{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.978823529411765, "eval_steps": 96, "global_step": 318, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.009411764705882352, "grad_norm": 0.8642500638961792, "learning_rate": 4e-05, "loss": 0.9841, "step": 1 }, { "epoch": 0.018823529411764704, "grad_norm": 0.8003044724464417, "learning_rate": 8e-05, "loss": 0.9727, "step": 2 }, { "epoch": 0.02823529411764706, "grad_norm": 0.7982213497161865, "learning_rate": 0.00012, "loss": 1.0076, "step": 3 }, { "epoch": 0.03764705882352941, "grad_norm": 0.4778502285480499, "learning_rate": 0.00016, "loss": 0.9179, "step": 4 }, { "epoch": 0.047058823529411764, "grad_norm": 0.1798139065504074, "learning_rate": 0.0002, "loss": 0.8544, "step": 5 }, { "epoch": 0.05647058823529412, "grad_norm": 0.10934074968099594, "learning_rate": 0.00019936102236421725, "loss": 0.8259, "step": 6 }, { "epoch": 0.06588235294117648, "grad_norm": 0.451732873916626, "learning_rate": 0.00019872204472843452, "loss": 0.8176, "step": 7 }, { "epoch": 0.07529411764705882, "grad_norm": 0.39763253927230835, "learning_rate": 0.00019808306709265177, "loss": 0.8091, "step": 8 }, { "epoch": 0.08470588235294117, "grad_norm": 0.08421512693166733, "learning_rate": 0.000197444089456869, "loss": 0.8066, "step": 9 }, { "epoch": 0.09411764705882353, "grad_norm": 0.0752546563744545, "learning_rate": 0.00019680511182108628, "loss": 0.788, "step": 10 }, { "epoch": 0.10352941176470588, "grad_norm": 0.07105962187051773, "learning_rate": 0.00019616613418530353, "loss": 0.8142, "step": 11 }, { "epoch": 0.11294117647058824, "grad_norm": 0.07268067449331284, "learning_rate": 0.0001955271565495208, "loss": 0.7427, "step": 12 }, { "epoch": 0.1223529411764706, "grad_norm": 0.071601502597332, "learning_rate": 0.00019488817891373804, "loss": 0.7673, "step": 13 }, { "epoch": 0.13176470588235295, "grad_norm": 0.06190289184451103, "learning_rate": 0.00019424920127795528, "loss": 0.7897, "step": 14 }, { "epoch": 0.1411764705882353, "grad_norm": 0.062015291303396225, "learning_rate": 0.00019361022364217253, "loss": 0.7552, "step": 15 }, { "epoch": 0.15058823529411763, "grad_norm": 0.06343454122543335, "learning_rate": 0.00019297124600638977, "loss": 0.7983, "step": 16 }, { "epoch": 0.16, "grad_norm": 0.0880446657538414, "learning_rate": 0.00019233226837060702, "loss": 0.7331, "step": 17 }, { "epoch": 0.16941176470588235, "grad_norm": 0.06399823725223541, "learning_rate": 0.00019169329073482429, "loss": 0.7017, "step": 18 }, { "epoch": 0.17882352941176471, "grad_norm": 0.06614473462104797, "learning_rate": 0.00019105431309904153, "loss": 0.7346, "step": 19 }, { "epoch": 0.18823529411764706, "grad_norm": 0.05928972363471985, "learning_rate": 0.0001904153354632588, "loss": 0.7088, "step": 20 }, { "epoch": 0.1976470588235294, "grad_norm": 0.05864707753062248, "learning_rate": 0.00018977635782747604, "loss": 0.7017, "step": 21 }, { "epoch": 0.20705882352941177, "grad_norm": 0.0725838840007782, "learning_rate": 0.0001891373801916933, "loss": 0.7255, "step": 22 }, { "epoch": 0.2164705882352941, "grad_norm": 0.07014375925064087, "learning_rate": 0.00018849840255591056, "loss": 0.6699, "step": 23 }, { "epoch": 0.22588235294117648, "grad_norm": 0.08222078531980515, "learning_rate": 0.0001878594249201278, "loss": 0.6802, "step": 24 }, { "epoch": 0.23529411764705882, "grad_norm": 0.07020223140716553, "learning_rate": 0.00018722044728434505, "loss": 0.7013, "step": 25 }, { "epoch": 0.2447058823529412, "grad_norm": 0.05753432214260101, "learning_rate": 0.00018658146964856232, "loss": 0.6547, "step": 26 }, { "epoch": 0.2541176470588235, "grad_norm": 0.06647774577140808, "learning_rate": 0.00018594249201277956, "loss": 0.7132, "step": 27 }, { "epoch": 0.2635294117647059, "grad_norm": 0.061453238129615784, "learning_rate": 0.00018530351437699683, "loss": 0.6891, "step": 28 }, { "epoch": 0.27294117647058824, "grad_norm": 0.055535465478897095, "learning_rate": 0.00018466453674121408, "loss": 0.6542, "step": 29 }, { "epoch": 0.2823529411764706, "grad_norm": 0.05627722293138504, "learning_rate": 0.00018402555910543132, "loss": 0.677, "step": 30 }, { "epoch": 0.2917647058823529, "grad_norm": 0.05428534746170044, "learning_rate": 0.0001833865814696486, "loss": 0.6592, "step": 31 }, { "epoch": 0.30117647058823527, "grad_norm": 0.06012285500764847, "learning_rate": 0.00018274760383386583, "loss": 0.6662, "step": 32 }, { "epoch": 0.31058823529411766, "grad_norm": 0.08650115132331848, "learning_rate": 0.00018210862619808308, "loss": 0.6546, "step": 33 }, { "epoch": 0.32, "grad_norm": 0.058147966861724854, "learning_rate": 0.00018146964856230032, "loss": 0.6505, "step": 34 }, { "epoch": 0.32941176470588235, "grad_norm": 0.054181504994630814, "learning_rate": 0.00018083067092651756, "loss": 0.6428, "step": 35 }, { "epoch": 0.3388235294117647, "grad_norm": 0.05629313737154007, "learning_rate": 0.00018019169329073484, "loss": 0.6916, "step": 36 }, { "epoch": 0.34823529411764703, "grad_norm": 0.05400744453072548, "learning_rate": 0.00017955271565495208, "loss": 0.6646, "step": 37 }, { "epoch": 0.35764705882352943, "grad_norm": 0.053580883890390396, "learning_rate": 0.00017891373801916932, "loss": 0.6297, "step": 38 }, { "epoch": 0.36705882352941177, "grad_norm": 0.05560213327407837, "learning_rate": 0.0001782747603833866, "loss": 0.6284, "step": 39 }, { "epoch": 0.3764705882352941, "grad_norm": 0.05281270295381546, "learning_rate": 0.00017763578274760384, "loss": 