{ "best_metric": null, "best_model_checkpoint": null, "epoch": 5.0, "eval_steps": 500, "global_step": 1235, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004048582995951417, "grad_norm": 7.817021969960366, "learning_rate": 3.2258064516129035e-07, "loss": 1.765, "step": 1 }, { "epoch": 0.008097165991902834, "grad_norm": 7.765311651486511, "learning_rate": 6.451612903225807e-07, "loss": 1.7663, "step": 2 }, { "epoch": 0.012145748987854251, "grad_norm": 7.684234892001452, "learning_rate": 9.67741935483871e-07, "loss": 1.7786, "step": 3 }, { "epoch": 0.016194331983805668, "grad_norm": 7.670419356376142, "learning_rate": 1.2903225806451614e-06, "loss": 1.7599, "step": 4 }, { "epoch": 0.020242914979757085, "grad_norm": 7.171756774419978, "learning_rate": 1.6129032258064516e-06, "loss": 1.7721, "step": 5 }, { "epoch": 0.024291497975708502, "grad_norm": 6.846906213794473, "learning_rate": 1.935483870967742e-06, "loss": 1.7291, "step": 6 }, { "epoch": 0.02834008097165992, "grad_norm": 5.390576266526584, "learning_rate": 2.2580645161290324e-06, "loss": 1.7143, "step": 7 }, { "epoch": 0.032388663967611336, "grad_norm": 4.891366600992698, "learning_rate": 2.580645161290323e-06, "loss": 1.7124, "step": 8 }, { "epoch": 0.03643724696356275, "grad_norm": 2.8297511912378237, "learning_rate": 2.903225806451613e-06, "loss": 1.709, "step": 9 }, { "epoch": 0.04048582995951417, "grad_norm": 2.652578167126808, "learning_rate": 3.225806451612903e-06, "loss": 1.7148, "step": 10 }, { "epoch": 0.044534412955465584, "grad_norm": 2.4539892352461448, "learning_rate": 3.548387096774194e-06, "loss": 1.6753, "step": 11 }, { "epoch": 0.048582995951417005, "grad_norm": 6.194910037608819, "learning_rate": 3.870967741935484e-06, "loss": 1.701, "step": 12 }, { "epoch": 0.05263157894736842, "grad_norm": 6.719202174719162, "learning_rate": 4.193548387096774e-06, "loss": 1.6607, "step": 13 }, { "epoch": 0.05668016194331984, "grad_norm": 5.986319568917846, "learning_rate": 4.516129032258065e-06, "loss": 1.6561, "step": 14 }, { "epoch": 0.06072874493927125, "grad_norm": 5.550226592196222, "learning_rate": 4.838709677419355e-06, "loss": 1.6785, "step": 15 }, { "epoch": 0.06477732793522267, "grad_norm": 2.9300033644690306, "learning_rate": 5.161290322580646e-06, "loss": 1.6327, "step": 16 }, { "epoch": 0.06882591093117409, "grad_norm": 2.3320855478142835, "learning_rate": 5.483870967741935e-06, "loss": 1.5764, "step": 17 }, { "epoch": 0.0728744939271255, "grad_norm": 2.0700213063428823, "learning_rate": 5.806451612903226e-06, "loss": 1.5621, "step": 18 }, { "epoch": 0.07692307692307693, "grad_norm": 2.1096231217952597, "learning_rate": 6.129032258064517e-06, "loss": 1.5671, "step": 19 }, { "epoch": 0.08097165991902834, "grad_norm": 1.76430715700395, "learning_rate": 6.451612903225806e-06, "loss": 1.5356, "step": 20 }, { "epoch": 0.08502024291497975, "grad_norm": 1.3205373980342754, "learning_rate": 6.774193548387097e-06, "loss": 1.5115, "step": 21 }, { "epoch": 0.08906882591093117, "grad_norm": 1.3187975483415941, "learning_rate": 7.096774193548388e-06, "loss": 1.519, "step": 22 }, { "epoch": 0.0931174089068826, "grad_norm": 1.4863234552697668, "learning_rate": 7.4193548387096784e-06, "loss": 1.5355, "step": 23 }, { "epoch": 0.09716599190283401, "grad_norm": 1.1386833005258963, "learning_rate": 7.741935483870968e-06, "loss": 1.4633, "step": 24 }, { "epoch": 0.10121457489878542, "grad_norm": 1.0603298285656089, "learning_rate": 8.064516129032258e-06, "loss": 1.4912, "step": 25 }, { "epoch": 0.10526315789473684, "grad_norm": 1.1074972713080737, "learning_rate": 8.387096774193549e-06, "loss": 1.4653, "step": 26 }, { "epoch": 0.10931174089068826, "grad_norm": 1.236235362023646, "learning_rate": 8.70967741935484e-06, "loss": 1.46, "step": 27 }, { "epoch": 0.11336032388663968, "grad_norm": 1.1432267499310544, "learning_rate": 9.03225806451613e-06, "loss": 1.4703, "step": 28 }, { "epoch": 0.11740890688259109, "grad_norm": 1.0013778268601865, "learning_rate": 9.35483870967742e-06, "loss": 1.4551, "step": 29 }, { "epoch": 0.1214574898785425, "grad_norm": 1.057496932679372, "learning_rate": 9.67741935483871e-06, "loss": 1.4477, "step": 30 }, { "epoch": 0.12550607287449392, "grad_norm": 1.0171386023735514, "learning_rate": 1e-05, "loss": 1.4631, "step": 31 }, { "epoch": 0.12955465587044535, "grad_norm": 1.0372881714538893, "learning_rate": 1.0322580645161291e-05, "loss": 1.4549, "step": 32 }, { "epoch": 0.13360323886639677, "grad_norm": 0.8989560758472218, "learning_rate": 1.0645161290322582e-05, "loss": 1.4247, "step": 33 }, { "epoch": 0.13765182186234817, "grad_norm": 0.9027457243585739, "learning_rate": 1.096774193548387e-05, "loss": 1.4347, "step": 34 }, { "epoch": 0.1417004048582996, "grad_norm": 0.9506271581833748, "learning_rate": 1.1290322580645164e-05, "loss": 1.4418, "step": 35 }, { "epoch": 0.145748987854251, "grad_norm": 0.8985044959186421, "learning_rate": 1.1612903225806453e-05, "loss": 1.4332, "step": 36 }, { "epoch": 0.14979757085020243, "grad_norm": 0.8104871634924339, "learning_rate": 1.1935483870967743e-05, "loss": 1.3939, "step": 37 }, { "epoch": 0.15384615384615385, "grad_norm": 0.7717706872353345, "learning_rate": 1.2258064516129034e-05, "loss": 1.4421, "step": 38 }, { "epoch": 0.15789473684210525, "grad_norm": 0.8361944830791279, "learning_rate": 1.2580645161290324e-05, "loss": 1.4296, "step": 39 }, { "epoch": 0.16194331983805668, "grad_norm": 0.7526929877711052, "learning_rate": 1.2903225806451613e-05, "loss": 1.4728, "step": 40 }, { "epoch": 0.1659919028340081, "grad_norm": 0.7227712171136478, "learning_rate": 1.3225806451612903e-05, "loss": 1.4055, "step": 41 }, { "epoch": 0.1700404858299595, "grad_norm": 0.7522670777510583, "learning_rate": 1.3548387096774194e-05, "loss": 1.4161, "step": 42 }, { "epoch": 0.17408906882591094, "grad_norm": 0.5855966433697393, "learning_rate": 1.3870967741935486e-05, "loss": 1.4141, "step": 43 }, { "epoch": 0.17813765182186234, "grad_norm": 0.6575307401292703, "learning_rate": 1.4193548387096776e-05, "loss": 1.3827, "step": 44 }, { "epoch": 0.18218623481781376, "grad_norm": 0.6186735709163782, "learning_rate": 1.4516129032258066e-05, "loss": 1.4106, "step": 45 }, { "epoch": 0.1862348178137652, "grad_norm": 0.6149483478331328, "learning_rate": 1.4838709677419357e-05, "loss": 1.3885, "step": 46 }, { "epoch": 0.1902834008097166, "grad_norm": 0.5413958364864355, "learning_rate": 1.5161290322580646e-05, "loss": 1.4153, "step": 47 }, { "epoch": 0.19433198380566802, "grad_norm": 0.5602383717198675, "learning_rate": 1.5483870967741936e-05, "loss": 1.3787, "step": 48 }, { "epoch": 0.19838056680161945, "grad_norm": 0.6180451866987275, "learning_rate": 1.5806451612903226e-05, "loss": 1.367, "step": 49 }, { "epoch": 0.20242914979757085, "grad_norm": 0.5741288390219407, "learning_rate": 1.6129032258064517e-05, "loss": 1.3858, "step": 50 }, { "epoch": 0.20647773279352227, "grad_norm": 0.6165147029035796, "learning_rate": 1.6451612903225807e-05, "loss": 1.3852, "step": 51 }, { "epoch": 0.21052631578947367, "grad_norm": 0.6146392583770736, "learning_rate": 1.6774193548387098e-05, "loss": 1.3632, "step": 52 }, { "epoch": 0.2145748987854251, "grad_norm": 0.5565533981434275, "learning_rate": 1.7096774193548388e-05, "loss": 1.3796, "step": 53 }, { "epoch": 0.21862348178137653, "grad_norm": 0.6551637678154335, "learning_rate": 1.741935483870968e-05, "loss": 1.3916, "step": 54 }, { "epoch": 0.22267206477732793, "grad_norm": 0.6608369855724604, "learning_rate": 1.774193548387097e-05, "loss": 1.3516, "step": 55 }, { "epoch": 0.22672064777327935, "grad_norm": 0.6382096760502834, "learning_rate": 1.806451612903226e-05, "loss": 1.4061, "step": 56 }, { "epoch": 0.23076923076923078, "grad_norm": 0.6773460793540146, "learning_rate": 1.838709677419355e-05, "loss": 1.3663, "step": 57 }, { "epoch": 0.23481781376518218, "grad_norm": 0.7094817638923763, "learning_rate": 1.870967741935484e-05, "loss": 1.3711, "step": 58 }, { "epoch": 0.2388663967611336, "grad_norm": 1.0233542778557734, "learning_rate": 1.903225806451613e-05, "loss": 1.4085, "step": 59 }, { "epoch": 0.242914979757085, "grad_norm": 1.177825296173323, "learning_rate": 1.935483870967742e-05, "loss": 1.3496, "step": 60 }, { "epoch": 0.24696356275303644, "grad_norm": 1.3750955531249274, "learning_rate": 1.967741935483871e-05, "loss": 1.4027, "step": 61 }, { "epoch": 0.25101214574898784, "grad_norm": 0.698689179040877, "learning_rate": 2e-05, "loss": 1.3531, "step": 62 }, { "epoch": 0.2550607287449393, "grad_norm": 1.4282204977257946, "learning_rate": 2.0322580645161292e-05, "loss": 1.3837, "step": 63 }, { "epoch": 0.2591093117408907, "grad_norm": 1.209639912318108, "learning_rate": 2.0645161290322582e-05, "loss": 1.3942, "step": 64 }, { "epoch": 0.2631578947368421, "grad_norm": 0.7622117666380419, "learning_rate": 2.0967741935483873e-05, "loss": 1.3524, "step": 65 }, { "epoch": 0.26720647773279355, "grad_norm": 0.9145284865707611, "learning_rate": 2.1290322580645163e-05, "loss": 1.3631, "step": 66 }, { "epoch": 0.27125506072874495, "grad_norm": 1.324103443744383, "learning_rate": 2.161290322580645e-05, "loss": 1.3696, "step": 67 }, { "epoch": 0.27530364372469635, "grad_norm": 0.9355920695529059, "learning_rate": 2.193548387096774e-05, "loss": 1.349, "step": 68 }, { "epoch": 0.2793522267206478, "grad_norm": 0.7125006012132146, "learning_rate": 2.225806451612903e-05, "loss": 1.3649, "step": 69 }, { "epoch": 0.2834008097165992, "grad_norm": 0.9387786635228477, "learning_rate": 2.2580645161290328e-05, "loss": 1.3588, "step": 70 }, { "epoch": 0.2874493927125506, "grad_norm": 1.2506814660268717, "learning_rate": 2.2903225806451615e-05, "loss": 1.3719, "step": 71 }, { "epoch": 0.291497975708502, "grad_norm": 0.8902371313021108, "learning_rate": 2.3225806451612906e-05, "loss": 1.3766, "step": 72 }, { "epoch": 0.29554655870445345, "grad_norm": 0.84209320180141, "learning_rate": 2.3548387096774196e-05, "loss": 1.37, "step": 73 }, { "epoch": 0.29959514170040485, "grad_norm": 1.3175439669659426, "learning_rate": 2.3870967741935486e-05, "loss": 1.3398, "step": 74 }, { "epoch": 0.30364372469635625, "grad_norm": 1.1718858123984623, "learning_rate": 2.4193548387096777e-05, "loss": 1.3716, "step": 75 }, { "epoch": 0.3076923076923077, "grad_norm": 0.9565435621493474, "learning_rate": 2.4516129032258067e-05, "loss": 1.3574, "step": 76 }, { "epoch": 0.3117408906882591, "grad_norm": 1.3207588053466395, "learning_rate": 2.4838709677419358e-05, "loss": 1.3199, "step": 77 }, { "epoch": 0.3157894736842105, "grad_norm": 1.0292264620667728, "learning_rate": 2.5161290322580648e-05, "loss": 1.3636, "step": 78 }, { "epoch": 0.31983805668016196, "grad_norm": 1.4980634077199375, "learning_rate": 2.548387096774194e-05, "loss": 1.3452, "step": 79 }, { "epoch": 0.32388663967611336, "grad_norm": 0.9029118893747843, "learning_rate": 2.5806451612903226e-05, "loss": 1.3618, "step": 80 }, { "epoch": 0.32793522267206476, "grad_norm": 1.7910532607407013, "learning_rate": 2.6129032258064516e-05, "loss": 1.3736, "step": 81 }, { "epoch": 0.3319838056680162, "grad_norm": 1.0595583930672032, "learning_rate": 2.6451612903225806e-05, "loss": 1.3427, "step": 82 }, { "epoch": 0.3360323886639676, "grad_norm": 2.004290397480525, "learning_rate": 2.6774193548387097e-05, "loss": 1.3709, "step": 83 }, { "epoch": 0.340080971659919, "grad_norm": 1.7717192463818767, "learning_rate": 2.7096774193548387e-05, "loss": 1.3701, "step": 84 }, { "epoch": 0.3441295546558704, "grad_norm": 1.5539697112103992, "learning_rate": 2.7419354838709678e-05, "loss": 1.3367, "step": 85 }, { "epoch": 0.3481781376518219, "grad_norm": 1.4793755303575082, "learning_rate": 2.774193548387097e-05, "loss": 1.3535, "step": 86 }, { "epoch": 0.3522267206477733, "grad_norm": 1.6904813266328693, "learning_rate": 2.8064516129032262e-05, "loss": 1.3582, "step": 87 }, { "epoch": 0.3562753036437247, "grad_norm": 1.2540476887909842, "learning_rate": 2.8387096774193552e-05, "loss": 1.3577, "step": 88 }, { "epoch": 0.3603238866396761, "grad_norm": 1.3213711758000102, "learning_rate": 2.8709677419354843e-05, "loss": 1.3394, "step": 89 }, { "epoch": 0.3643724696356275, "grad_norm": 1.1834520005833007, "learning_rate": 2.9032258064516133e-05, "loss": 1.3449, "step": 90 }, { "epoch": 0.3684210526315789, "grad_norm": 1.2044749303506188, "learning_rate": 2.9354838709677423e-05, "loss": 1.3998, "step": 91 }, { "epoch": 0.3724696356275304, "grad_norm": 1.0626272176963227, "learning_rate": 2.9677419354838714e-05, "loss": 1.3423, "step": 92 }, { "epoch": 0.3765182186234818, "grad_norm": 1.2817055233460468, "learning_rate": 3.0000000000000004e-05, "loss": 1.3224, "step": 93 }, { "epoch": 0.3805668016194332, "grad_norm": 1.2523592417565956, "learning_rate": 3.032258064516129e-05, "loss": 1.3396, "step": 94 }, { "epoch": 0.38461538461538464, "grad_norm": 1.3806497267137556, "learning_rate": 3.0645161290322585e-05, "loss": 1.3333, "step": 95 }, { "epoch": 0.38866396761133604, "grad_norm": 1.634420609221603, "learning_rate": 3.096774193548387e-05, "loss": 1.3422, "step": 96 }, { "epoch": 0.39271255060728744, "grad_norm": 1.1970840363129023, "learning_rate": 3.1290322580645166e-05, "loss": 1.3281, "step": 97 }, { "epoch": 0.3967611336032389, "grad_norm": 1.2170485522209205, "learning_rate": 3.161290322580645e-05, "loss": 1.3678, "step": 98 }, { "epoch": 0.4008097165991903, "grad_norm": 1.394450239679934, "learning_rate": 3.193548387096774e-05, "loss": 1.298, "step": 99 }, { "epoch": 0.4048582995951417, "grad_norm": 1.017846134491502, "learning_rate": 3.2258064516129034e-05, "loss": 1.3154, "step": 100 }, { "epoch": 0.4089068825910931, "grad_norm": 1.125157676317112, "learning_rate": 3.258064516129033e-05, "loss": 1.3735, "step": 101 }, { "epoch": 0.41295546558704455, "grad_norm": 1.4819440244651165, "learning_rate": 3.2903225806451614e-05, "loss": 1.3395, "step": 102 }, { "epoch": 0.41700404858299595, "grad_norm": 1.3118231422666415, "learning_rate": 3.322580645161291e-05, "loss": 1.3636, "step": 103 }, { "epoch": 0.42105263157894735, "grad_norm": 1.1269589178607553, "learning_rate": 3.3548387096774195e-05, "loss": 1.3617, "step": 104 }, { "epoch": 0.4251012145748988, "grad_norm": 1.3703080210755896, "learning_rate": 3.387096774193549e-05, "loss": 1.3686, "step": 105 }, { "epoch": 0.4291497975708502, "grad_norm": 1.379582727600038, "learning_rate": 3.4193548387096776e-05, "loss": 1.3564, "step": 106 }, { "epoch": 0.4331983805668016, "grad_norm": 1.405823561253003, "learning_rate": 3.451612903225807e-05, "loss": 1.3167, "step": 107 }, { "epoch": 0.43724696356275305, "grad_norm": 1.480119963557577, "learning_rate": 3.483870967741936e-05, "loss": 1.3278, "step": 108 }, { "epoch": 0.44129554655870445, "grad_norm": 1.1419234830607945, "learning_rate": 3.516129032258065e-05, "loss": 1.359, "step": 109 }, { "epoch": 0.44534412955465585, "grad_norm": 2.02127816646111, "learning_rate": 3.548387096774194e-05, "loss": 1.3195, "step": 110 }, { "epoch": 0.4493927125506073, "grad_norm": 1.2705840609411339, "learning_rate": 3.5806451612903225e-05, "loss": 1.3268, "step": 111 }, { "epoch": 0.4534412955465587, "grad_norm": 2.3082471075716895, "learning_rate": 3.612903225806452e-05, "loss": 1.3469, "step": 112 }, { "epoch": 0.4574898785425101, "grad_norm": 1.9716778908794839, "learning_rate": 3.6451612903225805e-05, "loss": 1.3301, "step": 113 }, { "epoch": 0.46153846153846156, "grad_norm": 1.7927876821156745, "learning_rate": 3.67741935483871e-05, "loss": 1.3463, "step": 114 }, { "epoch": 0.46558704453441296, "grad_norm": 1.4625380143680062, "learning_rate": 3.7096774193548386e-05, "loss": 1.3469, "step": 115 }, { "epoch": 0.46963562753036436, "grad_norm": 1.8432607603356967, "learning_rate": 3.741935483870968e-05, "loss": 1.3636, "step": 116 }, { "epoch": 0.47368421052631576, "grad_norm": 1.3812300847502532, "learning_rate": 3.7741935483870974e-05, "loss": 1.3234, "step": 117 }, { "epoch": 0.4777327935222672, "grad_norm": 1.5253766086165668, "learning_rate": 3.806451612903226e-05, "loss": 1.3279, "step": 118 }, { "epoch": 0.4817813765182186, "grad_norm": 1.699113816249027, "learning_rate": 3.8387096774193555e-05, "loss": 1.3526, "step": 119 }, { "epoch": 0.48582995951417, "grad_norm": 1.3766296273317913, "learning_rate": 3.870967741935484e-05, "loss": 1.3528, "step": 120 }, { "epoch": 0.4898785425101215, "grad_norm": 1.265590142005462, "learning_rate": 3.9032258064516135e-05, "loss": 1.308, "step": 121 }, { "epoch": 0.4939271255060729, "grad_norm": 1.1239186120314373, "learning_rate": 3.935483870967742e-05, "loss": 1.3384, "step": 122 }, { "epoch": 0.4979757085020243, "grad_norm": 2.0128540966693724, "learning_rate": 3.9677419354838716e-05, "loss": 1.3023, "step": 123 }, { "epoch": 0.5020242914979757, "grad_norm": 1.3938789431195133, "learning_rate": 4e-05, "loss": 1.3551, "step": 124 }, { "epoch": 0.5060728744939271, "grad_norm": 1.1485778679148233, "learning_rate": 3.9999920040266474e-05, "loss": 1.3539, "step": 125 }, { "epoch": 0.5101214574898786, "grad_norm": 1.034693830118066, "learning_rate": 3.999968016170525e-05, "loss": 1.3615, "step": 126 }, { "epoch": 0.5141700404858299, "grad_norm": 1.896057138739252, "learning_rate": 3.9999280366234394e-05, "loss": 1.3154, "step": 127 }, { "epoch": 0.5182186234817814, "grad_norm": 1.1289755636162684, "learning_rate": 3.999872065705065e-05, "loss": 1.3381, "step": 128 }, { "epoch": 0.5222672064777328, "grad_norm": 1.4714033691334871, "learning_rate": 3.999800103862945e-05, "loss": 1.3146, "step": 129 }, { "epoch": 0.5263157894736842, "grad_norm": 1.7260101879012333, "learning_rate": 3.9997121516724834e-05, "loss": 1.3031, "step": 130 }, { "epoch": 0.5303643724696356, "grad_norm": 1.5125541486614615, "learning_rate": 3.999608209836944e-05, "loss": 1.347, "step": 131 }, { "epoch": 0.5344129554655871, "grad_norm": 1.3908608866554601, "learning_rate": 3.999488279187443e-05, "loss": 1.3244, "step": 132 }, { "epoch": 0.5384615384615384, "grad_norm": 2.121035765171038, "learning_rate": 3.9993523606829425e-05, "loss": 1.339, "step": 133 }, { "epoch": 0.5425101214574899, "grad_norm": 1.3021053873851645, "learning_rate": 3.9992004554102435e-05, "loss": 1.301, "step": 134 }, { "epoch": 0.5465587044534413, "grad_norm": 2.384839257846606, "learning_rate": 3.999032564583976e-05, "loss": 1.3606, "step": 135 }, { "epoch": 0.5506072874493927, "grad_norm": 1.9211911077411383, "learning_rate": 3.998848689546591e-05, "loss": 1.3653, "step": 136 }, { "epoch": 0.5546558704453441, "grad_norm": 2.031499511856728, "learning_rate": 3.9986488317683496e-05, "loss": 1.3597, "step": 137 }, { "epoch": 0.5587044534412956, "grad_norm": 1.557125973439635, "learning_rate": 3.9984329928473067e-05, "loss": 1.3246, "step": 138 }, { "epoch": 0.562753036437247, "grad_norm": 1.8999402050512124, "learning_rate": 3.998201174509306e-05, "loss": 1.3186, "step": 139 }, { "epoch": 0.5668016194331984, "grad_norm": 1.2484902590029554, "learning_rate": 3.997953378607961e-05, "loss": 1.3495, "step": 140 }, { "epoch": 0.5708502024291497, "grad_norm": 1.6668411148048548, "learning_rate": 3.9976896071246403e-05, "loss": 1.3433, "step": 141 }, { "epoch": 0.5748987854251012, "grad_norm": 1.1658567561847932, "learning_rate": 3.997409862168454e-05, "loss": 1.3318, "step": 142 }, { "epoch": 0.5789473684210527, "grad_norm": 1.174696858108887, "learning_rate": 3.997114145976237e-05, "loss": 1.3181, "step": 143 }, { "epoch": 0.582995951417004, "grad_norm": 1.275471870904649, "learning_rate": 3.9968024609125245e-05, "loss": 1.3486, "step": 144 }, { "epoch": 0.5870445344129555, "grad_norm": 0.6996515147745968, "learning_rate": 3.996474809469545e-05, "loss": 1.3414, "step": 145 }, { "epoch": 0.5910931174089069, "grad_norm": 1.026677943451222, "learning_rate": 3.996131194267189e-05, "loss": 1.3299, "step": 146 }, { "epoch": 0.5951417004048583, "grad_norm": 1.4797081081186532, "learning_rate": 3.995771618052995e-05, "loss": 1.3176, "step": 147 }, { "epoch": 0.5991902834008097, "grad_norm": 1.3036610461452305, "learning_rate": 3.9953960837021256e-05, "loss": 1.3275, "step": 148 }, { "epoch": 0.6032388663967612, "grad_norm": 1.8544667621315807, "learning_rate": 3.995004594217343e-05, "loss": 1.2813, "step": 149 }, { "epoch": 0.6072874493927125, "grad_norm": 1.0010111570536093, "learning_rate": 3.994597152728987e-05, "loss": 1.3371, "step": 150 }, { "epoch": 0.611336032388664, "grad_norm": 1.6808321235217847, "learning_rate": 3.994173762494947e-05, "loss": 1.3281, "step": 151 }, { "epoch": 0.6153846153846154, "grad_norm": 1.5314770874622508, "learning_rate": 3.9937344269006424e-05, "loss": 1.3363, "step": 152 }, { "epoch": 0.6194331983805668, "grad_norm": 1.181550950007326, "learning_rate": 3.993279149458988e-05, "loss": 1.3141, "step": 153 }, { "epoch": 0.6234817813765182, "grad_norm": 1.444168010488198, "learning_rate": 3.9928079338103695e-05, "loss": 1.3544, "step": 154 }, { "epoch": 0.6275303643724697, "grad_norm": 0.9756993047344218, "learning_rate": 3.992320783722616e-05, "loss": 1.3005, "step": 155 }, { "epoch": 0.631578947368421, "grad_norm": 1.5739925776323878, "learning_rate": 3.991817703090965e-05, "loss": 1.3396, "step": 156 }, { "epoch": 0.6356275303643725, "grad_norm": 1.2627608238833188, "learning_rate": 3.991298695938038e-05, "loss": 1.3137, "step": 157 }, { "epoch": 0.6396761133603239, "grad_norm": 1.0281500021099295, "learning_rate": 3.9907637664138e-05, "loss": 1.341, "step": 158 }, { "epoch": 0.6437246963562753, "grad_norm": 1.148308312953846, "learning_rate": 3.990212918795534e-05, "loss": 1.3168, "step": 159 }, { "epoch": 0.6477732793522267, "grad_norm": 1.573397972005661, "learning_rate": 3.9896461574878036e-05, "loss": 1.354, "step": 160 }, { "epoch": 0.6518218623481782, "grad_norm": 1.4306175948639088, "learning_rate": 3.989063487022416e-05, "loss": 1.3533, "step": 161 }, { "epoch": 0.6558704453441295, "grad_norm": 1.0692681171240117, "learning_rate": 3.9884649120583903e-05, "loss": 1.3221, "step": 162 }, { "epoch": 0.659919028340081, "grad_norm": 1.1209999105459918, "learning_rate": 3.987850437381915e-05, "loss": 1.3389, "step": 163 }, { "epoch": 0.6639676113360324, "grad_norm": 1.3151047789509527, "learning_rate": 3.987220067906313e-05, "loss": 1.2916, "step": 164 }, { "epoch": 0.6680161943319838, "grad_norm": 1.2107934641928055, "learning_rate": 3.986573808672002e-05, "loss": 1.3093, "step": 165 }, { "epoch": 0.6720647773279352, "grad_norm": 1.291627023061809, "learning_rate": 3.9859116648464534e-05, "loss": 1.2766, "step": 166 }, { "epoch": 0.6761133603238867, "grad_norm": 0.9428756688392859, "learning_rate": 3.985233641724152e-05, "loss": 1.2858, "step": 167 }, { "epoch": 0.680161943319838, "grad_norm": 1.1194290685715451, "learning_rate": 3.984539744726554e-05, "loss": 1.2949, "step": 168 }, { "epoch": 0.6842105263157895, "grad_norm": 1.2055199418483535, "learning_rate": 3.983829979402038e-05, "loss": 1.3098, "step": 169 }, { "epoch": 0.6882591093117408, "grad_norm": 1.4212668652572948, "learning_rate": 3.983104351425871e-05, "loss": 1.315, "step": 170 }, { "epoch": 0.6923076923076923, "grad_norm": 0.7264372902145674, "learning_rate": 3.982362866600154e-05, "loss": 1.322, "step": 171 }, { "epoch": 0.6963562753036437, "grad_norm": 0.7150879452722274, "learning_rate": 3.9816055308537806e-05, "loss": 1.3074, "step": 172 }, { "epoch": 0.7004048582995951, "grad_norm": 1.2842882688733326, "learning_rate": 3.980832350242388e-05, "loss": 1.3116, "step": 173 }, { "epoch": 0.7044534412955465, "grad_norm": 1.2215613006579504, "learning_rate": 3.980043330948306e-05, "loss": 1.3175, "step": 174 }, { "epoch": 0.708502024291498, "grad_norm": 0.9640688561522441, "learning_rate": 3.9792384792805124e-05, "loss": 1.2975, "step": 175 }, { "epoch": 0.7125506072874493, "grad_norm": 0.9498327278018988, "learning_rate": 3.978417801674579e-05, "loss": 1.3119, "step": 176 }, { "epoch": 0.7165991902834008, "grad_norm": 0.8286110078573131, "learning_rate": 3.9775813046926244e-05, "loss": 1.322, "step": 177 }, { "epoch": 0.7206477732793523, "grad_norm": 0.879651344732452, "learning_rate": 3.976728995023254e-05, "loss": 1.2696, "step": 178 }, { "epoch": 0.7246963562753036, "grad_norm": 1.145469173972062, "learning_rate": 3.975860879481514e-05, "loss": 1.354, "step": 179 }, { "epoch": 0.728744939271255, "grad_norm": 1.5062803325715775, "learning_rate": 3.974976965008833e-05, "loss": 1.3293, "step": 180 }, { "epoch": 0.7327935222672065, "grad_norm": 0.8039906564751536, "learning_rate": 3.9740772586729674e-05, "loss": 1.3177, "step": 181 }, { "epoch": 0.7368421052631579, "grad_norm": 1.2932226133233815, "learning_rate": 3.973161767667946e-05, "loss": 1.3255, "step": 182 }, { "epoch": 0.7408906882591093, "grad_norm": 1.0485812888202983, "learning_rate": 3.972230499314009e-05, "loss": 1.2897, "step": 183 }, { "epoch": 0.7449392712550608, "grad_norm": 1.3785119860693829, "learning_rate": 3.9712834610575545e-05, "loss": 1.3464, "step": 184 }, { "epoch": 0.7489878542510121, "grad_norm": 0.8923528650197191, "learning_rate": 3.9703206604710746e-05, "loss": 1.3272, "step": 185 }, { "epoch": 0.7530364372469636, "grad_norm": 1.0329874955455602, "learning_rate": 3.969342105253098e-05, "loss": 1.3003, "step": 186 }, { "epoch": 0.757085020242915, "grad_norm": 1.129640189070115, "learning_rate": 3.9683478032281246e-05, "loss": 1.3313, "step": 187 }, { "epoch": 0.7611336032388664, "grad_norm": 1.0801446758187911, "learning_rate": 3.967337762346568e-05, "loss": 1.298, "step": 188 }, { "epoch": 0.7651821862348178, "grad_norm": 0.6683058890348609, "learning_rate": 3.9663119906846885e-05, "loss": 1.3417, "step": 189 }, { "epoch": 0.7692307692307693, "grad_norm": 1.023083462807274, "learning_rate": 3.965270496444528e-05, "loss": 1.3159, "step": 190 }, { "epoch": 0.7732793522267206, "grad_norm": 1.276494760549101, "learning_rate": 3.9642132879538465e-05, "loss": 1.2764, "step": 191 }, { "epoch": 0.7773279352226721, "grad_norm": 0.9612932850940913, "learning_rate": 3.9631403736660566e-05, "loss": 1.3303, "step": 192 }, { "epoch": 0.7813765182186235, "grad_norm": 1.0095174985087538, "learning_rate": 3.962051762160151e-05, "loss": 1.3156, "step": 193 }, { "epoch": 0.7854251012145749, "grad_norm": 0.9343403887395085, "learning_rate": 3.960947462140638e-05, "loss": 1.288, "step": 194 }, { "epoch": 0.7894736842105263, "grad_norm": 1.1906374977078023, "learning_rate": 3.959827482437472e-05, "loss": 1.2943, "step": 195 }, { "epoch": 0.7935222672064778, "grad_norm": 0.5937747420770079, "learning_rate": 3.958691832005981e-05, "loss": 1.3042, "step": 196 }, { "epoch": 0.7975708502024291, "grad_norm": 1.2844617404984138, "learning_rate": 3.9575405199267944e-05, "loss": 1.3621, "step": 197 }, { "epoch": 0.8016194331983806, "grad_norm": 0.7757634579690764, "learning_rate": 3.956373555405774e-05, "loss": 1.3375, "step": 198 }, { "epoch": 0.805668016194332, "grad_norm": 0.6631129067513153, "learning_rate": 3.955190947773937e-05, "loss": 1.3046, "step": 199 }, { "epoch": 0.8097165991902834, "grad_norm": 0.7116678225907216, "learning_rate": 3.9539927064873824e-05, "loss": 1.3106, "step": 200 }, { "epoch": 0.8137651821862348, "grad_norm": 0.958833050897086, "learning_rate": 3.952778841127214e-05, "loss": 1.3015, "step": 201 }, { "epoch": 0.8178137651821862, "grad_norm": 0.6666349712657758, "learning_rate": 3.95154936139947e-05, "loss": 1.3436, "step": 202 }, { "epoch": 0.8218623481781376, "grad_norm": 0.9938782964486379, "learning_rate": 3.950304277135034e-05, "loss": 1.3113, "step": 203 }, { "epoch": 0.8259109311740891, "grad_norm": 1.0634946964128857, "learning_rate": 3.94904359828957e-05, "loss": 1.3264, "step": 204 }, { "epoch": 0.8299595141700404, "grad_norm": 1.1108128803715909, "learning_rate": 3.94776733494343e-05, "loss": 1.3204, "step": 205 }, { "epoch": 0.8340080971659919, "grad_norm": 0.9149637019884883, "learning_rate": 3.9464754973015826e-05, "loss": 1.2972, "step": 206 }, { "epoch": 0.8380566801619433, "grad_norm": 0.9096983955532396, "learning_rate": 3.9451680956935275e-05, "loss": 1.3049, "step": 207 }, { "epoch": 0.8421052631578947, "grad_norm": 1.0410313256978614, "learning_rate": 3.943845140573213e-05, "loss": 1.2932, "step": 208 }, { "epoch": 0.8461538461538461, "grad_norm": 0.9676351941429718, "learning_rate": 3.942506642518952e-05, "loss": 1.2785, "step": 209 }, { "epoch": 0.8502024291497976, "grad_norm": 1.0186260334308657, "learning_rate": 3.9411526122333396e-05, "loss": 1.3242, "step": 210 }, { "epoch": 0.854251012145749, "grad_norm": 0.8320243560790769, "learning_rate": 3.939783060543167e-05, "loss": 1.2992, "step": 211 }, { "epoch": 0.8582995951417004, "grad_norm": 0.5123140485230406, "learning_rate": 3.938397998399333e-05, "loss": 1.3257, "step": 212 }, { "epoch": 0.8623481781376519, "grad_norm": 0.5600679428985245, "learning_rate": 3.936997436876756e-05, "loss": 1.3147, "step": 213 }, { "epoch": 0.8663967611336032, "grad_norm": 0.5711669776183217, "learning_rate": 3.935581387174289e-05, "loss": 1.3151, "step": 214 }, { "epoch": 0.8704453441295547, "grad_norm": 0.7953320023621919, "learning_rate": 3.9341498606146295e-05, "loss": 1.2997, "step": 215 }, { "epoch": 0.8744939271255061, "grad_norm": 1.0470871203756167, "learning_rate": 3.932702868644224e-05, "loss": 1.3459, "step": 216 }, { "epoch": 0.8785425101214575, "grad_norm": 1.1431631260209887, "learning_rate": 3.931240422833181e-05, "loss": 1.3369, "step": 217 }, { "epoch": 0.8825910931174089, "grad_norm": 0.8677196205683033, "learning_rate": 3.9297625348751806e-05, "loss": 1.2736, "step": 218 }, { "epoch": 0.8866396761133604, "grad_norm": 0.683683495134067, "learning_rate": 3.9282692165873744e-05, "loss": 1.2637, "step": 219 }, { "epoch": 0.8906882591093117, "grad_norm": 0.5146544652752715, "learning_rate": 3.9267604799102945e-05, "loss": 1.2924, "step": 220 }, { "epoch": 0.8947368421052632, "grad_norm": 0.5050575259419128, "learning_rate": 3.9252363369077615e-05, "loss": 1.2886, "step": 221 }, { "epoch": 0.8987854251012146, "grad_norm": 0.5741133836455966, "learning_rate": 3.9236967997667796e-05, "loss": 1.3018, "step": 222 }, { "epoch": 0.902834008097166, "grad_norm": 0.7984866229429344, "learning_rate": 3.9221418807974496e-05, "loss": 1.3084, "step": 223 }, { "epoch": 0.9068825910931174, "grad_norm": 0.8051546530574039, "learning_rate": 3.92057159243286e-05, "loss": 1.3022, "step": 224 }, { "epoch": 0.9109311740890689, "grad_norm": 0.5350091800094465, "learning_rate": 3.9189859472289956e-05, "loss": 1.2845, "step": 225 }, { "epoch": 0.9149797570850202, "grad_norm": 0.5508080432667909, "learning_rate": 3.9173849578646324e-05, "loss": 1.3103, "step": 226 }, { "epoch": 0.9190283400809717, "grad_norm": 0.6355131610463852, "learning_rate": 3.9157686371412395e-05, "loss": 1.3296, "step": 227 }, { "epoch": 0.9230769230769231, "grad_norm": 0.684599352599617, "learning_rate": 3.914136997982874e-05, "loss": 1.3176, "step": 228 }, { "epoch": 0.9271255060728745, "grad_norm": 0.7075870875168471, "learning_rate": 3.912490053436079e-05, "loss": 1.3092, "step": 229 }, { "epoch": 0.9311740890688259, "grad_norm": 0.5986821017530498, "learning_rate": 3.9108278166697805e-05, "loss": 1.2731, "step": 230 }, { "epoch": 0.9352226720647774, "grad_norm": 0.5960899369087306, "learning_rate": 3.909150300975178e-05, "loss": 1.2971, "step": 231 }, { "epoch": 0.9392712550607287, "grad_norm": 0.6944011184759394, "learning_rate": 3.907457519765642e-05, "loss": 1.2917, "step": 232 }, { "epoch": 0.9433198380566802, "grad_norm": 0.7160071287966202, "learning_rate": 3.905749486576607e-05, "loss": 1.2825, "step": 233 }, { "epoch": 0.9473684210526315, "grad_norm": 0.6583864026178007, "learning_rate": 3.90402621506546e-05, "loss": 1.3026, "step": 234 }, { "epoch": 0.951417004048583, "grad_norm": 0.597095390669564, "learning_rate": 3.902287719011435e-05, "loss": 1.3211, "step": 235 }, { "epoch": 0.9554655870445344, "grad_norm": 0.7640194330141886, "learning_rate": 3.900534012315499e-05, "loss": 1.2788, "step": 236 }, { "epoch": 0.9595141700404858, "grad_norm": 0.6503342299224983, "learning_rate": 3.8987651090002454e-05, "loss": 1.3066, "step": 237 }, { "epoch": 0.9635627530364372, "grad_norm": 0.5815686865216723, "learning_rate": 3.896981023209777e-05, "loss": 1.2764, "step": 238 }, { "epoch": 0.9676113360323887, "grad_norm": 0.6158569669126861, "learning_rate": 3.8951817692095966e-05, "loss": 1.3232, "step": 239 }, { "epoch": 0.97165991902834, "grad_norm": 0.5765978438038556, "learning_rate": 3.893367361386491e-05, "loss": 1.3412, "step": 240 }, { "epoch": 0.9757085020242915, "grad_norm": 0.6444332718453728, "learning_rate": 3.891537814248417e-05, "loss": 1.2881, "step": 241 }, { "epoch": 0.979757085020243, "grad_norm": 0.748963881191927, "learning_rate": 3.889693142424384e-05, "loss": 1.3004, "step": 242 }, { "epoch": 0.9838056680161943, "grad_norm": 0.9850456170866738, "learning_rate": 3.8878333606643405e-05, "loss": 1.2999, "step": 243 }, { "epoch": 0.9878542510121457, "grad_norm": 1.1819843700470634, "learning_rate": 3.885958483839049e-05, "loss": 1.2989, "step": 244 }, { "epoch": 0.9919028340080972, "grad_norm": 0.6942278146550706, "learning_rate": 3.8840685269399786e-05, "loss": 1.3272, "step": 245 }, { "epoch": 0.9959514170040485, "grad_norm": 0.48474820473905655, "learning_rate": 3.882163505079171e-05, "loss": 1.3052, "step": 246 }, { "epoch": 1.0, "grad_norm": 1.043214540097121, "learning_rate": 3.880243433489132e-05, "loss": 1.3175, "step": 247 }, { "epoch": 1.0040485829959513, "grad_norm": 1.2115479172877, "learning_rate": 3.878308327522702e-05, "loss": 1.2805, "step": 248 }, { "epoch": 1.008097165991903, "grad_norm": 0.852133865304501, "learning_rate": 3.876358202652936e-05, "loss": 1.2855, "step": 249 }, { "epoch": 1.0121457489878543, "grad_norm": 0.5677981479459124, "learning_rate": 3.8743930744729835e-05, "loss": 1.2592, "step": 250 }, { "epoch": 1.0161943319838056, "grad_norm": 0.6062777238888633, "learning_rate": 3.8724129586959535e-05, "loss": 1.294, "step": 251 }, { "epoch": 1.0202429149797572, "grad_norm": 0.7297466089326609, "learning_rate": 3.870417871154801e-05, "loss": 1.2656, "step": 252 }, { "epoch": 1.0242914979757085, "grad_norm": 0.6560327406362116, "learning_rate": 3.868407827802192e-05, "loss": 1.2752, "step": 253 }, { "epoch": 1.0283400809716599, "grad_norm": 0.5578918475029182, "learning_rate": 3.8663828447103804e-05, "loss": 1.2773, "step": 254 }, { "epoch": 1.0323886639676114, "grad_norm": 0.6736252897750953, "learning_rate": 3.8643429380710765e-05, "loss": 1.2857, "step": 255 }, { "epoch": 1.0364372469635628, "grad_norm": 0.5481541405605713, "learning_rate": 3.862288124195319e-05, "loss": 1.2444, "step": 256 }, { "epoch": 1.040485829959514, "grad_norm": 0.5924665347986072, "learning_rate": 3.8602184195133464e-05, "loss": 1.2478, "step": 257 }, { "epoch": 1.0445344129554657, "grad_norm": 0.8112821032943286, "learning_rate": 3.8581338405744604e-05, "loss": 1.296, "step": 258 }, { "epoch": 1.048582995951417, "grad_norm": 0.9271383607077617, "learning_rate": 3.8560344040468996e-05, "loss": 1.2798, "step": 259 }, { "epoch": 1.0526315789473684, "grad_norm": 0.7553240195336219, "learning_rate": 3.853920126717703e-05, "loss": 1.2539, "step": 260 }, { "epoch": 1.05668016194332, "grad_norm": 0.6929067191648801, "learning_rate": 3.851791025492574e-05, "loss": 1.2749, "step": 261 }, { "epoch": 1.0607287449392713, "grad_norm": 0.549309808987606, "learning_rate": 3.8496471173957515e-05, "loss": 1.2691, "step": 262 }, { "epoch": 1.0647773279352226, "grad_norm": 0.5487407852995552, "learning_rate": 3.847488419569866e-05, "loss": 1.2933, "step": 263 }, { "epoch": 1.0688259109311742, "grad_norm": 0.5613457979761841, "learning_rate": 3.8453149492758077e-05, "loss": 1.2584, "step": 264 }, { "epoch": 1.0728744939271255, "grad_norm": 0.5647892561889882, "learning_rate": 3.8431267238925886e-05, "loss": 1.2547, "step": 265 }, { "epoch": 1.0769230769230769, "grad_norm": 0.4512963620673711, "learning_rate": 3.840923760917199e-05, "loss": 1.3019, "step": 266 }, { "epoch": 1.0809716599190284, "grad_norm": 0.5671457913638348, "learning_rate": 3.838706077964473e-05, "loss": 1.265, "step": 267 }, { "epoch": 1.0850202429149798, "grad_norm": 0.53668562558085, "learning_rate": 3.836473692766944e-05, "loss": 1.2721, "step": 268 }, { "epoch": 1.0890688259109311, "grad_norm": 0.5605319020886342, "learning_rate": 3.834226623174705e-05, "loss": 1.2341, "step": 269 }, { "epoch": 1.0931174089068827, "grad_norm": 0.5707826002586577, "learning_rate": 3.831964887155264e-05, "loss": 1.2396, "step": 270 }, { "epoch": 1.097165991902834, "grad_norm": 0.6106281290175727, "learning_rate": 3.829688502793403e-05, "loss": 1.2877, "step": 271 }, { "epoch": 1.1012145748987854, "grad_norm": 0.42372059950261026, "learning_rate": 3.827397488291029e-05, "loss": 1.2638, "step": 272 }, { "epoch": 1.1052631578947367, "grad_norm": 0.43129393880491307, "learning_rate": 3.8250918619670343e-05, "loss": 1.2766, "step": 273 }, { "epoch": 1.1093117408906883, "grad_norm": 0.5168455389589575, "learning_rate": 3.822771642257145e-05, "loss": 1.2606, "step": 274 }, { "epoch": 1.1133603238866396, "grad_norm": 0.591244565082574, "learning_rate": 3.820436847713776e-05, "loss": 1.2933, "step": 275 }, { "epoch": 1.117408906882591, "grad_norm": 0.6359118467198084, "learning_rate": 3.8180874970058826e-05, "loss": 1.2658, "step": 276 }, { "epoch": 1.1214574898785425, "grad_norm": 0.546237945513659, "learning_rate": 3.8157236089188103e-05, "loss": 1.267, "step": 277 }, { "epoch": 1.125506072874494, "grad_norm": 0.6720950157168624, "learning_rate": 3.813345202354145e-05, "loss": 1.268, "step": 278 }, { "epoch": 1.1295546558704452, "grad_norm": 0.6658780574283746, "learning_rate": 3.810952296329563e-05, "loss": 1.2307, "step": 279 }, { "epoch": 1.1336032388663968, "grad_norm": 0.519614849604735, "learning_rate": 3.808544909978676e-05, "loss": 1.2394, "step": 280 }, { "epoch": 1.1376518218623481, "grad_norm": 0.5582585810448268, "learning_rate": 3.806123062550882e-05, "loss": 1.2465, "step": 281 }, { "epoch": 1.1417004048582995, "grad_norm": 0.5992638453320891, "learning_rate": 3.803686773411208e-05, "loss": 1.2648, "step": 282 }, { "epoch": 1.145748987854251, "grad_norm": 0.5946541436787931, "learning_rate": 3.801236062040158e-05, "loss": 1.2878, "step": 283 }, { "epoch": 1.1497975708502024, "grad_norm": 0.5588088605524333, "learning_rate": 3.798770948033553e-05, "loss": 1.2826, "step": 284 }, { "epoch": 1.1538461538461537, "grad_norm": 0.611575079608886, "learning_rate": 3.796291451102381e-05, "loss": 1.2828, "step": 285 }, { "epoch": 1.1578947368421053, "grad_norm": 0.6249666412851766, "learning_rate": 3.793797591072631e-05, "loss": 1.2733, "step": 286 }, { "epoch": 1.1619433198380567, "grad_norm": 0.6811329108841632, "learning_rate": 3.791289387885144e-05, "loss": 1.2741, "step": 287 }, { "epoch": 1.165991902834008, "grad_norm": 0.7187993747526958, "learning_rate": 3.788766861595443e-05, "loss": 1.2492, "step": 288 }, { "epoch": 1.1700404858299596, "grad_norm": 0.7292387088936695, "learning_rate": 3.7862300323735835e-05, "loss": 1.2738, "step": 289 }, { "epoch": 1.174089068825911, "grad_norm": 0.6305203851524754, "learning_rate": 3.783678920503983e-05, "loss": 1.2321, "step": 290 }, { "epoch": 1.1781376518218623, "grad_norm": 0.4266111828455623, "learning_rate": 3.781113546385265e-05, "loss": 1.2465, "step": 291 }, { "epoch": 1.1821862348178138, "grad_norm": 0.697898707463108, "learning_rate": 3.7785339305300916e-05, "loss": 1.2938, "step": 292 }, { "epoch": 1.1862348178137652, "grad_norm": 0.6480066637332251, "learning_rate": 3.7759400935650025e-05, "loss": 1.2629, "step": 293 }, { "epoch": 1.1902834008097165, "grad_norm": 0.6146202951346087, "learning_rate": 3.77333205623025e-05, "loss": 1.2709, "step": 294 }, { "epoch": 1.194331983805668, "grad_norm": 0.5782587375838868, "learning_rate": 3.7707098393796295e-05, "loss": 1.2761, "step": 295 }, { "epoch": 1.1983805668016194, "grad_norm": 0.5751990754698114, "learning_rate": 3.7680734639803185e-05, "loss": 1.2695, "step": 296 }, { "epoch": 1.2024291497975708, "grad_norm": 0.4246533120017889, "learning_rate": 3.765422951112704e-05, "loss": 1.2699, "step": 297 }, { "epoch": 1.2064777327935223, "grad_norm": 0.45319049057733435, "learning_rate": 3.762758321970216e-05, "loss": 1.2482, "step": 298 }, { "epoch": 1.2105263157894737, "grad_norm": 0.4899127262626817, "learning_rate": 3.7600795978591584e-05, "loss": 1.2634, "step": 299 }, { "epoch": 1.214574898785425, "grad_norm": 0.5762666725398966, "learning_rate": 3.757386800198538e-05, "loss": 1.257, "step": 300 }, { "epoch": 1.2186234817813766, "grad_norm": 0.5315076874824501, "learning_rate": 3.7546799505198925e-05, "loss": 1.2901, "step": 301 }, { "epoch": 1.222672064777328, "grad_norm": 0.63347431901163, "learning_rate": 3.7519590704671197e-05, "loss": 1.264, "step": 302 }, { "epoch": 1.2267206477732793, "grad_norm": 0.5635049371290454, "learning_rate": 3.749224181796305e-05, "loss": 1.275, "step": 303 }, { "epoch": 1.2307692307692308, "grad_norm": 0.5199863927510923, "learning_rate": 3.746475306375545e-05, "loss": 1.23, "step": 304 }, { "epoch": 1.2348178137651822, "grad_norm": 0.47384979979938946, "learning_rate": 3.743712466184774e-05, "loss": 1.2549, "step": 305 }, { "epoch": 1.2388663967611335, "grad_norm": 0.6246045575247265, "learning_rate": 3.7409356833155885e-05, "loss": 1.2618, "step": 306 }, { "epoch": 1.242914979757085, "grad_norm": 0.6039842952223937, "learning_rate": 3.73814497997107e-05, "loss": 1.261, "step": 307 }, { "epoch": 1.2469635627530364, "grad_norm": 0.4646932787191638, "learning_rate": 3.7353403784656095e-05, "loss": 1.252, "step": 308 }, { "epoch": 1.2510121457489878, "grad_norm": 0.539759486341796, "learning_rate": 3.732521901224724e-05, "loss": 1.2683, "step": 309 }, { "epoch": 1.2550607287449393, "grad_norm": 0.604372961881943, "learning_rate": 3.7296895707848844e-05, "loss": 1.2496, "step": 310 }, { "epoch": 1.2591093117408907, "grad_norm": 0.6047336687831651, "learning_rate": 3.7268434097933275e-05, "loss": 1.289, "step": 311 }, { "epoch": 1.263157894736842, "grad_norm": 0.7543544749797321, "learning_rate": 3.723983441007882e-05, "loss": 1.2595, "step": 312 }, { "epoch": 1.2672064777327936, "grad_norm": 0.7285542715093115, "learning_rate": 3.721109687296781e-05, "loss": 1.2687, "step": 313 }, { "epoch": 1.271255060728745, "grad_norm": 0.4893384921130019, "learning_rate": 3.718222171638484e-05, "loss": 1.281, "step": 314 }, { "epoch": 1.2753036437246963, "grad_norm": 0.6824568840604821, "learning_rate": 3.715320917121488e-05, "loss": 1.2771, "step": 315 }, { "epoch": 1.2793522267206479, "grad_norm": 0.7218259217180107, "learning_rate": 3.712405946944149e-05, "loss": 1.2344, "step": 316 }, { "epoch": 1.2834008097165992, "grad_norm": 0.6111962337867733, "learning_rate": 3.709477284414488e-05, "loss": 1.2725, "step": 317 }, { "epoch": 1.2874493927125505, "grad_norm": 0.7820269147388261, "learning_rate": 3.7065349529500136e-05, "loss": 1.271, "step": 318 }, { "epoch": 1.291497975708502, "grad_norm": 0.6596645444050189, "learning_rate": 3.7035789760775305e-05, "loss": 1.2537, "step": 319 }, { "epoch": 1.2955465587044535, "grad_norm": 0.6423585291324575, "learning_rate": 3.70060937743295e-05, "loss": 1.278, "step": 320 }, { "epoch": 1.2995951417004048, "grad_norm": 0.43968481866813247, "learning_rate": 3.6976261807611045e-05, "loss": 1.2671, "step": 321 }, { "epoch": 1.3036437246963564, "grad_norm": 0.5437197425410443, "learning_rate": 3.694629409915555e-05, "loss": 1.2862, "step": 322 }, { "epoch": 1.3076923076923077, "grad_norm": 0.5595000775215431, "learning_rate": 3.691619088858401e-05, "loss": 1.2905, "step": 323 }, { "epoch": 1.311740890688259, "grad_norm": 0.5954106637049246, "learning_rate": 3.68859524166009e-05, "loss": 1.3105, "step": 324 }, { "epoch": 1.3157894736842106, "grad_norm": 0.4978117847920989, "learning_rate": 3.6855578924992226e-05, "loss": 1.2494, "step": 325 }, { "epoch": 1.319838056680162, "grad_norm": 0.5170146414926063, "learning_rate": 3.6825070656623626e-05, "loss": 1.2519, "step": 326 }, { "epoch": 1.3238866396761133, "grad_norm": 0.5791360422268526, "learning_rate": 3.67944278554384e-05, "loss": 1.2677, "step": 327 }, { "epoch": 1.3279352226720649, "grad_norm": 0.6043807068590725, "learning_rate": 3.676365076645557e-05, "loss": 1.2478, "step": 328 }, { "epoch": 1.3319838056680162, "grad_norm": 0.5916694564296796, "learning_rate": 3.673273963576791e-05, "loss": 1.271, "step": 329 }, { "epoch": 1.3360323886639676, "grad_norm": 0.4977048455960521, "learning_rate": 3.670169471054001e-05, "loss": 1.2321, "step": 330 }, { "epoch": 1.3400809716599191, "grad_norm": 0.5201433924879197, "learning_rate": 3.6670516239006254e-05, "loss": 1.2233, "step": 331 }, { "epoch": 1.3441295546558705, "grad_norm": 0.5333484879593101, "learning_rate": 3.663920447046888e-05, "loss": 1.2984, "step": 332 }, { "epoch": 1.3481781376518218, "grad_norm": 0.7068789754513841, "learning_rate": 3.6607759655295954e-05, "loss": 1.2648, "step": 333 }, { "epoch": 1.3522267206477734, "grad_norm": 0.6874424504597673, "learning_rate": 3.657618204491937e-05, "loss": 1.2259, "step": 334 }, { "epoch": 1.3562753036437247, "grad_norm": 0.6701453000215625, "learning_rate": 3.6544471891832875e-05, "loss": 1.2612, "step": 335 }, { "epoch": 1.360323886639676, "grad_norm": 0.4597000121304947, "learning_rate": 3.6512629449589983e-05, "loss": 1.2695, "step": 336 }, { "epoch": 1.3643724696356276, "grad_norm": 0.4736062321485456, "learning_rate": 3.6480654972802045e-05, "loss": 1.2416, "step": 337 }, { "epoch": 1.368421052631579, "grad_norm": 0.5453116717486277, "learning_rate": 3.644854871713611e-05, "loss": 1.2602, "step": 338 }, { "epoch": 1.3724696356275303, "grad_norm": 0.6122504151083354, "learning_rate": 3.6416310939312924e-05, "loss": 1.2583, "step": 339 }, { "epoch": 1.376518218623482, "grad_norm": 0.622753459248387, "learning_rate": 3.638394189710493e-05, "loss": 1.2808, "step": 340 }, { "epoch": 1.3805668016194332, "grad_norm": 0.489505418384514, "learning_rate": 3.635144184933412e-05, "loss": 1.2507, "step": 341 }, { "epoch": 1.3846153846153846, "grad_norm": 0.4351752027443821, "learning_rate": 3.6318811055869994e-05, "loss": 1.2613, "step": 342 }, { "epoch": 1.3886639676113361, "grad_norm": 0.45378466251349264, "learning_rate": 3.628604977762752e-05, "loss": 1.2756, "step": 343 }, { "epoch": 1.3927125506072875, "grad_norm": 0.6067250126322401, "learning_rate": 3.6253158276565004e-05, "loss": 1.2272, "step": 344 }, { "epoch": 1.3967611336032388, "grad_norm": 0.5803578578903397, "learning_rate": 3.6220136815682016e-05, "loss": 1.2333, "step": 345 }, { "epoch": 1.4008097165991904, "grad_norm": 0.552012497361238, "learning_rate": 3.618698565901727e-05, "loss": 1.2646, "step": 346 }, { "epoch": 1.4048582995951417, "grad_norm": 0.4179553322430306, "learning_rate": 3.615370507164654e-05, "loss": 1.2808, "step": 347 }, { "epoch": 1.408906882591093, "grad_norm": 0.5198306857567839, "learning_rate": 3.61202953196805e-05, "loss": 1.2251, "step": 348 }, { "epoch": 1.4129554655870447, "grad_norm": 0.7453152381541523, "learning_rate": 3.6086756670262654e-05, "loss": 1.2189, "step": 349 }, { "epoch": 1.417004048582996, "grad_norm": 0.7346516596440464, "learning_rate": 3.6053089391567135e-05, "loss": 1.2738, "step": 350 }, { "epoch": 1.4210526315789473, "grad_norm": 0.44035589109287493, "learning_rate": 3.601929375279662e-05, "loss": 1.2559, "step": 351 }, { "epoch": 1.425101214574899, "grad_norm": 0.5160499743646662, "learning_rate": 3.598537002418012e-05, "loss": 1.2528, "step": 352 }, { "epoch": 1.4291497975708503, "grad_norm": 0.5793730332258012, "learning_rate": 3.5951318476970885e-05, "loss": 1.28, "step": 353 }, { "epoch": 1.4331983805668016, "grad_norm": 0.5603583307443534, "learning_rate": 3.591713938344416e-05, "loss": 1.2514, "step": 354 }, { "epoch": 1.4372469635627532, "grad_norm": 0.5318431154239239, "learning_rate": 3.588283301689507e-05, "loss": 1.2898, "step": 355 }, { "epoch": 1.4412955465587045, "grad_norm": 0.5414501560151116, "learning_rate": 3.5848399651636424e-05, "loss": 1.2507, "step": 356 }, { "epoch": 1.4453441295546559, "grad_norm": 0.4997597792810353, "learning_rate": 3.5813839562996473e-05, "loss": 1.2691, "step": 357 }, { "epoch": 1.4493927125506074, "grad_norm": 0.677753640166071, "learning_rate": 3.5779153027316775e-05, "loss": 1.2721, "step": 358 }, { "epoch": 1.4534412955465588, "grad_norm": 0.7149953988005853, "learning_rate": 3.574434032194994e-05, "loss": 1.2466, "step": 359 }, { "epoch": 1.45748987854251, "grad_norm": 0.6865530554382344, "learning_rate": 3.5709401725257436e-05, "loss": 1.2655, "step": 360 }, { "epoch": 1.4615384615384617, "grad_norm": 0.49044310743595926, "learning_rate": 3.5674337516607346e-05, "loss": 1.2371, "step": 361 }, { "epoch": 1.465587044534413, "grad_norm": 0.45357689053171035, "learning_rate": 3.563914797637216e-05, "loss": 1.2323, "step": 362 }, { "epoch": 1.4696356275303644, "grad_norm": 0.47686729146042606, "learning_rate": 3.560383338592649e-05, "loss": 1.266, "step": 363 }, { "epoch": 1.4736842105263157, "grad_norm": 0.5540396642049429, "learning_rate": 3.556839402764487e-05, "loss": 1.2647, "step": 364 }, { "epoch": 1.4777327935222673, "grad_norm": 0.6472986807273661, "learning_rate": 3.553283018489946e-05, "loss": 1.2948, "step": 365 }, { "epoch": 1.4817813765182186, "grad_norm": 0.5995142093401776, "learning_rate": 3.54971421420578e-05, "loss": 1.2528, "step": 366 }, { "epoch": 1.48582995951417, "grad_norm": 0.5827461598842469, "learning_rate": 3.5461330184480524e-05, "loss": 1.2778, "step": 367 }, { "epoch": 1.4898785425101215, "grad_norm": 0.5245511179107357, "learning_rate": 3.54253945985191e-05, "loss": 1.2392, "step": 368 }, { "epoch": 1.4939271255060729, "grad_norm": 0.577088144867939, "learning_rate": 3.5389335671513524e-05, "loss": 1.2589, "step": 369 }, { "epoch": 1.4979757085020242, "grad_norm": 0.638644072059853, "learning_rate": 3.5353153691789986e-05, "loss": 1.2316, "step": 370 }, { "epoch": 1.5020242914979756, "grad_norm": 0.6659091058696521, "learning_rate": 3.531684894865866e-05, "loss": 1.2457, "step": 371 }, { "epoch": 1.5060728744939271, "grad_norm": 0.621289637009036, "learning_rate": 3.528042173241128e-05, "loss": 1.2664, "step": 372 }, { "epoch": 1.5101214574898787, "grad_norm": 0.5848878951354088, "learning_rate": 3.524387233431892e-05, "loss": 1.2845, "step": 373 }, { "epoch": 1.5141700404858298, "grad_norm": 0.5119812892729275, "learning_rate": 3.520720104662958e-05, "loss": 1.2659, "step": 374 }, { "epoch": 1.5182186234817814, "grad_norm": 0.40558896801424527, "learning_rate": 3.5170408162565904e-05, "loss": 1.2508, "step": 375 }, { "epoch": 1.522267206477733, "grad_norm": 0.4842042039531039, "learning_rate": 3.513349397632281e-05, "loss": 1.2482, "step": 376 }, { "epoch": 1.526315789473684, "grad_norm": 0.4926369377968011, "learning_rate": 3.5096458783065145e-05, "loss": 1.2784, "step": 377 }, { "epoch": 1.5303643724696356, "grad_norm": 0.5074680194201903, "learning_rate": 3.505930287892533e-05, "loss": 1.2556, "step": 378 }, { "epoch": 1.5344129554655872, "grad_norm": 0.46769496412913314, "learning_rate": 3.502202656100099e-05, "loss": 1.2472, "step": 379 }, { "epoch": 1.5384615384615383, "grad_norm": 0.44017828563898603, "learning_rate": 3.498463012735256e-05, "loss": 1.2567, "step": 380 }, { "epoch": 1.54251012145749, "grad_norm": 0.4777652809593697, "learning_rate": 3.494711387700094e-05, "loss": 1.2403, "step": 381 }, { "epoch": 1.5465587044534415, "grad_norm": 0.41430469691818106, "learning_rate": 3.490947810992505e-05, "loss": 1.2442, "step": 382 }, { "epoch": 1.5506072874493926, "grad_norm": 0.5220680956807547, "learning_rate": 3.48717231270595e-05, "loss": 1.2787, "step": 383 }, { "epoch": 1.5546558704453441, "grad_norm": 0.5055904341949204, "learning_rate": 3.483384923029211e-05, "loss": 1.2558, "step": 384 }, { "epoch": 1.5587044534412957, "grad_norm": 0.4357480007305054, "learning_rate": 3.479585672246156e-05, "loss": 1.2556, "step": 385 }, { "epoch": 1.5627530364372468, "grad_norm": 0.5103254861254788, "learning_rate": 3.4757745907354924e-05, "loss": 1.2631, "step": 386 }, { "epoch": 1.5668016194331984, "grad_norm": 0.4433033096888469, "learning_rate": 3.471951708970527e-05, "loss": 1.2635, "step": 387 }, { "epoch": 1.5708502024291497, "grad_norm": 0.4510486955965351, "learning_rate": 3.468117057518921e-05, "loss": 1.2945, "step": 388 }, { "epoch": 1.574898785425101, "grad_norm": 0.5765804206708719, "learning_rate": 3.4642706670424426e-05, "loss": 1.2634, "step": 389 }, { "epoch": 1.5789473684210527, "grad_norm": 0.4629541570125335, "learning_rate": 3.460412568296731e-05, "loss": 1.276, "step": 390 }, { "epoch": 1.582995951417004, "grad_norm": 0.5578474761895469, "learning_rate": 3.456542792131039e-05, "loss": 1.2715, "step": 391 }, { "epoch": 1.5870445344129553, "grad_norm": 0.45092597789654953, "learning_rate": 3.4526613694879936e-05, "loss": 1.234, "step": 392 }, { "epoch": 1.591093117408907, "grad_norm": 0.5130268634376439, "learning_rate": 3.448768331403348e-05, "loss": 1.2605, "step": 393 }, { "epoch": 1.5951417004048583, "grad_norm": 0.5435065980842444, "learning_rate": 3.44486370900573e-05, "loss": 1.2708, "step": 394 }, { "epoch": 1.5991902834008096, "grad_norm": 0.6049999935706717, "learning_rate": 3.440947533516396e-05, "loss": 1.2449, "step": 395 }, { "epoch": 1.6032388663967612, "grad_norm": 0.5658823946092367, "learning_rate": 3.4370198362489816e-05, "loss": 1.259, "step": 396 }, { "epoch": 1.6072874493927125, "grad_norm": 0.3556946741009923, "learning_rate": 3.43308064860925e-05, "loss": 1.2499, "step": 397 }, { "epoch": 1.6113360323886639, "grad_norm": 0.5085421529030033, "learning_rate": 3.4291300020948393e-05, "loss": 1.244, "step": 398 }, { "epoch": 1.6153846153846154, "grad_norm": 0.5807219627660587, "learning_rate": 3.425167928295015e-05, "loss": 1.266, "step": 399 }, { "epoch": 1.6194331983805668, "grad_norm": 0.5494592346527412, "learning_rate": 3.421194458890411e-05, "loss": 1.229, "step": 400 }, { "epoch": 1.623481781376518, "grad_norm": 0.49617379351542606, "learning_rate": 3.4172096256527865e-05, "loss": 1.2334, "step": 401 }, { "epoch": 1.6275303643724697, "grad_norm": 0.48428129586397983, "learning_rate": 3.4132134604447595e-05, "loss": 1.266, "step": 402 }, { "epoch": 1.631578947368421, "grad_norm": 0.5076745992755775, "learning_rate": 3.409205995219561e-05, "loss": 1.2639, "step": 403 }, { "epoch": 1.6356275303643724, "grad_norm": 0.5548459570468455, "learning_rate": 3.4051872620207765e-05, "loss": 1.2529, "step": 404 }, { "epoch": 1.639676113360324, "grad_norm": 0.5498937697649128, "learning_rate": 3.40115729298209e-05, "loss": 1.2857, "step": 405 }, { "epoch": 1.6437246963562753, "grad_norm": 0.37351320171288305, "learning_rate": 3.397116120327025e-05, "loss": 1.235, "step": 406 }, { "epoch": 1.6477732793522266, "grad_norm": 0.5557592758540862, "learning_rate": 3.3930637763686916e-05, "loss": 1.2292, "step": 407 }, { "epoch": 1.6518218623481782, "grad_norm": 0.5366496019659959, "learning_rate": 3.389000293509524e-05, "loss": 1.2303, "step": 408 }, { "epoch": 1.6558704453441295, "grad_norm": 0.5016867542935498, "learning_rate": 3.3849257042410225e-05, "loss": 1.2691, "step": 409 }, { "epoch": 1.6599190283400809, "grad_norm": 0.5762580896400128, "learning_rate": 3.380840041143494e-05, "loss": 1.2656, "step": 410 }, { "epoch": 1.6639676113360324, "grad_norm": 0.7127549086700014, "learning_rate": 3.376743336885792e-05, "loss": 1.2734, "step": 411 }, { "epoch": 1.6680161943319838, "grad_norm": 0.43530710489121066, "learning_rate": 3.372635624225055e-05, "loss": 1.2358, "step": 412 }, { "epoch": 1.6720647773279351, "grad_norm": 0.5664880401203894, "learning_rate": 3.3685169360064445e-05, "loss": 1.2778, "step": 413 }, { "epoch": 1.6761133603238867, "grad_norm": 0.47796018609831087, "learning_rate": 3.3643873051628804e-05, "loss": 1.2671, "step": 414 }, { "epoch": 1.680161943319838, "grad_norm": 0.5308643646042376, "learning_rate": 3.3602467647147814e-05, "loss": 1.2523, "step": 415 }, { "epoch": 1.6842105263157894, "grad_norm": 0.48539810415567713, "learning_rate": 3.356095347769799e-05, "loss": 1.2612, "step": 416 }, { "epoch": 1.688259109311741, "grad_norm": 0.4261655399301163, "learning_rate": 3.351933087522552e-05, "loss": 1.2512, "step": 417 }, { "epoch": 1.6923076923076923, "grad_norm": 0.4414517639705776, "learning_rate": 3.3477600172543626e-05, "loss": 1.2586, "step": 418 }, { "epoch": 1.6963562753036436, "grad_norm": 0.5282303696299724, "learning_rate": 3.3435761703329894e-05, "loss": 1.2585, "step": 419 }, { "epoch": 1.7004048582995952, "grad_norm": 0.5518328646402083, "learning_rate": 3.3393815802123606e-05, "loss": 1.2342, "step": 420 }, { "epoch": 1.7044534412955465, "grad_norm": 0.4705465666583439, "learning_rate": 3.335176280432308e-05, "loss": 1.249, "step": 421 }, { "epoch": 1.708502024291498, "grad_norm": 0.4289126959312047, "learning_rate": 3.330960304618295e-05, "loss": 1.2726, "step": 422 }, { "epoch": 1.7125506072874495, "grad_norm": 0.6491926538669188, "learning_rate": 3.326733686481153e-05, "loss": 1.2861, "step": 423 }, { "epoch": 1.7165991902834008, "grad_norm": 0.4307520428323331, "learning_rate": 3.3224964598168084e-05, "loss": 1.2515, "step": 424 }, { "epoch": 1.7206477732793521, "grad_norm": 0.5054263884837367, "learning_rate": 3.318248658506012e-05, "loss": 1.2706, "step": 425 }, { "epoch": 1.7246963562753037, "grad_norm": 0.5237588864011985, "learning_rate": 3.313990316514069e-05, "loss": 1.2699, "step": 426 }, { "epoch": 1.728744939271255, "grad_norm": 0.43863326660900925, "learning_rate": 3.309721467890571e-05, "loss": 1.2671, "step": 427 }, { "epoch": 1.7327935222672064, "grad_norm": 0.5013312026828941, "learning_rate": 3.305442146769115e-05, "loss": 1.2376, "step": 428 }, { "epoch": 1.736842105263158, "grad_norm": 0.36717066110960467, "learning_rate": 3.30115238736704e-05, "loss": 1.2361, "step": 429 }, { "epoch": 1.7408906882591093, "grad_norm": 0.38804830948672525, "learning_rate": 3.296852223985148e-05, "loss": 1.2681, "step": 430 }, { "epoch": 1.7449392712550607, "grad_norm": 0.4650022973413087, "learning_rate": 3.2925416910074315e-05, "loss": 1.2389, "step": 431 }, { "epoch": 1.7489878542510122, "grad_norm": 0.35788341344242086, "learning_rate": 3.288220822900796e-05, "loss": 1.2569, "step": 432 }, { "epoch": 1.7530364372469636, "grad_norm": 0.42462460297981025, "learning_rate": 3.283889654214788e-05, "loss": 1.2807, "step": 433 }, { "epoch": 1.757085020242915, "grad_norm": 0.39667602866398344, "learning_rate": 3.279548219581317e-05, "loss": 1.2737, "step": 434 }, { "epoch": 1.7611336032388665, "grad_norm": 0.4145879771804451, "learning_rate": 3.275196553714379e-05, "loss": 1.2533, "step": 435 }, { "epoch": 1.7651821862348178, "grad_norm": 0.34758168614720053, "learning_rate": 3.270834691409778e-05, "loss": 1.2669, "step": 436 }, { "epoch": 1.7692307692307692, "grad_norm": 0.37203172091627346, "learning_rate": 3.266462667544849e-05, "loss": 1.2616, "step": 437 }, { "epoch": 1.7732793522267207, "grad_norm": 0.4263704418974159, "learning_rate": 3.262080517078178e-05, "loss": 1.2604, "step": 438 }, { "epoch": 1.777327935222672, "grad_norm": 0.4020677520581868, "learning_rate": 3.257688275049323e-05, "loss": 1.2423, "step": 439 }, { "epoch": 1.7813765182186234, "grad_norm": 0.41127483513574525, "learning_rate": 3.253285976578535e-05, "loss": 1.2612, "step": 440 }, { "epoch": 1.785425101214575, "grad_norm": 0.3523365659393506, "learning_rate": 3.2488736568664756e-05, "loss": 1.2403, "step": 441 }, { "epoch": 1.7894736842105263, "grad_norm": 0.449863701795312, "learning_rate": 3.244451351193935e-05, "loss": 1.2522, "step": 442 }, { "epoch": 1.7935222672064777, "grad_norm": 0.4029470068237894, "learning_rate": 3.240019094921551e-05, "loss": 1.2388, "step": 443 }, { "epoch": 1.7975708502024292, "grad_norm": 0.4890198064842675, "learning_rate": 3.235576923489527e-05, "loss": 1.2407, "step": 444 }, { "epoch": 1.8016194331983806, "grad_norm": 0.3634842814902805, "learning_rate": 3.2311248724173476e-05, "loss": 1.2626, "step": 445 }, { "epoch": 1.805668016194332, "grad_norm": 0.38796252489684646, "learning_rate": 3.226662977303494e-05, "loss": 1.2463, "step": 446 }, { "epoch": 1.8097165991902835, "grad_norm": 0.4405477568235973, "learning_rate": 3.2221912738251626e-05, "loss": 1.2703, "step": 447 }, { "epoch": 1.8137651821862348, "grad_norm": 0.4864781939958209, "learning_rate": 3.2177097977379736e-05, "loss": 1.2869, "step": 448 }, { "epoch": 1.8178137651821862, "grad_norm": 0.47876643286145515, "learning_rate": 3.21321858487569e-05, "loss": 1.2968, "step": 449 }, { "epoch": 1.8218623481781377, "grad_norm": 0.4744048538647224, "learning_rate": 3.208717671149931e-05, "loss": 1.2553, "step": 450 }, { "epoch": 1.825910931174089, "grad_norm": 0.4221194516718018, "learning_rate": 3.204207092549882e-05, "loss": 1.2678, "step": 451 }, { "epoch": 1.8299595141700404, "grad_norm": 0.4618369696434002, "learning_rate": 3.19968688514201e-05, "loss": 1.2659, "step": 452 }, { "epoch": 1.834008097165992, "grad_norm": 0.473184916525026, "learning_rate": 3.195157085069774e-05, "loss": 1.2668, "step": 453 }, { "epoch": 1.8380566801619433, "grad_norm": 0.3752731250394866, "learning_rate": 3.190617728553332e-05, "loss": 1.2523, "step": 454 }, { "epoch": 1.8421052631578947, "grad_norm": 0.5197622023759567, "learning_rate": 3.1860688518892606e-05, "loss": 1.2314, "step": 455 }, { "epoch": 1.8461538461538463, "grad_norm": 0.41999666432384225, "learning_rate": 3.181510491450254e-05, "loss": 1.2478, "step": 456 }, { "epoch": 1.8502024291497976, "grad_norm": 0.3972974586868983, "learning_rate": 3.176942683684842e-05, "loss": 1.2377, "step": 457 }, { "epoch": 1.854251012145749, "grad_norm": 0.45545519307440857, "learning_rate": 3.1723654651170934e-05, "loss": 1.2496, "step": 458 }, { "epoch": 1.8582995951417005, "grad_norm": 0.4231459837735363, "learning_rate": 3.167778872346327e-05, "loss": 1.2591, "step": 459 }, { "epoch": 1.8623481781376519, "grad_norm": 0.443010355088527, "learning_rate": 3.163182942046815e-05, "loss": 1.2392, "step": 460 }, { "epoch": 1.8663967611336032, "grad_norm": 0.44779572939907664, "learning_rate": 3.158577710967494e-05, "loss": 1.2547, "step": 461 }, { "epoch": 1.8704453441295548, "grad_norm": 0.490549315827022, "learning_rate": 3.153963215931669e-05, "loss": 1.2252, "step": 462 }, { "epoch": 1.874493927125506, "grad_norm": 0.3872133613827876, "learning_rate": 3.14933949383672e-05, "loss": 1.2669, "step": 463 }, { "epoch": 1.8785425101214575, "grad_norm": 0.4472571958612494, "learning_rate": 3.144706581653805e-05, "loss": 1.2502, "step": 464 }, { "epoch": 1.882591093117409, "grad_norm": 0.42570521399017586, "learning_rate": 3.140064516427566e-05, "loss": 1.2721, "step": 465 }, { "epoch": 1.8866396761133604, "grad_norm": 0.46511866686022224, "learning_rate": 3.135413335275833e-05, "loss": 1.2602, "step": 466 }, { "epoch": 1.8906882591093117, "grad_norm": 0.4487806128555255, "learning_rate": 3.130753075389327e-05, "loss": 1.2135, "step": 467 }, { "epoch": 1.8947368421052633, "grad_norm": 0.4873170095921315, "learning_rate": 3.1260837740313625e-05, "loss": 1.2823, "step": 468 }, { "epoch": 1.8987854251012146, "grad_norm": 0.4636461992753893, "learning_rate": 3.121405468537547e-05, "loss": 1.2307, "step": 469 }, { "epoch": 1.902834008097166, "grad_norm": 0.41654941962265457, "learning_rate": 3.116718196315488e-05, "loss": 1.249, "step": 470 }, { "epoch": 1.9068825910931175, "grad_norm": 0.4883857163165901, "learning_rate": 3.1120219948444894e-05, "loss": 1.2947, "step": 471 }, { "epoch": 1.9109311740890689, "grad_norm": 0.49486282838578444, "learning_rate": 3.107316901675252e-05, "loss": 1.2199, "step": 472 }, { "epoch": 1.9149797570850202, "grad_norm": 0.37934001541571394, "learning_rate": 3.1026029544295745e-05, "loss": 1.2919, "step": 473 }, { "epoch": 1.9190283400809718, "grad_norm": 0.42297136530107843, "learning_rate": 3.097880190800057e-05, "loss": 1.2614, "step": 474 }, { "epoch": 1.9230769230769231, "grad_norm": 0.3957961098817012, "learning_rate": 3.093148648549788e-05, "loss": 1.2206, "step": 475 }, { "epoch": 1.9271255060728745, "grad_norm": 0.4914486826524899, "learning_rate": 3.088408365512055e-05, "loss": 1.2473, "step": 476 }, { "epoch": 1.931174089068826, "grad_norm": 0.404584422193593, "learning_rate": 3.083659379590034e-05, "loss": 1.2833, "step": 477 }, { "epoch": 1.9352226720647774, "grad_norm": 0.47445304263869503, "learning_rate": 3.0789017287564913e-05, "loss": 1.2165, "step": 478 }, { "epoch": 1.9392712550607287, "grad_norm": 0.4338205345367263, "learning_rate": 3.074135451053475e-05, "loss": 1.2274, "step": 479 }, { "epoch": 1.9433198380566803, "grad_norm": 0.5178177595614323, "learning_rate": 3.069360584592015e-05, "loss": 1.2701, "step": 480 }, { "epoch": 1.9473684210526314, "grad_norm": 0.4492147637335455, "learning_rate": 3.064577167551816e-05, "loss": 1.2464, "step": 481 }, { "epoch": 1.951417004048583, "grad_norm": 0.4081504525972302, "learning_rate": 3.059785238180953e-05, "loss": 1.2848, "step": 482 }, { "epoch": 1.9554655870445345, "grad_norm": 0.42297769511579225, "learning_rate": 3.054984834795566e-05, "loss": 1.2348, "step": 483 }, { "epoch": 1.9595141700404857, "grad_norm": 0.4920485235841864, "learning_rate": 3.0501759957795537e-05, "loss": 1.2533, "step": 484 }, { "epoch": 1.9635627530364372, "grad_norm": 0.49260078863202994, "learning_rate": 3.0453587595842627e-05, "loss": 1.2621, "step": 485 }, { "epoch": 1.9676113360323888, "grad_norm": 0.39742251798509404, "learning_rate": 3.0405331647281856e-05, "loss": 1.254, "step": 486 }, { "epoch": 1.97165991902834, "grad_norm": 0.4503180590550873, "learning_rate": 3.0356992497966508e-05, "loss": 1.2849, "step": 487 }, { "epoch": 1.9757085020242915, "grad_norm": 0.3969937287273158, "learning_rate": 3.0308570534415137e-05, "loss": 1.2101, "step": 488 }, { "epoch": 1.979757085020243, "grad_norm": 0.42205913606849876, "learning_rate": 3.0260066143808467e-05, "loss": 1.251, "step": 489 }, { "epoch": 1.9838056680161942, "grad_norm": 0.4686960482888879, "learning_rate": 3.021147971398632e-05, "loss": 1.2446, "step": 490 }, { "epoch": 1.9878542510121457, "grad_norm": 0.49624664891395964, "learning_rate": 3.0162811633444478e-05, "loss": 1.2143, "step": 491 }, { "epoch": 1.9919028340080973, "grad_norm": 0.5312168250749583, "learning_rate": 3.0114062291331635e-05, "loss": 1.2538, "step": 492 }, { "epoch": 1.9959514170040484, "grad_norm": 0.5285673354927181, "learning_rate": 3.0065232077446217e-05, "loss": 1.2494, "step": 493 }, { "epoch": 2.0, "grad_norm": 0.4836241342247421, "learning_rate": 3.001632138223332e-05, "loss": 1.2275, "step": 494 }, { "epoch": 2.0040485829959516, "grad_norm": 0.6215343868367238, "learning_rate": 2.9967330596781565e-05, "loss": 1.2015, "step": 495 }, { "epoch": 2.0080971659919027, "grad_norm": 0.5656503629552208, "learning_rate": 2.9918260112819952e-05, "loss": 1.2102, "step": 496 }, { "epoch": 2.0121457489878543, "grad_norm": 0.5518940416290714, "learning_rate": 2.9869110322714778e-05, "loss": 1.2014, "step": 497 }, { "epoch": 2.016194331983806, "grad_norm": 0.5419264635893619, "learning_rate": 2.9819881619466447e-05, "loss": 1.2027, "step": 498 }, { "epoch": 2.020242914979757, "grad_norm": 0.429661590143475, "learning_rate": 2.9770574396706364e-05, "loss": 1.162, "step": 499 }, { "epoch": 2.0242914979757085, "grad_norm": 0.5294708687901519, "learning_rate": 2.972118904869376e-05, "loss": 1.2342, "step": 500 }, { "epoch": 2.02834008097166, "grad_norm": 0.49979737133300467, "learning_rate": 2.9671725970312563e-05, "loss": 1.1858, "step": 501 }, { "epoch": 2.032388663967611, "grad_norm": 0.4569531215218518, "learning_rate": 2.9622185557068238e-05, "loss": 1.2097, "step": 502 }, { "epoch": 2.0364372469635628, "grad_norm": 0.5572386621935732, "learning_rate": 2.95725682050846e-05, "loss": 1.212, "step": 503 }, { "epoch": 2.0404858299595143, "grad_norm": 0.5035130706522456, "learning_rate": 2.9522874311100684e-05, "loss": 1.2237, "step": 504 }, { "epoch": 2.0445344129554655, "grad_norm": 0.5375687140693954, "learning_rate": 2.9473104272467526e-05, "loss": 1.1635, "step": 505 }, { "epoch": 2.048582995951417, "grad_norm": 0.43398928408472626, "learning_rate": 2.942325848714505e-05, "loss": 1.191, "step": 506 }, { "epoch": 2.0526315789473686, "grad_norm": 0.5033874390372168, "learning_rate": 2.9373337353698804e-05, "loss": 1.1842, "step": 507 }, { "epoch": 2.0566801619433197, "grad_norm": 0.5088398485985043, "learning_rate": 2.932334127129686e-05, "loss": 1.2177, "step": 508 }, { "epoch": 2.0607287449392713, "grad_norm": 0.44184214092200913, "learning_rate": 2.9273270639706547e-05, "loss": 1.1613, "step": 509 }, { "epoch": 2.064777327935223, "grad_norm": 0.4916831393973544, "learning_rate": 2.922312585929131e-05, "loss": 1.2206, "step": 510 }, { "epoch": 2.068825910931174, "grad_norm": 0.41008153975743294, "learning_rate": 2.9172907331007478e-05, "loss": 1.2109, "step": 511 }, { "epoch": 2.0728744939271255, "grad_norm": 0.5349025006617955, "learning_rate": 2.9122615456401053e-05, "loss": 1.2287, "step": 512 }, { "epoch": 2.076923076923077, "grad_norm": 0.41678888119154994, "learning_rate": 2.9072250637604535e-05, "loss": 1.2078, "step": 513 }, { "epoch": 2.080971659919028, "grad_norm": 0.5279982851922177, "learning_rate": 2.9021813277333667e-05, "loss": 1.1754, "step": 514 }, { "epoch": 2.08502024291498, "grad_norm": 0.4515460443018123, "learning_rate": 2.8971303778884244e-05, "loss": 1.1895, "step": 515 }, { "epoch": 2.0890688259109313, "grad_norm": 0.5005355761031678, "learning_rate": 2.8920722546128863e-05, "loss": 1.2016, "step": 516 }, { "epoch": 2.0931174089068825, "grad_norm": 0.4803050441872652, "learning_rate": 2.887006998351372e-05, "loss": 1.1741, "step": 517 }, { "epoch": 2.097165991902834, "grad_norm": 0.4716496369437387, "learning_rate": 2.881934649605535e-05, "loss": 1.1823, "step": 518 }, { "epoch": 2.1012145748987856, "grad_norm": 0.45058247251275874, "learning_rate": 2.8768552489337408e-05, "loss": 1.2164, "step": 519 }, { "epoch": 2.1052631578947367, "grad_norm": 0.45110488688946104, "learning_rate": 2.8717688369507425e-05, "loss": 1.2098, "step": 520 }, { "epoch": 2.1093117408906883, "grad_norm": 0.3713558472136903, "learning_rate": 2.8666754543273535e-05, "loss": 1.1977, "step": 521 }, { "epoch": 2.11336032388664, "grad_norm": 0.39510354880319043, "learning_rate": 2.8615751417901273e-05, "loss": 1.2116, "step": 522 }, { "epoch": 2.117408906882591, "grad_norm": 0.39019577156917545, "learning_rate": 2.856467940121025e-05, "loss": 1.2169, "step": 523 }, { "epoch": 2.1214574898785425, "grad_norm": 0.40768670936912443, "learning_rate": 2.8513538901570964e-05, "loss": 1.1907, "step": 524 }, { "epoch": 2.125506072874494, "grad_norm": 0.3729652909940451, "learning_rate": 2.846233032790149e-05, "loss": 1.2107, "step": 525 }, { "epoch": 2.1295546558704452, "grad_norm": 0.40421036367735164, "learning_rate": 2.84110540896642e-05, "loss": 1.2051, "step": 526 }, { "epoch": 2.133603238866397, "grad_norm": 0.3514257454140682, "learning_rate": 2.8359710596862555e-05, "loss": 1.1694, "step": 527 }, { "epoch": 2.1376518218623484, "grad_norm": 0.41382225041060783, "learning_rate": 2.8308300260037734e-05, "loss": 1.1654, "step": 528 }, { "epoch": 2.1417004048582995, "grad_norm": 0.4849615729110766, "learning_rate": 2.8256823490265424e-05, "loss": 1.2069, "step": 529 }, { "epoch": 2.145748987854251, "grad_norm": 0.3749285593488319, "learning_rate": 2.8205280699152515e-05, "loss": 1.2188, "step": 530 }, { "epoch": 2.1497975708502026, "grad_norm": 0.3758672504024422, "learning_rate": 2.8153672298833777e-05, "loss": 1.2317, "step": 531 }, { "epoch": 2.1538461538461537, "grad_norm": 0.32168300816991174, "learning_rate": 2.8101998701968615e-05, "loss": 1.195, "step": 532 }, { "epoch": 2.1578947368421053, "grad_norm": 0.36589969827873703, "learning_rate": 2.805026032173773e-05, "loss": 1.1655, "step": 533 }, { "epoch": 2.161943319838057, "grad_norm": 0.3537410046809915, "learning_rate": 2.7998457571839832e-05, "loss": 1.1919, "step": 534 }, { "epoch": 2.165991902834008, "grad_norm": 0.336662128460781, "learning_rate": 2.7946590866488322e-05, "loss": 1.2, "step": 535 }, { "epoch": 2.1700404858299596, "grad_norm": 0.35606091709611143, "learning_rate": 2.7894660620408e-05, "loss": 1.2115, "step": 536 }, { "epoch": 2.174089068825911, "grad_norm": 0.3188853711219213, "learning_rate": 2.784266724883173e-05, "loss": 1.2091, "step": 537 }, { "epoch": 2.1781376518218623, "grad_norm": 0.3984573107586057, "learning_rate": 2.7790611167497128e-05, "loss": 1.2231, "step": 538 }, { "epoch": 2.182186234817814, "grad_norm": 0.3692112607046752, "learning_rate": 2.7738492792643224e-05, "loss": 1.2202, "step": 539 }, { "epoch": 2.1862348178137654, "grad_norm": 0.37072415462308067, "learning_rate": 2.768631254100716e-05, "loss": 1.2118, "step": 540 }, { "epoch": 2.1902834008097165, "grad_norm": 0.3383905968070152, "learning_rate": 2.7634070829820836e-05, "loss": 1.2269, "step": 541 }, { "epoch": 2.194331983805668, "grad_norm": 0.4037097239241696, "learning_rate": 2.7581768076807592e-05, "loss": 1.1843, "step": 542 }, { "epoch": 2.1983805668016196, "grad_norm": 0.4214979689042628, "learning_rate": 2.7529404700178832e-05, "loss": 1.1967, "step": 543 }, { "epoch": 2.2024291497975708, "grad_norm": 0.4197371865099488, "learning_rate": 2.7476981118630735e-05, "loss": 1.1988, "step": 544 }, { "epoch": 2.2064777327935223, "grad_norm": 0.32353242913476665, "learning_rate": 2.742449775134085e-05, "loss": 1.1775, "step": 545 }, { "epoch": 2.2105263157894735, "grad_norm": 0.36907250321861224, "learning_rate": 2.7371955017964788e-05, "loss": 1.2126, "step": 546 }, { "epoch": 2.214574898785425, "grad_norm": 0.3766895454788538, "learning_rate": 2.7319353338632845e-05, "loss": 1.2154, "step": 547 }, { "epoch": 2.2186234817813766, "grad_norm": 0.41484373099855587, "learning_rate": 2.7266693133946645e-05, "loss": 1.2129, "step": 548 }, { "epoch": 2.2226720647773277, "grad_norm": 0.38140863104457, "learning_rate": 2.7213974824975785e-05, "loss": 1.1588, "step": 549 }, { "epoch": 2.2267206477732793, "grad_norm": 0.38553334436991216, "learning_rate": 2.7161198833254464e-05, "loss": 1.2015, "step": 550 }, { "epoch": 2.230769230769231, "grad_norm": 0.3966588792560965, "learning_rate": 2.7108365580778095e-05, "loss": 1.216, "step": 551 }, { "epoch": 2.234817813765182, "grad_norm": 0.351278919023911, "learning_rate": 2.705547548999996e-05, "loss": 1.2163, "step": 552 }, { "epoch": 2.2388663967611335, "grad_norm": 0.3946501894619945, "learning_rate": 2.7002528983827817e-05, "loss": 1.2154, "step": 553 }, { "epoch": 2.242914979757085, "grad_norm": 0.38119161380996636, "learning_rate": 2.6949526485620517e-05, "loss": 1.2079, "step": 554 }, { "epoch": 2.246963562753036, "grad_norm": 0.45719104007353567, "learning_rate": 2.6896468419184623e-05, "loss": 1.212, "step": 555 }, { "epoch": 2.251012145748988, "grad_norm": 0.3671330608649302, "learning_rate": 2.6843355208771024e-05, "loss": 1.2125, "step": 556 }, { "epoch": 2.2550607287449393, "grad_norm": 0.45833732576268127, "learning_rate": 2.6790187279071536e-05, "loss": 1.2144, "step": 557 }, { "epoch": 2.2591093117408905, "grad_norm": 0.4313840142172795, "learning_rate": 2.67369650552155e-05, "loss": 1.1922, "step": 558 }, { "epoch": 2.263157894736842, "grad_norm": 0.42219645718382554, "learning_rate": 2.6683688962766407e-05, "loss": 1.1924, "step": 559 }, { "epoch": 2.2672064777327936, "grad_norm": 0.4362401222047061, "learning_rate": 2.6630359427718468e-05, "loss": 1.1971, "step": 560 }, { "epoch": 2.2712550607287447, "grad_norm": 0.316569277901333, "learning_rate": 2.6576976876493225e-05, "loss": 1.1913, "step": 561 }, { "epoch": 2.2753036437246963, "grad_norm": 0.414826663605554, "learning_rate": 2.652354173593614e-05, "loss": 1.173, "step": 562 }, { "epoch": 2.279352226720648, "grad_norm": 0.3324384402819273, "learning_rate": 2.647005443331317e-05, "loss": 1.2029, "step": 563 }, { "epoch": 2.283400809716599, "grad_norm": 0.3384485383874962, "learning_rate": 2.6416515396307354e-05, "loss": 1.222, "step": 564 }, { "epoch": 2.2874493927125505, "grad_norm": 0.3777888954905764, "learning_rate": 2.636292505301542e-05, "loss": 1.1774, "step": 565 }, { "epoch": 2.291497975708502, "grad_norm": 0.31895440750076315, "learning_rate": 2.630928383194431e-05, "loss": 1.2044, "step": 566 }, { "epoch": 2.2955465587044532, "grad_norm": 0.39067871126708653, "learning_rate": 2.625559216200781e-05, "loss": 1.2182, "step": 567 }, { "epoch": 2.299595141700405, "grad_norm": 0.3771773068043027, "learning_rate": 2.620185047252308e-05, "loss": 1.1805, "step": 568 }, { "epoch": 2.3036437246963564, "grad_norm": 0.4568395862163711, "learning_rate": 2.614805919320723e-05, "loss": 1.24, "step": 569 }, { "epoch": 2.3076923076923075, "grad_norm": 0.37364116092761585, "learning_rate": 2.6094218754173895e-05, "loss": 1.1737, "step": 570 }, { "epoch": 2.311740890688259, "grad_norm": 0.3742898315620629, "learning_rate": 2.60403295859298e-05, "loss": 1.22, "step": 571 }, { "epoch": 2.3157894736842106, "grad_norm": 0.4204641767912203, "learning_rate": 2.5986392119371297e-05, "loss": 1.1697, "step": 572 }, { "epoch": 2.3198380566801617, "grad_norm": 0.33090300725592187, "learning_rate": 2.5932406785780928e-05, "loss": 1.2281, "step": 573 }, { "epoch": 2.3238866396761133, "grad_norm": 0.4288836416004625, "learning_rate": 2.5878374016823987e-05, "loss": 1.2398, "step": 574 }, { "epoch": 2.327935222672065, "grad_norm": 0.3628818751213866, "learning_rate": 2.5824294244545045e-05, "loss": 1.1913, "step": 575 }, { "epoch": 2.331983805668016, "grad_norm": 0.38928754634615653, "learning_rate": 2.577016790136453e-05, "loss": 1.2042, "step": 576 }, { "epoch": 2.3360323886639676, "grad_norm": 0.3579287671185816, "learning_rate": 2.5715995420075225e-05, "loss": 1.1801, "step": 577 }, { "epoch": 2.340080971659919, "grad_norm": 0.4052158757242412, "learning_rate": 2.5661777233838864e-05, "loss": 1.2019, "step": 578 }, { "epoch": 2.3441295546558703, "grad_norm": 0.3357792028038485, "learning_rate": 2.5607513776182616e-05, "loss": 1.1944, "step": 579 }, { "epoch": 2.348178137651822, "grad_norm": 0.41928387698608827, "learning_rate": 2.5553205480995633e-05, "loss": 1.1634, "step": 580 }, { "epoch": 2.3522267206477734, "grad_norm": 0.36207017020272847, "learning_rate": 2.5498852782525604e-05, "loss": 1.1832, "step": 581 }, { "epoch": 2.3562753036437245, "grad_norm": 0.3829409072910727, "learning_rate": 2.5444456115375252e-05, "loss": 1.2103, "step": 582 }, { "epoch": 2.360323886639676, "grad_norm": 0.3827229235243023, "learning_rate": 2.539001591449889e-05, "loss": 1.2033, "step": 583 }, { "epoch": 2.3643724696356276, "grad_norm": 0.4350588227627273, "learning_rate": 2.53355326151989e-05, "loss": 1.2202, "step": 584 }, { "epoch": 2.3684210526315788, "grad_norm": 0.3716866741729946, "learning_rate": 2.5281006653122288e-05, "loss": 1.2187, "step": 585 }, { "epoch": 2.3724696356275303, "grad_norm": 0.43482299416850945, "learning_rate": 2.5226438464257217e-05, "loss": 1.1932, "step": 586 }, { "epoch": 2.376518218623482, "grad_norm": 0.3267547389586627, "learning_rate": 2.5171828484929447e-05, "loss": 1.1954, "step": 587 }, { "epoch": 2.380566801619433, "grad_norm": 0.39777814010003976, "learning_rate": 2.5117177151798934e-05, "loss": 1.1925, "step": 588 }, { "epoch": 2.3846153846153846, "grad_norm": 0.4112346303397014, "learning_rate": 2.506248490185627e-05, "loss": 1.2156, "step": 589 }, { "epoch": 2.388663967611336, "grad_norm": 0.3518771835377543, "learning_rate": 2.500775217241923e-05, "loss": 1.2327, "step": 590 }, { "epoch": 2.3927125506072873, "grad_norm": 0.4039590167596311, "learning_rate": 2.4952979401129266e-05, "loss": 1.2066, "step": 591 }, { "epoch": 2.396761133603239, "grad_norm": 0.409034333761468, "learning_rate": 2.4898167025948e-05, "loss": 1.2514, "step": 592 }, { "epoch": 2.4008097165991904, "grad_norm": 0.34382383883520823, "learning_rate": 2.4843315485153703e-05, "loss": 1.181, "step": 593 }, { "epoch": 2.4048582995951415, "grad_norm": 0.31149125302296843, "learning_rate": 2.4788425217337856e-05, "loss": 1.1861, "step": 594 }, { "epoch": 2.408906882591093, "grad_norm": 0.36718959906578874, "learning_rate": 2.4733496661401572e-05, "loss": 1.1991, "step": 595 }, { "epoch": 2.4129554655870447, "grad_norm": 0.29946777745003894, "learning_rate": 2.4678530256552114e-05, "loss": 1.206, "step": 596 }, { "epoch": 2.417004048582996, "grad_norm": 0.3843975896828274, "learning_rate": 2.46235264422994e-05, "loss": 1.1923, "step": 597 }, { "epoch": 2.4210526315789473, "grad_norm": 0.35753218398924064, "learning_rate": 2.4568485658452452e-05, "loss": 1.1947, "step": 598 }, { "epoch": 2.425101214574899, "grad_norm": 0.3998218661640942, "learning_rate": 2.451340834511592e-05, "loss": 1.182, "step": 599 }, { "epoch": 2.42914979757085, "grad_norm": 0.36609603941096375, "learning_rate": 2.4458294942686528e-05, "loss": 1.1976, "step": 600 }, { "epoch": 2.4331983805668016, "grad_norm": 0.37900672548696385, "learning_rate": 2.440314589184958e-05, "loss": 1.2098, "step": 601 }, { "epoch": 2.437246963562753, "grad_norm": 0.42186652522950785, "learning_rate": 2.434796163357541e-05, "loss": 1.2286, "step": 602 }, { "epoch": 2.4412955465587043, "grad_norm": 0.3836536110179635, "learning_rate": 2.429274260911588e-05, "loss": 1.2229, "step": 603 }, { "epoch": 2.445344129554656, "grad_norm": 0.34779855998576614, "learning_rate": 2.423748926000084e-05, "loss": 1.1682, "step": 604 }, { "epoch": 2.4493927125506074, "grad_norm": 0.3450881215978924, "learning_rate": 2.418220202803459e-05, "loss": 1.2063, "step": 605 }, { "epoch": 2.4534412955465585, "grad_norm": 0.3379601810498686, "learning_rate": 2.412688135529237e-05, "loss": 1.1685, "step": 606 }, { "epoch": 2.45748987854251, "grad_norm": 0.36460672185053317, "learning_rate": 2.4071527684116807e-05, "loss": 1.2062, "step": 607 }, { "epoch": 2.4615384615384617, "grad_norm": 0.30170440561039413, "learning_rate": 2.4016141457114372e-05, "loss": 1.191, "step": 608 }, { "epoch": 2.465587044534413, "grad_norm": 0.38598946165968634, "learning_rate": 2.396072311715187e-05, "loss": 1.209, "step": 609 }, { "epoch": 2.4696356275303644, "grad_norm": 0.3113512794870838, "learning_rate": 2.3905273107352863e-05, "loss": 1.2398, "step": 610 }, { "epoch": 2.473684210526316, "grad_norm": 0.34800563686079145, "learning_rate": 2.3849791871094157e-05, "loss": 1.2118, "step": 611 }, { "epoch": 2.477732793522267, "grad_norm": 0.32476430443578813, "learning_rate": 2.379427985200223e-05, "loss": 1.1786, "step": 612 }, { "epoch": 2.4817813765182186, "grad_norm": 0.40300663544578635, "learning_rate": 2.373873749394972e-05, "loss": 1.2205, "step": 613 }, { "epoch": 2.48582995951417, "grad_norm": 0.35977396739628387, "learning_rate": 2.3683165241051836e-05, "loss": 1.1584, "step": 614 }, { "epoch": 2.4898785425101213, "grad_norm": 0.35731263358591525, "learning_rate": 2.3627563537662823e-05, "loss": 1.1981, "step": 615 }, { "epoch": 2.493927125506073, "grad_norm": 0.3496472319831367, "learning_rate": 2.3571932828372433e-05, "loss": 1.1789, "step": 616 }, { "epoch": 2.4979757085020244, "grad_norm": 0.33384233313077205, "learning_rate": 2.351627355800233e-05, "loss": 1.2021, "step": 617 }, { "epoch": 2.5020242914979756, "grad_norm": 0.36397663614379355, "learning_rate": 2.346058617160256e-05, "loss": 1.2073, "step": 618 }, { "epoch": 2.506072874493927, "grad_norm": 0.3529126188727639, "learning_rate": 2.3404871114447976e-05, "loss": 1.2162, "step": 619 }, { "epoch": 2.5101214574898787, "grad_norm": 0.32197875010483545, "learning_rate": 2.334912883203469e-05, "loss": 1.2131, "step": 620 }, { "epoch": 2.51417004048583, "grad_norm": 0.3515826697150008, "learning_rate": 2.3293359770076505e-05, "loss": 1.2202, "step": 621 }, { "epoch": 2.5182186234817814, "grad_norm": 0.30434218229814997, "learning_rate": 2.323756437450136e-05, "loss": 1.2219, "step": 622 }, { "epoch": 2.522267206477733, "grad_norm": 0.34078544138019384, "learning_rate": 2.3181743091447754e-05, "loss": 1.1812, "step": 623 }, { "epoch": 2.526315789473684, "grad_norm": 0.33117645271665075, "learning_rate": 2.3125896367261164e-05, "loss": 1.2005, "step": 624 }, { "epoch": 2.5303643724696356, "grad_norm": 0.3465613136661275, "learning_rate": 2.307002464849052e-05, "loss": 1.2028, "step": 625 }, { "epoch": 2.534412955465587, "grad_norm": 0.37778894488607556, "learning_rate": 2.30141283818846e-05, "loss": 1.2298, "step": 626 }, { "epoch": 2.5384615384615383, "grad_norm": 0.29957244580460646, "learning_rate": 2.2958208014388462e-05, "loss": 1.1767, "step": 627 }, { "epoch": 2.54251012145749, "grad_norm": 0.3536925796374956, "learning_rate": 2.2902263993139857e-05, "loss": 1.2011, "step": 628 }, { "epoch": 2.5465587044534415, "grad_norm": 0.32559297834156675, "learning_rate": 2.2846296765465708e-05, "loss": 1.1891, "step": 629 }, { "epoch": 2.5506072874493926, "grad_norm": 0.3503067848009514, "learning_rate": 2.2790306778878465e-05, "loss": 1.1811, "step": 630 }, { "epoch": 2.554655870445344, "grad_norm": 0.29763124194557994, "learning_rate": 2.273429448107257e-05, "loss": 1.1751, "step": 631 }, { "epoch": 2.5587044534412957, "grad_norm": 0.3021453207925281, "learning_rate": 2.2678260319920868e-05, "loss": 1.2042, "step": 632 }, { "epoch": 2.562753036437247, "grad_norm": 0.31052634243485516, "learning_rate": 2.262220474347102e-05, "loss": 1.1694, "step": 633 }, { "epoch": 2.5668016194331984, "grad_norm": 0.3215984405385578, "learning_rate": 2.2566128199941918e-05, "loss": 1.2192, "step": 634 }, { "epoch": 2.57085020242915, "grad_norm": 0.32188976138582526, "learning_rate": 2.2510031137720104e-05, "loss": 1.1912, "step": 635 }, { "epoch": 2.574898785425101, "grad_norm": 0.3449580930524241, "learning_rate": 2.2453914005356206e-05, "loss": 1.1909, "step": 636 }, { "epoch": 2.5789473684210527, "grad_norm": 0.3109595619690715, "learning_rate": 2.2397777251561302e-05, "loss": 1.1843, "step": 637 }, { "epoch": 2.582995951417004, "grad_norm": 0.3448608728037004, "learning_rate": 2.2341621325203393e-05, "loss": 1.2117, "step": 638 }, { "epoch": 2.5870445344129553, "grad_norm": 0.37217111185261276, "learning_rate": 2.2285446675303764e-05, "loss": 1.1935, "step": 639 }, { "epoch": 2.591093117408907, "grad_norm": 0.31743849234007976, "learning_rate": 2.2229253751033423e-05, "loss": 1.1684, "step": 640 }, { "epoch": 2.5951417004048585, "grad_norm": 0.4388179250229573, "learning_rate": 2.2173043001709492e-05, "loss": 1.1859, "step": 641 }, { "epoch": 2.5991902834008096, "grad_norm": 0.3675799823661077, "learning_rate": 2.2116814876791627e-05, "loss": 1.2047, "step": 642 }, { "epoch": 2.603238866396761, "grad_norm": 0.39863643005696037, "learning_rate": 2.2060569825878413e-05, "loss": 1.1741, "step": 643 }, { "epoch": 2.6072874493927127, "grad_norm": 0.30919976350488043, "learning_rate": 2.2004308298703777e-05, "loss": 1.192, "step": 644 }, { "epoch": 2.611336032388664, "grad_norm": 0.35005665238533135, "learning_rate": 2.1948030745133396e-05, "loss": 1.2029, "step": 645 }, { "epoch": 2.6153846153846154, "grad_norm": 0.44611062644276905, "learning_rate": 2.1891737615161083e-05, "loss": 1.1825, "step": 646 }, { "epoch": 2.619433198380567, "grad_norm": 0.3395130394978325, "learning_rate": 2.1835429358905218e-05, "loss": 1.231, "step": 647 }, { "epoch": 2.623481781376518, "grad_norm": 0.39966390200945673, "learning_rate": 2.17791064266051e-05, "loss": 1.2043, "step": 648 }, { "epoch": 2.6275303643724697, "grad_norm": 0.3376126266336765, "learning_rate": 2.172276926861741e-05, "loss": 1.2384, "step": 649 }, { "epoch": 2.6315789473684212, "grad_norm": 0.28534418999967204, "learning_rate": 2.166641833541255e-05, "loss": 1.184, "step": 650 }, { "epoch": 2.6356275303643724, "grad_norm": 0.3384232238935232, "learning_rate": 2.161005407757109e-05, "loss": 1.199, "step": 651 }, { "epoch": 2.639676113360324, "grad_norm": 0.29594905950867556, "learning_rate": 2.155367694578013e-05, "loss": 1.2231, "step": 652 }, { "epoch": 2.6437246963562755, "grad_norm": 0.3122842976814226, "learning_rate": 2.1497287390829712e-05, "loss": 1.2113, "step": 653 }, { "epoch": 2.6477732793522266, "grad_norm": 0.34249471918240676, "learning_rate": 2.1440885863609208e-05, "loss": 1.2042, "step": 654 }, { "epoch": 2.651821862348178, "grad_norm": 0.3877558140946641, "learning_rate": 2.1384472815103737e-05, "loss": 1.201, "step": 655 }, { "epoch": 2.6558704453441297, "grad_norm": 0.3053839337759665, "learning_rate": 2.1328048696390534e-05, "loss": 1.2619, "step": 656 }, { "epoch": 2.659919028340081, "grad_norm": 0.41892878457313126, "learning_rate": 2.1271613958635342e-05, "loss": 1.1739, "step": 657 }, { "epoch": 2.6639676113360324, "grad_norm": 0.32936142094331633, "learning_rate": 2.1215169053088825e-05, "loss": 1.1589, "step": 658 }, { "epoch": 2.668016194331984, "grad_norm": 0.383386256410733, "learning_rate": 2.1158714431082937e-05, "loss": 1.2269, "step": 659 }, { "epoch": 2.672064777327935, "grad_norm": 0.3768797023325218, "learning_rate": 2.110225054402733e-05, "loss": 1.1834, "step": 660 }, { "epoch": 2.6761133603238867, "grad_norm": 0.285340597422708, "learning_rate": 2.1045777843405747e-05, "loss": 1.217, "step": 661 }, { "epoch": 2.6801619433198383, "grad_norm": 0.37662504377950196, "learning_rate": 2.09892967807724e-05, "loss": 1.2372, "step": 662 }, { "epoch": 2.6842105263157894, "grad_norm": 0.34914057344379246, "learning_rate": 2.093280780774835e-05, "loss": 1.2094, "step": 663 }, { "epoch": 2.688259109311741, "grad_norm": 0.31063265340861196, "learning_rate": 2.087631137601793e-05, "loss": 1.2196, "step": 664 }, { "epoch": 2.6923076923076925, "grad_norm": 0.3615100448084465, "learning_rate": 2.0819807937325104e-05, "loss": 1.2041, "step": 665 }, { "epoch": 2.6963562753036436, "grad_norm": 0.31630146684883925, "learning_rate": 2.0763297943469847e-05, "loss": 1.1686, "step": 666 }, { "epoch": 2.700404858299595, "grad_norm": 0.31629635328441746, "learning_rate": 2.070678184630458e-05, "loss": 1.2016, "step": 667 }, { "epoch": 2.7044534412955468, "grad_norm": 0.32166499918738606, "learning_rate": 2.06502600977305e-05, "loss": 1.1629, "step": 668 }, { "epoch": 2.708502024291498, "grad_norm": 0.32126322389908024, "learning_rate": 2.0593733149694008e-05, "loss": 1.2316, "step": 669 }, { "epoch": 2.7125506072874495, "grad_norm": 0.3160443911992318, "learning_rate": 2.0537201454183074e-05, "loss": 1.2244, "step": 670 }, { "epoch": 2.716599190283401, "grad_norm": 0.29539716297871665, "learning_rate": 2.0480665463223626e-05, "loss": 1.1677, "step": 671 }, { "epoch": 2.720647773279352, "grad_norm": 0.2978761964296307, "learning_rate": 2.042412562887594e-05, "loss": 1.2005, "step": 672 }, { "epoch": 2.7246963562753037, "grad_norm": 0.34628972835021626, "learning_rate": 2.0367582403231033e-05, "loss": 1.2124, "step": 673 }, { "epoch": 2.7287449392712553, "grad_norm": 0.3023177375593249, "learning_rate": 2.0311036238407023e-05, "loss": 1.1865, "step": 674 }, { "epoch": 2.7327935222672064, "grad_norm": 0.3393651126287393, "learning_rate": 2.0254487586545534e-05, "loss": 1.2024, "step": 675 }, { "epoch": 2.736842105263158, "grad_norm": 0.3075234622346812, "learning_rate": 2.0197936899808088e-05, "loss": 1.1863, "step": 676 }, { "epoch": 2.7408906882591095, "grad_norm": 0.34771618897077655, "learning_rate": 2.0141384630372466e-05, "loss": 1.1877, "step": 677 }, { "epoch": 2.7449392712550607, "grad_norm": 0.29026940501354687, "learning_rate": 2.0084831230429106e-05, "loss": 1.1957, "step": 678 }, { "epoch": 2.748987854251012, "grad_norm": 0.3915924414144518, "learning_rate": 2.0028277152177492e-05, "loss": 1.1928, "step": 679 }, { "epoch": 2.753036437246964, "grad_norm": 0.36773829508989125, "learning_rate": 1.9971722847822518e-05, "loss": 1.1835, "step": 680 }, { "epoch": 2.757085020242915, "grad_norm": 0.3930682318934858, "learning_rate": 1.99151687695709e-05, "loss": 1.211, "step": 681 }, { "epoch": 2.7611336032388665, "grad_norm": 0.34931081146554804, "learning_rate": 1.9858615369627537e-05, "loss": 1.2067, "step": 682 }, { "epoch": 2.765182186234818, "grad_norm": 0.34062108633624144, "learning_rate": 1.9802063100191916e-05, "loss": 1.2033, "step": 683 }, { "epoch": 2.769230769230769, "grad_norm": 0.3582169423906155, "learning_rate": 1.974551241345447e-05, "loss": 1.1836, "step": 684 }, { "epoch": 2.7732793522267207, "grad_norm": 0.37376422107268303, "learning_rate": 1.9688963761592984e-05, "loss": 1.201, "step": 685 }, { "epoch": 2.7773279352226723, "grad_norm": 0.3358381227086621, "learning_rate": 1.963241759676897e-05, "loss": 1.2166, "step": 686 }, { "epoch": 2.7813765182186234, "grad_norm": 0.38231787470133666, "learning_rate": 1.9575874371124066e-05, "loss": 1.1991, "step": 687 }, { "epoch": 2.785425101214575, "grad_norm": 0.2892540072047962, "learning_rate": 1.951933453677638e-05, "loss": 1.2132, "step": 688 }, { "epoch": 2.7894736842105265, "grad_norm": 0.38519655491369953, "learning_rate": 1.9462798545816932e-05, "loss": 1.2135, "step": 689 }, { "epoch": 2.7935222672064777, "grad_norm": 0.29377981855931684, "learning_rate": 1.9406266850305996e-05, "loss": 1.2131, "step": 690 }, { "epoch": 2.7975708502024292, "grad_norm": 0.38098383584703166, "learning_rate": 1.9349739902269503e-05, "loss": 1.2174, "step": 691 }, { "epoch": 2.801619433198381, "grad_norm": 0.2902754120962442, "learning_rate": 1.9293218153695425e-05, "loss": 1.2012, "step": 692 }, { "epoch": 2.805668016194332, "grad_norm": 0.37743060690703395, "learning_rate": 1.9236702056530153e-05, "loss": 1.1862, "step": 693 }, { "epoch": 2.8097165991902835, "grad_norm": 0.3068813234923841, "learning_rate": 1.9180192062674907e-05, "loss": 1.2044, "step": 694 }, { "epoch": 2.813765182186235, "grad_norm": 0.4227010247579375, "learning_rate": 1.9123688623982076e-05, "loss": 1.2137, "step": 695 }, { "epoch": 2.817813765182186, "grad_norm": 0.3283118631083638, "learning_rate": 1.906719219225165e-05, "loss": 1.1859, "step": 696 }, { "epoch": 2.8218623481781377, "grad_norm": 0.34362059798196526, "learning_rate": 1.9010703219227603e-05, "loss": 1.1721, "step": 697 }, { "epoch": 2.8259109311740893, "grad_norm": 0.3696818843618871, "learning_rate": 1.8954222156594256e-05, "loss": 1.2087, "step": 698 }, { "epoch": 2.8299595141700404, "grad_norm": 0.31881329308533196, "learning_rate": 1.8897749455972673e-05, "loss": 1.219, "step": 699 }, { "epoch": 2.834008097165992, "grad_norm": 0.34066151069775147, "learning_rate": 1.884128556891707e-05, "loss": 1.1614, "step": 700 }, { "epoch": 2.8380566801619436, "grad_norm": 0.31842160933505537, "learning_rate": 1.878483094691119e-05, "loss": 1.1837, "step": 701 }, { "epoch": 2.8421052631578947, "grad_norm": 0.396425532044836, "learning_rate": 1.8728386041364664e-05, "loss": 1.2372, "step": 702 }, { "epoch": 2.8461538461538463, "grad_norm": 0.29368519192697246, "learning_rate": 1.867195130360947e-05, "loss": 1.1844, "step": 703 }, { "epoch": 2.850202429149798, "grad_norm": 0.3559536568764513, "learning_rate": 1.8615527184896263e-05, "loss": 1.2068, "step": 704 }, { "epoch": 2.854251012145749, "grad_norm": 0.3096597122163552, "learning_rate": 1.8559114136390795e-05, "loss": 1.1582, "step": 705 }, { "epoch": 2.8582995951417005, "grad_norm": 0.3156311416441029, "learning_rate": 1.8502712609170298e-05, "loss": 1.1953, "step": 706 }, { "epoch": 2.862348178137652, "grad_norm": 0.27781668457057745, "learning_rate": 1.8446323054219876e-05, "loss": 1.1575, "step": 707 }, { "epoch": 2.866396761133603, "grad_norm": 0.3784875087511227, "learning_rate": 1.838994592242891e-05, "loss": 1.2035, "step": 708 }, { "epoch": 2.8704453441295548, "grad_norm": 0.32119271032239755, "learning_rate": 1.8333581664587453e-05, "loss": 1.181, "step": 709 }, { "epoch": 2.8744939271255063, "grad_norm": 0.3268427696777026, "learning_rate": 1.8277230731382593e-05, "loss": 1.2111, "step": 710 }, { "epoch": 2.8785425101214575, "grad_norm": 0.31988044635590906, "learning_rate": 1.82208935733949e-05, "loss": 1.2003, "step": 711 }, { "epoch": 2.882591093117409, "grad_norm": 0.29589852618879714, "learning_rate": 1.8164570641094793e-05, "loss": 1.2006, "step": 712 }, { "epoch": 2.8866396761133606, "grad_norm": 0.32880437256030914, "learning_rate": 1.810826238483892e-05, "loss": 1.2254, "step": 713 }, { "epoch": 2.8906882591093117, "grad_norm": 0.2542384317855246, "learning_rate": 1.8051969254866608e-05, "loss": 1.2233, "step": 714 }, { "epoch": 2.8947368421052633, "grad_norm": 0.32145702011062094, "learning_rate": 1.7995691701296226e-05, "loss": 1.2501, "step": 715 }, { "epoch": 2.898785425101215, "grad_norm": 0.31501464658206224, "learning_rate": 1.7939430174121593e-05, "loss": 1.2279, "step": 716 }, { "epoch": 2.902834008097166, "grad_norm": 0.28597532427351974, "learning_rate": 1.788318512320838e-05, "loss": 1.1808, "step": 717 }, { "epoch": 2.9068825910931175, "grad_norm": 0.28043642620064, "learning_rate": 1.782695699829051e-05, "loss": 1.2059, "step": 718 }, { "epoch": 2.910931174089069, "grad_norm": 0.31576410940404825, "learning_rate": 1.7770746248966587e-05, "loss": 1.1921, "step": 719 }, { "epoch": 2.91497975708502, "grad_norm": 0.31915985392840185, "learning_rate": 1.7714553324696243e-05, "loss": 1.2257, "step": 720 }, { "epoch": 2.919028340080972, "grad_norm": 0.3186206470880149, "learning_rate": 1.7658378674796614e-05, "loss": 1.2017, "step": 721 }, { "epoch": 2.9230769230769234, "grad_norm": 0.30122596521271916, "learning_rate": 1.76022227484387e-05, "loss": 1.2127, "step": 722 }, { "epoch": 2.9271255060728745, "grad_norm": 0.27571643515624483, "learning_rate": 1.7546085994643807e-05, "loss": 1.1929, "step": 723 }, { "epoch": 2.931174089068826, "grad_norm": 0.30103689506553677, "learning_rate": 1.7489968862279902e-05, "loss": 1.1977, "step": 724 }, { "epoch": 2.9352226720647776, "grad_norm": 0.25875052411296734, "learning_rate": 1.743387180005809e-05, "loss": 1.1841, "step": 725 }, { "epoch": 2.9392712550607287, "grad_norm": 0.29587364172646236, "learning_rate": 1.737779525652899e-05, "loss": 1.2119, "step": 726 }, { "epoch": 2.9433198380566803, "grad_norm": 0.3003117202113969, "learning_rate": 1.732173968007914e-05, "loss": 1.2342, "step": 727 }, { "epoch": 2.9473684210526314, "grad_norm": 0.2984176802468901, "learning_rate": 1.7265705518927437e-05, "loss": 1.2061, "step": 728 }, { "epoch": 2.951417004048583, "grad_norm": 0.2862883548616932, "learning_rate": 1.7209693221121542e-05, "loss": 1.1943, "step": 729 }, { "epoch": 2.9554655870445345, "grad_norm": 0.2620431894913766, "learning_rate": 1.7153703234534302e-05, "loss": 1.2265, "step": 730 }, { "epoch": 2.9595141700404857, "grad_norm": 0.31293919963236594, "learning_rate": 1.709773600686015e-05, "loss": 1.2014, "step": 731 }, { "epoch": 2.9635627530364372, "grad_norm": 0.264775223818132, "learning_rate": 1.7041791985611548e-05, "loss": 1.1941, "step": 732 }, { "epoch": 2.967611336032389, "grad_norm": 0.29446799235657906, "learning_rate": 1.69858716181154e-05, "loss": 1.2044, "step": 733 }, { "epoch": 2.97165991902834, "grad_norm": 0.28375225022551426, "learning_rate": 1.692997535150948e-05, "loss": 1.2156, "step": 734 }, { "epoch": 2.9757085020242915, "grad_norm": 0.27386934249532774, "learning_rate": 1.687410363273884e-05, "loss": 1.2052, "step": 735 }, { "epoch": 2.979757085020243, "grad_norm": 0.29694684283261497, "learning_rate": 1.6818256908552257e-05, "loss": 1.185, "step": 736 }, { "epoch": 2.983805668016194, "grad_norm": 0.29188536433130424, "learning_rate": 1.6762435625498646e-05, "loss": 1.2052, "step": 737 }, { "epoch": 2.9878542510121457, "grad_norm": 0.293895527277101, "learning_rate": 1.67066402299235e-05, "loss": 1.2037, "step": 738 }, { "epoch": 2.9919028340080973, "grad_norm": 0.29907655602493516, "learning_rate": 1.6650871167965313e-05, "loss": 1.2089, "step": 739 }, { "epoch": 2.9959514170040484, "grad_norm": 0.29686462777605566, "learning_rate": 1.6595128885552028e-05, "loss": 1.1994, "step": 740 }, { "epoch": 3.0, "grad_norm": 0.29545116757179635, "learning_rate": 1.653941382839745e-05, "loss": 1.1912, "step": 741 }, { "epoch": 3.0040485829959516, "grad_norm": 0.3773893438216, "learning_rate": 1.6483726441997673e-05, "loss": 1.1368, "step": 742 }, { "epoch": 3.0080971659919027, "grad_norm": 0.4774963721525608, "learning_rate": 1.642806717162757e-05, "loss": 1.1417, "step": 743 }, { "epoch": 3.0121457489878543, "grad_norm": 0.32921796542728815, "learning_rate": 1.637243646233718e-05, "loss": 1.1432, "step": 744 }, { "epoch": 3.016194331983806, "grad_norm": 0.46424104223768087, "learning_rate": 1.6316834758948174e-05, "loss": 1.1501, "step": 745 }, { "epoch": 3.020242914979757, "grad_norm": 0.46229515404466476, "learning_rate": 1.6261262506050282e-05, "loss": 1.1408, "step": 746 }, { "epoch": 3.0242914979757085, "grad_norm": 0.37532733224318265, "learning_rate": 1.620572014799777e-05, "loss": 1.125, "step": 747 }, { "epoch": 3.02834008097166, "grad_norm": 0.44319462042447744, "learning_rate": 1.6150208128905857e-05, "loss": 1.1457, "step": 748 }, { "epoch": 3.032388663967611, "grad_norm": 0.33794069845606817, "learning_rate": 1.6094726892647147e-05, "loss": 1.1679, "step": 749 }, { "epoch": 3.0364372469635628, "grad_norm": 0.4142678223275278, "learning_rate": 1.6039276882848135e-05, "loss": 1.1731, "step": 750 }, { "epoch": 3.0404858299595143, "grad_norm": 0.3533511176914553, "learning_rate": 1.5983858542885635e-05, "loss": 1.1699, "step": 751 }, { "epoch": 3.0445344129554655, "grad_norm": 0.3863140832569984, "learning_rate": 1.5928472315883203e-05, "loss": 1.1313, "step": 752 }, { "epoch": 3.048582995951417, "grad_norm": 0.3577790577345889, "learning_rate": 1.5873118644707633e-05, "loss": 1.1581, "step": 753 }, { "epoch": 3.0526315789473686, "grad_norm": 0.3912178192683828, "learning_rate": 1.5817797971965413e-05, "loss": 1.1376, "step": 754 }, { "epoch": 3.0566801619433197, "grad_norm": 0.4061831472534539, "learning_rate": 1.576251073999917e-05, "loss": 1.1696, "step": 755 }, { "epoch": 3.0607287449392713, "grad_norm": 0.4310701396086317, "learning_rate": 1.5707257390884126e-05, "loss": 1.1853, "step": 756 }, { "epoch": 3.064777327935223, "grad_norm": 0.4107611775717141, "learning_rate": 1.5652038366424595e-05, "loss": 1.1601, "step": 757 }, { "epoch": 3.068825910931174, "grad_norm": 0.4157338522629884, "learning_rate": 1.5596854108150424e-05, "loss": 1.162, "step": 758 }, { "epoch": 3.0728744939271255, "grad_norm": 0.43907368570233085, "learning_rate": 1.5541705057313476e-05, "loss": 1.1363, "step": 759 }, { "epoch": 3.076923076923077, "grad_norm": 0.3876587109739133, "learning_rate": 1.5486591654884086e-05, "loss": 1.1692, "step": 760 }, { "epoch": 3.080971659919028, "grad_norm": 0.42404815633783643, "learning_rate": 1.543151434154755e-05, "loss": 1.1557, "step": 761 }, { "epoch": 3.08502024291498, "grad_norm": 0.38890582977209703, "learning_rate": 1.5376473557700615e-05, "loss": 1.1423, "step": 762 }, { "epoch": 3.0890688259109313, "grad_norm": 0.3567680131641699, "learning_rate": 1.5321469743447893e-05, "loss": 1.1508, "step": 763 }, { "epoch": 3.0931174089068825, "grad_norm": 0.3372875214002496, "learning_rate": 1.5266503338598434e-05, "loss": 1.109, "step": 764 }, { "epoch": 3.097165991902834, "grad_norm": 0.36820297625334186, "learning_rate": 1.5211574782662149e-05, "loss": 1.1386, "step": 765 }, { "epoch": 3.1012145748987856, "grad_norm": 0.30795823509397213, "learning_rate": 1.5156684514846307e-05, "loss": 1.1668, "step": 766 }, { "epoch": 3.1052631578947367, "grad_norm": 0.3496217192427141, "learning_rate": 1.5101832974052012e-05, "loss": 1.1114, "step": 767 }, { "epoch": 3.1093117408906883, "grad_norm": 0.3439556488380225, "learning_rate": 1.5047020598870737e-05, "loss": 1.1627, "step": 768 }, { "epoch": 3.11336032388664, "grad_norm": 0.368271338204317, "learning_rate": 1.4992247827580778e-05, "loss": 1.1698, "step": 769 }, { "epoch": 3.117408906882591, "grad_norm": 0.36465389667527204, "learning_rate": 1.493751509814374e-05, "loss": 1.1504, "step": 770 }, { "epoch": 3.1214574898785425, "grad_norm": 0.3178293408679408, "learning_rate": 1.4882822848201073e-05, "loss": 1.1345, "step": 771 }, { "epoch": 3.125506072874494, "grad_norm": 0.3308193630138958, "learning_rate": 1.4828171515070553e-05, "loss": 1.1383, "step": 772 }, { "epoch": 3.1295546558704452, "grad_norm": 0.3056888233647905, "learning_rate": 1.4773561535742793e-05, "loss": 1.1673, "step": 773 }, { "epoch": 3.133603238866397, "grad_norm": 0.29759922325301646, "learning_rate": 1.4718993346877715e-05, "loss": 1.1424, "step": 774 }, { "epoch": 3.1376518218623484, "grad_norm": 0.29057012308340413, "learning_rate": 1.466446738480111e-05, "loss": 1.1688, "step": 775 }, { "epoch": 3.1417004048582995, "grad_norm": 0.3333024029764771, "learning_rate": 1.460998408550112e-05, "loss": 1.1667, "step": 776 }, { "epoch": 3.145748987854251, "grad_norm": 0.3192087066840809, "learning_rate": 1.4555543884624751e-05, "loss": 1.1453, "step": 777 }, { "epoch": 3.1497975708502026, "grad_norm": 0.313378671769112, "learning_rate": 1.4501147217474402e-05, "loss": 1.1493, "step": 778 }, { "epoch": 3.1538461538461537, "grad_norm": 0.31826007257576955, "learning_rate": 1.444679451900437e-05, "loss": 1.1343, "step": 779 }, { "epoch": 3.1578947368421053, "grad_norm": 0.2870758986194048, "learning_rate": 1.4392486223817397e-05, "loss": 1.1728, "step": 780 }, { "epoch": 3.161943319838057, "grad_norm": 0.2856842626119549, "learning_rate": 1.4338222766161143e-05, "loss": 1.1574, "step": 781 }, { "epoch": 3.165991902834008, "grad_norm": 0.316450741977947, "learning_rate": 1.4284004579924777e-05, "loss": 1.1393, "step": 782 }, { "epoch": 3.1700404858299596, "grad_norm": 0.3021816761777663, "learning_rate": 1.4229832098635479e-05, "loss": 1.1392, "step": 783 }, { "epoch": 3.174089068825911, "grad_norm": 0.31142796190026495, "learning_rate": 1.4175705755454963e-05, "loss": 1.131, "step": 784 }, { "epoch": 3.1781376518218623, "grad_norm": 0.3342570199698236, "learning_rate": 1.412162598317602e-05, "loss": 1.1499, "step": 785 }, { "epoch": 3.182186234817814, "grad_norm": 0.30592331041772663, "learning_rate": 1.406759321421907e-05, "loss": 1.139, "step": 786 }, { "epoch": 3.1862348178137654, "grad_norm": 0.3067206450043522, "learning_rate": 1.401360788062871e-05, "loss": 1.1338, "step": 787 }, { "epoch": 3.1902834008097165, "grad_norm": 0.33601703306377384, "learning_rate": 1.3959670414070204e-05, "loss": 1.1221, "step": 788 }, { "epoch": 3.194331983805668, "grad_norm": 0.27077045799422544, "learning_rate": 1.3905781245826108e-05, "loss": 1.1392, "step": 789 }, { "epoch": 3.1983805668016196, "grad_norm": 0.3424025295889978, "learning_rate": 1.3851940806792778e-05, "loss": 1.1414, "step": 790 }, { "epoch": 3.2024291497975708, "grad_norm": 0.3073749448343172, "learning_rate": 1.379814952747693e-05, "loss": 1.1605, "step": 791 }, { "epoch": 3.2064777327935223, "grad_norm": 0.2989598775991294, "learning_rate": 1.3744407837992193e-05, "loss": 1.1599, "step": 792 }, { "epoch": 3.2105263157894735, "grad_norm": 0.2770209310309876, "learning_rate": 1.3690716168055692e-05, "loss": 1.1751, "step": 793 }, { "epoch": 3.214574898785425, "grad_norm": 0.30600920805427007, "learning_rate": 1.363707494698459e-05, "loss": 1.1651, "step": 794 }, { "epoch": 3.2186234817813766, "grad_norm": 0.267456133519866, "learning_rate": 1.358348460369265e-05, "loss": 1.1594, "step": 795 }, { "epoch": 3.2226720647773277, "grad_norm": 0.2554057587853787, "learning_rate": 1.352994556668684e-05, "loss": 1.1312, "step": 796 }, { "epoch": 3.2267206477732793, "grad_norm": 0.2903770823971326, "learning_rate": 1.3476458264063865e-05, "loss": 1.1409, "step": 797 }, { "epoch": 3.230769230769231, "grad_norm": 0.2753175612555132, "learning_rate": 1.342302312350678e-05, "loss": 1.1297, "step": 798 }, { "epoch": 3.234817813765182, "grad_norm": 0.26220174440078536, "learning_rate": 1.3369640572281537e-05, "loss": 1.1458, "step": 799 }, { "epoch": 3.2388663967611335, "grad_norm": 0.28051357780357333, "learning_rate": 1.3316311037233596e-05, "loss": 1.1285, "step": 800 }, { "epoch": 3.242914979757085, "grad_norm": 0.2626549610524833, "learning_rate": 1.326303494478451e-05, "loss": 1.1329, "step": 801 }, { "epoch": 3.246963562753036, "grad_norm": 0.3000940537788932, "learning_rate": 1.3209812720928472e-05, "loss": 1.1472, "step": 802 }, { "epoch": 3.251012145748988, "grad_norm": 0.2786807622824845, "learning_rate": 1.315664479122898e-05, "loss": 1.1737, "step": 803 }, { "epoch": 3.2550607287449393, "grad_norm": 0.24669005347176445, "learning_rate": 1.3103531580815378e-05, "loss": 1.1468, "step": 804 }, { "epoch": 3.2591093117408905, "grad_norm": 0.2653913411590952, "learning_rate": 1.3050473514379488e-05, "loss": 1.1812, "step": 805 }, { "epoch": 3.263157894736842, "grad_norm": 0.278599422503895, "learning_rate": 1.2997471016172188e-05, "loss": 1.1625, "step": 806 }, { "epoch": 3.2672064777327936, "grad_norm": 0.2516799308935849, "learning_rate": 1.2944524510000042e-05, "loss": 1.1543, "step": 807 }, { "epoch": 3.2712550607287447, "grad_norm": 0.2798972948819043, "learning_rate": 1.2891634419221908e-05, "loss": 1.1651, "step": 808 }, { "epoch": 3.2753036437246963, "grad_norm": 0.2840072299547987, "learning_rate": 1.2838801166745545e-05, "loss": 1.1546, "step": 809 }, { "epoch": 3.279352226720648, "grad_norm": 0.24184204982863938, "learning_rate": 1.2786025175024216e-05, "loss": 1.1241, "step": 810 }, { "epoch": 3.283400809716599, "grad_norm": 0.2883456147526252, "learning_rate": 1.2733306866053357e-05, "loss": 1.1367, "step": 811 }, { "epoch": 3.2874493927125505, "grad_norm": 0.26087257832619964, "learning_rate": 1.2680646661367163e-05, "loss": 1.1542, "step": 812 }, { "epoch": 3.291497975708502, "grad_norm": 0.2566656963389959, "learning_rate": 1.2628044982035219e-05, "loss": 1.1523, "step": 813 }, { "epoch": 3.2955465587044532, "grad_norm": 0.295502168912164, "learning_rate": 1.2575502248659155e-05, "loss": 1.1343, "step": 814 }, { "epoch": 3.299595141700405, "grad_norm": 0.2902377707349703, "learning_rate": 1.2523018881369269e-05, "loss": 1.1203, "step": 815 }, { "epoch": 3.3036437246963564, "grad_norm": 0.2851122215243164, "learning_rate": 1.2470595299821176e-05, "loss": 1.1292, "step": 816 }, { "epoch": 3.3076923076923075, "grad_norm": 0.27656691287677104, "learning_rate": 1.2418231923192416e-05, "loss": 1.154, "step": 817 }, { "epoch": 3.311740890688259, "grad_norm": 0.2657346221304311, "learning_rate": 1.2365929170179165e-05, "loss": 1.1404, "step": 818 }, { "epoch": 3.3157894736842106, "grad_norm": 0.2750527931844225, "learning_rate": 1.2313687458992848e-05, "loss": 1.172, "step": 819 }, { "epoch": 3.3198380566801617, "grad_norm": 0.28474667369282874, "learning_rate": 1.2261507207356785e-05, "loss": 1.139, "step": 820 }, { "epoch": 3.3238866396761133, "grad_norm": 0.3036827226973683, "learning_rate": 1.220938883250288e-05, "loss": 1.1625, "step": 821 }, { "epoch": 3.327935222672065, "grad_norm": 0.2685460945793473, "learning_rate": 1.215733275116827e-05, "loss": 1.1772, "step": 822 }, { "epoch": 3.331983805668016, "grad_norm": 0.2800649373675273, "learning_rate": 1.2105339379592005e-05, "loss": 1.1491, "step": 823 }, { "epoch": 3.3360323886639676, "grad_norm": 0.26202915532019594, "learning_rate": 1.2053409133511681e-05, "loss": 1.1585, "step": 824 }, { "epoch": 3.340080971659919, "grad_norm": 0.25553375644594073, "learning_rate": 1.2001542428160173e-05, "loss": 1.1492, "step": 825 }, { "epoch": 3.3441295546558703, "grad_norm": 0.28537423275523527, "learning_rate": 1.1949739678262278e-05, "loss": 1.1479, "step": 826 }, { "epoch": 3.348178137651822, "grad_norm": 0.2915304505207573, "learning_rate": 1.189800129803139e-05, "loss": 1.1763, "step": 827 }, { "epoch": 3.3522267206477734, "grad_norm": 0.27117871193118814, "learning_rate": 1.1846327701166228e-05, "loss": 1.1706, "step": 828 }, { "epoch": 3.3562753036437245, "grad_norm": 0.34483082798891934, "learning_rate": 1.1794719300847493e-05, "loss": 1.1504, "step": 829 }, { "epoch": 3.360323886639676, "grad_norm": 0.2625301005134394, "learning_rate": 1.1743176509734582e-05, "loss": 1.1629, "step": 830 }, { "epoch": 3.3643724696356276, "grad_norm": 0.28763159289149925, "learning_rate": 1.1691699739962275e-05, "loss": 1.1459, "step": 831 }, { "epoch": 3.3684210526315788, "grad_norm": 0.32280358481016524, "learning_rate": 1.1640289403137456e-05, "loss": 1.1152, "step": 832 }, { "epoch": 3.3724696356275303, "grad_norm": 0.27939877820325454, "learning_rate": 1.1588945910335802e-05, "loss": 1.1481, "step": 833 }, { "epoch": 3.376518218623482, "grad_norm": 0.28584404740186575, "learning_rate": 1.1537669672098517e-05, "loss": 1.1429, "step": 834 }, { "epoch": 3.380566801619433, "grad_norm": 0.3017669380441542, "learning_rate": 1.1486461098429036e-05, "loss": 1.1422, "step": 835 }, { "epoch": 3.3846153846153846, "grad_norm": 0.29570365315667096, "learning_rate": 1.1435320598789747e-05, "loss": 1.1802, "step": 836 }, { "epoch": 3.388663967611336, "grad_norm": 0.31030303516386143, "learning_rate": 1.1384248582098736e-05, "loss": 1.1538, "step": 837 }, { "epoch": 3.3927125506072873, "grad_norm": 0.259171835274588, "learning_rate": 1.1333245456726467e-05, "loss": 1.1441, "step": 838 }, { "epoch": 3.396761133603239, "grad_norm": 0.29117321164794674, "learning_rate": 1.128231163049258e-05, "loss": 1.1248, "step": 839 }, { "epoch": 3.4008097165991904, "grad_norm": 0.2623071406384746, "learning_rate": 1.123144751066259e-05, "loss": 1.1349, "step": 840 }, { "epoch": 3.4048582995951415, "grad_norm": 0.2801081446770143, "learning_rate": 1.1180653503944657e-05, "loss": 1.18, "step": 841 }, { "epoch": 3.408906882591093, "grad_norm": 0.26754301567514027, "learning_rate": 1.1129930016486287e-05, "loss": 1.1301, "step": 842 }, { "epoch": 3.4129554655870447, "grad_norm": 0.26099535567448184, "learning_rate": 1.107927745387114e-05, "loss": 1.1489, "step": 843 }, { "epoch": 3.417004048582996, "grad_norm": 0.26065022600342, "learning_rate": 1.1028696221115766e-05, "loss": 1.1349, "step": 844 }, { "epoch": 3.4210526315789473, "grad_norm": 0.2593532489551216, "learning_rate": 1.0978186722666341e-05, "loss": 1.1478, "step": 845 }, { "epoch": 3.425101214574899, "grad_norm": 0.2578372057781798, "learning_rate": 1.0927749362395475e-05, "loss": 1.1458, "step": 846 }, { "epoch": 3.42914979757085, "grad_norm": 0.2672266009087319, "learning_rate": 1.0877384543598954e-05, "loss": 1.1716, "step": 847 }, { "epoch": 3.4331983805668016, "grad_norm": 0.2647877220715295, "learning_rate": 1.0827092668992529e-05, "loss": 1.1694, "step": 848 }, { "epoch": 3.437246963562753, "grad_norm": 0.2889297566595101, "learning_rate": 1.077687414070869e-05, "loss": 1.1428, "step": 849 }, { "epoch": 3.4412955465587043, "grad_norm": 0.27197158542721867, "learning_rate": 1.0726729360293451e-05, "loss": 1.1415, "step": 850 }, { "epoch": 3.445344129554656, "grad_norm": 2.3539518604830816, "learning_rate": 1.0676658728703147e-05, "loss": 1.1678, "step": 851 }, { "epoch": 3.4493927125506074, "grad_norm": 0.29337103084875077, "learning_rate": 1.0626662646301198e-05, "loss": 1.1374, "step": 852 }, { "epoch": 3.4534412955465585, "grad_norm": 0.2554446678436793, "learning_rate": 1.0576741512854958e-05, "loss": 1.1529, "step": 853 }, { "epoch": 3.45748987854251, "grad_norm": 0.273715195397098, "learning_rate": 1.052689572753247e-05, "loss": 1.1269, "step": 854 }, { "epoch": 3.4615384615384617, "grad_norm": 0.2565875794150299, "learning_rate": 1.0477125688899328e-05, "loss": 1.1592, "step": 855 }, { "epoch": 3.465587044534413, "grad_norm": 0.26296732322578104, "learning_rate": 1.0427431794915406e-05, "loss": 1.1706, "step": 856 }, { "epoch": 3.4696356275303644, "grad_norm": 0.2681199600657765, "learning_rate": 1.0377814442931769e-05, "loss": 1.1226, "step": 857 }, { "epoch": 3.473684210526316, "grad_norm": 0.25986532059937156, "learning_rate": 1.0328274029687439e-05, "loss": 1.1462, "step": 858 }, { "epoch": 3.477732793522267, "grad_norm": 0.2858693904690766, "learning_rate": 1.0278810951306253e-05, "loss": 1.1164, "step": 859 }, { "epoch": 3.4817813765182186, "grad_norm": 0.26902881145319524, "learning_rate": 1.0229425603293647e-05, "loss": 1.1514, "step": 860 }, { "epoch": 3.48582995951417, "grad_norm": 0.29035044726782655, "learning_rate": 1.0180118380533558e-05, "loss": 1.183, "step": 861 }, { "epoch": 3.4898785425101213, "grad_norm": 0.2627246917682968, "learning_rate": 1.0130889677285225e-05, "loss": 1.1691, "step": 862 }, { "epoch": 3.493927125506073, "grad_norm": 0.280502443474244, "learning_rate": 1.008173988718005e-05, "loss": 1.1734, "step": 863 }, { "epoch": 3.4979757085020244, "grad_norm": 0.27648205714402696, "learning_rate": 1.0032669403218439e-05, "loss": 1.1558, "step": 864 }, { "epoch": 3.5020242914979756, "grad_norm": 0.2809439489281512, "learning_rate": 9.983678617766677e-06, "loss": 1.1269, "step": 865 }, { "epoch": 3.506072874493927, "grad_norm": 0.2972144620663727, "learning_rate": 9.934767922553788e-06, "loss": 1.1645, "step": 866 }, { "epoch": 3.5101214574898787, "grad_norm": 0.2635051543609178, "learning_rate": 9.885937708668371e-06, "loss": 1.1476, "step": 867 }, { "epoch": 3.51417004048583, "grad_norm": 0.2681297906701883, "learning_rate": 9.837188366555524e-06, "loss": 1.143, "step": 868 }, { "epoch": 3.5182186234817814, "grad_norm": 0.27096563934488077, "learning_rate": 9.788520286013691e-06, "loss": 1.1789, "step": 869 }, { "epoch": 3.522267206477733, "grad_norm": 0.2771142641234029, "learning_rate": 9.739933856191537e-06, "loss": 1.1426, "step": 870 }, { "epoch": 3.526315789473684, "grad_norm": 0.2428088973375993, "learning_rate": 9.691429465584866e-06, "loss": 1.1478, "step": 871 }, { "epoch": 3.5303643724696356, "grad_norm": 0.2545476378900838, "learning_rate": 9.643007502033492e-06, "loss": 1.1655, "step": 872 }, { "epoch": 3.534412955465587, "grad_norm": 0.26753184345273073, "learning_rate": 9.594668352718152e-06, "loss": 1.1219, "step": 873 }, { "epoch": 3.5384615384615383, "grad_norm": 0.26402814403332614, "learning_rate": 9.546412404157383e-06, "loss": 1.1472, "step": 874 }, { "epoch": 3.54251012145749, "grad_norm": 0.26547469373544774, "learning_rate": 9.498240042204471e-06, "loss": 1.1494, "step": 875 }, { "epoch": 3.5465587044534415, "grad_norm": 0.2742924519023618, "learning_rate": 9.450151652044339e-06, "loss": 1.1491, "step": 876 }, { "epoch": 3.5506072874493926, "grad_norm": 0.255345617910611, "learning_rate": 9.402147618190472e-06, "loss": 1.1247, "step": 877 }, { "epoch": 3.554655870445344, "grad_norm": 0.24742352888506744, "learning_rate": 9.354228324481841e-06, "loss": 1.1797, "step": 878 }, { "epoch": 3.5587044534412957, "grad_norm": 0.25662312791319175, "learning_rate": 9.306394154079852e-06, "loss": 1.1673, "step": 879 }, { "epoch": 3.562753036437247, "grad_norm": 0.25280652232336454, "learning_rate": 9.258645489465254e-06, "loss": 1.1589, "step": 880 }, { "epoch": 3.5668016194331984, "grad_norm": 0.22578498479039388, "learning_rate": 9.21098271243509e-06, "loss": 1.1673, "step": 881 }, { "epoch": 3.57085020242915, "grad_norm": 0.26277722279477295, "learning_rate": 9.163406204099659e-06, "loss": 1.1384, "step": 882 }, { "epoch": 3.574898785425101, "grad_norm": 0.23818219328890514, "learning_rate": 9.115916344879452e-06, "loss": 1.1491, "step": 883 }, { "epoch": 3.5789473684210527, "grad_norm": 0.23973153497790659, "learning_rate": 9.068513514502126e-06, "loss": 1.137, "step": 884 }, { "epoch": 3.582995951417004, "grad_norm": 0.2505928982824874, "learning_rate": 9.021198091999439e-06, "loss": 1.1456, "step": 885 }, { "epoch": 3.5870445344129553, "grad_norm": 0.2422951967756025, "learning_rate": 8.973970455704251e-06, "loss": 1.1541, "step": 886 }, { "epoch": 3.591093117408907, "grad_norm": 0.24410238692860106, "learning_rate": 8.926830983247495e-06, "loss": 1.1363, "step": 887 }, { "epoch": 3.5951417004048585, "grad_norm": 0.2579617377978318, "learning_rate": 8.879780051555116e-06, "loss": 1.1704, "step": 888 }, { "epoch": 3.5991902834008096, "grad_norm": 0.27897600424912405, "learning_rate": 8.83281803684512e-06, "loss": 1.1409, "step": 889 }, { "epoch": 3.603238866396761, "grad_norm": 0.24120965129105593, "learning_rate": 8.785945314624532e-06, "loss": 1.1598, "step": 890 }, { "epoch": 3.6072874493927127, "grad_norm": 0.24186159265497897, "learning_rate": 8.739162259686385e-06, "loss": 1.1521, "step": 891 }, { "epoch": 3.611336032388664, "grad_norm": 0.2327139210655083, "learning_rate": 8.692469246106734e-06, "loss": 1.1383, "step": 892 }, { "epoch": 3.6153846153846154, "grad_norm": 0.24637626363763007, "learning_rate": 8.645866647241677e-06, "loss": 1.1286, "step": 893 }, { "epoch": 3.619433198380567, "grad_norm": 0.23774597718390408, "learning_rate": 8.599354835724348e-06, "loss": 1.1586, "step": 894 }, { "epoch": 3.623481781376518, "grad_norm": 0.26787933725509566, "learning_rate": 8.552934183461958e-06, "loss": 1.1659, "step": 895 }, { "epoch": 3.6275303643724697, "grad_norm": 0.2555927426360369, "learning_rate": 8.506605061632805e-06, "loss": 1.1468, "step": 896 }, { "epoch": 3.6315789473684212, "grad_norm": 0.2323411401384034, "learning_rate": 8.460367840683308e-06, "loss": 1.136, "step": 897 }, { "epoch": 3.6356275303643724, "grad_norm": 0.25194357823322694, "learning_rate": 8.414222890325065e-06, "loss": 1.1301, "step": 898 }, { "epoch": 3.639676113360324, "grad_norm": 0.2820102011521963, "learning_rate": 8.368170579531855e-06, "loss": 1.1675, "step": 899 }, { "epoch": 3.6437246963562755, "grad_norm": 0.24338102168054682, "learning_rate": 8.322211276536733e-06, "loss": 1.1405, "step": 900 }, { "epoch": 3.6477732793522266, "grad_norm": 0.28299677739980283, "learning_rate": 8.27634534882907e-06, "loss": 1.1562, "step": 901 }, { "epoch": 3.651821862348178, "grad_norm": 0.24570622166192393, "learning_rate": 8.230573163151585e-06, "loss": 1.1787, "step": 902 }, { "epoch": 3.6558704453441297, "grad_norm": 0.2733160845320815, "learning_rate": 8.184895085497466e-06, "loss": 1.1067, "step": 903 }, { "epoch": 3.659919028340081, "grad_norm": 0.25932189377668635, "learning_rate": 8.139311481107401e-06, "loss": 1.1643, "step": 904 }, { "epoch": 3.6639676113360324, "grad_norm": 0.2313454685103751, "learning_rate": 8.093822714466686e-06, "loss": 1.1366, "step": 905 }, { "epoch": 3.668016194331984, "grad_norm": 0.274168176030419, "learning_rate": 8.048429149302271e-06, "loss": 1.1518, "step": 906 }, { "epoch": 3.672064777327935, "grad_norm": 0.24574494266097702, "learning_rate": 8.003131148579902e-06, "loss": 1.1587, "step": 907 }, { "epoch": 3.6761133603238867, "grad_norm": 0.24292492372831404, "learning_rate": 7.957929074501182e-06, "loss": 1.1405, "step": 908 }, { "epoch": 3.6801619433198383, "grad_norm": 0.2503754183733327, "learning_rate": 7.912823288500695e-06, "loss": 1.154, "step": 909 }, { "epoch": 3.6842105263157894, "grad_norm": 0.23105346470238092, "learning_rate": 7.867814151243102e-06, "loss": 1.1166, "step": 910 }, { "epoch": 3.688259109311741, "grad_norm": 0.24810304431708108, "learning_rate": 7.822902022620267e-06, "loss": 1.1773, "step": 911 }, { "epoch": 3.6923076923076925, "grad_norm": 0.24238957956575993, "learning_rate": 7.778087261748377e-06, "loss": 1.1461, "step": 912 }, { "epoch": 3.6963562753036436, "grad_norm": 0.24603871755800139, "learning_rate": 7.733370226965056e-06, "loss": 1.1397, "step": 913 }, { "epoch": 3.700404858299595, "grad_norm": 0.2596803970317406, "learning_rate": 7.688751275826527e-06, "loss": 1.1375, "step": 914 }, { "epoch": 3.7044534412955468, "grad_norm": 0.2682394230278279, "learning_rate": 7.644230765104735e-06, "loss": 1.1478, "step": 915 }, { "epoch": 3.708502024291498, "grad_norm": 0.2509921024312598, "learning_rate": 7.599809050784502e-06, "loss": 1.1566, "step": 916 }, { "epoch": 3.7125506072874495, "grad_norm": 0.2598597043207127, "learning_rate": 7.555486488060661e-06, "loss": 1.1356, "step": 917 }, { "epoch": 3.716599190283401, "grad_norm": 0.2632340525549764, "learning_rate": 7.511263431335249e-06, "loss": 1.1569, "step": 918 }, { "epoch": 3.720647773279352, "grad_norm": 0.244545231094034, "learning_rate": 7.467140234214656e-06, "loss": 1.179, "step": 919 }, { "epoch": 3.7246963562753037, "grad_norm": 0.27338310056384824, "learning_rate": 7.423117249506777e-06, "loss": 1.1692, "step": 920 }, { "epoch": 3.7287449392712553, "grad_norm": 0.2450000070617953, "learning_rate": 7.379194829218231e-06, "loss": 1.1463, "step": 921 }, { "epoch": 3.7327935222672064, "grad_norm": 0.2188430446477123, "learning_rate": 7.335373324551518e-06, "loss": 1.1179, "step": 922 }, { "epoch": 3.736842105263158, "grad_norm": 0.2568307082393477, "learning_rate": 7.291653085902224e-06, "loss": 1.1499, "step": 923 }, { "epoch": 3.7408906882591095, "grad_norm": 0.25148291927850186, "learning_rate": 7.248034462856213e-06, "loss": 1.1745, "step": 924 }, { "epoch": 3.7449392712550607, "grad_norm": 0.24470902696714197, "learning_rate": 7.20451780418683e-06, "loss": 1.1136, "step": 925 }, { "epoch": 3.748987854251012, "grad_norm": 0.23252233867354472, "learning_rate": 7.161103457852128e-06, "loss": 1.1378, "step": 926 }, { "epoch": 3.753036437246964, "grad_norm": 0.22095893934537755, "learning_rate": 7.117791770992046e-06, "loss": 1.1599, "step": 927 }, { "epoch": 3.757085020242915, "grad_norm": 0.2348411150774812, "learning_rate": 7.074583089925688e-06, "loss": 1.1164, "step": 928 }, { "epoch": 3.7611336032388665, "grad_norm": 0.24084080621393444, "learning_rate": 7.0314777601485155e-06, "loss": 1.1808, "step": 929 }, { "epoch": 3.765182186234818, "grad_norm": 0.24243782588475837, "learning_rate": 6.988476126329604e-06, "loss": 1.1428, "step": 930 }, { "epoch": 3.769230769230769, "grad_norm": 0.22209372555839157, "learning_rate": 6.945578532308857e-06, "loss": 1.1805, "step": 931 }, { "epoch": 3.7732793522267207, "grad_norm": 0.22616491853282117, "learning_rate": 6.902785321094301e-06, "loss": 1.1442, "step": 932 }, { "epoch": 3.7773279352226723, "grad_norm": 0.23310180137794087, "learning_rate": 6.8600968348593115e-06, "loss": 1.1621, "step": 933 }, { "epoch": 3.7813765182186234, "grad_norm": 0.22568133337515026, "learning_rate": 6.817513414939892e-06, "loss": 1.1307, "step": 934 }, { "epoch": 3.785425101214575, "grad_norm": 0.22002900835786632, "learning_rate": 6.775035401831924e-06, "loss": 1.1618, "step": 935 }, { "epoch": 3.7894736842105265, "grad_norm": 0.22938109664064663, "learning_rate": 6.732663135188473e-06, "loss": 1.1631, "step": 936 }, { "epoch": 3.7935222672064777, "grad_norm": 0.24628250890152806, "learning_rate": 6.690396953817055e-06, "loss": 1.1583, "step": 937 }, { "epoch": 3.7975708502024292, "grad_norm": 0.24726952165618243, "learning_rate": 6.648237195676927e-06, "loss": 1.1176, "step": 938 }, { "epoch": 3.801619433198381, "grad_norm": 0.22095760102443562, "learning_rate": 6.606184197876395e-06, "loss": 1.1438, "step": 939 }, { "epoch": 3.805668016194332, "grad_norm": 0.21357708948491452, "learning_rate": 6.564238296670109e-06, "loss": 1.1162, "step": 940 }, { "epoch": 3.8097165991902835, "grad_norm": 0.23728149119825143, "learning_rate": 6.52239982745638e-06, "loss": 1.1485, "step": 941 }, { "epoch": 3.813765182186235, "grad_norm": 0.23147225818555953, "learning_rate": 6.480669124774484e-06, "loss": 1.1404, "step": 942 }, { "epoch": 3.817813765182186, "grad_norm": 0.24971092054055244, "learning_rate": 6.439046522302013e-06, "loss": 1.1235, "step": 943 }, { "epoch": 3.8218623481781377, "grad_norm": 0.24988620439217407, "learning_rate": 6.397532352852191e-06, "loss": 1.1661, "step": 944 }, { "epoch": 3.8259109311740893, "grad_norm": 0.20538854365990986, "learning_rate": 6.356126948371202e-06, "loss": 1.1326, "step": 945 }, { "epoch": 3.8299595141700404, "grad_norm": 0.2521194503101919, "learning_rate": 6.314830639935559e-06, "loss": 1.157, "step": 946 }, { "epoch": 3.834008097165992, "grad_norm": 0.24718029544327316, "learning_rate": 6.273643757749448e-06, "loss": 1.1874, "step": 947 }, { "epoch": 3.8380566801619436, "grad_norm": 0.22443679247967951, "learning_rate": 6.2325666311420856e-06, "loss": 1.1416, "step": 948 }, { "epoch": 3.8421052631578947, "grad_norm": 0.22457531373008943, "learning_rate": 6.1915995885650675e-06, "loss": 1.1407, "step": 949 }, { "epoch": 3.8461538461538463, "grad_norm": 0.22991031539650092, "learning_rate": 6.150742957589784e-06, "loss": 1.1536, "step": 950 }, { "epoch": 3.850202429149798, "grad_norm": 0.24313567335799327, "learning_rate": 6.109997064904774e-06, "loss": 1.1559, "step": 951 }, { "epoch": 3.854251012145749, "grad_norm": 0.21936397236111593, "learning_rate": 6.069362236313092e-06, "loss": 1.1605, "step": 952 }, { "epoch": 3.8582995951417005, "grad_norm": 0.2174917301798601, "learning_rate": 6.0288387967297565e-06, "loss": 1.1289, "step": 953 }, { "epoch": 3.862348178137652, "grad_norm": 0.2462552124631566, "learning_rate": 5.988427070179108e-06, "loss": 1.162, "step": 954 }, { "epoch": 3.866396761133603, "grad_norm": 0.2206201820075042, "learning_rate": 5.948127379792234e-06, "loss": 1.1033, "step": 955 }, { "epoch": 3.8704453441295548, "grad_norm": 0.21930633348248932, "learning_rate": 5.90794004780439e-06, "loss": 1.1251, "step": 956 }, { "epoch": 3.8744939271255063, "grad_norm": 0.25351576779475543, "learning_rate": 5.867865395552405e-06, "loss": 1.1581, "step": 957 }, { "epoch": 3.8785425101214575, "grad_norm": 0.2198011995789729, "learning_rate": 5.8279037434721364e-06, "loss": 1.1417, "step": 958 }, { "epoch": 3.882591093117409, "grad_norm": 0.22384153598038573, "learning_rate": 5.788055411095892e-06, "loss": 1.1615, "step": 959 }, { "epoch": 3.8866396761133606, "grad_norm": 0.24098695382261393, "learning_rate": 5.7483207170498625e-06, "loss": 1.1457, "step": 960 }, { "epoch": 3.8906882591093117, "grad_norm": 0.2210865839135142, "learning_rate": 5.708699979051613e-06, "loss": 1.1476, "step": 961 }, { "epoch": 3.8947368421052633, "grad_norm": 0.22394085675423972, "learning_rate": 5.66919351390751e-06, "loss": 1.1317, "step": 962 }, { "epoch": 3.898785425101215, "grad_norm": 0.24477761341307555, "learning_rate": 5.629801637510188e-06, "loss": 1.1675, "step": 963 }, { "epoch": 3.902834008097166, "grad_norm": 0.23307260340588906, "learning_rate": 5.590524664836043e-06, "loss": 1.1248, "step": 964 }, { "epoch": 3.9068825910931175, "grad_norm": 0.22285326006175213, "learning_rate": 5.551362909942708e-06, "loss": 1.1476, "step": 965 }, { "epoch": 3.910931174089069, "grad_norm": 0.2219026066222674, "learning_rate": 5.51231668596653e-06, "loss": 1.1605, "step": 966 }, { "epoch": 3.91497975708502, "grad_norm": 0.2373388759259673, "learning_rate": 5.47338630512007e-06, "loss": 1.1325, "step": 967 }, { "epoch": 3.919028340080972, "grad_norm": 0.2189278876217179, "learning_rate": 5.434572078689617e-06, "loss": 1.1406, "step": 968 }, { "epoch": 3.9230769230769234, "grad_norm": 0.226880487701696, "learning_rate": 5.395874317032694e-06, "loss": 1.149, "step": 969 }, { "epoch": 3.9271255060728745, "grad_norm": 0.22972875672754572, "learning_rate": 5.357293329575573e-06, "loss": 1.1397, "step": 970 }, { "epoch": 3.931174089068826, "grad_norm": 0.24218524998437777, "learning_rate": 5.318829424810797e-06, "loss": 1.1877, "step": 971 }, { "epoch": 3.9352226720647776, "grad_norm": 0.24412660565134225, "learning_rate": 5.280482910294728e-06, "loss": 1.1389, "step": 972 }, { "epoch": 3.9392712550607287, "grad_norm": 0.23095197656962393, "learning_rate": 5.242254092645078e-06, "loss": 1.156, "step": 973 }, { "epoch": 3.9433198380566803, "grad_norm": 0.2232949289833355, "learning_rate": 5.2041432775384445e-06, "loss": 1.1003, "step": 974 }, { "epoch": 3.9473684210526314, "grad_norm": 0.23140693648569646, "learning_rate": 5.166150769707892e-06, "loss": 1.1685, "step": 975 }, { "epoch": 3.951417004048583, "grad_norm": 0.24392522409485848, "learning_rate": 5.128276872940503e-06, "loss": 1.1355, "step": 976 }, { "epoch": 3.9554655870445345, "grad_norm": 0.20351662181806654, "learning_rate": 5.090521890074953e-06, "loss": 1.1476, "step": 977 }, { "epoch": 3.9595141700404857, "grad_norm": 0.22351262369645006, "learning_rate": 5.0528861229990675e-06, "loss": 1.1818, "step": 978 }, { "epoch": 3.9635627530364372, "grad_norm": 0.23215928391952334, "learning_rate": 5.015369872647442e-06, "loss": 1.1089, "step": 979 }, { "epoch": 3.967611336032389, "grad_norm": 0.22053128949718706, "learning_rate": 4.9779734389990195e-06, "loss": 1.1465, "step": 980 }, { "epoch": 3.97165991902834, "grad_norm": 0.2320026559745314, "learning_rate": 4.940697121074675e-06, "loss": 1.1433, "step": 981 }, { "epoch": 3.9757085020242915, "grad_norm": 0.2181955142246088, "learning_rate": 4.903541216934864e-06, "loss": 1.1478, "step": 982 }, { "epoch": 3.979757085020243, "grad_norm": 0.22568340892191754, "learning_rate": 4.8665060236772e-06, "loss": 1.1243, "step": 983 }, { "epoch": 3.983805668016194, "grad_norm": 0.21672985244422446, "learning_rate": 4.829591837434102e-06, "loss": 1.1584, "step": 984 }, { "epoch": 3.9878542510121457, "grad_norm": 0.21779345748038284, "learning_rate": 4.792798953370424e-06, "loss": 1.1743, "step": 985 }, { "epoch": 3.9919028340080973, "grad_norm": 0.23168713004077934, "learning_rate": 4.756127665681083e-06, "loss": 1.1411, "step": 986 }, { "epoch": 3.9959514170040484, "grad_norm": 0.22097972281355086, "learning_rate": 4.719578267588725e-06, "loss": 1.1172, "step": 987 }, { "epoch": 4.0, "grad_norm": 0.22248618902581144, "learning_rate": 4.6831510513413525e-06, "loss": 1.125, "step": 988 }, { "epoch": 4.004048582995951, "grad_norm": 0.3383546014229973, "learning_rate": 4.6468463082100176e-06, "loss": 1.1205, "step": 989 }, { "epoch": 4.008097165991903, "grad_norm": 0.25068451571756983, "learning_rate": 4.610664328486485e-06, "loss": 1.1135, "step": 990 }, { "epoch": 4.012145748987854, "grad_norm": 0.2518653231453495, "learning_rate": 4.5746054014809e-06, "loss": 1.1123, "step": 991 }, { "epoch": 4.016194331983805, "grad_norm": 0.3928058964818054, "learning_rate": 4.5386698155194766e-06, "loss": 1.1313, "step": 992 }, { "epoch": 4.020242914979757, "grad_norm": 0.2610019883277169, "learning_rate": 4.502857857942204e-06, "loss": 1.1298, "step": 993 }, { "epoch": 4.0242914979757085, "grad_norm": 0.3230004311034245, "learning_rate": 4.467169815100549e-06, "loss": 1.0988, "step": 994 }, { "epoch": 4.02834008097166, "grad_norm": 0.3141082569187121, "learning_rate": 4.431605972355137e-06, "loss": 1.1202, "step": 995 }, { "epoch": 4.032388663967612, "grad_norm": 0.2885959125094875, "learning_rate": 4.396166614073516e-06, "loss": 1.129, "step": 996 }, { "epoch": 4.036437246963563, "grad_norm": 0.2922438666751, "learning_rate": 4.360852023627846e-06, "loss": 1.1068, "step": 997 }, { "epoch": 4.040485829959514, "grad_norm": 0.3032499661456036, "learning_rate": 4.325662483392656e-06, "loss": 1.1208, "step": 998 }, { "epoch": 4.044534412955466, "grad_norm": 0.2875771410276206, "learning_rate": 4.29059827474257e-06, "loss": 1.1067, "step": 999 }, { "epoch": 4.048582995951417, "grad_norm": 0.30818098961150736, "learning_rate": 4.255659678050063e-06, "loss": 1.0806, "step": 1000 }, { "epoch": 4.052631578947368, "grad_norm": 0.297211325134837, "learning_rate": 4.22084697268323e-06, "loss": 1.1116, "step": 1001 }, { "epoch": 4.05668016194332, "grad_norm": 0.26322451618633713, "learning_rate": 4.186160437003535e-06, "loss": 1.107, "step": 1002 }, { "epoch": 4.060728744939271, "grad_norm": 0.27688585617209605, "learning_rate": 4.151600348363582e-06, "loss": 1.1363, "step": 1003 }, { "epoch": 4.064777327935222, "grad_norm": 0.28981651894103133, "learning_rate": 4.11716698310493e-06, "loss": 1.1267, "step": 1004 }, { "epoch": 4.068825910931174, "grad_norm": 0.2747020353875089, "learning_rate": 4.082860616555848e-06, "loss": 1.113, "step": 1005 }, { "epoch": 4.0728744939271255, "grad_norm": 0.2794610207615382, "learning_rate": 4.048681523029125e-06, "loss": 1.0684, "step": 1006 }, { "epoch": 4.076923076923077, "grad_norm": 0.27846424055462754, "learning_rate": 4.014629975819882e-06, "loss": 1.0882, "step": 1007 }, { "epoch": 4.080971659919029, "grad_norm": 0.26029918683778436, "learning_rate": 3.9807062472033855e-06, "loss": 1.0883, "step": 1008 }, { "epoch": 4.08502024291498, "grad_norm": 0.24344177585274787, "learning_rate": 3.94691060843287e-06, "loss": 1.1051, "step": 1009 }, { "epoch": 4.089068825910931, "grad_norm": 0.2754148494079168, "learning_rate": 3.913243329737353e-06, "loss": 1.0944, "step": 1010 }, { "epoch": 4.093117408906883, "grad_norm": 0.28320976265639125, "learning_rate": 3.879704680319503e-06, "loss": 1.099, "step": 1011 }, { "epoch": 4.097165991902834, "grad_norm": 0.2434317977184862, "learning_rate": 3.846294928353471e-06, "loss": 1.1063, "step": 1012 }, { "epoch": 4.101214574898785, "grad_norm": 0.23644147942701696, "learning_rate": 3.8130143409827345e-06, "loss": 1.0604, "step": 1013 }, { "epoch": 4.105263157894737, "grad_norm": 0.2811865435691943, "learning_rate": 3.7798631843179887e-06, "loss": 1.1069, "step": 1014 }, { "epoch": 4.109311740890688, "grad_norm": 0.2684846784841576, "learning_rate": 3.7468417234349973e-06, "loss": 1.0986, "step": 1015 }, { "epoch": 4.113360323886639, "grad_norm": 0.24959201088494815, "learning_rate": 3.7139502223724823e-06, "loss": 1.129, "step": 1016 }, { "epoch": 4.117408906882591, "grad_norm": 0.2418000773561899, "learning_rate": 3.6811889441300095e-06, "loss": 1.0869, "step": 1017 }, { "epoch": 4.1214574898785425, "grad_norm": 0.2647191179024516, "learning_rate": 3.648558150665886e-06, "loss": 1.1112, "step": 1018 }, { "epoch": 4.125506072874494, "grad_norm": 0.25923212068637064, "learning_rate": 3.616058102895075e-06, "loss": 1.1198, "step": 1019 }, { "epoch": 4.129554655870446, "grad_norm": 0.2497476429778314, "learning_rate": 3.583689060687079e-06, "loss": 1.111, "step": 1020 }, { "epoch": 4.133603238866397, "grad_norm": 0.25966665704134284, "learning_rate": 3.5514512828639023e-06, "loss": 1.0904, "step": 1021 }, { "epoch": 4.137651821862348, "grad_norm": 0.25993505179341814, "learning_rate": 3.51934502719796e-06, "loss": 1.0787, "step": 1022 }, { "epoch": 4.1417004048583, "grad_norm": 0.24729755287254226, "learning_rate": 3.4873705504100185e-06, "loss": 1.1051, "step": 1023 }, { "epoch": 4.145748987854251, "grad_norm": 0.2416418706487922, "learning_rate": 3.4555281081671345e-06, "loss": 1.1235, "step": 1024 }, { "epoch": 4.149797570850202, "grad_norm": 0.23613578668107063, "learning_rate": 3.4238179550806326e-06, "loss": 1.1256, "step": 1025 }, { "epoch": 4.153846153846154, "grad_norm": 0.23618445907153487, "learning_rate": 3.3922403447040497e-06, "loss": 1.1113, "step": 1026 }, { "epoch": 4.157894736842105, "grad_norm": 0.225369494427577, "learning_rate": 3.3607955295311247e-06, "loss": 1.132, "step": 1027 }, { "epoch": 4.161943319838056, "grad_norm": 0.22845472667196592, "learning_rate": 3.32948376099375e-06, "loss": 1.1237, "step": 1028 }, { "epoch": 4.165991902834008, "grad_norm": 0.2275813113744001, "learning_rate": 3.2983052894599976e-06, "loss": 1.0998, "step": 1029 }, { "epoch": 4.17004048582996, "grad_norm": 0.2262747076461356, "learning_rate": 3.2672603642320945e-06, "loss": 1.1077, "step": 1030 }, { "epoch": 4.174089068825911, "grad_norm": 0.22664407752233465, "learning_rate": 3.236349233544438e-06, "loss": 1.1002, "step": 1031 }, { "epoch": 4.178137651821863, "grad_norm": 0.2271767758684663, "learning_rate": 3.205572144561604e-06, "loss": 1.132, "step": 1032 }, { "epoch": 4.182186234817814, "grad_norm": 0.24900118478051278, "learning_rate": 3.174929343376374e-06, "loss": 1.1305, "step": 1033 }, { "epoch": 4.186234817813765, "grad_norm": 0.21693482469621717, "learning_rate": 3.1444210750077777e-06, "loss": 1.1068, "step": 1034 }, { "epoch": 4.190283400809717, "grad_norm": 0.24425019147800017, "learning_rate": 3.1140475833991046e-06, "loss": 1.105, "step": 1035 }, { "epoch": 4.194331983805668, "grad_norm": 0.20967885067336542, "learning_rate": 3.0838091114159895e-06, "loss": 1.1209, "step": 1036 }, { "epoch": 4.198380566801619, "grad_norm": 0.21775462662792178, "learning_rate": 3.0537059008444524e-06, "loss": 1.158, "step": 1037 }, { "epoch": 4.202429149797571, "grad_norm": 0.21537483807867613, "learning_rate": 3.0237381923889563e-06, "loss": 1.1044, "step": 1038 }, { "epoch": 4.206477732793522, "grad_norm": 0.23440597774601013, "learning_rate": 2.9939062256704997e-06, "loss": 1.1231, "step": 1039 }, { "epoch": 4.2105263157894735, "grad_norm": 0.21293087705985797, "learning_rate": 2.964210239224696e-06, "loss": 1.1104, "step": 1040 }, { "epoch": 4.2145748987854255, "grad_norm": 0.21398929459314675, "learning_rate": 2.934650470499869e-06, "loss": 1.0993, "step": 1041 }, { "epoch": 4.218623481781377, "grad_norm": 0.22150829731636615, "learning_rate": 2.905227155855128e-06, "loss": 1.0991, "step": 1042 }, { "epoch": 4.222672064777328, "grad_norm": 0.2083889416567368, "learning_rate": 2.875940530558519e-06, "loss": 1.1046, "step": 1043 }, { "epoch": 4.22672064777328, "grad_norm": 0.21848794503736416, "learning_rate": 2.8467908287851154e-06, "loss": 1.129, "step": 1044 }, { "epoch": 4.230769230769231, "grad_norm": 0.2126039587832773, "learning_rate": 2.8177782836151603e-06, "loss": 1.1267, "step": 1045 }, { "epoch": 4.234817813765182, "grad_norm": 0.2227185501900078, "learning_rate": 2.7889031270321874e-06, "loss": 1.1049, "step": 1046 }, { "epoch": 4.238866396761134, "grad_norm": 0.20810250888460083, "learning_rate": 2.760165589921184e-06, "loss": 1.1227, "step": 1047 }, { "epoch": 4.242914979757085, "grad_norm": 0.23839835472991383, "learning_rate": 2.7315659020667305e-06, "loss": 1.1028, "step": 1048 }, { "epoch": 4.246963562753036, "grad_norm": 0.2163761483510105, "learning_rate": 2.703104292151164e-06, "loss": 1.1011, "step": 1049 }, { "epoch": 4.251012145748988, "grad_norm": 0.20615060071672003, "learning_rate": 2.6747809877527607e-06, "loss": 1.1118, "step": 1050 }, { "epoch": 4.255060728744939, "grad_norm": 0.21930743530353694, "learning_rate": 2.6465962153439082e-06, "loss": 1.0721, "step": 1051 }, { "epoch": 4.2591093117408905, "grad_norm": 0.22279957626756208, "learning_rate": 2.618550200289303e-06, "loss": 1.1372, "step": 1052 }, { "epoch": 4.2631578947368425, "grad_norm": 0.2120936891152232, "learning_rate": 2.59064316684412e-06, "loss": 1.0958, "step": 1053 }, { "epoch": 4.267206477732794, "grad_norm": 0.21480406688913747, "learning_rate": 2.562875338152264e-06, "loss": 1.125, "step": 1054 }, { "epoch": 4.271255060728745, "grad_norm": 0.22095073313550329, "learning_rate": 2.5352469362445552e-06, "loss": 1.1288, "step": 1055 }, { "epoch": 4.275303643724697, "grad_norm": 0.20605299075629707, "learning_rate": 2.5077581820369523e-06, "loss": 1.1039, "step": 1056 }, { "epoch": 4.279352226720648, "grad_norm": 0.21949053460962747, "learning_rate": 2.480409295328803e-06, "loss": 1.1157, "step": 1057 }, { "epoch": 4.283400809716599, "grad_norm": 0.21326189947125082, "learning_rate": 2.45320049480108e-06, "loss": 1.0925, "step": 1058 }, { "epoch": 4.287449392712551, "grad_norm": 0.20529707498712965, "learning_rate": 2.4261319980146293e-06, "loss": 1.1105, "step": 1059 }, { "epoch": 4.291497975708502, "grad_norm": 0.22486736681980896, "learning_rate": 2.399204021408421e-06, "loss": 1.1234, "step": 1060 }, { "epoch": 4.295546558704453, "grad_norm": 0.21809626345028646, "learning_rate": 2.3724167802978395e-06, "loss": 1.0955, "step": 1061 }, { "epoch": 4.299595141700405, "grad_norm": 0.21138516831864188, "learning_rate": 2.3457704888729625e-06, "loss": 1.1251, "step": 1062 }, { "epoch": 4.303643724696356, "grad_norm": 0.23021375625585322, "learning_rate": 2.3192653601968162e-06, "loss": 1.1179, "step": 1063 }, { "epoch": 4.3076923076923075, "grad_norm": 0.21255184637312077, "learning_rate": 2.2929016062037057e-06, "loss": 1.0894, "step": 1064 }, { "epoch": 4.3117408906882595, "grad_norm": 0.213643464016218, "learning_rate": 2.2666794376975055e-06, "loss": 1.1181, "step": 1065 }, { "epoch": 4.315789473684211, "grad_norm": 0.2175573862814248, "learning_rate": 2.24059906434998e-06, "loss": 1.1416, "step": 1066 }, { "epoch": 4.319838056680162, "grad_norm": 0.21161297411977437, "learning_rate": 2.214660694699091e-06, "loss": 1.1006, "step": 1067 }, { "epoch": 4.323886639676114, "grad_norm": 0.2071223675942146, "learning_rate": 2.188864536147355e-06, "loss": 1.0854, "step": 1068 }, { "epoch": 4.327935222672065, "grad_norm": 0.20365890986744195, "learning_rate": 2.1632107949601757e-06, "loss": 1.1218, "step": 1069 }, { "epoch": 4.331983805668016, "grad_norm": 0.2232859698386971, "learning_rate": 2.137699676264171e-06, "loss": 1.0725, "step": 1070 }, { "epoch": 4.336032388663968, "grad_norm": 0.20887083675545062, "learning_rate": 2.1123313840455738e-06, "loss": 1.1143, "step": 1071 }, { "epoch": 4.340080971659919, "grad_norm": 0.21176271327602333, "learning_rate": 2.08710612114857e-06, "loss": 1.074, "step": 1072 }, { "epoch": 4.34412955465587, "grad_norm": 0.21133379511536937, "learning_rate": 2.0620240892736953e-06, "loss": 1.1143, "step": 1073 }, { "epoch": 4.348178137651822, "grad_norm": 0.20079259149889128, "learning_rate": 2.0370854889762e-06, "loss": 1.11, "step": 1074 }, { "epoch": 4.352226720647773, "grad_norm": 0.21166930005712833, "learning_rate": 2.0122905196644726e-06, "loss": 1.0929, "step": 1075 }, { "epoch": 4.3562753036437245, "grad_norm": 0.21303807448370807, "learning_rate": 1.987639379598427e-06, "loss": 1.092, "step": 1076 }, { "epoch": 4.3603238866396765, "grad_norm": 0.2126262599302757, "learning_rate": 1.963132265887919e-06, "loss": 1.1133, "step": 1077 }, { "epoch": 4.364372469635628, "grad_norm": 0.20588262639010188, "learning_rate": 1.9387693744911784e-06, "loss": 1.0917, "step": 1078 }, { "epoch": 4.368421052631579, "grad_norm": 0.22664764084847625, "learning_rate": 1.9145509002132368e-06, "loss": 1.1374, "step": 1079 }, { "epoch": 4.372469635627531, "grad_norm": 0.2085680660670062, "learning_rate": 1.8904770367043723e-06, "loss": 1.1054, "step": 1080 }, { "epoch": 4.376518218623482, "grad_norm": 0.2034162068514733, "learning_rate": 1.8665479764585504e-06, "loss": 1.1126, "step": 1081 }, { "epoch": 4.380566801619433, "grad_norm": 0.1986829354761151, "learning_rate": 1.8427639108118977e-06, "loss": 1.0918, "step": 1082 }, { "epoch": 4.384615384615385, "grad_norm": 0.2080383325922745, "learning_rate": 1.8191250299411755e-06, "loss": 1.103, "step": 1083 }, { "epoch": 4.388663967611336, "grad_norm": 0.2115227508560069, "learning_rate": 1.7956315228622446e-06, "loss": 1.1063, "step": 1084 }, { "epoch": 4.392712550607287, "grad_norm": 0.2139442580844618, "learning_rate": 1.7722835774285553e-06, "loss": 1.1179, "step": 1085 }, { "epoch": 4.396761133603239, "grad_norm": 0.21907701351396514, "learning_rate": 1.7490813803296624e-06, "loss": 1.1218, "step": 1086 }, { "epoch": 4.40080971659919, "grad_norm": 0.20955677753846172, "learning_rate": 1.726025117089718e-06, "loss": 1.1087, "step": 1087 }, { "epoch": 4.4048582995951415, "grad_norm": 0.20450412087640016, "learning_rate": 1.70311497206598e-06, "loss": 1.1203, "step": 1088 }, { "epoch": 4.4089068825910935, "grad_norm": 0.2062692185873478, "learning_rate": 1.6803511284473638e-06, "loss": 1.111, "step": 1089 }, { "epoch": 4.412955465587045, "grad_norm": 0.2155831347571027, "learning_rate": 1.6577337682529538e-06, "loss": 1.1321, "step": 1090 }, { "epoch": 4.417004048582996, "grad_norm": 0.21050694725540625, "learning_rate": 1.6352630723305617e-06, "loss": 1.1156, "step": 1091 }, { "epoch": 4.421052631578947, "grad_norm": 0.20742957210952495, "learning_rate": 1.612939220355272e-06, "loss": 1.0982, "step": 1092 }, { "epoch": 4.425101214574899, "grad_norm": 0.21812805438498553, "learning_rate": 1.5907623908280112e-06, "loss": 1.1291, "step": 1093 }, { "epoch": 4.42914979757085, "grad_norm": 0.21772303088659312, "learning_rate": 1.568732761074121e-06, "loss": 1.0989, "step": 1094 }, { "epoch": 4.433198380566802, "grad_norm": 0.20098700571071568, "learning_rate": 1.5468505072419237e-06, "loss": 1.0994, "step": 1095 }, { "epoch": 4.437246963562753, "grad_norm": 0.20275912097440668, "learning_rate": 1.5251158043013448e-06, "loss": 1.0617, "step": 1096 }, { "epoch": 4.441295546558704, "grad_norm": 0.20628368874042838, "learning_rate": 1.5035288260424885e-06, "loss": 1.1142, "step": 1097 }, { "epoch": 4.445344129554655, "grad_norm": 0.20426362333337156, "learning_rate": 1.4820897450742623e-06, "loss": 1.1355, "step": 1098 }, { "epoch": 4.449392712550607, "grad_norm": 0.222838061084354, "learning_rate": 1.4607987328229767e-06, "loss": 1.1414, "step": 1099 }, { "epoch": 4.4534412955465585, "grad_norm": 0.20550680974431662, "learning_rate": 1.4396559595310056e-06, "loss": 1.0996, "step": 1100 }, { "epoch": 4.4574898785425106, "grad_norm": 0.2131644289553144, "learning_rate": 1.4186615942553973e-06, "loss": 1.1009, "step": 1101 }, { "epoch": 4.461538461538462, "grad_norm": 0.2091833304161884, "learning_rate": 1.3978158048665424e-06, "loss": 1.1095, "step": 1102 }, { "epoch": 4.465587044534413, "grad_norm": 0.2086788880749258, "learning_rate": 1.3771187580468115e-06, "loss": 1.1309, "step": 1103 }, { "epoch": 4.469635627530364, "grad_norm": 0.20873231642645265, "learning_rate": 1.3565706192892392e-06, "loss": 1.1068, "step": 1104 }, { "epoch": 4.473684210526316, "grad_norm": 0.22173779829102483, "learning_rate": 1.3361715528961993e-06, "loss": 1.0896, "step": 1105 }, { "epoch": 4.477732793522267, "grad_norm": 0.20402315409698876, "learning_rate": 1.3159217219780817e-06, "loss": 1.0853, "step": 1106 }, { "epoch": 4.481781376518219, "grad_norm": 0.2130279184514706, "learning_rate": 1.2958212884519949e-06, "loss": 1.119, "step": 1107 }, { "epoch": 4.48582995951417, "grad_norm": 0.19946849549466697, "learning_rate": 1.2758704130404675e-06, "loss": 1.0951, "step": 1108 }, { "epoch": 4.489878542510121, "grad_norm": 0.1989826102786518, "learning_rate": 1.2560692552701738e-06, "loss": 1.1165, "step": 1109 }, { "epoch": 4.493927125506072, "grad_norm": 0.20008689061947024, "learning_rate": 1.2364179734706382e-06, "loss": 1.0905, "step": 1110 }, { "epoch": 4.497975708502024, "grad_norm": 0.20414860239062532, "learning_rate": 1.2169167247729852e-06, "loss": 1.0999, "step": 1111 }, { "epoch": 4.502024291497976, "grad_norm": 0.20811989854167226, "learning_rate": 1.1975656651086864e-06, "loss": 1.1204, "step": 1112 }, { "epoch": 4.506072874493928, "grad_norm": 0.20802673051743847, "learning_rate": 1.1783649492082926e-06, "loss": 1.1412, "step": 1113 }, { "epoch": 4.510121457489879, "grad_norm": 0.19698239439535858, "learning_rate": 1.1593147306002183e-06, "loss": 1.1218, "step": 1114 }, { "epoch": 4.51417004048583, "grad_norm": 0.19656803748224075, "learning_rate": 1.140415161609505e-06, "loss": 1.1196, "step": 1115 }, { "epoch": 4.518218623481781, "grad_norm": 0.1977990511205984, "learning_rate": 1.121666393356604e-06, "loss": 1.1185, "step": 1116 }, { "epoch": 4.522267206477733, "grad_norm": 0.1988962720961008, "learning_rate": 1.1030685757561632e-06, "loss": 1.1133, "step": 1117 }, { "epoch": 4.526315789473684, "grad_norm": 0.20763983819601692, "learning_rate": 1.0846218575158373e-06, "loss": 1.0722, "step": 1118 }, { "epoch": 4.530364372469636, "grad_norm": 0.20934509063045426, "learning_rate": 1.066326386135097e-06, "loss": 1.0954, "step": 1119 }, { "epoch": 4.534412955465587, "grad_norm": 0.20918655562513955, "learning_rate": 1.0481823079040398e-06, "loss": 1.0995, "step": 1120 }, { "epoch": 4.538461538461538, "grad_norm": 0.20753472733635575, "learning_rate": 1.0301897679022344e-06, "loss": 1.127, "step": 1121 }, { "epoch": 4.5425101214574894, "grad_norm": 0.20822595939161612, "learning_rate": 1.0123489099975491e-06, "loss": 1.0895, "step": 1122 }, { "epoch": 4.5465587044534415, "grad_norm": 0.2048218428015393, "learning_rate": 9.9465987684501e-07, "loss": 1.1607, "step": 1123 }, { "epoch": 4.550607287449393, "grad_norm": 0.2180491721707481, "learning_rate": 9.771228098856534e-07, "loss": 1.1085, "step": 1124 }, { "epoch": 4.554655870445345, "grad_norm": 0.19943338954702808, "learning_rate": 9.597378493454013e-07, "loss": 1.1038, "step": 1125 }, { "epoch": 4.558704453441296, "grad_norm": 0.20391779856926773, "learning_rate": 9.425051342339353e-07, "loss": 1.1314, "step": 1126 }, { "epoch": 4.562753036437247, "grad_norm": 0.20335705671123624, "learning_rate": 9.254248023435864e-07, "loss": 1.1025, "step": 1127 }, { "epoch": 4.566801619433198, "grad_norm": 0.2129363176837609, "learning_rate": 9.084969902482288e-07, "loss": 1.1037, "step": 1128 }, { "epoch": 4.57085020242915, "grad_norm": 0.21508666955779934, "learning_rate": 8.917218333021993e-07, "loss": 1.1053, "step": 1129 }, { "epoch": 4.574898785425101, "grad_norm": 0.21047375819083272, "learning_rate": 8.750994656392109e-07, "loss": 1.0989, "step": 1130 }, { "epoch": 4.578947368421053, "grad_norm": 0.2198509715001774, "learning_rate": 8.58630020171265e-07, "loss": 1.124, "step": 1131 }, { "epoch": 4.582995951417004, "grad_norm": 0.2073548904467989, "learning_rate": 8.423136285876099e-07, "loss": 1.1107, "step": 1132 }, { "epoch": 4.587044534412955, "grad_norm": 0.21085410081768008, "learning_rate": 8.26150421353682e-07, "loss": 1.104, "step": 1133 }, { "epoch": 4.5910931174089065, "grad_norm": 0.21105473945777434, "learning_rate": 8.101405277100549e-07, "loss": 1.1081, "step": 1134 }, { "epoch": 4.5951417004048585, "grad_norm": 0.2052746199259862, "learning_rate": 7.942840756714077e-07, "loss": 1.095, "step": 1135 }, { "epoch": 4.59919028340081, "grad_norm": 0.21291118334041093, "learning_rate": 7.785811920255093e-07, "loss": 1.0997, "step": 1136 }, { "epoch": 4.603238866396762, "grad_norm": 0.19628663553533546, "learning_rate": 7.630320023322024e-07, "loss": 1.1285, "step": 1137 }, { "epoch": 4.607287449392713, "grad_norm": 0.20071153808206219, "learning_rate": 7.476366309223903e-07, "loss": 1.1047, "step": 1138 }, { "epoch": 4.611336032388664, "grad_norm": 0.22235040038788959, "learning_rate": 7.323952008970537e-07, "loss": 1.1082, "step": 1139 }, { "epoch": 4.615384615384615, "grad_norm": 0.1940399509119476, "learning_rate": 7.173078341262618e-07, "loss": 1.0965, "step": 1140 }, { "epoch": 4.619433198380567, "grad_norm": 0.2176755007754408, "learning_rate": 7.023746512481989e-07, "loss": 1.0886, "step": 1141 }, { "epoch": 4.623481781376518, "grad_norm": 0.2026577448320902, "learning_rate": 6.875957716681902e-07, "loss": 1.113, "step": 1142 }, { "epoch": 4.62753036437247, "grad_norm": 0.2012726075333039, "learning_rate": 6.729713135577687e-07, "loss": 1.1064, "step": 1143 }, { "epoch": 4.631578947368421, "grad_norm": 0.201894341452953, "learning_rate": 6.585013938537143e-07, "loss": 1.1471, "step": 1144 }, { "epoch": 4.635627530364372, "grad_norm": 0.19509776092416609, "learning_rate": 6.441861282571115e-07, "loss": 1.0993, "step": 1145 }, { "epoch": 4.6396761133603235, "grad_norm": 0.20807939646601378, "learning_rate": 6.300256312324471e-07, "loss": 1.1055, "step": 1146 }, { "epoch": 4.6437246963562755, "grad_norm": 0.20481196644053098, "learning_rate": 6.160200160066776e-07, "loss": 1.104, "step": 1147 }, { "epoch": 4.647773279352227, "grad_norm": 0.20097503917290405, "learning_rate": 6.021693945683327e-07, "loss": 1.0904, "step": 1148 }, { "epoch": 4.651821862348179, "grad_norm": 0.1991400197563987, "learning_rate": 5.884738776666044e-07, "loss": 1.121, "step": 1149 }, { "epoch": 4.65587044534413, "grad_norm": 0.2106382182733694, "learning_rate": 5.749335748104878e-07, "loss": 1.1057, "step": 1150 }, { "epoch": 4.659919028340081, "grad_norm": 0.2022037104687257, "learning_rate": 5.615485942678778e-07, "loss": 1.1284, "step": 1151 }, { "epoch": 4.663967611336032, "grad_norm": 0.19312884751900086, "learning_rate": 5.483190430647289e-07, "loss": 1.0914, "step": 1152 }, { "epoch": 4.668016194331984, "grad_norm": 0.20732880444304708, "learning_rate": 5.352450269841747e-07, "loss": 1.0993, "step": 1153 }, { "epoch": 4.672064777327935, "grad_norm": 0.19495570184417643, "learning_rate": 5.22326650565701e-07, "loss": 1.0823, "step": 1154 }, { "epoch": 4.676113360323887, "grad_norm": 0.20614946412769342, "learning_rate": 5.095640171043048e-07, "loss": 1.105, "step": 1155 }, { "epoch": 4.680161943319838, "grad_norm": 0.2206952649549456, "learning_rate": 4.969572286496594e-07, "loss": 1.1103, "step": 1156 }, { "epoch": 4.684210526315789, "grad_norm": 0.20544552890986237, "learning_rate": 4.845063860053079e-07, "loss": 1.1035, "step": 1157 }, { "epoch": 4.6882591093117405, "grad_norm": 0.20479654954087098, "learning_rate": 4.7221158872785997e-07, "loss": 1.0963, "step": 1158 }, { "epoch": 4.6923076923076925, "grad_norm": 0.19952454592399288, "learning_rate": 4.600729351261857e-07, "loss": 1.0898, "step": 1159 }, { "epoch": 4.696356275303644, "grad_norm": 0.20709069224626112, "learning_rate": 4.4809052226063355e-07, "loss": 1.1365, "step": 1160 }, { "epoch": 4.700404858299595, "grad_norm": 0.20342904478890697, "learning_rate": 4.3626444594226046e-07, "loss": 1.1106, "step": 1161 }, { "epoch": 4.704453441295547, "grad_norm": 0.1974447718756348, "learning_rate": 4.245948007320588e-07, "loss": 1.1461, "step": 1162 }, { "epoch": 4.708502024291498, "grad_norm": 0.20528479677846317, "learning_rate": 4.130816799401971e-07, "loss": 1.0968, "step": 1163 }, { "epoch": 4.712550607287449, "grad_norm": 0.2033969916647999, "learning_rate": 4.017251756252827e-07, "loss": 1.0998, "step": 1164 }, { "epoch": 4.716599190283401, "grad_norm": 0.21815552141076522, "learning_rate": 3.9052537859362473e-07, "loss": 1.1245, "step": 1165 }, { "epoch": 4.720647773279352, "grad_norm": 0.2108504352626556, "learning_rate": 3.7948237839849687e-07, "loss": 1.1012, "step": 1166 }, { "epoch": 4.724696356275303, "grad_norm": 0.2014523926536759, "learning_rate": 3.6859626333943797e-07, "loss": 1.0963, "step": 1167 }, { "epoch": 4.728744939271255, "grad_norm": 0.20464846231603087, "learning_rate": 3.578671204615347e-07, "loss": 1.1549, "step": 1168 }, { "epoch": 4.732793522267206, "grad_norm": 0.19977753126015613, "learning_rate": 3.472950355547267e-07, "loss": 1.1068, "step": 1169 }, { "epoch": 4.7368421052631575, "grad_norm": 0.19651955151889255, "learning_rate": 3.3688009315312244e-07, "loss": 1.1275, "step": 1170 }, { "epoch": 4.7408906882591095, "grad_norm": 0.2043384840616479, "learning_rate": 3.266223765343224e-07, "loss": 1.1114, "step": 1171 }, { "epoch": 4.744939271255061, "grad_norm": 0.20610447875538665, "learning_rate": 3.16521967718757e-07, "loss": 1.1157, "step": 1172 }, { "epoch": 4.748987854251012, "grad_norm": 0.20890601361693784, "learning_rate": 3.0657894746902726e-07, "loss": 1.1147, "step": 1173 }, { "epoch": 4.753036437246964, "grad_norm": 0.20306544886622696, "learning_rate": 2.9679339528925654e-07, "loss": 1.106, "step": 1174 }, { "epoch": 4.757085020242915, "grad_norm": 0.19683893055629859, "learning_rate": 2.871653894244597e-07, "loss": 1.1097, "step": 1175 }, { "epoch": 4.761133603238866, "grad_norm": 0.2015726441653428, "learning_rate": 2.7769500685991266e-07, "loss": 1.0747, "step": 1176 }, { "epoch": 4.765182186234818, "grad_norm": 0.19539217144727755, "learning_rate": 2.683823233205485e-07, "loss": 1.0975, "step": 1177 }, { "epoch": 4.769230769230769, "grad_norm": 0.1975415837473976, "learning_rate": 2.592274132703287e-07, "loss": 1.137, "step": 1178 }, { "epoch": 4.77327935222672, "grad_norm": 0.20103523345823093, "learning_rate": 2.502303499116754e-07, "loss": 1.1075, "step": 1179 }, { "epoch": 4.777327935222672, "grad_norm": 0.19965534991296685, "learning_rate": 2.413912051848666e-07, "loss": 1.1204, "step": 1180 }, { "epoch": 4.781376518218623, "grad_norm": 0.1953467962617736, "learning_rate": 2.3271004976746613e-07, "loss": 1.1118, "step": 1181 }, { "epoch": 4.7854251012145745, "grad_norm": 0.19762117504461152, "learning_rate": 2.2418695307376393e-07, "loss": 1.0686, "step": 1182 }, { "epoch": 4.7894736842105265, "grad_norm": 0.2019143023160018, "learning_rate": 2.1582198325420968e-07, "loss": 1.1372, "step": 1183 }, { "epoch": 4.793522267206478, "grad_norm": 0.1973860337249094, "learning_rate": 2.0761520719488447e-07, "loss": 1.1128, "step": 1184 }, { "epoch": 4.797570850202429, "grad_norm": 0.20330058254934805, "learning_rate": 1.9956669051694798e-07, "loss": 1.1146, "step": 1185 }, { "epoch": 4.801619433198381, "grad_norm": 0.20560781301859138, "learning_rate": 1.916764975761254e-07, "loss": 1.1204, "step": 1186 }, { "epoch": 4.805668016194332, "grad_norm": 0.19404417763547616, "learning_rate": 1.839446914621923e-07, "loss": 1.113, "step": 1187 }, { "epoch": 4.809716599190283, "grad_norm": 0.2036391784785223, "learning_rate": 1.7637133399845962e-07, "loss": 1.1215, "step": 1188 }, { "epoch": 4.813765182186235, "grad_norm": 0.20288583039946192, "learning_rate": 1.6895648574129397e-07, "loss": 1.0921, "step": 1189 }, { "epoch": 4.817813765182186, "grad_norm": 0.19574425520280958, "learning_rate": 1.6170020597962465e-07, "loss": 1.1326, "step": 1190 }, { "epoch": 4.821862348178137, "grad_norm": 0.20617797171988744, "learning_rate": 1.5460255273447078e-07, "loss": 1.094, "step": 1191 }, { "epoch": 4.825910931174089, "grad_norm": 0.19047957806438628, "learning_rate": 1.4766358275847715e-07, "loss": 1.0998, "step": 1192 }, { "epoch": 4.82995951417004, "grad_norm": 0.18730485091297466, "learning_rate": 1.4088335153546573e-07, "loss": 1.1262, "step": 1193 }, { "epoch": 4.834008097165992, "grad_norm": 0.21115669851731642, "learning_rate": 1.3426191327998496e-07, "loss": 1.128, "step": 1194 }, { "epoch": 4.838056680161944, "grad_norm": 0.1912256003947877, "learning_rate": 1.277993209368744e-07, "loss": 1.0964, "step": 1195 }, { "epoch": 4.842105263157895, "grad_norm": 0.19634934608760596, "learning_rate": 1.214956261808542e-07, "loss": 1.1164, "step": 1196 }, { "epoch": 4.846153846153846, "grad_norm": 0.20016380852341073, "learning_rate": 1.1535087941609846e-07, "loss": 1.1177, "step": 1197 }, { "epoch": 4.850202429149798, "grad_norm": 0.2058486126053852, "learning_rate": 1.0936512977583802e-07, "loss": 1.1358, "step": 1198 }, { "epoch": 4.854251012145749, "grad_norm": 0.2057173927540503, "learning_rate": 1.0353842512196732e-07, "loss": 1.1362, "step": 1199 }, { "epoch": 4.8582995951417, "grad_norm": 0.20819168105840413, "learning_rate": 9.787081204466253e-08, "loss": 1.0697, "step": 1200 }, { "epoch": 4.862348178137652, "grad_norm": 0.1947815017453404, "learning_rate": 9.236233586200627e-08, "loss": 1.1009, "step": 1201 }, { "epoch": 4.866396761133603, "grad_norm": 0.21343337946162172, "learning_rate": 8.70130406196279e-08, "loss": 1.1108, "step": 1202 }, { "epoch": 4.870445344129554, "grad_norm": 0.19873755035898652, "learning_rate": 8.182296909035047e-08, "loss": 1.0694, "step": 1203 }, { "epoch": 4.874493927125506, "grad_norm": 0.20327588255140538, "learning_rate": 7.679216277384439e-08, "loss": 1.0813, "step": 1204 }, { "epoch": 4.8785425101214575, "grad_norm": 0.2089781625311041, "learning_rate": 7.19206618963053e-08, "loss": 1.1218, "step": 1205 }, { "epoch": 4.882591093117409, "grad_norm": 0.19413496970169974, "learning_rate": 6.720850541012347e-08, "loss": 1.1273, "step": 1206 }, { "epoch": 4.886639676113361, "grad_norm": 0.20604736241413585, "learning_rate": 6.265573099357714e-08, "loss": 1.1262, "step": 1207 }, { "epoch": 4.890688259109312, "grad_norm": 0.19336012996266622, "learning_rate": 5.826237505053067e-08, "loss": 1.0986, "step": 1208 }, { "epoch": 4.894736842105263, "grad_norm": 0.19320635046746293, "learning_rate": 5.4028472710137e-08, "loss": 1.0731, "step": 1209 }, { "epoch": 4.898785425101215, "grad_norm": 0.1961460073465759, "learning_rate": 4.9954057826571146e-08, "loss": 1.0778, "step": 1210 }, { "epoch": 4.902834008097166, "grad_norm": 0.19894967944795935, "learning_rate": 4.6039162978743776e-08, "loss": 1.1409, "step": 1211 }, { "epoch": 4.906882591093117, "grad_norm": 0.206907012279243, "learning_rate": 4.228381947004812e-08, "loss": 1.1187, "step": 1212 }, { "epoch": 4.910931174089069, "grad_norm": 0.20333835516789045, "learning_rate": 3.868805732811343e-08, "loss": 1.1, "step": 1213 }, { "epoch": 4.91497975708502, "grad_norm": 0.198677936006855, "learning_rate": 3.525190530455636e-08, "loss": 1.1077, "step": 1214 }, { "epoch": 4.919028340080971, "grad_norm": 0.20538614982734152, "learning_rate": 3.197539087475887e-08, "loss": 1.1287, "step": 1215 }, { "epoch": 4.923076923076923, "grad_norm": 0.19663057375074414, "learning_rate": 2.8858540237641786e-08, "loss": 1.1155, "step": 1216 }, { "epoch": 4.9271255060728745, "grad_norm": 0.19762711106738737, "learning_rate": 2.5901378315458247e-08, "loss": 1.084, "step": 1217 }, { "epoch": 4.931174089068826, "grad_norm": 0.1861784058415082, "learning_rate": 2.3103928753598347e-08, "loss": 1.0887, "step": 1218 }, { "epoch": 4.935222672064778, "grad_norm": 0.20456373610730685, "learning_rate": 2.0466213920393718e-08, "loss": 1.1163, "step": 1219 }, { "epoch": 4.939271255060729, "grad_norm": 0.19368082773606035, "learning_rate": 1.7988254906942115e-08, "loss": 1.1485, "step": 1220 }, { "epoch": 4.94331983805668, "grad_norm": 0.19371668590377009, "learning_rate": 1.5670071526936447e-08, "loss": 1.1161, "step": 1221 }, { "epoch": 4.947368421052632, "grad_norm": 0.2058538064948442, "learning_rate": 1.3511682316509344e-08, "loss": 1.1146, "step": 1222 }, { "epoch": 4.951417004048583, "grad_norm": 0.19323570132200318, "learning_rate": 1.1513104534086605e-08, "loss": 1.1292, "step": 1223 }, { "epoch": 4.955465587044534, "grad_norm": 0.20525367681955428, "learning_rate": 9.67435416023843e-09, "loss": 1.1149, "step": 1224 }, { "epoch": 4.959514170040486, "grad_norm": 0.19636464835685152, "learning_rate": 7.995445897566178e-09, "loss": 1.0821, "step": 1225 }, { "epoch": 4.963562753036437, "grad_norm": 0.19515299121860075, "learning_rate": 6.476393170578021e-09, "loss": 1.1148, "step": 1226 }, { "epoch": 4.967611336032388, "grad_norm": 0.2101592465515446, "learning_rate": 5.11720812557348e-09, "loss": 1.1117, "step": 1227 }, { "epoch": 4.97165991902834, "grad_norm": 0.18739082498898638, "learning_rate": 3.917901630563492e-09, "loss": 1.1167, "step": 1228 }, { "epoch": 4.9757085020242915, "grad_norm": 0.19515894836891506, "learning_rate": 2.878483275170485e-09, "loss": 1.1077, "step": 1229 }, { "epoch": 4.979757085020243, "grad_norm": 0.1930682802529107, "learning_rate": 1.998961370555108e-09, "loss": 1.1185, "step": 1230 }, { "epoch": 4.983805668016195, "grad_norm": 0.19390243142383376, "learning_rate": 1.2793429493518361e-09, "loss": 1.1094, "step": 1231 }, { "epoch": 4.987854251012146, "grad_norm": 0.20162028820896385, "learning_rate": 7.196337656112384e-10, "loss": 1.1061, "step": 1232 }, { "epoch": 4.991902834008097, "grad_norm": 0.20037661238636442, "learning_rate": 3.198382947511292e-10, "loss": 1.1384, "step": 1233 }, { "epoch": 4.995951417004049, "grad_norm": 0.19960169107117984, "learning_rate": 7.995973352770137e-11, "loss": 1.1439, "step": 1234 }, { "epoch": 5.0, "grad_norm": 0.19192217989320295, "learning_rate": 0.0, "loss": 1.1184, "step": 1235 }, { "epoch": 5.0, "step": 1235, "total_flos": 6.092619449649594e+18, "train_loss": 1.218237387313534, "train_runtime": 24581.7424, "train_samples_per_second": 6.428, "train_steps_per_second": 0.05 } ], "logging_steps": 1, "max_steps": 1235, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 6.092619449649594e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }