{ "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": 6.872058106739549, "learning_rate": 3.2258064516129035e-07, "loss": 1.1007, "step": 1 }, { "epoch": 0.008097165991902834, "grad_norm": 6.582835424031391, "learning_rate": 6.451612903225807e-07, "loss": 1.0663, "step": 2 }, { "epoch": 0.012145748987854251, "grad_norm": 6.419554739609611, "learning_rate": 9.67741935483871e-07, "loss": 1.0541, "step": 3 }, { "epoch": 0.016194331983805668, "grad_norm": 6.284318424194371, "learning_rate": 1.2903225806451614e-06, "loss": 1.0682, "step": 4 }, { "epoch": 0.020242914979757085, "grad_norm": 5.866069602731156, "learning_rate": 1.6129032258064516e-06, "loss": 1.0179, "step": 5 }, { "epoch": 0.024291497975708502, "grad_norm": 5.946497721465402, "learning_rate": 1.935483870967742e-06, "loss": 1.0362, "step": 6 }, { "epoch": 0.02834008097165992, "grad_norm": 4.752237675952469, "learning_rate": 2.2580645161290324e-06, "loss": 1.0024, "step": 7 }, { "epoch": 0.032388663967611336, "grad_norm": 4.480090351722704, "learning_rate": 2.580645161290323e-06, "loss": 0.9706, "step": 8 }, { "epoch": 0.03643724696356275, "grad_norm": 2.4459806342402044, "learning_rate": 2.903225806451613e-06, "loss": 0.9421, "step": 9 }, { "epoch": 0.04048582995951417, "grad_norm": 2.2514438815701894, "learning_rate": 3.225806451612903e-06, "loss": 0.9294, "step": 10 }, { "epoch": 0.044534412955465584, "grad_norm": 2.1572140505761794, "learning_rate": 3.548387096774194e-06, "loss": 0.9515, "step": 11 }, { "epoch": 0.048582995951417005, "grad_norm": 4.149024091919609, "learning_rate": 3.870967741935484e-06, "loss": 0.9508, "step": 12 }, { "epoch": 0.05263157894736842, "grad_norm": 4.625403534187607, "learning_rate": 4.193548387096774e-06, "loss": 0.9491, "step": 13 }, { "epoch": 0.05668016194331984, "grad_norm": 4.2666356678648265, "learning_rate": 4.516129032258065e-06, "loss": 0.9196, "step": 14 }, { "epoch": 0.06072874493927125, "grad_norm": 3.935275604442574, "learning_rate": 4.838709677419355e-06, "loss": 0.8761, "step": 15 }, { "epoch": 0.06477732793522267, "grad_norm": 3.1885637045497774, "learning_rate": 5.161290322580646e-06, "loss": 0.8641, "step": 16 }, { "epoch": 0.06882591093117409, "grad_norm": 2.9113755451313756, "learning_rate": 5.483870967741935e-06, "loss": 0.845, "step": 17 }, { "epoch": 0.0728744939271255, "grad_norm": 2.682385839534161, "learning_rate": 5.806451612903226e-06, "loss": 0.857, "step": 18 }, { "epoch": 0.07692307692307693, "grad_norm": 2.3351094940519705, "learning_rate": 6.129032258064517e-06, "loss": 0.8317, "step": 19 }, { "epoch": 0.08097165991902834, "grad_norm": 1.853639102558088, "learning_rate": 6.451612903225806e-06, "loss": 0.8121, "step": 20 }, { "epoch": 0.08502024291497975, "grad_norm": 1.6685633568198048, "learning_rate": 6.774193548387097e-06, "loss": 0.8176, "step": 21 }, { "epoch": 0.08906882591093117, "grad_norm": 1.6713681677835894, "learning_rate": 7.096774193548388e-06, "loss": 0.8035, "step": 22 }, { "epoch": 0.0931174089068826, "grad_norm": 1.967436100557157, "learning_rate": 7.4193548387096784e-06, "loss": 0.7904, "step": 23 }, { "epoch": 0.09716599190283401, "grad_norm": 1.7496527506410364, "learning_rate": 7.741935483870968e-06, "loss": 0.7871, "step": 24 }, { "epoch": 0.10121457489878542, "grad_norm": 1.5437910395135692, "learning_rate": 8.064516129032258e-06, "loss": 0.7971, "step": 25 }, { "epoch": 0.10526315789473684, "grad_norm": 1.2270571160601054, "learning_rate": 8.387096774193549e-06, "loss": 0.7659, "step": 26 }, { "epoch": 0.10931174089068826, "grad_norm": 1.3001251668249594, "learning_rate": 8.70967741935484e-06, "loss": 0.7516, "step": 27 }, { "epoch": 0.11336032388663968, "grad_norm": 1.2306904526556515, "learning_rate": 9.03225806451613e-06, "loss": 0.7642, "step": 28 }, { "epoch": 0.11740890688259109, "grad_norm": 0.9210746771446101, "learning_rate": 9.35483870967742e-06, "loss": 0.7384, "step": 29 }, { "epoch": 0.1214574898785425, "grad_norm": 0.9521894455224111, "learning_rate": 9.67741935483871e-06, "loss": 0.7721, "step": 30 }, { "epoch": 0.12550607287449392, "grad_norm": 0.9896625362955649, "learning_rate": 1e-05, "loss": 0.7706, "step": 31 }, { "epoch": 0.12955465587044535, "grad_norm": 0.7872712129191323, "learning_rate": 1.0322580645161291e-05, "loss": 0.7389, "step": 32 }, { "epoch": 0.13360323886639677, "grad_norm": 0.7901200549218331, "learning_rate": 1.0645161290322582e-05, "loss": 0.7121, "step": 33 }, { "epoch": 0.13765182186234817, "grad_norm": 0.8230924299545942, "learning_rate": 1.096774193548387e-05, "loss": 0.7447, "step": 34 }, { "epoch": 0.1417004048582996, "grad_norm": 0.8380293605717258, "learning_rate": 1.1290322580645164e-05, "loss": 0.7583, "step": 35 }, { "epoch": 0.145748987854251, "grad_norm": 0.6686168752759989, "learning_rate": 1.1612903225806453e-05, "loss": 0.7285, "step": 36 }, { "epoch": 0.14979757085020243, "grad_norm": 0.771606831428552, "learning_rate": 1.1935483870967743e-05, "loss": 0.7349, "step": 37 }, { "epoch": 0.15384615384615385, "grad_norm": 0.7665620063192806, "learning_rate": 1.2258064516129034e-05, "loss": 0.7221, "step": 38 }, { "epoch": 0.15789473684210525, "grad_norm": 0.6675000236522995, "learning_rate": 1.2580645161290324e-05, "loss": 0.7179, "step": 39 }, { "epoch": 0.16194331983805668, "grad_norm": 0.7089445099348893, "learning_rate": 1.2903225806451613e-05, "loss": 0.6953, "step": 40 }, { "epoch": 0.1659919028340081, "grad_norm": 0.7007529240361191, "learning_rate": 1.3225806451612903e-05, "loss": 0.6946, "step": 41 }, { "epoch": 0.1700404858299595, "grad_norm": 0.6008467264500886, "learning_rate": 1.3548387096774194e-05, "loss": 0.6862, "step": 42 }, { "epoch": 0.17408906882591094, "grad_norm": 0.6633966334094921, "learning_rate": 1.3870967741935486e-05, "loss": 0.7023, "step": 43 }, { "epoch": 0.17813765182186234, "grad_norm": 0.6527908596600178, "learning_rate": 1.4193548387096776e-05, "loss": 0.6903, "step": 44 }, { "epoch": 0.18218623481781376, "grad_norm": 0.6041486688842744, "learning_rate": 1.4516129032258066e-05, "loss": 0.6899, "step": 45 }, { "epoch": 0.1862348178137652, "grad_norm": 0.6441660476490368, "learning_rate": 1.4838709677419357e-05, "loss": 0.6707, "step": 46 }, { "epoch": 0.1902834008097166, "grad_norm": 0.6540944478599673, "learning_rate": 1.5161290322580646e-05, "loss": 0.6679, "step": 47 }, { "epoch": 0.19433198380566802, "grad_norm": 0.623060529703281, "learning_rate": 1.5483870967741936e-05, "loss": 0.6804, "step": 48 }, { "epoch": 0.19838056680161945, "grad_norm": 0.6252797172706698, "learning_rate": 1.5806451612903226e-05, "loss": 0.7047, "step": 49 }, { "epoch": 0.20242914979757085, "grad_norm": 0.6728736701291503, "learning_rate": 1.6129032258064517e-05, "loss": 0.6917, "step": 50 }, { "epoch": 0.20647773279352227, "grad_norm": 0.714912308318795, "learning_rate": 1.6451612903225807e-05, "loss": 0.6836, "step": 51 }, { "epoch": 0.21052631578947367, "grad_norm": 0.625543499908757, "learning_rate": 1.6774193548387098e-05, "loss": 0.6731, "step": 52 }, { "epoch": 0.2145748987854251, "grad_norm": 0.6560706283413559, "learning_rate": 1.7096774193548388e-05, "loss": 0.6601, "step": 53 }, { "epoch": 0.21862348178137653, "grad_norm": 0.8201110071388014, "learning_rate": 1.741935483870968e-05, "loss": 0.6841, "step": 54 }, { "epoch": 0.22267206477732793, "grad_norm": 0.6046209130063102, "learning_rate": 1.774193548387097e-05, "loss": 0.6754, "step": 55 }, { "epoch": 0.22672064777327935, "grad_norm": 0.7103403351753294, "learning_rate": 1.806451612903226e-05, "loss": 0.6683, "step": 56 }, { "epoch": 0.23076923076923078, "grad_norm": 0.8839568791823852, "learning_rate": 1.838709677419355e-05, "loss": 0.6933, "step": 57 }, { "epoch": 0.23481781376518218, "grad_norm": 0.6596000171217445, "learning_rate": 1.870967741935484e-05, "loss": 0.6962, "step": 58 }, { "epoch": 0.2388663967611336, "grad_norm": 0.7507990246225106, "learning_rate": 1.903225806451613e-05, "loss": 0.6494, "step": 59 }, { "epoch": 0.242914979757085, "grad_norm": 0.7000173275159771, "learning_rate": 1.935483870967742e-05, "loss": 0.6439, "step": 60 }, { "epoch": 0.24696356275303644, "grad_norm": 0.7087481854826149, "learning_rate": 1.967741935483871e-05, "loss": 0.6628, "step": 61 }, { "epoch": 0.25101214574898784, "grad_norm": 0.7275844199278112, "learning_rate": 2e-05, "loss": 0.6658, "step": 62 }, { "epoch": 0.2550607287449393, "grad_norm": 0.8439483399999423, "learning_rate": 2.0322580645161292e-05, "loss": 0.6529, "step": 63 }, { "epoch": 0.2591093117408907, "grad_norm": 0.7703950827713967, "learning_rate": 2.0645161290322582e-05, "loss": 0.6581, "step": 64 }, { "epoch": 0.2631578947368421, "grad_norm": 0.686282883043335, "learning_rate": 2.0967741935483873e-05, "loss": 0.6613, "step": 65 }, { "epoch": 0.26720647773279355, "grad_norm": 0.8147412959192025, "learning_rate": 2.1290322580645163e-05, "loss": 0.6373, "step": 66 }, { "epoch": 0.27125506072874495, "grad_norm": 0.7194224439053082, "learning_rate": 2.161290322580645e-05, "loss": 0.6295, "step": 67 }, { "epoch": 0.27530364372469635, "grad_norm": 0.9486993841909753, "learning_rate": 2.193548387096774e-05, "loss": 0.6524, "step": 68 }, { "epoch": 0.2793522267206478, "grad_norm": 0.8240300050020871, "learning_rate": 2.225806451612903e-05, "loss": 0.6712, "step": 69 }, { "epoch": 0.2834008097165992, "grad_norm": 0.7140344595773571, "learning_rate": 2.2580645161290328e-05, "loss": 0.6496, "step": 70 }, { "epoch": 0.2874493927125506, "grad_norm": 0.7773388872004502, "learning_rate": 2.2903225806451615e-05, "loss": 0.6588, "step": 71 }, { "epoch": 0.291497975708502, "grad_norm": 0.6803519279972946, "learning_rate": 2.3225806451612906e-05, "loss": 0.6396, "step": 72 }, { "epoch": 0.29554655870445345, "grad_norm": 0.946225427651021, "learning_rate": 2.3548387096774196e-05, "loss": 0.6624, "step": 73 }, { "epoch": 0.29959514170040485, "grad_norm": 0.6072677238202374, "learning_rate": 2.3870967741935486e-05, "loss": 0.6423, "step": 74 }, { "epoch": 0.30364372469635625, "grad_norm": 0.7975058750116822, "learning_rate": 2.4193548387096777e-05, "loss": 0.641, "step": 75 }, { "epoch": 0.3076923076923077, "grad_norm": 0.8383983434967787, "learning_rate": 2.4516129032258067e-05, "loss": 0.6454, "step": 76 }, { "epoch": 0.3117408906882591, "grad_norm": 0.8172118884308299, "learning_rate": 2.4838709677419358e-05, "loss": 0.6397, "step": 77 }, { "epoch": 0.3157894736842105, "grad_norm": 0.6885646457461496, "learning_rate": 2.5161290322580648e-05, "loss": 0.6601, "step": 78 }, { "epoch": 0.31983805668016196, "grad_norm": 0.7110465375761762, "learning_rate": 2.548387096774194e-05, "loss": 0.628, "step": 79 }, { "epoch": 0.32388663967611336, "grad_norm": 1.048874585287824, "learning_rate": 2.5806451612903226e-05, "loss": 0.6316, "step": 80 }, { "epoch": 0.32793522267206476, "grad_norm": 0.903052188907395, "learning_rate": 2.6129032258064516e-05, "loss": 0.6691, "step": 81 }, { "epoch": 0.3319838056680162, "grad_norm": 0.7520581932313326, "learning_rate": 2.6451612903225806e-05, "loss": 0.6267, "step": 82 }, { "epoch": 0.3360323886639676, "grad_norm": 0.8088680449565709, "learning_rate": 2.6774193548387097e-05, "loss": 0.6099, "step": 83 }, { "epoch": 0.340080971659919, "grad_norm": 0.7001213857341628, "learning_rate": 2.7096774193548387e-05, "loss": 0.6636, "step": 84 }, { "epoch": 0.3441295546558704, "grad_norm": 0.8837283421281316, "learning_rate": 2.7419354838709678e-05, "loss": 0.6201, "step": 85 }, { "epoch": 0.3481781376518219, "grad_norm": 1.0293934708564683, "learning_rate": 2.774193548387097e-05, "loss": 0.6468, "step": 86 }, { "epoch": 0.3522267206477733, "grad_norm": 0.8331657268620833, "learning_rate": 2.8064516129032262e-05, "loss": 0.6141, "step": 87 }, { "epoch": 0.3562753036437247, "grad_norm": 1.1570347924803865, "learning_rate": 2.8387096774193552e-05, "loss": 0.6107, "step": 88 }, { "epoch": 0.3603238866396761, "grad_norm": 0.7874403113168907, "learning_rate": 2.8709677419354843e-05, "loss": 0.6224, "step": 89 }, { "epoch": 0.3643724696356275, "grad_norm": 0.9336919034087356, "learning_rate": 2.9032258064516133e-05, "loss": 0.604, "step": 90 }, { "epoch": 0.3684210526315789, "grad_norm": 0.7697710345172428, "learning_rate": 2.9354838709677423e-05, "loss": 0.6314, "step": 91 }, { "epoch": 0.3724696356275304, "grad_norm": 0.7929019038337892, "learning_rate": 2.9677419354838714e-05, "loss": 0.6152, "step": 92 }, { "epoch": 0.3765182186234818, "grad_norm": 0.7407528100608951, "learning_rate": 3.0000000000000004e-05, "loss": 0.6213, "step": 93 }, { "epoch": 0.3805668016194332, "grad_norm": 0.8592621629421878, "learning_rate": 3.032258064516129e-05, "loss": 0.614, "step": 94 }, { "epoch": 0.38461538461538464, "grad_norm": 0.8749285938701279, "learning_rate": 3.0645161290322585e-05, "loss": 0.6105, "step": 95 }, { "epoch": 0.38866396761133604, "grad_norm": 0.7008481551666504, "learning_rate": 3.096774193548387e-05, "loss": 0.6156, "step": 96 }, { "epoch": 0.39271255060728744, "grad_norm": 0.8383409021670892, "learning_rate": 3.1290322580645166e-05, "loss": 0.658, "step": 97 }, { "epoch": 0.3967611336032389, "grad_norm": 0.7781527180072156, "learning_rate": 3.161290322580645e-05, "loss": 0.6125, "step": 98 }, { "epoch": 0.4008097165991903, "grad_norm": 0.845225588917659, "learning_rate": 3.193548387096774e-05, "loss": 0.6385, "step": 99 }, { "epoch": 0.4048582995951417, "grad_norm": 0.6953039253612868, "learning_rate": 3.2258064516129034e-05, "loss": 0.6005, "step": 100 }, { "epoch": 0.4089068825910931, "grad_norm": 0.848335640943964, "learning_rate": 3.258064516129033e-05, "loss": 0.6101, "step": 101 }, { "epoch": 0.41295546558704455, "grad_norm": 0.6283334040756356, "learning_rate": 3.2903225806451614e-05, "loss": 0.6307, "step": 102 }, { "epoch": 0.41700404858299595, "grad_norm": 0.8093696869239174, "learning_rate": 3.322580645161291e-05, "loss": 0.6154, "step": 103 }, { "epoch": 0.42105263157894735, "grad_norm": 0.6900304295340621, "learning_rate": 3.3548387096774195e-05, "loss": 0.6366, "step": 104 }, { "epoch": 0.4251012145748988, "grad_norm": 0.7956768203341333, "learning_rate": 3.387096774193549e-05, "loss": 0.6357, "step": 105 }, { "epoch": 0.4291497975708502, "grad_norm": 0.6782918489012386, "learning_rate": 3.4193548387096776e-05, "loss": 0.6009, "step": 106 }, { "epoch": 0.4331983805668016, "grad_norm": 0.9141958409404484, "learning_rate": 3.451612903225807e-05, "loss": 0.6328, "step": 107 }, { "epoch": 0.43724696356275305, "grad_norm": 0.6478924489952911, "learning_rate": 3.483870967741936e-05, "loss": 0.5918, "step": 108 }, { "epoch": 0.44129554655870445, "grad_norm": 0.7613123941392054, "learning_rate": 3.516129032258065e-05, "loss": 0.5953, "step": 109 }, { "epoch": 0.44534412955465585, "grad_norm": 0.9460876461396197, "learning_rate": 3.548387096774194e-05, "loss": 0.5998, "step": 110 }, { "epoch": 0.4493927125506073, "grad_norm": 1.1586812916889857, "learning_rate": 3.5806451612903225e-05, "loss": 0.6209, "step": 111 }, { "epoch": 0.4534412955465587, "grad_norm": 0.8302243864363696, "learning_rate": 3.612903225806452e-05, "loss": 0.6168, "step": 112 }, { "epoch": 0.4574898785425101, "grad_norm": 0.857647659612295, "learning_rate": 3.6451612903225805e-05, "loss": 0.6197, "step": 113 }, { "epoch": 0.46153846153846156, "grad_norm": 0.8342782732938426, "learning_rate": 3.67741935483871e-05, "loss": 0.6303, "step": 114 }, { "epoch": 0.46558704453441296, "grad_norm": 1.359074196204805, "learning_rate": 3.7096774193548386e-05, "loss": 0.6206, "step": 115 }, { "epoch": 0.46963562753036436, "grad_norm": 0.7949781449294608, "learning_rate": 3.741935483870968e-05, "loss": 0.6203, "step": 116 }, { "epoch": 0.47368421052631576, "grad_norm": 0.8357858511052211, "learning_rate": 3.7741935483870974e-05, "loss": 0.5973, "step": 117 }, { "epoch": 0.4777327935222672, "grad_norm": 1.003883172796933, "learning_rate": 3.806451612903226e-05, "loss": 0.6117, "step": 118 }, { "epoch": 0.4817813765182186, "grad_norm": 1.008794448485006, "learning_rate": 3.8387096774193555e-05, "loss": 0.5951, "step": 119 }, { "epoch": 0.48582995951417, "grad_norm": 0.7857521278453519, "learning_rate": 3.870967741935484e-05, "loss": 0.6178, "step": 120 }, { "epoch": 0.4898785425101215, "grad_norm": 0.9168668344852157, "learning_rate": 3.9032258064516135e-05, "loss": 0.595, "step": 121 }, { "epoch": 0.4939271255060729, "grad_norm": 0.9103092929005583, "learning_rate": 3.935483870967742e-05, "loss": 0.6069, "step": 122 }, { "epoch": 0.4979757085020243, "grad_norm": 0.7423214490653974, "learning_rate": 3.9677419354838716e-05, "loss": 0.5787, "step": 123 }, { "epoch": 0.5020242914979757, "grad_norm": 0.8817889131037113, "learning_rate": 4e-05, "loss": 0.5935, "step": 124 }, { "epoch": 0.5060728744939271, "grad_norm": 0.8127287071695587, "learning_rate": 3.9999920040266474e-05, "loss": 0.616, "step": 125 }, { "epoch": 0.5101214574898786, "grad_norm": 0.8478683696472399, "learning_rate": 3.999968016170525e-05, "loss": 0.6118, "step": 126 }, { "epoch": 0.5141700404858299, "grad_norm": 1.0128966517562308, "learning_rate": 3.9999280366234394e-05, "loss": 0.6104, "step": 127 }, { "epoch": 0.5182186234817814, "grad_norm": 0.8943419501949211, "learning_rate": 3.999872065705065e-05, "loss": 0.5894, "step": 128 }, { "epoch": 0.5222672064777328, "grad_norm": 0.6605883352655864, "learning_rate": 3.999800103862945e-05, "loss": 0.6196, "step": 129 }, { "epoch": 0.5263157894736842, "grad_norm": 1.0905285444194854, "learning_rate": 3.9997121516724834e-05, "loss": 0.6016, "step": 130 }, { "epoch": 0.5303643724696356, "grad_norm": 0.9966401477417336, "learning_rate": 3.999608209836944e-05, "loss": 0.6005, "step": 131 }, { "epoch": 0.5344129554655871, "grad_norm": 0.7319599579572226, "learning_rate": 3.999488279187443e-05, "loss": 0.5839, "step": 132 }, { "epoch": 0.5384615384615384, "grad_norm": 1.018181337528223, "learning_rate": 3.9993523606829425e-05, "loss": 0.6197, "step": 133 }, { "epoch": 0.5425101214574899, "grad_norm": 0.6950577681037384, "learning_rate": 3.9992004554102435e-05, "loss": 0.598, "step": 134 }, { "epoch": 0.5465587044534413, "grad_norm": 0.7702898612258848, "learning_rate": 3.999032564583976e-05, "loss": 0.5936, "step": 135 }, { "epoch": 0.5506072874493927, "grad_norm": 0.864982108125179, "learning_rate": 3.998848689546591e-05, "loss": 0.5913, "step": 136 }, { "epoch": 0.5546558704453441, "grad_norm": 0.7524307703029148, "learning_rate": 3.9986488317683496e-05, "loss": 0.6083, "step": 137 }, { "epoch": 0.5587044534412956, "grad_norm": 0.6717709418273798, "learning_rate": 3.9984329928473067e-05, "loss": 0.5981, "step": 138 }, { "epoch": 0.562753036437247, "grad_norm": 0.6274705252132531, "learning_rate": 3.998201174509306e-05, "loss": 0.6069, "step": 139 }, { "epoch": 0.5668016194331984, "grad_norm": 0.6641380218594632, "learning_rate": 3.997953378607961e-05, "loss": 0.6048, "step": 140 }, { "epoch": 0.5708502024291497, "grad_norm": 0.6954843888358881, "learning_rate": 3.9976896071246403e-05, "loss": 0.6047, "step": 141 }, { "epoch": 0.5748987854251012, "grad_norm": 0.6660752805187377, "learning_rate": 3.997409862168454e-05, "loss": 0.5849, "step": 142 }, { "epoch": 0.5789473684210527, "grad_norm": 0.6528563372320194, "learning_rate": 3.997114145976237e-05, "loss": 0.5914, "step": 143 }, { "epoch": 0.582995951417004, "grad_norm": 0.6432466879056904, "learning_rate": 3.9968024609125245e-05, "loss": 0.6162, "step": 144 }, { "epoch": 0.5870445344129555, "grad_norm": 0.6604439759254368, "learning_rate": 3.996474809469545e-05, "loss": 0.5586, "step": 145 }, { "epoch": 0.5910931174089069, "grad_norm": 0.6215528387194574, "learning_rate": 3.996131194267189e-05, "loss": 0.5987, "step": 146 }, { "epoch": 0.5951417004048583, "grad_norm": 0.7419683373704007, "learning_rate": 3.995771618052995e-05, "loss": 0.6102, "step": 147 }, { "epoch": 0.5991902834008097, "grad_norm": 0.6240089321907272, "learning_rate": 3.9953960837021256e-05, "loss": 0.5838, "step": 148 }, { "epoch": 0.6032388663967612, "grad_norm": 0.7230784949820379, "learning_rate": 3.995004594217343e-05, "loss": 0.5796, "step": 149 }, { "epoch": 0.6072874493927125, "grad_norm": 0.6221023979578855, "learning_rate": 3.994597152728987e-05, "loss": 0.589, "step": 150 }, { "epoch": 0.611336032388664, "grad_norm": 0.576701467251997, "learning_rate": 3.994173762494947e-05, "loss": 0.5982, "step": 151 }, { "epoch": 0.6153846153846154, "grad_norm": 0.6766798115573939, "learning_rate": 3.9937344269006424e-05, "loss": 0.5888, "step": 152 }, { "epoch": 0.6194331983805668, "grad_norm": 0.5896486733645082, "learning_rate": 3.993279149458988e-05, "loss": 0.575, "step": 153 }, { "epoch": 0.6234817813765182, "grad_norm": 0.7076382223626322, "learning_rate": 3.9928079338103695e-05, "loss": 0.5725, "step": 154 }, { "epoch": 0.6275303643724697, "grad_norm": 0.6101402286453745, "learning_rate": 3.992320783722616e-05, "loss": 0.5992, "step": 155 }, { "epoch": 0.631578947368421, "grad_norm": 0.70197736015413, "learning_rate": 3.991817703090965e-05, "loss": 0.6146, "step": 156 }, { "epoch": 0.6356275303643725, "grad_norm": 0.7092541829567073, "learning_rate": 3.991298695938038e-05, "loss": 0.6038, "step": 157 }, { "epoch": 0.6396761133603239, "grad_norm": 0.6238200413578407, "learning_rate": 3.9907637664138e-05, "loss": 0.5979, "step": 158 }, { "epoch": 0.6437246963562753, "grad_norm": 0.6897494197264318, "learning_rate": 3.990212918795534e-05, "loss": 0.5754, "step": 159 }, { "epoch": 0.6477732793522267, "grad_norm": 0.7867835552426475, "learning_rate": 3.9896461574878036e-05, "loss": 0.5831, "step": 160 }, { "epoch": 0.6518218623481782, "grad_norm": 0.7064265544911174, "learning_rate": 3.989063487022416e-05, "loss": 0.6036, "step": 161 }, { "epoch": 0.6558704453441295, "grad_norm": 0.5691577074496236, "learning_rate": 3.9884649120583903e-05, "loss": 0.6005, "step": 162 }, { "epoch": 0.659919028340081, "grad_norm": 0.6821053527216691, "learning_rate": 3.987850437381915e-05, "loss": 0.5721, "step": 163 }, { "epoch": 0.6639676113360324, "grad_norm": 0.6569374671572822, "learning_rate": 3.987220067906313e-05, "loss": 0.597, "step": 164 }, { "epoch": 0.6680161943319838, "grad_norm": 0.634527791529588, "learning_rate": 3.986573808672002e-05, "loss": 0.5983, "step": 165 }, { "epoch": 0.6720647773279352, "grad_norm": 0.7029264594888674, "learning_rate": 3.9859116648464534e-05, "loss": 0.5807, "step": 166 }, { "epoch": 0.6761133603238867, "grad_norm": 0.5457550547652635, "learning_rate": 3.985233641724152e-05, "loss": 0.5799, "step": 167 }, { "epoch": 0.680161943319838, "grad_norm": 0.7504390549774846, "learning_rate": 3.984539744726554e-05, "loss": 0.594, "step": 168 }, { "epoch": 0.6842105263157895, "grad_norm": 0.6460999925577385, "learning_rate": 3.983829979402038e-05, "loss": 0.5746, "step": 169 }, { "epoch": 0.6882591093117408, "grad_norm": 0.6362425712195046, "learning_rate": 3.983104351425871e-05, "loss": 0.5786, "step": 170 }, { "epoch": 0.6923076923076923, "grad_norm": 0.7305487972067727, "learning_rate": 3.982362866600154e-05, "loss": 0.5911, "step": 171 }, { "epoch": 0.6963562753036437, "grad_norm": 0.5275305683253574, "learning_rate": 3.9816055308537806e-05, "loss": 0.5673, "step": 172 }, { "epoch": 0.7004048582995951, "grad_norm": 0.8087043605226237, "learning_rate": 3.980832350242388e-05, "loss": 0.5539, "step": 173 }, { "epoch": 0.7044534412955465, "grad_norm": 0.6410343201569608, "learning_rate": 3.980043330948306e-05, "loss": 0.5822, "step": 174 }, { "epoch": 0.708502024291498, "grad_norm": 0.7286943086017676, "learning_rate": 3.9792384792805124e-05, "loss": 0.5827, "step": 175 }, { "epoch": 0.7125506072874493, "grad_norm": 0.6173392996306408, "learning_rate": 3.978417801674579e-05, "loss": 0.5671, "step": 176 }, { "epoch": 0.7165991902834008, "grad_norm": 0.7271390270823681, "learning_rate": 3.9775813046926244e-05, "loss": 0.5914, "step": 177 }, { "epoch": 0.7206477732793523, "grad_norm": 0.6346646375201048, "learning_rate": 3.976728995023254e-05, "loss": 0.5782, "step": 178 }, { "epoch": 0.7246963562753036, "grad_norm": 0.6729812788384931, "learning_rate": 3.975860879481514e-05, "loss": 0.5772, "step": 179 }, { "epoch": 0.728744939271255, "grad_norm": 0.5419390410419149, "learning_rate": 3.974976965008833e-05, "loss": 0.5798, "step": 180 }, { "epoch": 0.7327935222672065, "grad_norm": 0.5664383678948021, "learning_rate": 3.9740772586729674e-05, "loss": 0.5882, "step": 181 }, { "epoch": 0.7368421052631579, "grad_norm": 0.5581985058851804, "learning_rate": 3.973161767667946e-05, "loss": 0.577, "step": 182 }, { "epoch": 0.7408906882591093, "grad_norm": 0.5126857004140888, "learning_rate": 3.972230499314009e-05, "loss": 0.5573, "step": 183 }, { "epoch": 0.7449392712550608, "grad_norm": 0.8671814648608853, "learning_rate": 3.9712834610575545e-05, "loss": 0.5872, "step": 184 }, { "epoch": 0.7489878542510121, "grad_norm": 0.5446897285769183, "learning_rate": 3.9703206604710746e-05, "loss": 0.5807, "step": 185 }, { "epoch": 0.7530364372469636, "grad_norm": 0.8180826207525269, "learning_rate": 3.969342105253098e-05, "loss": 0.5728, "step": 186 }, { "epoch": 0.757085020242915, "grad_norm": 0.6609212380498105, "learning_rate": 3.9683478032281246e-05, "loss": 0.5899, "step": 187 }, { "epoch": 0.7611336032388664, "grad_norm": 0.7200485621533216, "learning_rate": 3.967337762346568e-05, "loss": 0.5684, "step": 188 }, { "epoch": 0.7651821862348178, "grad_norm": 0.733730671402651, "learning_rate": 3.9663119906846885e-05, "loss": 0.5411, "step": 189 }, { "epoch": 0.7692307692307693, "grad_norm": 0.5878336566038642, "learning_rate": 3.965270496444528e-05, "loss": 0.5558, "step": 190 }, { "epoch": 0.7732793522267206, "grad_norm": 0.6854783596666402, "learning_rate": 3.9642132879538465e-05, "loss": 0.5718, "step": 191 }, { "epoch": 0.7773279352226721, "grad_norm": 0.5582540505477989, "learning_rate": 3.9631403736660566e-05, "loss": 0.5952, "step": 192 }, { "epoch": 0.7813765182186235, "grad_norm": 0.5625973008795583, "learning_rate": 3.962051762160151e-05, "loss": 0.5533, "step": 193 }, { "epoch": 0.7854251012145749, "grad_norm": 0.4889707381430629, "learning_rate": 3.960947462140638e-05, "loss": 0.572, "step": 194 }, { "epoch": 0.7894736842105263, "grad_norm": 0.5367982177402775, "learning_rate": 3.959827482437472e-05, "loss": 0.5787, "step": 195 }, { "epoch": 0.7935222672064778, "grad_norm": 0.5180779305249603, "learning_rate": 3.958691832005981e-05, "loss": 0.5977, "step": 196 }, { "epoch": 0.7975708502024291, "grad_norm": 0.48251656901299356, "learning_rate": 3.9575405199267944e-05, "loss": 0.5541, "step": 197 }, { "epoch": 0.8016194331983806, "grad_norm": 0.5418336423694647, "learning_rate": 3.956373555405774e-05, "loss": 0.5528, "step": 198 }, { "epoch": 0.805668016194332, "grad_norm": 0.517677628881841, "learning_rate": 3.955190947773937e-05, "loss": 0.5668, "step": 199 }, { "epoch": 0.8097165991902834, "grad_norm": 0.5473523473852315, "learning_rate": 3.9539927064873824e-05, "loss": 0.5565, "step": 200 }, { "epoch": 0.8137651821862348, "grad_norm": 0.5532069644963435, "learning_rate": 3.952778841127214e-05, "loss": 0.5665, "step": 201 }, { "epoch": 0.8178137651821862, "grad_norm": 0.5032956640191627, "learning_rate": 3.95154936139947e-05, "loss": 0.5664, "step": 202 }, { "epoch": 0.8218623481781376, "grad_norm": 0.5540650645701493, "learning_rate": 3.950304277135034e-05, "loss": 0.5821, "step": 203 }, { "epoch": 0.8259109311740891, "grad_norm": 0.5103885087029932, "learning_rate": 3.94904359828957e-05, "loss": 0.5424, "step": 204 }, { "epoch": 0.8299595141700404, "grad_norm": 0.5800481217643471, "learning_rate": 3.94776733494343e-05, "loss": 0.5703, "step": 205 }, { "epoch": 0.8340080971659919, "grad_norm": 0.4966026116818763, "learning_rate": 3.9464754973015826e-05, "loss": 0.5671, "step": 206 }, { "epoch": 0.8380566801619433, "grad_norm": 0.5670614168616237, "learning_rate": 3.9451680956935275e-05, "loss": 0.5734, "step": 207 }, { "epoch": 0.8421052631578947, "grad_norm": 0.5915346434539885, "learning_rate": 3.943845140573213e-05, "loss": 0.5689, "step": 208 }, { "epoch": 0.8461538461538461, "grad_norm": 0.598097446815511, "learning_rate": 3.942506642518952e-05, "loss": 0.5509, "step": 209 }, { "epoch": 0.8502024291497976, "grad_norm": 0.7233847122010859, "learning_rate": 3.9411526122333396e-05, "loss": 0.5679, "step": 210 }, { "epoch": 0.854251012145749, "grad_norm": 0.5321448915194416, "learning_rate": 3.939783060543167e-05, "loss": 0.5719, "step": 211 }, { "epoch": 0.8582995951417004, "grad_norm": 0.8683113085503246, "learning_rate": 3.938397998399333e-05, "loss": 0.5448, "step": 212 }, { "epoch": 0.8623481781376519, "grad_norm": 0.5973326486111409, "learning_rate": 3.936997436876756e-05, "loss": 0.5654, "step": 213 }, { "epoch": 0.8663967611336032, "grad_norm": 0.6159697482779685, "learning_rate": 3.935581387174289e-05, "loss": 0.5997, "step": 214 }, { "epoch": 0.8704453441295547, "grad_norm": 0.5662206932123474, "learning_rate": 3.9341498606146295e-05, "loss": 0.5509, "step": 215 }, { "epoch": 0.8744939271255061, "grad_norm": 0.5376793227450686, "learning_rate": 3.932702868644224e-05, "loss": 0.5485, "step": 216 }, { "epoch": 0.8785425101214575, "grad_norm": 0.44913826992501105, "learning_rate": 3.931240422833181e-05, "loss": 0.5349, "step": 217 }, { "epoch": 0.8825910931174089, "grad_norm": 0.5635084188143485, "learning_rate": 3.9297625348751806e-05, "loss": 0.5601, "step": 218 }, { "epoch": 0.8866396761133604, "grad_norm": 0.5272360490556149, "learning_rate": 3.9282692165873744e-05, "loss": 0.5516, "step": 219 }, { "epoch": 0.8906882591093117, "grad_norm": 0.5186656324253741, "learning_rate": 3.9267604799102945e-05, "loss": 0.5534, "step": 220 }, { "epoch": 0.8947368421052632, "grad_norm": 0.5573084275367355, "learning_rate": 3.9252363369077615e-05, "loss": 0.5736, "step": 221 }, { "epoch": 0.8987854251012146, "grad_norm": 0.5036019936679064, "learning_rate": 3.9236967997667796e-05, "loss": 0.5501, "step": 222 }, { "epoch": 0.902834008097166, "grad_norm": 0.6267460135540358, "learning_rate": 3.9221418807974496e-05, "loss": 0.5593, "step": 223 }, { "epoch": 0.9068825910931174, "grad_norm": 0.5924908793407309, "learning_rate": 3.92057159243286e-05, "loss": 0.5296, "step": 224 }, { "epoch": 0.9109311740890689, "grad_norm": 0.48703821728000457, "learning_rate": 3.9189859472289956e-05, "loss": 0.5612, "step": 225 }, { "epoch": 0.9149797570850202, "grad_norm": 0.6589790934048543, "learning_rate": 3.9173849578646324e-05, "loss": 0.568, "step": 226 }, { "epoch": 0.9190283400809717, "grad_norm": 0.4480741733247539, "learning_rate": 3.9157686371412395e-05, "loss": 0.5451, "step": 227 }, { "epoch": 0.9230769230769231, "grad_norm": 0.6963773529643545, "learning_rate": 3.914136997982874e-05, "loss": 0.5608, "step": 228 }, { "epoch": 0.9271255060728745, "grad_norm": 0.5133466347847644, "learning_rate": 3.912490053436079e-05, "loss": 0.5286, "step": 229 }, { "epoch": 0.9311740890688259, "grad_norm": 0.46783638824436846, "learning_rate": 3.9108278166697805e-05, "loss": 0.536, "step": 230 }, { "epoch": 0.9352226720647774, "grad_norm": 0.5154398153681657, "learning_rate": 3.909150300975178e-05, "loss": 0.5656, "step": 231 }, { "epoch": 0.9392712550607287, "grad_norm": 0.4597105990802689, "learning_rate": 3.907457519765642e-05, "loss": 0.5562, "step": 232 }, { "epoch": 0.9433198380566802, "grad_norm": 0.5063039136069484, "learning_rate": 3.905749486576607e-05, "loss": 0.5514, "step": 233 }, { "epoch": 0.9473684210526315, "grad_norm": 0.49927937690066587, "learning_rate": 3.90402621506546e-05, "loss": 0.5604, "step": 234 }, { "epoch": 0.951417004048583, "grad_norm": 0.5992258667075168, "learning_rate": 3.902287719011435e-05, "loss": 0.5811, "step": 235 }, { "epoch": 0.9554655870445344, "grad_norm": 0.6693724102476368, "learning_rate": 3.900534012315499e-05, "loss": 0.561, "step": 236 }, { "epoch": 0.9595141700404858, "grad_norm": 0.5463950475151028, "learning_rate": 3.8987651090002454e-05, "loss": 0.5426, "step": 237 }, { "epoch": 0.9635627530364372, "grad_norm": 0.6387864777825885, "learning_rate": 3.896981023209777e-05, "loss": 0.5409, "step": 238 }, { "epoch": 0.9676113360323887, "grad_norm": 0.5979439741434258, "learning_rate": 3.8951817692095966e-05, "loss": 0.5425, "step": 239 }, { "epoch": 0.97165991902834, "grad_norm": 0.5669659159786624, "learning_rate": 3.893367361386491e-05, "loss": 0.5515, "step": 240 }, { "epoch": 0.9757085020242915, "grad_norm": 0.6219981459253048, "learning_rate": 3.891537814248417e-05, "loss": 0.5755, "step": 241 }, { "epoch": 0.979757085020243, "grad_norm": 0.5829631419160141, "learning_rate": 3.889693142424384e-05, "loss": 0.5767, "step": 242 }, { "epoch": 0.9838056680161943, "grad_norm": 0.5261294271950123, "learning_rate": 3.8878333606643405e-05, "loss": 0.5442, "step": 243 }, { "epoch": 0.9878542510121457, "grad_norm": 0.44465351312210194, "learning_rate": 3.885958483839049e-05, "loss": 0.5465, "step": 244 }, { "epoch": 0.9919028340080972, "grad_norm": 0.5414591504656251, "learning_rate": 3.8840685269399786e-05, "loss": 0.547, "step": 245 }, { "epoch": 0.9959514170040485, "grad_norm": 0.6158628344837758, "learning_rate": 3.882163505079171e-05, "loss": 0.5788, "step": 246 }, { "epoch": 1.0, "grad_norm": 0.46713586373829946, "learning_rate": 3.880243433489132e-05, "loss": 0.5317, "step": 247 }, { "epoch": 1.0040485829959513, "grad_norm": 0.6664246705191972, "learning_rate": 3.878308327522702e-05, "loss": 0.4645, "step": 248 }, { "epoch": 1.008097165991903, "grad_norm": 0.49579713233084927, "learning_rate": 3.876358202652936e-05, "loss": 0.4652, "step": 249 }, { "epoch": 1.0121457489878543, "grad_norm": 0.618532243444074, "learning_rate": 3.8743930744729835e-05, "loss": 0.4421, "step": 250 }, { "epoch": 1.0161943319838056, "grad_norm": 0.6235367077944738, "learning_rate": 3.8724129586959535e-05, "loss": 0.4576, "step": 251 }, { "epoch": 1.0202429149797572, "grad_norm": 0.553453215062299, "learning_rate": 3.870417871154801e-05, "loss": 0.4627, "step": 252 }, { "epoch": 1.0242914979757085, "grad_norm": 0.6386688173937467, "learning_rate": 3.868407827802192e-05, "loss": 0.4689, "step": 253 }, { "epoch": 1.0283400809716599, "grad_norm": 0.473014728097165, "learning_rate": 3.8663828447103804e-05, "loss": 0.4741, "step": 254 }, { "epoch": 1.0323886639676114, "grad_norm": 0.629074906702617, "learning_rate": 3.8643429380710765e-05, "loss": 0.4413, "step": 255 }, { "epoch": 1.0364372469635628, "grad_norm": 0.5653647335141028, "learning_rate": 3.862288124195319e-05, "loss": 0.4735, "step": 256 }, { "epoch": 1.040485829959514, "grad_norm": 0.5007065324609555, "learning_rate": 3.8602184195133464e-05, "loss": 0.4765, "step": 257 }, { "epoch": 1.0445344129554657, "grad_norm": 0.5766359284501051, "learning_rate": 3.8581338405744604e-05, "loss": 0.4762, "step": 258 }, { "epoch": 1.048582995951417, "grad_norm": 0.5620021738690882, "learning_rate": 3.8560344040468996e-05, "loss": 0.4682, "step": 259 }, { "epoch": 1.0526315789473684, "grad_norm": 0.5067610710447218, "learning_rate": 3.853920126717703e-05, "loss": 0.4728, "step": 260 }, { "epoch": 1.05668016194332, "grad_norm": 0.5733595451712956, "learning_rate": 3.851791025492574e-05, "loss": 0.4784, "step": 261 }, { "epoch": 1.0607287449392713, "grad_norm": 0.46823030028769036, "learning_rate": 3.8496471173957515e-05, "loss": 0.4479, "step": 262 }, { "epoch": 1.0647773279352226, "grad_norm": 0.5594887866492645, "learning_rate": 3.847488419569866e-05, "loss": 0.449, "step": 263 }, { "epoch": 1.0688259109311742, "grad_norm": 0.5382691744230178, "learning_rate": 3.8453149492758077e-05, "loss": 0.477, "step": 264 }, { "epoch": 1.0728744939271255, "grad_norm": 0.6470019863723906, "learning_rate": 3.8431267238925886e-05, "loss": 0.4388, "step": 265 }, { "epoch": 1.0769230769230769, "grad_norm": 0.5267988880917751, "learning_rate": 3.840923760917199e-05, "loss": 0.4949, "step": 266 }, { "epoch": 1.0809716599190284, "grad_norm": 0.6248347355085085, "learning_rate": 3.838706077964473e-05, "loss": 0.4726, "step": 267 }, { "epoch": 1.0850202429149798, "grad_norm": 0.5813604489516596, "learning_rate": 3.836473692766944e-05, "loss": 0.4482, "step": 268 }, { "epoch": 1.0890688259109311, "grad_norm": 0.5572985876501775, "learning_rate": 3.834226623174705e-05, "loss": 0.457, "step": 269 }, { "epoch": 1.0931174089068827, "grad_norm": 0.6644190351693268, "learning_rate": 3.831964887155264e-05, "loss": 0.4468, "step": 270 }, { "epoch": 1.097165991902834, "grad_norm": 0.5644810221616803, "learning_rate": 3.829688502793403e-05, "loss": 0.4549, "step": 271 }, { "epoch": 1.1012145748987854, "grad_norm": 0.5455149809783746, "learning_rate": 3.827397488291029e-05, "loss": 0.478, "step": 272 }, { "epoch": 1.1052631578947367, "grad_norm": 0.5253698700199828, "learning_rate": 3.8250918619670343e-05, "loss": 0.4478, "step": 273 }, { "epoch": 1.1093117408906883, "grad_norm": 0.5509641524766142, "learning_rate": 3.822771642257145e-05, "loss": 0.4739, "step": 274 }, { "epoch": 1.1133603238866396, "grad_norm": 0.5085312095362103, "learning_rate": 3.820436847713776e-05, "loss": 0.4509, "step": 275 }, { "epoch": 1.117408906882591, "grad_norm": 0.6491080149847492, "learning_rate": 3.8180874970058826e-05, "loss": 0.4574, "step": 276 }, { "epoch": 1.1214574898785425, "grad_norm": 0.5479539163150103, "learning_rate": 3.8157236089188103e-05, "loss": 0.4764, "step": 277 }, { "epoch": 1.125506072874494, "grad_norm": 0.5650582402371023, "learning_rate": 3.813345202354145e-05, "loss": 0.4614, "step": 278 }, { "epoch": 1.1295546558704452, "grad_norm": 0.501417692369805, "learning_rate": 3.810952296329563e-05, "loss": 0.4745, "step": 279 }, { "epoch": 1.1336032388663968, "grad_norm": 0.4977121695842139, "learning_rate": 3.808544909978676e-05, "loss": 0.4727, "step": 280 }, { "epoch": 1.1376518218623481, "grad_norm": 0.5040029724488416, "learning_rate": 3.806123062550882e-05, "loss": 0.4476, "step": 281 }, { "epoch": 1.1417004048582995, "grad_norm": 0.458749344363986, "learning_rate": 3.803686773411208e-05, "loss": 0.447, "step": 282 }, { "epoch": 1.145748987854251, "grad_norm": 0.4958448058443441, "learning_rate": 3.801236062040158e-05, "loss": 0.4719, "step": 283 }, { "epoch": 1.1497975708502024, "grad_norm": 0.4235876794105357, "learning_rate": 3.798770948033553e-05, "loss": 0.4602, "step": 284 }, { "epoch": 1.1538461538461537, "grad_norm": 0.4545094204170493, "learning_rate": 3.796291451102381e-05, "loss": 0.4582, "step": 285 }, { "epoch": 1.1578947368421053, "grad_norm": 0.5106129327119411, "learning_rate": 3.793797591072631e-05, "loss": 0.4616, "step": 286 }, { "epoch": 1.1619433198380567, "grad_norm": 0.5655079921714662, "learning_rate": 3.791289387885144e-05, "loss": 0.4283, "step": 287 }, { "epoch": 1.165991902834008, "grad_norm": 0.4499766378806911, "learning_rate": 3.788766861595443e-05, "loss": 0.4818, "step": 288 }, { "epoch": 1.1700404858299596, "grad_norm": 0.46234299068528995, "learning_rate": 3.7862300323735835e-05, "loss": 0.4763, "step": 289 }, { "epoch": 1.174089068825911, "grad_norm": 0.45728072594886177, "learning_rate": 3.783678920503983e-05, "loss": 0.4492, "step": 290 }, { "epoch": 1.1781376518218623, "grad_norm": 0.450064043355426, "learning_rate": 3.781113546385265e-05, "loss": 0.4414, "step": 291 }, { "epoch": 1.1821862348178138, "grad_norm": 0.4764766894114243, "learning_rate": 3.7785339305300916e-05, "loss": 0.4783, "step": 292 }, { "epoch": 1.1862348178137652, "grad_norm": 0.49072193670465275, "learning_rate": 3.7759400935650025e-05, "loss": 0.4685, "step": 293 }, { "epoch": 1.1902834008097165, "grad_norm": 0.4616111082661913, "learning_rate": 3.77333205623025e-05, "loss": 0.4182, "step": 294 }, { "epoch": 1.194331983805668, "grad_norm": 0.5355183924675356, "learning_rate": 3.7707098393796295e-05, "loss": 0.483, "step": 295 }, { "epoch": 1.1983805668016194, "grad_norm": 0.4867475275487421, "learning_rate": 3.7680734639803185e-05, "loss": 0.4578, "step": 296 }, { "epoch": 1.2024291497975708, "grad_norm": 0.5639223419955517, "learning_rate": 3.765422951112704e-05, "loss": 0.47, "step": 297 }, { "epoch": 1.2064777327935223, "grad_norm": 0.5547748836958333, "learning_rate": 3.762758321970216e-05, "loss": 0.4598, "step": 298 }, { "epoch": 1.2105263157894737, "grad_norm": 0.5365197514118076, "learning_rate": 3.7600795978591584e-05, "loss": 0.4506, "step": 299 }, { "epoch": 1.214574898785425, "grad_norm": 0.5016262895153869, "learning_rate": 3.757386800198538e-05, "loss": 0.4704, "step": 300 }, { "epoch": 1.2186234817813766, "grad_norm": 0.513968221320516, "learning_rate": 3.7546799505198925e-05, "loss": 0.4521, "step": 301 }, { "epoch": 1.222672064777328, "grad_norm": 0.4999242229462357, "learning_rate": 3.7519590704671197e-05, "loss": 0.468, "step": 302 }, { "epoch": 1.2267206477732793, "grad_norm": 0.4719604947739877, "learning_rate": 3.749224181796305e-05, "loss": 0.4431, "step": 303 }, { "epoch": 1.2307692307692308, "grad_norm": 0.4725062394084326, "learning_rate": 3.746475306375545e-05, "loss": 0.4494, "step": 304 }, { "epoch": 1.2348178137651822, "grad_norm": 0.5184714852089275, "learning_rate": 3.743712466184774e-05, "loss": 0.4676, "step": 305 }, { "epoch": 1.2388663967611335, "grad_norm": 0.5250343284717189, "learning_rate": 3.7409356833155885e-05, "loss": 0.4588, "step": 306 }, { "epoch": 1.242914979757085, "grad_norm": 0.46686724854524964, "learning_rate": 3.73814497997107e-05, "loss": 0.454, "step": 307 }, { "epoch": 1.2469635627530364, "grad_norm": 0.6042558260886649, "learning_rate": 3.7353403784656095e-05, "loss": 0.4549, "step": 308 }, { "epoch": 1.2510121457489878, "grad_norm": 0.47143421157845133, "learning_rate": 3.732521901224724e-05, "loss": 0.4472, "step": 309 }, { "epoch": 1.2550607287449393, "grad_norm": 0.6433996158078551, "learning_rate": 3.7296895707848844e-05, "loss": 0.4596, "step": 310 }, { "epoch": 1.2591093117408907, "grad_norm": 0.5582185734696281, "learning_rate": 3.7268434097933275e-05, "loss": 0.468, "step": 311 }, { "epoch": 1.263157894736842, "grad_norm": 0.5520147493538251, "learning_rate": 3.723983441007882e-05, "loss": 0.4618, "step": 312 }, { "epoch": 1.2672064777327936, "grad_norm": 0.662466426508298, "learning_rate": 3.721109687296781e-05, "loss": 0.4615, "step": 313 }, { "epoch": 1.271255060728745, "grad_norm": 0.43543671543571033, "learning_rate": 3.718222171638484e-05, "loss": 0.4444, "step": 314 }, { "epoch": 1.2753036437246963, "grad_norm": 0.5396309660631922, "learning_rate": 3.715320917121488e-05, "loss": 0.462, "step": 315 }, { "epoch": 1.2793522267206479, "grad_norm": 0.571702227749801, "learning_rate": 3.712405946944149e-05, "loss": 0.4686, "step": 316 }, { "epoch": 1.2834008097165992, "grad_norm": 0.46536715501894477, "learning_rate": 3.709477284414488e-05, "loss": 0.456, "step": 317 }, { "epoch": 1.2874493927125505, "grad_norm": 0.609464504461623, "learning_rate": 3.7065349529500136e-05, "loss": 0.4524, "step": 318 }, { "epoch": 1.291497975708502, "grad_norm": 0.5003481577171648, "learning_rate": 3.7035789760775305e-05, "loss": 0.4712, "step": 319 }, { "epoch": 1.2955465587044535, "grad_norm": 0.5981591367058731, "learning_rate": 3.70060937743295e-05, "loss": 0.4769, "step": 320 }, { "epoch": 1.2995951417004048, "grad_norm": 0.49644802621883216, "learning_rate": 3.6976261807611045e-05, "loss": 0.4668, "step": 321 }, { "epoch": 1.3036437246963564, "grad_norm": 0.4869345872800657, "learning_rate": 3.694629409915555e-05, "loss": 0.4595, "step": 322 }, { "epoch": 1.3076923076923077, "grad_norm": 0.4447417915501944, "learning_rate": 3.691619088858401e-05, "loss": 0.4463, "step": 323 }, { "epoch": 1.311740890688259, "grad_norm": 0.467612267183219, "learning_rate": 3.68859524166009e-05, "loss": 0.4622, "step": 324 }, { "epoch": 1.3157894736842106, "grad_norm": 0.44527521240370327, "learning_rate": 3.6855578924992226e-05, "loss": 0.4582, "step": 325 }, { "epoch": 1.319838056680162, "grad_norm": 0.4633613446142622, "learning_rate": 3.6825070656623626e-05, "loss": 0.4361, "step": 326 }, { "epoch": 1.3238866396761133, "grad_norm": 0.47339237625711267, "learning_rate": 3.67944278554384e-05, "loss": 0.4516, "step": 327 }, { "epoch": 1.3279352226720649, "grad_norm": 0.444587684027109, "learning_rate": 3.676365076645557e-05, "loss": 0.4662, "step": 328 }, { "epoch": 1.3319838056680162, "grad_norm": 0.4733206877440419, "learning_rate": 3.673273963576791e-05, "loss": 0.4732, "step": 329 }, { "epoch": 1.3360323886639676, "grad_norm": 0.44091497627889303, "learning_rate": 3.670169471054001e-05, "loss": 0.4731, "step": 330 }, { "epoch": 1.3400809716599191, "grad_norm": 0.4902016747465256, "learning_rate": 3.6670516239006254e-05, "loss": 0.4429, "step": 331 }, { "epoch": 1.3441295546558705, "grad_norm": 0.4481551797066044, "learning_rate": 3.663920447046888e-05, "loss": 0.4732, "step": 332 }, { "epoch": 1.3481781376518218, "grad_norm": 0.45514519100156464, "learning_rate": 3.6607759655295954e-05, "loss": 0.4603, "step": 333 }, { "epoch": 1.3522267206477734, "grad_norm": 0.47687873145252263, "learning_rate": 3.657618204491937e-05, "loss": 0.4725, "step": 334 }, { "epoch": 1.3562753036437247, "grad_norm": 0.5513987775327542, "learning_rate": 3.6544471891832875e-05, "loss": 0.4904, "step": 335 }, { "epoch": 1.360323886639676, "grad_norm": 0.44311240550091735, "learning_rate": 3.6512629449589983e-05, "loss": 0.4628, "step": 336 }, { "epoch": 1.3643724696356276, "grad_norm": 0.5906406098633066, "learning_rate": 3.6480654972802045e-05, "loss": 0.4395, "step": 337 }, { "epoch": 1.368421052631579, "grad_norm": 0.4979999548439868, "learning_rate": 3.644854871713611e-05, "loss": 0.4679, "step": 338 }, { "epoch": 1.3724696356275303, "grad_norm": 0.6544193050598207, "learning_rate": 3.6416310939312924e-05, "loss": 0.4725, "step": 339 }, { "epoch": 1.376518218623482, "grad_norm": 0.6504050199401463, "learning_rate": 3.638394189710493e-05, "loss": 0.4732, "step": 340 }, { "epoch": 1.3805668016194332, "grad_norm": 0.5049735818022115, "learning_rate": 3.635144184933412e-05, "loss": 0.4721, "step": 341 }, { "epoch": 1.3846153846153846, "grad_norm": 0.6490209330849904, "learning_rate": 3.6318811055869994e-05, "loss": 0.4507, "step": 342 }, { "epoch": 1.3886639676113361, "grad_norm": 0.4321927146090069, "learning_rate": 3.628604977762752e-05, "loss": 0.4439, "step": 343 }, { "epoch": 1.3927125506072875, "grad_norm": 0.6661132990714439, "learning_rate": 3.6253158276565004e-05, "loss": 0.4792, "step": 344 }, { "epoch": 1.3967611336032388, "grad_norm": 0.5465501159605418, "learning_rate": 3.6220136815682016e-05, "loss": 0.4774, "step": 345 }, { "epoch": 1.4008097165991904, "grad_norm": 0.5781369435890981, "learning_rate": 3.618698565901727e-05, "loss": 0.455, "step": 346 }, { "epoch": 1.4048582995951417, "grad_norm": 0.538126242340215, "learning_rate": 3.615370507164654e-05, "loss": 0.4401, "step": 347 }, { "epoch": 1.408906882591093, "grad_norm": 0.4551205592806124, "learning_rate": 3.61202953196805e-05, "loss": 0.4511, "step": 348 }, { "epoch": 1.4129554655870447, "grad_norm": 0.509974006006187, "learning_rate": 3.6086756670262654e-05, "loss": 0.4451, "step": 349 }, { "epoch": 1.417004048582996, "grad_norm": 0.4190651496663137, "learning_rate": 3.6053089391567135e-05, "loss": 0.4517, "step": 350 }, { "epoch": 1.4210526315789473, "grad_norm": 0.6806117976567219, "learning_rate": 3.601929375279662e-05, "loss": 0.4681, "step": 351 }, { "epoch": 1.425101214574899, "grad_norm": 0.47761132639059967, "learning_rate": 3.598537002418012e-05, "loss": 0.453, "step": 352 }, { "epoch": 1.4291497975708503, "grad_norm": 0.5399756102413964, "learning_rate": 3.5951318476970885e-05, "loss": 0.465, "step": 353 }, { "epoch": 1.4331983805668016, "grad_norm": 0.4542744937836544, "learning_rate": 3.591713938344416e-05, "loss": 0.4651, "step": 354 }, { "epoch": 1.4372469635627532, "grad_norm": 0.6219481859120001, "learning_rate": 3.588283301689507e-05, "loss": 0.4724, "step": 355 }, { "epoch": 1.4412955465587045, "grad_norm": 0.4706810535159858, "learning_rate": 3.5848399651636424e-05, "loss": 0.4415, "step": 356 }, { "epoch": 1.4453441295546559, "grad_norm": 0.5680879458412695, "learning_rate": 3.5813839562996473e-05, "loss": 0.4701, "step": 357 }, { "epoch": 1.4493927125506074, "grad_norm": 0.46914029124319145, "learning_rate": 3.5779153027316775e-05, "loss": 0.4719, "step": 358 }, { "epoch": 1.4534412955465588, "grad_norm": 0.4764965625429461, "learning_rate": 3.574434032194994e-05, "loss": 0.4522, "step": 359 }, { "epoch": 1.45748987854251, "grad_norm": 0.49122259925508344, "learning_rate": 3.5709401725257436e-05, "loss": 0.4446, "step": 360 }, { "epoch": 1.4615384615384617, "grad_norm": 0.4419249045684, "learning_rate": 3.5674337516607346e-05, "loss": 0.4589, "step": 361 }, { "epoch": 1.465587044534413, "grad_norm": 0.5001589980265122, "learning_rate": 3.563914797637216e-05, "loss": 0.4528, "step": 362 }, { "epoch": 1.4696356275303644, "grad_norm": 0.45249679371256635, "learning_rate": 3.560383338592649e-05, "loss": 0.4568, "step": 363 }, { "epoch": 1.4736842105263157, "grad_norm": 0.5029055114338162, "learning_rate": 3.556839402764487e-05, "loss": 0.4624, "step": 364 }, { "epoch": 1.4777327935222673, "grad_norm": 0.470427466779978, "learning_rate": 3.553283018489946e-05, "loss": 0.4561, "step": 365 }, { "epoch": 1.4817813765182186, "grad_norm": 0.5287544402444059, "learning_rate": 3.54971421420578e-05, "loss": 0.4514, "step": 366 }, { "epoch": 1.48582995951417, "grad_norm": 0.42960809210645384, "learning_rate": 3.5461330184480524e-05, "loss": 0.465, "step": 367 }, { "epoch": 1.4898785425101215, "grad_norm": 0.49402940412381086, "learning_rate": 3.54253945985191e-05, "loss": 0.4558, "step": 368 }, { "epoch": 1.4939271255060729, "grad_norm": 0.41214122975176715, "learning_rate": 3.5389335671513524e-05, "loss": 0.4694, "step": 369 }, { "epoch": 1.4979757085020242, "grad_norm": 0.4811624368763832, "learning_rate": 3.5353153691789986e-05, "loss": 0.4554, "step": 370 }, { "epoch": 1.5020242914979756, "grad_norm": 0.4227066197512243, "learning_rate": 3.531684894865866e-05, "loss": 0.4525, "step": 371 }, { "epoch": 1.5060728744939271, "grad_norm": 0.540309224166524, "learning_rate": 3.528042173241128e-05, "loss": 0.4616, "step": 372 }, { "epoch": 1.5101214574898787, "grad_norm": 0.4541543561646677, "learning_rate": 3.524387233431892e-05, "loss": 0.4597, "step": 373 }, { "epoch": 1.5141700404858298, "grad_norm": 0.4266589418306719, "learning_rate": 3.520720104662958e-05, "loss": 0.4263, "step": 374 }, { "epoch": 1.5182186234817814, "grad_norm": 0.4597259692850776, "learning_rate": 3.5170408162565904e-05, "loss": 0.4517, "step": 375 }, { "epoch": 1.522267206477733, "grad_norm": 0.43147703599727155, "learning_rate": 3.513349397632281e-05, "loss": 0.4701, "step": 376 }, { "epoch": 1.526315789473684, "grad_norm": 0.47470345430931726, "learning_rate": 3.5096458783065145e-05, "loss": 0.4559, "step": 377 }, { "epoch": 1.5303643724696356, "grad_norm": 0.4218014163243215, "learning_rate": 3.505930287892533e-05, "loss": 0.4545, "step": 378 }, { "epoch": 1.5344129554655872, "grad_norm": 0.45774286532224456, "learning_rate": 3.502202656100099e-05, "loss": 0.4511, "step": 379 }, { "epoch": 1.5384615384615383, "grad_norm": 0.4517416191312263, "learning_rate": 3.498463012735256e-05, "loss": 0.4517, "step": 380 }, { "epoch": 1.54251012145749, "grad_norm": 0.4242410970622322, "learning_rate": 3.494711387700094e-05, "loss": 0.4557, "step": 381 }, { "epoch": 1.5465587044534415, "grad_norm": 0.42622250459482525, "learning_rate": 3.490947810992505e-05, "loss": 0.4334, "step": 382 }, { "epoch": 1.5506072874493926, "grad_norm": 0.41935113738164725, "learning_rate": 3.48717231270595e-05, "loss": 0.4476, "step": 383 }, { "epoch": 1.5546558704453441, "grad_norm": 0.4566383257370379, "learning_rate": 3.483384923029211e-05, "loss": 0.4637, "step": 384 }, { "epoch": 1.5587044534412957, "grad_norm": 0.435061254042364, "learning_rate": 3.479585672246156e-05, "loss": 0.4441, "step": 385 }, { "epoch": 1.5627530364372468, "grad_norm": 0.4137451331498346, "learning_rate": 3.4757745907354924e-05, "loss": 0.4602, "step": 386 }, { "epoch": 1.5668016194331984, "grad_norm": 0.4278088067212076, "learning_rate": 3.471951708970527e-05, "loss": 0.439, "step": 387 }, { "epoch": 1.5708502024291497, "grad_norm": 0.4305866515707906, "learning_rate": 3.468117057518921e-05, "loss": 0.4434, "step": 388 }, { "epoch": 1.574898785425101, "grad_norm": 0.41137139000922734, "learning_rate": 3.4642706670424426e-05, "loss": 0.4557, "step": 389 }, { "epoch": 1.5789473684210527, "grad_norm": 0.40278143634983504, "learning_rate": 3.460412568296731e-05, "loss": 0.4494, "step": 390 }, { "epoch": 1.582995951417004, "grad_norm": 0.45953836415302596, "learning_rate": 3.456542792131039e-05, "loss": 0.4727, "step": 391 }, { "epoch": 1.5870445344129553, "grad_norm": 0.4045013857428911, "learning_rate": 3.4526613694879936e-05, "loss": 0.4507, "step": 392 }, { "epoch": 1.591093117408907, "grad_norm": 0.5292740994443514, "learning_rate": 3.448768331403348e-05, "loss": 0.4701, "step": 393 }, { "epoch": 1.5951417004048583, "grad_norm": 0.4175311883930499, "learning_rate": 3.44486370900573e-05, "loss": 0.4464, "step": 394 }, { "epoch": 1.5991902834008096, "grad_norm": 0.4647984219943599, "learning_rate": 3.440947533516396e-05, "loss": 0.4528, "step": 395 }, { "epoch": 1.6032388663967612, "grad_norm": 0.5144705890580547, "learning_rate": 3.4370198362489816e-05, "loss": 0.4398, "step": 396 }, { "epoch": 1.6072874493927125, "grad_norm": 0.42188800602011245, "learning_rate": 3.43308064860925e-05, "loss": 0.4323, "step": 397 }, { "epoch": 1.6113360323886639, "grad_norm": 0.5023884755772606, "learning_rate": 3.4291300020948393e-05, "loss": 0.4481, "step": 398 }, { "epoch": 1.6153846153846154, "grad_norm": 0.44609912320022665, "learning_rate": 3.425167928295015e-05, "loss": 0.453, "step": 399 }, { "epoch": 1.6194331983805668, "grad_norm": 0.47955490957695024, "learning_rate": 3.421194458890411e-05, "loss": 0.4518, "step": 400 }, { "epoch": 1.623481781376518, "grad_norm": 0.44663224120159073, "learning_rate": 3.4172096256527865e-05, "loss": 0.4396, "step": 401 }, { "epoch": 1.6275303643724697, "grad_norm": 0.5105647001424654, "learning_rate": 3.4132134604447595e-05, "loss": 0.4399, "step": 402 }, { "epoch": 1.631578947368421, "grad_norm": 0.40227595991608445, "learning_rate": 3.409205995219561e-05, "loss": 0.4481, "step": 403 }, { "epoch": 1.6356275303643724, "grad_norm": 0.46112153085558855, "learning_rate": 3.4051872620207765e-05, "loss": 0.4355, "step": 404 }, { "epoch": 1.639676113360324, "grad_norm": 0.4090502874206955, "learning_rate": 3.40115729298209e-05, "loss": 0.4475, "step": 405 }, { "epoch": 1.6437246963562753, "grad_norm": 0.45086740478041015, "learning_rate": 3.397116120327025e-05, "loss": 0.4523, "step": 406 }, { "epoch": 1.6477732793522266, "grad_norm": 0.42261841462774125, "learning_rate": 3.3930637763686916e-05, "loss": 0.4624, "step": 407 }, { "epoch": 1.6518218623481782, "grad_norm": 0.40076847510961056, "learning_rate": 3.389000293509524e-05, "loss": 0.464, "step": 408 }, { "epoch": 1.6558704453441295, "grad_norm": 0.4201662448370817, "learning_rate": 3.3849257042410225e-05, "loss": 0.4592, "step": 409 }, { "epoch": 1.6599190283400809, "grad_norm": 0.41701210123768107, "learning_rate": 3.380840041143494e-05, "loss": 0.4673, "step": 410 }, { "epoch": 1.6639676113360324, "grad_norm": 0.4407156336492628, "learning_rate": 3.376743336885792e-05, "loss": 0.4604, "step": 411 }, { "epoch": 1.6680161943319838, "grad_norm": 0.4324853121315475, "learning_rate": 3.372635624225055e-05, "loss": 0.455, "step": 412 }, { "epoch": 1.6720647773279351, "grad_norm": 0.47509966854363084, "learning_rate": 3.3685169360064445e-05, "loss": 0.4586, "step": 413 }, { "epoch": 1.6761133603238867, "grad_norm": 0.4361650424047843, "learning_rate": 3.3643873051628804e-05, "loss": 0.4385, "step": 414 }, { "epoch": 1.680161943319838, "grad_norm": 0.4645524476356292, "learning_rate": 3.3602467647147814e-05, "loss": 0.4608, "step": 415 }, { "epoch": 1.6842105263157894, "grad_norm": 0.4476779123864296, "learning_rate": 3.356095347769799e-05, "loss": 0.448, "step": 416 }, { "epoch": 1.688259109311741, "grad_norm": 0.4528907963058292, "learning_rate": 3.351933087522552e-05, "loss": 0.4399, "step": 417 }, { "epoch": 1.6923076923076923, "grad_norm": 0.43878536175461386, "learning_rate": 3.3477600172543626e-05, "loss": 0.4389, "step": 418 }, { "epoch": 1.6963562753036436, "grad_norm": 0.48832738932948755, "learning_rate": 3.3435761703329894e-05, "loss": 0.4461, "step": 419 }, { "epoch": 1.7004048582995952, "grad_norm": 0.3894674569093715, "learning_rate": 3.3393815802123606e-05, "loss": 0.4509, "step": 420 }, { "epoch": 1.7044534412955465, "grad_norm": 0.4329823188645695, "learning_rate": 3.335176280432308e-05, "loss": 0.4575, "step": 421 }, { "epoch": 1.708502024291498, "grad_norm": 0.4219655577043312, "learning_rate": 3.330960304618295e-05, "loss": 0.4546, "step": 422 }, { "epoch": 1.7125506072874495, "grad_norm": 0.4106529689098776, "learning_rate": 3.326733686481153e-05, "loss": 0.4415, "step": 423 }, { "epoch": 1.7165991902834008, "grad_norm": 0.4182578140177444, "learning_rate": 3.3224964598168084e-05, "loss": 0.4512, "step": 424 }, { "epoch": 1.7206477732793521, "grad_norm": 0.4921321428487148, "learning_rate": 3.318248658506012e-05, "loss": 0.4681, "step": 425 }, { "epoch": 1.7246963562753037, "grad_norm": 0.47830578725287876, "learning_rate": 3.313990316514069e-05, "loss": 0.4667, "step": 426 }, { "epoch": 1.728744939271255, "grad_norm": 0.5103765768881628, "learning_rate": 3.309721467890571e-05, "loss": 0.4629, "step": 427 }, { "epoch": 1.7327935222672064, "grad_norm": 0.5012386114251917, "learning_rate": 3.305442146769115e-05, "loss": 0.4652, "step": 428 }, { "epoch": 1.736842105263158, "grad_norm": 0.5082166497292012, "learning_rate": 3.30115238736704e-05, "loss": 0.473, "step": 429 }, { "epoch": 1.7408906882591093, "grad_norm": 0.4995707292868623, "learning_rate": 3.296852223985148e-05, "loss": 0.4376, "step": 430 }, { "epoch": 1.7449392712550607, "grad_norm": 0.46989285401208036, "learning_rate": 3.2925416910074315e-05, "loss": 0.4529, "step": 431 }, { "epoch": 1.7489878542510122, "grad_norm": 0.47204355451780267, "learning_rate": 3.288220822900796e-05, "loss": 0.4524, "step": 432 }, { "epoch": 1.7530364372469636, "grad_norm": 0.44197650034082164, "learning_rate": 3.283889654214788e-05, "loss": 0.4487, "step": 433 }, { "epoch": 1.757085020242915, "grad_norm": 0.3928453504606134, "learning_rate": 3.279548219581317e-05, "loss": 0.4544, "step": 434 }, { "epoch": 1.7611336032388665, "grad_norm": 0.5121873491496265, "learning_rate": 3.275196553714379e-05, "loss": 0.4617, "step": 435 }, { "epoch": 1.7651821862348178, "grad_norm": 0.4522567820240919, "learning_rate": 3.270834691409778e-05, "loss": 0.4529, "step": 436 }, { "epoch": 1.7692307692307692, "grad_norm": 0.47602680253897595, "learning_rate": 3.266462667544849e-05, "loss": 0.4432, "step": 437 }, { "epoch": 1.7732793522267207, "grad_norm": 0.559924071150495, "learning_rate": 3.262080517078178e-05, "loss": 0.4318, "step": 438 }, { "epoch": 1.777327935222672, "grad_norm": 0.43283971278060396, "learning_rate": 3.257688275049323e-05, "loss": 0.452, "step": 439 }, { "epoch": 1.7813765182186234, "grad_norm": 0.6386378952033852, "learning_rate": 3.253285976578535e-05, "loss": 0.4725, "step": 440 }, { "epoch": 1.785425101214575, "grad_norm": 0.4172637919788116, "learning_rate": 3.2488736568664756e-05, "loss": 0.4368, "step": 441 }, { "epoch": 1.7894736842105263, "grad_norm": 0.5675444893005949, "learning_rate": 3.244451351193935e-05, "loss": 0.4538, "step": 442 }, { "epoch": 1.7935222672064777, "grad_norm": 0.42712503893370884, "learning_rate": 3.240019094921551e-05, "loss": 0.4408, "step": 443 }, { "epoch": 1.7975708502024292, "grad_norm": 0.45765854882245954, "learning_rate": 3.235576923489527e-05, "loss": 0.4532, "step": 444 }, { "epoch": 1.8016194331983806, "grad_norm": 0.43293335700332225, "learning_rate": 3.2311248724173476e-05, "loss": 0.4506, "step": 445 }, { "epoch": 1.805668016194332, "grad_norm": 0.42733226362079635, "learning_rate": 3.226662977303494e-05, "loss": 0.4413, "step": 446 }, { "epoch": 1.8097165991902835, "grad_norm": 0.4381949654089606, "learning_rate": 3.2221912738251626e-05, "loss": 0.4538, "step": 447 }, { "epoch": 1.8137651821862348, "grad_norm": 0.40454709590144516, "learning_rate": 3.2177097977379736e-05, "loss": 0.4409, "step": 448 }, { "epoch": 1.8178137651821862, "grad_norm": 0.46907414432294225, "learning_rate": 3.21321858487569e-05, "loss": 0.4447, "step": 449 }, { "epoch": 1.8218623481781377, "grad_norm": 0.3924828168825286, "learning_rate": 3.208717671149931e-05, "loss": 0.4609, "step": 450 }, { "epoch": 1.825910931174089, "grad_norm": 0.4544734077249063, "learning_rate": 3.204207092549882e-05, "loss": 0.4728, "step": 451 }, { "epoch": 1.8299595141700404, "grad_norm": 0.3986742955418174, "learning_rate": 3.19968688514201e-05, "loss": 0.4651, "step": 452 }, { "epoch": 1.834008097165992, "grad_norm": 0.4509503867412026, "learning_rate": 3.195157085069774e-05, "loss": 0.4421, "step": 453 }, { "epoch": 1.8380566801619433, "grad_norm": 0.4473162756817529, "learning_rate": 3.190617728553332e-05, "loss": 0.441, "step": 454 }, { "epoch": 1.8421052631578947, "grad_norm": 0.479394347344928, "learning_rate": 3.1860688518892606e-05, "loss": 0.4499, "step": 455 }, { "epoch": 1.8461538461538463, "grad_norm": 0.4190481241392213, "learning_rate": 3.181510491450254e-05, "loss": 0.4586, "step": 456 }, { "epoch": 1.8502024291497976, "grad_norm": 0.4944019409649494, "learning_rate": 3.176942683684842e-05, "loss": 0.4494, "step": 457 }, { "epoch": 1.854251012145749, "grad_norm": 0.40556125054963144, "learning_rate": 3.1723654651170934e-05, "loss": 0.4515, "step": 458 }, { "epoch": 1.8582995951417005, "grad_norm": 0.4325260691194464, "learning_rate": 3.167778872346327e-05, "loss": 0.4595, "step": 459 }, { "epoch": 1.8623481781376519, "grad_norm": 0.39717060283141786, "learning_rate": 3.163182942046815e-05, "loss": 0.443, "step": 460 }, { "epoch": 1.8663967611336032, "grad_norm": 0.42858807429444323, "learning_rate": 3.158577710967494e-05, "loss": 0.4465, "step": 461 }, { "epoch": 1.8704453441295548, "grad_norm": 0.48359817597110405, "learning_rate": 3.153963215931669e-05, "loss": 0.4625, "step": 462 }, { "epoch": 1.874493927125506, "grad_norm": 0.4009530914610259, "learning_rate": 3.14933949383672e-05, "loss": 0.4667, "step": 463 }, { "epoch": 1.8785425101214575, "grad_norm": 0.45172788056911967, "learning_rate": 3.144706581653805e-05, "loss": 0.4639, "step": 464 }, { "epoch": 1.882591093117409, "grad_norm": 0.4408718564636046, "learning_rate": 3.140064516427566e-05, "loss": 0.4354, "step": 465 }, { "epoch": 1.8866396761133604, "grad_norm": 0.4092735079988685, "learning_rate": 3.135413335275833e-05, "loss": 0.4407, "step": 466 }, { "epoch": 1.8906882591093117, "grad_norm": 0.46901229640736214, "learning_rate": 3.130753075389327e-05, "loss": 0.44, "step": 467 }, { "epoch": 1.8947368421052633, "grad_norm": 0.39596538366115663, "learning_rate": 3.1260837740313625e-05, "loss": 0.4424, "step": 468 }, { "epoch": 1.8987854251012146, "grad_norm": 0.5226860058654853, "learning_rate": 3.121405468537547e-05, "loss": 0.4392, "step": 469 }, { "epoch": 1.902834008097166, "grad_norm": 0.4404177511291632, "learning_rate": 3.116718196315488e-05, "loss": 0.4552, "step": 470 }, { "epoch": 1.9068825910931175, "grad_norm": 0.48426112911581226, "learning_rate": 3.1120219948444894e-05, "loss": 0.4608, "step": 471 }, { "epoch": 1.9109311740890689, "grad_norm": 0.46295065193237483, "learning_rate": 3.107316901675252e-05, "loss": 0.4422, "step": 472 }, { "epoch": 1.9149797570850202, "grad_norm": 0.431889630089284, "learning_rate": 3.1026029544295745e-05, "loss": 0.4509, "step": 473 }, { "epoch": 1.9190283400809718, "grad_norm": 0.530059060005885, "learning_rate": 3.097880190800057e-05, "loss": 0.456, "step": 474 }, { "epoch": 1.9230769230769231, "grad_norm": 0.43191655850473953, "learning_rate": 3.093148648549788e-05, "loss": 0.4463, "step": 475 }, { "epoch": 1.9271255060728745, "grad_norm": 0.47695651492686847, "learning_rate": 3.088408365512055e-05, "loss": 0.4301, "step": 476 }, { "epoch": 1.931174089068826, "grad_norm": 0.45319336239117863, "learning_rate": 3.083659379590034e-05, "loss": 0.4463, "step": 477 }, { "epoch": 1.9352226720647774, "grad_norm": 0.46981076179473313, "learning_rate": 3.0789017287564913e-05, "loss": 0.4468, "step": 478 }, { "epoch": 1.9392712550607287, "grad_norm": 0.4515650241821968, "learning_rate": 3.074135451053475e-05, "loss": 0.4497, "step": 479 }, { "epoch": 1.9433198380566803, "grad_norm": 0.4555170266449801, "learning_rate": 3.069360584592015e-05, "loss": 0.4342, "step": 480 }, { "epoch": 1.9473684210526314, "grad_norm": 0.45386145322301696, "learning_rate": 3.064577167551816e-05, "loss": 0.4458, "step": 481 }, { "epoch": 1.951417004048583, "grad_norm": 0.43158266360647424, "learning_rate": 3.059785238180953e-05, "loss": 0.4456, "step": 482 }, { "epoch": 1.9554655870445345, "grad_norm": 0.4072051407829727, "learning_rate": 3.054984834795566e-05, "loss": 0.444, "step": 483 }, { "epoch": 1.9595141700404857, "grad_norm": 0.4966268366778386, "learning_rate": 3.0501759957795537e-05, "loss": 0.4609, "step": 484 }, { "epoch": 1.9635627530364372, "grad_norm": 0.40408449038858996, "learning_rate": 3.0453587595842627e-05, "loss": 0.4251, "step": 485 }, { "epoch": 1.9676113360323888, "grad_norm": 0.4854002061069841, "learning_rate": 3.0405331647281856e-05, "loss": 0.4396, "step": 486 }, { "epoch": 1.97165991902834, "grad_norm": 0.4172803429158572, "learning_rate": 3.0356992497966508e-05, "loss": 0.453, "step": 487 }, { "epoch": 1.9757085020242915, "grad_norm": 0.48780552928483106, "learning_rate": 3.0308570534415137e-05, "loss": 0.4457, "step": 488 }, { "epoch": 1.979757085020243, "grad_norm": 0.41515031121514545, "learning_rate": 3.0260066143808467e-05, "loss": 0.4507, "step": 489 }, { "epoch": 1.9838056680161942, "grad_norm": 0.45055890103736673, "learning_rate": 3.021147971398632e-05, "loss": 0.455, "step": 490 }, { "epoch": 1.9878542510121457, "grad_norm": 0.43509327995768776, "learning_rate": 3.0162811633444478e-05, "loss": 0.4627, "step": 491 }, { "epoch": 1.9919028340080973, "grad_norm": 0.4123634742537315, "learning_rate": 3.0114062291331635e-05, "loss": 0.4461, "step": 492 }, { "epoch": 1.9959514170040484, "grad_norm": 0.38229692926419556, "learning_rate": 3.0065232077446217e-05, "loss": 0.4462, "step": 493 }, { "epoch": 2.0, "grad_norm": 0.4138593540412117, "learning_rate": 3.001632138223332e-05, "loss": 0.4574, "step": 494 }, { "epoch": 2.0040485829959516, "grad_norm": 0.6536521237728865, "learning_rate": 2.9967330596781565e-05, "loss": 0.3589, "step": 495 }, { "epoch": 2.0080971659919027, "grad_norm": 0.42651672836191457, "learning_rate": 2.9918260112819952e-05, "loss": 0.345, "step": 496 }, { "epoch": 2.0121457489878543, "grad_norm": 0.8815823939100071, "learning_rate": 2.9869110322714778e-05, "loss": 0.3271, "step": 497 }, { "epoch": 2.016194331983806, "grad_norm": 0.48011868732113894, "learning_rate": 2.9819881619466447e-05, "loss": 0.3323, "step": 498 }, { "epoch": 2.020242914979757, "grad_norm": 0.43009401741124603, "learning_rate": 2.9770574396706364e-05, "loss": 0.346, "step": 499 }, { "epoch": 2.0242914979757085, "grad_norm": 0.4451941551895094, "learning_rate": 2.972118904869376e-05, "loss": 0.3424, "step": 500 }, { "epoch": 2.02834008097166, "grad_norm": 0.4324880934473873, "learning_rate": 2.9671725970312563e-05, "loss": 0.3245, "step": 501 }, { "epoch": 2.032388663967611, "grad_norm": 0.5122423876767911, "learning_rate": 2.9622185557068238e-05, "loss": 0.3329, "step": 502 }, { "epoch": 2.0364372469635628, "grad_norm": 0.4328985052646928, "learning_rate": 2.95725682050846e-05, "loss": 0.3229, "step": 503 }, { "epoch": 2.0404858299595143, "grad_norm": 0.5213926692788374, "learning_rate": 2.9522874311100684e-05, "loss": 0.3395, "step": 504 }, { "epoch": 2.0445344129554655, "grad_norm": 0.4646427186328402, "learning_rate": 2.9473104272467526e-05, "loss": 0.3334, "step": 505 }, { "epoch": 2.048582995951417, "grad_norm": 0.46603891174146883, "learning_rate": 2.942325848714505e-05, "loss": 0.3361, "step": 506 }, { "epoch": 2.0526315789473686, "grad_norm": 0.47726708705199916, "learning_rate": 2.9373337353698804e-05, "loss": 0.3381, "step": 507 }, { "epoch": 2.0566801619433197, "grad_norm": 0.3945776610212143, "learning_rate": 2.932334127129686e-05, "loss": 0.3113, "step": 508 }, { "epoch": 2.0607287449392713, "grad_norm": 0.5594884959771137, "learning_rate": 2.9273270639706547e-05, "loss": 0.3457, "step": 509 }, { "epoch": 2.064777327935223, "grad_norm": 0.40412281902378794, "learning_rate": 2.922312585929131e-05, "loss": 0.3163, "step": 510 }, { "epoch": 2.068825910931174, "grad_norm": 0.4632706441991674, "learning_rate": 2.9172907331007478e-05, "loss": 0.3189, "step": 511 }, { "epoch": 2.0728744939271255, "grad_norm": 0.41162828809352797, "learning_rate": 2.9122615456401053e-05, "loss": 0.3163, "step": 512 }, { "epoch": 2.076923076923077, "grad_norm": 0.42953037969733027, "learning_rate": 2.9072250637604535e-05, "loss": 0.3205, "step": 513 }, { "epoch": 2.080971659919028, "grad_norm": 0.4262191111016638, "learning_rate": 2.9021813277333667e-05, "loss": 0.3079, "step": 514 }, { "epoch": 2.08502024291498, "grad_norm": 0.39011091295524364, "learning_rate": 2.8971303778884244e-05, "loss": 0.3409, "step": 515 }, { "epoch": 2.0890688259109313, "grad_norm": 0.4135614054326196, "learning_rate": 2.8920722546128863e-05, "loss": 0.3472, "step": 516 }, { "epoch": 2.0931174089068825, "grad_norm": 0.39126283712445775, "learning_rate": 2.887006998351372e-05, "loss": 0.3244, "step": 517 }, { "epoch": 2.097165991902834, "grad_norm": 0.3845914500892814, "learning_rate": 2.881934649605535e-05, "loss": 0.3329, "step": 518 }, { "epoch": 2.1012145748987856, "grad_norm": 0.45239239382819996, "learning_rate": 2.8768552489337408e-05, "loss": 0.332, "step": 519 }, { "epoch": 2.1052631578947367, "grad_norm": 0.37798530335196107, "learning_rate": 2.8717688369507425e-05, "loss": 0.3271, "step": 520 }, { "epoch": 2.1093117408906883, "grad_norm": 0.41243518531516304, "learning_rate": 2.8666754543273535e-05, "loss": 0.3361, "step": 521 }, { "epoch": 2.11336032388664, "grad_norm": 0.38855788484509984, "learning_rate": 2.8615751417901273e-05, "loss": 0.3296, "step": 522 }, { "epoch": 2.117408906882591, "grad_norm": 0.39062968278275095, "learning_rate": 2.856467940121025e-05, "loss": 0.3338, "step": 523 }, { "epoch": 2.1214574898785425, "grad_norm": 0.46240347251094405, "learning_rate": 2.8513538901570964e-05, "loss": 0.3238, "step": 524 }, { "epoch": 2.125506072874494, "grad_norm": 0.40066255948297813, "learning_rate": 2.846233032790149e-05, "loss": 0.335, "step": 525 }, { "epoch": 2.1295546558704452, "grad_norm": 0.4540963045088433, "learning_rate": 2.84110540896642e-05, "loss": 0.3338, "step": 526 }, { "epoch": 2.133603238866397, "grad_norm": 0.37473932671423404, "learning_rate": 2.8359710596862555e-05, "loss": 0.3304, "step": 527 }, { "epoch": 2.1376518218623484, "grad_norm": 0.42651587315541173, "learning_rate": 2.8308300260037734e-05, "loss": 0.3329, "step": 528 }, { "epoch": 2.1417004048582995, "grad_norm": 0.37511787319989387, "learning_rate": 2.8256823490265424e-05, "loss": 0.3254, "step": 529 }, { "epoch": 2.145748987854251, "grad_norm": 0.3782396101129113, "learning_rate": 2.8205280699152515e-05, "loss": 0.3219, "step": 530 }, { "epoch": 2.1497975708502026, "grad_norm": 0.4197656003797071, "learning_rate": 2.8153672298833777e-05, "loss": 0.3213, "step": 531 }, { "epoch": 2.1538461538461537, "grad_norm": 0.3903752756261077, "learning_rate": 2.8101998701968615e-05, "loss": 0.311, "step": 532 }, { "epoch": 2.1578947368421053, "grad_norm": 0.3973680421657998, "learning_rate": 2.805026032173773e-05, "loss": 0.3302, "step": 533 }, { "epoch": 2.161943319838057, "grad_norm": 0.3730316081205025, "learning_rate": 2.7998457571839832e-05, "loss": 0.3245, "step": 534 }, { "epoch": 2.165991902834008, "grad_norm": 0.4044882049191902, "learning_rate": 2.7946590866488322e-05, "loss": 0.3511, "step": 535 }, { "epoch": 2.1700404858299596, "grad_norm": 0.4186932152216172, "learning_rate": 2.7894660620408e-05, "loss": 0.3185, "step": 536 }, { "epoch": 2.174089068825911, "grad_norm": 0.4135942249829825, "learning_rate": 2.784266724883173e-05, "loss": 0.3217, "step": 537 }, { "epoch": 2.1781376518218623, "grad_norm": 0.41317475479511867, "learning_rate": 2.7790611167497128e-05, "loss": 0.3571, "step": 538 }, { "epoch": 2.182186234817814, "grad_norm": 0.3974679130279559, "learning_rate": 2.7738492792643224e-05, "loss": 0.3274, "step": 539 }, { "epoch": 2.1862348178137654, "grad_norm": 0.4437324274841912, "learning_rate": 2.768631254100716e-05, "loss": 0.329, "step": 540 }, { "epoch": 2.1902834008097165, "grad_norm": 0.3842928067287583, "learning_rate": 2.7634070829820836e-05, "loss": 0.327, "step": 541 }, { "epoch": 2.194331983805668, "grad_norm": 0.3900342386238941, "learning_rate": 2.7581768076807592e-05, "loss": 0.321, "step": 542 }, { "epoch": 2.1983805668016196, "grad_norm": 0.4244252805552632, "learning_rate": 2.7529404700178832e-05, "loss": 0.3215, "step": 543 }, { "epoch": 2.2024291497975708, "grad_norm": 0.4309350673756582, "learning_rate": 2.7476981118630735e-05, "loss": 0.3377, "step": 544 }, { "epoch": 2.2064777327935223, "grad_norm": 0.39306705902525135, "learning_rate": 2.742449775134085e-05, "loss": 0.3521, "step": 545 }, { "epoch": 2.2105263157894735, "grad_norm": 0.4270573852380715, "learning_rate": 2.7371955017964788e-05, "loss": 0.336, "step": 546 }, { "epoch": 2.214574898785425, "grad_norm": 0.38251985531026533, "learning_rate": 2.7319353338632845e-05, "loss": 0.324, "step": 547 }, { "epoch": 2.2186234817813766, "grad_norm": 0.42270666219452263, "learning_rate": 2.7266693133946645e-05, "loss": 0.3197, "step": 548 }, { "epoch": 2.2226720647773277, "grad_norm": 0.3666850342281139, "learning_rate": 2.7213974824975785e-05, "loss": 0.3246, "step": 549 }, { "epoch": 2.2267206477732793, "grad_norm": 0.3900884204286097, "learning_rate": 2.7161198833254464e-05, "loss": 0.3347, "step": 550 }, { "epoch": 2.230769230769231, "grad_norm": 0.3709693805112457, "learning_rate": 2.7108365580778095e-05, "loss": 0.3341, "step": 551 }, { "epoch": 2.234817813765182, "grad_norm": 0.39033258762755535, "learning_rate": 2.705547548999996e-05, "loss": 0.3329, "step": 552 }, { "epoch": 2.2388663967611335, "grad_norm": 0.4136435457152908, "learning_rate": 2.7002528983827817e-05, "loss": 0.3341, "step": 553 }, { "epoch": 2.242914979757085, "grad_norm": 0.37703308155458454, "learning_rate": 2.6949526485620517e-05, "loss": 0.3381, "step": 554 }, { "epoch": 2.246963562753036, "grad_norm": 0.4392597772980004, "learning_rate": 2.6896468419184623e-05, "loss": 0.3379, "step": 555 }, { "epoch": 2.251012145748988, "grad_norm": 0.38246157013614607, "learning_rate": 2.6843355208771024e-05, "loss": 0.3537, "step": 556 }, { "epoch": 2.2550607287449393, "grad_norm": 0.4304544246227196, "learning_rate": 2.6790187279071536e-05, "loss": 0.3408, "step": 557 }, { "epoch": 2.2591093117408905, "grad_norm": 0.39716452992712065, "learning_rate": 2.67369650552155e-05, "loss": 0.3469, "step": 558 }, { "epoch": 2.263157894736842, "grad_norm": 0.4169505027649558, "learning_rate": 2.6683688962766407e-05, "loss": 0.3174, "step": 559 }, { "epoch": 2.2672064777327936, "grad_norm": 0.42180866964308267, "learning_rate": 2.6630359427718468e-05, "loss": 0.3443, "step": 560 }, { "epoch": 2.2712550607287447, "grad_norm": 0.39684514078889205, "learning_rate": 2.6576976876493225e-05, "loss": 0.3402, "step": 561 }, { "epoch": 2.2753036437246963, "grad_norm": 0.3929352551098495, "learning_rate": 2.652354173593614e-05, "loss": 0.3313, "step": 562 }, { "epoch": 2.279352226720648, "grad_norm": 0.3888928330509781, "learning_rate": 2.647005443331317e-05, "loss": 0.3445, "step": 563 }, { "epoch": 2.283400809716599, "grad_norm": 0.37524571584527566, "learning_rate": 2.6416515396307354e-05, "loss": 0.3205, "step": 564 }, { "epoch": 2.2874493927125505, "grad_norm": 0.40760754662404036, "learning_rate": 2.636292505301542e-05, "loss": 0.3498, "step": 565 }, { "epoch": 2.291497975708502, "grad_norm": 0.37543806410689196, "learning_rate": 2.630928383194431e-05, "loss": 0.3169, "step": 566 }, { "epoch": 2.2955465587044532, "grad_norm": 0.4075465736265335, "learning_rate": 2.625559216200781e-05, "loss": 0.333, "step": 567 }, { "epoch": 2.299595141700405, "grad_norm": 0.38091311248650217, "learning_rate": 2.620185047252308e-05, "loss": 0.3476, "step": 568 }, { "epoch": 2.3036437246963564, "grad_norm": 0.39186911788220613, "learning_rate": 2.614805919320723e-05, "loss": 0.3187, "step": 569 }, { "epoch": 2.3076923076923075, "grad_norm": 0.3745450894483282, "learning_rate": 2.6094218754173895e-05, "loss": 0.3263, "step": 570 }, { "epoch": 2.311740890688259, "grad_norm": 0.3674456591865424, "learning_rate": 2.60403295859298e-05, "loss": 0.3421, "step": 571 }, { "epoch": 2.3157894736842106, "grad_norm": 0.3860603868747454, "learning_rate": 2.5986392119371297e-05, "loss": 0.3322, "step": 572 }, { "epoch": 2.3198380566801617, "grad_norm": 0.37952726607777376, "learning_rate": 2.5932406785780928e-05, "loss": 0.3467, "step": 573 }, { "epoch": 2.3238866396761133, "grad_norm": 0.3989286403574394, "learning_rate": 2.5878374016823987e-05, "loss": 0.3407, "step": 574 }, { "epoch": 2.327935222672065, "grad_norm": 0.3995124204220533, "learning_rate": 2.5824294244545045e-05, "loss": 0.3354, "step": 575 }, { "epoch": 2.331983805668016, "grad_norm": 0.38222854561098246, "learning_rate": 2.577016790136453e-05, "loss": 0.3294, "step": 576 }, { "epoch": 2.3360323886639676, "grad_norm": 0.37447465847994155, "learning_rate": 2.5715995420075225e-05, "loss": 0.3522, "step": 577 }, { "epoch": 2.340080971659919, "grad_norm": 0.4163466130878294, "learning_rate": 2.5661777233838864e-05, "loss": 0.3475, "step": 578 }, { "epoch": 2.3441295546558703, "grad_norm": 0.3847148649376593, "learning_rate": 2.5607513776182616e-05, "loss": 0.3217, "step": 579 }, { "epoch": 2.348178137651822, "grad_norm": 0.3712573552288237, "learning_rate": 2.5553205480995633e-05, "loss": 0.3464, "step": 580 }, { "epoch": 2.3522267206477734, "grad_norm": 0.3589479477172961, "learning_rate": 2.5498852782525604e-05, "loss": 0.3246, "step": 581 }, { "epoch": 2.3562753036437245, "grad_norm": 0.3626694911992029, "learning_rate": 2.5444456115375252e-05, "loss": 0.3551, "step": 582 }, { "epoch": 2.360323886639676, "grad_norm": 0.4109690123994777, "learning_rate": 2.539001591449889e-05, "loss": 0.3204, "step": 583 }, { "epoch": 2.3643724696356276, "grad_norm": 0.373907987869019, "learning_rate": 2.53355326151989e-05, "loss": 0.3407, "step": 584 }, { "epoch": 2.3684210526315788, "grad_norm": 0.39693397690260834, "learning_rate": 2.5281006653122288e-05, "loss": 0.3244, "step": 585 }, { "epoch": 2.3724696356275303, "grad_norm": 0.3708622424472651, "learning_rate": 2.5226438464257217e-05, "loss": 0.3322, "step": 586 }, { "epoch": 2.376518218623482, "grad_norm": 0.41804599887959515, "learning_rate": 2.5171828484929447e-05, "loss": 0.3324, "step": 587 }, { "epoch": 2.380566801619433, "grad_norm": 0.39095699006705753, "learning_rate": 2.5117177151798934e-05, "loss": 0.3266, "step": 588 }, { "epoch": 2.3846153846153846, "grad_norm": 0.3935746265572346, "learning_rate": 2.506248490185627e-05, "loss": 0.3422, "step": 589 }, { "epoch": 2.388663967611336, "grad_norm": 0.35666171374163375, "learning_rate": 2.500775217241923e-05, "loss": 0.3272, "step": 590 }, { "epoch": 2.3927125506072873, "grad_norm": 0.44786287557754983, "learning_rate": 2.4952979401129266e-05, "loss": 0.3259, "step": 591 }, { "epoch": 2.396761133603239, "grad_norm": 0.37603943970069603, "learning_rate": 2.4898167025948e-05, "loss": 0.337, "step": 592 }, { "epoch": 2.4008097165991904, "grad_norm": 0.4200088781891686, "learning_rate": 2.4843315485153703e-05, "loss": 0.3293, "step": 593 }, { "epoch": 2.4048582995951415, "grad_norm": 0.3850990458722488, "learning_rate": 2.4788425217337856e-05, "loss": 0.3287, "step": 594 }, { "epoch": 2.408906882591093, "grad_norm": 0.44487935239639714, "learning_rate": 2.4733496661401572e-05, "loss": 0.3427, "step": 595 }, { "epoch": 2.4129554655870447, "grad_norm": 0.40365612712302007, "learning_rate": 2.4678530256552114e-05, "loss": 0.3504, "step": 596 }, { "epoch": 2.417004048582996, "grad_norm": 0.44323525764929633, "learning_rate": 2.46235264422994e-05, "loss": 0.338, "step": 597 }, { "epoch": 2.4210526315789473, "grad_norm": 0.4355020257235834, "learning_rate": 2.4568485658452452e-05, "loss": 0.3319, "step": 598 }, { "epoch": 2.425101214574899, "grad_norm": 0.4630585737968999, "learning_rate": 2.451340834511592e-05, "loss": 0.3418, "step": 599 }, { "epoch": 2.42914979757085, "grad_norm": 0.41135051363521724, "learning_rate": 2.4458294942686528e-05, "loss": 0.3513, "step": 600 }, { "epoch": 2.4331983805668016, "grad_norm": 0.4342342059450192, "learning_rate": 2.440314589184958e-05, "loss": 0.3325, "step": 601 }, { "epoch": 2.437246963562753, "grad_norm": 0.379771056227497, "learning_rate": 2.434796163357541e-05, "loss": 0.3153, "step": 602 }, { "epoch": 2.4412955465587043, "grad_norm": 0.40522267956203345, "learning_rate": 2.429274260911588e-05, "loss": 0.3302, "step": 603 }, { "epoch": 2.445344129554656, "grad_norm": 0.39633388177088574, "learning_rate": 2.423748926000084e-05, "loss": 0.331, "step": 604 }, { "epoch": 2.4493927125506074, "grad_norm": 0.4171619369226803, "learning_rate": 2.418220202803459e-05, "loss": 0.331, "step": 605 }, { "epoch": 2.4534412955465585, "grad_norm": 0.399224677090107, "learning_rate": 2.412688135529237e-05, "loss": 0.3263, "step": 606 }, { "epoch": 2.45748987854251, "grad_norm": 0.4456023181568636, "learning_rate": 2.4071527684116807e-05, "loss": 0.334, "step": 607 }, { "epoch": 2.4615384615384617, "grad_norm": 0.3742658407318305, "learning_rate": 2.4016141457114372e-05, "loss": 0.3471, "step": 608 }, { "epoch": 2.465587044534413, "grad_norm": 0.4286050997089446, "learning_rate": 2.396072311715187e-05, "loss": 0.3398, "step": 609 }, { "epoch": 2.4696356275303644, "grad_norm": 0.3816480248286151, "learning_rate": 2.3905273107352863e-05, "loss": 0.3334, "step": 610 }, { "epoch": 2.473684210526316, "grad_norm": 0.39005300422376665, "learning_rate": 2.3849791871094157e-05, "loss": 0.3209, "step": 611 }, { "epoch": 2.477732793522267, "grad_norm": 0.3698525385432666, "learning_rate": 2.379427985200223e-05, "loss": 0.3399, "step": 612 }, { "epoch": 2.4817813765182186, "grad_norm": 0.4131985168867916, "learning_rate": 2.373873749394972e-05, "loss": 0.3172, "step": 613 }, { "epoch": 2.48582995951417, "grad_norm": 0.3844649319913633, "learning_rate": 2.3683165241051836e-05, "loss": 0.3363, "step": 614 }, { "epoch": 2.4898785425101213, "grad_norm": 0.4448653115357331, "learning_rate": 2.3627563537662823e-05, "loss": 0.3468, "step": 615 }, { "epoch": 2.493927125506073, "grad_norm": 0.39501557545942667, "learning_rate": 2.3571932828372433e-05, "loss": 0.3464, "step": 616 }, { "epoch": 2.4979757085020244, "grad_norm": 0.3979339326337875, "learning_rate": 2.351627355800233e-05, "loss": 0.3258, "step": 617 }, { "epoch": 2.5020242914979756, "grad_norm": 0.45724717108116947, "learning_rate": 2.346058617160256e-05, "loss": 0.3486, "step": 618 }, { "epoch": 2.506072874493927, "grad_norm": 0.3734624575511948, "learning_rate": 2.3404871114447976e-05, "loss": 0.3178, "step": 619 }, { "epoch": 2.5101214574898787, "grad_norm": 0.3763908469056927, "learning_rate": 2.334912883203469e-05, "loss": 0.3423, "step": 620 }, { "epoch": 2.51417004048583, "grad_norm": 0.3799126401762934, "learning_rate": 2.3293359770076505e-05, "loss": 0.3258, "step": 621 }, { "epoch": 2.5182186234817814, "grad_norm": 0.4033858516794894, "learning_rate": 2.323756437450136e-05, "loss": 0.3202, "step": 622 }, { "epoch": 2.522267206477733, "grad_norm": 0.3545601969969016, "learning_rate": 2.3181743091447754e-05, "loss": 0.3375, "step": 623 }, { "epoch": 2.526315789473684, "grad_norm": 0.42129266825584016, "learning_rate": 2.3125896367261164e-05, "loss": 0.3224, "step": 624 }, { "epoch": 2.5303643724696356, "grad_norm": 0.39713168460333265, "learning_rate": 2.307002464849052e-05, "loss": 0.3382, "step": 625 }, { "epoch": 2.534412955465587, "grad_norm": 0.46560377755684984, "learning_rate": 2.30141283818846e-05, "loss": 0.3279, "step": 626 }, { "epoch": 2.5384615384615383, "grad_norm": 0.3669189935576969, "learning_rate": 2.2958208014388462e-05, "loss": 0.322, "step": 627 }, { "epoch": 2.54251012145749, "grad_norm": 0.41229760227336926, "learning_rate": 2.2902263993139857e-05, "loss": 0.3304, "step": 628 }, { "epoch": 2.5465587044534415, "grad_norm": 0.4025626217054555, "learning_rate": 2.2846296765465708e-05, "loss": 0.3175, "step": 629 }, { "epoch": 2.5506072874493926, "grad_norm": 0.3873940337256758, "learning_rate": 2.2790306778878465e-05, "loss": 0.3269, "step": 630 }, { "epoch": 2.554655870445344, "grad_norm": 0.39604423871091593, "learning_rate": 2.273429448107257e-05, "loss": 0.3342, "step": 631 }, { "epoch": 2.5587044534412957, "grad_norm": 0.3750798238492829, "learning_rate": 2.2678260319920868e-05, "loss": 0.3306, "step": 632 }, { "epoch": 2.562753036437247, "grad_norm": 0.39171432706079484, "learning_rate": 2.262220474347102e-05, "loss": 0.325, "step": 633 }, { "epoch": 2.5668016194331984, "grad_norm": 0.4276587856433395, "learning_rate": 2.2566128199941918e-05, "loss": 0.3395, "step": 634 }, { "epoch": 2.57085020242915, "grad_norm": 0.39730995795638885, "learning_rate": 2.2510031137720104e-05, "loss": 0.3389, "step": 635 }, { "epoch": 2.574898785425101, "grad_norm": 0.4100419649050483, "learning_rate": 2.2453914005356206e-05, "loss": 0.3415, "step": 636 }, { "epoch": 2.5789473684210527, "grad_norm": 0.39629728603750464, "learning_rate": 2.2397777251561302e-05, "loss": 0.3499, "step": 637 }, { "epoch": 2.582995951417004, "grad_norm": 0.38610380779186027, "learning_rate": 2.2341621325203393e-05, "loss": 0.3293, "step": 638 }, { "epoch": 2.5870445344129553, "grad_norm": 0.3976929152570026, "learning_rate": 2.2285446675303764e-05, "loss": 0.3225, "step": 639 }, { "epoch": 2.591093117408907, "grad_norm": 0.3875511247649301, "learning_rate": 2.2229253751033423e-05, "loss": 0.3371, "step": 640 }, { "epoch": 2.5951417004048585, "grad_norm": 0.34293583920451215, "learning_rate": 2.2173043001709492e-05, "loss": 0.3279, "step": 641 }, { "epoch": 2.5991902834008096, "grad_norm": 0.3760493837302276, "learning_rate": 2.2116814876791627e-05, "loss": 0.3159, "step": 642 }, { "epoch": 2.603238866396761, "grad_norm": 0.36989838917258816, "learning_rate": 2.2060569825878413e-05, "loss": 0.3535, "step": 643 }, { "epoch": 2.6072874493927127, "grad_norm": 0.38455152241584706, "learning_rate": 2.2004308298703777e-05, "loss": 0.3397, "step": 644 }, { "epoch": 2.611336032388664, "grad_norm": 0.3535699523415237, "learning_rate": 2.1948030745133396e-05, "loss": 0.342, "step": 645 }, { "epoch": 2.6153846153846154, "grad_norm": 0.3406125418037752, "learning_rate": 2.1891737615161083e-05, "loss": 0.3282, "step": 646 }, { "epoch": 2.619433198380567, "grad_norm": 0.37177052079040235, "learning_rate": 2.1835429358905218e-05, "loss": 0.346, "step": 647 }, { "epoch": 2.623481781376518, "grad_norm": 0.3634408703463283, "learning_rate": 2.17791064266051e-05, "loss": 0.3468, "step": 648 }, { "epoch": 2.6275303643724697, "grad_norm": 0.38226614464888936, "learning_rate": 2.172276926861741e-05, "loss": 0.3248, "step": 649 }, { "epoch": 2.6315789473684212, "grad_norm": 0.3713488447481757, "learning_rate": 2.166641833541255e-05, "loss": 0.3292, "step": 650 }, { "epoch": 2.6356275303643724, "grad_norm": 0.3686489508208221, "learning_rate": 2.161005407757109e-05, "loss": 0.3391, "step": 651 }, { "epoch": 2.639676113360324, "grad_norm": 0.3830315647529736, "learning_rate": 2.155367694578013e-05, "loss": 0.3445, "step": 652 }, { "epoch": 2.6437246963562755, "grad_norm": 0.33284495984698237, "learning_rate": 2.1497287390829712e-05, "loss": 0.3257, "step": 653 }, { "epoch": 2.6477732793522266, "grad_norm": 0.355753354649344, "learning_rate": 2.1440885863609208e-05, "loss": 0.3265, "step": 654 }, { "epoch": 2.651821862348178, "grad_norm": 0.36402251110730266, "learning_rate": 2.1384472815103737e-05, "loss": 0.3322, "step": 655 }, { "epoch": 2.6558704453441297, "grad_norm": 0.3361561227306645, "learning_rate": 2.1328048696390534e-05, "loss": 0.3365, "step": 656 }, { "epoch": 2.659919028340081, "grad_norm": 0.3681985407884413, "learning_rate": 2.1271613958635342e-05, "loss": 0.3481, "step": 657 }, { "epoch": 2.6639676113360324, "grad_norm": 0.35227773042640337, "learning_rate": 2.1215169053088825e-05, "loss": 0.3314, "step": 658 }, { "epoch": 2.668016194331984, "grad_norm": 0.3644141678553013, "learning_rate": 2.1158714431082937e-05, "loss": 0.3529, "step": 659 }, { "epoch": 2.672064777327935, "grad_norm": 0.3519002475372301, "learning_rate": 2.110225054402733e-05, "loss": 0.34, "step": 660 }, { "epoch": 2.6761133603238867, "grad_norm": 0.3859308542765228, "learning_rate": 2.1045777843405747e-05, "loss": 0.3227, "step": 661 }, { "epoch": 2.6801619433198383, "grad_norm": 0.37928506659435784, "learning_rate": 2.09892967807724e-05, "loss": 0.3326, "step": 662 }, { "epoch": 2.6842105263157894, "grad_norm": 0.3623690901339109, "learning_rate": 2.093280780774835e-05, "loss": 0.324, "step": 663 }, { "epoch": 2.688259109311741, "grad_norm": 0.36936204769479575, "learning_rate": 2.087631137601793e-05, "loss": 0.3278, "step": 664 }, { "epoch": 2.6923076923076925, "grad_norm": 0.3851829430390352, "learning_rate": 2.0819807937325104e-05, "loss": 0.3452, "step": 665 }, { "epoch": 2.6963562753036436, "grad_norm": 0.352591356057226, "learning_rate": 2.0763297943469847e-05, "loss": 0.3327, "step": 666 }, { "epoch": 2.700404858299595, "grad_norm": 0.372466158428975, "learning_rate": 2.070678184630458e-05, "loss": 0.3305, "step": 667 }, { "epoch": 2.7044534412955468, "grad_norm": 0.3589704518493423, "learning_rate": 2.06502600977305e-05, "loss": 0.3296, "step": 668 }, { "epoch": 2.708502024291498, "grad_norm": 0.36007882468940017, "learning_rate": 2.0593733149694008e-05, "loss": 0.3545, "step": 669 }, { "epoch": 2.7125506072874495, "grad_norm": 0.38477993288048445, "learning_rate": 2.0537201454183074e-05, "loss": 0.3171, "step": 670 }, { "epoch": 2.716599190283401, "grad_norm": 0.36732917922975, "learning_rate": 2.0480665463223626e-05, "loss": 0.3271, "step": 671 }, { "epoch": 2.720647773279352, "grad_norm": 0.3660156715115414, "learning_rate": 2.042412562887594e-05, "loss": 0.3229, "step": 672 }, { "epoch": 2.7246963562753037, "grad_norm": 0.3803680521688352, "learning_rate": 2.0367582403231033e-05, "loss": 0.3258, "step": 673 }, { "epoch": 2.7287449392712553, "grad_norm": 0.3745682008843603, "learning_rate": 2.0311036238407023e-05, "loss": 0.3022, "step": 674 }, { "epoch": 2.7327935222672064, "grad_norm": 0.36218190369365033, "learning_rate": 2.0254487586545534e-05, "loss": 0.3126, "step": 675 }, { "epoch": 2.736842105263158, "grad_norm": 0.39059393878264265, "learning_rate": 2.0197936899808088e-05, "loss": 0.3299, "step": 676 }, { "epoch": 2.7408906882591095, "grad_norm": 0.35840120045479523, "learning_rate": 2.0141384630372466e-05, "loss": 0.337, "step": 677 }, { "epoch": 2.7449392712550607, "grad_norm": 0.3890040819169426, "learning_rate": 2.0084831230429106e-05, "loss": 0.3287, "step": 678 }, { "epoch": 2.748987854251012, "grad_norm": 0.37271812273749083, "learning_rate": 2.0028277152177492e-05, "loss": 0.3224, "step": 679 }, { "epoch": 2.753036437246964, "grad_norm": 0.3737111577139371, "learning_rate": 1.9971722847822518e-05, "loss": 0.3309, "step": 680 }, { "epoch": 2.757085020242915, "grad_norm": 0.36004430399963544, "learning_rate": 1.99151687695709e-05, "loss": 0.3345, "step": 681 }, { "epoch": 2.7611336032388665, "grad_norm": 0.37921875700608854, "learning_rate": 1.9858615369627537e-05, "loss": 0.3331, "step": 682 }, { "epoch": 2.765182186234818, "grad_norm": 0.36322738918267805, "learning_rate": 1.9802063100191916e-05, "loss": 0.3618, "step": 683 }, { "epoch": 2.769230769230769, "grad_norm": 0.3559944355901215, "learning_rate": 1.974551241345447e-05, "loss": 0.3257, "step": 684 }, { "epoch": 2.7732793522267207, "grad_norm": 0.37071133589407773, "learning_rate": 1.9688963761592984e-05, "loss": 0.3007, "step": 685 }, { "epoch": 2.7773279352226723, "grad_norm": 0.3635534831615465, "learning_rate": 1.963241759676897e-05, "loss": 0.3226, "step": 686 }, { "epoch": 2.7813765182186234, "grad_norm": 0.36128020008105377, "learning_rate": 1.9575874371124066e-05, "loss": 0.3322, "step": 687 }, { "epoch": 2.785425101214575, "grad_norm": 0.3354425809766728, "learning_rate": 1.951933453677638e-05, "loss": 0.3321, "step": 688 }, { "epoch": 2.7894736842105265, "grad_norm": 0.37731578000964494, "learning_rate": 1.9462798545816932e-05, "loss": 0.3296, "step": 689 }, { "epoch": 2.7935222672064777, "grad_norm": 0.3737496364964882, "learning_rate": 1.9406266850305996e-05, "loss": 0.3338, "step": 690 }, { "epoch": 2.7975708502024292, "grad_norm": 0.35278018016452545, "learning_rate": 1.9349739902269503e-05, "loss": 0.3247, "step": 691 }, { "epoch": 2.801619433198381, "grad_norm": 0.3563838881358852, "learning_rate": 1.9293218153695425e-05, "loss": 0.3364, "step": 692 }, { "epoch": 2.805668016194332, "grad_norm": 0.3636036193845539, "learning_rate": 1.9236702056530153e-05, "loss": 0.3276, "step": 693 }, { "epoch": 2.8097165991902835, "grad_norm": 0.3594551154041091, "learning_rate": 1.9180192062674907e-05, "loss": 0.3364, "step": 694 }, { "epoch": 2.813765182186235, "grad_norm": 0.39585212893625665, "learning_rate": 1.9123688623982076e-05, "loss": 0.3185, "step": 695 }, { "epoch": 2.817813765182186, "grad_norm": 0.3529821016663356, "learning_rate": 1.906719219225165e-05, "loss": 0.3311, "step": 696 }, { "epoch": 2.8218623481781377, "grad_norm": 0.39664212195742987, "learning_rate": 1.9010703219227603e-05, "loss": 0.3355, "step": 697 }, { "epoch": 2.8259109311740893, "grad_norm": 0.35844044783791174, "learning_rate": 1.8954222156594256e-05, "loss": 0.3172, "step": 698 }, { "epoch": 2.8299595141700404, "grad_norm": 0.38314966241231824, "learning_rate": 1.8897749455972673e-05, "loss": 0.3279, "step": 699 }, { "epoch": 2.834008097165992, "grad_norm": 0.3811139092623785, "learning_rate": 1.884128556891707e-05, "loss": 0.3286, "step": 700 }, { "epoch": 2.8380566801619436, "grad_norm": 0.3553391858521037, "learning_rate": 1.878483094691119e-05, "loss": 0.3307, "step": 701 }, { "epoch": 2.8421052631578947, "grad_norm": 0.3708967654189989, "learning_rate": 1.8728386041364664e-05, "loss": 0.3355, "step": 702 }, { "epoch": 2.8461538461538463, "grad_norm": 0.37478519026060964, "learning_rate": 1.867195130360947e-05, "loss": 0.3316, "step": 703 }, { "epoch": 2.850202429149798, "grad_norm": 0.3575585765550056, "learning_rate": 1.8615527184896263e-05, "loss": 0.3341, "step": 704 }, { "epoch": 2.854251012145749, "grad_norm": 0.3525687294015912, "learning_rate": 1.8559114136390795e-05, "loss": 0.3147, "step": 705 }, { "epoch": 2.8582995951417005, "grad_norm": 0.40537933167071705, "learning_rate": 1.8502712609170298e-05, "loss": 0.3216, "step": 706 }, { "epoch": 2.862348178137652, "grad_norm": 0.3488098205159506, "learning_rate": 1.8446323054219876e-05, "loss": 0.3451, "step": 707 }, { "epoch": 2.866396761133603, "grad_norm": 0.4249818781164053, "learning_rate": 1.838994592242891e-05, "loss": 0.3243, "step": 708 }, { "epoch": 2.8704453441295548, "grad_norm": 0.38911593711460335, "learning_rate": 1.8333581664587453e-05, "loss": 0.3436, "step": 709 }, { "epoch": 2.8744939271255063, "grad_norm": 0.3521889014055704, "learning_rate": 1.8277230731382593e-05, "loss": 0.3408, "step": 710 }, { "epoch": 2.8785425101214575, "grad_norm": 0.43110150614198095, "learning_rate": 1.82208935733949e-05, "loss": 0.3219, "step": 711 }, { "epoch": 2.882591093117409, "grad_norm": 0.40829637851022094, "learning_rate": 1.8164570641094793e-05, "loss": 0.3362, "step": 712 }, { "epoch": 2.8866396761133606, "grad_norm": 0.3705199228959182, "learning_rate": 1.810826238483892e-05, "loss": 0.3253, "step": 713 }, { "epoch": 2.8906882591093117, "grad_norm": 0.4351509968719554, "learning_rate": 1.8051969254866608e-05, "loss": 0.3249, "step": 714 }, { "epoch": 2.8947368421052633, "grad_norm": 0.3789064911768832, "learning_rate": 1.7995691701296226e-05, "loss": 0.3296, "step": 715 }, { "epoch": 2.898785425101215, "grad_norm": 0.3465016087131927, "learning_rate": 1.7939430174121593e-05, "loss": 0.339, "step": 716 }, { "epoch": 2.902834008097166, "grad_norm": 0.3862001071307955, "learning_rate": 1.788318512320838e-05, "loss": 0.3336, "step": 717 }, { "epoch": 2.9068825910931175, "grad_norm": 0.3232321740468442, "learning_rate": 1.782695699829051e-05, "loss": 0.3209, "step": 718 }, { "epoch": 2.910931174089069, "grad_norm": 0.37013211566571264, "learning_rate": 1.7770746248966587e-05, "loss": 0.3405, "step": 719 }, { "epoch": 2.91497975708502, "grad_norm": 0.3546758773115873, "learning_rate": 1.7714553324696243e-05, "loss": 0.3271, "step": 720 }, { "epoch": 2.919028340080972, "grad_norm": 0.3776554619467601, "learning_rate": 1.7658378674796614e-05, "loss": 0.341, "step": 721 }, { "epoch": 2.9230769230769234, "grad_norm": 0.35536506530683265, "learning_rate": 1.76022227484387e-05, "loss": 0.3289, "step": 722 }, { "epoch": 2.9271255060728745, "grad_norm": 0.37640310321800297, "learning_rate": 1.7546085994643807e-05, "loss": 0.3414, "step": 723 }, { "epoch": 2.931174089068826, "grad_norm": 0.3741383334097057, "learning_rate": 1.7489968862279902e-05, "loss": 0.3222, "step": 724 }, { "epoch": 2.9352226720647776, "grad_norm": 0.3458831850636658, "learning_rate": 1.743387180005809e-05, "loss": 0.3209, "step": 725 }, { "epoch": 2.9392712550607287, "grad_norm": 0.3640805458553579, "learning_rate": 1.737779525652899e-05, "loss": 0.3327, "step": 726 }, { "epoch": 2.9433198380566803, "grad_norm": 0.3722688106241466, "learning_rate": 1.732173968007914e-05, "loss": 0.3213, "step": 727 }, { "epoch": 2.9473684210526314, "grad_norm": 0.3543649409718381, "learning_rate": 1.7265705518927437e-05, "loss": 0.3228, "step": 728 }, { "epoch": 2.951417004048583, "grad_norm": 0.3412197084783442, "learning_rate": 1.7209693221121542e-05, "loss": 0.3353, "step": 729 }, { "epoch": 2.9554655870445345, "grad_norm": 0.3495912541711106, "learning_rate": 1.7153703234534302e-05, "loss": 0.3408, "step": 730 }, { "epoch": 2.9595141700404857, "grad_norm": 0.37025025384514937, "learning_rate": 1.709773600686015e-05, "loss": 0.3309, "step": 731 }, { "epoch": 2.9635627530364372, "grad_norm": 0.3695962144306522, "learning_rate": 1.7041791985611548e-05, "loss": 0.3204, "step": 732 }, { "epoch": 2.967611336032389, "grad_norm": 0.39094727500471504, "learning_rate": 1.69858716181154e-05, "loss": 0.3344, "step": 733 }, { "epoch": 2.97165991902834, "grad_norm": 0.36065533866076205, "learning_rate": 1.692997535150948e-05, "loss": 0.3345, "step": 734 }, { "epoch": 2.9757085020242915, "grad_norm": 0.387795604924638, "learning_rate": 1.687410363273884e-05, "loss": 0.327, "step": 735 }, { "epoch": 2.979757085020243, "grad_norm": 0.3734622610714601, "learning_rate": 1.6818256908552257e-05, "loss": 0.3288, "step": 736 }, { "epoch": 2.983805668016194, "grad_norm": 0.33256409140388743, "learning_rate": 1.6762435625498646e-05, "loss": 0.3419, "step": 737 }, { "epoch": 2.9878542510121457, "grad_norm": 0.3706337622545545, "learning_rate": 1.67066402299235e-05, "loss": 0.323, "step": 738 }, { "epoch": 2.9919028340080973, "grad_norm": 0.37519351570651355, "learning_rate": 1.6650871167965313e-05, "loss": 0.3467, "step": 739 }, { "epoch": 2.9959514170040484, "grad_norm": 0.33562519003504726, "learning_rate": 1.6595128885552028e-05, "loss": 0.3143, "step": 740 }, { "epoch": 3.0, "grad_norm": 0.36278630371056764, "learning_rate": 1.653941382839745e-05, "loss": 0.3324, "step": 741 }, { "epoch": 3.0040485829959516, "grad_norm": 0.5670430911182307, "learning_rate": 1.6483726441997673e-05, "loss": 0.2527, "step": 742 }, { "epoch": 3.0080971659919027, "grad_norm": 0.3647987789859095, "learning_rate": 1.642806717162757e-05, "loss": 0.2454, "step": 743 }, { "epoch": 3.0121457489878543, "grad_norm": 0.526634091165354, "learning_rate": 1.637243646233718e-05, "loss": 0.25, "step": 744 }, { "epoch": 3.016194331983806, "grad_norm": 0.5794075842585749, "learning_rate": 1.6316834758948174e-05, "loss": 0.2286, "step": 745 }, { "epoch": 3.020242914979757, "grad_norm": 0.44593149549944133, "learning_rate": 1.6261262506050282e-05, "loss": 0.225, "step": 746 }, { "epoch": 3.0242914979757085, "grad_norm": 0.38990791304360356, "learning_rate": 1.620572014799777e-05, "loss": 0.2554, "step": 747 }, { "epoch": 3.02834008097166, "grad_norm": 0.4760818440097428, "learning_rate": 1.6150208128905857e-05, "loss": 0.219, "step": 748 }, { "epoch": 3.032388663967611, "grad_norm": 0.4509737805694372, "learning_rate": 1.6094726892647147e-05, "loss": 0.2331, "step": 749 }, { "epoch": 3.0364372469635628, "grad_norm": 0.35888607405572387, "learning_rate": 1.6039276882848135e-05, "loss": 0.2303, "step": 750 }, { "epoch": 3.0404858299595143, "grad_norm": 0.42744340799621644, "learning_rate": 1.5983858542885635e-05, "loss": 0.2275, "step": 751 }, { "epoch": 3.0445344129554655, "grad_norm": 0.4189534552512932, "learning_rate": 1.5928472315883203e-05, "loss": 0.2375, "step": 752 }, { "epoch": 3.048582995951417, "grad_norm": 0.36823879338599064, "learning_rate": 1.5873118644707633e-05, "loss": 0.2276, "step": 753 }, { "epoch": 3.0526315789473686, "grad_norm": 0.37273530218322326, "learning_rate": 1.5817797971965413e-05, "loss": 0.2336, "step": 754 }, { "epoch": 3.0566801619433197, "grad_norm": 0.3934567320986107, "learning_rate": 1.576251073999917e-05, "loss": 0.2325, "step": 755 }, { "epoch": 3.0607287449392713, "grad_norm": 0.3651148786908135, "learning_rate": 1.5707257390884126e-05, "loss": 0.2219, "step": 756 }, { "epoch": 3.064777327935223, "grad_norm": 0.34762341419867226, "learning_rate": 1.5652038366424595e-05, "loss": 0.2309, "step": 757 }, { "epoch": 3.068825910931174, "grad_norm": 0.35112565973612975, "learning_rate": 1.5596854108150424e-05, "loss": 0.2048, "step": 758 }, { "epoch": 3.0728744939271255, "grad_norm": 0.3683678575091851, "learning_rate": 1.5541705057313476e-05, "loss": 0.2276, "step": 759 }, { "epoch": 3.076923076923077, "grad_norm": 0.3635766875945011, "learning_rate": 1.5486591654884086e-05, "loss": 0.2253, "step": 760 }, { "epoch": 3.080971659919028, "grad_norm": 0.3581193414066482, "learning_rate": 1.543151434154755e-05, "loss": 0.2243, "step": 761 }, { "epoch": 3.08502024291498, "grad_norm": 0.3408368936533361, "learning_rate": 1.5376473557700615e-05, "loss": 0.221, "step": 762 }, { "epoch": 3.0890688259109313, "grad_norm": 0.3541385079329363, "learning_rate": 1.5321469743447893e-05, "loss": 0.2312, "step": 763 }, { "epoch": 3.0931174089068825, "grad_norm": 0.33505151126230387, "learning_rate": 1.5266503338598434e-05, "loss": 0.221, "step": 764 }, { "epoch": 3.097165991902834, "grad_norm": 0.3330077434167176, "learning_rate": 1.5211574782662149e-05, "loss": 0.2179, "step": 765 }, { "epoch": 3.1012145748987856, "grad_norm": 0.3344803562878045, "learning_rate": 1.5156684514846307e-05, "loss": 0.2253, "step": 766 }, { "epoch": 3.1052631578947367, "grad_norm": 0.31785559481505316, "learning_rate": 1.5101832974052012e-05, "loss": 0.2347, "step": 767 }, { "epoch": 3.1093117408906883, "grad_norm": 0.32353653139312316, "learning_rate": 1.5047020598870737e-05, "loss": 0.2586, "step": 768 }, { "epoch": 3.11336032388664, "grad_norm": 0.3400428101942078, "learning_rate": 1.4992247827580778e-05, "loss": 0.2246, "step": 769 }, { "epoch": 3.117408906882591, "grad_norm": 0.33415883932612284, "learning_rate": 1.493751509814374e-05, "loss": 0.2297, "step": 770 }, { "epoch": 3.1214574898785425, "grad_norm": 0.31942780910209, "learning_rate": 1.4882822848201073e-05, "loss": 0.2394, "step": 771 }, { "epoch": 3.125506072874494, "grad_norm": 0.33140979277266847, "learning_rate": 1.4828171515070553e-05, "loss": 0.2372, "step": 772 }, { "epoch": 3.1295546558704452, "grad_norm": 0.31473449974758644, "learning_rate": 1.4773561535742793e-05, "loss": 0.2217, "step": 773 }, { "epoch": 3.133603238866397, "grad_norm": 0.32604789241484045, "learning_rate": 1.4718993346877715e-05, "loss": 0.2319, "step": 774 }, { "epoch": 3.1376518218623484, "grad_norm": 0.32503037355697645, "learning_rate": 1.466446738480111e-05, "loss": 0.2155, "step": 775 }, { "epoch": 3.1417004048582995, "grad_norm": 0.3248398279625943, "learning_rate": 1.460998408550112e-05, "loss": 0.2399, "step": 776 }, { "epoch": 3.145748987854251, "grad_norm": 0.32575738923927766, "learning_rate": 1.4555543884624751e-05, "loss": 0.22, "step": 777 }, { "epoch": 3.1497975708502026, "grad_norm": 0.3145033842667739, "learning_rate": 1.4501147217474402e-05, "loss": 0.253, "step": 778 }, { "epoch": 3.1538461538461537, "grad_norm": 0.33181711032057554, "learning_rate": 1.444679451900437e-05, "loss": 0.2307, "step": 779 }, { "epoch": 3.1578947368421053, "grad_norm": 0.33473462029099116, "learning_rate": 1.4392486223817397e-05, "loss": 0.2036, "step": 780 }, { "epoch": 3.161943319838057, "grad_norm": 0.3163812080293453, "learning_rate": 1.4338222766161143e-05, "loss": 0.2391, "step": 781 }, { "epoch": 3.165991902834008, "grad_norm": 0.3218932356652463, "learning_rate": 1.4284004579924777e-05, "loss": 0.2144, "step": 782 }, { "epoch": 3.1700404858299596, "grad_norm": 0.3479288738980913, "learning_rate": 1.4229832098635479e-05, "loss": 0.2235, "step": 783 }, { "epoch": 3.174089068825911, "grad_norm": 0.3484311412003011, "learning_rate": 1.4175705755454963e-05, "loss": 0.2243, "step": 784 }, { "epoch": 3.1781376518218623, "grad_norm": 0.3269353629886974, "learning_rate": 1.412162598317602e-05, "loss": 0.2318, "step": 785 }, { "epoch": 3.182186234817814, "grad_norm": 0.32966472929393187, "learning_rate": 1.406759321421907e-05, "loss": 0.2395, "step": 786 }, { "epoch": 3.1862348178137654, "grad_norm": 0.3249394866676796, "learning_rate": 1.401360788062871e-05, "loss": 0.2094, "step": 787 }, { "epoch": 3.1902834008097165, "grad_norm": 0.31109260571412545, "learning_rate": 1.3959670414070204e-05, "loss": 0.2216, "step": 788 }, { "epoch": 3.194331983805668, "grad_norm": 0.3091848426843289, "learning_rate": 1.3905781245826108e-05, "loss": 0.2307, "step": 789 }, { "epoch": 3.1983805668016196, "grad_norm": 0.30747352912829706, "learning_rate": 1.3851940806792778e-05, "loss": 0.2272, "step": 790 }, { "epoch": 3.2024291497975708, "grad_norm": 0.3125515178379994, "learning_rate": 1.379814952747693e-05, "loss": 0.2173, "step": 791 }, { "epoch": 3.2064777327935223, "grad_norm": 0.31871042379410625, "learning_rate": 1.3744407837992193e-05, "loss": 0.2379, "step": 792 }, { "epoch": 3.2105263157894735, "grad_norm": 0.3121790929529279, "learning_rate": 1.3690716168055692e-05, "loss": 0.2297, "step": 793 }, { "epoch": 3.214574898785425, "grad_norm": 0.31553225106620836, "learning_rate": 1.363707494698459e-05, "loss": 0.2359, "step": 794 }, { "epoch": 3.2186234817813766, "grad_norm": 0.31137546237459457, "learning_rate": 1.358348460369265e-05, "loss": 0.2477, "step": 795 }, { "epoch": 3.2226720647773277, "grad_norm": 0.3212447646477147, "learning_rate": 1.352994556668684e-05, "loss": 0.2339, "step": 796 }, { "epoch": 3.2267206477732793, "grad_norm": 0.3189469182362053, "learning_rate": 1.3476458264063865e-05, "loss": 0.2161, "step": 797 }, { "epoch": 3.230769230769231, "grad_norm": 0.32641436451468914, "learning_rate": 1.342302312350678e-05, "loss": 0.2261, "step": 798 }, { "epoch": 3.234817813765182, "grad_norm": 0.3261996738078234, "learning_rate": 1.3369640572281537e-05, "loss": 0.2335, "step": 799 }, { "epoch": 3.2388663967611335, "grad_norm": 0.34934178229101276, "learning_rate": 1.3316311037233596e-05, "loss": 0.2593, "step": 800 }, { "epoch": 3.242914979757085, "grad_norm": 0.3189131344792294, "learning_rate": 1.326303494478451e-05, "loss": 0.2174, "step": 801 }, { "epoch": 3.246963562753036, "grad_norm": 0.36542225521961685, "learning_rate": 1.3209812720928472e-05, "loss": 0.2069, "step": 802 }, { "epoch": 3.251012145748988, "grad_norm": 0.3249796684122578, "learning_rate": 1.315664479122898e-05, "loss": 0.2249, "step": 803 }, { "epoch": 3.2550607287449393, "grad_norm": 0.30639130358775646, "learning_rate": 1.3103531580815378e-05, "loss": 0.2131, "step": 804 }, { "epoch": 3.2591093117408905, "grad_norm": 0.30131610545815135, "learning_rate": 1.3050473514379488e-05, "loss": 0.2277, "step": 805 }, { "epoch": 3.263157894736842, "grad_norm": 0.3156571013886975, "learning_rate": 1.2997471016172188e-05, "loss": 0.237, "step": 806 }, { "epoch": 3.2672064777327936, "grad_norm": 0.3087614860521808, "learning_rate": 1.2944524510000042e-05, "loss": 0.2424, "step": 807 }, { "epoch": 3.2712550607287447, "grad_norm": 0.30513371826847746, "learning_rate": 1.2891634419221908e-05, "loss": 0.2306, "step": 808 }, { "epoch": 3.2753036437246963, "grad_norm": 0.3041895812804349, "learning_rate": 1.2838801166745545e-05, "loss": 0.2309, "step": 809 }, { "epoch": 3.279352226720648, "grad_norm": 0.3166523952878452, "learning_rate": 1.2786025175024216e-05, "loss": 0.2325, "step": 810 }, { "epoch": 3.283400809716599, "grad_norm": 0.320708276583538, "learning_rate": 1.2733306866053357e-05, "loss": 0.2192, "step": 811 }, { "epoch": 3.2874493927125505, "grad_norm": 0.3278528659592668, "learning_rate": 1.2680646661367163e-05, "loss": 0.2229, "step": 812 }, { "epoch": 3.291497975708502, "grad_norm": 0.3301813505327344, "learning_rate": 1.2628044982035219e-05, "loss": 0.2399, "step": 813 }, { "epoch": 3.2955465587044532, "grad_norm": 0.3321745243715521, "learning_rate": 1.2575502248659155e-05, "loss": 0.2312, "step": 814 }, { "epoch": 3.299595141700405, "grad_norm": 0.31675884327584464, "learning_rate": 1.2523018881369269e-05, "loss": 0.2354, "step": 815 }, { "epoch": 3.3036437246963564, "grad_norm": 0.3534672492754462, "learning_rate": 1.2470595299821176e-05, "loss": 0.2355, "step": 816 }, { "epoch": 3.3076923076923075, "grad_norm": 0.30812399703851623, "learning_rate": 1.2418231923192416e-05, "loss": 0.2326, "step": 817 }, { "epoch": 3.311740890688259, "grad_norm": 0.32523714355679373, "learning_rate": 1.2365929170179165e-05, "loss": 0.2155, "step": 818 }, { "epoch": 3.3157894736842106, "grad_norm": 0.31471064872487614, "learning_rate": 1.2313687458992848e-05, "loss": 0.2382, "step": 819 }, { "epoch": 3.3198380566801617, "grad_norm": 0.3099916121983711, "learning_rate": 1.2261507207356785e-05, "loss": 0.2396, "step": 820 }, { "epoch": 3.3238866396761133, "grad_norm": 0.3149012657687765, "learning_rate": 1.220938883250288e-05, "loss": 0.2208, "step": 821 }, { "epoch": 3.327935222672065, "grad_norm": 0.31349167739489703, "learning_rate": 1.215733275116827e-05, "loss": 0.2191, "step": 822 }, { "epoch": 3.331983805668016, "grad_norm": 0.3126845141325557, "learning_rate": 1.2105339379592005e-05, "loss": 0.2279, "step": 823 }, { "epoch": 3.3360323886639676, "grad_norm": 0.30726139276213227, "learning_rate": 1.2053409133511681e-05, "loss": 0.2324, "step": 824 }, { "epoch": 3.340080971659919, "grad_norm": 0.3168303582782642, "learning_rate": 1.2001542428160173e-05, "loss": 0.2338, "step": 825 }, { "epoch": 3.3441295546558703, "grad_norm": 0.3151999669175157, "learning_rate": 1.1949739678262278e-05, "loss": 0.2364, "step": 826 }, { "epoch": 3.348178137651822, "grad_norm": 0.31490659097437934, "learning_rate": 1.189800129803139e-05, "loss": 0.2312, "step": 827 }, { "epoch": 3.3522267206477734, "grad_norm": 0.3143441897133468, "learning_rate": 1.1846327701166228e-05, "loss": 0.2314, "step": 828 }, { "epoch": 3.3562753036437245, "grad_norm": 0.33578726071279574, "learning_rate": 1.1794719300847493e-05, "loss": 0.2365, "step": 829 }, { "epoch": 3.360323886639676, "grad_norm": 0.33274640033286185, "learning_rate": 1.1743176509734582e-05, "loss": 0.2268, "step": 830 }, { "epoch": 3.3643724696356276, "grad_norm": 0.31092245832614096, "learning_rate": 1.1691699739962275e-05, "loss": 0.2499, "step": 831 }, { "epoch": 3.3684210526315788, "grad_norm": 0.3154946814554466, "learning_rate": 1.1640289403137456e-05, "loss": 0.2502, "step": 832 }, { "epoch": 3.3724696356275303, "grad_norm": 0.30963727944912867, "learning_rate": 1.1588945910335802e-05, "loss": 0.2119, "step": 833 }, { "epoch": 3.376518218623482, "grad_norm": 0.305514107427809, "learning_rate": 1.1537669672098517e-05, "loss": 0.2535, "step": 834 }, { "epoch": 3.380566801619433, "grad_norm": 0.3284677944702449, "learning_rate": 1.1486461098429036e-05, "loss": 0.2317, "step": 835 }, { "epoch": 3.3846153846153846, "grad_norm": 0.32256647707270686, "learning_rate": 1.1435320598789747e-05, "loss": 0.2352, "step": 836 }, { "epoch": 3.388663967611336, "grad_norm": 0.31831985055124395, "learning_rate": 1.1384248582098736e-05, "loss": 0.223, "step": 837 }, { "epoch": 3.3927125506072873, "grad_norm": 0.319658033614498, "learning_rate": 1.1333245456726467e-05, "loss": 0.2241, "step": 838 }, { "epoch": 3.396761133603239, "grad_norm": 0.3205114706974294, "learning_rate": 1.128231163049258e-05, "loss": 0.2302, "step": 839 }, { "epoch": 3.4008097165991904, "grad_norm": 0.3127769427627336, "learning_rate": 1.123144751066259e-05, "loss": 0.2165, "step": 840 }, { "epoch": 3.4048582995951415, "grad_norm": 0.3361839389709753, "learning_rate": 1.1180653503944657e-05, "loss": 0.2157, "step": 841 }, { "epoch": 3.408906882591093, "grad_norm": 0.30692196943110994, "learning_rate": 1.1129930016486287e-05, "loss": 0.2339, "step": 842 }, { "epoch": 3.4129554655870447, "grad_norm": 0.3140734232872295, "learning_rate": 1.107927745387114e-05, "loss": 0.236, "step": 843 }, { "epoch": 3.417004048582996, "grad_norm": 0.328582246340632, "learning_rate": 1.1028696221115766e-05, "loss": 0.2152, "step": 844 }, { "epoch": 3.4210526315789473, "grad_norm": 0.3167252804109089, "learning_rate": 1.0978186722666341e-05, "loss": 0.2276, "step": 845 }, { "epoch": 3.425101214574899, "grad_norm": 0.3284688091418458, "learning_rate": 1.0927749362395475e-05, "loss": 0.2325, "step": 846 }, { "epoch": 3.42914979757085, "grad_norm": 0.3062217906282762, "learning_rate": 1.0877384543598954e-05, "loss": 0.2353, "step": 847 }, { "epoch": 3.4331983805668016, "grad_norm": 0.30967178837849196, "learning_rate": 1.0827092668992529e-05, "loss": 0.2262, "step": 848 }, { "epoch": 3.437246963562753, "grad_norm": 0.30125939589539164, "learning_rate": 1.077687414070869e-05, "loss": 0.2442, "step": 849 }, { "epoch": 3.4412955465587043, "grad_norm": 0.3022181967317688, "learning_rate": 1.0726729360293451e-05, "loss": 0.2372, "step": 850 }, { "epoch": 3.445344129554656, "grad_norm": 0.3214263632092804, "learning_rate": 1.0676658728703147e-05, "loss": 0.2301, "step": 851 }, { "epoch": 3.4493927125506074, "grad_norm": 0.3266407538558891, "learning_rate": 1.0626662646301198e-05, "loss": 0.2104, "step": 852 }, { "epoch": 3.4534412955465585, "grad_norm": 0.31496541345637985, "learning_rate": 1.0576741512854958e-05, "loss": 0.2124, "step": 853 }, { "epoch": 3.45748987854251, "grad_norm": 0.3042375189687864, "learning_rate": 1.052689572753247e-05, "loss": 0.234, "step": 854 }, { "epoch": 3.4615384615384617, "grad_norm": 0.32060988141159724, "learning_rate": 1.0477125688899328e-05, "loss": 0.2316, "step": 855 }, { "epoch": 3.465587044534413, "grad_norm": 0.30338645806129616, "learning_rate": 1.0427431794915406e-05, "loss": 0.2188, "step": 856 }, { "epoch": 3.4696356275303644, "grad_norm": 0.31829743676374356, "learning_rate": 1.0377814442931769e-05, "loss": 0.2484, "step": 857 }, { "epoch": 3.473684210526316, "grad_norm": 0.3108814340710607, "learning_rate": 1.0328274029687439e-05, "loss": 0.2216, "step": 858 }, { "epoch": 3.477732793522267, "grad_norm": 0.3110920631463749, "learning_rate": 1.0278810951306253e-05, "loss": 0.2403, "step": 859 }, { "epoch": 3.4817813765182186, "grad_norm": 0.3091612014731493, "learning_rate": 1.0229425603293647e-05, "loss": 0.2177, "step": 860 }, { "epoch": 3.48582995951417, "grad_norm": 0.33655400641585603, "learning_rate": 1.0180118380533558e-05, "loss": 0.2294, "step": 861 }, { "epoch": 3.4898785425101213, "grad_norm": 0.3337059330671961, "learning_rate": 1.0130889677285225e-05, "loss": 0.2447, "step": 862 }, { "epoch": 3.493927125506073, "grad_norm": 0.3176599394683939, "learning_rate": 1.008173988718005e-05, "loss": 0.2136, "step": 863 }, { "epoch": 3.4979757085020244, "grad_norm": 0.31559792868383907, "learning_rate": 1.0032669403218439e-05, "loss": 0.2306, "step": 864 }, { "epoch": 3.5020242914979756, "grad_norm": 0.3300223374874324, "learning_rate": 9.983678617766677e-06, "loss": 0.2138, "step": 865 }, { "epoch": 3.506072874493927, "grad_norm": 0.30771137542985405, "learning_rate": 9.934767922553788e-06, "loss": 0.212, "step": 866 }, { "epoch": 3.5101214574898787, "grad_norm": 0.3205557329620269, "learning_rate": 9.885937708668371e-06, "loss": 0.2282, "step": 867 }, { "epoch": 3.51417004048583, "grad_norm": 0.3184155868032561, "learning_rate": 9.837188366555524e-06, "loss": 0.2293, "step": 868 }, { "epoch": 3.5182186234817814, "grad_norm": 0.3453178573030517, "learning_rate": 9.788520286013691e-06, "loss": 0.234, "step": 869 }, { "epoch": 3.522267206477733, "grad_norm": 0.31124035140911627, "learning_rate": 9.739933856191537e-06, "loss": 0.2335, "step": 870 }, { "epoch": 3.526315789473684, "grad_norm": 0.32847392895680344, "learning_rate": 9.691429465584866e-06, "loss": 0.2127, "step": 871 }, { "epoch": 3.5303643724696356, "grad_norm": 0.30949731697913313, "learning_rate": 9.643007502033492e-06, "loss": 0.2163, "step": 872 }, { "epoch": 3.534412955465587, "grad_norm": 0.31003577559481715, "learning_rate": 9.594668352718152e-06, "loss": 0.2283, "step": 873 }, { "epoch": 3.5384615384615383, "grad_norm": 0.31863248602372274, "learning_rate": 9.546412404157383e-06, "loss": 0.2299, "step": 874 }, { "epoch": 3.54251012145749, "grad_norm": 0.32012452799642077, "learning_rate": 9.498240042204471e-06, "loss": 0.2232, "step": 875 }, { "epoch": 3.5465587044534415, "grad_norm": 0.30427387519476323, "learning_rate": 9.450151652044339e-06, "loss": 0.2371, "step": 876 }, { "epoch": 3.5506072874493926, "grad_norm": 0.3143327224380876, "learning_rate": 9.402147618190472e-06, "loss": 0.2277, "step": 877 }, { "epoch": 3.554655870445344, "grad_norm": 0.31336557532690296, "learning_rate": 9.354228324481841e-06, "loss": 0.2347, "step": 878 }, { "epoch": 3.5587044534412957, "grad_norm": 0.297608052401848, "learning_rate": 9.306394154079852e-06, "loss": 0.2413, "step": 879 }, { "epoch": 3.562753036437247, "grad_norm": 0.30028521188678214, "learning_rate": 9.258645489465254e-06, "loss": 0.2227, "step": 880 }, { "epoch": 3.5668016194331984, "grad_norm": 0.31151411703599535, "learning_rate": 9.21098271243509e-06, "loss": 0.2207, "step": 881 }, { "epoch": 3.57085020242915, "grad_norm": 0.326221968635777, "learning_rate": 9.163406204099659e-06, "loss": 0.2208, "step": 882 }, { "epoch": 3.574898785425101, "grad_norm": 0.30190794919629516, "learning_rate": 9.115916344879452e-06, "loss": 0.2348, "step": 883 }, { "epoch": 3.5789473684210527, "grad_norm": 0.30503977449098185, "learning_rate": 9.068513514502126e-06, "loss": 0.2214, "step": 884 }, { "epoch": 3.582995951417004, "grad_norm": 0.2987751317765071, "learning_rate": 9.021198091999439e-06, "loss": 0.2454, "step": 885 }, { "epoch": 3.5870445344129553, "grad_norm": 0.3039012038689804, "learning_rate": 8.973970455704251e-06, "loss": 0.2357, "step": 886 }, { "epoch": 3.591093117408907, "grad_norm": 0.3182004134494251, "learning_rate": 8.926830983247495e-06, "loss": 0.2183, "step": 887 }, { "epoch": 3.5951417004048585, "grad_norm": 0.2901620986567785, "learning_rate": 8.879780051555116e-06, "loss": 0.2354, "step": 888 }, { "epoch": 3.5991902834008096, "grad_norm": 0.3150321669262113, "learning_rate": 8.83281803684512e-06, "loss": 0.2198, "step": 889 }, { "epoch": 3.603238866396761, "grad_norm": 0.3131200540877491, "learning_rate": 8.785945314624532e-06, "loss": 0.2333, "step": 890 }, { "epoch": 3.6072874493927127, "grad_norm": 0.3148632416615739, "learning_rate": 8.739162259686385e-06, "loss": 0.2261, "step": 891 }, { "epoch": 3.611336032388664, "grad_norm": 0.3100202116965604, "learning_rate": 8.692469246106734e-06, "loss": 0.2401, "step": 892 }, { "epoch": 3.6153846153846154, "grad_norm": 0.32973493038281587, "learning_rate": 8.645866647241677e-06, "loss": 0.2359, "step": 893 }, { "epoch": 3.619433198380567, "grad_norm": 0.30352172829483615, "learning_rate": 8.599354835724348e-06, "loss": 0.2165, "step": 894 }, { "epoch": 3.623481781376518, "grad_norm": 0.31619406925327587, "learning_rate": 8.552934183461958e-06, "loss": 0.2318, "step": 895 }, { "epoch": 3.6275303643724697, "grad_norm": 0.32058875913964774, "learning_rate": 8.506605061632805e-06, "loss": 0.2436, "step": 896 }, { "epoch": 3.6315789473684212, "grad_norm": 0.30427371759764527, "learning_rate": 8.460367840683308e-06, "loss": 0.2087, "step": 897 }, { "epoch": 3.6356275303643724, "grad_norm": 0.30325789729337227, "learning_rate": 8.414222890325065e-06, "loss": 0.2474, "step": 898 }, { "epoch": 3.639676113360324, "grad_norm": 0.3143848534759895, "learning_rate": 8.368170579531855e-06, "loss": 0.2357, "step": 899 }, { "epoch": 3.6437246963562755, "grad_norm": 0.3185821088297442, "learning_rate": 8.322211276536733e-06, "loss": 0.2335, "step": 900 }, { "epoch": 3.6477732793522266, "grad_norm": 0.3049895878743502, "learning_rate": 8.27634534882907e-06, "loss": 0.2384, "step": 901 }, { "epoch": 3.651821862348178, "grad_norm": 0.30805944532817936, "learning_rate": 8.230573163151585e-06, "loss": 0.2291, "step": 902 }, { "epoch": 3.6558704453441297, "grad_norm": 0.30614569457479096, "learning_rate": 8.184895085497466e-06, "loss": 0.2195, "step": 903 }, { "epoch": 3.659919028340081, "grad_norm": 0.3144748999100987, "learning_rate": 8.139311481107401e-06, "loss": 0.228, "step": 904 }, { "epoch": 3.6639676113360324, "grad_norm": 0.3167666349184677, "learning_rate": 8.093822714466686e-06, "loss": 0.2312, "step": 905 }, { "epoch": 3.668016194331984, "grad_norm": 0.2979666317978873, "learning_rate": 8.048429149302271e-06, "loss": 0.2101, "step": 906 }, { "epoch": 3.672064777327935, "grad_norm": 0.2993639591337566, "learning_rate": 8.003131148579902e-06, "loss": 0.2293, "step": 907 }, { "epoch": 3.6761133603238867, "grad_norm": 0.2972121153416639, "learning_rate": 7.957929074501182e-06, "loss": 0.234, "step": 908 }, { "epoch": 3.6801619433198383, "grad_norm": 0.30081954020431956, "learning_rate": 7.912823288500695e-06, "loss": 0.2386, "step": 909 }, { "epoch": 3.6842105263157894, "grad_norm": 0.3062346692449234, "learning_rate": 7.867814151243102e-06, "loss": 0.2122, "step": 910 }, { "epoch": 3.688259109311741, "grad_norm": 0.30024423405564765, "learning_rate": 7.822902022620267e-06, "loss": 0.2169, "step": 911 }, { "epoch": 3.6923076923076925, "grad_norm": 0.29849674994007674, "learning_rate": 7.778087261748377e-06, "loss": 0.2177, "step": 912 }, { "epoch": 3.6963562753036436, "grad_norm": 0.31202434675365925, "learning_rate": 7.733370226965056e-06, "loss": 0.2421, "step": 913 }, { "epoch": 3.700404858299595, "grad_norm": 0.31455274238003444, "learning_rate": 7.688751275826527e-06, "loss": 0.2106, "step": 914 }, { "epoch": 3.7044534412955468, "grad_norm": 0.2988474191594574, "learning_rate": 7.644230765104735e-06, "loss": 0.2381, "step": 915 }, { "epoch": 3.708502024291498, "grad_norm": 0.30510900613508746, "learning_rate": 7.599809050784502e-06, "loss": 0.2187, "step": 916 }, { "epoch": 3.7125506072874495, "grad_norm": 0.29816876900944483, "learning_rate": 7.555486488060661e-06, "loss": 0.2245, "step": 917 }, { "epoch": 3.716599190283401, "grad_norm": 0.2954600677250161, "learning_rate": 7.511263431335249e-06, "loss": 0.23, "step": 918 }, { "epoch": 3.720647773279352, "grad_norm": 0.31564572840382976, "learning_rate": 7.467140234214656e-06, "loss": 0.2255, "step": 919 }, { "epoch": 3.7246963562753037, "grad_norm": 0.30495392907778873, "learning_rate": 7.423117249506777e-06, "loss": 0.2242, "step": 920 }, { "epoch": 3.7287449392712553, "grad_norm": 0.30588426814779207, "learning_rate": 7.379194829218231e-06, "loss": 0.2094, "step": 921 }, { "epoch": 3.7327935222672064, "grad_norm": 0.309242072212407, "learning_rate": 7.335373324551518e-06, "loss": 0.2217, "step": 922 }, { "epoch": 3.736842105263158, "grad_norm": 0.3174837540024323, "learning_rate": 7.291653085902224e-06, "loss": 0.2075, "step": 923 }, { "epoch": 3.7408906882591095, "grad_norm": 0.2964617518738107, "learning_rate": 7.248034462856213e-06, "loss": 0.2298, "step": 924 }, { "epoch": 3.7449392712550607, "grad_norm": 0.31417045560010437, "learning_rate": 7.20451780418683e-06, "loss": 0.2224, "step": 925 }, { "epoch": 3.748987854251012, "grad_norm": 0.29607020656069755, "learning_rate": 7.161103457852128e-06, "loss": 0.2479, "step": 926 }, { "epoch": 3.753036437246964, "grad_norm": 0.30794773831132477, "learning_rate": 7.117791770992046e-06, "loss": 0.2124, "step": 927 }, { "epoch": 3.757085020242915, "grad_norm": 0.3021537650097355, "learning_rate": 7.074583089925688e-06, "loss": 0.2223, "step": 928 }, { "epoch": 3.7611336032388665, "grad_norm": 0.3064974355002209, "learning_rate": 7.0314777601485155e-06, "loss": 0.214, "step": 929 }, { "epoch": 3.765182186234818, "grad_norm": 0.2898257029673636, "learning_rate": 6.988476126329604e-06, "loss": 0.234, "step": 930 }, { "epoch": 3.769230769230769, "grad_norm": 0.30471141613908825, "learning_rate": 6.945578532308857e-06, "loss": 0.2234, "step": 931 }, { "epoch": 3.7732793522267207, "grad_norm": 0.29459351248132104, "learning_rate": 6.902785321094301e-06, "loss": 0.2352, "step": 932 }, { "epoch": 3.7773279352226723, "grad_norm": 0.30299773439443295, "learning_rate": 6.8600968348593115e-06, "loss": 0.2311, "step": 933 }, { "epoch": 3.7813765182186234, "grad_norm": 0.30159867360962356, "learning_rate": 6.817513414939892e-06, "loss": 0.2162, "step": 934 }, { "epoch": 3.785425101214575, "grad_norm": 0.31746643358477783, "learning_rate": 6.775035401831924e-06, "loss": 0.2217, "step": 935 }, { "epoch": 3.7894736842105265, "grad_norm": 0.3113069805410265, "learning_rate": 6.732663135188473e-06, "loss": 0.2227, "step": 936 }, { "epoch": 3.7935222672064777, "grad_norm": 0.31564610259631876, "learning_rate": 6.690396953817055e-06, "loss": 0.2533, "step": 937 }, { "epoch": 3.7975708502024292, "grad_norm": 0.30965474835063966, "learning_rate": 6.648237195676927e-06, "loss": 0.2283, "step": 938 }, { "epoch": 3.801619433198381, "grad_norm": 0.29800550077434285, "learning_rate": 6.606184197876395e-06, "loss": 0.2326, "step": 939 }, { "epoch": 3.805668016194332, "grad_norm": 0.29947882225673, "learning_rate": 6.564238296670109e-06, "loss": 0.2215, "step": 940 }, { "epoch": 3.8097165991902835, "grad_norm": 0.30099068041529264, "learning_rate": 6.52239982745638e-06, "loss": 0.2415, "step": 941 }, { "epoch": 3.813765182186235, "grad_norm": 0.3057312620273116, "learning_rate": 6.480669124774484e-06, "loss": 0.2313, "step": 942 }, { "epoch": 3.817813765182186, "grad_norm": 0.30044100854807965, "learning_rate": 6.439046522302013e-06, "loss": 0.2302, "step": 943 }, { "epoch": 3.8218623481781377, "grad_norm": 0.2976151377046079, "learning_rate": 6.397532352852191e-06, "loss": 0.2348, "step": 944 }, { "epoch": 3.8259109311740893, "grad_norm": 0.2957217144283612, "learning_rate": 6.356126948371202e-06, "loss": 0.2307, "step": 945 }, { "epoch": 3.8299595141700404, "grad_norm": 0.29613818540237913, "learning_rate": 6.314830639935559e-06, "loss": 0.2358, "step": 946 }, { "epoch": 3.834008097165992, "grad_norm": 0.2924051197033915, "learning_rate": 6.273643757749448e-06, "loss": 0.2264, "step": 947 }, { "epoch": 3.8380566801619436, "grad_norm": 0.3052658399470645, "learning_rate": 6.2325666311420856e-06, "loss": 0.2125, "step": 948 }, { "epoch": 3.8421052631578947, "grad_norm": 0.30386030199091607, "learning_rate": 6.1915995885650675e-06, "loss": 0.2045, "step": 949 }, { "epoch": 3.8461538461538463, "grad_norm": 0.295204776712793, "learning_rate": 6.150742957589784e-06, "loss": 0.2295, "step": 950 }, { "epoch": 3.850202429149798, "grad_norm": 0.30146824379869686, "learning_rate": 6.109997064904774e-06, "loss": 0.2035, "step": 951 }, { "epoch": 3.854251012145749, "grad_norm": 0.30552894649570056, "learning_rate": 6.069362236313092e-06, "loss": 0.2233, "step": 952 }, { "epoch": 3.8582995951417005, "grad_norm": 0.3122408380618247, "learning_rate": 6.0288387967297565e-06, "loss": 0.2354, "step": 953 }, { "epoch": 3.862348178137652, "grad_norm": 0.29768367136159785, "learning_rate": 5.988427070179108e-06, "loss": 0.2269, "step": 954 }, { "epoch": 3.866396761133603, "grad_norm": 0.29518346493988035, "learning_rate": 5.948127379792234e-06, "loss": 0.2282, "step": 955 }, { "epoch": 3.8704453441295548, "grad_norm": 0.30181451972894363, "learning_rate": 5.90794004780439e-06, "loss": 0.2112, "step": 956 }, { "epoch": 3.8744939271255063, "grad_norm": 0.2924368532498023, "learning_rate": 5.867865395552405e-06, "loss": 0.2382, "step": 957 }, { "epoch": 3.8785425101214575, "grad_norm": 0.30123937308312715, "learning_rate": 5.8279037434721364e-06, "loss": 0.2348, "step": 958 }, { "epoch": 3.882591093117409, "grad_norm": 0.30673753313547464, "learning_rate": 5.788055411095892e-06, "loss": 0.2194, "step": 959 }, { "epoch": 3.8866396761133606, "grad_norm": 0.2898279181663926, "learning_rate": 5.7483207170498625e-06, "loss": 0.2139, "step": 960 }, { "epoch": 3.8906882591093117, "grad_norm": 0.29584092190221706, "learning_rate": 5.708699979051613e-06, "loss": 0.2464, "step": 961 }, { "epoch": 3.8947368421052633, "grad_norm": 0.2981795882500886, "learning_rate": 5.66919351390751e-06, "loss": 0.21, "step": 962 }, { "epoch": 3.898785425101215, "grad_norm": 0.2909174334540446, "learning_rate": 5.629801637510188e-06, "loss": 0.233, "step": 963 }, { "epoch": 3.902834008097166, "grad_norm": 0.29925317698882115, "learning_rate": 5.590524664836043e-06, "loss": 0.2381, "step": 964 }, { "epoch": 3.9068825910931175, "grad_norm": 0.3066563721066459, "learning_rate": 5.551362909942708e-06, "loss": 0.2211, "step": 965 }, { "epoch": 3.910931174089069, "grad_norm": 0.2910757672231705, "learning_rate": 5.51231668596653e-06, "loss": 0.2164, "step": 966 }, { "epoch": 3.91497975708502, "grad_norm": 0.2956656817178651, "learning_rate": 5.47338630512007e-06, "loss": 0.2137, "step": 967 }, { "epoch": 3.919028340080972, "grad_norm": 0.2987530089457755, "learning_rate": 5.434572078689617e-06, "loss": 0.24, "step": 968 }, { "epoch": 3.9230769230769234, "grad_norm": 0.30465506118018487, "learning_rate": 5.395874317032694e-06, "loss": 0.2447, "step": 969 }, { "epoch": 3.9271255060728745, "grad_norm": 0.2916057388673398, "learning_rate": 5.357293329575573e-06, "loss": 0.224, "step": 970 }, { "epoch": 3.931174089068826, "grad_norm": 0.2959367899230164, "learning_rate": 5.318829424810797e-06, "loss": 0.2251, "step": 971 }, { "epoch": 3.9352226720647776, "grad_norm": 0.3054623492962634, "learning_rate": 5.280482910294728e-06, "loss": 0.2139, "step": 972 }, { "epoch": 3.9392712550607287, "grad_norm": 0.3004076800157919, "learning_rate": 5.242254092645078e-06, "loss": 0.2229, "step": 973 }, { "epoch": 3.9433198380566803, "grad_norm": 0.31235785655542725, "learning_rate": 5.2041432775384445e-06, "loss": 0.2224, "step": 974 }, { "epoch": 3.9473684210526314, "grad_norm": 0.30119929346872226, "learning_rate": 5.166150769707892e-06, "loss": 0.2252, "step": 975 }, { "epoch": 3.951417004048583, "grad_norm": 0.29683855125605685, "learning_rate": 5.128276872940503e-06, "loss": 0.2033, "step": 976 }, { "epoch": 3.9554655870445345, "grad_norm": 0.3136437120836609, "learning_rate": 5.090521890074953e-06, "loss": 0.2146, "step": 977 }, { "epoch": 3.9595141700404857, "grad_norm": 0.3039786065839984, "learning_rate": 5.0528861229990675e-06, "loss": 0.2225, "step": 978 }, { "epoch": 3.9635627530364372, "grad_norm": 0.31636754340580225, "learning_rate": 5.015369872647442e-06, "loss": 0.2217, "step": 979 }, { "epoch": 3.967611336032389, "grad_norm": 0.3039214782358905, "learning_rate": 4.9779734389990195e-06, "loss": 0.2114, "step": 980 }, { "epoch": 3.97165991902834, "grad_norm": 0.31160643845270497, "learning_rate": 4.940697121074675e-06, "loss": 0.2053, "step": 981 }, { "epoch": 3.9757085020242915, "grad_norm": 0.2933863424631389, "learning_rate": 4.903541216934864e-06, "loss": 0.2352, "step": 982 }, { "epoch": 3.979757085020243, "grad_norm": 0.29672777978453585, "learning_rate": 4.8665060236772e-06, "loss": 0.2398, "step": 983 }, { "epoch": 3.983805668016194, "grad_norm": 0.2953094973312532, "learning_rate": 4.829591837434102e-06, "loss": 0.2251, "step": 984 }, { "epoch": 3.9878542510121457, "grad_norm": 0.3016806783227866, "learning_rate": 4.792798953370424e-06, "loss": 0.22, "step": 985 }, { "epoch": 3.9919028340080973, "grad_norm": 0.29585917993829736, "learning_rate": 4.756127665681083e-06, "loss": 0.2196, "step": 986 }, { "epoch": 3.9959514170040484, "grad_norm": 0.2961618905930332, "learning_rate": 4.719578267588725e-06, "loss": 0.221, "step": 987 }, { "epoch": 4.0, "grad_norm": 0.2934555964872919, "learning_rate": 4.6831510513413525e-06, "loss": 0.2309, "step": 988 }, { "epoch": 4.004048582995951, "grad_norm": 0.4113651353708687, "learning_rate": 4.6468463082100176e-06, "loss": 0.1785, "step": 989 }, { "epoch": 4.008097165991903, "grad_norm": 0.38106221175734073, "learning_rate": 4.610664328486485e-06, "loss": 0.1776, "step": 990 }, { "epoch": 4.012145748987854, "grad_norm": 0.29913251183956036, "learning_rate": 4.5746054014809e-06, "loss": 0.1684, "step": 991 }, { "epoch": 4.016194331983805, "grad_norm": 0.2637137359454082, "learning_rate": 4.5386698155194766e-06, "loss": 0.1692, "step": 992 }, { "epoch": 4.020242914979757, "grad_norm": 0.3574130919431414, "learning_rate": 4.502857857942204e-06, "loss": 0.1632, "step": 993 }, { "epoch": 4.0242914979757085, "grad_norm": 0.41392427826155814, "learning_rate": 4.467169815100549e-06, "loss": 0.1642, "step": 994 }, { "epoch": 4.02834008097166, "grad_norm": 0.4629002691593695, "learning_rate": 4.431605972355137e-06, "loss": 0.184, "step": 995 }, { "epoch": 4.032388663967612, "grad_norm": 0.34275158045703547, "learning_rate": 4.396166614073516e-06, "loss": 0.1606, "step": 996 }, { "epoch": 4.036437246963563, "grad_norm": 0.29009187589404084, "learning_rate": 4.360852023627846e-06, "loss": 0.1711, "step": 997 }, { "epoch": 4.040485829959514, "grad_norm": 0.34350001160983895, "learning_rate": 4.325662483392656e-06, "loss": 0.1995, "step": 998 }, { "epoch": 4.044534412955466, "grad_norm": 0.32056108741546324, "learning_rate": 4.29059827474257e-06, "loss": 0.1466, "step": 999 }, { "epoch": 4.048582995951417, "grad_norm": 0.30973881520144425, "learning_rate": 4.255659678050063e-06, "loss": 0.1555, "step": 1000 }, { "epoch": 4.052631578947368, "grad_norm": 0.29822751061281033, "learning_rate": 4.22084697268323e-06, "loss": 0.1668, "step": 1001 }, { "epoch": 4.05668016194332, "grad_norm": 0.2778031351174379, "learning_rate": 4.186160437003535e-06, "loss": 0.191, "step": 1002 }, { "epoch": 4.060728744939271, "grad_norm": 0.29028424679296727, "learning_rate": 4.151600348363582e-06, "loss": 0.1545, "step": 1003 }, { "epoch": 4.064777327935222, "grad_norm": 0.31861765722019736, "learning_rate": 4.11716698310493e-06, "loss": 0.1559, "step": 1004 }, { "epoch": 4.068825910931174, "grad_norm": 0.3073345181596962, "learning_rate": 4.082860616555848e-06, "loss": 0.1731, "step": 1005 }, { "epoch": 4.0728744939271255, "grad_norm": 0.31285289620848056, "learning_rate": 4.048681523029125e-06, "loss": 0.169, "step": 1006 }, { "epoch": 4.076923076923077, "grad_norm": 0.28848863243643547, "learning_rate": 4.014629975819882e-06, "loss": 0.17, "step": 1007 }, { "epoch": 4.080971659919029, "grad_norm": 0.2862015667572566, "learning_rate": 3.9807062472033855e-06, "loss": 0.1591, "step": 1008 }, { "epoch": 4.08502024291498, "grad_norm": 0.29226173542352746, "learning_rate": 3.94691060843287e-06, "loss": 0.1639, "step": 1009 }, { "epoch": 4.089068825910931, "grad_norm": 0.295477725837025, "learning_rate": 3.913243329737353e-06, "loss": 0.1629, "step": 1010 }, { "epoch": 4.093117408906883, "grad_norm": 0.28885683916391974, "learning_rate": 3.879704680319503e-06, "loss": 0.1739, "step": 1011 }, { "epoch": 4.097165991902834, "grad_norm": 0.2696969652299651, "learning_rate": 3.846294928353471e-06, "loss": 0.1731, "step": 1012 }, { "epoch": 4.101214574898785, "grad_norm": 0.28121193094734037, "learning_rate": 3.8130143409827345e-06, "loss": 0.1482, "step": 1013 }, { "epoch": 4.105263157894737, "grad_norm": 0.2694672890227457, "learning_rate": 3.7798631843179887e-06, "loss": 0.178, "step": 1014 }, { "epoch": 4.109311740890688, "grad_norm": 0.28445537387644454, "learning_rate": 3.7468417234349973e-06, "loss": 0.1685, "step": 1015 }, { "epoch": 4.113360323886639, "grad_norm": 0.261381554032796, "learning_rate": 3.7139502223724823e-06, "loss": 0.1718, "step": 1016 }, { "epoch": 4.117408906882591, "grad_norm": 0.2644420878306194, "learning_rate": 3.6811889441300095e-06, "loss": 0.2017, "step": 1017 }, { "epoch": 4.1214574898785425, "grad_norm": 0.24819318076481806, "learning_rate": 3.648558150665886e-06, "loss": 0.1716, "step": 1018 }, { "epoch": 4.125506072874494, "grad_norm": 0.2608860652391622, "learning_rate": 3.616058102895075e-06, "loss": 0.1614, "step": 1019 }, { "epoch": 4.129554655870446, "grad_norm": 0.25212267485879325, "learning_rate": 3.583689060687079e-06, "loss": 0.1687, "step": 1020 }, { "epoch": 4.133603238866397, "grad_norm": 0.2691819247032846, "learning_rate": 3.5514512828639023e-06, "loss": 0.188, "step": 1021 }, { "epoch": 4.137651821862348, "grad_norm": 0.26076911037966055, "learning_rate": 3.51934502719796e-06, "loss": 0.1633, "step": 1022 }, { "epoch": 4.1417004048583, "grad_norm": 0.2698152478946938, "learning_rate": 3.4873705504100185e-06, "loss": 0.1777, "step": 1023 }, { "epoch": 4.145748987854251, "grad_norm": 0.26525049166484854, "learning_rate": 3.4555281081671345e-06, "loss": 0.1876, "step": 1024 }, { "epoch": 4.149797570850202, "grad_norm": 0.25160804284941585, "learning_rate": 3.4238179550806326e-06, "loss": 0.1611, "step": 1025 }, { "epoch": 4.153846153846154, "grad_norm": 0.2558881951571739, "learning_rate": 3.3922403447040497e-06, "loss": 0.1811, "step": 1026 }, { "epoch": 4.157894736842105, "grad_norm": 0.2467050586224601, "learning_rate": 3.3607955295311247e-06, "loss": 0.1758, "step": 1027 }, { "epoch": 4.161943319838056, "grad_norm": 0.2530893685581475, "learning_rate": 3.32948376099375e-06, "loss": 0.157, "step": 1028 }, { "epoch": 4.165991902834008, "grad_norm": 0.2602806698100944, "learning_rate": 3.2983052894599976e-06, "loss": 0.1547, "step": 1029 }, { "epoch": 4.17004048582996, "grad_norm": 0.25520283924646225, "learning_rate": 3.2672603642320945e-06, "loss": 0.1725, "step": 1030 }, { "epoch": 4.174089068825911, "grad_norm": 0.2692380566886611, "learning_rate": 3.236349233544438e-06, "loss": 0.16, "step": 1031 }, { "epoch": 4.178137651821863, "grad_norm": 0.2504426899258434, "learning_rate": 3.205572144561604e-06, "loss": 0.1784, "step": 1032 }, { "epoch": 4.182186234817814, "grad_norm": 0.2531603009844425, "learning_rate": 3.174929343376374e-06, "loss": 0.1776, "step": 1033 }, { "epoch": 4.186234817813765, "grad_norm": 0.2526981204216861, "learning_rate": 3.1444210750077777e-06, "loss": 0.1662, "step": 1034 }, { "epoch": 4.190283400809717, "grad_norm": 0.25068408936436515, "learning_rate": 3.1140475833991046e-06, "loss": 0.1501, "step": 1035 }, { "epoch": 4.194331983805668, "grad_norm": 0.2685026145409084, "learning_rate": 3.0838091114159895e-06, "loss": 0.1663, "step": 1036 }, { "epoch": 4.198380566801619, "grad_norm": 0.2479669893672087, "learning_rate": 3.0537059008444524e-06, "loss": 0.1914, "step": 1037 }, { "epoch": 4.202429149797571, "grad_norm": 0.2508749058408086, "learning_rate": 3.0237381923889563e-06, "loss": 0.1662, "step": 1038 }, { "epoch": 4.206477732793522, "grad_norm": 0.2554335871658155, "learning_rate": 2.9939062256704997e-06, "loss": 0.1611, "step": 1039 }, { "epoch": 4.2105263157894735, "grad_norm": 0.25658113993953807, "learning_rate": 2.964210239224696e-06, "loss": 0.1576, "step": 1040 }, { "epoch": 4.2145748987854255, "grad_norm": 0.25497865390519114, "learning_rate": 2.934650470499869e-06, "loss": 0.1671, "step": 1041 }, { "epoch": 4.218623481781377, "grad_norm": 0.2543380352791214, "learning_rate": 2.905227155855128e-06, "loss": 0.1715, "step": 1042 }, { "epoch": 4.222672064777328, "grad_norm": 0.2541003190317777, "learning_rate": 2.875940530558519e-06, "loss": 0.1748, "step": 1043 }, { "epoch": 4.22672064777328, "grad_norm": 0.26162118748350827, "learning_rate": 2.8467908287851154e-06, "loss": 0.1702, "step": 1044 }, { "epoch": 4.230769230769231, "grad_norm": 0.25400939631752767, "learning_rate": 2.8177782836151603e-06, "loss": 0.1473, "step": 1045 }, { "epoch": 4.234817813765182, "grad_norm": 0.26133598216853393, "learning_rate": 2.7889031270321874e-06, "loss": 0.1679, "step": 1046 }, { "epoch": 4.238866396761134, "grad_norm": 0.2516260746124712, "learning_rate": 2.760165589921184e-06, "loss": 0.1771, "step": 1047 }, { "epoch": 4.242914979757085, "grad_norm": 0.25688421334815903, "learning_rate": 2.7315659020667305e-06, "loss": 0.1783, "step": 1048 }, { "epoch": 4.246963562753036, "grad_norm": 0.25433056686496053, "learning_rate": 2.703104292151164e-06, "loss": 0.1524, "step": 1049 }, { "epoch": 4.251012145748988, "grad_norm": 0.2608259412959581, "learning_rate": 2.6747809877527607e-06, "loss": 0.1598, "step": 1050 }, { "epoch": 4.255060728744939, "grad_norm": 0.263787748814867, "learning_rate": 2.6465962153439082e-06, "loss": 0.1648, "step": 1051 }, { "epoch": 4.2591093117408905, "grad_norm": 0.2567674923934054, "learning_rate": 2.618550200289303e-06, "loss": 0.1669, "step": 1052 }, { "epoch": 4.2631578947368425, "grad_norm": 0.25064997303479297, "learning_rate": 2.59064316684412e-06, "loss": 0.161, "step": 1053 }, { "epoch": 4.267206477732794, "grad_norm": 0.24947965677032402, "learning_rate": 2.562875338152264e-06, "loss": 0.1686, "step": 1054 }, { "epoch": 4.271255060728745, "grad_norm": 0.26401868217022323, "learning_rate": 2.5352469362445552e-06, "loss": 0.1646, "step": 1055 }, { "epoch": 4.275303643724697, "grad_norm": 0.2534551509997295, "learning_rate": 2.5077581820369523e-06, "loss": 0.1794, "step": 1056 }, { "epoch": 4.279352226720648, "grad_norm": 0.24853750603152852, "learning_rate": 2.480409295328803e-06, "loss": 0.2022, "step": 1057 }, { "epoch": 4.283400809716599, "grad_norm": 0.24950165752678408, "learning_rate": 2.45320049480108e-06, "loss": 0.1692, "step": 1058 }, { "epoch": 4.287449392712551, "grad_norm": 0.24532736218813841, "learning_rate": 2.4261319980146293e-06, "loss": 0.1652, "step": 1059 }, { "epoch": 4.291497975708502, "grad_norm": 0.25799242367149433, "learning_rate": 2.399204021408421e-06, "loss": 0.1668, "step": 1060 }, { "epoch": 4.295546558704453, "grad_norm": 0.24588734334731113, "learning_rate": 2.3724167802978395e-06, "loss": 0.1721, "step": 1061 }, { "epoch": 4.299595141700405, "grad_norm": 0.25413179115247087, "learning_rate": 2.3457704888729625e-06, "loss": 0.1953, "step": 1062 }, { "epoch": 4.303643724696356, "grad_norm": 0.25009887739805037, "learning_rate": 2.3192653601968162e-06, "loss": 0.1567, "step": 1063 }, { "epoch": 4.3076923076923075, "grad_norm": 0.2656740089409259, "learning_rate": 2.2929016062037057e-06, "loss": 0.1516, "step": 1064 }, { "epoch": 4.3117408906882595, "grad_norm": 0.2620081494069713, "learning_rate": 2.2666794376975055e-06, "loss": 0.1684, "step": 1065 }, { "epoch": 4.315789473684211, "grad_norm": 0.2594768941507778, "learning_rate": 2.24059906434998e-06, "loss": 0.1612, "step": 1066 }, { "epoch": 4.319838056680162, "grad_norm": 0.270372722816982, "learning_rate": 2.214660694699091e-06, "loss": 0.1524, "step": 1067 }, { "epoch": 4.323886639676114, "grad_norm": 0.25553413651137125, "learning_rate": 2.188864536147355e-06, "loss": 0.181, "step": 1068 }, { "epoch": 4.327935222672065, "grad_norm": 0.2591321276457931, "learning_rate": 2.1632107949601757e-06, "loss": 0.1463, "step": 1069 }, { "epoch": 4.331983805668016, "grad_norm": 0.2491347732064662, "learning_rate": 2.137699676264171e-06, "loss": 0.1689, "step": 1070 }, { "epoch": 4.336032388663968, "grad_norm": 0.24454871870657144, "learning_rate": 2.1123313840455738e-06, "loss": 0.1943, "step": 1071 }, { "epoch": 4.340080971659919, "grad_norm": 0.25872336410194824, "learning_rate": 2.08710612114857e-06, "loss": 0.1521, "step": 1072 }, { "epoch": 4.34412955465587, "grad_norm": 0.2589113507900544, "learning_rate": 2.0620240892736953e-06, "loss": 0.1701, "step": 1073 }, { "epoch": 4.348178137651822, "grad_norm": 0.24876163332191747, "learning_rate": 2.0370854889762e-06, "loss": 0.1772, "step": 1074 }, { "epoch": 4.352226720647773, "grad_norm": 0.24622993499206716, "learning_rate": 2.0122905196644726e-06, "loss": 0.1849, "step": 1075 }, { "epoch": 4.3562753036437245, "grad_norm": 0.24733155150649117, "learning_rate": 1.987639379598427e-06, "loss": 0.1742, "step": 1076 }, { "epoch": 4.3603238866396765, "grad_norm": 0.25065324618574847, "learning_rate": 1.963132265887919e-06, "loss": 0.1731, "step": 1077 }, { "epoch": 4.364372469635628, "grad_norm": 0.26786755908330623, "learning_rate": 1.9387693744911784e-06, "loss": 0.1658, "step": 1078 }, { "epoch": 4.368421052631579, "grad_norm": 0.2598296336864935, "learning_rate": 1.9145509002132368e-06, "loss": 0.1667, "step": 1079 }, { "epoch": 4.372469635627531, "grad_norm": 0.24324491751973587, "learning_rate": 1.8904770367043723e-06, "loss": 0.1782, "step": 1080 }, { "epoch": 4.376518218623482, "grad_norm": 0.24666633599095875, "learning_rate": 1.8665479764585504e-06, "loss": 0.1806, "step": 1081 }, { "epoch": 4.380566801619433, "grad_norm": 0.2545068004669214, "learning_rate": 1.8427639108118977e-06, "loss": 0.1784, "step": 1082 }, { "epoch": 4.384615384615385, "grad_norm": 0.2454279398205721, "learning_rate": 1.8191250299411755e-06, "loss": 0.1844, "step": 1083 }, { "epoch": 4.388663967611336, "grad_norm": 0.2574927264401085, "learning_rate": 1.7956315228622446e-06, "loss": 0.1555, "step": 1084 }, { "epoch": 4.392712550607287, "grad_norm": 0.24472600711800746, "learning_rate": 1.7722835774285553e-06, "loss": 0.1798, "step": 1085 }, { "epoch": 4.396761133603239, "grad_norm": 0.2528301944304256, "learning_rate": 1.7490813803296624e-06, "loss": 0.1625, "step": 1086 }, { "epoch": 4.40080971659919, "grad_norm": 0.2542761262668971, "learning_rate": 1.726025117089718e-06, "loss": 0.1808, "step": 1087 }, { "epoch": 4.4048582995951415, "grad_norm": 0.25068174651327313, "learning_rate": 1.70311497206598e-06, "loss": 0.1614, "step": 1088 }, { "epoch": 4.4089068825910935, "grad_norm": 0.2556085492569175, "learning_rate": 1.6803511284473638e-06, "loss": 0.155, "step": 1089 }, { "epoch": 4.412955465587045, "grad_norm": 0.25216800175341897, "learning_rate": 1.6577337682529538e-06, "loss": 0.1792, "step": 1090 }, { "epoch": 4.417004048582996, "grad_norm": 0.2502475379768753, "learning_rate": 1.6352630723305617e-06, "loss": 0.1745, "step": 1091 }, { "epoch": 4.421052631578947, "grad_norm": 0.24321410438064914, "learning_rate": 1.612939220355272e-06, "loss": 0.1588, "step": 1092 }, { "epoch": 4.425101214574899, "grad_norm": 0.253586229909242, "learning_rate": 1.5907623908280112e-06, "loss": 0.1652, "step": 1093 }, { "epoch": 4.42914979757085, "grad_norm": 0.2512021736681626, "learning_rate": 1.568732761074121e-06, "loss": 0.1699, "step": 1094 }, { "epoch": 4.433198380566802, "grad_norm": 0.25277979334578315, "learning_rate": 1.5468505072419237e-06, "loss": 0.1608, "step": 1095 }, { "epoch": 4.437246963562753, "grad_norm": 0.2521908704514002, "learning_rate": 1.5251158043013448e-06, "loss": 0.1587, "step": 1096 }, { "epoch": 4.441295546558704, "grad_norm": 0.25114541468951973, "learning_rate": 1.5035288260424885e-06, "loss": 0.1488, "step": 1097 }, { "epoch": 4.445344129554655, "grad_norm": 0.25779342261039484, "learning_rate": 1.4820897450742623e-06, "loss": 0.1575, "step": 1098 }, { "epoch": 4.449392712550607, "grad_norm": 0.2434259227770616, "learning_rate": 1.4607987328229767e-06, "loss": 0.1923, "step": 1099 }, { "epoch": 4.4534412955465585, "grad_norm": 0.2571959049702795, "learning_rate": 1.4396559595310056e-06, "loss": 0.1608, "step": 1100 }, { "epoch": 4.4574898785425106, "grad_norm": 0.25167577614434444, "learning_rate": 1.4186615942553973e-06, "loss": 0.1693, "step": 1101 }, { "epoch": 4.461538461538462, "grad_norm": 0.2515918318986122, "learning_rate": 1.3978158048665424e-06, "loss": 0.153, "step": 1102 }, { "epoch": 4.465587044534413, "grad_norm": 0.2508961779420286, "learning_rate": 1.3771187580468115e-06, "loss": 0.1717, "step": 1103 }, { "epoch": 4.469635627530364, "grad_norm": 0.2628046835358127, "learning_rate": 1.3565706192892392e-06, "loss": 0.1572, "step": 1104 }, { "epoch": 4.473684210526316, "grad_norm": 0.2431761440094737, "learning_rate": 1.3361715528961993e-06, "loss": 0.1592, "step": 1105 }, { "epoch": 4.477732793522267, "grad_norm": 0.2546010339161158, "learning_rate": 1.3159217219780817e-06, "loss": 0.1736, "step": 1106 }, { "epoch": 4.481781376518219, "grad_norm": 0.2455261846229183, "learning_rate": 1.2958212884519949e-06, "loss": 0.1564, "step": 1107 }, { "epoch": 4.48582995951417, "grad_norm": 0.2455671489474861, "learning_rate": 1.2758704130404675e-06, "loss": 0.1455, "step": 1108 }, { "epoch": 4.489878542510121, "grad_norm": 0.24699859872951216, "learning_rate": 1.2560692552701738e-06, "loss": 0.1803, "step": 1109 }, { "epoch": 4.493927125506072, "grad_norm": 0.25056672439731054, "learning_rate": 1.2364179734706382e-06, "loss": 0.1762, "step": 1110 }, { "epoch": 4.497975708502024, "grad_norm": 0.25555396906730515, "learning_rate": 1.2169167247729852e-06, "loss": 0.1705, "step": 1111 }, { "epoch": 4.502024291497976, "grad_norm": 0.2405139158518995, "learning_rate": 1.1975656651086864e-06, "loss": 0.1639, "step": 1112 }, { "epoch": 4.506072874493928, "grad_norm": 0.24988874631051622, "learning_rate": 1.1783649492082926e-06, "loss": 0.1569, "step": 1113 }, { "epoch": 4.510121457489879, "grad_norm": 0.24642149997491394, "learning_rate": 1.1593147306002183e-06, "loss": 0.184, "step": 1114 }, { "epoch": 4.51417004048583, "grad_norm": 0.2541654141184227, "learning_rate": 1.140415161609505e-06, "loss": 0.1625, "step": 1115 }, { "epoch": 4.518218623481781, "grad_norm": 0.24008816182749973, "learning_rate": 1.121666393356604e-06, "loss": 0.1706, "step": 1116 }, { "epoch": 4.522267206477733, "grad_norm": 0.2531126591379594, "learning_rate": 1.1030685757561632e-06, "loss": 0.1614, "step": 1117 }, { "epoch": 4.526315789473684, "grad_norm": 0.24659535471360672, "learning_rate": 1.0846218575158373e-06, "loss": 0.1646, "step": 1118 }, { "epoch": 4.530364372469636, "grad_norm": 0.2468971505127164, "learning_rate": 1.066326386135097e-06, "loss": 0.1484, "step": 1119 }, { "epoch": 4.534412955465587, "grad_norm": 0.25783275563054253, "learning_rate": 1.0481823079040398e-06, "loss": 0.1507, "step": 1120 }, { "epoch": 4.538461538461538, "grad_norm": 0.2590202804475492, "learning_rate": 1.0301897679022344e-06, "loss": 0.1639, "step": 1121 }, { "epoch": 4.5425101214574894, "grad_norm": 0.25270207667936734, "learning_rate": 1.0123489099975491e-06, "loss": 0.1622, "step": 1122 }, { "epoch": 4.5465587044534415, "grad_norm": 0.2505996844486312, "learning_rate": 9.9465987684501e-07, "loss": 0.1723, "step": 1123 }, { "epoch": 4.550607287449393, "grad_norm": 0.2504108744424855, "learning_rate": 9.771228098856534e-07, "loss": 0.1748, "step": 1124 }, { "epoch": 4.554655870445345, "grad_norm": 0.25967541334842265, "learning_rate": 9.597378493454013e-07, "loss": 0.1441, "step": 1125 }, { "epoch": 4.558704453441296, "grad_norm": 0.23839832922640844, "learning_rate": 9.425051342339353e-07, "loss": 0.1755, "step": 1126 }, { "epoch": 4.562753036437247, "grad_norm": 0.2454116523918595, "learning_rate": 9.254248023435864e-07, "loss": 0.1648, "step": 1127 }, { "epoch": 4.566801619433198, "grad_norm": 0.2479253687611135, "learning_rate": 9.084969902482288e-07, "loss": 0.1683, "step": 1128 }, { "epoch": 4.57085020242915, "grad_norm": 0.2531234356721739, "learning_rate": 8.917218333021993e-07, "loss": 0.1717, "step": 1129 }, { "epoch": 4.574898785425101, "grad_norm": 0.2541301759977706, "learning_rate": 8.750994656392109e-07, "loss": 0.1721, "step": 1130 }, { "epoch": 4.578947368421053, "grad_norm": 0.2560272136159639, "learning_rate": 8.58630020171265e-07, "loss": 0.1651, "step": 1131 }, { "epoch": 4.582995951417004, "grad_norm": 0.2469222391400382, "learning_rate": 8.423136285876099e-07, "loss": 0.1692, "step": 1132 }, { "epoch": 4.587044534412955, "grad_norm": 0.25491887333303215, "learning_rate": 8.26150421353682e-07, "loss": 0.1657, "step": 1133 }, { "epoch": 4.5910931174089065, "grad_norm": 0.2526650959887439, "learning_rate": 8.101405277100549e-07, "loss": 0.1646, "step": 1134 }, { "epoch": 4.5951417004048585, "grad_norm": 0.2376963494485588, "learning_rate": 7.942840756714077e-07, "loss": 0.1754, "step": 1135 }, { "epoch": 4.59919028340081, "grad_norm": 0.26119003668257434, "learning_rate": 7.785811920255093e-07, "loss": 0.1563, "step": 1136 }, { "epoch": 4.603238866396762, "grad_norm": 0.24705437027622298, "learning_rate": 7.630320023322024e-07, "loss": 0.1786, "step": 1137 }, { "epoch": 4.607287449392713, "grad_norm": 0.24485551903099928, "learning_rate": 7.476366309223903e-07, "loss": 0.1747, "step": 1138 }, { "epoch": 4.611336032388664, "grad_norm": 0.2452583203590927, "learning_rate": 7.323952008970537e-07, "loss": 0.1612, "step": 1139 }, { "epoch": 4.615384615384615, "grad_norm": 0.2473266729083651, "learning_rate": 7.173078341262618e-07, "loss": 0.1695, "step": 1140 }, { "epoch": 4.619433198380567, "grad_norm": 0.2583693316670105, "learning_rate": 7.023746512481989e-07, "loss": 0.164, "step": 1141 }, { "epoch": 4.623481781376518, "grad_norm": 0.2595992458379004, "learning_rate": 6.875957716681902e-07, "loss": 0.1713, "step": 1142 }, { "epoch": 4.62753036437247, "grad_norm": 0.2567209320932437, "learning_rate": 6.729713135577687e-07, "loss": 0.1612, "step": 1143 }, { "epoch": 4.631578947368421, "grad_norm": 0.24451529524029683, "learning_rate": 6.585013938537143e-07, "loss": 0.1635, "step": 1144 }, { "epoch": 4.635627530364372, "grad_norm": 0.24343497158618127, "learning_rate": 6.441861282571115e-07, "loss": 0.1659, "step": 1145 }, { "epoch": 4.6396761133603235, "grad_norm": 0.2354495934753019, "learning_rate": 6.300256312324471e-07, "loss": 0.1688, "step": 1146 }, { "epoch": 4.6437246963562755, "grad_norm": 0.252974150385158, "learning_rate": 6.160200160066776e-07, "loss": 0.1682, "step": 1147 }, { "epoch": 4.647773279352227, "grad_norm": 0.2588850868470319, "learning_rate": 6.021693945683327e-07, "loss": 0.1776, "step": 1148 }, { "epoch": 4.651821862348179, "grad_norm": 0.24515709457570242, "learning_rate": 5.884738776666044e-07, "loss": 0.165, "step": 1149 }, { "epoch": 4.65587044534413, "grad_norm": 0.24415091854914733, "learning_rate": 5.749335748104878e-07, "loss": 0.1544, "step": 1150 }, { "epoch": 4.659919028340081, "grad_norm": 0.24757503128764843, "learning_rate": 5.615485942678778e-07, "loss": 0.1511, "step": 1151 }, { "epoch": 4.663967611336032, "grad_norm": 0.27641468996838436, "learning_rate": 5.483190430647289e-07, "loss": 0.1766, "step": 1152 }, { "epoch": 4.668016194331984, "grad_norm": 0.24617226977610512, "learning_rate": 5.352450269841747e-07, "loss": 0.1713, "step": 1153 }, { "epoch": 4.672064777327935, "grad_norm": 0.24576451310885858, "learning_rate": 5.22326650565701e-07, "loss": 0.1682, "step": 1154 }, { "epoch": 4.676113360323887, "grad_norm": 0.2450441698234969, "learning_rate": 5.095640171043048e-07, "loss": 0.1584, "step": 1155 }, { "epoch": 4.680161943319838, "grad_norm": 0.2459313140321692, "learning_rate": 4.969572286496594e-07, "loss": 0.1611, "step": 1156 }, { "epoch": 4.684210526315789, "grad_norm": 0.24651219989169895, "learning_rate": 4.845063860053079e-07, "loss": 0.1464, "step": 1157 }, { "epoch": 4.6882591093117405, "grad_norm": 0.24789664153070864, "learning_rate": 4.7221158872785997e-07, "loss": 0.1624, "step": 1158 }, { "epoch": 4.6923076923076925, "grad_norm": 0.255993348315638, "learning_rate": 4.600729351261857e-07, "loss": 0.1739, "step": 1159 }, { "epoch": 4.696356275303644, "grad_norm": 0.25231053825655736, "learning_rate": 4.4809052226063355e-07, "loss": 0.1631, "step": 1160 }, { "epoch": 4.700404858299595, "grad_norm": 0.24504001006993004, "learning_rate": 4.3626444594226046e-07, "loss": 0.1688, "step": 1161 }, { "epoch": 4.704453441295547, "grad_norm": 0.2524341903757773, "learning_rate": 4.245948007320588e-07, "loss": 0.1779, "step": 1162 }, { "epoch": 4.708502024291498, "grad_norm": 0.2546644333678284, "learning_rate": 4.130816799401971e-07, "loss": 0.1792, "step": 1163 }, { "epoch": 4.712550607287449, "grad_norm": 0.23865274515206628, "learning_rate": 4.017251756252827e-07, "loss": 0.182, "step": 1164 }, { "epoch": 4.716599190283401, "grad_norm": 0.25579741321865973, "learning_rate": 3.9052537859362473e-07, "loss": 0.154, "step": 1165 }, { "epoch": 4.720647773279352, "grad_norm": 0.25263366586295205, "learning_rate": 3.7948237839849687e-07, "loss": 0.1732, "step": 1166 }, { "epoch": 4.724696356275303, "grad_norm": 0.25687940280849086, "learning_rate": 3.6859626333943797e-07, "loss": 0.1775, "step": 1167 }, { "epoch": 4.728744939271255, "grad_norm": 0.24114539798572496, "learning_rate": 3.578671204615347e-07, "loss": 0.1586, "step": 1168 }, { "epoch": 4.732793522267206, "grad_norm": 0.2477055966856705, "learning_rate": 3.472950355547267e-07, "loss": 0.1708, "step": 1169 }, { "epoch": 4.7368421052631575, "grad_norm": 0.24816938329649968, "learning_rate": 3.3688009315312244e-07, "loss": 0.1894, "step": 1170 }, { "epoch": 4.7408906882591095, "grad_norm": 0.2513048982288636, "learning_rate": 3.266223765343224e-07, "loss": 0.1811, "step": 1171 }, { "epoch": 4.744939271255061, "grad_norm": 0.2557839569801896, "learning_rate": 3.16521967718757e-07, "loss": 0.1648, "step": 1172 }, { "epoch": 4.748987854251012, "grad_norm": 0.25198297095475053, "learning_rate": 3.0657894746902726e-07, "loss": 0.1955, "step": 1173 }, { "epoch": 4.753036437246964, "grad_norm": 0.2562955271864, "learning_rate": 2.9679339528925654e-07, "loss": 0.1659, "step": 1174 }, { "epoch": 4.757085020242915, "grad_norm": 0.26633104085651843, "learning_rate": 2.871653894244597e-07, "loss": 0.1505, "step": 1175 }, { "epoch": 4.761133603238866, "grad_norm": 0.25420600286806705, "learning_rate": 2.7769500685991266e-07, "loss": 0.1661, "step": 1176 }, { "epoch": 4.765182186234818, "grad_norm": 0.2453284091720981, "learning_rate": 2.683823233205485e-07, "loss": 0.1692, "step": 1177 }, { "epoch": 4.769230769230769, "grad_norm": 0.2536436397650403, "learning_rate": 2.592274132703287e-07, "loss": 0.1682, "step": 1178 }, { "epoch": 4.77327935222672, "grad_norm": 0.24329649827745278, "learning_rate": 2.502303499116754e-07, "loss": 0.1587, "step": 1179 }, { "epoch": 4.777327935222672, "grad_norm": 0.24472675056871027, "learning_rate": 2.413912051848666e-07, "loss": 0.1565, "step": 1180 }, { "epoch": 4.781376518218623, "grad_norm": 0.2521203081537305, "learning_rate": 2.3271004976746613e-07, "loss": 0.1894, "step": 1181 }, { "epoch": 4.7854251012145745, "grad_norm": 0.2414611414735031, "learning_rate": 2.2418695307376393e-07, "loss": 0.1808, "step": 1182 }, { "epoch": 4.7894736842105265, "grad_norm": 0.24086821021825644, "learning_rate": 2.1582198325420968e-07, "loss": 0.1625, "step": 1183 }, { "epoch": 4.793522267206478, "grad_norm": 0.25087168778563085, "learning_rate": 2.0761520719488447e-07, "loss": 0.1529, "step": 1184 }, { "epoch": 4.797570850202429, "grad_norm": 0.25049863405389, "learning_rate": 1.9956669051694798e-07, "loss": 0.1517, "step": 1185 }, { "epoch": 4.801619433198381, "grad_norm": 0.23961641088309885, "learning_rate": 1.916764975761254e-07, "loss": 0.1613, "step": 1186 }, { "epoch": 4.805668016194332, "grad_norm": 0.2417717276700803, "learning_rate": 1.839446914621923e-07, "loss": 0.1709, "step": 1187 }, { "epoch": 4.809716599190283, "grad_norm": 0.24419568317714746, "learning_rate": 1.7637133399845962e-07, "loss": 0.1605, "step": 1188 }, { "epoch": 4.813765182186235, "grad_norm": 0.2442121746883796, "learning_rate": 1.6895648574129397e-07, "loss": 0.1708, "step": 1189 }, { "epoch": 4.817813765182186, "grad_norm": 0.25563691884221185, "learning_rate": 1.6170020597962465e-07, "loss": 0.1691, "step": 1190 }, { "epoch": 4.821862348178137, "grad_norm": 0.24615537309805113, "learning_rate": 1.5460255273447078e-07, "loss": 0.1574, "step": 1191 }, { "epoch": 4.825910931174089, "grad_norm": 0.24648271829352264, "learning_rate": 1.4766358275847715e-07, "loss": 0.1895, "step": 1192 }, { "epoch": 4.82995951417004, "grad_norm": 0.25091743950203976, "learning_rate": 1.4088335153546573e-07, "loss": 0.1574, "step": 1193 }, { "epoch": 4.834008097165992, "grad_norm": 0.2466667644586656, "learning_rate": 1.3426191327998496e-07, "loss": 0.175, "step": 1194 }, { "epoch": 4.838056680161944, "grad_norm": 0.2452544798209131, "learning_rate": 1.277993209368744e-07, "loss": 0.1761, "step": 1195 }, { "epoch": 4.842105263157895, "grad_norm": 0.24813039962138836, "learning_rate": 1.214956261808542e-07, "loss": 0.1611, "step": 1196 }, { "epoch": 4.846153846153846, "grad_norm": 0.2484564499093421, "learning_rate": 1.1535087941609846e-07, "loss": 0.1682, "step": 1197 }, { "epoch": 4.850202429149798, "grad_norm": 0.24229428890789162, "learning_rate": 1.0936512977583802e-07, "loss": 0.1579, "step": 1198 }, { "epoch": 4.854251012145749, "grad_norm": 0.24666993624099845, "learning_rate": 1.0353842512196732e-07, "loss": 0.1853, "step": 1199 }, { "epoch": 4.8582995951417, "grad_norm": 0.25538402057953696, "learning_rate": 9.787081204466253e-08, "loss": 0.1667, "step": 1200 }, { "epoch": 4.862348178137652, "grad_norm": 0.24437996242042748, "learning_rate": 9.236233586200627e-08, "loss": 0.1626, "step": 1201 }, { "epoch": 4.866396761133603, "grad_norm": 0.2472236251647808, "learning_rate": 8.70130406196279e-08, "loss": 0.1674, "step": 1202 }, { "epoch": 4.870445344129554, "grad_norm": 0.2433735037238243, "learning_rate": 8.182296909035047e-08, "loss": 0.1689, "step": 1203 }, { "epoch": 4.874493927125506, "grad_norm": 0.24754511258134174, "learning_rate": 7.679216277384439e-08, "loss": 0.1654, "step": 1204 }, { "epoch": 4.8785425101214575, "grad_norm": 0.2538597661292144, "learning_rate": 7.19206618963053e-08, "loss": 0.1664, "step": 1205 }, { "epoch": 4.882591093117409, "grad_norm": 0.24732647857192708, "learning_rate": 6.720850541012347e-08, "loss": 0.165, "step": 1206 }, { "epoch": 4.886639676113361, "grad_norm": 0.24517973501943222, "learning_rate": 6.265573099357714e-08, "loss": 0.1671, "step": 1207 }, { "epoch": 4.890688259109312, "grad_norm": 0.24136995500684905, "learning_rate": 5.826237505053067e-08, "loss": 0.1743, "step": 1208 }, { "epoch": 4.894736842105263, "grad_norm": 0.25341169622936727, "learning_rate": 5.4028472710137e-08, "loss": 0.1805, "step": 1209 }, { "epoch": 4.898785425101215, "grad_norm": 0.2434651800650058, "learning_rate": 4.9954057826571146e-08, "loss": 0.1601, "step": 1210 }, { "epoch": 4.902834008097166, "grad_norm": 0.2578287476891399, "learning_rate": 4.6039162978743776e-08, "loss": 0.167, "step": 1211 }, { "epoch": 4.906882591093117, "grad_norm": 0.24237892447290074, "learning_rate": 4.228381947004812e-08, "loss": 0.1482, "step": 1212 }, { "epoch": 4.910931174089069, "grad_norm": 0.2496166473598281, "learning_rate": 3.868805732811343e-08, "loss": 0.1831, "step": 1213 }, { "epoch": 4.91497975708502, "grad_norm": 0.26091927174091856, "learning_rate": 3.525190530455636e-08, "loss": 0.1655, "step": 1214 }, { "epoch": 4.919028340080971, "grad_norm": 0.23957773925231965, "learning_rate": 3.197539087475887e-08, "loss": 0.1677, "step": 1215 }, { "epoch": 4.923076923076923, "grad_norm": 0.2340694931659839, "learning_rate": 2.8858540237641786e-08, "loss": 0.1693, "step": 1216 }, { "epoch": 4.9271255060728745, "grad_norm": 0.24705813553528755, "learning_rate": 2.5901378315458247e-08, "loss": 0.1507, "step": 1217 }, { "epoch": 4.931174089068826, "grad_norm": 0.24151354457384108, "learning_rate": 2.3103928753598347e-08, "loss": 0.1849, "step": 1218 }, { "epoch": 4.935222672064778, "grad_norm": 0.2508668057858703, "learning_rate": 2.0466213920393718e-08, "loss": 0.1866, "step": 1219 }, { "epoch": 4.939271255060729, "grad_norm": 0.24720367885578898, "learning_rate": 1.7988254906942115e-08, "loss": 0.1517, "step": 1220 }, { "epoch": 4.94331983805668, "grad_norm": 0.25032888172763984, "learning_rate": 1.5670071526936447e-08, "loss": 0.1647, "step": 1221 }, { "epoch": 4.947368421052632, "grad_norm": 0.25415154534308626, "learning_rate": 1.3511682316509344e-08, "loss": 0.1635, "step": 1222 }, { "epoch": 4.951417004048583, "grad_norm": 0.24671683348348156, "learning_rate": 1.1513104534086605e-08, "loss": 0.1755, "step": 1223 }, { "epoch": 4.955465587044534, "grad_norm": 0.2506898881002704, "learning_rate": 9.67435416023843e-09, "loss": 0.1518, "step": 1224 }, { "epoch": 4.959514170040486, "grad_norm": 0.24541268703040928, "learning_rate": 7.995445897566178e-09, "loss": 0.1619, "step": 1225 }, { "epoch": 4.963562753036437, "grad_norm": 0.24323728151581608, "learning_rate": 6.476393170578021e-09, "loss": 0.159, "step": 1226 }, { "epoch": 4.967611336032388, "grad_norm": 0.24658568330413455, "learning_rate": 5.11720812557348e-09, "loss": 0.1681, "step": 1227 }, { "epoch": 4.97165991902834, "grad_norm": 0.24588032240638533, "learning_rate": 3.917901630563492e-09, "loss": 0.1767, "step": 1228 }, { "epoch": 4.9757085020242915, "grad_norm": 0.2531261445795952, "learning_rate": 2.878483275170485e-09, "loss": 0.164, "step": 1229 }, { "epoch": 4.979757085020243, "grad_norm": 0.24808437006746573, "learning_rate": 1.998961370555108e-09, "loss": 0.1809, "step": 1230 }, { "epoch": 4.983805668016195, "grad_norm": 0.252224839860576, "learning_rate": 1.2793429493518361e-09, "loss": 0.1823, "step": 1231 }, { "epoch": 4.987854251012146, "grad_norm": 0.2444363064783835, "learning_rate": 7.196337656112384e-10, "loss": 0.1547, "step": 1232 }, { "epoch": 4.991902834008097, "grad_norm": 0.2454060628565618, "learning_rate": 3.198382947511292e-10, "loss": 0.1798, "step": 1233 }, { "epoch": 4.995951417004049, "grad_norm": 0.25709167785108245, "learning_rate": 7.995973352770137e-11, "loss": 0.1572, "step": 1234 }, { "epoch": 5.0, "grad_norm": 0.25030767977596424, "learning_rate": 0.0, "loss": 0.1646, "step": 1235 }, { "epoch": 5.0, "step": 1235, "total_flos": 2.213207912522711e+18, "train_loss": 0.3652493509083142, "train_runtime": 24175.7912, "train_samples_per_second": 6.539, "train_steps_per_second": 0.051 } ], "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": 2.213207912522711e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }