{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8253968253968254,
  "eval_steps": 5,
  "global_step": 104,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007936507936507936,
      "grad_norm": 3.5297670364379883,
      "learning_rate": 5.555555555555555e-07,
      "loss": 0.404,
      "step": 1
    },
    {
      "epoch": 0.015873015873015872,
      "grad_norm": 3.6838796138763428,
      "learning_rate": 1.111111111111111e-06,
      "loss": 0.3185,
      "step": 2
    },
    {
      "epoch": 0.023809523809523808,
      "grad_norm": 3.5556721687316895,
      "learning_rate": 1.6666666666666665e-06,
      "loss": 0.2821,
      "step": 3
    },
    {
      "epoch": 0.031746031746031744,
      "grad_norm": 3.922109842300415,
      "learning_rate": 2.222222222222222e-06,
      "loss": 0.4036,
      "step": 4
    },
    {
      "epoch": 0.03968253968253968,
      "grad_norm": 3.9366657733917236,
      "learning_rate": 2.7777777777777775e-06,
      "loss": 0.3442,
      "step": 5
    },
    {
      "epoch": 0.03968253968253968,
      "eval_loss": 0.12529698014259338,
      "eval_runtime": 113.8002,
      "eval_samples_per_second": 26.819,
      "eval_steps_per_second": 0.211,
      "eval_sts-test_pearson_cosine": 0.886081184413048,
      "eval_sts-test_pearson_dot": 0.8767533438290611,
      "eval_sts-test_pearson_euclidean": 0.9080817963557108,
      "eval_sts-test_pearson_manhattan": 0.9087794191320873,
      "eval_sts-test_pearson_max": 0.9087794191320873,
      "eval_sts-test_spearman_cosine": 0.9077787555581409,
      "eval_sts-test_spearman_dot": 0.8792746633711961,
      "eval_sts-test_spearman_euclidean": 0.9039925750881216,
      "eval_sts-test_spearman_manhattan": 0.904489537845873,
      "eval_sts-test_spearman_max": 0.9077787555581409,
      "step": 5
    },
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 3.8135547637939453,
      "learning_rate": 3.333333333333333e-06,
      "loss": 0.4145,
      "step": 6
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 4.132374286651611,
      "learning_rate": 3.888888888888889e-06,
      "loss": 0.4224,
      "step": 7
    },
    {
      "epoch": 0.06349206349206349,
      "grad_norm": 3.9953386783599854,
      "learning_rate": 4.444444444444444e-06,
      "loss": 0.4048,
      "step": 8
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 4.023675918579102,
      "learning_rate": 4.9999999999999996e-06,
      "loss": 0.3899,
      "step": 9
    },
    {
      "epoch": 0.07936507936507936,
      "grad_norm": 3.854191780090332,
      "learning_rate": 5.555555555555555e-06,
      "loss": 0.4127,
      "step": 10
    },
    {
      "epoch": 0.07936507936507936,
      "eval_loss": 0.12369368970394135,
      "eval_runtime": 113.6707,
      "eval_samples_per_second": 26.849,
      "eval_steps_per_second": 0.211,
      "eval_sts-test_pearson_cosine": 0.8860118050647048,
      "eval_sts-test_pearson_dot": 0.8760605933678182,
      "eval_sts-test_pearson_euclidean": 0.9086480781293332,
      "eval_sts-test_pearson_manhattan": 0.9092897840847158,
      "eval_sts-test_pearson_max": 0.9092897840847158,
      "eval_sts-test_spearman_cosine": 0.9078577415344969,
      "eval_sts-test_spearman_dot": 0.8791339654053815,
      "eval_sts-test_spearman_euclidean": 0.9047648028546915,
      "eval_sts-test_spearman_manhattan": 0.9052383607027356,
      "eval_sts-test_spearman_max": 0.9078577415344969,
      "step": 10
    },
    {
      "epoch": 0.0873015873015873,
      "grad_norm": 3.8079540729522705,
      "learning_rate": 6.11111111111111e-06,
      "loss": 0.3496,
      "step": 11
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 3.929018259048462,
      "learning_rate": 6.666666666666666e-06,
      "loss": 0.3731,
      "step": 12
    },
    {
      "epoch": 0.10317460317460317,
      "grad_norm": 4.284013271331787,
      "learning_rate": 7.222222222222221e-06,
      "loss": 0.3929,
      "step": 13
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 3.3490402698516846,
      "learning_rate": 7.777777777777777e-06,
      "loss": 0.2957,
      "step": 14
    },
    {
      "epoch": 0.11904761904761904,
      "grad_norm": 3.553280830383301,
      "learning_rate": 8.333333333333332e-06,
      "loss": 0.3324,
      "step": 15
    },
    {
      "epoch": 0.11904761904761904,
      "eval_loss": 0.12056715041399002,
      "eval_runtime": 113.718,
      "eval_samples_per_second": 26.838,
      "eval_steps_per_second": 0.211,
      "eval_sts-test_pearson_cosine": 0.8856265458568289,
      "eval_sts-test_pearson_dot": 0.8743050518330721,
      "eval_sts-test_pearson_euclidean": 0.9095228583162331,
      "eval_sts-test_pearson_manhattan": 0.9101600217218586,
      "eval_sts-test_pearson_max": 0.9101600217218586,
      "eval_sts-test_spearman_cosine": 0.908261263658463,
      "eval_sts-test_spearman_dot": 0.87867141636764,
      "eval_sts-test_spearman_euclidean": 0.9060734192402989,
      "eval_sts-test_spearman_manhattan": 0.9066336155303966,
      "eval_sts-test_spearman_max": 0.908261263658463,
      "step": 15
    },
    {
      "epoch": 0.12698412698412698,
      "grad_norm": 3.6310322284698486,
      "learning_rate": 8.888888888888888e-06,
      "loss": 0.3341,
      "step": 16
    },
    {
      "epoch": 0.1349206349206349,
      "grad_norm": 3.6535122394561768,
      "learning_rate": 9.444444444444443e-06,
      "loss": 0.3466,
      "step": 17
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 3.6199331283569336,
      "learning_rate": 9.999999999999999e-06,
      "loss": 0.3558,
      "step": 18
    },
    {
      "epoch": 0.15079365079365079,
      "grad_norm": 3.089895248413086,
      "learning_rate": 1.0555555555555554e-05,
      "loss": 0.2634,
      "step": 19
    },
    {
      "epoch": 0.15873015873015872,
      "grad_norm": 3.320916175842285,
      "learning_rate": 1.111111111111111e-05,
      "loss": 0.3095,
      "step": 20
    },
    {
      "epoch": 0.15873015873015872,
      "eval_loss": 0.11563990265130997,
      "eval_runtime": 113.5377,
      "eval_samples_per_second": 26.881,
      "eval_steps_per_second": 0.211,
      "eval_sts-test_pearson_cosine": 0.8848740042612456,
      "eval_sts-test_pearson_dot": 0.8724689429546052,
      "eval_sts-test_pearson_euclidean": 0.9104294765782397,
      "eval_sts-test_pearson_manhattan": 0.9111381492292419,
      "eval_sts-test_pearson_max": 0.9111381492292419,
      "eval_sts-test_spearman_cosine": 0.9087803335393421,
      "eval_sts-test_spearman_dot": 0.8777188410176626,
      "eval_sts-test_spearman_euclidean": 0.9069791847708608,
      "eval_sts-test_spearman_manhattan": 0.9078148698260838,
      "eval_sts-test_spearman_max": 0.9087803335393421,
      "step": 20
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 3.0193159580230713,
      "learning_rate": 1.1666666666666665e-05,
      "loss": 0.2973,
      "step": 21
    },
    {
      "epoch": 0.1746031746031746,
      "grad_norm": 3.3553476333618164,
      "learning_rate": 1.222222222222222e-05,
      "loss": 0.2884,
      "step": 22
    },
    {
      "epoch": 0.18253968253968253,
      "grad_norm": 3.5176496505737305,
      "learning_rate": 1.2777777777777775e-05,
      "loss": 0.3697,
      "step": 23
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 3.2073943614959717,
      "learning_rate": 1.3333333333333332e-05,
      "loss": 0.2683,
      "step": 24
    },
    {
      "epoch": 0.1984126984126984,
      "grad_norm": 3.2101964950561523,
      "learning_rate": 1.3888888888888886e-05,
      "loss": 0.3026,
      "step": 25
    },
    {
      "epoch": 0.1984126984126984,
      "eval_loss": 0.10958973318338394,
      "eval_runtime": 113.6214,
      "eval_samples_per_second": 26.861,
      "eval_steps_per_second": 0.211,
      "eval_sts-test_pearson_cosine": 0.8832622086480311,
      "eval_sts-test_pearson_dot": 0.8697582354953435,
      "eval_sts-test_pearson_euclidean": 0.9107566690862425,
      "eval_sts-test_pearson_manhattan": 0.9115546986654615,
      "eval_sts-test_pearson_max": 0.9115546986654615,
      "eval_sts-test_spearman_cosine": 0.9087605087305455,
      "eval_sts-test_spearman_dot": 0.8760767382321666,
      "eval_sts-test_spearman_euclidean": 0.9073999361304628,
      "eval_sts-test_spearman_manhattan": 0.9084107328715103,
      "eval_sts-test_spearman_max": 0.9087605087305455,
      "step": 25
    },
    {
      "epoch": 0.20634920634920634,
      "grad_norm": 2.84037709236145,
      "learning_rate": 1.4444444444444442e-05,
      "loss": 0.2441,
      "step": 26
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 3.3099992275238037,
      "learning_rate": 1.4999999999999999e-05,
      "loss": 0.3145,
      "step": 27
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 3.061953067779541,
      "learning_rate": 1.5555555555555555e-05,
      "loss": 0.3119,
      "step": 28
    },
    {
      "epoch": 0.23015873015873015,
      "grad_norm": 3.0163729190826416,
      "learning_rate": 1.6111111111111108e-05,
      "loss": 0.2766,
      "step": 29
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 3.140418291091919,
      "learning_rate": 1.6666666666666664e-05,
      "loss": 0.3343,
      "step": 30
    },
    {
      "epoch": 0.23809523809523808,
      "eval_loss": 0.10535401105880737,
      "eval_runtime": 113.5942,
      "eval_samples_per_second": 26.868,
      "eval_steps_per_second": 0.211,
      "eval_sts-test_pearson_cosine": 0.8819465403802665,
      "eval_sts-test_pearson_dot": 0.866997957398371,
      "eval_sts-test_pearson_euclidean": 0.9110501477101954,
      "eval_sts-test_pearson_manhattan": 0.9119047974126511,
      "eval_sts-test_pearson_max": 0.9119047974126511,
      "eval_sts-test_spearman_cosine": 0.9084358383291508,
      "eval_sts-test_spearman_dot": 0.8727757956894143,
      "eval_sts-test_spearman_euclidean": 0.9077817538926543,
      "eval_sts-test_spearman_manhattan": 0.9089103807049453,
      "eval_sts-test_spearman_max": 0.9089103807049453,
      "step": 30
    },
    {
      "epoch": 0.24603174603174602,
      "grad_norm": 3.1329221725463867,
      "learning_rate": 1.722222222222222e-05,
      "loss": 0.344,
      "step": 31
    },
    {
      "epoch": 0.25396825396825395,
      "grad_norm": 2.9861748218536377,
      "learning_rate": 1.7777777777777777e-05,
      "loss": 0.3005,
      "step": 32
    },
    {
      "epoch": 0.2619047619047619,
      "grad_norm": 2.8316733837127686,
      "learning_rate": 1.8333333333333333e-05,
      "loss": 0.2526,
      "step": 33
    },
    {
      "epoch": 0.2698412698412698,
      "grad_norm": 2.8335487842559814,
      "learning_rate": 1.8888888888888886e-05,
      "loss": 0.2422,
      "step": 34
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 3.0785422325134277,
      "learning_rate": 1.9444444444444442e-05,
      "loss": 0.3447,
      "step": 35
    },
    {
      "epoch": 0.2777777777777778,
      "eval_loss": 0.10223711282014847,
      "eval_runtime": 113.9847,
      "eval_samples_per_second": 26.776,
      "eval_steps_per_second": 0.211,
      "eval_sts-test_pearson_cosine": 0.8812001280334643,
      "eval_sts-test_pearson_dot": 0.8652746969985129,
      "eval_sts-test_pearson_euclidean": 0.9105701789873448,
      "eval_sts-test_pearson_manhattan": 0.9116177887236803,
      "eval_sts-test_pearson_max": 0.9116177887236803,
      "eval_sts-test_spearman_cosine": 0.9072243769320245,
      "eval_sts-test_spearman_dot": 0.8716048789351082,
      "eval_sts-test_spearman_euclidean": 0.9073166540330135,
      "eval_sts-test_spearman_manhattan": 0.9081332302996223,
      "eval_sts-test_spearman_max": 0.9081332302996223,
      "step": 35
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 2.944396734237671,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 0.2809,
      "step": 36
    },
    {
      "epoch": 0.29365079365079366,
      "grad_norm": 2.8323400020599365,
      "learning_rate": 2.0555555555555555e-05,
      "loss": 0.2836,
      "step": 37
    },
    {
      "epoch": 0.30158730158730157,
      "grad_norm": 2.8760273456573486,
      "learning_rate": 2.1111111111111107e-05,
      "loss": 0.2878,
      "step": 38
    },
    {
      "epoch": 0.30952380952380953,
      "grad_norm": 2.744379758834839,
      "learning_rate": 2.1666666666666667e-05,
      "loss": 0.2738,
      "step": 39
    },
    {
      "epoch": 0.31746031746031744,
      "grad_norm": 2.8519983291625977,
      "learning_rate": 2.222222222222222e-05,
      "loss": 0.2806,
      "step": 40
    },
    {
      "epoch": 0.31746031746031744,
      "eval_loss": 0.10033170133829117,
      "eval_runtime": 113.5147,
      "eval_samples_per_second": 26.886,
      "eval_steps_per_second": 0.211,
      "eval_sts-test_pearson_cosine": 0.8802115569848467,
      "eval_sts-test_pearson_dot": 0.8634798448575132,
      "eval_sts-test_pearson_euclidean": 0.9094188438238102,
      "eval_sts-test_pearson_manhattan": 0.9105849471172345,
      "eval_sts-test_pearson_max": 0.9105849471172345,
      "eval_sts-test_spearman_cosine": 0.9064710789490229,
      "eval_sts-test_spearman_dot": 0.8693704037025742,
      "eval_sts-test_spearman_euclidean": 0.9064271779615981,
      "eval_sts-test_spearman_manhattan": 0.9073247092600637,
      "eval_sts-test_spearman_max": 0.9073247092600637,
      "step": 40
    },
    {
      "epoch": 0.3253968253968254,
      "grad_norm": 2.9139747619628906,
      "learning_rate": 2.2777777777777776e-05,
      "loss": 0.2797,
      "step": 41
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 2.9206557273864746,
      "learning_rate": 2.333333333333333e-05,
      "loss": 0.3217,
      "step": 42
    },
    {
      "epoch": 0.3412698412698413,
      "grad_norm": 2.755398988723755,
      "learning_rate": 2.388888888888889e-05,
      "loss": 0.2544,
      "step": 43
    },
    {
      "epoch": 0.3492063492063492,
      "grad_norm": 3.0441982746124268,
      "learning_rate": 2.444444444444444e-05,
      "loss": 0.3203,
      "step": 44
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 2.978891611099243,
      "learning_rate": 2.4999999999999998e-05,
      "loss": 0.2987,
      "step": 45
    },
    {
      "epoch": 0.35714285714285715,
      "eval_loss": 0.09902294725179672,
      "eval_runtime": 113.6912,
      "eval_samples_per_second": 26.845,
      "eval_steps_per_second": 0.211,
      "eval_sts-test_pearson_cosine": 0.8796209948380269,
      "eval_sts-test_pearson_dot": 0.8617122615494917,
      "eval_sts-test_pearson_euclidean": 0.9092272396432914,
      "eval_sts-test_pearson_manhattan": 0.9100341993020892,
      "eval_sts-test_pearson_max": 0.9100341993020892,
      "eval_sts-test_spearman_cosine": 0.9063911531961779,
      "eval_sts-test_spearman_dot": 0.867835166929281,
      "eval_sts-test_spearman_euclidean": 0.9066020658911155,
      "eval_sts-test_spearman_manhattan": 0.9072894005148261,
      "eval_sts-test_spearman_max": 0.9072894005148261,
      "step": 45
    },
    {
      "epoch": 0.36507936507936506,
      "grad_norm": 2.9183595180511475,
      "learning_rate": 2.555555555555555e-05,
      "loss": 0.2765,
      "step": 46
    },
    {
      "epoch": 0.373015873015873,
      "grad_norm": 2.960238456726074,
      "learning_rate": 2.611111111111111e-05,
      "loss": 0.2716,
      "step": 47
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 3.23356294631958,
      "learning_rate": 2.6666666666666663e-05,
      "loss": 0.3726,
      "step": 48
    },
    {
      "epoch": 0.3888888888888889,
      "grad_norm": 2.974705457687378,
      "learning_rate": 2.722222222222222e-05,
      "loss": 0.2963,
      "step": 49
    },
    {
      "epoch": 0.3968253968253968,
      "grad_norm": 2.8041574954986572,
      "learning_rate": 2.7777777777777772e-05,
      "loss": 0.2784,
      "step": 50
    },
    {
      "epoch": 0.3968253968253968,
      "eval_loss": 0.09521521627902985,
      "eval_runtime": 113.6139,
      "eval_samples_per_second": 26.863,
      "eval_steps_per_second": 0.211,
      "eval_sts-test_pearson_cosine": 0.8802451373465323,
      "eval_sts-test_pearson_dot": 0.8609764645232105,
      "eval_sts-test_pearson_euclidean": 0.9103012041260427,
      "eval_sts-test_pearson_manhattan": 0.9108880877390901,
      "eval_sts-test_pearson_max": 0.9108880877390901,
      "eval_sts-test_spearman_cosine": 0.9071928272927434,
      "eval_sts-test_spearman_dot": 0.867374407941995,
      "eval_sts-test_spearman_euclidean": 0.9083242734345022,
      "eval_sts-test_spearman_manhattan": 0.9086424996542565,
      "eval_sts-test_spearman_max": 0.9086424996542565,
      "step": 50
    },
    {
      "epoch": 0.40476190476190477,
      "grad_norm": 2.6451456546783447,
      "learning_rate": 2.8333333333333332e-05,
      "loss": 0.2437,
      "step": 51
    },
    {
      "epoch": 0.4126984126984127,
      "grad_norm": 2.7020044326782227,
      "learning_rate": 2.8888888888888885e-05,
      "loss": 0.2258,
      "step": 52
    },
    {
      "epoch": 0.42063492063492064,
      "grad_norm": 2.7229156494140625,
      "learning_rate": 2.944444444444444e-05,
      "loss": 0.2821,
      "step": 53
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 2.770799398422241,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 0.249,
      "step": 54
    },
    {
      "epoch": 0.4365079365079365,
      "grad_norm": 2.762690305709839,
      "learning_rate": 3.0555555555555554e-05,
      "loss": 0.2813,
      "step": 55
    },
    {
      "epoch": 0.4365079365079365,
      "eval_loss": 0.09280610829591751,
      "eval_runtime": 113.4966,
      "eval_samples_per_second": 26.891,
      "eval_steps_per_second": 0.211,
      "eval_sts-test_pearson_cosine": 0.8804507408393794,
      "eval_sts-test_pearson_dot": 0.8631869703781383,
      "eval_sts-test_pearson_euclidean": 0.9108211341698824,
      "eval_sts-test_pearson_manhattan": 0.9114068237803576,
      "eval_sts-test_pearson_max": 0.9114068237803576,
      "eval_sts-test_spearman_cosine": 0.9079720810073518,
      "eval_sts-test_spearman_dot": 0.8709471248951776,
      "eval_sts-test_spearman_euclidean": 0.9085633794241165,
      "eval_sts-test_spearman_manhattan": 0.9093315348258998,
      "eval_sts-test_spearman_max": 0.9093315348258998,
      "step": 55
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 2.9767086505889893,
      "learning_rate": 3.111111111111111e-05,
      "loss": 0.3003,
      "step": 56
    },
    {
      "epoch": 0.4523809523809524,
      "grad_norm": 2.816253185272217,
      "learning_rate": 3.1666666666666666e-05,
      "loss": 0.2812,
      "step": 57
    },
    {
      "epoch": 0.4603174603174603,
      "grad_norm": 2.5184807777404785,
      "learning_rate": 3.2222222222222216e-05,
      "loss": 0.2619,
      "step": 58
    },
    {
      "epoch": 0.46825396825396826,
      "grad_norm": 2.7500715255737305,
      "learning_rate": 3.277777777777777e-05,
      "loss": 0.299,
      "step": 59
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 2.5309386253356934,
      "learning_rate": 3.333333333333333e-05,
      "loss": 0.2706,
      "step": 60
    },
    {
      "epoch": 0.47619047619047616,
      "eval_loss": 0.09274312108755112,
      "eval_runtime": 113.479,
      "eval_samples_per_second": 26.895,
      "eval_steps_per_second": 0.211,
      "eval_sts-test_pearson_cosine": 0.8814996628266308,
      "eval_sts-test_pearson_dot": 0.8647617194348185,
      "eval_sts-test_pearson_euclidean": 0.9116395612568413,
      "eval_sts-test_pearson_manhattan": 0.9121591417317261,
      "eval_sts-test_pearson_max": 0.9121591417317261,
      "eval_sts-test_spearman_cosine": 0.9087614932582961,
      "eval_sts-test_spearman_dot": 0.8732032149869635,
      "eval_sts-test_spearman_euclidean": 0.9101066714244602,
      "eval_sts-test_spearman_manhattan": 0.9099515188012163,
      "eval_sts-test_spearman_max": 0.9101066714244602,
      "step": 60
    },
    {
      "epoch": 0.48412698412698413,
      "grad_norm": 2.7175261974334717,
      "learning_rate": 3.3888888888888884e-05,
      "loss": 0.297,
      "step": 61
    },
    {
      "epoch": 0.49206349206349204,
      "grad_norm": 2.7492423057556152,
      "learning_rate": 3.444444444444444e-05,
      "loss": 0.2906,
      "step": 62
    },
    {
      "epoch": 0.5,
      "grad_norm": 2.815702438354492,
      "learning_rate": 3.5e-05,
      "loss": 0.2914,
      "step": 63
    },
    {
      "epoch": 0.5079365079365079,
      "grad_norm": 2.9056921005249023,
      "learning_rate": 3.499798538091195e-05,
      "loss": 0.2669,
      "step": 64
    },
    {
      "epoch": 0.5158730158730159,
      "grad_norm": 2.832461357116699,
      "learning_rate": 3.4991942080268184e-05,
      "loss": 0.2723,
      "step": 65
    },
    {
      "epoch": 0.5158730158730159,
      "eval_loss": 0.09455278515815735,
      "eval_runtime": 113.5618,
      "eval_samples_per_second": 26.875,
      "eval_steps_per_second": 0.211,
      "eval_sts-test_pearson_cosine": 0.8827592572843797,
      "eval_sts-test_pearson_dot": 0.8655702748779494,
      "eval_sts-test_pearson_euclidean": 0.9124138196335778,
      "eval_sts-test_pearson_manhattan": 0.9124858955018784,
      "eval_sts-test_pearson_max": 0.9124858955018784,
      "eval_sts-test_spearman_cosine": 0.9092536676310787,
      "eval_sts-test_spearman_dot": 0.87468645079452,
      "eval_sts-test_spearman_euclidean": 0.910149408879089,
      "eval_sts-test_spearman_manhattan": 0.9104867886387189,
      "eval_sts-test_spearman_max": 0.9104867886387189,
      "step": 65
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 2.834491729736328,
      "learning_rate": 3.4981871767775944e-05,
      "loss": 0.3194,
      "step": 66
    },
    {
      "epoch": 0.5317460317460317,
      "grad_norm": 3.168403148651123,
      "learning_rate": 3.496777722576811e-05,
      "loss": 0.3585,
      "step": 67
    },
    {
      "epoch": 0.5396825396825397,
      "grad_norm": 2.8590433597564697,
      "learning_rate": 3.494966234843439e-05,
      "loss": 0.2843,
      "step": 68
    },
    {
      "epoch": 0.5476190476190477,
      "grad_norm": 2.4585649967193604,
      "learning_rate": 3.4927532140745435e-05,
      "loss": 0.1916,
      "step": 69
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 3.0862460136413574,
      "learning_rate": 3.490139271707e-05,
      "loss": 0.351,
      "step": 70
    },
    {
      "epoch": 0.5555555555555556,
      "eval_loss": 0.09706800431013107,
      "eval_runtime": 113.496,
      "eval_samples_per_second": 26.891,
      "eval_steps_per_second": 0.211,
      "eval_sts-test_pearson_cosine": 0.8816183440112817,
      "eval_sts-test_pearson_dot": 0.863407251078466,
      "eval_sts-test_pearson_euclidean": 0.9125994563651346,
      "eval_sts-test_pearson_manhattan": 0.9121928260729458,
      "eval_sts-test_pearson_max": 0.9125994563651346,
      "eval_sts-test_spearman_cosine": 0.9103631836274073,
      "eval_sts-test_spearman_dot": 0.8729154643762167,
      "eval_sts-test_spearman_euclidean": 0.9106339755374351,
      "eval_sts-test_spearman_manhattan": 0.9104940383430642,
      "eval_sts-test_spearman_max": 0.9106339755374351,
      "step": 70
    },
    {
      "epoch": 0.5634920634920635,
      "grad_norm": 2.948397636413574,
      "learning_rate": 3.48712512994856e-05,
      "loss": 0.3105,
      "step": 71
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 2.904085159301758,
      "learning_rate": 3.4837116215783116e-05,
      "loss": 0.2847,
      "step": 72
    },
    {
      "epoch": 0.5793650793650794,
      "grad_norm": 2.6948978900909424,
      "learning_rate": 3.4798996897165926e-05,
      "loss": 0.2641,
      "step": 73
    },
    {
      "epoch": 0.5873015873015873,
      "grad_norm": 3.068554162979126,
      "learning_rate": 3.475690387564411e-05,
      "loss": 0.3305,
      "step": 74
    },
    {
      "epoch": 0.5952380952380952,
      "grad_norm": 2.6903178691864014,
      "learning_rate": 3.471084878112459e-05,
      "loss": 0.2461,
      "step": 75
    },
    {
      "epoch": 0.5952380952380952,
      "eval_loss": 0.09646341949701309,
      "eval_runtime": 113.5342,
      "eval_samples_per_second": 26.882,
      "eval_steps_per_second": 0.211,
      "eval_sts-test_pearson_cosine": 0.879746728283104,
      "eval_sts-test_pearson_dot": 0.85998475002447,
      "eval_sts-test_pearson_euclidean": 0.9117602609729114,
      "eval_sts-test_pearson_manhattan": 0.9111396965114745,
      "eval_sts-test_pearson_max": 0.9117602609729114,
      "eval_sts-test_spearman_cosine": 0.9096228207862964,
      "eval_sts-test_spearman_dot": 0.8689540379665887,
      "eval_sts-test_spearman_euclidean": 0.9099527718365351,
      "eval_sts-test_spearman_manhattan": 0.9098263942743658,
      "eval_sts-test_spearman_max": 0.9099527718365351,
      "step": 75
    },
    {
      "epoch": 0.6031746031746031,
      "grad_norm": 2.81105637550354,
      "learning_rate": 3.4660844338197886e-05,
      "loss": 0.259,
      "step": 76
    },
    {
      "epoch": 0.6111111111111112,
      "grad_norm": 2.629365921020508,
      "learning_rate": 3.460690436262242e-05,
      "loss": 0.2506,
      "step": 77
    },
    {
      "epoch": 0.6190476190476191,
      "grad_norm": 2.6665291786193848,
      "learning_rate": 3.454904375750738e-05,
      "loss": 0.2832,
      "step": 78
    },
    {
      "epoch": 0.626984126984127,
      "grad_norm": 2.916246175765991,
      "learning_rate": 3.448727850919509e-05,
      "loss": 0.3322,
      "step": 79
    },
    {
      "epoch": 0.6349206349206349,
      "grad_norm": 2.4879415035247803,
      "learning_rate": 3.442162568284416e-05,
      "loss": 0.2533,
      "step": 80
    },
    {
      "epoch": 0.6349206349206349,
      "eval_loss": 0.10007175803184509,
      "eval_runtime": 113.3295,
      "eval_samples_per_second": 26.93,
      "eval_steps_per_second": 0.212,
      "eval_sts-test_pearson_cosine": 0.8791063595826033,
      "eval_sts-test_pearson_dot": 0.8594763353424633,
      "eval_sts-test_pearson_euclidean": 0.9109289279488433,
      "eval_sts-test_pearson_manhattan": 0.9101783025650423,
      "eval_sts-test_pearson_max": 0.9109289279488433,
      "eval_sts-test_spearman_cosine": 0.9088725211378084,
      "eval_sts-test_spearman_dot": 0.8680133664521414,
      "eval_sts-test_spearman_euclidean": 0.9091277823327847,
      "eval_sts-test_spearman_manhattan": 0.9091334209917199,
      "eval_sts-test_spearman_max": 0.9091334209917199,
      "step": 80
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 2.6558098793029785,
      "learning_rate": 3.435210341771455e-05,
      "loss": 0.2349,
      "step": 81
    },
    {
      "epoch": 0.6507936507936508,
      "grad_norm": 2.690624475479126,
      "learning_rate": 3.427873092215584e-05,
      "loss": 0.2748,
      "step": 82
    },
    {
      "epoch": 0.6587301587301587,
      "grad_norm": 2.451726198196411,
      "learning_rate": 3.420152846830015e-05,
      "loss": 0.223,
      "step": 83
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 2.6376216411590576,
      "learning_rate": 3.412051738646116e-05,
      "loss": 0.2416,
      "step": 84
    },
    {
      "epoch": 0.6746031746031746,
      "grad_norm": 2.8111939430236816,
      "learning_rate": 3.403572005924071e-05,
      "loss": 0.2637,
      "step": 85
    },
    {
      "epoch": 0.6746031746031746,
      "eval_loss": 0.10335631668567657,
      "eval_runtime": 113.4166,
      "eval_samples_per_second": 26.91,
      "eval_steps_per_second": 0.212,
      "eval_sts-test_pearson_cosine": 0.8779388329417936,
      "eval_sts-test_pearson_dot": 0.8608493769098732,
      "eval_sts-test_pearson_euclidean": 0.9095252832629803,
      "eval_sts-test_pearson_manhattan": 0.9090695197203245,
      "eval_sts-test_pearson_max": 0.9095252832629803,
      "eval_sts-test_spearman_cosine": 0.9082387985252446,
      "eval_sts-test_spearman_dot": 0.8707913010030126,
      "eval_sts-test_spearman_euclidean": 0.9083403391373417,
      "eval_sts-test_spearman_manhattan": 0.9084906586243554,
      "eval_sts-test_spearman_max": 0.9084906586243554,
      "step": 85
    },
    {
      "epoch": 0.6825396825396826,
      "grad_norm": 2.859077215194702,
      "learning_rate": 3.394715991534474e-05,
      "loss": 0.2856,
      "step": 86
    },
    {
      "epoch": 0.6904761904761905,
      "grad_norm": 2.433560371398926,
      "learning_rate": 3.385486142311011e-05,
      "loss": 0.2476,
      "step": 87
    },
    {
      "epoch": 0.6984126984126984,
      "grad_norm": 2.6791834831237793,
      "learning_rate": 3.375885008374425e-05,
      "loss": 0.2427,
      "step": 88
    },
    {
      "epoch": 0.7063492063492064,
      "grad_norm": 2.6574490070343018,
      "learning_rate": 3.365915242427944e-05,
      "loss": 0.2614,
      "step": 89
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 2.5747766494750977,
      "learning_rate": 3.355579599024361e-05,
      "loss": 0.26,
      "step": 90
    },
    {
      "epoch": 0.7142857142857143,
      "eval_loss": 0.10315236449241638,
      "eval_runtime": 113.4044,
      "eval_samples_per_second": 26.913,
      "eval_steps_per_second": 0.212,
      "eval_sts-test_pearson_cosine": 0.8793659111713259,
      "eval_sts-test_pearson_dot": 0.8641308245754843,
      "eval_sts-test_pearson_euclidean": 0.9095961426218309,
      "eval_sts-test_pearson_manhattan": 0.9093977382821561,
      "eval_sts-test_pearson_max": 0.9095961426218309,
      "eval_sts-test_spearman_cosine": 0.9087700407492219,
      "eval_sts-test_spearman_dot": 0.8756799287974091,
      "eval_sts-test_spearman_euclidean": 0.9084703415516837,
      "eval_sts-test_spearman_manhattan": 0.908642678659302,
      "eval_sts-test_spearman_max": 0.9087700407492219,
      "step": 90
    },
    {
      "epoch": 0.7222222222222222,
      "grad_norm": 2.3570423126220703,
      "learning_rate": 3.3448809338049753e-05,
      "loss": 0.1862,
      "step": 91
    },
    {
      "epoch": 0.7301587301587301,
      "grad_norm": 2.486401319503784,
      "learning_rate": 3.333822202710612e-05,
      "loss": 0.267,
      "step": 92
    },
    {
      "epoch": 0.7380952380952381,
      "grad_norm": 2.436018705368042,
      "learning_rate": 3.322406461164916e-05,
      "loss": 0.2175,
      "step": 93
    },
    {
      "epoch": 0.746031746031746,
      "grad_norm": 2.2685282230377197,
      "learning_rate": 3.310636863230172e-05,
      "loss": 0.2079,
      "step": 94
    },
    {
      "epoch": 0.753968253968254,
      "grad_norm": 2.564317464828491,
      "learning_rate": 3.2985166607358637e-05,
      "loss": 0.2562,
      "step": 95
    },
    {
      "epoch": 0.753968253968254,
      "eval_loss": 0.09990089386701584,
      "eval_runtime": 113.4641,
      "eval_samples_per_second": 26.898,
      "eval_steps_per_second": 0.212,
      "eval_sts-test_pearson_cosine": 0.8795677625682299,
      "eval_sts-test_pearson_dot": 0.8659349142313639,
      "eval_sts-test_pearson_euclidean": 0.9099982334792637,
      "eval_sts-test_pearson_manhattan": 0.9099098081017423,
      "eval_sts-test_pearson_max": 0.9099982334792637,
      "eval_sts-test_spearman_cosine": 0.9085842782631862,
      "eval_sts-test_spearman_dot": 0.8767303751560495,
      "eval_sts-test_spearman_euclidean": 0.9083879992307234,
      "eval_sts-test_spearman_manhattan": 0.9084153422514337,
      "eval_sts-test_spearman_max": 0.9085842782631862,
      "step": 95
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 2.594452381134033,
      "learning_rate": 3.286049202380226e-05,
      "loss": 0.2516,
      "step": 96
    },
    {
      "epoch": 0.7698412698412699,
      "grad_norm": 2.6356875896453857,
      "learning_rate": 3.273237932805032e-05,
      "loss": 0.2956,
      "step": 97
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 2.6263818740844727,
      "learning_rate": 3.260086391643865e-05,
      "loss": 0.2733,
      "step": 98
    },
    {
      "epoch": 0.7857142857142857,
      "grad_norm": 2.636934757232666,
      "learning_rate": 3.246598212544159e-05,
      "loss": 0.2919,
      "step": 99
    },
    {
      "epoch": 0.7936507936507936,
      "grad_norm": 2.710754632949829,
      "learning_rate": 3.2327771221632486e-05,
      "loss": 0.2997,
      "step": 100
    },
    {
      "epoch": 0.7936507936507936,
      "eval_loss": 0.10318750143051147,
      "eval_runtime": 113.3236,
      "eval_samples_per_second": 26.932,
      "eval_steps_per_second": 0.212,
      "eval_sts-test_pearson_cosine": 0.8759700287215791,
      "eval_sts-test_pearson_dot": 0.8604257798750153,
      "eval_sts-test_pearson_euclidean": 0.9085309767938886,
      "eval_sts-test_pearson_manhattan": 0.9086607224369581,
      "eval_sts-test_pearson_max": 0.9086607224369581,
      "eval_sts-test_spearman_cosine": 0.9069411909499396,
      "eval_sts-test_spearman_dot": 0.8719651713405704,
      "eval_sts-test_spearman_euclidean": 0.9080629260679763,
      "eval_sts-test_spearman_manhattan": 0.907642129957113,
      "eval_sts-test_spearman_max": 0.9080629260679763,
      "step": 100
    },
    {
      "epoch": 0.8015873015873016,
      "grad_norm": 2.516517162322998,
      "learning_rate": 3.218626939138736e-05,
      "loss": 0.2276,
      "step": 101
    },
    {
      "epoch": 0.8095238095238095,
      "grad_norm": 2.6900599002838135,
      "learning_rate": 3.204151573033428e-05,
      "loss": 0.2582,
      "step": 102
    },
    {
      "epoch": 0.8174603174603174,
      "grad_norm": 2.5696845054626465,
      "learning_rate": 3.189355023255171e-05,
      "loss": 0.2559,
      "step": 103
    },
    {
      "epoch": 0.8253968253968254,
      "grad_norm": 2.7647061347961426,
      "learning_rate": 3.174241377951843e-05,
      "loss": 0.2864,
      "step": 104
    }
  ],
  "logging_steps": 1,
  "max_steps": 252,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 26,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 960,
  "trial_name": null,
  "trial_params": null
}