0.6392, "step": 40 }, { "epoch": 0.38588235294117645, "grad_norm": 0.06260088086128235, "learning_rate": 0.00017699680511182108, "loss": 0.7056, "step": 41 }, { "epoch": 0.3952941176470588, "grad_norm": 0.058404579758644104, "learning_rate": 0.00017635782747603835, "loss": 0.6138, "step": 42 }, { "epoch": 0.4047058823529412, "grad_norm": 0.050437066704034805, "learning_rate": 0.0001757188498402556, "loss": 0.6569, "step": 43 }, { "epoch": 0.41411764705882353, "grad_norm": 0.05336596816778183, "learning_rate": 0.00017507987220447287, "loss": 0.612, "step": 44 }, { "epoch": 0.4235294117647059, "grad_norm": 0.05253816023468971, "learning_rate": 0.0001744408945686901, "loss": 0.6195, "step": 45 }, { "epoch": 0.4329411764705882, "grad_norm": 0.05323391407728195, "learning_rate": 0.00017380191693290735, "loss": 0.624, "step": 46 }, { "epoch": 0.4423529411764706, "grad_norm": 0.05454220622777939, "learning_rate": 0.00017316293929712462, "loss": 0.6654, "step": 47 }, { "epoch": 0.45176470588235296, "grad_norm": 0.05840761214494705, "learning_rate": 0.00017252396166134187, "loss": 0.6791, "step": 48 }, { "epoch": 0.4611764705882353, "grad_norm": 0.05933906137943268, "learning_rate": 0.0001718849840255591, "loss": 0.6501, "step": 49 }, { "epoch": 0.47058823529411764, "grad_norm": 0.06150069832801819, "learning_rate": 0.00017124600638977638, "loss": 0.6332, "step": 50 }, { "epoch": 0.48, "grad_norm": 0.054139360785484314, "learning_rate": 0.00017060702875399363, "loss": 0.6268, "step": 51 }, { "epoch": 0.4894117647058824, "grad_norm": 0.05578823760151863, "learning_rate": 0.00016996805111821087, "loss": 0.6259, "step": 52 }, { "epoch": 0.4988235294117647, "grad_norm": 0.06352369487285614, "learning_rate": 0.00016932907348242811, "loss": 0.6271, "step": 53 }, { "epoch": 0.508235294117647, "grad_norm": 0.06086834892630577, "learning_rate": 0.00016869009584664536, "loss": 0.631, "step": 54 }, { "epoch": 0.5176470588235295, "grad_norm": 0.05695689842104912, "learning_rate": 0.00016805111821086263, "loss": 0.64, "step": 55 }, { "epoch": 0.5270588235294118, "grad_norm": 0.056874532252550125, "learning_rate": 0.00016741214057507987, "loss": 0.6296, "step": 56 }, { "epoch": 0.5364705882352941, "grad_norm": 0.061433881521224976, "learning_rate": 0.00016677316293929712, "loss": 0.683, "step": 57 }, { "epoch": 0.5458823529411765, "grad_norm": 0.06481802463531494, "learning_rate": 0.0001661341853035144, "loss": 0.599, "step": 58 }, { "epoch": 0.5552941176470588, "grad_norm": 0.06558655947446823, "learning_rate": 0.00016549520766773163, "loss": 0.6362, "step": 59 }, { "epoch": 0.5647058823529412, "grad_norm": 0.057915814220905304, "learning_rate": 0.0001648562300319489, "loss": 0.6396, "step": 60 }, { "epoch": 0.5741176470588235, "grad_norm": 0.06019767373800278, "learning_rate": 0.00016421725239616614, "loss": 0.6444, "step": 61 }, { "epoch": 0.5835294117647059, "grad_norm": 0.06425336748361588, "learning_rate": 0.0001635782747603834, "loss": 0.6175, "step": 62 }, { "epoch": 0.5929411764705882, "grad_norm": 0.062431298196315765, "learning_rate": 0.00016293929712460066, "loss": 0.6458, "step": 63 }, { "epoch": 0.6023529411764705, "grad_norm": 0.057641636580228806, "learning_rate": 0.0001623003194888179, "loss": 0.6262, "step": 64 }, { "epoch": 0.611764705882353, "grad_norm": 0.05894685909152031, "learning_rate": 0.00016166134185303515, "loss": 0.6036, "step": 65 }, { "epoch": 0.6211764705882353, "grad_norm": 0.06207429617643356, "learning_rate": 0.00016102236421725242, "loss": 0.6367, "step": 66 }, { "epoch": 0.6305882352941177, "grad_norm": 0.06500203162431717, "learning_rate": 0.00016038338658146966, "loss": 0.6443, "step": 67 }, { "epoch": 0.64, "grad_norm": 0.06465457379817963, "learning_rate": 0.0001597444089456869, "loss": 0.6105, "step": 68 }, { "epoch": 0.6494117647058824, "grad_norm": 0.060090478509664536, "learning_rate": 0.00015910543130990418, "loss": 0.6447, "step": 69 }, { "epoch": 0.6588235294117647, "grad_norm": 0.06724690645933151, "learning_rate": 0.00015846645367412142, "loss": 0.6062, "step": 70 }, { "epoch": 0.668235294117647, "grad_norm": 0.06291332095861435, "learning_rate": 0.00015782747603833866, "loss": 0.6005, "step": 71 }, { "epoch": 0.6776470588235294, "grad_norm": 0.06592954695224762, "learning_rate": 0.0001571884984025559, "loss": 0.6036, "step": 72 }, { "epoch": 0.6870588235294117, "grad_norm": 0.06050164997577667, "learning_rate": 0.00015654952076677315, "loss": 0.5993, "step": 73 }, { "epoch": 0.6964705882352941, "grad_norm": 0.061909306794404984, "learning_rate": 0.00015591054313099042, "loss": 0.6159, "step": 74 }, { "epoch": 0.7058823529411765, "grad_norm": 0.06927211582660675, "learning_rate": 0.00015527156549520767, "loss": 0.6554, "step": 75 }, { "epoch": 0.7152941176470589, "grad_norm": 0.06098336726427078, "learning_rate": 0.00015463258785942494, "loss": 0.5998, "step": 76 }, { "epoch": 0.7247058823529412, "grad_norm": 0.06612212210893631, "learning_rate": 0.00015399361022364218, "loss": 0.6057, "step": 77 }, { "epoch": 0.7341176470588235, "grad_norm": 0.06455227732658386, "learning_rate": 0.00015335463258785942, "loss": 0.64, "step": 78 }, { "epoch": 0.7435294117647059, "grad_norm": 0.40494394302368164, "learning_rate": 0.0001527156549520767, "loss": 0.6397, "step": 79 }, { "epoch": 0.7529411764705882, "grad_norm": 0.05910542979836464, "learning_rate": 0.00015207667731629394, "loss": 0.6087, "step": 80 }, { "epoch": 0.7623529411764706, "grad_norm": 0.06125890091061592, "learning_rate": 0.00015143769968051118, "loss": 0.6133, "step": 81 }, { "epoch": 0.7717647058823529, "grad_norm": 0.0716337338089943, "learning_rate": 0.00015079872204472845, "loss": 0.6136, "step": 82 }, { "epoch": 0.7811764705882352, "grad_norm": 0.07003322243690491, "learning_rate": 0.0001501597444089457, "loss": 0.6236, "step": 83 }, { "epoch": 0.7905882352941176, "grad_norm": 0.06324715912342072, "learning_rate": 0.00014952076677316297, "loss": 0.6282, "step": 84 }, { "epoch": 0.8, "grad_norm": 0.07135389745235443, "learning_rate": 0.0001488817891373802, "loss": 0.6443, "step": 85 }, { "epoch": 0.8094117647058824, "grad_norm": 0.06127123162150383, "learning_rate": 0.00014824281150159745, "loss": 0.6396, "step": 86 }, { "epoch": 0.8188235294117647, "grad_norm": 0.06172896921634674, "learning_rate": 0.0001476038338658147, "loss": 0.6377, "step": 87 }, { "epoch": 0.8282352941176471, "grad_norm": 0.3543515205383301, "learning_rate": 0.00014696485623003194, "loss": 0.6454, "step": 88 }, { "epoch": 0.8376470588235294, "grad_norm": 0.06527980417013168, "learning_rate": 0.0001463258785942492, "loss": 0.615, "step": 89 }, { "epoch": 0.8470588235294118, "grad_norm": 0.06327975541353226, "learning_rate": 0.00014568690095846646, "loss": 0.6447, "step": 90 }, { "epoch": 0.8564705882352941, "grad_norm": 0.06739926338195801, "learning_rate": 0.0001450479233226837, "loss": 0.6087, "step": 91 }, { "epoch": 0.8658823529411764, "grad_norm": 0.06617800146341324, "learning_rate": 0.00014440894568690097, "loss": 0.6259, "step": 92 }, { "epoch": 0.8752941176470588, "grad_norm": 0.06242835149168968, "learning_rate": 0.00014376996805111821, "loss": 0.6049, "step": 93 }, { "epoch": 0.8847058823529412, "grad_norm": 0.06359254568815231, "learning_rate": 0.00014313099041533546, "loss": 0.6274, "step": 94 }, { "epoch": 0.8941176470588236, "grad_norm": 0.06559597700834274, "learning_rate": 0.00014249201277955273, "loss": 0.5935, "step": 95 }, { "epoch": 0.9035294117647059, "grad_norm": 0.07493000477552414, "learning_rate": 0.00014185303514376997, "loss": 0.5881, "step": 96 }, { "epoch": 0.9035294117647059, "eval_loss": 0.6278424859046936, "eval_runtime": 5.469, "eval_samples_per_second": 8.045, "eval_steps_per_second": 1.097, "step": 96 }, { "epoch": 0.9129411764705883, "grad_norm": 0.06714215129613876, "learning_rate": 0.00014121405750798722, "loss": 0.6438, "step": 97 }, { "epoch": 0.9223529411764706, "grad_norm": 0.06775335222482681, "learning_rate": 0.0001405750798722045, "loss": 0.6256, "step": 98 }, { "epoch": 0.9317647058823529, "grad_norm": 0.07045792043209076, "learning_rate": 0.00013993610223642173, "loss": 0.6712, "step": 99 }, { "epoch": 0.9411764705882353, "grad_norm": 0.06958217918872833, "learning_rate": 0.000139297124600639, "loss": 0.6278, "step": 100 }, { "epoch": 0.9505882352941176, "grad_norm": 0.06508302688598633, "learning_rate": 0.00013865814696485625, "loss": 0.6415, "step": 101 }, { "epoch": 0.96, "grad_norm": 0.06876156479120255, "learning_rate": 0.0001380191693290735, "loss": 0.6211, "step": 102 }, { "epoch": 0.9694117647058823, "grad_norm": 0.07631471753120422, "learning_rate": 0.00013738019169329076, "loss": 0.6276, "step": 103 }, { "epoch": 0.9788235294117648, "grad_norm": 0.07122895866632462, "learning_rate": 0.000136741214057508, "loss": 0.5997, "step": 104 }, { "epoch": 0.9882352941176471, "grad_norm": 0.06862416863441467, "learning_rate": 0.00013610223642172525, "loss": 0.6563, "step": 105 }, { "epoch": 0.9976470588235294, "grad_norm": 0.06701315939426422, "learning_rate": 0.0001354632587859425, "loss": 0.61, "step": 106 }, { "epoch": 1.0, "grad_norm": 0.14547984302043915, "learning_rate": 0.00013482428115015973, "loss": 0.6382, "step": 107 }, { "epoch": 1.0094117647058825, "grad_norm": 0.0676453560590744, "learning_rate": 0.000134185303514377, "loss": 0.5766, "step": 108 }, { "epoch": 1.0188235294117647, "grad_norm": 0.06471403688192368, "learning_rate": 0.00013354632587859425, "loss": 0.5769, "step": 109 }, { "epoch": 1.0282352941176471, "grad_norm": 0.07038411498069763, "learning_rate": 0.0001329073482428115, "loss": 0.5828, "step": 110 }, { "epoch": 1.0376470588235294, "grad_norm": 0.0679129809141159, "learning_rate": 0.00013226837060702876, "loss": 0.5755, "step": 111 }, { "epoch": 1.0470588235294118, "grad_norm": 0.07297012954950333, "learning_rate": 0.000131629392971246, "loss": 0.6114, "step": 112 }, { "epoch": 1.056470588235294, "grad_norm": 0.07036986202001572, "learning_rate": 0.00013099041533546325, "loss": 0.6254, "step": 113 }, { "epoch": 1.0658823529411765, "grad_norm": 0.08385265618562698, "learning_rate": 0.00013035143769968052, "loss": 0.6284, "step": 114 }, { "epoch": 1.0752941176470587, "grad_norm": 0.08367498964071274, "learning_rate": 0.00012971246006389777, "loss": 0.6128, "step": 115 }, { "epoch": 1.0847058823529412, "grad_norm": 0.082453154027462, "learning_rate": 0.000129073482428115, "loss": 0.6012, "step": 116 }, { "epoch": 1.0941176470588236, "grad_norm": 0.0714535042643547, "learning_rate": 0.00012843450479233228, "loss": 0.599, "step": 117 }, { "epoch": 1.1035294117647059, "grad_norm": 0.07391790300607681, "learning_rate": 0.00012779552715654952, "loss": 0.5897, "step": 118 }, { "epoch": 1.1129411764705883, "grad_norm": 0.08383256196975708, "learning_rate": 0.0001271565495207668, "loss": 0.634, "step": 119 }, { "epoch": 1.1223529411764706, "grad_norm": 0.08821647614240646, "learning_rate": 0.00012651757188498404, "loss": 0.5869, "step": 120 }, { "epoch": 1.131764705882353, "grad_norm": 0.07556191831827164, "learning_rate": 0.00012587859424920128, "loss": 0.6275, "step": 121 }, { "epoch": 1.1411764705882352, "grad_norm": 0.08794881403446198, "learning_rate": 0.00012523961661341855, "loss": 0.6115, "step": 122 }, { "epoch": 1.1505882352941177, "grad_norm": 0.0785142183303833, "learning_rate": 0.0001246006389776358, "loss": 0.6156, "step": 123 }, { "epoch": 1.16, "grad_norm": 0.07684168219566345, "learning_rate": 0.00012396166134185304, "loss": 0.6107, "step": 124 }, { "epoch": 1.1694117647058824, "grad_norm": 0.07763410359621048, "learning_rate": 0.00012332268370607028, "loss": 0.5888, "step": 125 }, { "epoch": 1.1788235294117646, "grad_norm": 0.09084579348564148, "learning_rate": 0.00012268370607028753, "loss": 0.5912, "step": 126 }, { "epoch": 1.188235294117647, "grad_norm": 0.0838058665394783, "learning_rate": 0.00012204472843450481, "loss": 0.6152, "step": 127 }, { "epoch": 1.1976470588235295, "grad_norm": 0.08908473700284958, "learning_rate": 0.00012140575079872206, "loss": 0.6049, "step": 128 }, { "epoch": 1.2070588235294117, "grad_norm": 0.08239720016717911, "learning_rate": 0.0001207667731629393, "loss": 0.5852, "step": 129 }, { "epoch": 1.2164705882352942, "grad_norm": 0.08228597790002823, "learning_rate": 0.00012012779552715656, "loss": 0.5642, "step": 130 }, { "epoch": 1.2258823529411764, "grad_norm": 0.08196559548377991, "learning_rate": 0.0001194888178913738, "loss": 0.5971, "step": 131 }, { "epoch": 1.2352941176470589, "grad_norm": 0.08850298076868057, "learning_rate": 0.00011884984025559104, "loss": 0.6149, "step": 132 }, { "epoch": 1.244705882352941, "grad_norm": 0.08643686771392822, "learning_rate": 0.00011821086261980832, "loss": 0.6097, "step": 133 }, { "epoch": 1.2541176470588236, "grad_norm": 0.08877662569284439, "learning_rate": 0.00011757188498402556, "loss": 0.6362, "step": 134 }, { "epoch": 1.263529411764706, "grad_norm": 0.08452433347702026, "learning_rate": 0.00011693290734824283, "loss": 0.6331, "step": 135 }, { "epoch": 1.2729411764705882, "grad_norm": 0.08155957609415054, "learning_rate": 0.00011629392971246007, "loss": 0.6214, "step": 136 }, { "epoch": 1.2823529411764705, "grad_norm": 0.08229539543390274, "learning_rate": 0.00011565495207667732, "loss": 0.5981, "step": 137 }, { "epoch": 1.291764705882353, "grad_norm": 0.09338800609111786, "learning_rate": 0.00011501597444089457, "loss": 0.6326, "step": 138 }, { "epoch": 1.3011764705882354, "grad_norm": 0.0837632343173027, "learning_rate": 0.00011437699680511182, "loss": 0.5736, "step": 139 }, { "epoch": 1.3105882352941176, "grad_norm": 0.08500789105892181, "learning_rate": 0.00011373801916932908, "loss": 0.6253, "step": 140 }, { "epoch": 1.32, "grad_norm": 0.0843970999121666, "learning_rate": 0.00011309904153354633, "loss": 0.6053, "step": 141 }, { "epoch": 1.3294117647058823, "grad_norm": 0.08848956227302551, "learning_rate": 0.00011246006389776358, "loss": 0.6184, "step": 142 }, { "epoch": 1.3388235294117647, "grad_norm": 0.10718461126089096, "learning_rate": 0.00011182108626198085, "loss": 0.583, "step": 143 }, { "epoch": 1.348235294117647, "grad_norm": 0.08756856620311737, "learning_rate": 0.00011118210862619809, "loss": 0.5861, "step": 144 }, { "epoch": 1.3576470588235294, "grad_norm": 0.08492905646562576, "learning_rate": 0.00011054313099041533, "loss": 0.5707, "step": 145 }, { "epoch": 1.3670588235294119, "grad_norm": 0.08758281171321869, "learning_rate": 0.0001099041533546326, "loss": 0.555, "step": 146 }, { "epoch": 1.3764705882352941, "grad_norm": 0.09751519560813904, "learning_rate": 0.00010926517571884985, "loss": 0.5976, "step": 147 }, { "epoch": 1.3858823529411763, "grad_norm": 0.09590818732976913, "learning_rate": 0.00010862619808306709, "loss": 0.6015, "step": 148 }, { "epoch": 1.3952941176470588, "grad_norm": 0.08812163025140762, "learning_rate": 0.00010798722044728435, "loss": 0.5905, "step": 149 }, { "epoch": 1.4047058823529412, "grad_norm": 0.09162674099206924, "learning_rate": 0.0001073482428115016, "loss": 0.6063, "step": 150 }, { "epoch": 1.4141176470588235, "grad_norm": 0.08727669715881348, "learning_rate": 0.00010670926517571886, "loss": 0.6181, "step": 151 }, { "epoch": 1.423529411764706, "grad_norm": 0.0928676649928093, "learning_rate": 0.00010607028753993611, "loss": 0.6188, "step": 152 }, { "epoch": 1.4329411764705882, "grad_norm": 0.09681576490402222, "learning_rate": 0.00010543130990415335, "loss": 0.5818, "step": 153 }, { "epoch": 1.4423529411764706, "grad_norm": 0.08795556426048279, "learning_rate": 0.00010479233226837062, "loss": 0.6134, "step": 154 }, { "epoch": 1.4517647058823528, "grad_norm": 0.0861482247710228, "learning_rate": 0.00010415335463258787, "loss": 0.6082, "step": 155 }, { "epoch": 1.4611764705882353, "grad_norm": 0.09977812319993973, "learning_rate": 0.00010351437699680511, "loss": 0.5921, "step": 156 }, { "epoch": 1.4705882352941178, "grad_norm": 0.10190846771001816, "learning_rate": 0.00010287539936102237, "loss": 0.6271, "step": 157 }, { "epoch": 1.48, "grad_norm": 0.09232486039400101, "learning_rate": 0.00010223642172523961, "loss": 0.6067, "step": 158 }, { "epoch": 1.4894117647058824, "grad_norm": 0.10211990028619766, "learning_rate": 0.00010159744408945688, "loss": 0.6238, "step": 159 }, { "epoch": 1.4988235294117647, "grad_norm": 0.08955651521682739, "learning_rate": 0.00010095846645367413, "loss": 0.6002, "step": 160 }, { "epoch": 1.5082352941176471, "grad_norm": 0.10033038258552551, "learning_rate": 0.00010031948881789137, "loss": 0.6129, "step": 161 }, { "epoch": 1.5176470588235293, "grad_norm": 0.09701602160930634, "learning_rate": 9.968051118210863e-05, "loss": 0.5867, "step": 162 }, { "epoch": 1.5270588235294118, "grad_norm": 0.0969882607460022, "learning_rate": 9.904153354632588e-05, "loss": 0.599, "step": 163 }, { "epoch": 1.5364705882352943, "grad_norm": 0.09163233637809753, "learning_rate": 9.840255591054314e-05, "loss": 0.6078, "step": 164 }, { "epoch": 1.5458823529411765, "grad_norm": 0.0925818681716919, "learning_rate": 9.77635782747604e-05, "loss": 0.6231, "step": 165 }, { "epoch": 1.5552941176470587, "grad_norm": 0.09490446001291275, "learning_rate": 9.712460063897764e-05, "loss": 0.6099, "step": 166 }, { "epoch": 1.5647058823529412, "grad_norm": 0.10370604693889618, "learning_rate": 9.648562300319489e-05, "loss": 0.6133, "step": 167 }, { "epoch": 1.5741176470588236, "grad_norm": 0.10043718665838242, "learning_rate": 9.584664536741214e-05, "loss": 0.6002, "step": 168 }, { "epoch": 1.5835294117647059, "grad_norm": 0.10102451592683792, "learning_rate": 9.52076677316294e-05, "loss": 0.6326, "step": 169 }, { "epoch": 1.592941176470588, "grad_norm": 0.09170352667570114, "learning_rate": 9.456869009584664e-05, "loss": 0.5725, "step": 170 }, { "epoch": 1.6023529411764705, "grad_norm": 0.09696916490793228, "learning_rate": 9.39297124600639e-05, "loss": 0.6162, "step": 171 }, { "epoch": 1.611764705882353, "grad_norm": 0.1032591313123703, "learning_rate": 9.329073482428116e-05, "loss": 0.6022, "step": 172 }, { "epoch": 1.6211764705882352, "grad_norm": 0.09963531792163849, "learning_rate": 9.265175718849842e-05, "loss": 0.5918, "step": 173 }, { "epoch": 1.6305882352941177, "grad_norm": 0.10566572844982147, "learning_rate": 9.201277955271566e-05, "loss": 0.6248, "step": 174 }, { "epoch": 1.6400000000000001, "grad_norm": 0.09654838591814041, "learning_rate": 9.137380191693292e-05, "loss": 0.5747, "step": 175 }, { "epoch": 1.6494117647058824, "grad_norm": 0.09412531554698944, "learning_rate": 9.073482428115016e-05, "loss": 0.611, "step": 176 }, { "epoch": 1.6588235294117646, "grad_norm": 0.10707147419452667, "learning_rate": 9.009584664536742e-05, "loss": 0.6371, "step": 177 }, { "epoch": 1.668235294117647, "grad_norm": 0.0976637527346611, "learning_rate": 8.945686900958466e-05, "loss": 0.636, "step": 178 }, { "epoch": 1.6776470588235295, "grad_norm": 0.09769190102815628, "learning_rate": 8.881789137380192e-05, "loss": 0.6379, "step": 179 }, { "epoch": 1.6870588235294117, "grad_norm": 0.1029646173119545, "learning_rate": 8.817891373801918e-05, "loss": 0.6533, "step": 180 }, { "epoch": 1.696470588235294, "grad_norm": 0.10120602697134018, "learning_rate": 8.753993610223643e-05, "loss": 0.6044, "step": 181 }, { "epoch": 1.7058823529411766, "grad_norm": 0.0992206409573555, "learning_rate": 8.690095846645368e-05, "loss": 0.6072, "step": 182 }, { "epoch": 1.7152941176470589, "grad_norm": 0.10124579071998596, "learning_rate": 8.626198083067093e-05, "loss": 0.5923, "step": 183 }, { "epoch": 1.724705882352941, "grad_norm": 0.10673081874847412, "learning_rate": 8.562300319488819e-05, "loss": 0.5964, "step": 184 }, { "epoch": 1.7341176470588235, "grad_norm": 0.10745410621166229, "learning_rate": 8.498402555910544e-05, "loss": 0.6052, "step": 185 }, { "epoch": 1.743529411764706, "grad_norm": 0.10404065251350403, "learning_rate": 8.434504792332268e-05, "loss": 0.5975, "step": 186 }, { "epoch": 1.7529411764705882, "grad_norm": 0.09927040338516235, "learning_rate": 8.370607028753994e-05, "loss": 0.5901, "step": 187 }, { "epoch": 1.7623529411764705, "grad_norm": 0.10322125256061554, "learning_rate": 8.30670926517572e-05, "loss": 0.6154, "step": 188 }, { "epoch": 1.771764705882353, "grad_norm": 0.10899791866540909, "learning_rate": 8.242811501597445e-05, "loss": 0.6255, "step": 189 }, { "epoch": 1.7811764705882354, "grad_norm": 0.1041494831442833, "learning_rate": 8.17891373801917e-05, "loss": 0.5925, "step": 190 }, { "epoch": 1.7905882352941176, "grad_norm": 0.09239751845598221, "learning_rate": 8.115015974440895e-05, "loss": 0.5713, "step": 191 }, { "epoch": 1.8, "grad_norm": 0.09495066851377487, "learning_rate": 8.051118210862621e-05, "loss": 0.5896, "step": 192 }, { "epoch": 1.8, "eval_loss": 0.6196094155311584, "eval_runtime": 5.4299, "eval_samples_per_second": 8.103, "eval_steps_per_second": 1.105, "step": 192 }, { "epoch": 1.8094117647058825, "grad_norm": 0.09602215141057968, "learning_rate": 7.987220447284345e-05, "loss": 0.5979, "step": 193 }, { "epoch": 1.8188235294117647, "grad_norm": 0.10422977060079575, "learning_rate": 7.923322683706071e-05, "loss": 0.5704, "step": 194 }, { "epoch": 1.828235294117647, "grad_norm": 0.09678755700588226, "learning_rate": 7.859424920127795e-05, "loss": 0.5774, "step": 195 }, { "epoch": 1.8376470588235294, "grad_norm": 0.09845128655433655, "learning_rate": 7.795527156549521e-05, "loss": 0.5816, "step": 196 }, { "epoch": 1.8470588235294119, "grad_norm": 0.1065673753619194, "learning_rate": 7.731629392971247e-05, "loss": 0.6135, "step": 197 }, { "epoch": 1.856470588235294, "grad_norm": 0.10570935904979706, "learning_rate": 7.667731629392971e-05, "loss": 0.5908, "step": 198 }, { "epoch": 1.8658823529411763, "grad_norm": 0.09649720042943954, "learning_rate": 7.603833865814697e-05, "loss": 0.599, "step": 199 }, { "epoch": 1.8752941176470588, "grad_norm": 0.10398146510124207, "learning_rate": 7.539936102236423e-05, "loss": 0.5853, "step": 200 }, { "epoch": 1.8847058823529412, "grad_norm": 0.09633094817399979, "learning_rate": 7.476038338658148e-05, "loss": 0.5927, "step": 201 }, { "epoch": 1.8941176470588235, "grad_norm": 0.0993979275226593, "learning_rate": 7.412140575079873e-05, "loss": 0.5928, "step": 202 }, { "epoch": 1.903529411764706, "grad_norm": 0.10687059164047241, "learning_rate": 7.348242811501597e-05, "loss": 0.5882, "step": 203 }, { "epoch": 1.9129411764705884, "grad_norm": 0.10128702223300934, "learning_rate": 7.284345047923323e-05, "loss": 0.6009, "step": 204 }, { "epoch": 1.9223529411764706, "grad_norm": 0.10716967284679413, "learning_rate": 7.220447284345049e-05, "loss": 0.6198, "step": 205 }, { "epoch": 1.9317647058823528, "grad_norm": 0.10603494942188263, "learning_rate": 7.156549520766773e-05, "loss": 0.6222, "step": 206 }, { "epoch": 1.9411764705882353, "grad_norm": 0.10125169903039932, "learning_rate": 7.092651757188499e-05, "loss": 0.5938, "step": 207 }, { "epoch": 1.9505882352941177, "grad_norm": 0.10542251914739609, "learning_rate": 7.028753993610224e-05, "loss": 0.6341, "step": 208 }, { "epoch": 1.96, "grad_norm": 0.09659598022699356, "learning_rate": 6.96485623003195e-05, "loss": 0.59, "step": 209 }, { "epoch": 1.9694117647058822, "grad_norm": 0.1122719794511795, "learning_rate": 6.900958466453674e-05, "loss": 0.6109, "step": 210 }, { "epoch": 1.9788235294117649, "grad_norm": 0.11106933653354645, "learning_rate": 6.8370607028754e-05, "loss": 0.58, "step": 211 }, { "epoch": 1.988235294117647, "grad_norm": 0.09962272644042969, "learning_rate": 6.773162939297125e-05, "loss": 0.6105, "step": 212 }, { "epoch": 1.9976470588235293, "grad_norm": 0.09547895193099976, "learning_rate": 6.70926517571885e-05, "loss": 0.5709, "step": 213 }, { "epoch": 2.0, "grad_norm": 0.21181434392929077, "learning_rate": 6.645367412140575e-05, "loss": 0.6164, "step": 214 }, { "epoch": 2.0094117647058822, "grad_norm": 0.11414559185504913, "learning_rate": 6.5814696485623e-05, "loss": 0.5642, "step": 215 }, { "epoch": 2.018823529411765, "grad_norm": 0.11991499364376068, "learning_rate": 6.517571884984026e-05, "loss": 0.5741, "step": 216 }, { "epoch": 2.028235294117647, "grad_norm": 0.10295461863279343, "learning_rate": 6.45367412140575e-05, "loss": 0.5604, "step": 217 }, { "epoch": 2.0376470588235294, "grad_norm": 0.10355547070503235, "learning_rate": 6.389776357827476e-05, "loss": 0.5884, "step": 218 }, { "epoch": 2.0470588235294116, "grad_norm": 0.12203363329172134, "learning_rate": 6.325878594249202e-05, "loss": 0.5903, "step": 219 }, { "epoch": 2.0564705882352943, "grad_norm": 0.12483850866556168, "learning_rate": 6.261980830670928e-05, "loss": 0.5666, "step": 220 }, { "epoch": 2.0658823529411765, "grad_norm": 0.12819188833236694, "learning_rate": 6.198083067092652e-05, "loss": 0.5493, "step": 221 }, { "epoch": 2.0752941176470587, "grad_norm": 0.11613185703754425, "learning_rate": 6.134185303514376e-05, "loss": 0.6121, "step": 222 }, { "epoch": 2.084705882352941, "grad_norm": 0.11060836911201477, "learning_rate": 6.070287539936103e-05, "loss": 0.5748, "step": 223 }, { "epoch": 2.0941176470588236, "grad_norm": 0.13958008587360382, "learning_rate": 6.006389776357828e-05, "loss": 0.62, "step": 224 }, { "epoch": 2.103529411764706, "grad_norm": 0.14533892273902893, "learning_rate": 5.942492012779552e-05, "loss": 0.5897, "step": 225 }, { "epoch": 2.112941176470588, "grad_norm": 0.12220677733421326, "learning_rate": 5.878594249201278e-05, "loss": 0.5508, "step": 226 }, { "epoch": 2.1223529411764708, "grad_norm": 0.11975925415754318, "learning_rate": 5.814696485623004e-05, "loss": 0.5483, "step": 227 }, { "epoch": 2.131764705882353, "grad_norm": 0.12308664619922638, "learning_rate": 5.750798722044729e-05, "loss": 0.5921, "step": 228 }, { "epoch": 2.1411764705882352, "grad_norm": 0.12570548057556152, "learning_rate": 5.686900958466454e-05, "loss": 0.6229, "step": 229 }, { "epoch": 2.1505882352941175, "grad_norm": 0.12253190577030182, "learning_rate": 5.623003194888179e-05, "loss": 0.5758, "step": 230 }, { "epoch": 2.16, "grad_norm": 0.1249895840883255, "learning_rate": 5.5591054313099045e-05, "loss": 0.5633, "step": 231 }, { "epoch": 2.1694117647058824, "grad_norm": 0.1355949193239212, "learning_rate": 5.49520766773163e-05, "loss": 0.5486, "step": 232 }, { "epoch": 2.1788235294117646, "grad_norm": 0.12255489826202393, "learning_rate": 5.4313099041533546e-05, "loss": 0.5906, "step": 233 }, { "epoch": 2.1882352941176473, "grad_norm": 0.12850622832775116, "learning_rate": 5.36741214057508e-05, "loss": 0.5738, "step": 234 }, { "epoch": 2.1976470588235295, "grad_norm": 0.18490703403949738, "learning_rate": 5.3035143769968054e-05, "loss": 0.5737, "step": 235 }, { "epoch": 2.2070588235294117, "grad_norm": 0.135318785905838, "learning_rate": 5.239616613418531e-05, "loss": 0.5963, "step": 236 }, { "epoch": 2.216470588235294, "grad_norm": 0.12884393334388733, "learning_rate": 5.1757188498402555e-05, "loss": 0.5399, "step": 237 }, { "epoch": 2.2258823529411766, "grad_norm": 0.13065044581890106, "learning_rate": 5.1118210862619806e-05, "loss": 0.5611, "step": 238 }, { "epoch": 2.235294117647059, "grad_norm": 0.12230806797742844, "learning_rate": 5.047923322683706e-05, "loss": 0.5446, "step": 239 }, { "epoch": 2.244705882352941, "grad_norm": 0.13359951972961426, "learning_rate": 4.984025559105431e-05, "loss": 0.5652, "step": 240 }, { "epoch": 2.2541176470588233, "grad_norm": 0.1409720480442047, "learning_rate": 4.920127795527157e-05, "loss": 0.5437, "step": 241 }, { "epoch": 2.263529411764706, "grad_norm": 0.1343528777360916, "learning_rate": 4.856230031948882e-05, "loss": 0.5811, "step": 242 }, { "epoch": 2.2729411764705882, "grad_norm": 0.1315775066614151, "learning_rate": 4.792332268370607e-05, "loss": 0.5718, "step": 243 }, { "epoch": 2.2823529411764705, "grad_norm": 0.1300155520439148, "learning_rate": 4.728434504792332e-05, "loss": 0.5629, "step": 244 }, { "epoch": 2.291764705882353, "grad_norm": 0.1364685744047165, "learning_rate": 4.664536741214058e-05, "loss": 0.5641, "step": 245 }, { "epoch": 2.3011764705882354, "grad_norm": 0.13575628399848938, "learning_rate": 4.600638977635783e-05, "loss": 0.5861, "step": 246 }, { "epoch": 2.3105882352941176, "grad_norm": 0.13364288210868835, "learning_rate": 4.536741214057508e-05, "loss": 0.5959, "step": 247 }, { "epoch": 2.32, "grad_norm": 0.129843071103096, "learning_rate": 4.472843450479233e-05, "loss": 0.5631, "step": 248 }, { "epoch": 2.3294117647058825, "grad_norm": 0.13373443484306335, "learning_rate": 4.408945686900959e-05, "loss": 0.557, "step": 249 }, { "epoch": 2.3388235294117647, "grad_norm": 0.14091914892196655, "learning_rate": 4.345047923322684e-05, "loss": 0.577, "step": 250 }, { "epoch": 2.348235294117647, "grad_norm": 0.13922256231307983, "learning_rate": 4.2811501597444096e-05, "loss": 0.5404, "step": 251 }, { "epoch": 2.357647058823529, "grad_norm": 0.13278770446777344, "learning_rate": 4.217252396166134e-05, "loss": 0.5131, "step": 252 }, { "epoch": 2.367058823529412, "grad_norm": 0.1421966701745987, "learning_rate": 4.15335463258786e-05, "loss": 0.5803, "step": 253 }, { "epoch": 2.376470588235294, "grad_norm": 0.13415196537971497, "learning_rate": 4.089456869009585e-05, "loss": 0.5689, "step": 254 }, { "epoch": 2.3858823529411763, "grad_norm": 0.13316908478736877, "learning_rate": 4.0255591054313104e-05, "loss": 0.5741, "step": 255 }, { "epoch": 2.395294117647059, "grad_norm": 0.13901880383491516, "learning_rate": 3.9616613418530355e-05, "loss": 0.5365, "step": 256 }, { "epoch": 2.4047058823529412, "grad_norm": 0.13510987162590027, "learning_rate": 3.8977635782747605e-05, "loss": 0.5511, "step": 257 }, { "epoch": 2.4141176470588235, "grad_norm": 0.140598326921463, "learning_rate": 3.8338658146964856e-05, "loss": 0.5566, "step": 258 }, { "epoch": 2.4235294117647057, "grad_norm": 0.13736282289028168, "learning_rate": 3.769968051118211e-05, "loss": 0.576, "step": 259 }, { "epoch": 2.4329411764705884, "grad_norm": 0.13893315196037292, "learning_rate": 3.7060702875399364e-05, "loss": 0.5839, "step": 260 }, { "epoch": 2.4423529411764706, "grad_norm": 0.13888853788375854, "learning_rate": 3.6421725239616614e-05, "loss": 0.5634, "step": 261 }, { "epoch": 2.451764705882353, "grad_norm": 0.1429632157087326, "learning_rate": 3.5782747603833865e-05, "loss": 0.5627, "step": 262 }, { "epoch": 2.461176470588235, "grad_norm": 0.13526563346385956, "learning_rate": 3.514376996805112e-05, "loss": 0.5538, "step": 263 }, { "epoch": 2.4705882352941178, "grad_norm": 0.1388704627752304, "learning_rate": 3.450479233226837e-05, "loss": 0.5671, "step": 264 }, { "epoch": 2.48, "grad_norm": 0.13550125062465668, "learning_rate": 3.386581469648562e-05, "loss": 0.5431, "step": 265 }, { "epoch": 2.489411764705882, "grad_norm": 0.13878309726715088, "learning_rate": 3.322683706070287e-05, "loss": 0.5771, "step": 266 }, { "epoch": 2.498823529411765, "grad_norm": 0.15442192554473877, "learning_rate": 3.258785942492013e-05, "loss": 0.5689, "step": 267 }, { "epoch": 2.508235294117647, "grad_norm": 0.13992522656917572, "learning_rate": 3.194888178913738e-05, "loss": 0.5514, "step": 268 }, { "epoch": 2.5176470588235293, "grad_norm": 0.13724872469902039, "learning_rate": 3.130990415335464e-05, "loss": 0.5537, "step": 269 }, { "epoch": 2.527058823529412, "grad_norm": 0.13630978763103485, "learning_rate": 3.067092651757188e-05, "loss": 0.5616, "step": 270 }, { "epoch": 2.5364705882352943, "grad_norm": 0.13853025436401367, "learning_rate": 3.003194888178914e-05, "loss": 0.5656, "step": 271 }, { "epoch": 2.5458823529411765, "grad_norm": 0.1420363038778305, "learning_rate": 2.939297124600639e-05, "loss": 0.5826, "step": 272 }, { "epoch": 2.5552941176470587, "grad_norm": 0.1408669352531433, "learning_rate": 2.8753993610223644e-05, "loss": 0.5583, "step": 273 }, { "epoch": 2.564705882352941, "grad_norm": 0.1526196449995041, "learning_rate": 2.8115015974440894e-05, "loss": 0.5917, "step": 274 }, { "epoch": 2.5741176470588236, "grad_norm": 0.1629597693681717, "learning_rate": 2.747603833865815e-05, "loss": 0.5624, "step": 275 }, { "epoch": 2.583529411764706, "grad_norm": 0.14529789984226227, "learning_rate": 2.68370607028754e-05, "loss": 0.5328, "step": 276 }, { "epoch": 2.592941176470588, "grad_norm": 0.1526152491569519, "learning_rate": 2.6198083067092656e-05, "loss": 0.588, "step": 277 }, { "epoch": 2.6023529411764708, "grad_norm": 0.14647038280963898, "learning_rate": 2.5559105431309903e-05, "loss": 0.5696, "step": 278 }, { "epoch": 2.611764705882353, "grad_norm": 0.13880112767219543, "learning_rate": 2.4920127795527157e-05, "loss": 0.5448, "step": 279 }, { "epoch": 2.621176470588235, "grad_norm": 0.1403883844614029, "learning_rate": 2.428115015974441e-05, "loss": 0.5485, "step": 280 }, { "epoch": 2.630588235294118, "grad_norm": 0.1447409838438034, "learning_rate": 2.364217252396166e-05, "loss": 0.5519, "step": 281 }, { "epoch": 2.64, "grad_norm": 0.14351636171340942, "learning_rate": 2.3003194888178915e-05, "loss": 0.5546, "step": 282 }, { "epoch": 2.6494117647058824, "grad_norm": 0.13909754157066345, "learning_rate": 2.2364217252396165e-05, "loss": 0.5576, "step": 283 }, { "epoch": 2.6588235294117646, "grad_norm": 0.14639312028884888, "learning_rate": 2.172523961661342e-05, "loss": 0.5786, "step": 284 }, { "epoch": 2.668235294117647, "grad_norm": 0.1540895700454712, "learning_rate": 2.108626198083067e-05, "loss": 0.6019, "step": 285 }, { "epoch": 2.6776470588235295, "grad_norm": 0.1561094969511032, "learning_rate": 2.0447284345047924e-05, "loss": 0.6138, "step": 286 }, { "epoch": 2.6870588235294117, "grad_norm": 0.14837074279785156, "learning_rate": 1.9808306709265177e-05, "loss": 0.5633, "step": 287 }, { "epoch": 2.696470588235294, "grad_norm": 0.1421661227941513, "learning_rate": 1.9169329073482428e-05, "loss": 0.5308, "step": 288 }, { "epoch": 2.696470588235294, "eval_loss": 0.6246063709259033, "eval_runtime": 5.4441, "eval_samples_per_second": 8.082, "eval_steps_per_second": 1.102, "step": 288 }, { "epoch": 2.7058823529411766, "grad_norm": 0.14756028354167938, "learning_rate": 1.8530351437699682e-05, "loss": 0.5692, "step": 289 }, { "epoch": 2.715294117647059, "grad_norm": 0.1475173979997635, "learning_rate": 1.7891373801916932e-05, "loss": 0.5383, "step": 290 }, { "epoch": 2.724705882352941, "grad_norm": 0.14893798530101776, "learning_rate": 1.7252396166134186e-05, "loss": 0.5603, "step": 291 }, { "epoch": 2.7341176470588238, "grad_norm": 0.14635878801345825, "learning_rate": 1.6613418530351437e-05, "loss": 0.573, "step": 292 }, { "epoch": 2.743529411764706, "grad_norm": 0.14744271337985992, "learning_rate": 1.597444089456869e-05, "loss": 0.5646, "step": 293 }, { "epoch": 2.7529411764705882, "grad_norm": 0.14066603779792786, "learning_rate": 1.533546325878594e-05, "loss": 0.5335, "step": 294 }, { "epoch": 2.7623529411764705, "grad_norm": 0.14420145750045776, "learning_rate": 1.4696485623003195e-05, "loss": 0.5885, "step": 295 }, { "epoch": 2.7717647058823527, "grad_norm": 0.1417757123708725, "learning_rate": 1.4057507987220447e-05, "loss": 0.525, "step": 296 }, { "epoch": 2.7811764705882354, "grad_norm": 0.13913412392139435, "learning_rate": 1.34185303514377e-05, "loss": 0.5355, "step": 297 }, { "epoch": 2.7905882352941176, "grad_norm": 0.14291714131832123, "learning_rate": 1.2779552715654951e-05, "loss": 0.5419, "step": 298 }, { "epoch": 2.8, "grad_norm": 0.15101145207881927, "learning_rate": 1.2140575079872205e-05, "loss": 0.5945, "step": 299 }, { "epoch": 2.8094117647058825, "grad_norm": 0.15145310759544373, "learning_rate": 1.1501597444089457e-05, "loss": 0.5801, "step": 300 }, { "epoch": 2.8188235294117647, "grad_norm": 0.14465861022472382, "learning_rate": 1.086261980830671e-05, "loss": 0.561, "step": 301 }, { "epoch": 2.828235294117647, "grad_norm": 0.14341317117214203, "learning_rate": 1.0223642172523962e-05, "loss": 0.5524, "step": 302 }, { "epoch": 2.8376470588235296, "grad_norm": 0.15162834525108337, "learning_rate": 9.584664536741214e-06, "loss": 0.568, "step": 303 }, { "epoch": 2.847058823529412, "grad_norm": 0.14496251940727234, "learning_rate": 8.945686900958466e-06, "loss": 0.5336, "step": 304 }, { "epoch": 2.856470588235294, "grad_norm": 0.14667992293834686, "learning_rate": 8.306709265175718e-06, "loss": 0.5613, "step": 305 }, { "epoch": 2.8658823529411763, "grad_norm": 0.1467258483171463, "learning_rate": 7.66773162939297e-06, "loss": 0.5572, "step": 306 }, { "epoch": 2.8752941176470586, "grad_norm": 0.1460108608007431, "learning_rate": 7.0287539936102235e-06, "loss": 0.5788, "step": 307 }, { "epoch": 2.8847058823529412, "grad_norm": 0.14580175280570984, "learning_rate": 6.389776357827476e-06, "loss": 0.5501, "step": 308 }, { "epoch": 2.8941176470588235, "grad_norm": 0.1488231122493744, "learning_rate": 5.750798722044729e-06, "loss": 0.5537, "step": 309 }, { "epoch": 2.9035294117647057, "grad_norm": 0.14228259027004242, "learning_rate": 5.111821086261981e-06, "loss": 0.5383, "step": 310 }, { "epoch": 2.9129411764705884, "grad_norm": 0.15516069531440735, "learning_rate": 4.472843450479233e-06, "loss": 0.5889, "step": 311 }, { "epoch": 2.9223529411764706, "grad_norm": 0.14953361451625824, "learning_rate": 3.833865814696485e-06, "loss": 0.5448, "step": 312 }, { "epoch": 2.931764705882353, "grad_norm": 0.15361154079437256, "learning_rate": 3.194888178913738e-06, "loss": 0.5687, "step": 313 }, { "epoch": 2.9411764705882355, "grad_norm": 0.15242530405521393, "learning_rate": 2.5559105431309904e-06, "loss": 0.5819, "step": 314 }, { "epoch": 2.9505882352941177, "grad_norm": 0.1486331820487976, "learning_rate": 1.9169329073482426e-06, "loss": 0.5652, "step": 315 }, { "epoch": 2.96, "grad_norm": 0.15188926458358765, "learning_rate": 1.2779552715654952e-06, "loss": 0.5816, "step": 316 }, { "epoch": 2.969411764705882, "grad_norm": 0.1547756791114807, "learning_rate": 6.389776357827476e-07, "loss": 0.5798, "step": 317 }, { "epoch": 2.978823529411765, "grad_norm": 0.15288227796554565, "learning_rate": 0.0, "loss": 0.5555, "step": 318 } ], "logging_steps": 1, "max_steps": 318, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 300, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 4.4215740961652736e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }