{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8042328042328042,
  "eval_steps": 5,
  "global_step": 152,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005291005291005291,
      "grad_norm": 4.4978814125061035,
      "learning_rate": 3.684210526315789e-07,
      "loss": 0.3768,
      "step": 1
    },
    {
      "epoch": 0.010582010582010581,
      "grad_norm": 4.62701416015625,
      "learning_rate": 7.368421052631578e-07,
      "loss": 0.3162,
      "step": 2
    },
    {
      "epoch": 0.015873015873015872,
      "grad_norm": 4.304025650024414,
      "learning_rate": 1.1052631578947367e-06,
      "loss": 0.275,
      "step": 3
    },
    {
      "epoch": 0.021164021164021163,
      "grad_norm": 4.237359046936035,
      "learning_rate": 1.4736842105263156e-06,
      "loss": 0.293,
      "step": 4
    },
    {
      "epoch": 0.026455026455026454,
      "grad_norm": 3.979759693145752,
      "learning_rate": 1.8421052631578944e-06,
      "loss": 0.2437,
      "step": 5
    },
    {
      "epoch": 0.026455026455026454,
      "eval_loss": 0.2190357893705368,
      "eval_runtime": 116.0092,
      "eval_samples_per_second": 26.308,
      "eval_steps_per_second": 0.207,
      "eval_sts-test_pearson_cosine": 0.8862434303901607,
      "eval_sts-test_pearson_dot": 0.8769941125545049,
      "eval_sts-test_pearson_euclidean": 0.9081330515608292,
      "eval_sts-test_pearson_manhattan": 0.9088207208262792,
      "eval_sts-test_pearson_max": 0.9088207208262792,
      "eval_sts-test_spearman_cosine": 0.9078630669346023,
      "eval_sts-test_spearman_dot": 0.8793787995564538,
      "eval_sts-test_spearman_euclidean": 0.9040411749579927,
      "eval_sts-test_spearman_manhattan": 0.9044944604846262,
      "eval_sts-test_spearman_max": 0.9078630669346023,
      "step": 5
    },
    {
      "epoch": 0.031746031746031744,
      "grad_norm": 4.23664665222168,
      "learning_rate": 2.2105263157894734e-06,
      "loss": 0.3681,
      "step": 6
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 3.7219350337982178,
      "learning_rate": 2.5789473684210523e-06,
      "loss": 0.2314,
      "step": 7
    },
    {
      "epoch": 0.042328042328042326,
      "grad_norm": 4.135527610778809,
      "learning_rate": 2.9473684210526313e-06,
      "loss": 0.2481,
      "step": 8
    },
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 3.6268699169158936,
      "learning_rate": 3.3157894736842103e-06,
      "loss": 0.2403,
      "step": 9
    },
    {
      "epoch": 0.05291005291005291,
      "grad_norm": 4.4451069831848145,
      "learning_rate": 3.684210526315789e-06,
      "loss": 0.2966,
      "step": 10
    },
    {
      "epoch": 0.05291005291005291,
      "eval_loss": 0.21254141628742218,
      "eval_runtime": 115.9559,
      "eval_samples_per_second": 26.32,
      "eval_steps_per_second": 0.207,
      "eval_sts-test_pearson_cosine": 0.8863175059264351,
      "eval_sts-test_pearson_dot": 0.8768417645238664,
      "eval_sts-test_pearson_euclidean": 0.908487750463006,
      "eval_sts-test_pearson_manhattan": 0.9091691821321777,
      "eval_sts-test_pearson_max": 0.9091691821321777,
      "eval_sts-test_spearman_cosine": 0.9079303280804736,
      "eval_sts-test_spearman_dot": 0.8797622731153167,
      "eval_sts-test_spearman_euclidean": 0.9046558335332037,
      "eval_sts-test_spearman_manhattan": 0.905077211410465,
      "eval_sts-test_spearman_max": 0.9079303280804736,
      "step": 10
    },
    {
      "epoch": 0.0582010582010582,
      "grad_norm": 4.20427942276001,
      "learning_rate": 4.052631578947368e-06,
      "loss": 0.2867,
      "step": 11
    },
    {
      "epoch": 0.06349206349206349,
      "grad_norm": 4.593740463256836,
      "learning_rate": 4.421052631578947e-06,
      "loss": 0.3413,
      "step": 12
    },
    {
      "epoch": 0.06878306878306878,
      "grad_norm": 4.476904392242432,
      "learning_rate": 4.789473684210526e-06,
      "loss": 0.4119,
      "step": 13
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 4.580070495605469,
      "learning_rate": 5.157894736842105e-06,
      "loss": 0.3118,
      "step": 14
    },
    {
      "epoch": 0.07936507936507936,
      "grad_norm": 4.245151042938232,
      "learning_rate": 5.526315789473683e-06,
      "loss": 0.327,
      "step": 15
    },
    {
      "epoch": 0.07936507936507936,
      "eval_loss": 0.20313723385334015,
      "eval_runtime": 115.9643,
      "eval_samples_per_second": 26.318,
      "eval_steps_per_second": 0.207,
      "eval_sts-test_pearson_cosine": 0.886401463284574,
      "eval_sts-test_pearson_dot": 0.8764131384801311,
      "eval_sts-test_pearson_euclidean": 0.9089963447148983,
      "eval_sts-test_pearson_manhattan": 0.9096769425767649,
      "eval_sts-test_pearson_max": 0.9096769425767649,
      "eval_sts-test_spearman_cosine": 0.9081527866008503,
      "eval_sts-test_spearman_dot": 0.8798801031865603,
      "eval_sts-test_spearman_euclidean": 0.9051157869977845,
      "eval_sts-test_spearman_manhattan": 0.9058301961346367,
      "eval_sts-test_spearman_max": 0.9081527866008503,
      "step": 15
    },
    {
      "epoch": 0.08465608465608465,
      "grad_norm": 4.45465087890625,
      "learning_rate": 5.894736842105263e-06,
      "loss": 0.3389,
      "step": 16
    },
    {
      "epoch": 0.08994708994708994,
      "grad_norm": 3.7058451175689697,
      "learning_rate": 6.263157894736842e-06,
      "loss": 0.2018,
      "step": 17
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 4.276317119598389,
      "learning_rate": 6.6315789473684205e-06,
      "loss": 0.2861,
      "step": 18
    },
    {
      "epoch": 0.10052910052910052,
      "grad_norm": 4.1567511558532715,
      "learning_rate": 7e-06,
      "loss": 0.2848,
      "step": 19
    },
    {
      "epoch": 0.10582010582010581,
      "grad_norm": 3.727539300918579,
      "learning_rate": 7.368421052631578e-06,
      "loss": 0.2563,
      "step": 20
    },
    {
      "epoch": 0.10582010582010581,
      "eval_loss": 0.19427762925624847,
      "eval_runtime": 115.9622,
      "eval_samples_per_second": 26.319,
      "eval_steps_per_second": 0.207,
      "eval_sts-test_pearson_cosine": 0.8859728422141003,
      "eval_sts-test_pearson_dot": 0.8747321172801832,
      "eval_sts-test_pearson_euclidean": 0.9094621598863318,
      "eval_sts-test_pearson_manhattan": 0.9101781902466943,
      "eval_sts-test_pearson_max": 0.9101781902466943,
      "eval_sts-test_spearman_cosine": 0.9082097102053401,
      "eval_sts-test_spearman_dot": 0.8789482924218687,
      "eval_sts-test_spearman_euclidean": 0.9059236815196834,
      "eval_sts-test_spearman_manhattan": 0.9063636311704222,
      "eval_sts-test_spearman_max": 0.9082097102053401,
      "step": 20
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 4.300179958343506,
      "learning_rate": 7.736842105263158e-06,
      "loss": 0.3058,
      "step": 21
    },
    {
      "epoch": 0.1164021164021164,
      "grad_norm": 4.133388042449951,
      "learning_rate": 8.105263157894736e-06,
      "loss": 0.285,
      "step": 22
    },
    {
      "epoch": 0.12169312169312169,
      "grad_norm": 4.270442962646484,
      "learning_rate": 8.473684210526315e-06,
      "loss": 0.3151,
      "step": 23
    },
    {
      "epoch": 0.12698412698412698,
      "grad_norm": 3.83665132522583,
      "learning_rate": 8.842105263157893e-06,
      "loss": 0.2716,
      "step": 24
    },
    {
      "epoch": 0.13227513227513227,
      "grad_norm": 3.7526190280914307,
      "learning_rate": 9.210526315789472e-06,
      "loss": 0.2422,
      "step": 25
    },
    {
      "epoch": 0.13227513227513227,
      "eval_loss": 0.17938196659088135,
      "eval_runtime": 115.932,
      "eval_samples_per_second": 26.326,
      "eval_steps_per_second": 0.207,
      "eval_sts-test_pearson_cosine": 0.8855121875537549,
      "eval_sts-test_pearson_dot": 0.8729669422265561,
      "eval_sts-test_pearson_euclidean": 0.9099991783491139,
      "eval_sts-test_pearson_manhattan": 0.9106856714841502,
      "eval_sts-test_pearson_max": 0.9106856714841502,
      "eval_sts-test_spearman_cosine": 0.9081626318783566,
      "eval_sts-test_spearman_dot": 0.8777849833819992,
      "eval_sts-test_spearman_euclidean": 0.9059934934874541,
      "eval_sts-test_spearman_manhattan": 0.9070222354843194,
      "eval_sts-test_spearman_max": 0.9081626318783566,
      "step": 25
    },
    {
      "epoch": 0.13756613756613756,
      "grad_norm": 4.082998275756836,
      "learning_rate": 9.578947368421052e-06,
      "loss": 0.2858,
      "step": 26
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 4.099833965301514,
      "learning_rate": 9.94736842105263e-06,
      "loss": 0.3211,
      "step": 27
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 3.2643215656280518,
      "learning_rate": 1.031578947368421e-05,
      "loss": 0.2158,
      "step": 28
    },
    {
      "epoch": 0.15343915343915343,
      "grad_norm": 3.7243423461914062,
      "learning_rate": 1.068421052631579e-05,
      "loss": 0.2811,
      "step": 29
    },
    {
      "epoch": 0.15873015873015872,
      "grad_norm": 3.2406320571899414,
      "learning_rate": 1.1052631578947366e-05,
      "loss": 0.2063,
      "step": 30
    },
    {
      "epoch": 0.15873015873015872,
      "eval_loss": 0.16362369060516357,
      "eval_runtime": 115.8583,
      "eval_samples_per_second": 26.343,
      "eval_steps_per_second": 0.207,
      "eval_sts-test_pearson_cosine": 0.884331218823937,
      "eval_sts-test_pearson_dot": 0.8704189891244698,
      "eval_sts-test_pearson_euclidean": 0.9099375497606286,
      "eval_sts-test_pearson_manhattan": 0.9105955358876667,
      "eval_sts-test_pearson_max": 0.9105955358876667,
      "eval_sts-test_spearman_cosine": 0.907708540829018,
      "eval_sts-test_spearman_dot": 0.8752376073298165,
      "eval_sts-test_spearman_euclidean": 0.9062101343438497,
      "eval_sts-test_spearman_manhattan": 0.9067411975627813,
      "eval_sts-test_spearman_max": 0.907708540829018,
      "step": 30
    },
    {
      "epoch": 0.164021164021164,
      "grad_norm": 3.6572649478912354,
      "learning_rate": 1.1421052631578947e-05,
      "loss": 0.2492,
      "step": 31
    },
    {
      "epoch": 0.1693121693121693,
      "grad_norm": 3.982050657272339,
      "learning_rate": 1.1789473684210525e-05,
      "loss": 0.3096,
      "step": 32
    },
    {
      "epoch": 0.1746031746031746,
      "grad_norm": 3.694265365600586,
      "learning_rate": 1.2157894736842105e-05,
      "loss": 0.2914,
      "step": 33
    },
    {
      "epoch": 0.17989417989417988,
      "grad_norm": 3.955336809158325,
      "learning_rate": 1.2526315789473684e-05,
      "loss": 0.2888,
      "step": 34
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 3.3689701557159424,
      "learning_rate": 1.289473684210526e-05,
      "loss": 0.223,
      "step": 35
    },
    {
      "epoch": 0.18518518518518517,
      "eval_loss": 0.15322057902812958,
      "eval_runtime": 115.8758,
      "eval_samples_per_second": 26.339,
      "eval_steps_per_second": 0.207,
      "eval_sts-test_pearson_cosine": 0.8831736003329786,
      "eval_sts-test_pearson_dot": 0.8675011167098496,
      "eval_sts-test_pearson_euclidean": 0.9098679645586549,
      "eval_sts-test_pearson_manhattan": 0.9104851057704236,
      "eval_sts-test_pearson_max": 0.9104851057704236,
      "eval_sts-test_spearman_cosine": 0.9071846378119088,
      "eval_sts-test_spearman_dot": 0.8722759240996724,
      "eval_sts-test_spearman_euclidean": 0.9062134214414588,
      "eval_sts-test_spearman_manhattan": 0.9068589381315022,
      "eval_sts-test_spearman_max": 0.9071846378119088,
      "step": 35
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 3.665268898010254,
      "learning_rate": 1.3263157894736841e-05,
      "loss": 0.2595,
      "step": 36
    },
    {
      "epoch": 0.19576719576719576,
      "grad_norm": 3.816418409347534,
      "learning_rate": 1.363157894736842e-05,
      "loss": 0.3122,
      "step": 37
    },
    {
      "epoch": 0.20105820105820105,
      "grad_norm": 3.2825276851654053,
      "learning_rate": 1.4e-05,
      "loss": 0.2327,
      "step": 38
    },
    {
      "epoch": 0.20634920634920634,
      "grad_norm": 2.9109766483306885,
      "learning_rate": 1.4368421052631578e-05,
      "loss": 0.1718,
      "step": 39
    },
    {
      "epoch": 0.21164021164021163,
      "grad_norm": 3.6622438430786133,
      "learning_rate": 1.4736842105263155e-05,
      "loss": 0.3162,
      "step": 40
    },
    {
      "epoch": 0.21164021164021163,
      "eval_loss": 0.14427155256271362,
      "eval_runtime": 115.8732,
      "eval_samples_per_second": 26.339,
      "eval_steps_per_second": 0.207,
      "eval_sts-test_pearson_cosine": 0.8815373372232074,
      "eval_sts-test_pearson_dot": 0.8638584960095411,
      "eval_sts-test_pearson_euclidean": 0.909867067075244,
      "eval_sts-test_pearson_manhattan": 0.9104161328856638,
      "eval_sts-test_pearson_max": 0.9104161328856638,
      "eval_sts-test_spearman_cosine": 0.9066622115864256,
      "eval_sts-test_spearman_dot": 0.8693618114603872,
      "eval_sts-test_spearman_euclidean": 0.9060806241933829,
      "eval_sts-test_spearman_manhattan": 0.907040852009058,
      "eval_sts-test_spearman_max": 0.907040852009058,
      "step": 40
    },
    {
      "epoch": 0.21693121693121692,
      "grad_norm": 3.7417047023773193,
      "learning_rate": 1.5105263157894735e-05,
      "loss": 0.296,
      "step": 41
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 3.4067814350128174,
      "learning_rate": 1.5473684210526316e-05,
      "loss": 0.2821,
      "step": 42
    },
    {
      "epoch": 0.2275132275132275,
      "grad_norm": 3.0177342891693115,
      "learning_rate": 1.5842105263157892e-05,
      "loss": 0.2069,
      "step": 43
    },
    {
      "epoch": 0.2328042328042328,
      "grad_norm": 3.4185049533843994,
      "learning_rate": 1.6210526315789473e-05,
      "loss": 0.2573,
      "step": 44
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 3.918159246444702,
      "learning_rate": 1.657894736842105e-05,
      "loss": 0.3119,
      "step": 45
    },
    {
      "epoch": 0.23809523809523808,
      "eval_loss": 0.13426049053668976,
      "eval_runtime": 115.9898,
      "eval_samples_per_second": 26.313,
      "eval_steps_per_second": 0.207,
      "eval_sts-test_pearson_cosine": 0.8805625986040617,
      "eval_sts-test_pearson_dot": 0.8616132264481751,
      "eval_sts-test_pearson_euclidean": 0.9101879546714963,
      "eval_sts-test_pearson_manhattan": 0.9107296923568013,
      "eval_sts-test_pearson_max": 0.9107296923568013,
      "eval_sts-test_spearman_cosine": 0.9064269094540296,
      "eval_sts-test_spearman_dot": 0.8677769455382106,
      "eval_sts-test_spearman_euclidean": 0.9069313904236947,
      "eval_sts-test_spearman_manhattan": 0.9076995905767397,
      "eval_sts-test_spearman_max": 0.9076995905767397,
      "step": 45
    },
    {
      "epoch": 0.24338624338624337,
      "grad_norm": 3.0733871459960938,
      "learning_rate": 1.694736842105263e-05,
      "loss": 0.2743,
      "step": 46
    },
    {
      "epoch": 0.24867724867724866,
      "grad_norm": 3.3528106212615967,
      "learning_rate": 1.731578947368421e-05,
      "loss": 0.2666,
      "step": 47
    },
    {
      "epoch": 0.25396825396825395,
      "grad_norm": 3.0437304973602295,
      "learning_rate": 1.7684210526315787e-05,
      "loss": 0.2414,
      "step": 48
    },
    {
      "epoch": 0.25925925925925924,
      "grad_norm": 3.451265573501587,
      "learning_rate": 1.8052631578947367e-05,
      "loss": 0.2793,
      "step": 49
    },
    {
      "epoch": 0.26455026455026454,
      "grad_norm": 2.9664905071258545,
      "learning_rate": 1.8421052631578944e-05,
      "loss": 0.2212,
      "step": 50
    },
    {
      "epoch": 0.26455026455026454,
      "eval_loss": 0.12510398030281067,
      "eval_runtime": 116.2617,
      "eval_samples_per_second": 26.251,
      "eval_steps_per_second": 0.206,
      "eval_sts-test_pearson_cosine": 0.8803749979605222,
      "eval_sts-test_pearson_dot": 0.8597944232348109,
      "eval_sts-test_pearson_euclidean": 0.9105906609339514,
      "eval_sts-test_pearson_manhattan": 0.9111264139452835,
      "eval_sts-test_pearson_max": 0.9111264139452835,
      "eval_sts-test_spearman_cosine": 0.9067783858609977,
      "eval_sts-test_spearman_dot": 0.8664887804790594,
      "eval_sts-test_spearman_euclidean": 0.9077306479521453,
      "eval_sts-test_spearman_manhattan": 0.9082951851145977,
      "eval_sts-test_spearman_max": 0.9082951851145977,
      "step": 50
    },
    {
      "epoch": 0.2698412698412698,
      "grad_norm": 3.051281690597534,
      "learning_rate": 1.8789473684210524e-05,
      "loss": 0.2071,
      "step": 51
    },
    {
      "epoch": 0.2751322751322751,
      "grad_norm": 3.539724826812744,
      "learning_rate": 1.9157894736842104e-05,
      "loss": 0.296,
      "step": 52
    },
    {
      "epoch": 0.2804232804232804,
      "grad_norm": 3.101149559020996,
      "learning_rate": 1.952631578947368e-05,
      "loss": 0.2061,
      "step": 53
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 3.113757848739624,
      "learning_rate": 1.989473684210526e-05,
      "loss": 0.2164,
      "step": 54
    },
    {
      "epoch": 0.291005291005291,
      "grad_norm": 2.9952962398529053,
      "learning_rate": 2.0263157894736842e-05,
      "loss": 0.188,
      "step": 55
    },
    {
      "epoch": 0.291005291005291,
      "eval_loss": 0.11972539871931076,
      "eval_runtime": 115.8621,
      "eval_samples_per_second": 26.342,
      "eval_steps_per_second": 0.207,
      "eval_sts-test_pearson_cosine": 0.881021505301097,
      "eval_sts-test_pearson_dot": 0.8597228411065384,
      "eval_sts-test_pearson_euclidean": 0.9108125110302233,
      "eval_sts-test_pearson_manhattan": 0.9112746469255748,
      "eval_sts-test_pearson_max": 0.9112746469255748,
      "eval_sts-test_spearman_cosine": 0.9072042388643983,
      "eval_sts-test_spearman_dot": 0.8659804956521757,
      "eval_sts-test_spearman_euclidean": 0.9079662185921096,
      "eval_sts-test_spearman_manhattan": 0.9082669470686597,
      "eval_sts-test_spearman_max": 0.9082669470686597,
      "step": 55
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 3.065542697906494,
      "learning_rate": 2.063157894736842e-05,
      "loss": 0.2411,
      "step": 56
    },
    {
      "epoch": 0.30158730158730157,
      "grad_norm": 2.8689684867858887,
      "learning_rate": 2.1e-05,
      "loss": 0.2031,
      "step": 57
    },
    {
      "epoch": 0.30687830687830686,
      "grad_norm": 2.9906833171844482,
      "learning_rate": 2.136842105263158e-05,
      "loss": 0.2438,
      "step": 58
    },
    {
      "epoch": 0.31216931216931215,
      "grad_norm": 3.040048837661743,
      "learning_rate": 2.1736842105263156e-05,
      "loss": 0.2417,
      "step": 59
    },
    {
      "epoch": 0.31746031746031744,
      "grad_norm": 2.7314910888671875,
      "learning_rate": 2.2105263157894733e-05,
      "loss": 0.1515,
      "step": 60
    },
    {
      "epoch": 0.31746031746031744,
      "eval_loss": 0.12329312413930893,
      "eval_runtime": 115.9779,
      "eval_samples_per_second": 26.315,
      "eval_steps_per_second": 0.207,
      "eval_sts-test_pearson_cosine": 0.8813346129633393,
      "eval_sts-test_pearson_dot": 0.8610768249798144,
      "eval_sts-test_pearson_euclidean": 0.9107487658386748,
      "eval_sts-test_pearson_manhattan": 0.9112378269812353,
      "eval_sts-test_pearson_max": 0.9112378269812353,
      "eval_sts-test_spearman_cosine": 0.9065531975136762,
      "eval_sts-test_spearman_dot": 0.867737743433232,
      "eval_sts-test_spearman_euclidean": 0.9073249330163708,
      "eval_sts-test_spearman_manhattan": 0.9077088988391091,
      "eval_sts-test_spearman_max": 0.9077088988391091,
      "step": 60
    },
    {
      "epoch": 0.32275132275132273,
      "grad_norm": 3.0552306175231934,
      "learning_rate": 2.2473684210526313e-05,
      "loss": 0.21,
      "step": 61
    },
    {
      "epoch": 0.328042328042328,
      "grad_norm": 3.1015548706054688,
      "learning_rate": 2.2842105263157893e-05,
      "loss": 0.21,
      "step": 62
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 3.154890537261963,
      "learning_rate": 2.321052631578947e-05,
      "loss": 0.2157,
      "step": 63
    },
    {
      "epoch": 0.3386243386243386,
      "grad_norm": 3.384970188140869,
      "learning_rate": 2.357894736842105e-05,
      "loss": 0.2138,
      "step": 64
    },
    {
      "epoch": 0.3439153439153439,
      "grad_norm": 3.58601713180542,
      "learning_rate": 2.394736842105263e-05,
      "loss": 0.2403,
      "step": 65
    },
    {
      "epoch": 0.3439153439153439,
      "eval_loss": 0.12730959057807922,
      "eval_runtime": 115.9959,
      "eval_samples_per_second": 26.311,
      "eval_steps_per_second": 0.207,
      "eval_sts-test_pearson_cosine": 0.8797954361206015,
      "eval_sts-test_pearson_dot": 0.8587071220533238,
      "eval_sts-test_pearson_euclidean": 0.9093975785151563,
      "eval_sts-test_pearson_manhattan": 0.9102944590146977,
      "eval_sts-test_pearson_max": 0.9102944590146977,
      "eval_sts-test_spearman_cosine": 0.9058099238132263,
      "eval_sts-test_spearman_dot": 0.8649206962799048,
      "eval_sts-test_spearman_euclidean": 0.906062455181258,
      "eval_sts-test_spearman_manhattan": 0.9070602293052407,
      "eval_sts-test_spearman_max": 0.9070602293052407,
      "step": 65
    },
    {
      "epoch": 0.3492063492063492,
      "grad_norm": 3.397090435028076,
      "learning_rate": 2.431578947368421e-05,
      "loss": 0.2808,
      "step": 66
    },
    {
      "epoch": 0.3544973544973545,
      "grad_norm": 2.786862373352051,
      "learning_rate": 2.4684210526315788e-05,
      "loss": 0.1891,
      "step": 67
    },
    {
      "epoch": 0.35978835978835977,
      "grad_norm": 3.0845346450805664,
      "learning_rate": 2.5052631578947368e-05,
      "loss": 0.1991,
      "step": 68
    },
    {
      "epoch": 0.36507936507936506,
      "grad_norm": 3.1166787147521973,
      "learning_rate": 2.5421052631578948e-05,
      "loss": 0.2121,
      "step": 69
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 3.181523323059082,
      "learning_rate": 2.578947368421052e-05,
      "loss": 0.2039,
      "step": 70
    },
    {
      "epoch": 0.37037037037037035,
      "eval_loss": 0.13109122216701508,
      "eval_runtime": 115.9695,
      "eval_samples_per_second": 26.317,
      "eval_steps_per_second": 0.207,
      "eval_sts-test_pearson_cosine": 0.8802169762825238,
      "eval_sts-test_pearson_dot": 0.8598037708245074,
      "eval_sts-test_pearson_euclidean": 0.9094245832802006,
      "eval_sts-test_pearson_manhattan": 0.9105289688155764,
      "eval_sts-test_pearson_max": 0.9105289688155764,
      "eval_sts-test_spearman_cosine": 0.906595934968305,
      "eval_sts-test_spearman_dot": 0.8654662141562657,
      "eval_sts-test_spearman_euclidean": 0.906532611933436,
      "eval_sts-test_spearman_manhattan": 0.9073325407308075,
      "eval_sts-test_spearman_max": 0.9073325407308075,
      "step": 70
    },
    {
      "epoch": 0.37566137566137564,
      "grad_norm": 3.032498598098755,
      "learning_rate": 2.6157894736842102e-05,
      "loss": 0.1986,
      "step": 71
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 3.486334800720215,
      "learning_rate": 2.6526315789473682e-05,
      "loss": 0.2925,
      "step": 72
    },
    {
      "epoch": 0.3862433862433862,
      "grad_norm": 3.424903631210327,
      "learning_rate": 2.689473684210526e-05,
      "loss": 0.2527,
      "step": 73
    },
    {
      "epoch": 0.3915343915343915,
      "grad_norm": 3.587599992752075,
      "learning_rate": 2.726315789473684e-05,
      "loss": 0.279,
      "step": 74
    },
    {
      "epoch": 0.3968253968253968,
      "grad_norm": 3.3220415115356445,
      "learning_rate": 2.763157894736842e-05,
      "loss": 0.2419,
      "step": 75
    },
    {
      "epoch": 0.3968253968253968,
      "eval_loss": 0.13154849410057068,
      "eval_runtime": 115.989,
      "eval_samples_per_second": 26.313,
      "eval_steps_per_second": 0.207,
      "eval_sts-test_pearson_cosine": 0.879906095889138,
      "eval_sts-test_pearson_dot": 0.8607649105164801,
      "eval_sts-test_pearson_euclidean": 0.9088378228597751,
      "eval_sts-test_pearson_manhattan": 0.9102620649137054,
      "eval_sts-test_pearson_max": 0.9102620649137054,
      "eval_sts-test_spearman_cosine": 0.9066359425959888,
      "eval_sts-test_spearman_dot": 0.8668292928269864,
      "eval_sts-test_spearman_euclidean": 0.9061907122964057,
      "eval_sts-test_spearman_manhattan": 0.9072107277972998,
      "eval_sts-test_spearman_max": 0.9072107277972998,
      "step": 75
    },
    {
      "epoch": 0.4021164021164021,
      "grad_norm": 2.994913101196289,
      "learning_rate": 2.8e-05,
      "loss": 0.2228,
      "step": 76
    },
    {
      "epoch": 0.4074074074074074,
      "grad_norm": 3.613633632659912,
      "learning_rate": 2.8368421052631576e-05,
      "loss": 0.2242,
      "step": 77
    },
    {
      "epoch": 0.4126984126984127,
      "grad_norm": 3.4389431476593018,
      "learning_rate": 2.8736842105263157e-05,
      "loss": 0.2737,
      "step": 78
    },
    {
      "epoch": 0.41798941798941797,
      "grad_norm": 3.348423957824707,
      "learning_rate": 2.9105263157894737e-05,
      "loss": 0.2328,
      "step": 79
    },
    {
      "epoch": 0.42328042328042326,
      "grad_norm": 3.3796963691711426,
      "learning_rate": 2.947368421052631e-05,
      "loss": 0.2802,
      "step": 80
    },
    {
      "epoch": 0.42328042328042326,
      "eval_loss": 0.12620440125465393,
      "eval_runtime": 115.88,
      "eval_samples_per_second": 26.338,
      "eval_steps_per_second": 0.207,
      "eval_sts-test_pearson_cosine": 0.8786083890603608,
      "eval_sts-test_pearson_dot": 0.8607044568869332,
      "eval_sts-test_pearson_euclidean": 0.9083064997932102,
      "eval_sts-test_pearson_manhattan": 0.909785902193573,
      "eval_sts-test_pearson_max": 0.909785902193573,
      "eval_sts-test_spearman_cosine": 0.9058450088021573,
      "eval_sts-test_spearman_dot": 0.8683225529170947,
      "eval_sts-test_spearman_euclidean": 0.9058583894293133,
      "eval_sts-test_spearman_manhattan": 0.9067757007853141,
      "eval_sts-test_spearman_max": 0.9067757007853141,
      "step": 80
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 2.940751314163208,
      "learning_rate": 2.984210526315789e-05,
      "loss": 0.2044,
      "step": 81
    },
    {
      "epoch": 0.43386243386243384,
      "grad_norm": 2.742959499359131,
      "learning_rate": 3.021052631578947e-05,
      "loss": 0.1828,
      "step": 82
    },
    {
      "epoch": 0.43915343915343913,
      "grad_norm": 3.1117758750915527,
      "learning_rate": 3.0578947368421054e-05,
      "loss": 0.2372,
      "step": 83
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 3.11297869682312,
      "learning_rate": 3.094736842105263e-05,
      "loss": 0.2241,
      "step": 84
    },
    {
      "epoch": 0.4497354497354497,
      "grad_norm": 3.2359349727630615,
      "learning_rate": 3.131578947368421e-05,
      "loss": 0.2782,
      "step": 85
    },
    {
      "epoch": 0.4497354497354497,
      "eval_loss": 0.12065601348876953,
      "eval_runtime": 115.9874,
      "eval_samples_per_second": 26.313,
      "eval_steps_per_second": 0.207,
      "eval_sts-test_pearson_cosine": 0.8792266747813421,
      "eval_sts-test_pearson_dot": 0.8635914020857025,
      "eval_sts-test_pearson_euclidean": 0.909050966414346,
      "eval_sts-test_pearson_manhattan": 0.9104391562008682,
      "eval_sts-test_pearson_max": 0.9104391562008682,
      "eval_sts-test_spearman_cosine": 0.9062812888494619,
      "eval_sts-test_spearman_dot": 0.8713958905444104,
      "eval_sts-test_spearman_euclidean": 0.9064880396770901,
      "eval_sts-test_spearman_manhattan": 0.9073885693100694,
      "eval_sts-test_spearman_max": 0.9073885693100694,
      "step": 85
    },
    {
      "epoch": 0.455026455026455,
      "grad_norm": 3.3813822269439697,
      "learning_rate": 3.1684210526315785e-05,
      "loss": 0.3244,
      "step": 86
    },
    {
      "epoch": 0.4603174603174603,
      "grad_norm": 2.657428503036499,
      "learning_rate": 3.205263157894736e-05,
      "loss": 0.2102,
      "step": 87
    },
    {
      "epoch": 0.4656084656084656,
      "grad_norm": 2.7600059509277344,
      "learning_rate": 3.2421052631578945e-05,
      "loss": 0.2265,
      "step": 88
    },
    {
      "epoch": 0.4708994708994709,
      "grad_norm": 3.10657000541687,
      "learning_rate": 3.278947368421052e-05,
      "loss": 0.2666,
      "step": 89
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 3.0764777660369873,
      "learning_rate": 3.31578947368421e-05,
      "loss": 0.23,
      "step": 90
    },
    {
      "epoch": 0.47619047619047616,
      "eval_loss": 0.11863212287425995,
      "eval_runtime": 115.9856,
      "eval_samples_per_second": 26.314,
      "eval_steps_per_second": 0.207,
      "eval_sts-test_pearson_cosine": 0.8796178782254354,
      "eval_sts-test_pearson_dot": 0.8632853604720685,
      "eval_sts-test_pearson_euclidean": 0.9106195949839817,
      "eval_sts-test_pearson_manhattan": 0.9115246839048733,
      "eval_sts-test_pearson_max": 0.9115246839048733,
      "eval_sts-test_spearman_cosine": 0.9078120057453548,
      "eval_sts-test_spearman_dot": 0.8720862682538955,
      "eval_sts-test_spearman_euclidean": 0.9083378778179652,
      "eval_sts-test_spearman_manhattan": 0.9089643954774449,
      "eval_sts-test_spearman_max": 0.9089643954774449,
      "step": 90
    },
    {
      "epoch": 0.48148148148148145,
      "grad_norm": 3.020212411880493,
      "learning_rate": 3.352631578947368e-05,
      "loss": 0.2358,
      "step": 91
    },
    {
      "epoch": 0.48677248677248675,
      "grad_norm": 3.419471502304077,
      "learning_rate": 3.389473684210526e-05,
      "loss": 0.2896,
      "step": 92
    },
    {
      "epoch": 0.49206349206349204,
      "grad_norm": 3.062520980834961,
      "learning_rate": 3.426315789473684e-05,
      "loss": 0.2126,
      "step": 93
    },
    {
      "epoch": 0.4973544973544973,
      "grad_norm": 3.3430864810943604,
      "learning_rate": 3.463157894736842e-05,
      "loss": 0.2669,
      "step": 94
    },
    {
      "epoch": 0.5026455026455027,
      "grad_norm": 3.1061036586761475,
      "learning_rate": 3.5e-05,
      "loss": 0.2375,
      "step": 95
    },
    {
      "epoch": 0.5026455026455027,
      "eval_loss": 0.11278577148914337,
      "eval_runtime": 115.9371,
      "eval_samples_per_second": 26.325,
      "eval_steps_per_second": 0.207,
      "eval_sts-test_pearson_cosine": 0.8790475705877597,
      "eval_sts-test_pearson_dot": 0.8631845510913274,
      "eval_sts-test_pearson_euclidean": 0.9107267591418424,
      "eval_sts-test_pearson_manhattan": 0.911801845501315,
      "eval_sts-test_pearson_max": 0.911801845501315,
      "eval_sts-test_spearman_cosine": 0.9087454723067182,
      "eval_sts-test_spearman_dot": 0.8721337493422319,
      "eval_sts-test_spearman_euclidean": 0.9085557269584185,
      "eval_sts-test_spearman_manhattan": 0.9095949855017109,
      "eval_sts-test_spearman_max": 0.9095949855017109,
      "step": 95
    },
    {
      "epoch": 0.5079365079365079,
      "grad_norm": 2.760911703109741,
      "learning_rate": 3.4999101435573165e-05,
      "loss": 0.1903,
      "step": 96
    },
    {
      "epoch": 0.5132275132275133,
      "grad_norm": 2.9554224014282227,
      "learning_rate": 3.499640585302429e-05,
      "loss": 0.2507,
      "step": 97
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 2.9563987255096436,
      "learning_rate": 3.4991913584534566e-05,
      "loss": 0.1897,
      "step": 98
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 3.0752642154693604,
      "learning_rate": 3.4985625183693854e-05,
      "loss": 0.2775,
      "step": 99
    },
    {
      "epoch": 0.5291005291005291,
      "grad_norm": 2.8446006774902344,
      "learning_rate": 3.4977541425432415e-05,
      "loss": 0.2098,
      "step": 100
    },
    {
      "epoch": 0.5291005291005291,
      "eval_loss": 0.11681391298770905,
      "eval_runtime": 115.9468,
      "eval_samples_per_second": 26.322,
      "eval_steps_per_second": 0.207,
      "eval_sts-test_pearson_cosine": 0.8772591964347106,
      "eval_sts-test_pearson_dot": 0.8585096145266702,
      "eval_sts-test_pearson_euclidean": 0.9091316759212603,
      "eval_sts-test_pearson_manhattan": 0.9099210072486108,
      "eval_sts-test_pearson_max": 0.9099210072486108,
      "eval_sts-test_spearman_cosine": 0.9064237321144708,
      "eval_sts-test_spearman_dot": 0.8648877146002593,
      "eval_sts-test_spearman_euclidean": 0.9063920482214057,
      "eval_sts-test_spearman_manhattan": 0.9075959914066186,
      "eval_sts-test_spearman_max": 0.9075959914066186,
      "step": 100
    },
    {
      "epoch": 0.5343915343915344,
      "grad_norm": 2.7542779445648193,
      "learning_rate": 3.496766330592549e-05,
      "loss": 0.1628,
      "step": 101
    },
    {
      "epoch": 0.5396825396825397,
      "grad_norm": 2.7565367221832275,
      "learning_rate": 3.4955992042470456e-05,
      "loss": 0.2158,
      "step": 102
    },
    {
      "epoch": 0.544973544973545,
      "grad_norm": 2.4343347549438477,
      "learning_rate": 3.494252907333686e-05,
      "loss": 0.1552,
      "step": 103
    },
    {
      "epoch": 0.5502645502645502,
      "grad_norm": 3.1311893463134766,
      "learning_rate": 3.492727605758918e-05,
      "loss": 0.2364,
      "step": 104
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 3.080811023712158,
      "learning_rate": 3.491023487488238e-05,
      "loss": 0.272,
      "step": 105
    },
    {
      "epoch": 0.5555555555555556,
      "eval_loss": 0.1177554726600647,
      "eval_runtime": 115.9887,
      "eval_samples_per_second": 26.313,
      "eval_steps_per_second": 0.207,
      "eval_sts-test_pearson_cosine": 0.8775298085625183,
      "eval_sts-test_pearson_dot": 0.8593352032357447,
      "eval_sts-test_pearson_euclidean": 0.9089120653468052,
      "eval_sts-test_pearson_manhattan": 0.908955609090125,
      "eval_sts-test_pearson_max": 0.908955609090125,
      "eval_sts-test_spearman_cosine": 0.9056424645930997,
      "eval_sts-test_spearman_dot": 0.8631139983550111,
      "eval_sts-test_spearman_euclidean": 0.9054400993890878,
      "eval_sts-test_spearman_manhattan": 0.9059316024929496,
      "eval_sts-test_spearman_max": 0.9059316024929496,
      "step": 105
    },
    {
      "epoch": 0.5608465608465608,
      "grad_norm": 2.8664119243621826,
      "learning_rate": 3.489140762523023e-05,
      "loss": 0.2271,
      "step": 106
    },
    {
      "epoch": 0.5661375661375662,
      "grad_norm": 2.7945520877838135,
      "learning_rate": 3.4870796628746594e-05,
      "loss": 0.2132,
      "step": 107
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 2.8966565132141113,
      "learning_rate": 3.4848404425359456e-05,
      "loss": 0.1782,
      "step": 108
    },
    {
      "epoch": 0.5767195767195767,
      "grad_norm": 2.6960151195526123,
      "learning_rate": 3.4824233774497946e-05,
      "loss": 0.1598,
      "step": 109
    },
    {
      "epoch": 0.582010582010582,
      "grad_norm": 3.1113312244415283,
      "learning_rate": 3.4798287654752294e-05,
      "loss": 0.2472,
      "step": 110
    },
    {
      "epoch": 0.582010582010582,
      "eval_loss": 0.12694795429706573,
      "eval_runtime": 115.9427,
      "eval_samples_per_second": 26.323,
      "eval_steps_per_second": 0.207,
      "eval_sts-test_pearson_cosine": 0.8781162735100789,
      "eval_sts-test_pearson_dot": 0.8634318341628767,
      "eval_sts-test_pearson_euclidean": 0.9086688422059872,
      "eval_sts-test_pearson_manhattan": 0.9085119625190576,
      "eval_sts-test_pearson_max": 0.9086688422059872,
      "eval_sts-test_spearman_cosine": 0.9050255684548193,
      "eval_sts-test_spearman_dot": 0.8664220563483247,
      "eval_sts-test_spearman_euclidean": 0.9042466279990407,
      "eval_sts-test_spearman_manhattan": 0.9047099825594873,
      "eval_sts-test_spearman_max": 0.9050255684548193,
      "step": 110
    },
    {
      "epoch": 0.5873015873015873,
      "grad_norm": 3.0204665660858154,
      "learning_rate": 3.477056926350673e-05,
      "loss": 0.2041,
      "step": 111
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 3.3232171535491943,
      "learning_rate": 3.474108201654556e-05,
      "loss": 0.2426,
      "step": 112
    },
    {
      "epoch": 0.5978835978835979,
      "grad_norm": 3.1148412227630615,
      "learning_rate": 3.4709829547632134e-05,
      "loss": 0.2105,
      "step": 113
    },
    {
      "epoch": 0.6031746031746031,
      "grad_norm": 2.886481523513794,
      "learning_rate": 3.467681570806109e-05,
      "loss": 0.1923,
      "step": 114
    },
    {
      "epoch": 0.6084656084656085,
      "grad_norm": 3.2116329669952393,
      "learning_rate": 3.464204456618378e-05,
      "loss": 0.2271,
      "step": 115
    },
    {
      "epoch": 0.6084656084656085,
      "eval_loss": 0.12330599874258041,
      "eval_runtime": 115.9423,
      "eval_samples_per_second": 26.323,
      "eval_steps_per_second": 0.207,
      "eval_sts-test_pearson_cosine": 0.8798272374408064,
      "eval_sts-test_pearson_dot": 0.867285673702976,
      "eval_sts-test_pearson_euclidean": 0.909363327246087,
      "eval_sts-test_pearson_manhattan": 0.9091246101967716,
      "eval_sts-test_pearson_max": 0.909363327246087,
      "eval_sts-test_spearman_cosine": 0.9060899772070137,
      "eval_sts-test_spearman_dot": 0.8704560245526682,
      "eval_sts-test_spearman_euclidean": 0.9054406364042247,
      "eval_sts-test_spearman_manhattan": 0.9051852857067252,
      "eval_sts-test_spearman_max": 0.9060899772070137,
      "step": 115
    },
    {
      "epoch": 0.6137566137566137,
      "grad_norm": 3.385223627090454,
      "learning_rate": 3.460552040690687e-05,
      "loss": 0.3029,
      "step": 116
    },
    {
      "epoch": 0.6190476190476191,
      "grad_norm": 3.150688409805298,
      "learning_rate": 3.456724773116434e-05,
      "loss": 0.2554,
      "step": 117
    },
    {
      "epoch": 0.6243386243386243,
      "grad_norm": 3.0149803161621094,
      "learning_rate": 3.452723125536281e-05,
      "loss": 0.2182,
      "step": 118
    },
    {
      "epoch": 0.6296296296296297,
      "grad_norm": 3.19419002532959,
      "learning_rate": 3.448547591080033e-05,
      "loss": 0.2852,
      "step": 119
    },
    {
      "epoch": 0.6349206349206349,
      "grad_norm": 2.99879789352417,
      "learning_rate": 3.444198684305871e-05,
      "loss": 0.2285,
      "step": 120
    },
    {
      "epoch": 0.6349206349206349,
      "eval_loss": 0.12802907824516296,
      "eval_runtime": 115.8977,
      "eval_samples_per_second": 26.334,
      "eval_steps_per_second": 0.207,
      "eval_sts-test_pearson_cosine": 0.8798175425010222,
      "eval_sts-test_pearson_dot": 0.863763595764963,
      "eval_sts-test_pearson_euclidean": 0.9094261191010624,
      "eval_sts-test_pearson_manhattan": 0.9090772657963855,
      "eval_sts-test_pearson_max": 0.9094261191010624,
      "eval_sts-test_spearman_cosine": 0.9053311300675998,
      "eval_sts-test_spearman_dot": 0.8654653191310379,
      "eval_sts-test_spearman_euclidean": 0.9053121555327698,
      "eval_sts-test_spearman_manhattan": 0.9052343330892101,
      "eval_sts-test_spearman_max": 0.9053311300675998,
      "step": 120
    },
    {
      "epoch": 0.6402116402116402,
      "grad_norm": 3.01249361038208,
      "learning_rate": 3.439676941136937e-05,
      "loss": 0.218,
      "step": 121
    },
    {
      "epoch": 0.6455026455026455,
      "grad_norm": 2.7809016704559326,
      "learning_rate": 3.4349829187952966e-05,
      "loss": 0.1841,
      "step": 122
    },
    {
      "epoch": 0.6507936507936508,
      "grad_norm": 3.183194398880005,
      "learning_rate": 3.4301171957332694e-05,
      "loss": 0.2629,
      "step": 123
    },
    {
      "epoch": 0.656084656084656,
      "grad_norm": 3.006030797958374,
      "learning_rate": 3.425080371562145e-05,
      "loss": 0.1749,
      "step": 124
    },
    {
      "epoch": 0.6613756613756614,
      "grad_norm": 2.9949681758880615,
      "learning_rate": 3.4198730669782925e-05,
      "loss": 0.2417,
      "step": 125
    },
    {
      "epoch": 0.6613756613756614,
      "eval_loss": 0.14149585366249084,
      "eval_runtime": 115.9037,
      "eval_samples_per_second": 26.332,
      "eval_steps_per_second": 0.207,
      "eval_sts-test_pearson_cosine": 0.8801193496474387,
      "eval_sts-test_pearson_dot": 0.8614489114996757,
      "eval_sts-test_pearson_euclidean": 0.9096775446763254,
      "eval_sts-test_pearson_manhattan": 0.909541166275706,
      "eval_sts-test_pearson_max": 0.9096775446763254,
      "eval_sts-test_spearman_cosine": 0.9056506540739345,
      "eval_sts-test_spearman_dot": 0.8627393855459037,
      "eval_sts-test_spearman_euclidean": 0.905229410450457,
      "eval_sts-test_spearman_manhattan": 0.9051265720517796,
      "eval_sts-test_spearman_max": 0.9056506540739345,
      "step": 125
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 2.9404184818267822,
      "learning_rate": 3.414495923686671e-05,
      "loss": 0.2305,
      "step": 126
    },
    {
      "epoch": 0.671957671957672,
      "grad_norm": 3.515538215637207,
      "learning_rate": 3.408949604321751e-05,
      "loss": 0.2841,
      "step": 127
    },
    {
      "epoch": 0.6772486772486772,
      "grad_norm": 2.7193102836608887,
      "learning_rate": 3.4032347923658554e-05,
      "loss": 0.1785,
      "step": 128
    },
    {
      "epoch": 0.6825396825396826,
      "grad_norm": 2.949784755706787,
      "learning_rate": 3.397352192064938e-05,
      "loss": 0.2153,
      "step": 129
    },
    {
      "epoch": 0.6878306878306878,
      "grad_norm": 3.263798475265503,
      "learning_rate": 3.39130252834179e-05,
      "loss": 0.2548,
      "step": 130
    },
    {
      "epoch": 0.6878306878306878,
      "eval_loss": 0.1412901133298874,
      "eval_runtime": 115.8261,
      "eval_samples_per_second": 26.35,
      "eval_steps_per_second": 0.207,
      "eval_sts-test_pearson_cosine": 0.8817491042172992,
      "eval_sts-test_pearson_dot": 0.8653158778803413,
      "eval_sts-test_pearson_euclidean": 0.9109017540975314,
      "eval_sts-test_pearson_manhattan": 0.9110420593534589,
      "eval_sts-test_pearson_max": 0.9110420593534589,
      "eval_sts-test_spearman_cosine": 0.9079463490320518,
      "eval_sts-test_spearman_dot": 0.8671617499478633,
      "eval_sts-test_spearman_euclidean": 0.9076926541312239,
      "eval_sts-test_spearman_manhattan": 0.9074005626481224,
      "eval_sts-test_spearman_max": 0.9079463490320518,
      "step": 130
    },
    {
      "epoch": 0.6931216931216931,
      "grad_norm": 2.7200613021850586,
      "learning_rate": 3.385086546706714e-05,
      "loss": 0.2059,
      "step": 131
    },
    {
      "epoch": 0.6984126984126984,
      "grad_norm": 2.916797399520874,
      "learning_rate": 3.3787050131656496e-05,
      "loss": 0.2073,
      "step": 132
    },
    {
      "epoch": 0.7037037037037037,
      "grad_norm": 3.0047614574432373,
      "learning_rate": 3.372158714125777e-05,
      "loss": 0.191,
      "step": 133
    },
    {
      "epoch": 0.708994708994709,
      "grad_norm": 2.702082633972168,
      "learning_rate": 3.36544845629861e-05,
      "loss": 0.1633,
      "step": 134
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 3.3000283241271973,
      "learning_rate": 3.358575066600578e-05,
      "loss": 0.2627,
      "step": 135
    },
    {
      "epoch": 0.7142857142857143,
      "eval_loss": 0.13328148424625397,
      "eval_runtime": 115.7947,
      "eval_samples_per_second": 26.357,
      "eval_steps_per_second": 0.207,
      "eval_sts-test_pearson_cosine": 0.8814270028194036,
      "eval_sts-test_pearson_dot": 0.8654755263554079,
      "eval_sts-test_pearson_euclidean": 0.9100944689124159,
      "eval_sts-test_pearson_manhattan": 0.9103746959208892,
      "eval_sts-test_pearson_max": 0.9103746959208892,
      "eval_sts-test_spearman_cosine": 0.9076914905984277,
      "eval_sts-test_spearman_dot": 0.8685219197865933,
      "eval_sts-test_spearman_euclidean": 0.9077337805404427,
      "eval_sts-test_spearman_manhattan": 0.9075425136492559,
      "eval_sts-test_spearman_max": 0.9077337805404427,
      "step": 135
    },
    {
      "epoch": 0.7195767195767195,
      "grad_norm": 3.1306369304656982,
      "learning_rate": 3.351539392051131e-05,
      "loss": 0.2451,
      "step": 136
    },
    {
      "epoch": 0.7248677248677249,
      "grad_norm": 2.528568983078003,
      "learning_rate": 3.344342299668353e-05,
      "loss": 0.1441,
      "step": 137
    },
    {
      "epoch": 0.7301587301587301,
      "grad_norm": 2.893615484237671,
      "learning_rate": 3.33698467636212e-05,
      "loss": 0.2138,
      "step": 138
    },
    {
      "epoch": 0.7354497354497355,
      "grad_norm": 3.235039472579956,
      "learning_rate": 3.32946742882481e-05,
      "loss": 0.2564,
      "step": 139
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 2.8678057193756104,
      "learning_rate": 3.321791483419561e-05,
      "loss": 0.1524,
      "step": 140
    },
    {
      "epoch": 0.7407407407407407,
      "eval_loss": 0.13225606083869934,
      "eval_runtime": 115.8232,
      "eval_samples_per_second": 26.351,
      "eval_steps_per_second": 0.207,
      "eval_sts-test_pearson_cosine": 0.8781919392624582,
      "eval_sts-test_pearson_dot": 0.8608413217193998,
      "eval_sts-test_pearson_euclidean": 0.9068541902117857,
      "eval_sts-test_pearson_manhattan": 0.9075012201786494,
      "eval_sts-test_pearson_max": 0.9075012201786494,
      "eval_sts-test_spearman_cosine": 0.9049418835960173,
      "eval_sts-test_spearman_dot": 0.8634087749137961,
      "eval_sts-test_spearman_euclidean": 0.9045396592586316,
      "eval_sts-test_spearman_manhattan": 0.9048969533295804,
      "eval_sts-test_spearman_max": 0.9049418835960173,
      "step": 140
    },
    {
      "epoch": 0.746031746031746,
      "grad_norm": 2.5006282329559326,
      "learning_rate": 3.313957786066119e-05,
      "loss": 0.1786,
      "step": 141
    },
    {
      "epoch": 0.7513227513227513,
      "grad_norm": 3.081282377243042,
      "learning_rate": 3.3059673021242716e-05,
      "loss": 0.2104,
      "step": 142
    },
    {
      "epoch": 0.7566137566137566,
      "grad_norm": 3.044879198074341,
      "learning_rate": 3.297821016274879e-05,
      "loss": 0.2512,
      "step": 143
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 2.87981915473938,
      "learning_rate": 3.2895199323985386e-05,
      "loss": 0.1889,
      "step": 144
    },
    {
      "epoch": 0.7671957671957672,
      "grad_norm": 2.799271821975708,
      "learning_rate": 3.281065073451867e-05,
      "loss": 0.2127,
      "step": 145
    },
    {
      "epoch": 0.7671957671957672,
      "eval_loss": 0.12909488379955292,
      "eval_runtime": 115.7825,
      "eval_samples_per_second": 26.36,
      "eval_steps_per_second": 0.207,
      "eval_sts-test_pearson_cosine": 0.8735553111785674,
      "eval_sts-test_pearson_dot": 0.8567353468688738,
      "eval_sts-test_pearson_euclidean": 0.9031851032382168,
      "eval_sts-test_pearson_manhattan": 0.9046152117713773,
      "eval_sts-test_pearson_max": 0.9046152117713773,
      "eval_sts-test_spearman_cosine": 0.9015403849689184,
      "eval_sts-test_spearman_dot": 0.8596978213141758,
      "eval_sts-test_spearman_euclidean": 0.9003828040905072,
      "eval_sts-test_spearman_manhattan": 0.9019434148290095,
      "eval_sts-test_spearman_max": 0.9019434148290095,
      "step": 145
    },
    {
      "epoch": 0.7724867724867724,
      "grad_norm": 2.8767826557159424,
      "learning_rate": 3.2724574813414464e-05,
      "loss": 0.2115,
      "step": 146
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 2.861135244369507,
      "learning_rate": 3.2636982167954236e-05,
      "loss": 0.179,
      "step": 147
    },
    {
      "epoch": 0.783068783068783,
      "grad_norm": 2.881589651107788,
      "learning_rate": 3.254788359232795e-05,
      "loss": 0.2188,
      "step": 148
    },
    {
      "epoch": 0.7883597883597884,
      "grad_norm": 2.7440359592437744,
      "learning_rate": 3.245729006630393e-05,
      "loss": 0.1687,
      "step": 149
    },
    {
      "epoch": 0.7936507936507936,
      "grad_norm": 2.965336561203003,
      "learning_rate": 3.236521275387573e-05,
      "loss": 0.2265,
      "step": 150
    },
    {
      "epoch": 0.7936507936507936,
      "eval_loss": 0.11447698622941971,
      "eval_runtime": 115.8332,
      "eval_samples_per_second": 26.348,
      "eval_steps_per_second": 0.207,
      "eval_sts-test_pearson_cosine": 0.874015974599682,
      "eval_sts-test_pearson_dot": 0.8572630785995417,
      "eval_sts-test_pearson_euclidean": 0.9037766701587291,
      "eval_sts-test_pearson_manhattan": 0.905395978358323,
      "eval_sts-test_pearson_max": 0.905395978358323,
      "eval_sts-test_spearman_cosine": 0.9014261797498476,
      "eval_sts-test_spearman_dot": 0.8600332320183043,
      "eval_sts-test_spearman_euclidean": 0.9009870356218139,
      "eval_sts-test_spearman_manhattan": 0.9018416504606055,
      "eval_sts-test_spearman_max": 0.9018416504606055,
      "step": 150
    },
    {
      "epoch": 0.798941798941799,
      "grad_norm": 2.718717098236084,
      "learning_rate": 3.227166300188643e-05,
      "loss": 0.182,
      "step": 151
    },
    {
      "epoch": 0.8042328042328042,
      "grad_norm": 2.84299373626709,
      "learning_rate": 3.2176652338630344e-05,
      "loss": 0.1789,
      "step": 152
    }
  ],
  "logging_steps": 1,
  "max_steps": 378,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 38,
  "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": 640,
  "trial_name": null,
  "trial_params": null
}