
      "epoch": 1.0168697282099344,
      "grad_norm": 2.9166879653930664,
      "learning_rate": 1.9364456419868794e-05,
      "loss": 0.2927,
      "step": 2170
    },
    {
      "epoch": 1.021555763823805,
      "grad_norm": 1.8774973154067993,
      "learning_rate": 1.9361527647610124e-05,
      "loss": 0.3217,
      "step": 2180
    },
    {
      "epoch": 1.0262417994376758,
      "grad_norm": 2.0291717052459717,
      "learning_rate": 1.9358598875351457e-05,
      "loss": 0.3236,
      "step": 2190
    },
    {
      "epoch": 1.0309278350515463,
      "grad_norm": 2.500614643096924,
      "learning_rate": 1.9355670103092786e-05,
      "loss": 0.3187,
      "step": 2200
    },
    {
      "epoch": 1.035613870665417,
      "grad_norm": 2.4826183319091797,
      "learning_rate": 1.9352741330834116e-05,
      "loss": 0.3284,
      "step": 2210
    },
    {
      "epoch": 1.0402999062792877,
      "grad_norm": 2.647724151611328,
      "learning_rate": 1.934981255857545e-05,
      "loss": 0.3432,
      "step": 2220
    },
    {
      "epoch": 1.0449859418931584,
      "grad_norm": 2.356365203857422,
      "learning_rate": 1.9346883786316778e-05,
      "loss": 0.3321,
      "step": 2230
    },
    {
      "epoch": 1.0496719775070291,
      "grad_norm": 2.514002561569214,
      "learning_rate": 1.9343955014058108e-05,
      "loss": 0.3115,
      "step": 2240
    },
    {
      "epoch": 1.0543580131208996,
      "grad_norm": 2.049299716949463,
      "learning_rate": 1.9341026241799437e-05,
      "loss": 0.3474,
      "step": 2250
    },
    {
      "epoch": 1.0543580131208996,
      "eval_loss": 0.0818348377943039,
      "eval_pearson_cosine": 0.7662947284133068,
      "eval_pearson_dot": 0.5774155023095773,
      "eval_pearson_euclidean": 0.7536499802604126,
      "eval_pearson_manhattan": 0.7526750534069606,
      "eval_runtime": 3.4518,
      "eval_samples_per_second": 434.553,
      "eval_spearman_cosine": 0.7776893657594519,
      "eval_spearman_dot": 0.5747770364870878,
      "eval_spearman_euclidean": 0.7641629894500831,
      "eval_spearman_manhattan": 0.7635836296791149,
      "eval_steps_per_second": 27.232,
      "step": 2250
    },
    {
      "epoch": 1.0590440487347703,
      "grad_norm": 1.9242613315582275,
      "learning_rate": 1.933809746954077e-05,
      "loss": 0.3362,
      "step": 2260
    },
    {
      "epoch": 1.063730084348641,
      "grad_norm": 2.6948235034942627,
      "learning_rate": 1.93351686972821e-05,
      "loss": 0.3524,
      "step": 2270
    },
    {
      "epoch": 1.0684161199625117,
      "grad_norm": 2.162079334259033,
      "learning_rate": 1.9332239925023432e-05,
      "loss": 0.3292,
      "step": 2280
    },
    {
      "epoch": 1.0731021555763824,
      "grad_norm": 2.1351771354675293,
      "learning_rate": 1.9329311152764762e-05,
      "loss": 0.3409,
      "step": 2290
    },
    {
      "epoch": 1.077788191190253,
      "grad_norm": 2.527005434036255,
      "learning_rate": 1.932638238050609e-05,
      "loss": 0.3027,
      "step": 2300
    },
    {
      "epoch": 1.0824742268041236,
      "grad_norm": 2.446911334991455,
      "learning_rate": 1.9323453608247424e-05,
      "loss": 0.3376,
      "step": 2310
    },
    {
      "epoch": 1.0871602624179943,
      "grad_norm": 2.478301763534546,
      "learning_rate": 1.9320524835988754e-05,
      "loss": 0.298,
      "step": 2320
    },
    {
      "epoch": 1.091846298031865,
      "grad_norm": 2.537336587905884,
      "learning_rate": 1.9317596063730087e-05,
      "loss": 0.3312,
      "step": 2330
    },
    {
      "epoch": 1.0965323336457358,
      "grad_norm": 2.4405462741851807,
      "learning_rate": 1.9314667291471416e-05,
      "loss": 0.2998,
      "step": 2340
    },
    {
      "epoch": 1.1012183692596063,
      "grad_norm": 2.2255520820617676,
      "learning_rate": 1.931173851921275e-05,
      "loss": 0.2987,
      "step": 2350
    },
    {
      "epoch": 1.105904404873477,
      "grad_norm": 2.541879177093506,
      "learning_rate": 1.930880974695408e-05,
      "loss": 0.3286,
      "step": 2360
    },
    {
      "epoch": 1.1105904404873477,
      "grad_norm": 2.1010048389434814,
      "learning_rate": 1.930588097469541e-05,
      "loss": 0.2989,
      "step": 2370
    },
    {
      "epoch": 1.1152764761012184,
      "grad_norm": 1.9881564378738403,
      "learning_rate": 1.930295220243674e-05,
      "loss": 0.3537,
      "step": 2380
    },
    {
      "epoch": 1.119962511715089,
      "grad_norm": 2.503845691680908,
      "learning_rate": 1.930002343017807e-05,
      "loss": 0.3242,
      "step": 2390
    },
    {
      "epoch": 1.1246485473289598,
      "grad_norm": 2.773836612701416,
      "learning_rate": 1.9297094657919403e-05,
      "loss": 0.3144,
      "step": 2400
    },
    {
      "epoch": 1.1293345829428303,
      "grad_norm": 2.7757749557495117,
      "learning_rate": 1.9294165885660733e-05,
      "loss": 0.3114,
      "step": 2410
    },
    {
      "epoch": 1.134020618556701,
      "grad_norm": 2.707315444946289,
      "learning_rate": 1.9291237113402062e-05,
      "loss": 0.2872,
      "step": 2420
    },
    {
      "epoch": 1.1387066541705717,
      "grad_norm": 2.1421258449554443,
      "learning_rate": 1.9288308341143395e-05,
      "loss": 0.3122,
      "step": 2430
    },
    {
      "epoch": 1.1433926897844424,
      "grad_norm": 2.2792320251464844,
      "learning_rate": 1.9285379568884725e-05,
      "loss": 0.304,
      "step": 2440
    },
    {
      "epoch": 1.148078725398313,
      "grad_norm": 2.1971569061279297,
      "learning_rate": 1.9282450796626054e-05,
      "loss": 0.3571,
      "step": 2450
    },
    {
      "epoch": 1.1527647610121836,
      "grad_norm": 2.101923704147339,
      "learning_rate": 1.9279522024367387e-05,
      "loss": 0.3069,
      "step": 2460
    },
    {
      "epoch": 1.1574507966260543,
      "grad_norm": 2.395801305770874,
      "learning_rate": 1.9276593252108717e-05,
      "loss": 0.3145,
      "step": 2470
    },
    {
      "epoch": 1.162136832239925,
      "grad_norm": 1.9261037111282349,
      "learning_rate": 1.927366447985005e-05,
      "loss": 0.3229,
      "step": 2480
    },
    {
      "epoch": 1.1668228678537957,
      "grad_norm": 2.185063362121582,
      "learning_rate": 1.927073570759138e-05,
      "loss": 0.3289,
      "step": 2490
    },
    {
      "epoch": 1.1715089034676662,
      "grad_norm": 2.2372336387634277,
      "learning_rate": 1.926780693533271e-05,
      "loss": 0.319,
      "step": 2500
    },
    {
      "epoch": 1.1715089034676662,
      "eval_loss": 0.07521134614944458,
      "eval_pearson_cosine": 0.7753374743054451,
      "eval_pearson_dot": 0.5929128805152892,
      "eval_pearson_euclidean": 0.7592332760910097,
      "eval_pearson_manhattan": 0.7589109467518398,
      "eval_runtime": 3.6686,
      "eval_samples_per_second": 408.877,
      "eval_spearman_cosine": 0.785757446712241,
      "eval_spearman_dot": 0.5918750155733082,
      "eval_spearman_euclidean": 0.7692376569048597,
      "eval_spearman_manhattan": 0.7692457770843739,
      "eval_steps_per_second": 25.623,
      "step": 2500
    },
    {
      "epoch": 1.176194939081537,
      "grad_norm": 2.2003061771392822,
      "learning_rate": 1.926487816307404e-05,
      "loss": 0.2979,
      "step": 2510
    },
    {
      "epoch": 1.1808809746954076,
      "grad_norm": 1.9160058498382568,
      "learning_rate": 1.926194939081537e-05,
      "loss": 0.3119,
      "step": 2520
    },
    {
      "epoch": 1.1855670103092784,
      "grad_norm": 2.5396270751953125,
      "learning_rate": 1.9259020618556704e-05,
      "loss": 0.2882,
      "step": 2530
    },
    {
      "epoch": 1.190253045923149,
      "grad_norm": 2.184056520462036,
      "learning_rate": 1.9256091846298033e-05,
      "loss": 0.3012,
      "step": 2540
    },
    {
      "epoch": 1.1949390815370198,
      "grad_norm": 2.4930028915405273,
      "learning_rate": 1.9253163074039366e-05,
      "loss": 0.3399,
      "step": 2550
    },
    {
      "epoch": 1.1996251171508903,
      "grad_norm": 2.0577898025512695,
      "learning_rate": 1.9250234301780696e-05,
      "loss": 0.3013,
      "step": 2560
    },
    {
      "epoch": 1.204311152764761,
      "grad_norm": 1.9735450744628906,
      "learning_rate": 1.9247305529522025e-05,
      "loss": 0.315,
      "step": 2570
    },
    {
      "epoch": 1.2089971883786317,
      "grad_norm": 2.815910577774048,
      "learning_rate": 1.9244376757263358e-05,
      "loss": 0.3134,
      "step": 2580
    },
    {
      "epoch": 1.2136832239925024,
      "grad_norm": 2.4166650772094727,
      "learning_rate": 1.9241447985004687e-05,
      "loss": 0.2924,
      "step": 2590
    },
    {
      "epoch": 1.218369259606373,
      "grad_norm": 2.65451979637146,
      "learning_rate": 1.9238519212746017e-05,
      "loss": 0.313,
      "step": 2600
    },
    {
      "epoch": 1.2230552952202436,
      "grad_norm": 3.048393726348877,
      "learning_rate": 1.923559044048735e-05,
      "loss": 0.3396,
      "step": 2610
    },
    {
      "epoch": 1.2277413308341143,
      "grad_norm": 2.1255080699920654,
      "learning_rate": 1.923266166822868e-05,
      "loss": 0.2918,
      "step": 2620
    },
    {
      "epoch": 1.232427366447985,
      "grad_norm": 2.4257168769836426,
      "learning_rate": 1.922973289597001e-05,
      "loss": 0.3221,
      "step": 2630
    },
    {
      "epoch": 1.2371134020618557,
      "grad_norm": 2.3977224826812744,
      "learning_rate": 1.9226804123711342e-05,
      "loss": 0.3777,
      "step": 2640
    },
    {
      "epoch": 1.2417994376757264,
      "grad_norm": 2.0743911266326904,
      "learning_rate": 1.922387535145267e-05,
      "loss": 0.2981,
      "step": 2650
    },
    {
      "epoch": 1.246485473289597,
      "grad_norm": 2.740622043609619,
      "learning_rate": 1.9220946579194004e-05,
      "loss": 0.3239,
      "step": 2660
    },
    {
      "epoch": 1.2511715089034676,
      "grad_norm": 2.5174942016601562,
      "learning_rate": 1.9218017806935334e-05,
      "loss": 0.2981,
      "step": 2670
    },
    {
      "epoch": 1.2558575445173383,
      "grad_norm": 2.3390488624572754,
      "learning_rate": 1.9215089034676667e-05,
      "loss": 0.3509,
      "step": 2680
    },
    {
      "epoch": 1.260543580131209,
      "grad_norm": 2.495445966720581,
      "learning_rate": 1.9212160262417996e-05,
      "loss": 0.3153,
      "step": 2690
    },
    {
      "epoch": 1.2652296157450795,
      "grad_norm": 2.384673595428467,
      "learning_rate": 1.9209231490159326e-05,
      "loss": 0.3541,
      "step": 2700
    },
    {
      "epoch": 1.2699156513589505,
      "grad_norm": 1.9707324504852295,
      "learning_rate": 1.920630271790066e-05,
      "loss": 0.3053,
      "step": 2710
    },
    {
      "epoch": 1.274601686972821,
      "grad_norm": 2.0584781169891357,
      "learning_rate": 1.9203373945641988e-05,
      "loss": 0.2716,
      "step": 2720
    },
    {
      "epoch": 1.2792877225866917,
      "grad_norm": 1.9361029863357544,
      "learning_rate": 1.920044517338332e-05,
      "loss": 0.2988,
      "step": 2730
    },
    {
      "epoch": 1.2839737582005624,
      "grad_norm": 2.3929100036621094,
      "learning_rate": 1.919751640112465e-05,
      "loss": 0.3356,
      "step": 2740
    },
    {
      "epoch": 1.2886597938144329,
      "grad_norm": 2.7867496013641357,
      "learning_rate": 1.9194587628865983e-05,
      "loss": 0.3682,
      "step": 2750
    },
    {
      "epoch": 1.2886597938144329,
      "eval_loss": 0.07667941600084305,
      "eval_pearson_cosine": 0.7735852714798206,
      "eval_pearson_dot": 0.578414803552846,
      "eval_pearson_euclidean": 0.7564370361137946,
      "eval_pearson_manhattan": 0.7556229015098381,
      "eval_runtime": 3.3395,
      "eval_samples_per_second": 449.165,
      "eval_spearman_cosine": 0.7851408708188664,
      "eval_spearman_dot": 0.5785312770170487,
      "eval_spearman_euclidean": 0.7670951414033645,
      "eval_spearman_manhattan": 0.7667469763884154,
      "eval_steps_per_second": 28.148,
      "step": 2750
    },
    {
      "epoch": 1.2933458294283038,
      "grad_norm": 2.0457334518432617,
      "learning_rate": 1.9191658856607313e-05,
      "loss": 0.3118,
      "step": 2760
    },
    {
      "epoch": 1.2980318650421743,
      "grad_norm": 2.1723532676696777,
      "learning_rate": 1.9188730084348642e-05,
      "loss": 0.2918,
      "step": 2770
    },
    {
      "epoch": 1.302717900656045,
      "grad_norm": 2.041738748550415,
      "learning_rate": 1.9185801312089972e-05,
      "loss": 0.3084,
      "step": 2780
    },
    {
      "epoch": 1.3074039362699157,
      "grad_norm": 2.774698257446289,
      "learning_rate": 1.9182872539831305e-05,
      "loss": 0.3337,
      "step": 2790
    },
    {
      "epoch": 1.3120899718837864,
      "grad_norm": 1.9762837886810303,
      "learning_rate": 1.9179943767572634e-05,
      "loss": 0.3029,
      "step": 2800
    },
    {
      "epoch": 1.316776007497657,
      "grad_norm": 2.1785385608673096,
      "learning_rate": 1.9177014995313964e-05,
      "loss": 0.3337,
      "step": 2810
    },
    {
      "epoch": 1.3214620431115276,
      "grad_norm": 2.0208494663238525,
      "learning_rate": 1.9174086223055296e-05,
      "loss": 0.2931,
      "step": 2820
    },
    {
      "epoch": 1.3261480787253983,
      "grad_norm": 2.3976972103118896,
      "learning_rate": 1.9171157450796626e-05,
      "loss": 0.3316,
      "step": 2830
    },
    {
      "epoch": 1.330834114339269,
      "grad_norm": 1.9782285690307617,
      "learning_rate": 1.916822867853796e-05,
      "loss": 0.3173,
      "step": 2840
    },
    {
      "epoch": 1.3355201499531397,
      "grad_norm": 2.0938830375671387,
      "learning_rate": 1.916529990627929e-05,
      "loss": 0.2858,
      "step": 2850
    },
    {
      "epoch": 1.3402061855670104,
      "grad_norm": 2.079247236251831,
      "learning_rate": 1.916237113402062e-05,
      "loss": 0.2911,
      "step": 2860
    },
    {
      "epoch": 1.344892221180881,
      "grad_norm": 2.5487163066864014,
      "learning_rate": 1.915944236176195e-05,
      "loss": 0.2782,
      "step": 2870
    },
    {
      "epoch": 1.3495782567947516,
      "grad_norm": 2.4930672645568848,
      "learning_rate": 1.9156513589503284e-05,
      "loss": 0.309,
      "step": 2880
    },
    {
      "epoch": 1.3542642924086223,
      "grad_norm": 2.208987236022949,
      "learning_rate": 1.9153584817244613e-05,
      "loss": 0.302,
      "step": 2890
    },
    {
      "epoch": 1.358950328022493,
      "grad_norm": 2.2777154445648193,
      "learning_rate": 1.9150656044985943e-05,
      "loss": 0.2932,
      "step": 2900
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 2.0704426765441895,
      "learning_rate": 1.9147727272727276e-05,
      "loss": 0.3326,
      "step": 2910
    },
    {
      "epoch": 1.3683223992502342,
      "grad_norm": 2.550323486328125,
      "learning_rate": 1.9144798500468605e-05,
      "loss": 0.2945,
      "step": 2920
    },
    {
      "epoch": 1.373008434864105,
      "grad_norm": 2.1471896171569824,
      "learning_rate": 1.9141869728209938e-05,
      "loss": 0.3258,
      "step": 2930
    },
    {
      "epoch": 1.3776944704779757,
      "grad_norm": 2.4434566497802734,
      "learning_rate": 1.9138940955951267e-05,
      "loss": 0.3,
      "step": 2940
    },
    {
      "epoch": 1.3823805060918464,
      "grad_norm": 2.2125484943389893,
      "learning_rate": 1.9136012183692597e-05,
      "loss": 0.3618,
      "step": 2950
    },
    {
      "epoch": 1.387066541705717,
      "grad_norm": 2.5156352519989014,
      "learning_rate": 1.913308341143393e-05,
      "loss": 0.3102,
      "step": 2960
    },
    {
      "epoch": 1.3917525773195876,
      "grad_norm": 2.1281540393829346,
      "learning_rate": 1.913015463917526e-05,
      "loss": 0.31,
      "step": 2970
    },
    {
      "epoch": 1.3964386129334583,
      "grad_norm": 2.1260693073272705,
      "learning_rate": 1.912722586691659e-05,
      "loss": 0.2946,
      "step": 2980
    },
    {
      "epoch": 1.401124648547329,
      "grad_norm": 2.591770887374878,
      "learning_rate": 1.912429709465792e-05,
      "loss": 0.2906,
      "step": 2990
    },
    {
      "epoch": 1.4058106841611997,
      "grad_norm": 1.832505226135254,
      "learning_rate": 1.912136832239925e-05,
      "loss": 0.3033,
      "step": 3000
    },
    {
      "epoch": 1.4058106841611997,
      "eval_loss": 0.07158821821212769,
      "eval_pearson_cosine": 0.7835729367892306,
      "eval_pearson_dot": 0.5987220055863389,
      "eval_pearson_euclidean": 0.7599913918565986,
      "eval_pearson_manhattan": 0.7589542766532986,
      "eval_runtime": 3.4365,
      "eval_samples_per_second": 436.486,
      "eval_spearman_cosine": 0.7961581681624044,
      "eval_spearman_dot": 0.5975812797826083,
      "eval_spearman_euclidean": 0.7727385023345612,
      "eval_spearman_manhattan": 0.7723228512152759,
      "eval_steps_per_second": 27.353,
      "step": 3000
    },
    {
      "epoch": 1.4104967197750704,
      "grad_norm": 2.3309245109558105,
      "learning_rate": 1.911843955014058e-05,
      "loss": 0.3238,
      "step": 3010
    },
    {
      "epoch": 1.415182755388941,
      "grad_norm": 2.3359642028808594,
      "learning_rate": 1.9115510777881914e-05,
      "loss": 0.2933,
      "step": 3020
    },
    {
      "epoch": 1.4198687910028116,
      "grad_norm": 2.363147497177124,
      "learning_rate": 1.9112582005623243e-05,
      "loss": 0.3204,
      "step": 3030
    },
    {
      "epoch": 1.4245548266166823,
      "grad_norm": 2.353273391723633,
      "learning_rate": 1.9109653233364576e-05,
      "loss": 0.295,
      "step": 3040
    },
    {
      "epoch": 1.429240862230553,
      "grad_norm": 2.418267011642456,
      "learning_rate": 1.9106724461105905e-05,
      "loss": 0.3397,
      "step": 3050
    },
    {
      "epoch": 1.4339268978444237,
      "grad_norm": 2.612607955932617,
      "learning_rate": 1.910379568884724e-05,
      "loss": 0.3001,
      "step": 3060
    },
    {
      "epoch": 1.4386129334582942,
      "grad_norm": 2.506488084793091,
      "learning_rate": 1.9100866916588568e-05,
      "loss": 0.3101,
      "step": 3070
    },
    {
      "epoch": 1.443298969072165,
      "grad_norm": 2.437333345413208,
      "learning_rate": 1.90979381443299e-05,
      "loss": 0.3017,
      "step": 3080
    },
    {
      "epoch": 1.4479850046860356,
      "grad_norm": 2.3391661643981934,
      "learning_rate": 1.909500937207123e-05,
      "loss": 0.2943,
      "step": 3090
    },
    {
      "epoch": 1.4526710402999063,
      "grad_norm": 2.410454511642456,
      "learning_rate": 1.909208059981256e-05,
      "loss": 0.3242,
      "step": 3100
    },
    {
      "epoch": 1.457357075913777,
      "grad_norm": 2.6086418628692627,
      "learning_rate": 1.9089151827553893e-05,
      "loss": 0.3442,
      "step": 3110
    },
    {
      "epoch": 1.4620431115276475,
      "grad_norm": 2.1769497394561768,
      "learning_rate": 1.9086223055295222e-05,
      "loss": 0.3114,
      "step": 3120
    },
    {
      "epoch": 1.4667291471415183,
      "grad_norm": 1.9582467079162598,
      "learning_rate": 1.908329428303655e-05,
      "loss": 0.3261,
      "step": 3130
    },
    {
      "epoch": 1.471415182755389,
      "grad_norm": 2.577211380004883,
      "learning_rate": 1.9080365510777884e-05,
      "loss": 0.31,
      "step": 3140
    },
    {
      "epoch": 1.4761012183692597,
      "grad_norm": 2.725773811340332,
      "learning_rate": 1.9077436738519214e-05,
      "loss": 0.2859,
      "step": 3150
    },
    {
      "epoch": 1.4807872539831304,
      "grad_norm": 2.779578685760498,
      "learning_rate": 1.9074507966260543e-05,
      "loss": 0.3304,
      "step": 3160
    },
    {
      "epoch": 1.4854732895970009,
      "grad_norm": 1.9493879079818726,
      "learning_rate": 1.9071579194001876e-05,
      "loss": 0.2992,
      "step": 3170
    },
    {
      "epoch": 1.4901593252108716,
      "grad_norm": 3.1011288166046143,
      "learning_rate": 1.9068650421743206e-05,
      "loss": 0.3406,
      "step": 3180
    },
    {
      "epoch": 1.4948453608247423,
      "grad_norm": 2.466146230697632,
      "learning_rate": 1.906572164948454e-05,
      "loss": 0.357,
      "step": 3190
    },
    {
      "epoch": 1.499531396438613,
      "grad_norm": 2.0382285118103027,
      "learning_rate": 1.9062792877225868e-05,
      "loss": 0.2968,
      "step": 3200
    },
    {
      "epoch": 1.5042174320524837,
      "grad_norm": 2.331540584564209,
      "learning_rate": 1.9059864104967198e-05,
      "loss": 0.3125,
      "step": 3210
    },
    {
      "epoch": 1.5089034676663542,
      "grad_norm": 2.590193271636963,
      "learning_rate": 1.905693533270853e-05,
      "loss": 0.2762,
      "step": 3220
    },
    {
      "epoch": 1.513589503280225,
      "grad_norm": 2.878938913345337,
      "learning_rate": 1.905400656044986e-05,
      "loss": 0.2868,
      "step": 3230
    },
    {
      "epoch": 1.5182755388940956,
      "grad_norm": 2.4432168006896973,
      "learning_rate": 1.9051077788191193e-05,
      "loss": 0.3021,
      "step": 3240
    },
    {
      "epoch": 1.522961574507966,
      "grad_norm": 2.849559783935547,
      "learning_rate": 1.9048149015932523e-05,
      "loss": 0.3247,
      "step": 3250
    },
    {
      "epoch": 1.522961574507966,
      "eval_loss": 0.07676094025373459,
      "eval_pearson_cosine": 0.7779113850636818,
      "eval_pearson_dot": 0.5637961042064976,
      "eval_pearson_euclidean": 0.7621398908224677,
      "eval_pearson_manhattan": 0.7612994290780648,
      "eval_runtime": 3.2908,
      "eval_samples_per_second": 455.817,
      "eval_spearman_cosine": 0.7910676412952927,
      "eval_spearman_dot": 0.562324725935799,
      "eval_spearman_euclidean": 0.7734903614875008,
      "eval_spearman_manhattan": 0.7731474604573987,
      "eval_steps_per_second": 28.565,
      "step": 3250
    },
    {
      "epoch": 1.527647610121837,
      "grad_norm": 2.372697591781616,
      "learning_rate": 1.9045220243673855e-05,
      "loss": 0.3423,
      "step": 3260
    },
    {
      "epoch": 1.5323336457357075,
      "grad_norm": 2.9068384170532227,
      "learning_rate": 1.9042291471415185e-05,
      "loss": 0.3133,
      "step": 3270
    },
    {
      "epoch": 1.5370196813495782,
      "grad_norm": 2.738391160964966,
      "learning_rate": 1.9039362699156518e-05,
      "loss": 0.3018,
      "step": 3280
    },
    {
      "epoch": 1.541705716963449,
      "grad_norm": 2.121777296066284,
      "learning_rate": 1.9036433926897847e-05,
      "loss": 0.3203,
      "step": 3290
    },
    {
      "epoch": 1.5463917525773194,
      "grad_norm": 2.1887810230255127,
      "learning_rate": 1.9033505154639177e-05,
      "loss": 0.3639,
      "step": 3300
    },
    {
      "epoch": 1.5510777881911904,
      "grad_norm": 2.4203438758850098,
      "learning_rate": 1.9030576382380506e-05,
      "loss": 0.3116,
      "step": 3310
    },
    {
      "epoch": 1.5557638238050608,
      "grad_norm": 2.00972318649292,
      "learning_rate": 1.902764761012184e-05,
      "loss": 0.3139,
      "step": 3320
    },
    {
      "epoch": 1.5604498594189316,
      "grad_norm": 2.093622922897339,
      "learning_rate": 1.902471883786317e-05,
      "loss": 0.3248,
      "step": 3330
    },
    {
      "epoch": 1.5651358950328023,
      "grad_norm": 2.5851595401763916,
      "learning_rate": 1.9021790065604498e-05,
      "loss": 0.3386,
      "step": 3340
    },
    {
      "epoch": 1.569821930646673,
      "grad_norm": 2.208651304244995,
      "learning_rate": 1.901886129334583e-05,
      "loss": 0.3138,
      "step": 3350
    },
    {
      "epoch": 1.5745079662605437,
      "grad_norm": 2.5663788318634033,
      "learning_rate": 1.901593252108716e-05,
      "loss": 0.3165,
      "step": 3360
    },
    {
      "epoch": 1.5791940018744142,
      "grad_norm": 2.443042039871216,
      "learning_rate": 1.9013003748828493e-05,
      "loss": 0.3178,
      "step": 3370
    },
    {
      "epoch": 1.5838800374882849,
      "grad_norm": 2.385019540786743,
      "learning_rate": 1.9010074976569823e-05,
      "loss": 0.2779,
      "step": 3380
    },
    {
      "epoch": 1.5885660731021556,
      "grad_norm": 2.5440433025360107,
      "learning_rate": 1.9007146204311156e-05,
      "loss": 0.3182,
      "step": 3390
    },
    {
      "epoch": 1.5932521087160263,
      "grad_norm": 2.1016016006469727,
      "learning_rate": 1.9004217432052485e-05,
      "loss": 0.3224,
      "step": 3400
    },
    {
      "epoch": 1.597938144329897,
      "grad_norm": 1.8776601552963257,
      "learning_rate": 1.9001288659793815e-05,
      "loss": 0.2926,
      "step": 3410
    },
    {
      "epoch": 1.6026241799437675,
      "grad_norm": 1.7855247259140015,
      "learning_rate": 1.8998359887535148e-05,
      "loss": 0.3087,
      "step": 3420
    },
    {
      "epoch": 1.6073102155576382,
      "grad_norm": 2.239816188812256,
      "learning_rate": 1.8995431115276477e-05,
      "loss": 0.3254,
      "step": 3430
    },
    {
      "epoch": 1.611996251171509,
      "grad_norm": 2.309274673461914,
      "learning_rate": 1.899250234301781e-05,
      "loss": 0.2741,
      "step": 3440
    },
    {
      "epoch": 1.6166822867853796,
      "grad_norm": 2.672464370727539,
      "learning_rate": 1.898957357075914e-05,
      "loss": 0.3137,
      "step": 3450
    },
    {
      "epoch": 1.6213683223992503,
      "grad_norm": 2.3761508464813232,
      "learning_rate": 1.8986644798500473e-05,
      "loss": 0.322,
      "step": 3460
    },
    {
      "epoch": 1.6260543580131208,
      "grad_norm": 2.497772216796875,
      "learning_rate": 1.8983716026241802e-05,
      "loss": 0.2832,
      "step": 3470
    },
    {
      "epoch": 1.6307403936269915,
      "grad_norm": 2.2633016109466553,
      "learning_rate": 1.898078725398313e-05,
      "loss": 0.2659,
      "step": 3480
    },
    {
      "epoch": 1.6354264292408622,
      "grad_norm": 2.2554588317871094,
      "learning_rate": 1.897785848172446e-05,
      "loss": 0.3039,
      "step": 3490
    },
    {
      "epoch": 1.640112464854733,
      "grad_norm": 2.0419113636016846,
      "learning_rate": 1.8974929709465794e-05,
      "loss": 0.26,
      "step": 3500
    },
    {
      "epoch": 1.640112464854733,
      "eval_loss": 0.06864778697490692,
      "eval_pearson_cosine": 0.7792468184875077,
      "eval_pearson_dot": 0.6003709070725307,
      "eval_pearson_euclidean": 0.762291216964627,
      "eval_pearson_manhattan": 0.7615198846806042,
      "eval_runtime": 3.2918,
      "eval_samples_per_second": 455.681,
      "eval_spearman_cosine": 0.7902077133733839,
      "eval_spearman_dot": 0.5998471986095437,
      "eval_spearman_euclidean": 0.7733862684662854,
      "eval_spearman_manhattan": 0.7732713082323596,
      "eval_steps_per_second": 28.556,
      "step": 3500
    },
    {
      "epoch": 1.6447985004686037,
      "grad_norm": 2.1808488368988037,
      "learning_rate": 1.8972000937207123e-05,
      "loss": 0.2977,
      "step": 3510
    },
    {
      "epoch": 1.6494845360824741,
      "grad_norm": 2.5023481845855713,
      "learning_rate": 1.8969072164948453e-05,
      "loss": 0.3275,
      "step": 3520
    },
    {
      "epoch": 1.6541705716963448,
      "grad_norm": 1.9074852466583252,
      "learning_rate": 1.8966143392689786e-05,
      "loss": 0.3084,
      "step": 3530
    },
    {
      "epoch": 1.6588566073102156,
      "grad_norm": 2.4666028022766113,
      "learning_rate": 1.8963214620431115e-05,
      "loss": 0.3202,
      "step": 3540
    },
    {
      "epoch": 1.6635426429240863,
      "grad_norm": 2.2712929248809814,
      "learning_rate": 1.8960285848172448e-05,
      "loss": 0.3023,
      "step": 3550
    },
    {
      "epoch": 1.668228678537957,
      "grad_norm": 2.274965286254883,
      "learning_rate": 1.8957357075913778e-05,
      "loss": 0.3134,
      "step": 3560
    },
    {
      "epoch": 1.6729147141518275,
      "grad_norm": 2.2933590412139893,
      "learning_rate": 1.895442830365511e-05,
      "loss": 0.2935,
      "step": 3570
    },
    {
      "epoch": 1.6776007497656982,
      "grad_norm": 2.492459774017334,
      "learning_rate": 1.895149953139644e-05,
      "loss": 0.2891,
      "step": 3580
    },
    {
      "epoch": 1.6822867853795689,
      "grad_norm": 2.4401142597198486,
      "learning_rate": 1.894857075913777e-05,
      "loss": 0.329,
      "step": 3590
    },
    {
      "epoch": 1.6869728209934396,
      "grad_norm": 2.0816047191619873,
      "learning_rate": 1.8945641986879102e-05,
      "loss": 0.3042,
      "step": 3600
    },
    {
      "epoch": 1.6916588566073103,
      "grad_norm": 2.2334861755371094,
      "learning_rate": 1.8942713214620432e-05,
      "loss": 0.2909,
      "step": 3610
    },
    {
      "epoch": 1.6963448922211808,
      "grad_norm": 2.3555166721343994,
      "learning_rate": 1.8939784442361765e-05,
      "loss": 0.3284,
      "step": 3620
    },
    {
      "epoch": 1.7010309278350515,
      "grad_norm": 1.751710295677185,
      "learning_rate": 1.8936855670103094e-05,
      "loss": 0.2848,
      "step": 3630
    },
    {
      "epoch": 1.7057169634489222,
      "grad_norm": 1.920424461364746,
      "learning_rate": 1.8933926897844427e-05,
      "loss": 0.279,
      "step": 3640
    },
    {
      "epoch": 1.710402999062793,
      "grad_norm": 2.840911865234375,
      "learning_rate": 1.8930998125585757e-05,
      "loss": 0.3116,
      "step": 3650
    },
    {
      "epoch": 1.7150890346766636,
      "grad_norm": 2.429884672164917,
      "learning_rate": 1.8928069353327086e-05,
      "loss": 0.264,
      "step": 3660
    },
    {
      "epoch": 1.7197750702905341,
      "grad_norm": 2.2484772205352783,
      "learning_rate": 1.892514058106842e-05,
      "loss": 0.3201,
      "step": 3670
    },
    {
      "epoch": 1.7244611059044048,
      "grad_norm": 2.342460870742798,
      "learning_rate": 1.892221180880975e-05,
      "loss": 0.3068,
      "step": 3680
    },
    {
      "epoch": 1.7291471415182755,
      "grad_norm": 2.332886219024658,
      "learning_rate": 1.8919283036551078e-05,
      "loss": 0.3238,
      "step": 3690
    },
    {
      "epoch": 1.7338331771321462,
      "grad_norm": 1.7878814935684204,
      "learning_rate": 1.8916354264292408e-05,
      "loss": 0.2866,
      "step": 3700
    },
    {
      "epoch": 1.738519212746017,
      "grad_norm": 2.455904722213745,
      "learning_rate": 1.891342549203374e-05,
      "loss": 0.2887,
      "step": 3710
    },
    {
      "epoch": 1.7432052483598874,
      "grad_norm": 2.273310899734497,
      "learning_rate": 1.891049671977507e-05,
      "loss": 0.3377,
      "step": 3720
    },
    {
      "epoch": 1.7478912839737581,
      "grad_norm": 2.77280592918396,
      "learning_rate": 1.8907567947516403e-05,
      "loss": 0.2928,
      "step": 3730
    },
    {
      "epoch": 1.7525773195876289,
      "grad_norm": 2.2917518615722656,
      "learning_rate": 1.8904639175257732e-05,
      "loss": 0.3154,
      "step": 3740
    },
    {
      "epoch": 1.7572633552014996,
      "grad_norm": 3.0059680938720703,
      "learning_rate": 1.8901710402999065e-05,
      "loss": 0.3216,
      "step": 3750
    },
    {
      "epoch": 1.7572633552014996,
      "eval_loss": 0.07067140191793442,
      "eval_pearson_cosine": 0.7850573661327331,
      "eval_pearson_dot": 0.6098455249231733,
      "eval_pearson_euclidean": 0.7677167356750871,
      "eval_pearson_manhattan": 0.7668202443827852,
      "eval_runtime": 3.5184,
      "eval_samples_per_second": 426.329,
      "eval_spearman_cosine": 0.7949681180333369,
      "eval_spearman_dot": 0.6135646781276878,
      "eval_spearman_euclidean": 0.7791366533328872,
      "eval_spearman_manhattan": 0.7786680488005274,
      "eval_steps_per_second": 26.717,
      "step": 3750
    },
    {
      "epoch": 1.7619493908153703,
      "grad_norm": 2.2580602169036865,
      "learning_rate": 1.8898781630740395e-05,
      "loss": 0.2838,
      "step": 3760
    },
    {
      "epoch": 1.7666354264292408,
      "grad_norm": 2.6639926433563232,
      "learning_rate": 1.8895852858481728e-05,
      "loss": 0.3388,
      "step": 3770
    },
    {
      "epoch": 1.7713214620431117,
      "grad_norm": 2.4491138458251953,
      "learning_rate": 1.8892924086223057e-05,
      "loss": 0.2905,
      "step": 3780
    },
    {
      "epoch": 1.7760074976569822,
      "grad_norm": 2.4412620067596436,
      "learning_rate": 1.8889995313964387e-05,
      "loss": 0.2982,
      "step": 3790
    },
    {
      "epoch": 1.780693533270853,
      "grad_norm": 2.356416702270508,
      "learning_rate": 1.888706654170572e-05,
      "loss": 0.3302,
      "step": 3800
    },
    {
      "epoch": 1.7853795688847236,
      "grad_norm": 2.3429980278015137,
      "learning_rate": 1.888413776944705e-05,
      "loss": 0.3069,
      "step": 3810
    },
    {
      "epoch": 1.790065604498594,
      "grad_norm": 2.228518486022949,
      "learning_rate": 1.8881208997188382e-05,
      "loss": 0.3016,
      "step": 3820
    },
    {
      "epoch": 1.794751640112465,
      "grad_norm": 2.8037281036376953,
      "learning_rate": 1.887828022492971e-05,
      "loss": 0.3324,
      "step": 3830
    },
    {
      "epoch": 1.7994376757263355,
      "grad_norm": 1.893836498260498,
      "learning_rate": 1.887535145267104e-05,
      "loss": 0.2592,
      "step": 3840
    },
    {
      "epoch": 1.8041237113402062,
      "grad_norm": 2.6253368854522705,
      "learning_rate": 1.8872422680412374e-05,
      "loss": 0.295,
      "step": 3850
    },
    {
      "epoch": 1.808809746954077,
      "grad_norm": 2.2410082817077637,
      "learning_rate": 1.8869493908153703e-05,
      "loss": 0.2495,
      "step": 3860
    },
    {
      "epoch": 1.8134957825679474,
      "grad_norm": 2.3530426025390625,
      "learning_rate": 1.8866565135895033e-05,
      "loss": 0.3004,
      "step": 3870
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 2.178670644760132,
      "learning_rate": 1.8863636363636366e-05,
      "loss": 0.3386,
      "step": 3880
    },
    {
      "epoch": 1.8228678537956888,
      "grad_norm": 2.0660688877105713,
      "learning_rate": 1.8860707591377695e-05,
      "loss": 0.3117,
      "step": 3890
    },
    {
      "epoch": 1.8275538894095595,
      "grad_norm": 2.5521416664123535,
      "learning_rate": 1.8857778819119025e-05,
      "loss": 0.3011,
      "step": 3900
    },
    {
      "epoch": 1.8322399250234302,
      "grad_norm": 2.3752758502960205,
      "learning_rate": 1.8854850046860358e-05,
      "loss": 0.3203,
      "step": 3910
    },
    {
      "epoch": 1.8369259606373007,
      "grad_norm": 2.0836801528930664,
      "learning_rate": 1.8851921274601687e-05,
      "loss": 0.2706,
      "step": 3920
    },
    {
      "epoch": 1.8416119962511717,
      "grad_norm": 2.767982006072998,
      "learning_rate": 1.884899250234302e-05,
      "loss": 0.3077,
      "step": 3930
    },
    {
      "epoch": 1.8462980318650422,
      "grad_norm": 2.7820098400115967,
      "learning_rate": 1.884606373008435e-05,
      "loss": 0.2991,
      "step": 3940
    },
    {
      "epoch": 1.8509840674789129,
      "grad_norm": 2.6888327598571777,
      "learning_rate": 1.8843134957825682e-05,
      "loss": 0.2862,
      "step": 3950
    },
    {
      "epoch": 1.8556701030927836,
      "grad_norm": 2.4160315990448,
      "learning_rate": 1.8840206185567012e-05,
      "loss": 0.2725,
      "step": 3960
    },
    {
      "epoch": 1.860356138706654,
      "grad_norm": 2.778198719024658,
      "learning_rate": 1.8837277413308345e-05,
      "loss": 0.3509,
      "step": 3970
    },
    {
      "epoch": 1.865042174320525,
      "grad_norm": 1.8606864213943481,
      "learning_rate": 1.8834348641049674e-05,
      "loss": 0.2971,
      "step": 3980
    },
    {
      "epoch": 1.8697282099343955,
      "grad_norm": 1.98170804977417,
      "learning_rate": 1.8831419868791004e-05,
      "loss": 0.3131,
      "step": 3990
    },
    {
      "epoch": 1.8744142455482662,
      "grad_norm": 1.828123927116394,
      "learning_rate": 1.8828491096532337e-05,
      "loss": 0.3166,
      "step": 4000
    },
    {
      "epoch": 1.8744142455482662,
      "eval_loss": 0.07189416140317917,
      "eval_pearson_cosine": 0.7798801652938181,
      "eval_pearson_dot": 0.5736722449381091,
      "eval_pearson_euclidean": 0.7563095863468678,
      "eval_pearson_manhattan": 0.7550479478827015,
      "eval_runtime": 3.2996,
      "eval_samples_per_second": 454.607,
      "eval_spearman_cosine": 0.7910837741143455,
      "eval_spearman_dot": 0.5753555851409241,
      "eval_spearman_euclidean": 0.7700926689739851,
      "eval_spearman_manhattan": 0.7692694796240825,
      "eval_steps_per_second": 28.489,
      "step": 4000
    },
    {
      "epoch": 1.879100281162137,
      "grad_norm": 1.8813470602035522,
      "learning_rate": 1.8825562324273666e-05,
      "loss": 0.2484,
      "step": 4010
    },
    {
      "epoch": 1.8837863167760074,
      "grad_norm": 2.005892038345337,
      "learning_rate": 1.8822633552014996e-05,
      "loss": 0.3137,
      "step": 4020
    },
    {
      "epoch": 1.8884723523898783,
      "grad_norm": 2.067732572555542,
      "learning_rate": 1.881970477975633e-05,
      "loss": 0.3143,
      "step": 4030
    },
    {
      "epoch": 1.8931583880037488,
      "grad_norm": 2.33829665184021,
      "learning_rate": 1.8816776007497658e-05,
      "loss": 0.3252,
      "step": 4040
    },
    {
      "epoch": 1.8978444236176195,
      "grad_norm": 1.655529260635376,
      "learning_rate": 1.8813847235238987e-05,
      "loss": 0.2889,
      "step": 4050
    },
    {
      "epoch": 1.9025304592314902,
      "grad_norm": 2.849501609802246,
      "learning_rate": 1.881091846298032e-05,
      "loss": 0.323,
      "step": 4060
    },
    {
      "epoch": 1.9072164948453607,
      "grad_norm": 2.8345351219177246,
      "learning_rate": 1.880798969072165e-05,
      "loss": 0.316,
      "step": 4070
    },
    {
      "epoch": 1.9119025304592316,
      "grad_norm": 2.061378240585327,
      "learning_rate": 1.8805060918462983e-05,
      "loss": 0.3112,
      "step": 4080
    },
    {
      "epoch": 1.9165885660731021,
      "grad_norm": 1.883039116859436,
      "learning_rate": 1.8802132146204312e-05,
      "loss": 0.2625,
      "step": 4090
    },
    {
      "epoch": 1.9212746016869728,
      "grad_norm": 2.2609167098999023,
      "learning_rate": 1.8799203373945642e-05,
      "loss": 0.3043,
      "step": 4100
    },
    {
      "epoch": 1.9259606373008435,
      "grad_norm": 2.27116060256958,
      "learning_rate": 1.8796274601686975e-05,
      "loss": 0.3022,
      "step": 4110
    },
    {
      "epoch": 1.930646672914714,
      "grad_norm": 1.9829683303833008,
      "learning_rate": 1.8793345829428304e-05,
      "loss": 0.3147,
      "step": 4120
    },
    {
      "epoch": 1.935332708528585,
      "grad_norm": 2.073610305786133,
      "learning_rate": 1.8790417057169637e-05,
      "loss": 0.2779,
      "step": 4130
    },
    {
      "epoch": 1.9400187441424555,
      "grad_norm": 2.183823585510254,
      "learning_rate": 1.8787488284910967e-05,
      "loss": 0.3041,
      "step": 4140
    },
    {
      "epoch": 1.9447047797563262,
      "grad_norm": 2.373502016067505,
      "learning_rate": 1.87845595126523e-05,
      "loss": 0.3037,
      "step": 4150
    },
    {
      "epoch": 1.9493908153701969,
      "grad_norm": 3.190950393676758,
      "learning_rate": 1.878163074039363e-05,
      "loss": 0.2876,
      "step": 4160
    },
    {
      "epoch": 1.9540768509840674,
      "grad_norm": 2.2904293537139893,
      "learning_rate": 1.8778701968134962e-05,
      "loss": 0.2957,
      "step": 4170
    },
    {
      "epoch": 1.9587628865979383,
      "grad_norm": 2.5620875358581543,
      "learning_rate": 1.877577319587629e-05,
      "loss": 0.2865,
      "step": 4180
    },
    {
      "epoch": 1.9634489222118088,
      "grad_norm": 1.8882808685302734,
      "learning_rate": 1.877284442361762e-05,
      "loss": 0.302,
      "step": 4190
    },
    {
      "epoch": 1.9681349578256795,
      "grad_norm": 2.736853837966919,
      "learning_rate": 1.876991565135895e-05,
      "loss": 0.2783,
      "step": 4200
    },
    {
      "epoch": 1.9728209934395502,
      "grad_norm": 2.6126515865325928,
      "learning_rate": 1.8766986879100283e-05,
      "loss": 0.3337,
      "step": 4210
    },
    {
      "epoch": 1.9775070290534207,
      "grad_norm": 1.9608129262924194,
      "learning_rate": 1.8764058106841613e-05,
      "loss": 0.2817,
      "step": 4220
    },
    {
      "epoch": 1.9821930646672916,
      "grad_norm": 2.7429044246673584,
      "learning_rate": 1.8761129334582942e-05,
      "loss": 0.2827,
      "step": 4230
    },
    {
      "epoch": 1.986879100281162,
      "grad_norm": 2.322411298751831,
      "learning_rate": 1.8758200562324275e-05,
      "loss": 0.2967,
      "step": 4240
    },
    {
      "epoch": 1.9915651358950328,
      "grad_norm": 1.80522882938385,
      "learning_rate": 1.8755271790065605e-05,
      "loss": 0.315,
      "step": 4250
    },
    {
      "epoch": 1.9915651358950328,
      "eval_loss": 0.0709637850522995,
      "eval_pearson_cosine": 0.7818087092412611,
      "eval_pearson_dot": 0.5917647670204929,
      "eval_pearson_euclidean": 0.7671767812906438,
      "eval_pearson_manhattan": 0.7657443892799449,
      "eval_runtime": 3.3617,
      "eval_samples_per_second": 446.198,
      "eval_spearman_cosine": 0.7925261968709182,
      "eval_spearman_dot": 0.5930341342679433,
      "eval_spearman_euclidean": 0.7790026457642986,
      "eval_spearman_manhattan": 0.7779600937996545,
      "eval_steps_per_second": 27.962,
      "step": 4250
    },
    {
      "epoch": 1.9962511715089035,
      "grad_norm": 2.3154516220092773,
      "learning_rate": 1.8752343017806937e-05,
      "loss": 0.3019,
      "step": 4260
    },
    {
      "epoch": 2.000937207122774,
      "grad_norm": 1.769853949546814,
      "learning_rate": 1.8749414245548267e-05,
      "loss": 0.2639,
      "step": 4270
    },
    {
      "epoch": 2.005623242736645,
      "grad_norm": 2.7089197635650635,
      "learning_rate": 1.87464854732896e-05,
      "loss": 0.1872,
      "step": 4280
    },
    {
      "epoch": 2.0103092783505154,
      "grad_norm": 2.1212291717529297,
      "learning_rate": 1.874355670103093e-05,
      "loss": 0.189,
      "step": 4290
    },
    {
      "epoch": 2.014995313964386,
      "grad_norm": 1.8745218515396118,
      "learning_rate": 1.874062792877226e-05,
      "loss": 0.1749,
      "step": 4300
    },
    {
      "epoch": 2.019681349578257,
      "grad_norm": 2.0145514011383057,
      "learning_rate": 1.8737699156513592e-05,
      "loss": 0.1809,
      "step": 4310
    },
    {
      "epoch": 2.0243673851921273,
      "grad_norm": 2.370055913925171,
      "learning_rate": 1.873477038425492e-05,
      "loss": 0.2056,
      "step": 4320
    },
    {
      "epoch": 2.0290534208059983,
      "grad_norm": 1.7560367584228516,
      "learning_rate": 1.8731841611996254e-05,
      "loss": 0.1742,
      "step": 4330
    },
    {
      "epoch": 2.0337394564198688,
      "grad_norm": 2.693603277206421,
      "learning_rate": 1.8728912839737584e-05,
      "loss": 0.2017,
      "step": 4340
    },
    {
      "epoch": 2.0384254920337392,
      "grad_norm": 2.1456475257873535,
      "learning_rate": 1.8725984067478917e-05,
      "loss": 0.1967,
      "step": 4350
    },
    {
      "epoch": 2.04311152764761,
      "grad_norm": 1.8832343816757202,
      "learning_rate": 1.8723055295220246e-05,
      "loss": 0.182,
      "step": 4360
    },
    {
      "epoch": 2.0477975632614807,
      "grad_norm": 2.2446205615997314,
      "learning_rate": 1.8720126522961576e-05,
      "loss": 0.1895,
      "step": 4370
    },
    {
      "epoch": 2.0524835988753516,
      "grad_norm": 1.8662675619125366,
      "learning_rate": 1.871719775070291e-05,
      "loss": 0.2091,
      "step": 4380
    },
    {
      "epoch": 2.057169634489222,
      "grad_norm": 2.3427059650421143,
      "learning_rate": 1.8714268978444238e-05,
      "loss": 0.2046,
      "step": 4390
    },
    {
      "epoch": 2.0618556701030926,
      "grad_norm": 1.8921583890914917,
      "learning_rate": 1.8711340206185567e-05,
      "loss": 0.21,
      "step": 4400
    },
    {
      "epoch": 2.0665417057169635,
      "grad_norm": 2.3345112800598145,
      "learning_rate": 1.8708411433926897e-05,
      "loss": 0.211,
      "step": 4410
    },
    {
      "epoch": 2.071227741330834,
      "grad_norm": 2.8094024658203125,
      "learning_rate": 1.870548266166823e-05,
      "loss": 0.185,
      "step": 4420
    },
    {
      "epoch": 2.075913776944705,
      "grad_norm": 2.182375192642212,
      "learning_rate": 1.870255388940956e-05,
      "loss": 0.1743,
      "step": 4430
    },
    {
      "epoch": 2.0805998125585754,
      "grad_norm": 1.9309943914413452,
      "learning_rate": 1.8699625117150892e-05,
      "loss": 0.2002,
      "step": 4440
    },
    {
      "epoch": 2.085285848172446,
      "grad_norm": 2.410891532897949,
      "learning_rate": 1.869669634489222e-05,
      "loss": 0.2034,
      "step": 4450
    },
    {
      "epoch": 2.089971883786317,
      "grad_norm": 1.9030256271362305,
      "learning_rate": 1.8693767572633555e-05,
      "loss": 0.1985,
      "step": 4460
    },
    {
      "epoch": 2.0946579194001873,
      "grad_norm": 2.387491226196289,
      "learning_rate": 1.8690838800374884e-05,
      "loss": 0.1657,
      "step": 4470
    },
    {
      "epoch": 2.0993439550140582,
      "grad_norm": 2.448557138442993,
      "learning_rate": 1.8687910028116217e-05,
      "loss": 0.1889,
      "step": 4480
    },
    {
      "epoch": 2.1040299906279287,
      "grad_norm": 1.8442336320877075,
      "learning_rate": 1.8684981255857546e-05,
      "loss": 0.1638,
      "step": 4490
    },
    {
      "epoch": 2.108716026241799,
      "grad_norm": 2.192814588546753,
      "learning_rate": 1.8682052483598876e-05,
      "loss": 0.2117,
      "step": 4500
    },
    {
      "epoch": 2.108716026241799,
      "eval_loss": 0.0544867068529129,
      "eval_pearson_cosine": 0.7772149225219422,
      "eval_pearson_dot": 0.6058722441499071,
      "eval_pearson_euclidean": 0.7566861769282127,
      "eval_pearson_manhattan": 0.7550653692259459,
      "eval_runtime": 3.562,
      "eval_samples_per_second": 421.112,
      "eval_spearman_cosine": 0.7889882574404774,
      "eval_spearman_dot": 0.609585139530218,
      "eval_spearman_euclidean": 0.7711664957300913,
      "eval_spearman_manhattan": 0.7702480077346849,
      "eval_steps_per_second": 26.39,
      "step": 4500
    },
    {
      "epoch": 2.11340206185567,
      "grad_norm": 1.964051604270935,
      "learning_rate": 1.867912371134021e-05,
      "loss": 0.1727,
      "step": 4510
    },
    {
      "epoch": 2.1180880974695406,
      "grad_norm": 2.180359363555908,
      "learning_rate": 1.867619493908154e-05,
      "loss": 0.1929,
      "step": 4520
    },
    {
      "epoch": 2.1227741330834116,
      "grad_norm": 1.5920389890670776,
      "learning_rate": 1.867326616682287e-05,
      "loss": 0.215,
      "step": 4530
    },
    {
      "epoch": 2.127460168697282,
      "grad_norm": 2.0330374240875244,
      "learning_rate": 1.86703373945642e-05,
      "loss": 0.1782,
      "step": 4540
    },
    {
      "epoch": 2.1321462043111525,
      "grad_norm": 3.1396799087524414,
      "learning_rate": 1.866740862230553e-05,
      "loss": 0.1843,
      "step": 4550
    },
    {
      "epoch": 2.1368322399250235,
      "grad_norm": 2.507819652557373,
      "learning_rate": 1.8664479850046863e-05,
      "loss": 0.2272,
      "step": 4560
    },
    {
      "epoch": 2.141518275538894,
      "grad_norm": 1.9377321004867554,
      "learning_rate": 1.8661551077788193e-05,
      "loss": 0.2003,
      "step": 4570
    },
    {
      "epoch": 2.146204311152765,
      "grad_norm": 2.868741512298584,
      "learning_rate": 1.8658622305529522e-05,
      "loss": 0.2266,
      "step": 4580
    },
    {
      "epoch": 2.1508903467666354,
      "grad_norm": 1.8727847337722778,
      "learning_rate": 1.8655693533270855e-05,
      "loss": 0.1965,
      "step": 4590
    },
    {
      "epoch": 2.155576382380506,
      "grad_norm": 1.937414526939392,
      "learning_rate": 1.8652764761012184e-05,
      "loss": 0.1957,
      "step": 4600
    },
    {
      "epoch": 2.160262417994377,
      "grad_norm": 2.084174156188965,
      "learning_rate": 1.8649835988753514e-05,
      "loss": 0.1668,
      "step": 4610
    },
    {
      "epoch": 2.1649484536082473,
      "grad_norm": 1.846552848815918,
      "learning_rate": 1.8646907216494847e-05,
      "loss": 0.184,
      "step": 4620
    },
    {
      "epoch": 2.169634489222118,
      "grad_norm": 1.9087766408920288,
      "learning_rate": 1.8643978444236176e-05,
      "loss": 0.1961,
      "step": 4630
    },
    {
      "epoch": 2.1743205248359887,
      "grad_norm": 2.011108875274658,
      "learning_rate": 1.864104967197751e-05,
      "loss": 0.1848,
      "step": 4640
    },
    {
      "epoch": 2.179006560449859,
      "grad_norm": 2.8976380825042725,
      "learning_rate": 1.863812089971884e-05,
      "loss": 0.2082,
      "step": 4650
    },
    {
      "epoch": 2.18369259606373,
      "grad_norm": 2.1731081008911133,
      "learning_rate": 1.863519212746017e-05,
      "loss": 0.1852,
      "step": 4660
    },
    {
      "epoch": 2.1883786316776006,
      "grad_norm": 1.7672990560531616,
      "learning_rate": 1.86322633552015e-05,
      "loss": 0.2023,
      "step": 4670
    },
    {
      "epoch": 2.1930646672914715,
      "grad_norm": 1.6886131763458252,
      "learning_rate": 1.8629334582942834e-05,
      "loss": 0.2126,
      "step": 4680
    },
    {
      "epoch": 2.197750702905342,
      "grad_norm": 1.4913769960403442,
      "learning_rate": 1.8626405810684164e-05,
      "loss": 0.1836,
      "step": 4690
    },
    {
      "epoch": 2.2024367385192125,
      "grad_norm": 2.0632176399230957,
      "learning_rate": 1.8623477038425493e-05,
      "loss": 0.2048,
      "step": 4700
    },
    {
      "epoch": 2.2071227741330834,
      "grad_norm": 1.9084508419036865,
      "learning_rate": 1.8620548266166826e-05,
      "loss": 0.1836,
      "step": 4710
    },
    {
      "epoch": 2.211808809746954,
      "grad_norm": 1.9352916479110718,
      "learning_rate": 1.8617619493908155e-05,
      "loss": 0.1653,
      "step": 4720
    },
    {
      "epoch": 2.216494845360825,
      "grad_norm": 1.974461317062378,
      "learning_rate": 1.8614690721649485e-05,
      "loss": 0.2053,
      "step": 4730
    },
    {
      "epoch": 2.2211808809746953,
      "grad_norm": 2.1307456493377686,
      "learning_rate": 1.8611761949390818e-05,
      "loss": 0.1835,
      "step": 4740
    },
    {
      "epoch": 2.2258669165885663,
      "grad_norm": 1.413037896156311,
      "learning_rate": 1.8608833177132147e-05,
      "loss": 0.1725,
      "step": 4750
    },
    {
      "epoch": 2.2258669165885663,
      "eval_loss": 0.05439988151192665,
      "eval_pearson_cosine": 0.7779719017710534,
      "eval_pearson_dot": 0.6064920766481805,
      "eval_pearson_euclidean": 0.7604967084059453,
      "eval_pearson_manhattan": 0.7592805758538006,
      "eval_runtime": 3.2739,
      "eval_samples_per_second": 458.175,
      "eval_spearman_cosine": 0.786759628149343,
      "eval_spearman_dot": 0.6127818290418755,
      "eval_spearman_euclidean": 0.7721037448944629,
      "eval_spearman_manhattan": 0.7714373415381524,
      "eval_steps_per_second": 28.712,
      "step": 4750
    },
    {
      "epoch": 2.2305529522024368,
      "grad_norm": 2.033710241317749,
      "learning_rate": 1.8605904404873477e-05,
      "loss": 0.1769,
      "step": 4760
    },
    {
      "epoch": 2.2352389878163073,
      "grad_norm": 2.065793752670288,
      "learning_rate": 1.860297563261481e-05,
      "loss": 0.1896,
      "step": 4770
    },
    {
      "epoch": 2.239925023430178,
      "grad_norm": 2.0393176078796387,
      "learning_rate": 1.860004686035614e-05,
      "loss": 0.1944,
      "step": 4780
    },
    {
      "epoch": 2.2446110590440487,
      "grad_norm": 1.967092514038086,
      "learning_rate": 1.859711808809747e-05,
      "loss": 0.218,
      "step": 4790
    },
    {
      "epoch": 2.2492970946579196,
      "grad_norm": 2.614811420440674,
      "learning_rate": 1.85941893158388e-05,
      "loss": 0.2158,
      "step": 4800
    },
    {
      "epoch": 2.25398313027179,
      "grad_norm": 1.9915626049041748,
      "learning_rate": 1.859126054358013e-05,
      "loss": 0.199,
      "step": 4810
    },
    {
      "epoch": 2.2586691658856606,
      "grad_norm": 2.308933973312378,
      "learning_rate": 1.8588331771321464e-05,
      "loss": 0.1746,
      "step": 4820
    },
    {
      "epoch": 2.2633552014995315,
      "grad_norm": 2.2984583377838135,
      "learning_rate": 1.8585402999062793e-05,
      "loss": 0.1905,
      "step": 4830
    },
    {
      "epoch": 2.268041237113402,
      "grad_norm": 2.0273101329803467,
      "learning_rate": 1.8582474226804126e-05,
      "loss": 0.1655,
      "step": 4840
    },
    {
      "epoch": 2.2727272727272725,
      "grad_norm": 1.745671272277832,
      "learning_rate": 1.8579545454545456e-05,
      "loss": 0.1745,
      "step": 4850
    },
    {
      "epoch": 2.2774133083411434,
      "grad_norm": 1.9413400888442993,
      "learning_rate": 1.857661668228679e-05,
      "loss": 0.1899,
      "step": 4860
    },
    {
      "epoch": 2.282099343955014,
      "grad_norm": 2.113260269165039,
      "learning_rate": 1.8573687910028118e-05,
      "loss": 0.1826,
      "step": 4870
    },
    {
      "epoch": 2.286785379568885,
      "grad_norm": 1.9468377828598022,
      "learning_rate": 1.857075913776945e-05,
      "loss": 0.1596,
      "step": 4880
    },
    {
      "epoch": 2.2914714151827553,
      "grad_norm": 2.1250803470611572,
      "learning_rate": 1.856783036551078e-05,
      "loss": 0.1969,
      "step": 4890
    },
    {
      "epoch": 2.296157450796626,
      "grad_norm": 1.5394418239593506,
      "learning_rate": 1.856490159325211e-05,
      "loss": 0.1731,
      "step": 4900
    },
    {
      "epoch": 2.3008434864104967,
      "grad_norm": 2.2445003986358643,
      "learning_rate": 1.8561972820993443e-05,
      "loss": 0.1817,
      "step": 4910
    },
    {
      "epoch": 2.3055295220243672,
      "grad_norm": 2.201733350753784,
      "learning_rate": 1.8559044048734773e-05,
      "loss": 0.175,
      "step": 4920
    },
    {
      "epoch": 2.310215557638238,
      "grad_norm": 2.077092409133911,
      "learning_rate": 1.8556115276476102e-05,
      "loss": 0.1755,
      "step": 4930
    },
    {
      "epoch": 2.3149015932521086,
      "grad_norm": 2.0630977153778076,
      "learning_rate": 1.855318650421743e-05,
      "loss": 0.1967,
      "step": 4940
    },
    {
      "epoch": 2.319587628865979,
      "grad_norm": 2.737861156463623,
      "learning_rate": 1.8550257731958764e-05,
      "loss": 0.2175,
      "step": 4950
    },
    {
      "epoch": 2.32427366447985,
      "grad_norm": 2.0301871299743652,
      "learning_rate": 1.8547328959700094e-05,
      "loss": 0.1938,
      "step": 4960
    },
    {
      "epoch": 2.3289597000937206,
      "grad_norm": 1.6436868906021118,
      "learning_rate": 1.8544400187441427e-05,
      "loss": 0.2215,
      "step": 4970
    },
    {
      "epoch": 2.3336457357075915,
      "grad_norm": 2.0046422481536865,
      "learning_rate": 1.8541471415182756e-05,
      "loss": 0.189,
      "step": 4980
    },
    {
      "epoch": 2.338331771321462,
      "grad_norm": 2.598639488220215,
      "learning_rate": 1.8538542642924086e-05,
      "loss": 0.2075,
      "step": 4990
    },
    {
      "epoch": 2.3430178069353325,
      "grad_norm": 1.8523390293121338,
      "learning_rate": 1.853561387066542e-05,
      "loss": 0.1985,
      "step": 5000
    },
    {
      "epoch": 2.3430178069353325,
      "eval_loss": 0.05401456356048584,
      "eval_pearson_cosine": 0.781767118943602,
      "eval_pearson_dot": 0.6017329721420595,
      "eval_pearson_euclidean": 0.7626066877478763,
      "eval_pearson_manhattan": 0.7620550203728129,
      "eval_runtime": 3.2064,
      "eval_samples_per_second": 467.808,
      "eval_spearman_cosine": 0.7915644905642973,
      "eval_spearman_dot": 0.6077979618715047,
      "eval_spearman_euclidean": 0.773425356513352,
      "eval_spearman_manhattan": 0.7732819218811388,
      "eval_steps_per_second": 29.316,
      "step": 5000
    },
    {
      "epoch": 2.3477038425492034,
      "grad_norm": 2.0773608684539795,
      "learning_rate": 1.8532685098406748e-05,
      "loss": 0.1749,
      "step": 5010
    },
    {
      "epoch": 2.352389878163074,
      "grad_norm": 1.6482021808624268,
      "learning_rate": 1.852975632614808e-05,
      "loss": 0.1719,
      "step": 5020
    },
    {
      "epoch": 2.357075913776945,
      "grad_norm": 2.1038990020751953,
      "learning_rate": 1.852682755388941e-05,
      "loss": 0.2014,
      "step": 5030
    },
    {
      "epoch": 2.3617619493908153,
      "grad_norm": 2.396871566772461,
      "learning_rate": 1.8523898781630743e-05,
      "loss": 0.1855,
      "step": 5040
    },
    {
      "epoch": 2.3664479850046862,
      "grad_norm": 2.3098223209381104,
      "learning_rate": 1.8520970009372073e-05,
      "loss": 0.1819,
      "step": 5050
    },
    {
      "epoch": 2.3711340206185567,
      "grad_norm": 1.9691858291625977,
      "learning_rate": 1.8518041237113406e-05,
      "loss": 0.1786,
      "step": 5060
    },
    {
      "epoch": 2.375820056232427,
      "grad_norm": 2.8055005073547363,
      "learning_rate": 1.8515112464854735e-05,
      "loss": 0.1864,
      "step": 5070
    },
    {
      "epoch": 2.380506091846298,
      "grad_norm": 2.2753820419311523,
      "learning_rate": 1.8512183692596065e-05,
      "loss": 0.1918,
      "step": 5080
    },
    {
      "epoch": 2.3851921274601686,
      "grad_norm": 1.632279634475708,
      "learning_rate": 1.8509254920337398e-05,
      "loss": 0.1767,
      "step": 5090
    },
    {
      "epoch": 2.3898781630740396,
      "grad_norm": 2.177457571029663,
      "learning_rate": 1.8506326148078727e-05,
      "loss": 0.1866,
      "step": 5100
    },
    {
      "epoch": 2.39456419868791,
      "grad_norm": 1.8641494512557983,
      "learning_rate": 1.8503397375820057e-05,
      "loss": 0.1833,
      "step": 5110
    },
    {
      "epoch": 2.3992502343017805,
      "grad_norm": 2.0116262435913086,
      "learning_rate": 1.8500468603561386e-05,
      "loss": 0.1975,
      "step": 5120
    },
    {
      "epoch": 2.4039362699156515,
      "grad_norm": 1.130846381187439,
      "learning_rate": 1.849753983130272e-05,
      "loss": 0.1992,
      "step": 5130
    },
    {
      "epoch": 2.408622305529522,
      "grad_norm": 2.743990421295166,
      "learning_rate": 1.849461105904405e-05,
      "loss": 0.1996,
      "step": 5140
    },
    {
      "epoch": 2.413308341143393,
      "grad_norm": 2.4368762969970703,
      "learning_rate": 1.849168228678538e-05,
      "loss": 0.1722,
      "step": 5150
    },
    {
      "epoch": 2.4179943767572634,
      "grad_norm": 2.659679889678955,
      "learning_rate": 1.848875351452671e-05,
      "loss": 0.1834,
      "step": 5160
    },
    {
      "epoch": 2.422680412371134,
      "grad_norm": 1.9601231813430786,
      "learning_rate": 1.8485824742268044e-05,
      "loss": 0.1943,
      "step": 5170
    },
    {
      "epoch": 2.427366447985005,
      "grad_norm": 1.521337628364563,
      "learning_rate": 1.8482895970009373e-05,
      "loss": 0.2009,
      "step": 5180
    },
    {
      "epoch": 2.4320524835988753,
      "grad_norm": 1.4766628742218018,
      "learning_rate": 1.8479967197750703e-05,
      "loss": 0.1848,
      "step": 5190
    },
    {
      "epoch": 2.436738519212746,
      "grad_norm": 2.3502743244171143,
      "learning_rate": 1.8477038425492036e-05,
      "loss": 0.165,
      "step": 5200
    },
    {
      "epoch": 2.4414245548266167,
      "grad_norm": 1.5100184679031372,
      "learning_rate": 1.8474109653233365e-05,
      "loss": 0.1983,
      "step": 5210
    },
    {
      "epoch": 2.446110590440487,
      "grad_norm": 2.336106061935425,
      "learning_rate": 1.8471180880974698e-05,
      "loss": 0.1871,
      "step": 5220
    },
    {
      "epoch": 2.450796626054358,
      "grad_norm": 2.1695876121520996,
      "learning_rate": 1.8468252108716028e-05,
      "loss": 0.1996,
      "step": 5230
    },
    {
      "epoch": 2.4554826616682286,
      "grad_norm": 2.047522783279419,
      "learning_rate": 1.846532333645736e-05,
      "loss": 0.2088,
      "step": 5240
    },
    {
      "epoch": 2.4601686972820995,
      "grad_norm": 1.9469248056411743,
      "learning_rate": 1.846239456419869e-05,
      "loss": 0.1871,
      "step": 5250
    },
    {
      "epoch": 2.4601686972820995,
      "eval_loss": 0.05267513543367386,
      "eval_pearson_cosine": 0.7830377509621513,
      "eval_pearson_dot": 0.5843463467596735,
      "eval_pearson_euclidean": 0.7586592990276699,
      "eval_pearson_manhattan": 0.7576312827364555,
      "eval_runtime": 3.3095,
      "eval_samples_per_second": 453.24,
      "eval_spearman_cosine": 0.7898144287463136,
      "eval_spearman_dot": 0.5893690662486756,
      "eval_spearman_euclidean": 0.7723820863953171,
      "eval_spearman_manhattan": 0.7718409919252442,
      "eval_steps_per_second": 28.403,
      "step": 5250
    },
    {
      "epoch": 2.46485473289597,
      "grad_norm": 2.1970055103302,
      "learning_rate": 1.845946579194002e-05,
      "loss": 0.2059,
      "step": 5260
    },
    {
      "epoch": 2.4695407685098405,
      "grad_norm": 1.7079726457595825,
      "learning_rate": 1.8456537019681352e-05,
      "loss": 0.1677,
      "step": 5270
    },
    {
      "epoch": 2.4742268041237114,
      "grad_norm": 2.1129045486450195,
      "learning_rate": 1.8453608247422682e-05,
      "loss": 0.1774,
      "step": 5280
    },
    {
      "epoch": 2.478912839737582,
      "grad_norm": 2.0570807456970215,
      "learning_rate": 1.845067947516401e-05,
      "loss": 0.1863,
      "step": 5290
    },
    {
      "epoch": 2.483598875351453,
      "grad_norm": 2.095052719116211,
      "learning_rate": 1.8447750702905344e-05,
      "loss": 0.1675,
      "step": 5300
    },
    {
      "epoch": 2.4882849109653233,
      "grad_norm": 2.5408618450164795,
      "learning_rate": 1.8444821930646674e-05,
      "loss": 0.2033,
      "step": 5310
    },
    {
      "epoch": 2.492970946579194,
      "grad_norm": 2.0885772705078125,
      "learning_rate": 1.8441893158388003e-05,
      "loss": 0.178,
      "step": 5320
    },
    {
      "epoch": 2.4976569821930648,
      "grad_norm": 2.907564640045166,
      "learning_rate": 1.8438964386129336e-05,
      "loss": 0.2121,
      "step": 5330
    },
    {
      "epoch": 2.5023430178069352,
      "grad_norm": 1.3953640460968018,
      "learning_rate": 1.8436035613870666e-05,
      "loss": 0.1838,
      "step": 5340
    },
    {
      "epoch": 2.5070290534208057,
      "grad_norm": 1.825296401977539,
      "learning_rate": 1.8433106841612e-05,
      "loss": 0.1688,
      "step": 5350
    },
    {
      "epoch": 2.5117150890346767,
      "grad_norm": 2.5563881397247314,
      "learning_rate": 1.8430178069353328e-05,
      "loss": 0.1798,
      "step": 5360
    },
    {
      "epoch": 2.5164011246485476,
      "grad_norm": 2.355055570602417,
      "learning_rate": 1.842724929709466e-05,
      "loss": 0.1858,
      "step": 5370
    },
    {
      "epoch": 2.521087160262418,
      "grad_norm": 2.4546165466308594,
      "learning_rate": 1.842432052483599e-05,
      "loss": 0.2149,
      "step": 5380
    },
    {
      "epoch": 2.5257731958762886,
      "grad_norm": 2.0621817111968994,
      "learning_rate": 1.842139175257732e-05,
      "loss": 0.2215,
      "step": 5390
    },
    {
      "epoch": 2.530459231490159,
      "grad_norm": 1.7873655557632446,
      "learning_rate": 1.8418462980318653e-05,
      "loss": 0.1872,
      "step": 5400
    },
    {
      "epoch": 2.53514526710403,
      "grad_norm": 1.8408267498016357,
      "learning_rate": 1.8415534208059982e-05,
      "loss": 0.181,
      "step": 5410
    },
    {
      "epoch": 2.539831302717901,
      "grad_norm": 2.56502628326416,
      "learning_rate": 1.8412605435801315e-05,
      "loss": 0.1946,
      "step": 5420
    },
    {
      "epoch": 2.5445173383317714,
      "grad_norm": 1.9909722805023193,
      "learning_rate": 1.8409676663542645e-05,
      "loss": 0.1912,
      "step": 5430
    },
    {
      "epoch": 2.549203373945642,
      "grad_norm": 2.530014753341675,
      "learning_rate": 1.8406747891283974e-05,
      "loss": 0.1898,
      "step": 5440
    },
    {
      "epoch": 2.5538894095595124,
      "grad_norm": 2.452223300933838,
      "learning_rate": 1.8403819119025307e-05,
      "loss": 0.2114,
      "step": 5450
    },
    {
      "epoch": 2.5585754451733833,
      "grad_norm": 2.0805137157440186,
      "learning_rate": 1.8400890346766637e-05,
      "loss": 0.2237,
      "step": 5460
    },
    {
      "epoch": 2.5632614807872542,
      "grad_norm": 1.8469469547271729,
      "learning_rate": 1.8397961574507966e-05,
      "loss": 0.1895,
      "step": 5470
    },
    {
      "epoch": 2.5679475164011247,
      "grad_norm": 2.0643043518066406,
      "learning_rate": 1.83950328022493e-05,
      "loss": 0.1943,
      "step": 5480
    },
    {
      "epoch": 2.572633552014995,
      "grad_norm": 2.1368064880371094,
      "learning_rate": 1.839210402999063e-05,
      "loss": 0.1851,
      "step": 5490
    },
    {
      "epoch": 2.5773195876288657,
      "grad_norm": 1.7404872179031372,
      "learning_rate": 1.8389175257731958e-05,
      "loss": 0.17,
      "step": 5500
    },
    {
      "epoch": 2.5773195876288657,
      "eval_loss": 0.052087847143411636,
      "eval_pearson_cosine": 0.7876996404495316,
      "eval_pearson_dot": 0.6239791899062368,
      "eval_pearson_euclidean": 0.7632876525798107,
      "eval_pearson_manhattan": 0.7621358820486535,
      "eval_runtime": 3.2114,
      "eval_samples_per_second": 467.081,
      "eval_spearman_cosine": 0.7959069730064968,
      "eval_spearman_dot": 0.6246328836004849,
      "eval_spearman_euclidean": 0.775279722994119,
      "eval_spearman_manhattan": 0.7746119015682993,
      "eval_steps_per_second": 29.27,
      "step": 5500
    },
    {
      "epoch": 2.5820056232427366,
      "grad_norm": 1.7516288757324219,
      "learning_rate": 1.838624648547329e-05,
      "loss": 0.2103,
      "step": 5510
    },
    {
      "epoch": 2.5866916588566076,
      "grad_norm": 2.0095157623291016,
      "learning_rate": 1.838331771321462e-05,
      "loss": 0.2149,
      "step": 5520
    },
    {
      "epoch": 2.591377694470478,
      "grad_norm": 2.3408539295196533,
      "learning_rate": 1.8380388940955953e-05,
      "loss": 0.1737,
      "step": 5530
    },
    {
      "epoch": 2.5960637300843485,
      "grad_norm": 2.1319546699523926,
      "learning_rate": 1.8377460168697283e-05,
      "loss": 0.1963,
      "step": 5540
    },
    {
      "epoch": 2.600749765698219,
      "grad_norm": 1.6769325733184814,
      "learning_rate": 1.8374531396438616e-05,
      "loss": 0.1953,
      "step": 5550
    },
    {
      "epoch": 2.60543580131209,
      "grad_norm": 2.503340244293213,
      "learning_rate": 1.8371602624179945e-05,
      "loss": 0.1872,
      "step": 5560
    },
    {
      "epoch": 2.610121836925961,
      "grad_norm": 1.9402929544448853,
      "learning_rate": 1.8368673851921278e-05,
      "loss": 0.2101,
      "step": 5570
    },
    {
      "epoch": 2.6148078725398314,
      "grad_norm": 1.980652928352356,
      "learning_rate": 1.8365745079662608e-05,
      "loss": 0.1847,
      "step": 5580
    },
    {
      "epoch": 2.619493908153702,
      "grad_norm": 2.6117632389068604,
      "learning_rate": 1.8362816307403937e-05,
      "loss": 0.1934,
      "step": 5590
    },
    {
      "epoch": 2.624179943767573,
      "grad_norm": 1.8052171468734741,
      "learning_rate": 1.835988753514527e-05,
      "loss": 0.1827,
      "step": 5600
    },
    {
      "epoch": 2.6288659793814433,
      "grad_norm": 2.384441375732422,
      "learning_rate": 1.83569587628866e-05,
      "loss": 0.1765,
      "step": 5610
    },
    {
      "epoch": 2.633552014995314,
      "grad_norm": 1.8288124799728394,
      "learning_rate": 1.8354029990627932e-05,
      "loss": 0.189,
      "step": 5620
    },
    {
      "epoch": 2.6382380506091847,
      "grad_norm": 1.8904608488082886,
      "learning_rate": 1.8351101218369262e-05,
      "loss": 0.1858,
      "step": 5630
    },
    {
      "epoch": 2.642924086223055,
      "grad_norm": 2.4750778675079346,
      "learning_rate": 1.834817244611059e-05,
      "loss": 0.2139,
      "step": 5640
    },
    {
      "epoch": 2.647610121836926,
      "grad_norm": 1.642340898513794,
      "learning_rate": 1.834524367385192e-05,
      "loss": 0.2069,
      "step": 5650
    },
    {
      "epoch": 2.6522961574507966,
      "grad_norm": 2.656212091445923,
      "learning_rate": 1.8342314901593254e-05,
      "loss": 0.1975,
      "step": 5660
    },
    {
      "epoch": 2.6569821930646675,
      "grad_norm": 1.8371754884719849,
      "learning_rate": 1.8339386129334583e-05,
      "loss": 0.2044,
      "step": 5670
    },
    {
      "epoch": 2.661668228678538,
      "grad_norm": 1.4980151653289795,
      "learning_rate": 1.8336457357075916e-05,
      "loss": 0.1641,
      "step": 5680
    },
    {
      "epoch": 2.6663542642924085,
      "grad_norm": 2.300854206085205,
      "learning_rate": 1.8333528584817246e-05,
      "loss": 0.22,
      "step": 5690
    },
    {
      "epoch": 2.6710402999062794,
      "grad_norm": 1.6950479745864868,
      "learning_rate": 1.8330599812558575e-05,
      "loss": 0.194,
      "step": 5700
    },
    {
      "epoch": 2.67572633552015,
      "grad_norm": 2.4695844650268555,
      "learning_rate": 1.8327671040299908e-05,
      "loss": 0.2099,
      "step": 5710
    },
    {
      "epoch": 2.680412371134021,
      "grad_norm": 1.6376041173934937,
      "learning_rate": 1.8324742268041237e-05,
      "loss": 0.1844,
      "step": 5720
    },
    {
      "epoch": 2.6850984067478914,
      "grad_norm": 2.3736367225646973,
      "learning_rate": 1.832181349578257e-05,
      "loss": 0.1886,
      "step": 5730
    },
    {
      "epoch": 2.689784442361762,
      "grad_norm": 1.9710888862609863,
      "learning_rate": 1.83188847235239e-05,
      "loss": 0.1881,
      "step": 5740
    },
    {
      "epoch": 2.6944704779756328,
      "grad_norm": 2.38665771484375,
      "learning_rate": 1.8315955951265233e-05,
      "loss": 0.174,
      "step": 5750
    },
    {
      "epoch": 2.6944704779756328,
      "eval_loss": 0.052811067551374435,
      "eval_pearson_cosine": 0.7875700428566148,
      "eval_pearson_dot": 0.6195988091254279,
      "eval_pearson_euclidean": 0.7602836109774316,
      "eval_pearson_manhattan": 0.7593741208437699,
      "eval_runtime": 3.3995,
      "eval_samples_per_second": 441.245,
      "eval_spearman_cosine": 0.7949301691809272,
      "eval_spearman_dot": 0.6234473775126543,
      "eval_spearman_euclidean": 0.771585595419442,
      "eval_spearman_manhattan": 0.7712513119620406,
      "eval_steps_per_second": 27.651,
      "step": 5750
    },
    {
      "epoch": 2.6991565135895033,
      "grad_norm": 1.9556349515914917,
      "learning_rate": 1.8313027179006562e-05,
      "loss": 0.1984,
      "step": 5760
    },
    {
      "epoch": 2.703842549203374,
      "grad_norm": 1.8807729482650757,
      "learning_rate": 1.8310098406747895e-05,
      "loss": 0.2057,
      "step": 5770
    },
    {
      "epoch": 2.7085285848172447,
      "grad_norm": 1.74807870388031,
      "learning_rate": 1.8307169634489225e-05,
      "loss": 0.2158,
      "step": 5780
    },
    {
      "epoch": 2.713214620431115,
      "grad_norm": 2.3334672451019287,
      "learning_rate": 1.8304240862230554e-05,
      "loss": 0.1676,
      "step": 5790
    },
    {
      "epoch": 2.717900656044986,
      "grad_norm": 2.0100314617156982,
      "learning_rate": 1.8301312089971887e-05,
      "loss": 0.1785,
      "step": 5800
    },
    {
      "epoch": 2.7225866916588566,
      "grad_norm": 1.9850749969482422,
      "learning_rate": 1.8298383317713217e-05,
      "loss": 0.191,
      "step": 5810
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 2.1841342449188232,
      "learning_rate": 1.8295454545454546e-05,
      "loss": 0.1814,
      "step": 5820
    },
    {
      "epoch": 2.731958762886598,
      "grad_norm": 2.6331992149353027,
      "learning_rate": 1.8292525773195876e-05,
      "loss": 0.2218,
      "step": 5830
    },
    {
      "epoch": 2.7366447985004685,
      "grad_norm": 2.161170482635498,
      "learning_rate": 1.828959700093721e-05,
      "loss": 0.1834,
      "step": 5840
    },
    {
      "epoch": 2.7413308341143394,
      "grad_norm": 2.3174726963043213,
      "learning_rate": 1.8286668228678538e-05,
      "loss": 0.1863,
      "step": 5850
    },
    {
      "epoch": 2.74601686972821,
      "grad_norm": 1.9110337495803833,
      "learning_rate": 1.828373945641987e-05,
      "loss": 0.179,
      "step": 5860
    },
    {
      "epoch": 2.750702905342081,
      "grad_norm": 2.59794545173645,
      "learning_rate": 1.82808106841612e-05,
      "loss": 0.1891,
      "step": 5870
    },
    {
      "epoch": 2.7553889409559513,
      "grad_norm": 2.1763062477111816,
      "learning_rate": 1.8277881911902533e-05,
      "loss": 0.2094,
      "step": 5880
    },
    {
      "epoch": 2.760074976569822,
      "grad_norm": 2.3349921703338623,
      "learning_rate": 1.8274953139643863e-05,
      "loss": 0.1848,
      "step": 5890
    },
    {
      "epoch": 2.7647610121836927,
      "grad_norm": 2.5409889221191406,
      "learning_rate": 1.8272024367385192e-05,
      "loss": 0.2392,
      "step": 5900
    },
    {
      "epoch": 2.7694470477975632,
      "grad_norm": 2.0501179695129395,
      "learning_rate": 1.8269095595126525e-05,
      "loss": 0.2116,
      "step": 5910
    },
    {
      "epoch": 2.774133083411434,
      "grad_norm": 2.486163854598999,
      "learning_rate": 1.8266166822867855e-05,
      "loss": 0.1899,
      "step": 5920
    },
    {
      "epoch": 2.7788191190253047,
      "grad_norm": 2.43495774269104,
      "learning_rate": 1.8263238050609187e-05,
      "loss": 0.212,
      "step": 5930
    },
    {
      "epoch": 2.783505154639175,
      "grad_norm": 1.9861983060836792,
      "learning_rate": 1.8260309278350517e-05,
      "loss": 0.2135,
      "step": 5940
    },
    {
      "epoch": 2.788191190253046,
      "grad_norm": 2.46321964263916,
      "learning_rate": 1.825738050609185e-05,
      "loss": 0.2033,
      "step": 5950
    },
    {
      "epoch": 2.7928772258669166,
      "grad_norm": 2.2375664710998535,
      "learning_rate": 1.825445173383318e-05,
      "loss": 0.2483,
      "step": 5960
    },
    {
      "epoch": 2.7975632614807875,
      "grad_norm": 2.2775328159332275,
      "learning_rate": 1.825152296157451e-05,
      "loss": 0.1921,
      "step": 5970
    },
    {
      "epoch": 2.802249297094658,
      "grad_norm": 2.1675665378570557,
      "learning_rate": 1.8248594189315842e-05,
      "loss": 0.1666,
      "step": 5980
    },
    {
      "epoch": 2.8069353327085285,
      "grad_norm": 1.969119668006897,
      "learning_rate": 1.824566541705717e-05,
      "loss": 0.1997,
      "step": 5990
    },
    {
      "epoch": 2.8116213683223994,
      "grad_norm": 3.1404953002929688,
      "learning_rate": 1.82427366447985e-05,
      "loss": 0.1896,
      "step": 6000
    },
    {
      "epoch": 2.8116213683223994,
      "eval_loss": 0.0506160594522953,
      "eval_pearson_cosine": 0.7847906228898438,
      "eval_pearson_dot": 0.6051671435295134,
      "eval_pearson_euclidean": 0.7605907930754796,
      "eval_pearson_manhattan": 0.7595079560474858,
      "eval_runtime": 3.1727,
      "eval_samples_per_second": 472.783,
      "eval_spearman_cosine": 0.7891227097506602,
      "eval_spearman_dot": 0.6083246161085648,
      "eval_spearman_euclidean": 0.7718421311199012,
      "eval_spearman_manhattan": 0.7711946620901435,
      "eval_steps_per_second": 29.628,
      "step": 6000
    },
    {
      "epoch": 2.81630740393627,
      "grad_norm": 2.5197956562042236,
      "learning_rate": 1.8239807872539834e-05,
      "loss": 0.19,
      "step": 6010
    },
    {
      "epoch": 2.820993439550141,
      "grad_norm": 2.342001438140869,
      "learning_rate": 1.8236879100281163e-05,
      "loss": 0.1902,
      "step": 6020
    },
    {
      "epoch": 2.8256794751640113,
      "grad_norm": 2.081195592880249,
      "learning_rate": 1.8233950328022493e-05,
      "loss": 0.1861,
      "step": 6030
    },
    {
      "epoch": 2.830365510777882,
      "grad_norm": 2.2222466468811035,
      "learning_rate": 1.8231021555763825e-05,
      "loss": 0.1956,
      "step": 6040
    },
    {
      "epoch": 2.8350515463917527,
      "grad_norm": 2.531655788421631,
      "learning_rate": 1.8228092783505155e-05,
      "loss": 0.2001,
      "step": 6050
    },
    {
      "epoch": 2.839737582005623,
      "grad_norm": 1.8432163000106812,
      "learning_rate": 1.8225164011246488e-05,
      "loss": 0.1917,
      "step": 6060
    },
    {
      "epoch": 2.844423617619494,
      "grad_norm": 1.8071563243865967,
      "learning_rate": 1.8222235238987817e-05,
      "loss": 0.2292,
      "step": 6070
    },
    {
      "epoch": 2.8491096532333646,
      "grad_norm": 2.596858501434326,
      "learning_rate": 1.821930646672915e-05,
      "loss": 0.2025,
      "step": 6080
    },
    {
      "epoch": 2.853795688847235,
      "grad_norm": 2.516810655593872,
      "learning_rate": 1.821637769447048e-05,
      "loss": 0.2008,
      "step": 6090
    },
    {
      "epoch": 2.858481724461106,
      "grad_norm": 2.685643196105957,
      "learning_rate": 1.821344892221181e-05,
      "loss": 0.2181,
      "step": 6100
    },
    {
      "epoch": 2.8631677600749765,
      "grad_norm": 2.3013880252838135,
      "learning_rate": 1.8210520149953142e-05,
      "loss": 0.2089,
      "step": 6110
    },
    {
      "epoch": 2.8678537956888475,
      "grad_norm": 2.1551058292388916,
      "learning_rate": 1.820759137769447e-05,
      "loss": 0.2096,
      "step": 6120
    },
    {
      "epoch": 2.872539831302718,
      "grad_norm": 2.2167651653289795,
      "learning_rate": 1.8204662605435805e-05,
      "loss": 0.1928,
      "step": 6130
    },
    {
      "epoch": 2.8772258669165884,
      "grad_norm": 2.3424344062805176,
      "learning_rate": 1.8201733833177134e-05,
      "loss": 0.1843,
      "step": 6140
    },
    {
      "epoch": 2.8819119025304594,
      "grad_norm": 2.8250808715820312,
      "learning_rate": 1.8198805060918464e-05,
      "loss": 0.2221,
      "step": 6150
    },
    {
      "epoch": 2.88659793814433,
      "grad_norm": 2.3614280223846436,
      "learning_rate": 1.8195876288659796e-05,
      "loss": 0.1862,
      "step": 6160
    },
    {
      "epoch": 2.891283973758201,
      "grad_norm": 1.918118953704834,
      "learning_rate": 1.8192947516401126e-05,
      "loss": 0.1867,
      "step": 6170
    },
    {
      "epoch": 2.8959700093720713,
      "grad_norm": 1.8377277851104736,
      "learning_rate": 1.8190018744142455e-05,
      "loss": 0.1826,
      "step": 6180
    },
    {
      "epoch": 2.9006560449859418,
      "grad_norm": 2.527493715286255,
      "learning_rate": 1.8187089971883788e-05,
      "loss": 0.1986,
      "step": 6190
    },
    {
      "epoch": 2.9053420805998127,
      "grad_norm": 2.125455379486084,
      "learning_rate": 1.8184161199625118e-05,
      "loss": 0.1936,
      "step": 6200
    },
    {
      "epoch": 2.910028116213683,
      "grad_norm": 2.2447023391723633,
      "learning_rate": 1.8181232427366447e-05,
      "loss": 0.1887,
      "step": 6210
    },
    {
      "epoch": 2.914714151827554,
      "grad_norm": 2.3427064418792725,
      "learning_rate": 1.817830365510778e-05,
      "loss": 0.197,
      "step": 6220
    },
    {
      "epoch": 2.9194001874414246,
      "grad_norm": 2.480989933013916,
      "learning_rate": 1.817537488284911e-05,
      "loss": 0.2145,
      "step": 6230
    },
    {
      "epoch": 2.924086223055295,
      "grad_norm": 2.2610814571380615,
      "learning_rate": 1.8172446110590443e-05,
      "loss": 0.1854,
      "step": 6240
    },
    {
      "epoch": 2.928772258669166,
      "grad_norm": 2.220090866088867,
      "learning_rate": 1.8169517338331772e-05,
      "loss": 0.1897,
      "step": 6250
    },
    {
      "epoch": 2.928772258669166,
      "eval_loss": 0.05493560805916786,
      "eval_pearson_cosine": 0.7819311073703084,
      "eval_pearson_dot": 0.5956676516410369,
      "eval_pearson_euclidean": 0.7532898404318757,
      "eval_pearson_manhattan": 0.7521288710513865,
      "eval_runtime": 3.273,
      "eval_samples_per_second": 458.299,
      "eval_spearman_cosine": 0.7902389528249426,
      "eval_spearman_dot": 0.5980515739599185,
      "eval_spearman_euclidean": 0.7666646754982684,
      "eval_spearman_manhattan": 0.7664381416282928,
      "eval_steps_per_second": 28.72,
      "step": 6250
    },
    {
      "epoch": 2.9334582942830365,
      "grad_norm": 2.517014741897583,
      "learning_rate": 1.8166588566073105e-05,
      "loss": 0.2132,
      "step": 6260
    },
    {
      "epoch": 2.9381443298969074,
      "grad_norm": 1.9690264463424683,
      "learning_rate": 1.8163659793814434e-05,
      "loss": 0.1756,
      "step": 6270
    },
    {
      "epoch": 2.942830365510778,
      "grad_norm": 1.812945008277893,
      "learning_rate": 1.8160731021555767e-05,
      "loss": 0.1848,
      "step": 6280
    },
    {
      "epoch": 2.9475164011246484,
      "grad_norm": 2.003582000732422,
      "learning_rate": 1.8157802249297097e-05,
      "loss": 0.2071,
      "step": 6290
    },
    {
      "epoch": 2.9522024367385193,
      "grad_norm": 3.1531078815460205,
      "learning_rate": 1.8154873477038426e-05,
      "loss": 0.2146,
      "step": 6300
    },
    {
      "epoch": 2.95688847235239,
      "grad_norm": 2.5869102478027344,
      "learning_rate": 1.815194470477976e-05,
      "loss": 0.1854,
      "step": 6310
    },
    {
      "epoch": 2.9615745079662608,
      "grad_norm": 2.2422142028808594,
      "learning_rate": 1.814901593252109e-05,
      "loss": 0.179,
      "step": 6320
    },
    {
      "epoch": 2.9662605435801312,
      "grad_norm": 2.346750497817993,
      "learning_rate": 1.814608716026242e-05,
      "loss": 0.1937,
      "step": 6330
    },
    {
      "epoch": 2.9709465791940017,
      "grad_norm": 1.6241106986999512,
      "learning_rate": 1.814315838800375e-05,
      "loss": 0.1945,
      "step": 6340
    },
    {
      "epoch": 2.9756326148078727,
      "grad_norm": 2.8439619541168213,
      "learning_rate": 1.814022961574508e-05,
      "loss": 0.2265,
      "step": 6350
    },
    {
      "epoch": 2.980318650421743,
      "grad_norm": 1.69356107711792,
      "learning_rate": 1.813730084348641e-05,
      "loss": 0.1869,
      "step": 6360
    },
    {
      "epoch": 2.985004686035614,
      "grad_norm": 2.3386266231536865,
      "learning_rate": 1.8134372071227743e-05,
      "loss": 0.1752,
      "step": 6370
    },
    {
      "epoch": 2.9896907216494846,
      "grad_norm": 1.873734712600708,
      "learning_rate": 1.8131443298969072e-05,
      "loss": 0.1972,
      "step": 6380
    },
    {
      "epoch": 2.994376757263355,
      "grad_norm": 2.3732969760894775,
      "learning_rate": 1.8128514526710402e-05,
      "loss": 0.2229,
      "step": 6390
    },
    {
      "epoch": 2.999062792877226,
      "grad_norm": 2.2805166244506836,
      "learning_rate": 1.8125585754451735e-05,
      "loss": 0.2022,
      "step": 6400
    },
    {
      "epoch": 3.0037488284910965,
      "grad_norm": 1.8053455352783203,
      "learning_rate": 1.8122656982193064e-05,
      "loss": 0.132,
      "step": 6410
    },
    {
      "epoch": 3.0084348641049674,
      "grad_norm": 2.322193145751953,
      "learning_rate": 1.8119728209934397e-05,
      "loss": 0.1341,
      "step": 6420
    },
    {
      "epoch": 3.013120899718838,
      "grad_norm": 2.2462315559387207,
      "learning_rate": 1.8116799437675727e-05,
      "loss": 0.1294,
      "step": 6430
    },
    {
      "epoch": 3.0178069353327084,
      "grad_norm": 1.5314648151397705,
      "learning_rate": 1.811387066541706e-05,
      "loss": 0.0974,
      "step": 6440
    },
    {
      "epoch": 3.0224929709465793,
      "grad_norm": 1.4587002992630005,
      "learning_rate": 1.811094189315839e-05,
      "loss": 0.1019,
      "step": 6450
    },
    {
      "epoch": 3.02717900656045,
      "grad_norm": 0.887192964553833,
      "learning_rate": 1.8108013120899722e-05,
      "loss": 0.0945,
      "step": 6460
    },
    {
      "epoch": 3.0318650421743207,
      "grad_norm": 1.8087823390960693,
      "learning_rate": 1.810508434864105e-05,
      "loss": 0.1103,
      "step": 6470
    },
    {
      "epoch": 3.036551077788191,
      "grad_norm": 2.4967281818389893,
      "learning_rate": 1.8102155576382384e-05,
      "loss": 0.1261,
      "step": 6480
    },
    {
      "epoch": 3.0412371134020617,
      "grad_norm": 1.4955415725708008,
      "learning_rate": 1.8099226804123714e-05,
      "loss": 0.1255,
      "step": 6490
    },
    {
      "epoch": 3.0459231490159326,
      "grad_norm": 1.0758466720581055,
      "learning_rate": 1.8096298031865043e-05,
      "loss": 0.105,
      "step": 6500
    },
    {
      "epoch": 3.0459231490159326,
      "eval_loss": 0.04503355920314789,
      "eval_pearson_cosine": 0.7887213700331159,
      "eval_pearson_dot": 0.638523586851079,
      "eval_pearson_euclidean": 0.7527277991826509,
      "eval_pearson_manhattan": 0.7516127412435569,
      "eval_runtime": 3.2262,
      "eval_samples_per_second": 464.937,
      "eval_spearman_cosine": 0.7931480987271526,
      "eval_spearman_dot": 0.6449590450062397,
      "eval_spearman_euclidean": 0.7674534939783395,
      "eval_spearman_manhattan": 0.7668609796988295,
      "eval_steps_per_second": 29.136,
      "step": 6500
    },
    {
      "epoch": 3.050609184629803,
      "grad_norm": 2.3318862915039062,
      "learning_rate": 1.8093369259606376e-05,
      "loss": 0.1364,
      "step": 6510
    },
    {
      "epoch": 3.055295220243674,
      "grad_norm": 1.8145966529846191,
      "learning_rate": 1.8090440487347706e-05,
      "loss": 0.1236,
      "step": 6520
    },
    {
      "epoch": 3.0599812558575445,
      "grad_norm": 1.584845781326294,
      "learning_rate": 1.8087511715089035e-05,
      "loss": 0.128,
      "step": 6530
    },
    {
      "epoch": 3.064667291471415,
      "grad_norm": 1.2164894342422485,
      "learning_rate": 1.8084582942830368e-05,
      "loss": 0.1233,
      "step": 6540
    },
    {
      "epoch": 3.069353327085286,
      "grad_norm": 1.761679768562317,
      "learning_rate": 1.8081654170571698e-05,
      "loss": 0.1107,
      "step": 6550
    },
    {
      "epoch": 3.0740393626991565,
      "grad_norm": 1.9818497896194458,
      "learning_rate": 1.8078725398313027e-05,
      "loss": 0.1373,
      "step": 6560
    },
    {
      "epoch": 3.0787253983130274,
      "grad_norm": 2.124472141265869,
      "learning_rate": 1.807579662605436e-05,
      "loss": 0.1409,
      "step": 6570
    },
    {
      "epoch": 3.083411433926898,
      "grad_norm": 1.6288917064666748,
      "learning_rate": 1.807286785379569e-05,
      "loss": 0.1022,
      "step": 6580
    },
    {
      "epoch": 3.0880974695407684,
      "grad_norm": 1.5154041051864624,
      "learning_rate": 1.806993908153702e-05,
      "loss": 0.1167,
      "step": 6590
    },
    {
      "epoch": 3.0927835051546393,
      "grad_norm": 1.736624836921692,
      "learning_rate": 1.8067010309278352e-05,
      "loss": 0.0932,
      "step": 6600
    },
    {
      "epoch": 3.0974695407685098,
      "grad_norm": 2.2292051315307617,
      "learning_rate": 1.806408153701968e-05,
      "loss": 0.1458,
      "step": 6610
    },
    {
      "epoch": 3.1021555763823807,
      "grad_norm": 1.8836901187896729,
      "learning_rate": 1.8061152764761014e-05,
      "loss": 0.1145,
      "step": 6620
    },
    {
      "epoch": 3.106841611996251,
      "grad_norm": 2.0602309703826904,
      "learning_rate": 1.8058223992502344e-05,
      "loss": 0.1091,
      "step": 6630
    },
    {
      "epoch": 3.1115276476101217,
      "grad_norm": 1.7996163368225098,
      "learning_rate": 1.8055295220243677e-05,
      "loss": 0.1155,
      "step": 6640
    },
    {
      "epoch": 3.1162136832239926,
      "grad_norm": 1.695610761642456,
      "learning_rate": 1.8052366447985006e-05,
      "loss": 0.1268,
      "step": 6650
    },
    {
      "epoch": 3.120899718837863,
      "grad_norm": 1.6327197551727295,
      "learning_rate": 1.804943767572634e-05,
      "loss": 0.1157,
      "step": 6660
    },
    {
      "epoch": 3.125585754451734,
      "grad_norm": 2.457167387008667,
      "learning_rate": 1.804650890346767e-05,
      "loss": 0.1348,
      "step": 6670
    },
    {
      "epoch": 3.1302717900656045,
      "grad_norm": 1.1226837635040283,
      "learning_rate": 1.8043580131208998e-05,
      "loss": 0.1112,
      "step": 6680
    },
    {
      "epoch": 3.134957825679475,
      "grad_norm": 1.904137134552002,
      "learning_rate": 1.804065135895033e-05,
      "loss": 0.1288,
      "step": 6690
    },
    {
      "epoch": 3.139643861293346,
      "grad_norm": 1.8711892366409302,
      "learning_rate": 1.803772258669166e-05,
      "loss": 0.1341,
      "step": 6700
    },
    {
      "epoch": 3.1443298969072164,
      "grad_norm": 1.8008291721343994,
      "learning_rate": 1.803479381443299e-05,
      "loss": 0.1198,
      "step": 6710
    },
    {
      "epoch": 3.1490159325210874,
      "grad_norm": 1.8362482786178589,
      "learning_rate": 1.8031865042174323e-05,
      "loss": 0.1479,
      "step": 6720
    },
    {
      "epoch": 3.153701968134958,
      "grad_norm": 1.6150809526443481,
      "learning_rate": 1.8028936269915652e-05,
      "loss": 0.1138,
      "step": 6730
    },
    {
      "epoch": 3.1583880037488283,
      "grad_norm": 2.2239766120910645,
      "learning_rate": 1.8026007497656982e-05,
      "loss": 0.1309,
      "step": 6740
    },
    {
      "epoch": 3.1630740393626993,
      "grad_norm": 1.669233798980713,
      "learning_rate": 1.8023078725398315e-05,
      "loss": 0.1055,
      "step": 6750
    },
    {
      "epoch": 3.1630740393626993,
      "eval_loss": 0.04599650204181671,
      "eval_pearson_cosine": 0.7875010466521104,
      "eval_pearson_dot": 0.6256249285068609,
      "eval_pearson_euclidean": 0.752459338375715,
      "eval_pearson_manhattan": 0.7515050600000066,
      "eval_runtime": 3.3759,
      "eval_samples_per_second": 444.332,
      "eval_spearman_cosine": 0.792665874705252,
      "eval_spearman_dot": 0.6331527343675145,
      "eval_spearman_euclidean": 0.7657151594858318,
      "eval_spearman_manhattan": 0.7651890994431135,
      "eval_steps_per_second": 27.845,
      "step": 6750
    },
    {
      "epoch": 3.1677600749765698,
      "grad_norm": 2.1133861541748047,
      "learning_rate": 1.8020149953139644e-05,
      "loss": 0.1128,
      "step": 6760
    },
    {
      "epoch": 3.1724461105904407,
      "grad_norm": 1.5470513105392456,
      "learning_rate": 1.8017221180880977e-05,
      "loss": 0.1246,
      "step": 6770
    },
    {
      "epoch": 3.177132146204311,
      "grad_norm": 1.9087189435958862,
      "learning_rate": 1.8014292408622307e-05,
      "loss": 0.1137,
      "step": 6780
    },
    {
      "epoch": 3.1818181818181817,
      "grad_norm": 1.9185723066329956,
      "learning_rate": 1.8011363636363636e-05,
      "loss": 0.1196,
      "step": 6790
    },
    {
      "epoch": 3.1865042174320526,
      "grad_norm": 1.7757681608200073,
      "learning_rate": 1.800843486410497e-05,
      "loss": 0.0978,
      "step": 6800
    },
    {
      "epoch": 3.191190253045923,
      "grad_norm": 1.6667931079864502,
      "learning_rate": 1.80055060918463e-05,
      "loss": 0.113,
      "step": 6810
    },
    {
      "epoch": 3.195876288659794,
      "grad_norm": 2.101773500442505,
      "learning_rate": 1.800257731958763e-05,
      "loss": 0.1034,
      "step": 6820
    },
    {
      "epoch": 3.2005623242736645,
      "grad_norm": 1.6078181266784668,
      "learning_rate": 1.799964854732896e-05,
      "loss": 0.1276,
      "step": 6830
    },
    {
      "epoch": 3.205248359887535,
      "grad_norm": 1.3552807569503784,
      "learning_rate": 1.7996719775070294e-05,
      "loss": 0.1184,
      "step": 6840
    },
    {
      "epoch": 3.209934395501406,
      "grad_norm": 1.5063031911849976,
      "learning_rate": 1.7993791002811623e-05,
      "loss": 0.1367,
      "step": 6850
    },
    {
      "epoch": 3.2146204311152764,
      "grad_norm": 1.9200366735458374,
      "learning_rate": 1.7990862230552956e-05,
      "loss": 0.1222,
      "step": 6860
    },
    {
      "epoch": 3.2193064667291473,
      "grad_norm": 1.4902859926223755,
      "learning_rate": 1.7987933458294286e-05,
      "loss": 0.1414,
      "step": 6870
    },
    {
      "epoch": 3.223992502343018,
      "grad_norm": 1.7316768169403076,
      "learning_rate": 1.7985004686035615e-05,
      "loss": 0.1451,
      "step": 6880
    },
    {
      "epoch": 3.2286785379568883,
      "grad_norm": 1.8446965217590332,
      "learning_rate": 1.7982075913776945e-05,
      "loss": 0.1227,
      "step": 6890
    },
    {
      "epoch": 3.2333645735707592,
      "grad_norm": 1.5571191310882568,
      "learning_rate": 1.7979147141518278e-05,
      "loss": 0.1193,
      "step": 6900
    },
    {
      "epoch": 3.2380506091846297,
      "grad_norm": 2.3433127403259277,
      "learning_rate": 1.7976218369259607e-05,
      "loss": 0.1175,
      "step": 6910
    },
    {
      "epoch": 3.2427366447985007,
      "grad_norm": 1.8916155099868774,
      "learning_rate": 1.7973289597000937e-05,
      "loss": 0.1352,
      "step": 6920
    },
    {
      "epoch": 3.247422680412371,
      "grad_norm": 1.3708059787750244,
      "learning_rate": 1.797036082474227e-05,
      "loss": 0.1174,
      "step": 6930
    },
    {
      "epoch": 3.2521087160262416,
      "grad_norm": 1.5119550228118896,
      "learning_rate": 1.79674320524836e-05,
      "loss": 0.1331,
      "step": 6940
    },
    {
      "epoch": 3.2567947516401126,
      "grad_norm": 1.8884799480438232,
      "learning_rate": 1.7964503280224932e-05,
      "loss": 0.125,
      "step": 6950
    },
    {
      "epoch": 3.261480787253983,
      "grad_norm": 1.6222647428512573,
      "learning_rate": 1.796157450796626e-05,
      "loss": 0.1191,
      "step": 6960
    },
    {
      "epoch": 3.266166822867854,
      "grad_norm": 1.2746548652648926,
      "learning_rate": 1.7958645735707594e-05,
      "loss": 0.1256,
      "step": 6970
    },
    {
      "epoch": 3.2708528584817245,
      "grad_norm": 1.883239984512329,
      "learning_rate": 1.7955716963448924e-05,
      "loss": 0.1283,
      "step": 6980
    },
    {
      "epoch": 3.275538894095595,
      "grad_norm": 2.0994622707366943,
      "learning_rate": 1.7952788191190253e-05,
      "loss": 0.1316,
      "step": 6990
    },
    {
      "epoch": 3.280224929709466,
      "grad_norm": 1.844297170639038,
      "learning_rate": 1.7949859418931586e-05,
      "loss": 0.1145,
      "step": 7000
    },
    {
      "epoch": 3.280224929709466,
      "eval_loss": 0.045286137610673904,
      "eval_pearson_cosine": 0.7924534055849843,
      "eval_pearson_dot": 0.6315508963322145,
      "eval_pearson_euclidean": 0.7559423098506386,
      "eval_pearson_manhattan": 0.7547566595358202,
      "eval_runtime": 3.1537,
      "eval_samples_per_second": 475.63,
      "eval_spearman_cosine": 0.7977173793324885,
      "eval_spearman_dot": 0.6408281685024612,
      "eval_spearman_euclidean": 0.7678066060450297,
      "eval_spearman_manhattan": 0.7671464837523794,
      "eval_steps_per_second": 29.806,
      "step": 7000
    },
    {
      "epoch": 3.2849109653233364,
      "grad_norm": 1.3316779136657715,
      "learning_rate": 1.7946930646672916e-05,
      "loss": 0.1139,
      "step": 7010
    },
    {
      "epoch": 3.2895970009372073,
      "grad_norm": 1.3782374858856201,
      "learning_rate": 1.794400187441425e-05,
      "loss": 0.1238,
      "step": 7020
    },
    {
      "epoch": 3.294283036551078,
      "grad_norm": 1.4582282304763794,
      "learning_rate": 1.7941073102155578e-05,
      "loss": 0.1279,
      "step": 7030
    },
    {
      "epoch": 3.2989690721649483,
      "grad_norm": 2.3581652641296387,
      "learning_rate": 1.793814432989691e-05,
      "loss": 0.118,
      "step": 7040
    },
    {
      "epoch": 3.303655107778819,
      "grad_norm": 2.1047656536102295,
      "learning_rate": 1.793521555763824e-05,
      "loss": 0.1086,
      "step": 7050
    },
    {
      "epoch": 3.3083411433926897,
      "grad_norm": 1.748353123664856,
      "learning_rate": 1.793228678537957e-05,
      "loss": 0.1357,
      "step": 7060
    },
    {
      "epoch": 3.3130271790065606,
      "grad_norm": 1.905609130859375,
      "learning_rate": 1.79293580131209e-05,
      "loss": 0.1239,
      "step": 7070
    },
    {
      "epoch": 3.317713214620431,
      "grad_norm": 1.5777533054351807,
      "learning_rate": 1.7926429240862232e-05,
      "loss": 0.1179,
      "step": 7080
    },
    {
      "epoch": 3.3223992502343016,
      "grad_norm": 1.8429454565048218,
      "learning_rate": 1.7923500468603562e-05,
      "loss": 0.1103,
      "step": 7090
    },
    {
      "epoch": 3.3270852858481725,
      "grad_norm": 1.601769208908081,
      "learning_rate": 1.792057169634489e-05,
      "loss": 0.1282,
      "step": 7100
    },
    {
      "epoch": 3.331771321462043,
      "grad_norm": 1.948339581489563,
      "learning_rate": 1.7917642924086224e-05,
      "loss": 0.1314,
      "step": 7110
    },
    {
      "epoch": 3.336457357075914,
      "grad_norm": 2.035210609436035,
      "learning_rate": 1.7914714151827554e-05,
      "loss": 0.1232,
      "step": 7120
    },
    {
      "epoch": 3.3411433926897844,
      "grad_norm": 1.3871088027954102,
      "learning_rate": 1.7911785379568887e-05,
      "loss": 0.1225,
      "step": 7130
    },
    {
      "epoch": 3.345829428303655,
      "grad_norm": 1.9721599817276,
      "learning_rate": 1.7908856607310216e-05,
      "loss": 0.1364,
      "step": 7140
    },
    {
      "epoch": 3.350515463917526,
      "grad_norm": 2.2410221099853516,
      "learning_rate": 1.790592783505155e-05,
      "loss": 0.1277,
      "step": 7150
    },
    {
      "epoch": 3.3552014995313963,
      "grad_norm": 1.8568767309188843,
      "learning_rate": 1.790299906279288e-05,
      "loss": 0.1114,
      "step": 7160
    },
    {
      "epoch": 3.3598875351452673,
      "grad_norm": 2.367185115814209,
      "learning_rate": 1.790007029053421e-05,
      "loss": 0.1334,
      "step": 7170
    },
    {
      "epoch": 3.3645735707591378,
      "grad_norm": 1.6528865098953247,
      "learning_rate": 1.789714151827554e-05,
      "loss": 0.1223,
      "step": 7180
    },
    {
      "epoch": 3.3692596063730083,
      "grad_norm": 1.9136816263198853,
      "learning_rate": 1.789421274601687e-05,
      "loss": 0.1066,
      "step": 7190
    },
    {
      "epoch": 3.373945641986879,
      "grad_norm": 2.2870426177978516,
      "learning_rate": 1.7891283973758203e-05,
      "loss": 0.1058,
      "step": 7200
    },
    {
      "epoch": 3.3786316776007497,
      "grad_norm": 1.5177735090255737,
      "learning_rate": 1.7888355201499533e-05,
      "loss": 0.1179,
      "step": 7210
    },
    {
      "epoch": 3.3833177132146206,
      "grad_norm": 2.215899705886841,
      "learning_rate": 1.7885426429240866e-05,
      "loss": 0.1321,
      "step": 7220
    },
    {
      "epoch": 3.388003748828491,
      "grad_norm": 1.7164250612258911,
      "learning_rate": 1.7882497656982195e-05,
      "loss": 0.1111,
      "step": 7230
    },
    {
      "epoch": 3.3926897844423616,
      "grad_norm": 2.3435146808624268,
      "learning_rate": 1.7879568884723525e-05,
      "loss": 0.1513,
      "step": 7240
    },
    {
      "epoch": 3.3973758200562325,
      "grad_norm": 1.6385475397109985,
      "learning_rate": 1.7876640112464858e-05,
      "loss": 0.1252,
      "step": 7250
    },
    {
      "epoch": 3.3973758200562325,
      "eval_loss": 0.047000955790281296,
      "eval_pearson_cosine": 0.7888804465638501,
      "eval_pearson_dot": 0.6256929197655836,
      "eval_pearson_euclidean": 0.7570957556748965,
      "eval_pearson_manhattan": 0.7561323835241964,
      "eval_runtime": 3.4083,
      "eval_samples_per_second": 440.106,
      "eval_spearman_cosine": 0.7947042550328448,
      "eval_spearman_dot": 0.6282838912238756,
      "eval_spearman_euclidean": 0.7692784528325559,
      "eval_spearman_manhattan": 0.7683456146298958,
      "eval_steps_per_second": 27.58,
      "step": 7250
    },
    {
      "epoch": 3.402061855670103,
      "grad_norm": 1.5348442792892456,
      "learning_rate": 1.7873711340206187e-05,
      "loss": 0.1304,
      "step": 7260
    },
    {
      "epoch": 3.406747891283974,
      "grad_norm": 1.854861855506897,
      "learning_rate": 1.7870782567947517e-05,
      "loss": 0.1296,
      "step": 7270
    },
    {
      "epoch": 3.4114339268978444,
      "grad_norm": 1.5103728771209717,
      "learning_rate": 1.7867853795688846e-05,
      "loss": 0.1182,
      "step": 7280
    },
    {
      "epoch": 3.416119962511715,
      "grad_norm": 1.4604400396347046,
      "learning_rate": 1.786492502343018e-05,
      "loss": 0.1155,
      "step": 7290
    },
    {
      "epoch": 3.420805998125586,
      "grad_norm": 1.9087272882461548,
      "learning_rate": 1.786199625117151e-05,
      "loss": 0.1265,
      "step": 7300
    },
    {
      "epoch": 3.4254920337394563,
      "grad_norm": 2.3286941051483154,
      "learning_rate": 1.785906747891284e-05,
      "loss": 0.0926,
      "step": 7310
    },
    {
      "epoch": 3.4301780693533273,
      "grad_norm": 1.8551883697509766,
      "learning_rate": 1.785613870665417e-05,
      "loss": 0.122,
      "step": 7320
    },
    {
      "epoch": 3.4348641049671977,
      "grad_norm": 1.7142447233200073,
      "learning_rate": 1.7853209934395504e-05,
      "loss": 0.138,
      "step": 7330
    },
    {
      "epoch": 3.4395501405810682,
      "grad_norm": 1.5548756122589111,
      "learning_rate": 1.7850281162136833e-05,
      "loss": 0.1123,
      "step": 7340
    },
    {
      "epoch": 3.444236176194939,
      "grad_norm": 1.3273271322250366,
      "learning_rate": 1.7847352389878166e-05,
      "loss": 0.129,
      "step": 7350
    },
    {
      "epoch": 3.4489222118088096,
      "grad_norm": 2.410999298095703,
      "learning_rate": 1.7844423617619496e-05,
      "loss": 0.1329,
      "step": 7360
    },
    {
      "epoch": 3.4536082474226806,
      "grad_norm": 2.0272533893585205,
      "learning_rate": 1.784149484536083e-05,
      "loss": 0.1251,
      "step": 7370
    },
    {
      "epoch": 3.458294283036551,
      "grad_norm": 2.4070749282836914,
      "learning_rate": 1.7838566073102158e-05,
      "loss": 0.1384,
      "step": 7380
    },
    {
      "epoch": 3.4629803186504216,
      "grad_norm": 2.0983331203460693,
      "learning_rate": 1.7835637300843487e-05,
      "loss": 0.1268,
      "step": 7390
    },
    {
      "epoch": 3.4676663542642925,
      "grad_norm": 1.5650460720062256,
      "learning_rate": 1.783270852858482e-05,
      "loss": 0.1218,
      "step": 7400
    },
    {
      "epoch": 3.472352389878163,
      "grad_norm": 1.4505574703216553,
      "learning_rate": 1.782977975632615e-05,
      "loss": 0.1278,
      "step": 7410
    },
    {
      "epoch": 3.477038425492034,
      "grad_norm": 2.4104747772216797,
      "learning_rate": 1.782685098406748e-05,
      "loss": 0.1506,
      "step": 7420
    },
    {
      "epoch": 3.4817244611059044,
      "grad_norm": 2.2749085426330566,
      "learning_rate": 1.7823922211808812e-05,
      "loss": 0.1382,
      "step": 7430
    },
    {
      "epoch": 3.486410496719775,
      "grad_norm": 1.619983434677124,
      "learning_rate": 1.7820993439550142e-05,
      "loss": 0.1145,
      "step": 7440
    },
    {
      "epoch": 3.491096532333646,
      "grad_norm": 1.797600269317627,
      "learning_rate": 1.781806466729147e-05,
      "loss": 0.1381,
      "step": 7450
    },
    {
      "epoch": 3.4957825679475163,
      "grad_norm": 1.2865104675292969,
      "learning_rate": 1.7815135895032804e-05,
      "loss": 0.1088,
      "step": 7460
    },
    {
      "epoch": 3.5004686035613872,
      "grad_norm": 2.2955312728881836,
      "learning_rate": 1.7812207122774134e-05,
      "loss": 0.1389,
      "step": 7470
    },
    {
      "epoch": 3.5051546391752577,
      "grad_norm": 1.884758472442627,
      "learning_rate": 1.7809278350515463e-05,
      "loss": 0.1399,
      "step": 7480
    },
    {
      "epoch": 3.509840674789128,
      "grad_norm": 2.0076119899749756,
      "learning_rate": 1.7806349578256796e-05,
      "loss": 0.1028,
      "step": 7490
    },
    {
      "epoch": 3.514526710402999,
      "grad_norm": 1.5606528520584106,
      "learning_rate": 1.7803420805998125e-05,
      "loss": 0.1058,
      "step": 7500
    },
    {
      "epoch": 3.514526710402999,
      "eval_loss": 0.044608332216739655,
      "eval_pearson_cosine": 0.7913143880230251,
      "eval_pearson_dot": 0.6221286850907433,
      "eval_pearson_euclidean": 0.7578325537672654,
      "eval_pearson_manhattan": 0.7571791901529252,
      "eval_runtime": 3.3012,
      "eval_samples_per_second": 454.374,
      "eval_spearman_cosine": 0.7958246101441605,
      "eval_spearman_dot": 0.6338421877202784,
      "eval_spearman_euclidean": 0.7715109007041803,
      "eval_spearman_manhattan": 0.7714185275105551,
      "eval_steps_per_second": 28.474,
      "step": 7500
    },
    {
      "epoch": 3.5192127460168696,
      "grad_norm": 1.9054310321807861,
      "learning_rate": 1.780049203373946e-05,
      "loss": 0.1149,
      "step": 7510
    },
    {
      "epoch": 3.5238987816307406,
      "grad_norm": 2.2473042011260986,
      "learning_rate": 1.7797563261480788e-05,
      "loss": 0.1241,
      "step": 7520
    },
    {
      "epoch": 3.528584817244611,
      "grad_norm": 2.9301676750183105,
      "learning_rate": 1.779463448922212e-05,
      "loss": 0.1155,
      "step": 7530
    },
    {
      "epoch": 3.5332708528584815,
      "grad_norm": 1.8250157833099365,
      "learning_rate": 1.779170571696345e-05,
      "loss": 0.118,
      "step": 7540
    },
    {
      "epoch": 3.5379568884723525,
      "grad_norm": 2.101794958114624,
      "learning_rate": 1.7788776944704783e-05,
      "loss": 0.1338,
      "step": 7550
    },
    {
      "epoch": 3.542642924086223,
      "grad_norm": 1.9058297872543335,
      "learning_rate": 1.7785848172446113e-05,
      "loss": 0.1172,
      "step": 7560
    },
    {
      "epoch": 3.547328959700094,
      "grad_norm": 2.1106228828430176,
      "learning_rate": 1.7782919400187446e-05,
      "loss": 0.119,
      "step": 7570
    },
    {
      "epoch": 3.5520149953139644,
      "grad_norm": 1.572771430015564,
      "learning_rate": 1.7779990627928775e-05,
      "loss": 0.1303,
      "step": 7580
    },
    {
      "epoch": 3.556701030927835,
      "grad_norm": 2.670691967010498,
      "learning_rate": 1.7777061855670105e-05,
      "loss": 0.1367,
      "step": 7590
    },
    {
      "epoch": 3.561387066541706,
      "grad_norm": 1.0899403095245361,
      "learning_rate": 1.7774133083411434e-05,
      "loss": 0.131,
      "step": 7600
    },
    {
      "epoch": 3.5660731021555763,
      "grad_norm": 1.66856050491333,
      "learning_rate": 1.7771204311152767e-05,
      "loss": 0.1282,
      "step": 7610
    },
    {
      "epoch": 3.570759137769447,
      "grad_norm": 1.9693597555160522,
      "learning_rate": 1.7768275538894096e-05,
      "loss": 0.1141,
      "step": 7620
    },
    {
      "epoch": 3.5754451733833177,
      "grad_norm": 2.5107643604278564,
      "learning_rate": 1.7765346766635426e-05,
      "loss": 0.1302,
      "step": 7630
    },
    {
      "epoch": 3.580131208997188,
      "grad_norm": 1.843782663345337,
      "learning_rate": 1.776241799437676e-05,
      "loss": 0.1295,
      "step": 7640
    },
    {
      "epoch": 3.584817244611059,
      "grad_norm": 1.5396898984909058,
      "learning_rate": 1.7759489222118088e-05,
      "loss": 0.1146,
      "step": 7650
    },
    {
      "epoch": 3.5895032802249296,
      "grad_norm": 1.250181794166565,
      "learning_rate": 1.775656044985942e-05,
      "loss": 0.0997,
      "step": 7660
    },
    {
      "epoch": 3.5941893158388005,
      "grad_norm": 1.0038021802902222,
      "learning_rate": 1.775363167760075e-05,
      "loss": 0.131,
      "step": 7670
    },
    {
      "epoch": 3.598875351452671,
      "grad_norm": 1.7689967155456543,
      "learning_rate": 1.775070290534208e-05,
      "loss": 0.1323,
      "step": 7680
    },
    {
      "epoch": 3.6035613870665415,
      "grad_norm": 1.6515671014785767,
      "learning_rate": 1.7747774133083413e-05,
      "loss": 0.1228,
      "step": 7690
    },
    {
      "epoch": 3.6082474226804124,
      "grad_norm": 1.6234405040740967,
      "learning_rate": 1.7744845360824743e-05,
      "loss": 0.1177,
      "step": 7700
    },
    {
      "epoch": 3.612933458294283,
      "grad_norm": 1.1468828916549683,
      "learning_rate": 1.7741916588566075e-05,
      "loss": 0.121,
      "step": 7710
    },
    {
      "epoch": 3.617619493908154,
      "grad_norm": 2.2512290477752686,
      "learning_rate": 1.7738987816307405e-05,
      "loss": 0.1506,
      "step": 7720
    },
    {
      "epoch": 3.6223055295220243,
      "grad_norm": 1.967869758605957,
      "learning_rate": 1.7736059044048738e-05,
      "loss": 0.1278,
      "step": 7730
    },
    {
      "epoch": 3.626991565135895,
      "grad_norm": 1.6843619346618652,
      "learning_rate": 1.7733130271790067e-05,
      "loss": 0.1292,
      "step": 7740
    },
    {
      "epoch": 3.6316776007497658,
      "grad_norm": 1.7128106355667114,
      "learning_rate": 1.77302014995314e-05,
      "loss": 0.1144,
      "step": 7750
    },
    {
      "epoch": 3.6316776007497658,
      "eval_loss": 0.043338797986507416,
      "eval_pearson_cosine": 0.7938926107691149,
      "eval_pearson_dot": 0.6518687502689318,
      "eval_pearson_euclidean": 0.7541829192023144,
      "eval_pearson_manhattan": 0.7533667893162033,
      "eval_runtime": 3.5292,
      "eval_samples_per_second": 425.028,
      "eval_spearman_cosine": 0.7989181032598132,
      "eval_spearman_dot": 0.658312239789335,
      "eval_spearman_euclidean": 0.7677205029787961,
      "eval_spearman_manhattan": 0.7673451483642694,
      "eval_steps_per_second": 26.635,
      "step": 7750
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 2.2347500324249268,
      "learning_rate": 1.772727272727273e-05,
      "loss": 0.145,
      "step": 7760
    },
    {
      "epoch": 3.641049671977507,
      "grad_norm": 1.1075607538223267,
      "learning_rate": 1.772434395501406e-05,
      "loss": 0.122,
      "step": 7770
    },
    {
      "epoch": 3.6457357075913777,
      "grad_norm": 1.9819576740264893,
      "learning_rate": 1.772141518275539e-05,
      "loss": 0.1542,
      "step": 7780
    },
    {
      "epoch": 3.650421743205248,
      "grad_norm": 1.3385450839996338,
      "learning_rate": 1.771848641049672e-05,
      "loss": 0.1269,
      "step": 7790
    },
    {
      "epoch": 3.655107778819119,
      "grad_norm": 1.2146624326705933,
      "learning_rate": 1.771555763823805e-05,
      "loss": 0.1124,
      "step": 7800
    },
    {
      "epoch": 3.6597938144329896,
      "grad_norm": 1.8543137311935425,
      "learning_rate": 1.771262886597938e-05,
      "loss": 0.1513,
      "step": 7810
    },
    {
      "epoch": 3.6644798500468605,
      "grad_norm": 1.147740125656128,
      "learning_rate": 1.7709700093720713e-05,
      "loss": 0.1207,
      "step": 7820
    },
    {
      "epoch": 3.669165885660731,
      "grad_norm": 2.1737101078033447,
      "learning_rate": 1.7706771321462043e-05,
      "loss": 0.1345,
      "step": 7830
    },
    {
      "epoch": 3.6738519212746015,
      "grad_norm": 2.481095790863037,
      "learning_rate": 1.7703842549203376e-05,
      "loss": 0.1304,
      "step": 7840
    },
    {
      "epoch": 3.6785379568884724,
      "grad_norm": 1.9203423261642456,
      "learning_rate": 1.7700913776944705e-05,
      "loss": 0.1257,
      "step": 7850
    },
    {
      "epoch": 3.683223992502343,
      "grad_norm": 2.324158191680908,
      "learning_rate": 1.7697985004686038e-05,
      "loss": 0.126,
      "step": 7860
    },
    {
      "epoch": 3.687910028116214,
      "grad_norm": 1.6233323812484741,
      "learning_rate": 1.7695056232427368e-05,
      "loss": 0.1228,
      "step": 7870
    },
    {
      "epoch": 3.6925960637300843,
      "grad_norm": 1.0567041635513306,
      "learning_rate": 1.7692127460168697e-05,
      "loss": 0.1129,
      "step": 7880
    },
    {
      "epoch": 3.697282099343955,
      "grad_norm": 1.4684457778930664,
      "learning_rate": 1.768919868791003e-05,
      "loss": 0.1164,
      "step": 7890
    },
    {
      "epoch": 3.7019681349578257,
      "grad_norm": 2.070171594619751,
      "learning_rate": 1.768626991565136e-05,
      "loss": 0.1488,
      "step": 7900
    },
    {
      "epoch": 3.706654170571696,
      "grad_norm": 1.93710458278656,
      "learning_rate": 1.7683341143392693e-05,
      "loss": 0.1423,
      "step": 7910
    },
    {
      "epoch": 3.711340206185567,
      "grad_norm": 2.109379529953003,
      "learning_rate": 1.7680412371134022e-05,
      "loss": 0.1247,
      "step": 7920
    },
    {
      "epoch": 3.7160262417994376,
      "grad_norm": 1.9402395486831665,
      "learning_rate": 1.7677483598875355e-05,
      "loss": 0.1258,
      "step": 7930
    },
    {
      "epoch": 3.720712277413308,
      "grad_norm": 1.3770403861999512,
      "learning_rate": 1.7674554826616684e-05,
      "loss": 0.1152,
      "step": 7940
    },
    {
      "epoch": 3.725398313027179,
      "grad_norm": 1.8845633268356323,
      "learning_rate": 1.7671626054358014e-05,
      "loss": 0.1128,
      "step": 7950
    },
    {
      "epoch": 3.7300843486410495,
      "grad_norm": 1.80978524684906,
      "learning_rate": 1.7668697282099347e-05,
      "loss": 0.1506,
      "step": 7960
    },
    {
      "epoch": 3.7347703842549205,
      "grad_norm": 1.714689016342163,
      "learning_rate": 1.7665768509840676e-05,
      "loss": 0.1295,
      "step": 7970
    },
    {
      "epoch": 3.739456419868791,
      "grad_norm": 2.2683634757995605,
      "learning_rate": 1.7662839737582006e-05,
      "loss": 0.153,
      "step": 7980
    },
    {
      "epoch": 3.7441424554826614,
      "grad_norm": 1.1487226486206055,
      "learning_rate": 1.7659910965323335e-05,
      "loss": 0.1305,
      "step": 7990
    },
    {
      "epoch": 3.7488284910965324,
      "grad_norm": 1.4769738912582397,
      "learning_rate": 1.7656982193064668e-05,
      "loss": 0.0971,
      "step": 8000
    },
    {
      "epoch": 3.7488284910965324,
      "eval_loss": 0.04381699115037918,
      "eval_pearson_cosine": 0.7952038190054296,
      "eval_pearson_dot": 0.6344663529067152,
      "eval_pearson_euclidean": 0.7547335910463318,
      "eval_pearson_manhattan": 0.7536726944037966,
      "eval_runtime": 3.6935,
      "eval_samples_per_second": 406.123,
      "eval_spearman_cosine": 0.7993143516157027,
      "eval_spearman_dot": 0.6382938851288388,
      "eval_spearman_euclidean": 0.7679077610624258,
      "eval_spearman_manhattan": 0.767544325158077,
      "eval_steps_per_second": 25.45,
      "step": 8000
    },
    {
      "epoch": 3.753514526710403,
      "grad_norm": 2.859675645828247,
      "learning_rate": 1.7654053420805998e-05,
      "loss": 0.1442,
      "step": 8010
    },
    {
      "epoch": 3.758200562324274,
      "grad_norm": 1.54740571975708,
      "learning_rate": 1.765112464854733e-05,
      "loss": 0.1194,
      "step": 8020
    },
    {
      "epoch": 3.7628865979381443,
      "grad_norm": 1.5696630477905273,
      "learning_rate": 1.764819587628866e-05,
      "loss": 0.1542,
      "step": 8030
    },
    {
      "epoch": 3.7675726335520148,
      "grad_norm": 1.8833867311477661,
      "learning_rate": 1.7645267104029993e-05,
      "loss": 0.1222,
      "step": 8040
    },
    {
      "epoch": 3.7722586691658857,
      "grad_norm": 2.2312562465667725,
      "learning_rate": 1.7642338331771322e-05,
      "loss": 0.1378,
      "step": 8050
    },
    {
      "epoch": 3.776944704779756,
      "grad_norm": 1.9470106363296509,
      "learning_rate": 1.7639409559512655e-05,
      "loss": 0.136,
      "step": 8060
    },
    {
      "epoch": 3.781630740393627,
      "grad_norm": 1.736140489578247,
      "learning_rate": 1.7636480787253985e-05,
      "loss": 0.144,
      "step": 8070
    },
    {
      "epoch": 3.7863167760074976,
      "grad_norm": 2.0280628204345703,
      "learning_rate": 1.7633552014995314e-05,
      "loss": 0.1331,
      "step": 8080
    },
    {
      "epoch": 3.791002811621368,
      "grad_norm": 1.1331037282943726,
      "learning_rate": 1.7630623242736647e-05,
      "loss": 0.1327,
      "step": 8090
    },
    {
      "epoch": 3.795688847235239,
      "grad_norm": 2.00110125541687,
      "learning_rate": 1.7627694470477977e-05,
      "loss": 0.1335,
      "step": 8100
    },
    {
      "epoch": 3.8003748828491095,
      "grad_norm": 1.589747428894043,
      "learning_rate": 1.762476569821931e-05,
      "loss": 0.1222,
      "step": 8110
    },
    {
      "epoch": 3.8050609184629804,
      "grad_norm": 1.8979542255401611,
      "learning_rate": 1.762183692596064e-05,
      "loss": 0.1534,
      "step": 8120
    },
    {
      "epoch": 3.809746954076851,
      "grad_norm": 2.384608268737793,
      "learning_rate": 1.761890815370197e-05,
      "loss": 0.1395,
      "step": 8130
    },
    {
      "epoch": 3.8144329896907214,
      "grad_norm": 1.8555763959884644,
      "learning_rate": 1.76159793814433e-05,
      "loss": 0.1298,
      "step": 8140
    },
    {
      "epoch": 3.8191190253045924,
      "grad_norm": 2.0810048580169678,
      "learning_rate": 1.761305060918463e-05,
      "loss": 0.1165,
      "step": 8150
    },
    {
      "epoch": 3.823805060918463,
      "grad_norm": 1.9116188287734985,
      "learning_rate": 1.761012183692596e-05,
      "loss": 0.1316,
      "step": 8160
    },
    {
      "epoch": 3.8284910965323338,
      "grad_norm": 2.3420250415802,
      "learning_rate": 1.7607193064667293e-05,
      "loss": 0.1176,
      "step": 8170
    },
    {
      "epoch": 3.8331771321462043,
      "grad_norm": 2.0588436126708984,
      "learning_rate": 1.7604264292408623e-05,
      "loss": 0.1365,
      "step": 8180
    },
    {
      "epoch": 3.8378631677600747,
      "grad_norm": 1.89832603931427,
      "learning_rate": 1.7601335520149952e-05,
      "loss": 0.1459,
      "step": 8190
    },
    {
      "epoch": 3.8425492033739457,
      "grad_norm": 2.0133140087127686,
      "learning_rate": 1.7598406747891285e-05,
      "loss": 0.1075,
      "step": 8200
    },
    {
      "epoch": 3.847235238987816,
      "grad_norm": 1.7235685586929321,
      "learning_rate": 1.7595477975632615e-05,
      "loss": 0.1143,
      "step": 8210
    },
    {
      "epoch": 3.851921274601687,
      "grad_norm": 1.6717524528503418,
      "learning_rate": 1.7592549203373948e-05,
      "loss": 0.1269,
      "step": 8220
    },
    {
      "epoch": 3.8566073102155576,
      "grad_norm": 1.5314955711364746,
      "learning_rate": 1.7589620431115277e-05,
      "loss": 0.1264,
      "step": 8230
    },
    {
      "epoch": 3.861293345829428,
      "grad_norm": 2.4005510807037354,
      "learning_rate": 1.758669165885661e-05,
      "loss": 0.1299,
      "step": 8240
    },
    {
      "epoch": 3.865979381443299,
      "grad_norm": 1.6033201217651367,
      "learning_rate": 1.758376288659794e-05,
      "loss": 0.1107,
      "step": 8250
    },
    {
      "epoch": 3.865979381443299,
      "eval_loss": 0.04320518299937248,
      "eval_pearson_cosine": 0.7953389681810563,
      "eval_pearson_dot": 0.6355398535557981,
      "eval_pearson_euclidean": 0.7518228241740452,
      "eval_pearson_manhattan": 0.7507054666151873,
      "eval_runtime": 3.6594,
      "eval_samples_per_second": 409.902,
      "eval_spearman_cosine": 0.799221389686279,
      "eval_spearman_dot": 0.6411224962967852,
      "eval_spearman_euclidean": 0.7674570737836293,
      "eval_spearman_manhattan": 0.7673149114040088,
      "eval_steps_per_second": 25.687,
      "step": 8250
    },
    {
      "epoch": 3.8706654170571695,
      "grad_norm": 1.8069274425506592,
      "learning_rate": 1.7580834114339272e-05,
      "loss": 0.1293,
      "step": 8260
    },
    {
      "epoch": 3.8753514526710404,
      "grad_norm": 1.9214448928833008,
      "learning_rate": 1.7577905342080602e-05,
      "loss": 0.1235,
      "step": 8270
    },
    {
      "epoch": 3.880037488284911,
      "grad_norm": 2.0332281589508057,
      "learning_rate": 1.757497656982193e-05,
      "loss": 0.1303,
      "step": 8280
    },
    {
      "epoch": 3.8847235238987814,
      "grad_norm": 1.8587048053741455,
      "learning_rate": 1.7572047797563264e-05,
      "loss": 0.1272,
      "step": 8290
    },
    {
      "epoch": 3.8894095595126523,
      "grad_norm": 1.7040314674377441,
      "learning_rate": 1.7569119025304594e-05,
      "loss": 0.1304,
      "step": 8300
    },
    {
      "epoch": 3.894095595126523,
      "grad_norm": 1.7979313135147095,
      "learning_rate": 1.7566190253045923e-05,
      "loss": 0.1226,
      "step": 8310
    },
    {
      "epoch": 3.8987816307403937,
      "grad_norm": 1.6295264959335327,
      "learning_rate": 1.7563261480787256e-05,
      "loss": 0.1198,
      "step": 8320
    },
    {
      "epoch": 3.9034676663542642,
      "grad_norm": 1.764858603477478,
      "learning_rate": 1.7560332708528586e-05,
      "loss": 0.1294,
      "step": 8330
    },
    {
      "epoch": 3.9081537019681347,
      "grad_norm": 2.3997533321380615,
      "learning_rate": 1.7557403936269915e-05,
      "loss": 0.1288,
      "step": 8340
    },
    {
      "epoch": 3.9128397375820057,
      "grad_norm": 2.302992820739746,
      "learning_rate": 1.7554475164011248e-05,
      "loss": 0.1482,
      "step": 8350
    },
    {
      "epoch": 3.917525773195876,
      "grad_norm": 1.8705153465270996,
      "learning_rate": 1.7551546391752578e-05,
      "loss": 0.1203,
      "step": 8360
    },
    {
      "epoch": 3.922211808809747,
      "grad_norm": 2.1490349769592285,
      "learning_rate": 1.754861761949391e-05,
      "loss": 0.1074,
      "step": 8370
    },
    {
      "epoch": 3.9268978444236176,
      "grad_norm": 1.5012431144714355,
      "learning_rate": 1.754568884723524e-05,
      "loss": 0.1202,
      "step": 8380
    },
    {
      "epoch": 3.931583880037488,
      "grad_norm": 1.2775022983551025,
      "learning_rate": 1.754276007497657e-05,
      "loss": 0.1241,
      "step": 8390
    },
    {
      "epoch": 3.936269915651359,
      "grad_norm": 2.361064910888672,
      "learning_rate": 1.7539831302717902e-05,
      "loss": 0.1393,
      "step": 8400
    },
    {
      "epoch": 3.9409559512652295,
      "grad_norm": 1.8726896047592163,
      "learning_rate": 1.7536902530459232e-05,
      "loss": 0.1191,
      "step": 8410
    },
    {
      "epoch": 3.9456419868791004,
      "grad_norm": 1.8277250528335571,
      "learning_rate": 1.7533973758200565e-05,
      "loss": 0.1265,
      "step": 8420
    },
    {
      "epoch": 3.950328022492971,
      "grad_norm": 1.534006118774414,
      "learning_rate": 1.7531044985941894e-05,
      "loss": 0.1153,
      "step": 8430
    },
    {
      "epoch": 3.9550140581068414,
      "grad_norm": 1.9085185527801514,
      "learning_rate": 1.7528116213683227e-05,
      "loss": 0.1216,
      "step": 8440
    },
    {
      "epoch": 3.9597000937207123,
      "grad_norm": 2.059544563293457,
      "learning_rate": 1.7525187441424557e-05,
      "loss": 0.1185,
      "step": 8450
    },
    {
      "epoch": 3.964386129334583,
      "grad_norm": 2.6308438777923584,
      "learning_rate": 1.752225866916589e-05,
      "loss": 0.1137,
      "step": 8460
    },
    {
      "epoch": 3.9690721649484537,
      "grad_norm": 1.2617682218551636,
      "learning_rate": 1.751932989690722e-05,
      "loss": 0.143,
      "step": 8470
    },
    {
      "epoch": 3.973758200562324,
      "grad_norm": 2.1921794414520264,
      "learning_rate": 1.751640112464855e-05,
      "loss": 0.1086,
      "step": 8480
    },
    {
      "epoch": 3.9784442361761947,
      "grad_norm": 1.7036564350128174,
      "learning_rate": 1.751347235238988e-05,
      "loss": 0.127,
      "step": 8490
    },
    {
      "epoch": 3.9831302717900656,
      "grad_norm": 1.6190659999847412,
      "learning_rate": 1.751054358013121e-05,
      "loss": 0.1232,
      "step": 8500
    },
    {
      "epoch": 3.9831302717900656,
      "eval_loss": 0.04382430762052536,
      "eval_pearson_cosine": 0.7946660833476784,
      "eval_pearson_dot": 0.6408322008008298,
      "eval_pearson_euclidean": 0.7506581872281402,
      "eval_pearson_manhattan": 0.7492952268314212,
      "eval_runtime": 3.2595,
      "eval_samples_per_second": 460.2,
      "eval_spearman_cosine": 0.7991836067006112,
      "eval_spearman_dot": 0.6471776019534929,
      "eval_spearman_euclidean": 0.7665561093361127,
      "eval_spearman_manhattan": 0.7655283844207366,
      "eval_steps_per_second": 28.839,
      "step": 8500
    },
    {
      "epoch": 3.987816307403936,
      "grad_norm": 1.5553314685821533,
      "learning_rate": 1.750761480787254e-05,
      "loss": 0.1199,
      "step": 8510
    },
    {
      "epoch": 3.992502343017807,
      "grad_norm": 1.8198939561843872,
      "learning_rate": 1.750468603561387e-05,
      "loss": 0.1387,
      "step": 8520
    },
    {
      "epoch": 3.9971883786316775,
      "grad_norm": 1.5737895965576172,
      "learning_rate": 1.7501757263355203e-05,
      "loss": 0.1291,
      "step": 8530
    }
  ],
  "logging_steps": 10,
  "max_steps": 8536,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}