{ "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": 6.458304021751614, "learning_rate": 3.2258064516129035e-07, "loss": 1.0506, "step": 1 }, { "epoch": 0.008097165991902834, "grad_norm": 6.356013854155811, "learning_rate": 6.451612903225807e-07, "loss": 1.0244, "step": 2 }, { "epoch": 0.012145748987854251, "grad_norm": 6.455705077557856, "learning_rate": 9.67741935483871e-07, "loss": 1.0544, "step": 3 }, { "epoch": 0.016194331983805668, "grad_norm": 6.257161302676687, "learning_rate": 1.2903225806451614e-06, "loss": 1.0289, "step": 4 }, { "epoch": 0.020242914979757085, "grad_norm": 6.058059237240253, "learning_rate": 1.6129032258064516e-06, "loss": 1.0605, "step": 5 }, { "epoch": 0.024291497975708502, "grad_norm": 5.757028116335258, "learning_rate": 1.935483870967742e-06, "loss": 1.0295, "step": 6 }, { "epoch": 0.02834008097165992, "grad_norm": 4.631849649572181, "learning_rate": 2.2580645161290324e-06, "loss": 1.0102, "step": 7 }, { "epoch": 0.032388663967611336, "grad_norm": 4.225771269053461, "learning_rate": 2.580645161290323e-06, "loss": 1.0042, "step": 8 }, { "epoch": 0.03643724696356275, "grad_norm": 2.7968218244819107, "learning_rate": 2.903225806451613e-06, "loss": 0.9872, "step": 9 }, { "epoch": 0.04048582995951417, "grad_norm": 2.5314354511621397, "learning_rate": 3.225806451612903e-06, "loss": 0.9677, "step": 10 }, { "epoch": 0.044534412955465584, "grad_norm": 2.498523568194102, "learning_rate": 3.548387096774194e-06, "loss": 0.9706, "step": 11 }, { "epoch": 0.048582995951417005, "grad_norm": 3.8007205963078854, "learning_rate": 3.870967741935484e-06, "loss": 0.9566, "step": 12 }, { "epoch": 0.05263157894736842, "grad_norm": 4.008060397790492, "learning_rate": 4.193548387096774e-06, "loss": 0.9254, "step": 13 }, { "epoch": 0.05668016194331984, "grad_norm": 3.8694509159222217, "learning_rate": 4.516129032258065e-06, "loss": 0.9458, "step": 14 }, { "epoch": 0.06072874493927125, "grad_norm": 3.434419560900035, "learning_rate": 4.838709677419355e-06, "loss": 0.9106, "step": 15 }, { "epoch": 0.06477732793522267, "grad_norm": 2.6051196445722136, "learning_rate": 5.161290322580646e-06, "loss": 0.8828, "step": 16 }, { "epoch": 0.06882591093117409, "grad_norm": 2.4493482535143283, "learning_rate": 5.483870967741935e-06, "loss": 0.8867, "step": 17 }, { "epoch": 0.0728744939271255, "grad_norm": 1.989369525908678, "learning_rate": 5.806451612903226e-06, "loss": 0.8626, "step": 18 }, { "epoch": 0.07692307692307693, "grad_norm": 1.5135022122172321, "learning_rate": 6.129032258064517e-06, "loss": 0.8402, "step": 19 }, { "epoch": 0.08097165991902834, "grad_norm": 1.0498472108302517, "learning_rate": 6.451612903225806e-06, "loss": 0.8297, "step": 20 }, { "epoch": 0.08502024291497975, "grad_norm": 1.060321298964548, "learning_rate": 6.774193548387097e-06, "loss": 0.8139, "step": 21 }, { "epoch": 0.08906882591093117, "grad_norm": 1.2215993255403055, "learning_rate": 7.096774193548388e-06, "loss": 0.8069, "step": 22 }, { "epoch": 0.0931174089068826, "grad_norm": 1.0217209981154431, "learning_rate": 7.4193548387096784e-06, "loss": 0.7895, "step": 23 }, { "epoch": 0.09716599190283401, "grad_norm": 0.9160018407202818, "learning_rate": 7.741935483870968e-06, "loss": 0.7983, "step": 24 }, { "epoch": 0.10121457489878542, "grad_norm": 1.05001719500963, "learning_rate": 8.064516129032258e-06, "loss": 0.7972, "step": 25 }, { "epoch": 0.10526315789473684, "grad_norm": 0.9209523392164932, "learning_rate": 8.387096774193549e-06, "loss": 0.7859, "step": 26 }, { "epoch": 0.10931174089068826, "grad_norm": 0.7715198486738587, "learning_rate": 8.70967741935484e-06, "loss": 0.7847, "step": 27 }, { "epoch": 0.11336032388663968, "grad_norm": 0.7528360413289695, "learning_rate": 9.03225806451613e-06, "loss": 0.7673, "step": 28 }, { "epoch": 0.11740890688259109, "grad_norm": 0.8171384582302095, "learning_rate": 9.35483870967742e-06, "loss": 0.7522, "step": 29 }, { "epoch": 0.1214574898785425, "grad_norm": 0.7406143357414685, "learning_rate": 9.67741935483871e-06, "loss": 0.7666, "step": 30 }, { "epoch": 0.12550607287449392, "grad_norm": 0.6686668284552244, "learning_rate": 1e-05, "loss": 0.7563, "step": 31 }, { "epoch": 0.12955465587044535, "grad_norm": 0.6820285034407254, "learning_rate": 1.0322580645161291e-05, "loss": 0.7635, "step": 32 }, { "epoch": 0.13360323886639677, "grad_norm": 0.6208387483457936, "learning_rate": 1.0645161290322582e-05, "loss": 0.7428, "step": 33 }, { "epoch": 0.13765182186234817, "grad_norm": 0.6292662833815938, "learning_rate": 1.096774193548387e-05, "loss": 0.7417, "step": 34 }, { "epoch": 0.1417004048582996, "grad_norm": 0.5863927727505922, "learning_rate": 1.1290322580645164e-05, "loss": 0.7486, "step": 35 }, { "epoch": 0.145748987854251, "grad_norm": 0.5334581663362096, "learning_rate": 1.1612903225806453e-05, "loss": 0.73, "step": 36 }, { "epoch": 0.14979757085020243, "grad_norm": 0.6247547442506911, "learning_rate": 1.1935483870967743e-05, "loss": 0.7545, "step": 37 }, { "epoch": 0.15384615384615385, "grad_norm": 0.4900709443803612, "learning_rate": 1.2258064516129034e-05, "loss": 0.7215, "step": 38 }, { "epoch": 0.15789473684210525, "grad_norm": 0.5993833052268721, "learning_rate": 1.2580645161290324e-05, "loss": 0.7395, "step": 39 }, { "epoch": 0.16194331983805668, "grad_norm": 0.522741422168129, "learning_rate": 1.2903225806451613e-05, "loss": 0.7195, "step": 40 }, { "epoch": 0.1659919028340081, "grad_norm": 0.5122554080375915, "learning_rate": 1.3225806451612903e-05, "loss": 0.7134, "step": 41 }, { "epoch": 0.1700404858299595, "grad_norm": 0.5228208401243004, "learning_rate": 1.3548387096774194e-05, "loss": 0.7092, "step": 42 }, { "epoch": 0.17408906882591094, "grad_norm": 0.49174062611580943, "learning_rate": 1.3870967741935486e-05, "loss": 0.7171, "step": 43 }, { "epoch": 0.17813765182186234, "grad_norm": 0.48307385145558285, "learning_rate": 1.4193548387096776e-05, "loss": 0.7272, "step": 44 }, { "epoch": 0.18218623481781376, "grad_norm": 0.49126044330626384, "learning_rate": 1.4516129032258066e-05, "loss": 0.702, "step": 45 }, { "epoch": 0.1862348178137652, "grad_norm": 0.5495594192446525, "learning_rate": 1.4838709677419357e-05, "loss": 0.7151, "step": 46 }, { "epoch": 0.1902834008097166, "grad_norm": 0.4733535183217129, "learning_rate": 1.5161290322580646e-05, "loss": 0.7106, "step": 47 }, { "epoch": 0.19433198380566802, "grad_norm": 0.5309937911798068, "learning_rate": 1.5483870967741936e-05, "loss": 0.6984, "step": 48 }, { "epoch": 0.19838056680161945, "grad_norm": 0.5522371559000459, "learning_rate": 1.5806451612903226e-05, "loss": 0.7061, "step": 49 }, { "epoch": 0.20242914979757085, "grad_norm": 0.49746366146218984, "learning_rate": 1.6129032258064517e-05, "loss": 0.6983, "step": 50 }, { "epoch": 0.20647773279352227, "grad_norm": 0.4827699545419963, "learning_rate": 1.6451612903225807e-05, "loss": 0.6873, "step": 51 }, { "epoch": 0.21052631578947367, "grad_norm": 0.5239046494909968, "learning_rate": 1.6774193548387098e-05, "loss": 0.6967, "step": 52 }, { "epoch": 0.2145748987854251, "grad_norm": 0.4744004656618616, "learning_rate": 1.7096774193548388e-05, "loss": 0.6953, "step": 53 }, { "epoch": 0.21862348178137653, "grad_norm": 0.5017999133135246, "learning_rate": 1.741935483870968e-05, "loss": 0.6958, "step": 54 }, { "epoch": 0.22267206477732793, "grad_norm": 0.5175322136516028, "learning_rate": 1.774193548387097e-05, "loss": 0.6781, "step": 55 }, { "epoch": 0.22672064777327935, "grad_norm": 0.6712720492848043, "learning_rate": 1.806451612903226e-05, "loss": 0.6852, "step": 56 }, { "epoch": 0.23076923076923078, "grad_norm": 0.6095643530479813, "learning_rate": 1.838709677419355e-05, "loss": 0.6968, "step": 57 }, { "epoch": 0.23481781376518218, "grad_norm": 0.7126697904082433, "learning_rate": 1.870967741935484e-05, "loss": 0.683, "step": 58 }, { "epoch": 0.2388663967611336, "grad_norm": 0.5833871350722787, "learning_rate": 1.903225806451613e-05, "loss": 0.6753, "step": 59 }, { "epoch": 0.242914979757085, "grad_norm": 0.5658989400633292, "learning_rate": 1.935483870967742e-05, "loss": 0.6764, "step": 60 }, { "epoch": 0.24696356275303644, "grad_norm": 0.5324515359045915, "learning_rate": 1.967741935483871e-05, "loss": 0.6728, "step": 61 }, { "epoch": 0.25101214574898784, "grad_norm": 0.46508555497347526, "learning_rate": 2e-05, "loss": 0.6755, "step": 62 }, { "epoch": 0.2550607287449393, "grad_norm": 0.5360021285603959, "learning_rate": 2.0322580645161292e-05, "loss": 0.6661, "step": 63 }, { "epoch": 0.2591093117408907, "grad_norm": 0.5318203056156215, "learning_rate": 2.0645161290322582e-05, "loss": 0.6853, "step": 64 }, { "epoch": 0.2631578947368421, "grad_norm": 0.5854726298515118, "learning_rate": 2.0967741935483873e-05, "loss": 0.6763, "step": 65 }, { "epoch": 0.26720647773279355, "grad_norm": 0.5752129841608264, "learning_rate": 2.1290322580645163e-05, "loss": 0.6629, "step": 66 }, { "epoch": 0.27125506072874495, "grad_norm": 0.7125733713796644, "learning_rate": 2.161290322580645e-05, "loss": 0.6682, "step": 67 }, { "epoch": 0.27530364372469635, "grad_norm": 0.9164341184072468, "learning_rate": 2.193548387096774e-05, "loss": 0.6714, "step": 68 }, { "epoch": 0.2793522267206478, "grad_norm": 0.9438379838240928, "learning_rate": 2.225806451612903e-05, "loss": 0.6862, "step": 69 }, { "epoch": 0.2834008097165992, "grad_norm": 1.039436800952271, "learning_rate": 2.2580645161290328e-05, "loss": 0.6653, "step": 70 }, { "epoch": 0.2874493927125506, "grad_norm": 0.7893182611461236, "learning_rate": 2.2903225806451615e-05, "loss": 0.676, "step": 71 }, { "epoch": 0.291497975708502, "grad_norm": 0.7534089550617806, "learning_rate": 2.3225806451612906e-05, "loss": 0.6473, "step": 72 }, { "epoch": 0.29554655870445345, "grad_norm": 1.3415013786346013, "learning_rate": 2.3548387096774196e-05, "loss": 0.676, "step": 73 }, { "epoch": 0.29959514170040485, "grad_norm": 0.6561981873833707, "learning_rate": 2.3870967741935486e-05, "loss": 0.6797, "step": 74 }, { "epoch": 0.30364372469635625, "grad_norm": 1.57182953060322, "learning_rate": 2.4193548387096777e-05, "loss": 0.6784, "step": 75 }, { "epoch": 0.3076923076923077, "grad_norm": 0.8908771990059763, "learning_rate": 2.4516129032258067e-05, "loss": 0.6592, "step": 76 }, { "epoch": 0.3117408906882591, "grad_norm": 1.0697072721766394, "learning_rate": 2.4838709677419358e-05, "loss": 0.6606, "step": 77 }, { "epoch": 0.3157894736842105, "grad_norm": 1.0377700913780186, "learning_rate": 2.5161290322580648e-05, "loss": 0.6629, "step": 78 }, { "epoch": 0.31983805668016196, "grad_norm": 0.9954165288052407, "learning_rate": 2.548387096774194e-05, "loss": 0.6784, "step": 79 }, { "epoch": 0.32388663967611336, "grad_norm": 1.3381690612664292, "learning_rate": 2.5806451612903226e-05, "loss": 0.6584, "step": 80 }, { "epoch": 0.32793522267206476, "grad_norm": 1.107247375125904, "learning_rate": 2.6129032258064516e-05, "loss": 0.6541, "step": 81 }, { "epoch": 0.3319838056680162, "grad_norm": 0.8353456393381341, "learning_rate": 2.6451612903225806e-05, "loss": 0.6495, "step": 82 }, { "epoch": 0.3360323886639676, "grad_norm": 0.8285148993614042, "learning_rate": 2.6774193548387097e-05, "loss": 0.6509, "step": 83 }, { "epoch": 0.340080971659919, "grad_norm": 1.4257998031074706, "learning_rate": 2.7096774193548387e-05, "loss": 0.6603, "step": 84 }, { "epoch": 0.3441295546558704, "grad_norm": 0.7167513227986504, "learning_rate": 2.7419354838709678e-05, "loss": 0.6651, "step": 85 }, { "epoch": 0.3481781376518219, "grad_norm": 1.4888664224772732, "learning_rate": 2.774193548387097e-05, "loss": 0.651, "step": 86 }, { "epoch": 0.3522267206477733, "grad_norm": 0.7887039566289111, "learning_rate": 2.8064516129032262e-05, "loss": 0.6644, "step": 87 }, { "epoch": 0.3562753036437247, "grad_norm": 1.482229511444836, "learning_rate": 2.8387096774193552e-05, "loss": 0.6613, "step": 88 }, { "epoch": 0.3603238866396761, "grad_norm": 0.9681091766917314, "learning_rate": 2.8709677419354843e-05, "loss": 0.6489, "step": 89 }, { "epoch": 0.3643724696356275, "grad_norm": 1.3520704417826008, "learning_rate": 2.9032258064516133e-05, "loss": 0.659, "step": 90 }, { "epoch": 0.3684210526315789, "grad_norm": 1.0300649874076813, "learning_rate": 2.9354838709677423e-05, "loss": 0.6545, "step": 91 }, { "epoch": 0.3724696356275304, "grad_norm": 1.3508427966212795, "learning_rate": 2.9677419354838714e-05, "loss": 0.6599, "step": 92 }, { "epoch": 0.3765182186234818, "grad_norm": 1.0825811649994344, "learning_rate": 3.0000000000000004e-05, "loss": 0.6674, "step": 93 }, { "epoch": 0.3805668016194332, "grad_norm": 1.2941095724653338, "learning_rate": 3.032258064516129e-05, "loss": 0.6599, "step": 94 }, { "epoch": 0.38461538461538464, "grad_norm": 1.1497800227555044, "learning_rate": 3.0645161290322585e-05, "loss": 0.6559, "step": 95 }, { "epoch": 0.38866396761133604, "grad_norm": 1.118956290965174, "learning_rate": 3.096774193548387e-05, "loss": 0.6561, "step": 96 }, { "epoch": 0.39271255060728744, "grad_norm": 1.0885621564330972, "learning_rate": 3.1290322580645166e-05, "loss": 0.6446, "step": 97 }, { "epoch": 0.3967611336032389, "grad_norm": 1.0738710313806181, "learning_rate": 3.161290322580645e-05, "loss": 0.6613, "step": 98 }, { "epoch": 0.4008097165991903, "grad_norm": 0.7996340302366259, "learning_rate": 3.193548387096774e-05, "loss": 0.6667, "step": 99 }, { "epoch": 0.4048582995951417, "grad_norm": 1.0124723227196577, "learning_rate": 3.2258064516129034e-05, "loss": 0.6549, "step": 100 }, { "epoch": 0.4089068825910931, "grad_norm": 1.2378178488068732, "learning_rate": 3.258064516129033e-05, "loss": 0.6474, "step": 101 }, { "epoch": 0.41295546558704455, "grad_norm": 1.149815896156196, "learning_rate": 3.2903225806451614e-05, "loss": 0.6606, "step": 102 }, { "epoch": 0.41700404858299595, "grad_norm": 1.1133355258004385, "learning_rate": 3.322580645161291e-05, "loss": 0.659, "step": 103 }, { "epoch": 0.42105263157894735, "grad_norm": 1.6058615311726785, "learning_rate": 3.3548387096774195e-05, "loss": 0.6724, "step": 104 }, { "epoch": 0.4251012145748988, "grad_norm": 0.7868441583741643, "learning_rate": 3.387096774193549e-05, "loss": 0.638, "step": 105 }, { "epoch": 0.4291497975708502, "grad_norm": 2.158645414656651, "learning_rate": 3.4193548387096776e-05, "loss": 0.6513, "step": 106 }, { "epoch": 0.4331983805668016, "grad_norm": 1.2547655023741182, "learning_rate": 3.451612903225807e-05, "loss": 0.6707, "step": 107 }, { "epoch": 0.43724696356275305, "grad_norm": 2.0300026325568257, "learning_rate": 3.483870967741936e-05, "loss": 0.6521, "step": 108 }, { "epoch": 0.44129554655870445, "grad_norm": 1.5839717977111025, "learning_rate": 3.516129032258065e-05, "loss": 0.646, "step": 109 }, { "epoch": 0.44534412955465585, "grad_norm": 1.7429700803649824, "learning_rate": 3.548387096774194e-05, "loss": 0.6597, "step": 110 }, { "epoch": 0.4493927125506073, "grad_norm": 1.1960990784916172, "learning_rate": 3.5806451612903225e-05, "loss": 0.6413, "step": 111 }, { "epoch": 0.4534412955465587, "grad_norm": 1.3417938505602396, "learning_rate": 3.612903225806452e-05, "loss": 0.6576, "step": 112 }, { "epoch": 0.4574898785425101, "grad_norm": 1.2463158896188358, "learning_rate": 3.6451612903225805e-05, "loss": 0.6397, "step": 113 }, { "epoch": 0.46153846153846156, "grad_norm": 1.1875440882779837, "learning_rate": 3.67741935483871e-05, "loss": 0.6638, "step": 114 }, { "epoch": 0.46558704453441296, "grad_norm": 1.0673340099350825, "learning_rate": 3.7096774193548386e-05, "loss": 0.6494, "step": 115 }, { "epoch": 0.46963562753036436, "grad_norm": 1.515739015115741, "learning_rate": 3.741935483870968e-05, "loss": 0.6562, "step": 116 }, { "epoch": 0.47368421052631576, "grad_norm": 1.1812276525805696, "learning_rate": 3.7741935483870974e-05, "loss": 0.6461, "step": 117 }, { "epoch": 0.4777327935222672, "grad_norm": 1.853814942506465, "learning_rate": 3.806451612903226e-05, "loss": 0.6605, "step": 118 }, { "epoch": 0.4817813765182186, "grad_norm": 1.4575231853733515, "learning_rate": 3.8387096774193555e-05, "loss": 0.6331, "step": 119 }, { "epoch": 0.48582995951417, "grad_norm": 1.8321536051165517, "learning_rate": 3.870967741935484e-05, "loss": 0.6371, "step": 120 }, { "epoch": 0.4898785425101215, "grad_norm": 1.7373565351689262, "learning_rate": 3.9032258064516135e-05, "loss": 0.6529, "step": 121 }, { "epoch": 0.4939271255060729, "grad_norm": 1.4709876205412298, "learning_rate": 3.935483870967742e-05, "loss": 0.639, "step": 122 }, { "epoch": 0.4979757085020243, "grad_norm": 1.2268838670816888, "learning_rate": 3.9677419354838716e-05, "loss": 0.6394, "step": 123 }, { "epoch": 0.5020242914979757, "grad_norm": 1.554072764760975, "learning_rate": 4e-05, "loss": 0.6448, "step": 124 }, { "epoch": 0.5060728744939271, "grad_norm": 1.236016538189751, "learning_rate": 3.9999920040266474e-05, "loss": 0.6525, "step": 125 }, { "epoch": 0.5101214574898786, "grad_norm": 1.413675558225995, "learning_rate": 3.999968016170525e-05, "loss": 0.6454, "step": 126 }, { "epoch": 0.5141700404858299, "grad_norm": 0.9343687654808603, "learning_rate": 3.9999280366234394e-05, "loss": 0.6284, "step": 127 }, { "epoch": 0.5182186234817814, "grad_norm": 1.3827329028666133, "learning_rate": 3.999872065705065e-05, "loss": 0.6276, "step": 128 }, { "epoch": 0.5222672064777328, "grad_norm": 0.8807067382925496, "learning_rate": 3.999800103862945e-05, "loss": 0.6357, "step": 129 }, { "epoch": 0.5263157894736842, "grad_norm": 1.3482435693371573, "learning_rate": 3.9997121516724834e-05, "loss": 0.6659, "step": 130 }, { "epoch": 0.5303643724696356, "grad_norm": 0.8866949555521896, "learning_rate": 3.999608209836944e-05, "loss": 0.6444, "step": 131 }, { "epoch": 0.5344129554655871, "grad_norm": 1.3363794417401984, "learning_rate": 3.999488279187443e-05, "loss": 0.6424, "step": 132 }, { "epoch": 0.5384615384615384, "grad_norm": 1.1828049077159473, "learning_rate": 3.9993523606829425e-05, "loss": 0.6415, "step": 133 }, { "epoch": 0.5425101214574899, "grad_norm": 1.1194046747244306, "learning_rate": 3.9992004554102435e-05, "loss": 0.6361, "step": 134 }, { "epoch": 0.5465587044534413, "grad_norm": 0.8959574976736537, "learning_rate": 3.999032564583976e-05, "loss": 0.6244, "step": 135 }, { "epoch": 0.5506072874493927, "grad_norm": 1.102512077027649, "learning_rate": 3.998848689546591e-05, "loss": 0.6314, "step": 136 }, { "epoch": 0.5546558704453441, "grad_norm": 1.0599618507886606, "learning_rate": 3.9986488317683496e-05, "loss": 0.6413, "step": 137 }, { "epoch": 0.5587044534412956, "grad_norm": 1.11791167705884, "learning_rate": 3.9984329928473067e-05, "loss": 0.6279, "step": 138 }, { "epoch": 0.562753036437247, "grad_norm": 0.8418677470871079, "learning_rate": 3.998201174509306e-05, "loss": 0.6375, "step": 139 }, { "epoch": 0.5668016194331984, "grad_norm": 0.9765774848765263, "learning_rate": 3.997953378607961e-05, "loss": 0.6401, "step": 140 }, { "epoch": 0.5708502024291497, "grad_norm": 1.0446839226194544, "learning_rate": 3.9976896071246403e-05, "loss": 0.6301, "step": 141 }, { "epoch": 0.5748987854251012, "grad_norm": 1.3266866466267044, "learning_rate": 3.997409862168454e-05, "loss": 0.6456, "step": 142 }, { "epoch": 0.5789473684210527, "grad_norm": 1.1341881496704944, "learning_rate": 3.997114145976237e-05, "loss": 0.6357, "step": 143 }, { "epoch": 0.582995951417004, "grad_norm": 0.9944387169576148, "learning_rate": 3.9968024609125245e-05, "loss": 0.6342, "step": 144 }, { "epoch": 0.5870445344129555, "grad_norm": 0.8742614285831564, "learning_rate": 3.996474809469545e-05, "loss": 0.64, "step": 145 }, { "epoch": 0.5910931174089069, "grad_norm": 0.7491548300448472, "learning_rate": 3.996131194267189e-05, "loss": 0.6369, "step": 146 }, { "epoch": 0.5951417004048583, "grad_norm": 0.639913130543383, "learning_rate": 3.995771618052995e-05, "loss": 0.64, "step": 147 }, { "epoch": 0.5991902834008097, "grad_norm": 0.7621562960398266, "learning_rate": 3.9953960837021256e-05, "loss": 0.632, "step": 148 }, { "epoch": 0.6032388663967612, "grad_norm": 0.7522833846449622, "learning_rate": 3.995004594217343e-05, "loss": 0.6318, "step": 149 }, { "epoch": 0.6072874493927125, "grad_norm": 0.7487484815285281, "learning_rate": 3.994597152728987e-05, "loss": 0.6398, "step": 150 }, { "epoch": 0.611336032388664, "grad_norm": 0.6114768197573321, "learning_rate": 3.994173762494947e-05, "loss": 0.6381, "step": 151 }, { "epoch": 0.6153846153846154, "grad_norm": 0.6327180772977419, "learning_rate": 3.9937344269006424e-05, "loss": 0.6304, "step": 152 }, { "epoch": 0.6194331983805668, "grad_norm": 0.8082456397355829, "learning_rate": 3.993279149458988e-05, "loss": 0.6286, "step": 153 }, { "epoch": 0.6234817813765182, "grad_norm": 1.1528889054329938, "learning_rate": 3.9928079338103695e-05, "loss": 0.6403, "step": 154 }, { "epoch": 0.6275303643724697, "grad_norm": 0.8277033078103596, "learning_rate": 3.992320783722616e-05, "loss": 0.6301, "step": 155 }, { "epoch": 0.631578947368421, "grad_norm": 0.7792475406227825, "learning_rate": 3.991817703090965e-05, "loss": 0.6364, "step": 156 }, { "epoch": 0.6356275303643725, "grad_norm": 0.6125210331204863, "learning_rate": 3.991298695938038e-05, "loss": 0.6168, "step": 157 }, { "epoch": 0.6396761133603239, "grad_norm": 0.7242864163419543, "learning_rate": 3.9907637664138e-05, "loss": 0.6325, "step": 158 }, { "epoch": 0.6437246963562753, "grad_norm": 0.7490849934032955, "learning_rate": 3.990212918795534e-05, "loss": 0.6252, "step": 159 }, { "epoch": 0.6477732793522267, "grad_norm": 0.7206106601351754, "learning_rate": 3.9896461574878036e-05, "loss": 0.6117, "step": 160 }, { "epoch": 0.6518218623481782, "grad_norm": 0.7722791552639757, "learning_rate": 3.989063487022416e-05, "loss": 0.6374, "step": 161 }, { "epoch": 0.6558704453441295, "grad_norm": 0.6616364303231328, "learning_rate": 3.9884649120583903e-05, "loss": 0.6308, "step": 162 }, { "epoch": 0.659919028340081, "grad_norm": 0.6235533236673955, "learning_rate": 3.987850437381915e-05, "loss": 0.6135, "step": 163 }, { "epoch": 0.6639676113360324, "grad_norm": 0.5873657438124675, "learning_rate": 3.987220067906313e-05, "loss": 0.629, "step": 164 }, { "epoch": 0.6680161943319838, "grad_norm": 0.678375298152664, "learning_rate": 3.986573808672002e-05, "loss": 0.6351, "step": 165 }, { "epoch": 0.6720647773279352, "grad_norm": 0.9390605565690515, "learning_rate": 3.9859116648464534e-05, "loss": 0.638, "step": 166 }, { "epoch": 0.6761133603238867, "grad_norm": 1.0022424198068496, "learning_rate": 3.985233641724152e-05, "loss": 0.6306, "step": 167 }, { "epoch": 0.680161943319838, "grad_norm": 0.848202026487848, "learning_rate": 3.984539744726554e-05, "loss": 0.6414, "step": 168 }, { "epoch": 0.6842105263157895, "grad_norm": 0.7585772103090916, "learning_rate": 3.983829979402038e-05, "loss": 0.6241, "step": 169 }, { "epoch": 0.6882591093117408, "grad_norm": 0.818713875049984, "learning_rate": 3.983104351425871e-05, "loss": 0.6283, "step": 170 }, { "epoch": 0.6923076923076923, "grad_norm": 0.6061991188146383, "learning_rate": 3.982362866600154e-05, "loss": 0.6188, "step": 171 }, { "epoch": 0.6963562753036437, "grad_norm": 0.65398098239242, "learning_rate": 3.9816055308537806e-05, "loss": 0.6352, "step": 172 }, { "epoch": 0.7004048582995951, "grad_norm": 0.6729520502188366, "learning_rate": 3.980832350242388e-05, "loss": 0.6268, "step": 173 }, { "epoch": 0.7044534412955465, "grad_norm": 0.9076807583040533, "learning_rate": 3.980043330948306e-05, "loss": 0.6204, "step": 174 }, { "epoch": 0.708502024291498, "grad_norm": 0.8696177637771678, "learning_rate": 3.9792384792805124e-05, "loss": 0.6226, "step": 175 }, { "epoch": 0.7125506072874493, "grad_norm": 0.5170543639888612, "learning_rate": 3.978417801674579e-05, "loss": 0.6235, "step": 176 }, { "epoch": 0.7165991902834008, "grad_norm": 0.7330543712258322, "learning_rate": 3.9775813046926244e-05, "loss": 0.6244, "step": 177 }, { "epoch": 0.7206477732793523, "grad_norm": 0.8130736969976474, "learning_rate": 3.976728995023254e-05, "loss": 0.6241, "step": 178 }, { "epoch": 0.7246963562753036, "grad_norm": 0.724682864465411, "learning_rate": 3.975860879481514e-05, "loss": 0.629, "step": 179 }, { "epoch": 0.728744939271255, "grad_norm": 0.5861171179861348, "learning_rate": 3.974976965008833e-05, "loss": 0.6259, "step": 180 }, { "epoch": 0.7327935222672065, "grad_norm": 0.5139256632749776, "learning_rate": 3.9740772586729674e-05, "loss": 0.6221, "step": 181 }, { "epoch": 0.7368421052631579, "grad_norm": 0.5682679727952463, "learning_rate": 3.973161767667946e-05, "loss": 0.6113, "step": 182 }, { "epoch": 0.7408906882591093, "grad_norm": 0.6015449589801147, "learning_rate": 3.972230499314009e-05, "loss": 0.6134, "step": 183 }, { "epoch": 0.7449392712550608, "grad_norm": 0.6619876608664359, "learning_rate": 3.9712834610575545e-05, "loss": 0.6087, "step": 184 }, { "epoch": 0.7489878542510121, "grad_norm": 0.6727014815532529, "learning_rate": 3.9703206604710746e-05, "loss": 0.6224, "step": 185 }, { "epoch": 0.7530364372469636, "grad_norm": 0.6603386485185269, "learning_rate": 3.969342105253098e-05, "loss": 0.6104, "step": 186 }, { "epoch": 0.757085020242915, "grad_norm": 0.6775137225918221, "learning_rate": 3.9683478032281246e-05, "loss": 0.6363, "step": 187 }, { "epoch": 0.7611336032388664, "grad_norm": 0.6030984225514586, "learning_rate": 3.967337762346568e-05, "loss": 0.6313, "step": 188 }, { "epoch": 0.7651821862348178, "grad_norm": 0.7551299737122794, "learning_rate": 3.9663119906846885e-05, "loss": 0.6341, "step": 189 }, { "epoch": 0.7692307692307693, "grad_norm": 0.9864913562370916, "learning_rate": 3.965270496444528e-05, "loss": 0.6243, "step": 190 }, { "epoch": 0.7732793522267206, "grad_norm": 0.6208477572848886, "learning_rate": 3.9642132879538465e-05, "loss": 0.6194, "step": 191 }, { "epoch": 0.7773279352226721, "grad_norm": 0.5699973046440563, "learning_rate": 3.9631403736660566e-05, "loss": 0.6195, "step": 192 }, { "epoch": 0.7813765182186235, "grad_norm": 0.7568039627236558, "learning_rate": 3.962051762160151e-05, "loss": 0.6241, "step": 193 }, { "epoch": 0.7854251012145749, "grad_norm": 0.6166892476247, "learning_rate": 3.960947462140638e-05, "loss": 0.624, "step": 194 }, { "epoch": 0.7894736842105263, "grad_norm": 0.4167789941110034, "learning_rate": 3.959827482437472e-05, "loss": 0.6215, "step": 195 }, { "epoch": 0.7935222672064778, "grad_norm": 0.6155949456762915, "learning_rate": 3.958691832005981e-05, "loss": 0.6098, "step": 196 }, { "epoch": 0.7975708502024291, "grad_norm": 0.6385662609122278, "learning_rate": 3.9575405199267944e-05, "loss": 0.6093, "step": 197 }, { "epoch": 0.8016194331983806, "grad_norm": 0.6241974649477146, "learning_rate": 3.956373555405774e-05, "loss": 0.6102, "step": 198 }, { "epoch": 0.805668016194332, "grad_norm": 0.6021092647771615, "learning_rate": 3.955190947773937e-05, "loss": 0.5987, "step": 199 }, { "epoch": 0.8097165991902834, "grad_norm": 0.520223597667846, "learning_rate": 3.9539927064873824e-05, "loss": 0.615, "step": 200 }, { "epoch": 0.8137651821862348, "grad_norm": 0.6258589150159297, "learning_rate": 3.952778841127214e-05, "loss": 0.6257, "step": 201 }, { "epoch": 0.8178137651821862, "grad_norm": 0.5784116649343984, "learning_rate": 3.95154936139947e-05, "loss": 0.617, "step": 202 }, { "epoch": 0.8218623481781376, "grad_norm": 0.5071754059189284, "learning_rate": 3.950304277135034e-05, "loss": 0.5975, "step": 203 }, { "epoch": 0.8259109311740891, "grad_norm": 0.6785192683791013, "learning_rate": 3.94904359828957e-05, "loss": 0.6122, "step": 204 }, { "epoch": 0.8299595141700404, "grad_norm": 0.7292904972100962, "learning_rate": 3.94776733494343e-05, "loss": 0.6039, "step": 205 }, { "epoch": 0.8340080971659919, "grad_norm": 0.6529894657216692, "learning_rate": 3.9464754973015826e-05, "loss": 0.6118, "step": 206 }, { "epoch": 0.8380566801619433, "grad_norm": 0.4975701369301112, "learning_rate": 3.9451680956935275e-05, "loss": 0.6298, "step": 207 }, { "epoch": 0.8421052631578947, "grad_norm": 0.585217197346017, "learning_rate": 3.943845140573213e-05, "loss": 0.62, "step": 208 }, { "epoch": 0.8461538461538461, "grad_norm": 0.7028388208438517, "learning_rate": 3.942506642518952e-05, "loss": 0.613, "step": 209 }, { "epoch": 0.8502024291497976, "grad_norm": 0.8259521935191466, "learning_rate": 3.9411526122333396e-05, "loss": 0.6133, "step": 210 }, { "epoch": 0.854251012145749, "grad_norm": 0.61910634034058, "learning_rate": 3.939783060543167e-05, "loss": 0.5998, "step": 211 }, { "epoch": 0.8582995951417004, "grad_norm": 0.5018498189825537, "learning_rate": 3.938397998399333e-05, "loss": 0.6068, "step": 212 }, { "epoch": 0.8623481781376519, "grad_norm": 0.5255409192769653, "learning_rate": 3.936997436876756e-05, "loss": 0.6023, "step": 213 }, { "epoch": 0.8663967611336032, "grad_norm": 0.6251059683976398, "learning_rate": 3.935581387174289e-05, "loss": 0.6119, "step": 214 }, { "epoch": 0.8704453441295547, "grad_norm": 0.5158147917541284, "learning_rate": 3.9341498606146295e-05, "loss": 0.6158, "step": 215 }, { "epoch": 0.8744939271255061, "grad_norm": 0.4484527438027624, "learning_rate": 3.932702868644224e-05, "loss": 0.6066, "step": 216 }, { "epoch": 0.8785425101214575, "grad_norm": 0.5550550085537298, "learning_rate": 3.931240422833181e-05, "loss": 0.6138, "step": 217 }, { "epoch": 0.8825910931174089, "grad_norm": 0.6647105286961182, "learning_rate": 3.9297625348751806e-05, "loss": 0.6189, "step": 218 }, { "epoch": 0.8866396761133604, "grad_norm": 0.6536327101140403, "learning_rate": 3.9282692165873744e-05, "loss": 0.6063, "step": 219 }, { "epoch": 0.8906882591093117, "grad_norm": 0.578212130602017, "learning_rate": 3.9267604799102945e-05, "loss": 0.6045, "step": 220 }, { "epoch": 0.8947368421052632, "grad_norm": 0.5522505733399578, "learning_rate": 3.9252363369077615e-05, "loss": 0.594, "step": 221 }, { "epoch": 0.8987854251012146, "grad_norm": 0.6114106386699563, "learning_rate": 3.9236967997667796e-05, "loss": 0.6002, "step": 222 }, { "epoch": 0.902834008097166, "grad_norm": 0.5887791979466925, "learning_rate": 3.9221418807974496e-05, "loss": 0.6146, "step": 223 }, { "epoch": 0.9068825910931174, "grad_norm": 0.5304819408714808, "learning_rate": 3.92057159243286e-05, "loss": 0.6155, "step": 224 }, { "epoch": 0.9109311740890689, "grad_norm": 0.48940080939838804, "learning_rate": 3.9189859472289956e-05, "loss": 0.6216, "step": 225 }, { "epoch": 0.9149797570850202, "grad_norm": 0.5427016610090085, "learning_rate": 3.9173849578646324e-05, "loss": 0.6202, "step": 226 }, { "epoch": 0.9190283400809717, "grad_norm": 0.5354270811037868, "learning_rate": 3.9157686371412395e-05, "loss": 0.6227, "step": 227 }, { "epoch": 0.9230769230769231, "grad_norm": 0.5712048029591726, "learning_rate": 3.914136997982874e-05, "loss": 0.6063, "step": 228 }, { "epoch": 0.9271255060728745, "grad_norm": 0.5994380899139953, "learning_rate": 3.912490053436079e-05, "loss": 0.6147, "step": 229 }, { "epoch": 0.9311740890688259, "grad_norm": 0.6031097888961449, "learning_rate": 3.9108278166697805e-05, "loss": 0.6205, "step": 230 }, { "epoch": 0.9352226720647774, "grad_norm": 0.7153558457045956, "learning_rate": 3.909150300975178e-05, "loss": 0.6044, "step": 231 }, { "epoch": 0.9392712550607287, "grad_norm": 0.6180823607079209, "learning_rate": 3.907457519765642e-05, "loss": 0.6224, "step": 232 }, { "epoch": 0.9433198380566802, "grad_norm": 0.6760955361781799, "learning_rate": 3.905749486576607e-05, "loss": 0.5942, "step": 233 }, { "epoch": 0.9473684210526315, "grad_norm": 0.6489062319729789, "learning_rate": 3.90402621506546e-05, "loss": 0.6111, "step": 234 }, { "epoch": 0.951417004048583, "grad_norm": 0.8029640361618223, "learning_rate": 3.902287719011435e-05, "loss": 0.6165, "step": 235 }, { "epoch": 0.9554655870445344, "grad_norm": 0.658389244151477, "learning_rate": 3.900534012315499e-05, "loss": 0.6218, "step": 236 }, { "epoch": 0.9595141700404858, "grad_norm": 0.5122343023683553, "learning_rate": 3.8987651090002454e-05, "loss": 0.6012, "step": 237 }, { "epoch": 0.9635627530364372, "grad_norm": 0.7221829381494153, "learning_rate": 3.896981023209777e-05, "loss": 0.5867, "step": 238 }, { "epoch": 0.9676113360323887, "grad_norm": 0.5405994686501947, "learning_rate": 3.8951817692095966e-05, "loss": 0.6145, "step": 239 }, { "epoch": 0.97165991902834, "grad_norm": 0.5434478291648694, "learning_rate": 3.893367361386491e-05, "loss": 0.6078, "step": 240 }, { "epoch": 0.9757085020242915, "grad_norm": 0.603325915886022, "learning_rate": 3.891537814248417e-05, "loss": 0.6152, "step": 241 }, { "epoch": 0.979757085020243, "grad_norm": 0.43054202691534843, "learning_rate": 3.889693142424384e-05, "loss": 0.6204, "step": 242 }, { "epoch": 0.9838056680161943, "grad_norm": 0.4865036975262847, "learning_rate": 3.8878333606643405e-05, "loss": 0.6036, "step": 243 }, { "epoch": 0.9878542510121457, "grad_norm": 0.5051467362193536, "learning_rate": 3.885958483839049e-05, "loss": 0.6146, "step": 244 }, { "epoch": 0.9919028340080972, "grad_norm": 0.4161617871530522, "learning_rate": 3.8840685269399786e-05, "loss": 0.6058, "step": 245 }, { "epoch": 0.9959514170040485, "grad_norm": 0.5015933065035297, "learning_rate": 3.882163505079171e-05, "loss": 0.625, "step": 246 }, { "epoch": 1.0, "grad_norm": 0.4894088957032897, "learning_rate": 3.880243433489132e-05, "loss": 0.6112, "step": 247 }, { "epoch": 1.0040485829959513, "grad_norm": 0.4136242323983045, "learning_rate": 3.878308327522702e-05, "loss": 0.5588, "step": 248 }, { "epoch": 1.008097165991903, "grad_norm": 0.4770855242090523, "learning_rate": 3.876358202652936e-05, "loss": 0.5559, "step": 249 }, { "epoch": 1.0121457489878543, "grad_norm": 0.4828834696301999, "learning_rate": 3.8743930744729835e-05, "loss": 0.5474, "step": 250 }, { "epoch": 1.0161943319838056, "grad_norm": 0.4648462941721393, "learning_rate": 3.8724129586959535e-05, "loss": 0.545, "step": 251 }, { "epoch": 1.0202429149797572, "grad_norm": 0.5296147135594446, "learning_rate": 3.870417871154801e-05, "loss": 0.5446, "step": 252 }, { "epoch": 1.0242914979757085, "grad_norm": 0.4567677321030925, "learning_rate": 3.868407827802192e-05, "loss": 0.5602, "step": 253 }, { "epoch": 1.0283400809716599, "grad_norm": 0.5215305139963706, "learning_rate": 3.8663828447103804e-05, "loss": 0.5561, "step": 254 }, { "epoch": 1.0323886639676114, "grad_norm": 0.5258932277406124, "learning_rate": 3.8643429380710765e-05, "loss": 0.5687, "step": 255 }, { "epoch": 1.0364372469635628, "grad_norm": 0.5925378209024165, "learning_rate": 3.862288124195319e-05, "loss": 0.5581, "step": 256 }, { "epoch": 1.040485829959514, "grad_norm": 0.5684963317025332, "learning_rate": 3.8602184195133464e-05, "loss": 0.5637, "step": 257 }, { "epoch": 1.0445344129554657, "grad_norm": 0.5111001428273252, "learning_rate": 3.8581338405744604e-05, "loss": 0.5489, "step": 258 }, { "epoch": 1.048582995951417, "grad_norm": 0.5476480438541614, "learning_rate": 3.8560344040468996e-05, "loss": 0.5554, "step": 259 }, { "epoch": 1.0526315789473684, "grad_norm": 0.5571655709356473, "learning_rate": 3.853920126717703e-05, "loss": 0.5496, "step": 260 }, { "epoch": 1.05668016194332, "grad_norm": 0.5159098525171174, "learning_rate": 3.851791025492574e-05, "loss": 0.5624, "step": 261 }, { "epoch": 1.0607287449392713, "grad_norm": 0.3756432221672389, "learning_rate": 3.8496471173957515e-05, "loss": 0.5607, "step": 262 }, { "epoch": 1.0647773279352226, "grad_norm": 0.4155359681478562, "learning_rate": 3.847488419569866e-05, "loss": 0.5622, "step": 263 }, { "epoch": 1.0688259109311742, "grad_norm": 0.4513719354850318, "learning_rate": 3.8453149492758077e-05, "loss": 0.5487, "step": 264 }, { "epoch": 1.0728744939271255, "grad_norm": 0.5186867223413585, "learning_rate": 3.8431267238925886e-05, "loss": 0.5652, "step": 265 }, { "epoch": 1.0769230769230769, "grad_norm": 0.42305662366867874, "learning_rate": 3.840923760917199e-05, "loss": 0.5538, "step": 266 }, { "epoch": 1.0809716599190284, "grad_norm": 0.4783089476853469, "learning_rate": 3.838706077964473e-05, "loss": 0.5596, "step": 267 }, { "epoch": 1.0850202429149798, "grad_norm": 0.45926446681027777, "learning_rate": 3.836473692766944e-05, "loss": 0.5465, "step": 268 }, { "epoch": 1.0890688259109311, "grad_norm": 0.4068288163789672, "learning_rate": 3.834226623174705e-05, "loss": 0.5369, "step": 269 }, { "epoch": 1.0931174089068827, "grad_norm": 0.42159226987746073, "learning_rate": 3.831964887155264e-05, "loss": 0.5525, "step": 270 }, { "epoch": 1.097165991902834, "grad_norm": 0.4583343646398631, "learning_rate": 3.829688502793403e-05, "loss": 0.539, "step": 271 }, { "epoch": 1.1012145748987854, "grad_norm": 0.49899029576368475, "learning_rate": 3.827397488291029e-05, "loss": 0.5494, "step": 272 }, { "epoch": 1.1052631578947367, "grad_norm": 0.4825154906680624, "learning_rate": 3.8250918619670343e-05, "loss": 0.538, "step": 273 }, { "epoch": 1.1093117408906883, "grad_norm": 0.5040995689405443, "learning_rate": 3.822771642257145e-05, "loss": 0.5617, "step": 274 }, { "epoch": 1.1133603238866396, "grad_norm": 0.5053998487833926, "learning_rate": 3.820436847713776e-05, "loss": 0.5477, "step": 275 }, { "epoch": 1.117408906882591, "grad_norm": 0.62917191556257, "learning_rate": 3.8180874970058826e-05, "loss": 0.5498, "step": 276 }, { "epoch": 1.1214574898785425, "grad_norm": 0.78811012063701, "learning_rate": 3.8157236089188103e-05, "loss": 0.5401, "step": 277 }, { "epoch": 1.125506072874494, "grad_norm": 0.5467413797295737, "learning_rate": 3.813345202354145e-05, "loss": 0.555, "step": 278 }, { "epoch": 1.1295546558704452, "grad_norm": 0.5069670370593699, "learning_rate": 3.810952296329563e-05, "loss": 0.5575, "step": 279 }, { "epoch": 1.1336032388663968, "grad_norm": 0.7001058223173838, "learning_rate": 3.808544909978676e-05, "loss": 0.5442, "step": 280 }, { "epoch": 1.1376518218623481, "grad_norm": 0.740151621504363, "learning_rate": 3.806123062550882e-05, "loss": 0.5469, "step": 281 }, { "epoch": 1.1417004048582995, "grad_norm": 0.6092512443866509, "learning_rate": 3.803686773411208e-05, "loss": 0.5693, "step": 282 }, { "epoch": 1.145748987854251, "grad_norm": 0.415796889156042, "learning_rate": 3.801236062040158e-05, "loss": 0.5428, "step": 283 }, { "epoch": 1.1497975708502024, "grad_norm": 0.5265735892627309, "learning_rate": 3.798770948033553e-05, "loss": 0.563, "step": 284 }, { "epoch": 1.1538461538461537, "grad_norm": 0.5277937455356484, "learning_rate": 3.796291451102381e-05, "loss": 0.5566, "step": 285 }, { "epoch": 1.1578947368421053, "grad_norm": 0.5563815924870609, "learning_rate": 3.793797591072631e-05, "loss": 0.5504, "step": 286 }, { "epoch": 1.1619433198380567, "grad_norm": 0.6434303105568608, "learning_rate": 3.791289387885144e-05, "loss": 0.5641, "step": 287 }, { "epoch": 1.165991902834008, "grad_norm": 0.4010368921628997, "learning_rate": 3.788766861595443e-05, "loss": 0.5618, "step": 288 }, { "epoch": 1.1700404858299596, "grad_norm": 0.5220310772496756, "learning_rate": 3.7862300323735835e-05, "loss": 0.5563, "step": 289 }, { "epoch": 1.174089068825911, "grad_norm": 0.44253377990643816, "learning_rate": 3.783678920503983e-05, "loss": 0.565, "step": 290 }, { "epoch": 1.1781376518218623, "grad_norm": 0.4896032824413573, "learning_rate": 3.781113546385265e-05, "loss": 0.5553, "step": 291 }, { "epoch": 1.1821862348178138, "grad_norm": 0.5040720989606134, "learning_rate": 3.7785339305300916e-05, "loss": 0.5625, "step": 292 }, { "epoch": 1.1862348178137652, "grad_norm": 0.5725255202034925, "learning_rate": 3.7759400935650025e-05, "loss": 0.5557, "step": 293 }, { "epoch": 1.1902834008097165, "grad_norm": 0.5039169334069039, "learning_rate": 3.77333205623025e-05, "loss": 0.5679, "step": 294 }, { "epoch": 1.194331983805668, "grad_norm": 0.4049597278432174, "learning_rate": 3.7707098393796295e-05, "loss": 0.5435, "step": 295 }, { "epoch": 1.1983805668016194, "grad_norm": 0.49966731220921884, "learning_rate": 3.7680734639803185e-05, "loss": 0.5405, "step": 296 }, { "epoch": 1.2024291497975708, "grad_norm": 0.44889463072173597, "learning_rate": 3.765422951112704e-05, "loss": 0.5482, "step": 297 }, { "epoch": 1.2064777327935223, "grad_norm": 0.47471954071771666, "learning_rate": 3.762758321970216e-05, "loss": 0.5388, "step": 298 }, { "epoch": 1.2105263157894737, "grad_norm": 0.4816883433123761, "learning_rate": 3.7600795978591584e-05, "loss": 0.5666, "step": 299 }, { "epoch": 1.214574898785425, "grad_norm": 0.45883614720092736, "learning_rate": 3.757386800198538e-05, "loss": 0.5453, "step": 300 }, { "epoch": 1.2186234817813766, "grad_norm": 0.5198274478714284, "learning_rate": 3.7546799505198925e-05, "loss": 0.5464, "step": 301 }, { "epoch": 1.222672064777328, "grad_norm": 0.5446338551692823, "learning_rate": 3.7519590704671197e-05, "loss": 0.5644, "step": 302 }, { "epoch": 1.2267206477732793, "grad_norm": 0.4996483786317483, "learning_rate": 3.749224181796305e-05, "loss": 0.5583, "step": 303 }, { "epoch": 1.2307692307692308, "grad_norm": 0.4766128695040993, "learning_rate": 3.746475306375545e-05, "loss": 0.5459, "step": 304 }, { "epoch": 1.2348178137651822, "grad_norm": 0.5117580671376967, "learning_rate": 3.743712466184774e-05, "loss": 0.5566, "step": 305 }, { "epoch": 1.2388663967611335, "grad_norm": 0.4519912230004407, "learning_rate": 3.7409356833155885e-05, "loss": 0.5347, "step": 306 }, { "epoch": 1.242914979757085, "grad_norm": 0.49053228495253837, "learning_rate": 3.73814497997107e-05, "loss": 0.562, "step": 307 }, { "epoch": 1.2469635627530364, "grad_norm": 0.5802661257464676, "learning_rate": 3.7353403784656095e-05, "loss": 0.5546, "step": 308 }, { "epoch": 1.2510121457489878, "grad_norm": 0.5562908921999705, "learning_rate": 3.732521901224724e-05, "loss": 0.5539, "step": 309 }, { "epoch": 1.2550607287449393, "grad_norm": 0.4965319819473251, "learning_rate": 3.7296895707848844e-05, "loss": 0.5583, "step": 310 }, { "epoch": 1.2591093117408907, "grad_norm": 0.576013779617948, "learning_rate": 3.7268434097933275e-05, "loss": 0.5439, "step": 311 }, { "epoch": 1.263157894736842, "grad_norm": 0.593598574080705, "learning_rate": 3.723983441007882e-05, "loss": 0.5536, "step": 312 }, { "epoch": 1.2672064777327936, "grad_norm": 0.5015754981274269, "learning_rate": 3.721109687296781e-05, "loss": 0.5572, "step": 313 }, { "epoch": 1.271255060728745, "grad_norm": 0.5338431447163761, "learning_rate": 3.718222171638484e-05, "loss": 0.5632, "step": 314 }, { "epoch": 1.2753036437246963, "grad_norm": 0.5193704994839577, "learning_rate": 3.715320917121488e-05, "loss": 0.5547, "step": 315 }, { "epoch": 1.2793522267206479, "grad_norm": 0.5086212756034518, "learning_rate": 3.712405946944149e-05, "loss": 0.5504, "step": 316 }, { "epoch": 1.2834008097165992, "grad_norm": 0.37648990576942676, "learning_rate": 3.709477284414488e-05, "loss": 0.5439, "step": 317 }, { "epoch": 1.2874493927125505, "grad_norm": 0.5007182822312584, "learning_rate": 3.7065349529500136e-05, "loss": 0.5511, "step": 318 }, { "epoch": 1.291497975708502, "grad_norm": 0.4085273336818686, "learning_rate": 3.7035789760775305e-05, "loss": 0.544, "step": 319 }, { "epoch": 1.2955465587044535, "grad_norm": 0.4650218207191389, "learning_rate": 3.70060937743295e-05, "loss": 0.5409, "step": 320 }, { "epoch": 1.2995951417004048, "grad_norm": 0.4151660957546068, "learning_rate": 3.6976261807611045e-05, "loss": 0.5566, "step": 321 }, { "epoch": 1.3036437246963564, "grad_norm": 0.39738589659168855, "learning_rate": 3.694629409915555e-05, "loss": 0.5582, "step": 322 }, { "epoch": 1.3076923076923077, "grad_norm": 0.4598329907763567, "learning_rate": 3.691619088858401e-05, "loss": 0.5609, "step": 323 }, { "epoch": 1.311740890688259, "grad_norm": 0.38843436035700474, "learning_rate": 3.68859524166009e-05, "loss": 0.5567, "step": 324 }, { "epoch": 1.3157894736842106, "grad_norm": 0.3924314816631673, "learning_rate": 3.6855578924992226e-05, "loss": 0.5597, "step": 325 }, { "epoch": 1.319838056680162, "grad_norm": 0.42736946908957896, "learning_rate": 3.6825070656623626e-05, "loss": 0.5473, "step": 326 }, { "epoch": 1.3238866396761133, "grad_norm": 0.43285807717728225, "learning_rate": 3.67944278554384e-05, "loss": 0.5663, "step": 327 }, { "epoch": 1.3279352226720649, "grad_norm": 0.4297901397997501, "learning_rate": 3.676365076645557e-05, "loss": 0.551, "step": 328 }, { "epoch": 1.3319838056680162, "grad_norm": 0.40459687070976696, "learning_rate": 3.673273963576791e-05, "loss": 0.541, "step": 329 }, { "epoch": 1.3360323886639676, "grad_norm": 0.40011115370114103, "learning_rate": 3.670169471054001e-05, "loss": 0.5607, "step": 330 }, { "epoch": 1.3400809716599191, "grad_norm": 0.45869717867521914, "learning_rate": 3.6670516239006254e-05, "loss": 0.5625, "step": 331 }, { "epoch": 1.3441295546558705, "grad_norm": 0.4007522293306284, "learning_rate": 3.663920447046888e-05, "loss": 0.564, "step": 332 }, { "epoch": 1.3481781376518218, "grad_norm": 0.485554821354389, "learning_rate": 3.6607759655295954e-05, "loss": 0.5478, "step": 333 }, { "epoch": 1.3522267206477734, "grad_norm": 0.4363638107506989, "learning_rate": 3.657618204491937e-05, "loss": 0.552, "step": 334 }, { "epoch": 1.3562753036437247, "grad_norm": 0.3447269077686771, "learning_rate": 3.6544471891832875e-05, "loss": 0.5599, "step": 335 }, { "epoch": 1.360323886639676, "grad_norm": 0.4277098098712849, "learning_rate": 3.6512629449589983e-05, "loss": 0.5677, "step": 336 }, { "epoch": 1.3643724696356276, "grad_norm": 0.41203616451442177, "learning_rate": 3.6480654972802045e-05, "loss": 0.5685, "step": 337 }, { "epoch": 1.368421052631579, "grad_norm": 0.39673309317029903, "learning_rate": 3.644854871713611e-05, "loss": 0.5499, "step": 338 }, { "epoch": 1.3724696356275303, "grad_norm": 0.4144404302973331, "learning_rate": 3.6416310939312924e-05, "loss": 0.553, "step": 339 }, { "epoch": 1.376518218623482, "grad_norm": 0.49298454817497034, "learning_rate": 3.638394189710493e-05, "loss": 0.5452, "step": 340 }, { "epoch": 1.3805668016194332, "grad_norm": 0.4700528359950587, "learning_rate": 3.635144184933412e-05, "loss": 0.5508, "step": 341 }, { "epoch": 1.3846153846153846, "grad_norm": 0.444377935004793, "learning_rate": 3.6318811055869994e-05, "loss": 0.5677, "step": 342 }, { "epoch": 1.3886639676113361, "grad_norm": 0.500263923435066, "learning_rate": 3.628604977762752e-05, "loss": 0.5352, "step": 343 }, { "epoch": 1.3927125506072875, "grad_norm": 0.3952420349412448, "learning_rate": 3.6253158276565004e-05, "loss": 0.5564, "step": 344 }, { "epoch": 1.3967611336032388, "grad_norm": 0.5487760115978857, "learning_rate": 3.6220136815682016e-05, "loss": 0.557, "step": 345 }, { "epoch": 1.4008097165991904, "grad_norm": 0.41452427794764807, "learning_rate": 3.618698565901727e-05, "loss": 0.57, "step": 346 }, { "epoch": 1.4048582995951417, "grad_norm": 0.38261676850452503, "learning_rate": 3.615370507164654e-05, "loss": 0.5502, "step": 347 }, { "epoch": 1.408906882591093, "grad_norm": 0.5138849133289172, "learning_rate": 3.61202953196805e-05, "loss": 0.5477, "step": 348 }, { "epoch": 1.4129554655870447, "grad_norm": 0.44996045669491125, "learning_rate": 3.6086756670262654e-05, "loss": 0.5438, "step": 349 }, { "epoch": 1.417004048582996, "grad_norm": 0.4572381264862759, "learning_rate": 3.6053089391567135e-05, "loss": 0.5555, "step": 350 }, { "epoch": 1.4210526315789473, "grad_norm": 0.4171427375919102, "learning_rate": 3.601929375279662e-05, "loss": 0.5559, "step": 351 }, { "epoch": 1.425101214574899, "grad_norm": 0.389536309672225, "learning_rate": 3.598537002418012e-05, "loss": 0.5409, "step": 352 }, { "epoch": 1.4291497975708503, "grad_norm": 0.3801900758503341, "learning_rate": 3.5951318476970885e-05, "loss": 0.5389, "step": 353 }, { "epoch": 1.4331983805668016, "grad_norm": 0.43288598242796456, "learning_rate": 3.591713938344416e-05, "loss": 0.5676, "step": 354 }, { "epoch": 1.4372469635627532, "grad_norm": 0.3818415482372027, "learning_rate": 3.588283301689507e-05, "loss": 0.5512, "step": 355 }, { "epoch": 1.4412955465587045, "grad_norm": 0.38218878708207904, "learning_rate": 3.5848399651636424e-05, "loss": 0.5397, "step": 356 }, { "epoch": 1.4453441295546559, "grad_norm": 0.4415639180952206, "learning_rate": 3.5813839562996473e-05, "loss": 0.5493, "step": 357 }, { "epoch": 1.4493927125506074, "grad_norm": 0.37403565546378936, "learning_rate": 3.5779153027316775e-05, "loss": 0.5593, "step": 358 }, { "epoch": 1.4534412955465588, "grad_norm": 0.36981978528880133, "learning_rate": 3.574434032194994e-05, "loss": 0.5549, "step": 359 }, { "epoch": 1.45748987854251, "grad_norm": 0.45528224035303516, "learning_rate": 3.5709401725257436e-05, "loss": 0.5469, "step": 360 }, { "epoch": 1.4615384615384617, "grad_norm": 0.4657370904570974, "learning_rate": 3.5674337516607346e-05, "loss": 0.5579, "step": 361 }, { "epoch": 1.465587044534413, "grad_norm": 0.46031856494791673, "learning_rate": 3.563914797637216e-05, "loss": 0.5568, "step": 362 }, { "epoch": 1.4696356275303644, "grad_norm": 0.3701267385619495, "learning_rate": 3.560383338592649e-05, "loss": 0.5646, "step": 363 }, { "epoch": 1.4736842105263157, "grad_norm": 0.5251803395483935, "learning_rate": 3.556839402764487e-05, "loss": 0.538, "step": 364 }, { "epoch": 1.4777327935222673, "grad_norm": 0.4393778608615084, "learning_rate": 3.553283018489946e-05, "loss": 0.5583, "step": 365 }, { "epoch": 1.4817813765182186, "grad_norm": 0.3668350354436685, "learning_rate": 3.54971421420578e-05, "loss": 0.5514, "step": 366 }, { "epoch": 1.48582995951417, "grad_norm": 0.47635736298371073, "learning_rate": 3.5461330184480524e-05, "loss": 0.5621, "step": 367 }, { "epoch": 1.4898785425101215, "grad_norm": 0.4137095018300083, "learning_rate": 3.54253945985191e-05, "loss": 0.5616, "step": 368 }, { "epoch": 1.4939271255060729, "grad_norm": 0.3901763640149011, "learning_rate": 3.5389335671513524e-05, "loss": 0.552, "step": 369 }, { "epoch": 1.4979757085020242, "grad_norm": 0.4202186253765791, "learning_rate": 3.5353153691789986e-05, "loss": 0.5443, "step": 370 }, { "epoch": 1.5020242914979756, "grad_norm": 0.4105358949305723, "learning_rate": 3.531684894865866e-05, "loss": 0.5455, "step": 371 }, { "epoch": 1.5060728744939271, "grad_norm": 0.4146127921714996, "learning_rate": 3.528042173241128e-05, "loss": 0.5462, "step": 372 }, { "epoch": 1.5101214574898787, "grad_norm": 0.3583715601345977, "learning_rate": 3.524387233431892e-05, "loss": 0.573, "step": 373 }, { "epoch": 1.5141700404858298, "grad_norm": 0.38951773722379807, "learning_rate": 3.520720104662958e-05, "loss": 0.5611, "step": 374 }, { "epoch": 1.5182186234817814, "grad_norm": 0.40978286581070744, "learning_rate": 3.5170408162565904e-05, "loss": 0.5431, "step": 375 }, { "epoch": 1.522267206477733, "grad_norm": 0.3940220036171082, "learning_rate": 3.513349397632281e-05, "loss": 0.55, "step": 376 }, { "epoch": 1.526315789473684, "grad_norm": 0.4222436721452989, "learning_rate": 3.5096458783065145e-05, "loss": 0.554, "step": 377 }, { "epoch": 1.5303643724696356, "grad_norm": 0.3289930760213392, "learning_rate": 3.505930287892533e-05, "loss": 0.5492, "step": 378 }, { "epoch": 1.5344129554655872, "grad_norm": 0.41844849797301914, "learning_rate": 3.502202656100099e-05, "loss": 0.5482, "step": 379 }, { "epoch": 1.5384615384615383, "grad_norm": 0.3443850683528698, "learning_rate": 3.498463012735256e-05, "loss": 0.5464, "step": 380 }, { "epoch": 1.54251012145749, "grad_norm": 0.3959988407640295, "learning_rate": 3.494711387700094e-05, "loss": 0.5456, "step": 381 }, { "epoch": 1.5465587044534415, "grad_norm": 0.4205061168550115, "learning_rate": 3.490947810992505e-05, "loss": 0.5578, "step": 382 }, { "epoch": 1.5506072874493926, "grad_norm": 0.3823600593407087, "learning_rate": 3.48717231270595e-05, "loss": 0.555, "step": 383 }, { "epoch": 1.5546558704453441, "grad_norm": 0.4413533099740041, "learning_rate": 3.483384923029211e-05, "loss": 0.5572, "step": 384 }, { "epoch": 1.5587044534412957, "grad_norm": 0.33322278364212643, "learning_rate": 3.479585672246156e-05, "loss": 0.5418, "step": 385 }, { "epoch": 1.5627530364372468, "grad_norm": 0.37454639255310085, "learning_rate": 3.4757745907354924e-05, "loss": 0.5574, "step": 386 }, { "epoch": 1.5668016194331984, "grad_norm": 0.38711155732758173, "learning_rate": 3.471951708970527e-05, "loss": 0.5402, "step": 387 }, { "epoch": 1.5708502024291497, "grad_norm": 0.37597734185373266, "learning_rate": 3.468117057518921e-05, "loss": 0.5376, "step": 388 }, { "epoch": 1.574898785425101, "grad_norm": 0.3756090513091634, "learning_rate": 3.4642706670424426e-05, "loss": 0.5421, "step": 389 }, { "epoch": 1.5789473684210527, "grad_norm": 0.3738385909485519, "learning_rate": 3.460412568296731e-05, "loss": 0.5476, "step": 390 }, { "epoch": 1.582995951417004, "grad_norm": 0.3909604794922382, "learning_rate": 3.456542792131039e-05, "loss": 0.5391, "step": 391 }, { "epoch": 1.5870445344129553, "grad_norm": 0.4373207572176005, "learning_rate": 3.4526613694879936e-05, "loss": 0.5595, "step": 392 }, { "epoch": 1.591093117408907, "grad_norm": 0.36183961971911155, "learning_rate": 3.448768331403348e-05, "loss": 0.5407, "step": 393 }, { "epoch": 1.5951417004048583, "grad_norm": 0.388903212724822, "learning_rate": 3.44486370900573e-05, "loss": 0.5492, "step": 394 }, { "epoch": 1.5991902834008096, "grad_norm": 0.38416767301508914, "learning_rate": 3.440947533516396e-05, "loss": 0.5516, "step": 395 }, { "epoch": 1.6032388663967612, "grad_norm": 0.44242716208122274, "learning_rate": 3.4370198362489816e-05, "loss": 0.5527, "step": 396 }, { "epoch": 1.6072874493927125, "grad_norm": 0.477691614293588, "learning_rate": 3.43308064860925e-05, "loss": 0.5595, "step": 397 }, { "epoch": 1.6113360323886639, "grad_norm": 0.5917982574045366, "learning_rate": 3.4291300020948393e-05, "loss": 0.5529, "step": 398 }, { "epoch": 1.6153846153846154, "grad_norm": 0.46184556801683274, "learning_rate": 3.425167928295015e-05, "loss": 0.5583, "step": 399 }, { "epoch": 1.6194331983805668, "grad_norm": 0.38346799978683066, "learning_rate": 3.421194458890411e-05, "loss": 0.5476, "step": 400 }, { "epoch": 1.623481781376518, "grad_norm": 0.4242180897441699, "learning_rate": 3.4172096256527865e-05, "loss": 0.5482, "step": 401 }, { "epoch": 1.6275303643724697, "grad_norm": 0.5212531688989838, "learning_rate": 3.4132134604447595e-05, "loss": 0.5561, "step": 402 }, { "epoch": 1.631578947368421, "grad_norm": 0.37352110929510685, "learning_rate": 3.409205995219561e-05, "loss": 0.5452, "step": 403 }, { "epoch": 1.6356275303643724, "grad_norm": 0.4543336257897698, "learning_rate": 3.4051872620207765e-05, "loss": 0.5428, "step": 404 }, { "epoch": 1.639676113360324, "grad_norm": 0.5820610799568545, "learning_rate": 3.40115729298209e-05, "loss": 0.5515, "step": 405 }, { "epoch": 1.6437246963562753, "grad_norm": 0.5275559447312682, "learning_rate": 3.397116120327025e-05, "loss": 0.5537, "step": 406 }, { "epoch": 1.6477732793522266, "grad_norm": 0.40521698154436475, "learning_rate": 3.3930637763686916e-05, "loss": 0.5486, "step": 407 }, { "epoch": 1.6518218623481782, "grad_norm": 0.6064837118610619, "learning_rate": 3.389000293509524e-05, "loss": 0.5514, "step": 408 }, { "epoch": 1.6558704453441295, "grad_norm": 0.5340369889680381, "learning_rate": 3.3849257042410225e-05, "loss": 0.5516, "step": 409 }, { "epoch": 1.6599190283400809, "grad_norm": 0.5049902221355212, "learning_rate": 3.380840041143494e-05, "loss": 0.5456, "step": 410 }, { "epoch": 1.6639676113360324, "grad_norm": 0.4278843822312111, "learning_rate": 3.376743336885792e-05, "loss": 0.5504, "step": 411 }, { "epoch": 1.6680161943319838, "grad_norm": 0.6009667400972722, "learning_rate": 3.372635624225055e-05, "loss": 0.5475, "step": 412 }, { "epoch": 1.6720647773279351, "grad_norm": 0.415553767215986, "learning_rate": 3.3685169360064445e-05, "loss": 0.5397, "step": 413 }, { "epoch": 1.6761133603238867, "grad_norm": 0.4932198269657775, "learning_rate": 3.3643873051628804e-05, "loss": 0.5459, "step": 414 }, { "epoch": 1.680161943319838, "grad_norm": 0.4504138865594964, "learning_rate": 3.3602467647147814e-05, "loss": 0.5608, "step": 415 }, { "epoch": 1.6842105263157894, "grad_norm": 0.35656992085349143, "learning_rate": 3.356095347769799e-05, "loss": 0.5531, "step": 416 }, { "epoch": 1.688259109311741, "grad_norm": 0.46204113341815295, "learning_rate": 3.351933087522552e-05, "loss": 0.5679, "step": 417 }, { "epoch": 1.6923076923076923, "grad_norm": 0.39326779356267355, "learning_rate": 3.3477600172543626e-05, "loss": 0.5404, "step": 418 }, { "epoch": 1.6963562753036436, "grad_norm": 0.3608951382540235, "learning_rate": 3.3435761703329894e-05, "loss": 0.5471, "step": 419 }, { "epoch": 1.7004048582995952, "grad_norm": 0.3106427449752925, "learning_rate": 3.3393815802123606e-05, "loss": 0.5523, "step": 420 }, { "epoch": 1.7044534412955465, "grad_norm": 0.35750187156818125, "learning_rate": 3.335176280432308e-05, "loss": 0.5523, "step": 421 }, { "epoch": 1.708502024291498, "grad_norm": 0.360040975758784, "learning_rate": 3.330960304618295e-05, "loss": 0.5304, "step": 422 }, { "epoch": 1.7125506072874495, "grad_norm": 0.38103967748448186, "learning_rate": 3.326733686481153e-05, "loss": 0.5516, "step": 423 }, { "epoch": 1.7165991902834008, "grad_norm": 0.3395734349368895, "learning_rate": 3.3224964598168084e-05, "loss": 0.5524, "step": 424 }, { "epoch": 1.7206477732793521, "grad_norm": 0.3512175881044695, "learning_rate": 3.318248658506012e-05, "loss": 0.5633, "step": 425 }, { "epoch": 1.7246963562753037, "grad_norm": 0.33843974991607023, "learning_rate": 3.313990316514069e-05, "loss": 0.5521, "step": 426 }, { "epoch": 1.728744939271255, "grad_norm": 0.30996743063581467, "learning_rate": 3.309721467890571e-05, "loss": 0.5461, "step": 427 }, { "epoch": 1.7327935222672064, "grad_norm": 0.37753182327993245, "learning_rate": 3.305442146769115e-05, "loss": 0.5624, "step": 428 }, { "epoch": 1.736842105263158, "grad_norm": 0.3114199285026566, "learning_rate": 3.30115238736704e-05, "loss": 0.5529, "step": 429 }, { "epoch": 1.7408906882591093, "grad_norm": 0.37001531844653396, "learning_rate": 3.296852223985148e-05, "loss": 0.5445, "step": 430 }, { "epoch": 1.7449392712550607, "grad_norm": 0.3107858791601823, "learning_rate": 3.2925416910074315e-05, "loss": 0.5358, "step": 431 }, { "epoch": 1.7489878542510122, "grad_norm": 0.3625215905855626, "learning_rate": 3.288220822900796e-05, "loss": 0.5448, "step": 432 }, { "epoch": 1.7530364372469636, "grad_norm": 0.35125193853146996, "learning_rate": 3.283889654214788e-05, "loss": 0.5349, "step": 433 }, { "epoch": 1.757085020242915, "grad_norm": 0.35409331629277857, "learning_rate": 3.279548219581317e-05, "loss": 0.5654, "step": 434 }, { "epoch": 1.7611336032388665, "grad_norm": 0.38791603292032617, "learning_rate": 3.275196553714379e-05, "loss": 0.5421, "step": 435 }, { "epoch": 1.7651821862348178, "grad_norm": 0.36608739255074996, "learning_rate": 3.270834691409778e-05, "loss": 0.5436, "step": 436 }, { "epoch": 1.7692307692307692, "grad_norm": 0.3910391891171895, "learning_rate": 3.266462667544849e-05, "loss": 0.5496, "step": 437 }, { "epoch": 1.7732793522267207, "grad_norm": 0.45522025469062205, "learning_rate": 3.262080517078178e-05, "loss": 0.5396, "step": 438 }, { "epoch": 1.777327935222672, "grad_norm": 0.4045696338454225, "learning_rate": 3.257688275049323e-05, "loss": 0.5416, "step": 439 }, { "epoch": 1.7813765182186234, "grad_norm": 0.48028213325713115, "learning_rate": 3.253285976578535e-05, "loss": 0.5571, "step": 440 }, { "epoch": 1.785425101214575, "grad_norm": 0.4184255204820569, "learning_rate": 3.2488736568664756e-05, "loss": 0.553, "step": 441 }, { "epoch": 1.7894736842105263, "grad_norm": 0.3749280813594411, "learning_rate": 3.244451351193935e-05, "loss": 0.5423, "step": 442 }, { "epoch": 1.7935222672064777, "grad_norm": 0.3468157835409962, "learning_rate": 3.240019094921551e-05, "loss": 0.5382, "step": 443 }, { "epoch": 1.7975708502024292, "grad_norm": 0.42457163076788346, "learning_rate": 3.235576923489527e-05, "loss": 0.5461, "step": 444 }, { "epoch": 1.8016194331983806, "grad_norm": 0.35652913164976974, "learning_rate": 3.2311248724173476e-05, "loss": 0.5429, "step": 445 }, { "epoch": 1.805668016194332, "grad_norm": 0.44815456848307916, "learning_rate": 3.226662977303494e-05, "loss": 0.5582, "step": 446 }, { "epoch": 1.8097165991902835, "grad_norm": 0.32351193408299017, "learning_rate": 3.2221912738251626e-05, "loss": 0.5616, "step": 447 }, { "epoch": 1.8137651821862348, "grad_norm": 0.3869934480824244, "learning_rate": 3.2177097977379736e-05, "loss": 0.5389, "step": 448 }, { "epoch": 1.8178137651821862, "grad_norm": 0.3393359564359591, "learning_rate": 3.21321858487569e-05, "loss": 0.5534, "step": 449 }, { "epoch": 1.8218623481781377, "grad_norm": 0.398800596494253, "learning_rate": 3.208717671149931e-05, "loss": 0.5362, "step": 450 }, { "epoch": 1.825910931174089, "grad_norm": 0.3635442306078888, "learning_rate": 3.204207092549882e-05, "loss": 0.5408, "step": 451 }, { "epoch": 1.8299595141700404, "grad_norm": 0.38647420111957936, "learning_rate": 3.19968688514201e-05, "loss": 0.5406, "step": 452 }, { "epoch": 1.834008097165992, "grad_norm": 0.38594798312368533, "learning_rate": 3.195157085069774e-05, "loss": 0.5427, "step": 453 }, { "epoch": 1.8380566801619433, "grad_norm": 0.3755205372877453, "learning_rate": 3.190617728553332e-05, "loss": 0.5456, "step": 454 }, { "epoch": 1.8421052631578947, "grad_norm": 0.3559345409500518, "learning_rate": 3.1860688518892606e-05, "loss": 0.5322, "step": 455 }, { "epoch": 1.8461538461538463, "grad_norm": 0.3687962579527369, "learning_rate": 3.181510491450254e-05, "loss": 0.5378, "step": 456 }, { "epoch": 1.8502024291497976, "grad_norm": 0.42898916413612137, "learning_rate": 3.176942683684842e-05, "loss": 0.5477, "step": 457 }, { "epoch": 1.854251012145749, "grad_norm": 0.3892752103378158, "learning_rate": 3.1723654651170934e-05, "loss": 0.5468, "step": 458 }, { "epoch": 1.8582995951417005, "grad_norm": 0.4036560511471313, "learning_rate": 3.167778872346327e-05, "loss": 0.5458, "step": 459 }, { "epoch": 1.8623481781376519, "grad_norm": 0.48115163336606254, "learning_rate": 3.163182942046815e-05, "loss": 0.5345, "step": 460 }, { "epoch": 1.8663967611336032, "grad_norm": 0.3091237832091826, "learning_rate": 3.158577710967494e-05, "loss": 0.5474, "step": 461 }, { "epoch": 1.8704453441295548, "grad_norm": 0.5198920028965661, "learning_rate": 3.153963215931669e-05, "loss": 0.5371, "step": 462 }, { "epoch": 1.874493927125506, "grad_norm": 0.6106324429409382, "learning_rate": 3.14933949383672e-05, "loss": 0.5475, "step": 463 }, { "epoch": 1.8785425101214575, "grad_norm": 0.46829929517084945, "learning_rate": 3.144706581653805e-05, "loss": 0.5552, "step": 464 }, { "epoch": 1.882591093117409, "grad_norm": 0.60044523687321, "learning_rate": 3.140064516427566e-05, "loss": 0.5493, "step": 465 }, { "epoch": 1.8866396761133604, "grad_norm": 0.38044232816290113, "learning_rate": 3.135413335275833e-05, "loss": 0.5393, "step": 466 }, { "epoch": 1.8906882591093117, "grad_norm": 0.5125508793634476, "learning_rate": 3.130753075389327e-05, "loss": 0.5488, "step": 467 }, { "epoch": 1.8947368421052633, "grad_norm": 0.3466184005208077, "learning_rate": 3.1260837740313625e-05, "loss": 0.5617, "step": 468 }, { "epoch": 1.8987854251012146, "grad_norm": 0.4391877003316788, "learning_rate": 3.121405468537547e-05, "loss": 0.5399, "step": 469 }, { "epoch": 1.902834008097166, "grad_norm": 0.3567773156323048, "learning_rate": 3.116718196315488e-05, "loss": 0.5384, "step": 470 }, { "epoch": 1.9068825910931175, "grad_norm": 0.4181255031513476, "learning_rate": 3.1120219948444894e-05, "loss": 0.5534, "step": 471 }, { "epoch": 1.9109311740890689, "grad_norm": 0.36530021953554803, "learning_rate": 3.107316901675252e-05, "loss": 0.5481, "step": 472 }, { "epoch": 1.9149797570850202, "grad_norm": 0.38154450778560345, "learning_rate": 3.1026029544295745e-05, "loss": 0.5487, "step": 473 }, { "epoch": 1.9190283400809718, "grad_norm": 0.35406148749346833, "learning_rate": 3.097880190800057e-05, "loss": 0.5491, "step": 474 }, { "epoch": 1.9230769230769231, "grad_norm": 0.37824962786392474, "learning_rate": 3.093148648549788e-05, "loss": 0.5507, "step": 475 }, { "epoch": 1.9271255060728745, "grad_norm": 0.29592005260638704, "learning_rate": 3.088408365512055e-05, "loss": 0.5387, "step": 476 }, { "epoch": 1.931174089068826, "grad_norm": 0.39461259920405684, "learning_rate": 3.083659379590034e-05, "loss": 0.5584, "step": 477 }, { "epoch": 1.9352226720647774, "grad_norm": 0.36222628647053634, "learning_rate": 3.0789017287564913e-05, "loss": 0.5536, "step": 478 }, { "epoch": 1.9392712550607287, "grad_norm": 0.3869510065505903, "learning_rate": 3.074135451053475e-05, "loss": 0.5585, "step": 479 }, { "epoch": 1.9433198380566803, "grad_norm": 0.350693351839758, "learning_rate": 3.069360584592015e-05, "loss": 0.5533, "step": 480 }, { "epoch": 1.9473684210526314, "grad_norm": 0.39960808047122337, "learning_rate": 3.064577167551816e-05, "loss": 0.545, "step": 481 }, { "epoch": 1.951417004048583, "grad_norm": 0.34050746379203206, "learning_rate": 3.059785238180953e-05, "loss": 0.561, "step": 482 }, { "epoch": 1.9554655870445345, "grad_norm": 0.398082621785747, "learning_rate": 3.054984834795566e-05, "loss": 0.546, "step": 483 }, { "epoch": 1.9595141700404857, "grad_norm": 0.3974379753843848, "learning_rate": 3.0501759957795537e-05, "loss": 0.5334, "step": 484 }, { "epoch": 1.9635627530364372, "grad_norm": 0.33736226794613594, "learning_rate": 3.0453587595842627e-05, "loss": 0.553, "step": 485 }, { "epoch": 1.9676113360323888, "grad_norm": 0.38381849242084237, "learning_rate": 3.0405331647281856e-05, "loss": 0.5482, "step": 486 }, { "epoch": 1.97165991902834, "grad_norm": 0.42234008578450255, "learning_rate": 3.0356992497966508e-05, "loss": 0.5442, "step": 487 }, { "epoch": 1.9757085020242915, "grad_norm": 0.34119948465295086, "learning_rate": 3.0308570534415137e-05, "loss": 0.5554, "step": 488 }, { "epoch": 1.979757085020243, "grad_norm": 0.44242804689889503, "learning_rate": 3.0260066143808467e-05, "loss": 0.5487, "step": 489 }, { "epoch": 1.9838056680161942, "grad_norm": 0.37092305750505256, "learning_rate": 3.021147971398632e-05, "loss": 0.5334, "step": 490 }, { "epoch": 1.9878542510121457, "grad_norm": 0.3769064542460475, "learning_rate": 3.0162811633444478e-05, "loss": 0.5476, "step": 491 }, { "epoch": 1.9919028340080973, "grad_norm": 0.5047422519565066, "learning_rate": 3.0114062291331635e-05, "loss": 0.5526, "step": 492 }, { "epoch": 1.9959514170040484, "grad_norm": 0.3680919184223388, "learning_rate": 3.0065232077446217e-05, "loss": 0.5398, "step": 493 }, { "epoch": 2.0, "grad_norm": 0.33410560719203675, "learning_rate": 3.001632138223332e-05, "loss": 0.5269, "step": 494 }, { "epoch": 2.0040485829959516, "grad_norm": 0.4869166262103096, "learning_rate": 2.9967330596781565e-05, "loss": 0.4699, "step": 495 }, { "epoch": 2.0080971659919027, "grad_norm": 0.569479781154693, "learning_rate": 2.9918260112819952e-05, "loss": 0.4735, "step": 496 }, { "epoch": 2.0121457489878543, "grad_norm": 0.4387772850096707, "learning_rate": 2.9869110322714778e-05, "loss": 0.4741, "step": 497 }, { "epoch": 2.016194331983806, "grad_norm": 0.4598192258229452, "learning_rate": 2.9819881619466447e-05, "loss": 0.4811, "step": 498 }, { "epoch": 2.020242914979757, "grad_norm": 0.6189327980253092, "learning_rate": 2.9770574396706364e-05, "loss": 0.4896, "step": 499 }, { "epoch": 2.0242914979757085, "grad_norm": 0.41398744291906087, "learning_rate": 2.972118904869376e-05, "loss": 0.4809, "step": 500 }, { "epoch": 2.02834008097166, "grad_norm": 0.564960475565481, "learning_rate": 2.9671725970312563e-05, "loss": 0.4771, "step": 501 }, { "epoch": 2.032388663967611, "grad_norm": 0.45783403789165256, "learning_rate": 2.9622185557068238e-05, "loss": 0.4744, "step": 502 }, { "epoch": 2.0364372469635628, "grad_norm": 0.41587836335433476, "learning_rate": 2.95725682050846e-05, "loss": 0.4742, "step": 503 }, { "epoch": 2.0404858299595143, "grad_norm": 0.4314083266419606, "learning_rate": 2.9522874311100684e-05, "loss": 0.4744, "step": 504 }, { "epoch": 2.0445344129554655, "grad_norm": 0.3529744386511963, "learning_rate": 2.9473104272467526e-05, "loss": 0.4773, "step": 505 }, { "epoch": 2.048582995951417, "grad_norm": 0.42194196414191726, "learning_rate": 2.942325848714505e-05, "loss": 0.4721, "step": 506 }, { "epoch": 2.0526315789473686, "grad_norm": 0.32458754197531636, "learning_rate": 2.9373337353698804e-05, "loss": 0.4833, "step": 507 }, { "epoch": 2.0566801619433197, "grad_norm": 0.4362348781473212, "learning_rate": 2.932334127129686e-05, "loss": 0.4691, "step": 508 }, { "epoch": 2.0607287449392713, "grad_norm": 0.3770429866694741, "learning_rate": 2.9273270639706547e-05, "loss": 0.462, "step": 509 }, { "epoch": 2.064777327935223, "grad_norm": 0.3630097644772169, "learning_rate": 2.922312585929131e-05, "loss": 0.4623, "step": 510 }, { "epoch": 2.068825910931174, "grad_norm": 0.39841248294558573, "learning_rate": 2.9172907331007478e-05, "loss": 0.4656, "step": 511 }, { "epoch": 2.0728744939271255, "grad_norm": 0.44871770844587927, "learning_rate": 2.9122615456401053e-05, "loss": 0.4836, "step": 512 }, { "epoch": 2.076923076923077, "grad_norm": 0.3441729012263812, "learning_rate": 2.9072250637604535e-05, "loss": 0.4631, "step": 513 }, { "epoch": 2.080971659919028, "grad_norm": 0.4076656097275203, "learning_rate": 2.9021813277333667e-05, "loss": 0.4773, "step": 514 }, { "epoch": 2.08502024291498, "grad_norm": 0.3724011054355104, "learning_rate": 2.8971303778884244e-05, "loss": 0.4724, "step": 515 }, { "epoch": 2.0890688259109313, "grad_norm": 0.3867841607366545, "learning_rate": 2.8920722546128863e-05, "loss": 0.468, "step": 516 }, { "epoch": 2.0931174089068825, "grad_norm": 0.3279608534043855, "learning_rate": 2.887006998351372e-05, "loss": 0.4605, "step": 517 }, { "epoch": 2.097165991902834, "grad_norm": 0.4504265611550235, "learning_rate": 2.881934649605535e-05, "loss": 0.4924, "step": 518 }, { "epoch": 2.1012145748987856, "grad_norm": 0.35880121877571863, "learning_rate": 2.8768552489337408e-05, "loss": 0.4799, "step": 519 }, { "epoch": 2.1052631578947367, "grad_norm": 0.30866285779507424, "learning_rate": 2.8717688369507425e-05, "loss": 0.461, "step": 520 }, { "epoch": 2.1093117408906883, "grad_norm": 0.41418588264375156, "learning_rate": 2.8666754543273535e-05, "loss": 0.4789, "step": 521 }, { "epoch": 2.11336032388664, "grad_norm": 0.3670666683486113, "learning_rate": 2.8615751417901273e-05, "loss": 0.4772, "step": 522 }, { "epoch": 2.117408906882591, "grad_norm": 0.32525443547906596, "learning_rate": 2.856467940121025e-05, "loss": 0.4826, "step": 523 }, { "epoch": 2.1214574898785425, "grad_norm": 0.364548384446213, "learning_rate": 2.8513538901570964e-05, "loss": 0.4668, "step": 524 }, { "epoch": 2.125506072874494, "grad_norm": 0.3279843768067789, "learning_rate": 2.846233032790149e-05, "loss": 0.4752, "step": 525 }, { "epoch": 2.1295546558704452, "grad_norm": 0.3556790753044936, "learning_rate": 2.84110540896642e-05, "loss": 0.4735, "step": 526 }, { "epoch": 2.133603238866397, "grad_norm": 0.3496782948234419, "learning_rate": 2.8359710596862555e-05, "loss": 0.4764, "step": 527 }, { "epoch": 2.1376518218623484, "grad_norm": 0.34097198258915545, "learning_rate": 2.8308300260037734e-05, "loss": 0.4578, "step": 528 }, { "epoch": 2.1417004048582995, "grad_norm": 0.32701992460434753, "learning_rate": 2.8256823490265424e-05, "loss": 0.4729, "step": 529 }, { "epoch": 2.145748987854251, "grad_norm": 0.324413738783009, "learning_rate": 2.8205280699152515e-05, "loss": 0.4728, "step": 530 }, { "epoch": 2.1497975708502026, "grad_norm": 0.37784957139145775, "learning_rate": 2.8153672298833777e-05, "loss": 0.4837, "step": 531 }, { "epoch": 2.1538461538461537, "grad_norm": 0.3654905167742029, "learning_rate": 2.8101998701968615e-05, "loss": 0.4699, "step": 532 }, { "epoch": 2.1578947368421053, "grad_norm": 0.3490370941506545, "learning_rate": 2.805026032173773e-05, "loss": 0.459, "step": 533 }, { "epoch": 2.161943319838057, "grad_norm": 0.4118109202844005, "learning_rate": 2.7998457571839832e-05, "loss": 0.4782, "step": 534 }, { "epoch": 2.165991902834008, "grad_norm": 0.3632227912921212, "learning_rate": 2.7946590866488322e-05, "loss": 0.4748, "step": 535 }, { "epoch": 2.1700404858299596, "grad_norm": 0.3807598203209906, "learning_rate": 2.7894660620408e-05, "loss": 0.4705, "step": 536 }, { "epoch": 2.174089068825911, "grad_norm": 0.4431389426287297, "learning_rate": 2.784266724883173e-05, "loss": 0.4843, "step": 537 }, { "epoch": 2.1781376518218623, "grad_norm": 0.3442880937085951, "learning_rate": 2.7790611167497128e-05, "loss": 0.4787, "step": 538 }, { "epoch": 2.182186234817814, "grad_norm": 0.3749103068496095, "learning_rate": 2.7738492792643224e-05, "loss": 0.4637, "step": 539 }, { "epoch": 2.1862348178137654, "grad_norm": 0.3547715531970823, "learning_rate": 2.768631254100716e-05, "loss": 0.4681, "step": 540 }, { "epoch": 2.1902834008097165, "grad_norm": 0.36982850612877927, "learning_rate": 2.7634070829820836e-05, "loss": 0.4815, "step": 541 }, { "epoch": 2.194331983805668, "grad_norm": 0.3626684978411283, "learning_rate": 2.7581768076807592e-05, "loss": 0.4575, "step": 542 }, { "epoch": 2.1983805668016196, "grad_norm": 0.3525166758428372, "learning_rate": 2.7529404700178832e-05, "loss": 0.4535, "step": 543 }, { "epoch": 2.2024291497975708, "grad_norm": 0.3705632486292503, "learning_rate": 2.7476981118630735e-05, "loss": 0.4745, "step": 544 }, { "epoch": 2.2064777327935223, "grad_norm": 0.3301278749167876, "learning_rate": 2.742449775134085e-05, "loss": 0.4721, "step": 545 }, { "epoch": 2.2105263157894735, "grad_norm": 0.32075206049285854, "learning_rate": 2.7371955017964788e-05, "loss": 0.4781, "step": 546 }, { "epoch": 2.214574898785425, "grad_norm": 0.37084015493787287, "learning_rate": 2.7319353338632845e-05, "loss": 0.4904, "step": 547 }, { "epoch": 2.2186234817813766, "grad_norm": 0.3296474458446154, "learning_rate": 2.7266693133946645e-05, "loss": 0.4818, "step": 548 }, { "epoch": 2.2226720647773277, "grad_norm": 0.3535234461363666, "learning_rate": 2.7213974824975785e-05, "loss": 0.474, "step": 549 }, { "epoch": 2.2267206477732793, "grad_norm": 0.35606700189401974, "learning_rate": 2.7161198833254464e-05, "loss": 0.4702, "step": 550 }, { "epoch": 2.230769230769231, "grad_norm": 0.3324225852693797, "learning_rate": 2.7108365580778095e-05, "loss": 0.4728, "step": 551 }, { "epoch": 2.234817813765182, "grad_norm": 1.3920239888253152, "learning_rate": 2.705547548999996e-05, "loss": 0.5439, "step": 552 }, { "epoch": 2.2388663967611335, "grad_norm": 0.5519776666976656, "learning_rate": 2.7002528983827817e-05, "loss": 0.4975, "step": 553 }, { "epoch": 2.242914979757085, "grad_norm": 0.43345890208713295, "learning_rate": 2.6949526485620517e-05, "loss": 0.4822, "step": 554 }, { "epoch": 2.246963562753036, "grad_norm": 0.3266371809345488, "learning_rate": 2.6896468419184623e-05, "loss": 0.4851, "step": 555 }, { "epoch": 2.251012145748988, "grad_norm": 0.3774842602839189, "learning_rate": 2.6843355208771024e-05, "loss": 0.4705, "step": 556 }, { "epoch": 2.2550607287449393, "grad_norm": 0.3680281226568418, "learning_rate": 2.6790187279071536e-05, "loss": 0.4685, "step": 557 }, { "epoch": 2.2591093117408905, "grad_norm": 0.3433831787404414, "learning_rate": 2.67369650552155e-05, "loss": 0.465, "step": 558 }, { "epoch": 2.263157894736842, "grad_norm": 0.37156849190148195, "learning_rate": 2.6683688962766407e-05, "loss": 0.4797, "step": 559 }, { "epoch": 2.2672064777327936, "grad_norm": 0.31388805693589394, "learning_rate": 2.6630359427718468e-05, "loss": 0.4867, "step": 560 }, { "epoch": 2.2712550607287447, "grad_norm": 0.3711095053743293, "learning_rate": 2.6576976876493225e-05, "loss": 0.4925, "step": 561 }, { "epoch": 2.2753036437246963, "grad_norm": 0.3276191766869072, "learning_rate": 2.652354173593614e-05, "loss": 0.4587, "step": 562 }, { "epoch": 2.279352226720648, "grad_norm": 0.35565282147576693, "learning_rate": 2.647005443331317e-05, "loss": 0.4755, "step": 563 }, { "epoch": 2.283400809716599, "grad_norm": 0.3069374224880348, "learning_rate": 2.6416515396307354e-05, "loss": 0.4893, "step": 564 }, { "epoch": 2.2874493927125505, "grad_norm": 0.3977865425694921, "learning_rate": 2.636292505301542e-05, "loss": 0.4877, "step": 565 }, { "epoch": 2.291497975708502, "grad_norm": 0.31808706316731455, "learning_rate": 2.630928383194431e-05, "loss": 0.4744, "step": 566 }, { "epoch": 2.2955465587044532, "grad_norm": 0.36562327772878744, "learning_rate": 2.625559216200781e-05, "loss": 0.4825, "step": 567 }, { "epoch": 2.299595141700405, "grad_norm": 0.2884455916106593, "learning_rate": 2.620185047252308e-05, "loss": 0.4763, "step": 568 }, { "epoch": 2.3036437246963564, "grad_norm": 0.33553458474636977, "learning_rate": 2.614805919320723e-05, "loss": 0.4683, "step": 569 }, { "epoch": 2.3076923076923075, "grad_norm": 0.3061666533524434, "learning_rate": 2.6094218754173895e-05, "loss": 0.4696, "step": 570 }, { "epoch": 2.311740890688259, "grad_norm": 0.3646620315315709, "learning_rate": 2.60403295859298e-05, "loss": 0.4673, "step": 571 }, { "epoch": 2.3157894736842106, "grad_norm": 0.31160091018919933, "learning_rate": 2.5986392119371297e-05, "loss": 0.474, "step": 572 }, { "epoch": 2.3198380566801617, "grad_norm": 0.380540719602795, "learning_rate": 2.5932406785780928e-05, "loss": 0.4736, "step": 573 }, { "epoch": 2.3238866396761133, "grad_norm": 0.3066185770906116, "learning_rate": 2.5878374016823987e-05, "loss": 0.4714, "step": 574 }, { "epoch": 2.327935222672065, "grad_norm": 0.40832750947771446, "learning_rate": 2.5824294244545045e-05, "loss": 0.4837, "step": 575 }, { "epoch": 2.331983805668016, "grad_norm": 0.32714359953714417, "learning_rate": 2.577016790136453e-05, "loss": 0.4846, "step": 576 }, { "epoch": 2.3360323886639676, "grad_norm": 0.3243444840434671, "learning_rate": 2.5715995420075225e-05, "loss": 0.4873, "step": 577 }, { "epoch": 2.340080971659919, "grad_norm": 0.33844206534486443, "learning_rate": 2.5661777233838864e-05, "loss": 0.471, "step": 578 }, { "epoch": 2.3441295546558703, "grad_norm": 0.3346018557823487, "learning_rate": 2.5607513776182616e-05, "loss": 0.4873, "step": 579 }, { "epoch": 2.348178137651822, "grad_norm": 0.33933171907240023, "learning_rate": 2.5553205480995633e-05, "loss": 0.4682, "step": 580 }, { "epoch": 2.3522267206477734, "grad_norm": 0.3294490737907595, "learning_rate": 2.5498852782525604e-05, "loss": 0.4862, "step": 581 }, { "epoch": 2.3562753036437245, "grad_norm": 0.3197511465927068, "learning_rate": 2.5444456115375252e-05, "loss": 0.4857, "step": 582 }, { "epoch": 2.360323886639676, "grad_norm": 0.3607399566158029, "learning_rate": 2.539001591449889e-05, "loss": 0.4783, "step": 583 }, { "epoch": 2.3643724696356276, "grad_norm": 0.2929349719120113, "learning_rate": 2.53355326151989e-05, "loss": 0.4714, "step": 584 }, { "epoch": 2.3684210526315788, "grad_norm": 0.3267491320327216, "learning_rate": 2.5281006653122288e-05, "loss": 0.4757, "step": 585 }, { "epoch": 2.3724696356275303, "grad_norm": 0.33988351130418204, "learning_rate": 2.5226438464257217e-05, "loss": 0.4876, "step": 586 }, { "epoch": 2.376518218623482, "grad_norm": 0.2667865767341829, "learning_rate": 2.5171828484929447e-05, "loss": 0.4872, "step": 587 }, { "epoch": 2.380566801619433, "grad_norm": 0.2957829949484941, "learning_rate": 2.5117177151798934e-05, "loss": 0.4749, "step": 588 }, { "epoch": 2.3846153846153846, "grad_norm": 0.30689848995582747, "learning_rate": 2.506248490185627e-05, "loss": 0.4655, "step": 589 }, { "epoch": 2.388663967611336, "grad_norm": 0.29895265634972934, "learning_rate": 2.500775217241923e-05, "loss": 0.4835, "step": 590 }, { "epoch": 2.3927125506072873, "grad_norm": 0.3305706245316812, "learning_rate": 2.4952979401129266e-05, "loss": 0.4759, "step": 591 }, { "epoch": 2.396761133603239, "grad_norm": 0.32214505720136943, "learning_rate": 2.4898167025948e-05, "loss": 0.4704, "step": 592 }, { "epoch": 2.4008097165991904, "grad_norm": 0.2985962828767287, "learning_rate": 2.4843315485153703e-05, "loss": 0.4786, "step": 593 }, { "epoch": 2.4048582995951415, "grad_norm": 0.28910428746356726, "learning_rate": 2.4788425217337856e-05, "loss": 0.4724, "step": 594 }, { "epoch": 2.408906882591093, "grad_norm": 0.2897940673635523, "learning_rate": 2.4733496661401572e-05, "loss": 0.4858, "step": 595 }, { "epoch": 2.4129554655870447, "grad_norm": 0.33903651851132294, "learning_rate": 2.4678530256552114e-05, "loss": 0.4825, "step": 596 }, { "epoch": 2.417004048582996, "grad_norm": 0.3521503485041243, "learning_rate": 2.46235264422994e-05, "loss": 0.4798, "step": 597 }, { "epoch": 2.4210526315789473, "grad_norm": 0.32127493524145645, "learning_rate": 2.4568485658452452e-05, "loss": 0.486, "step": 598 }, { "epoch": 2.425101214574899, "grad_norm": 0.39000765920839126, "learning_rate": 2.451340834511592e-05, "loss": 0.4884, "step": 599 }, { "epoch": 2.42914979757085, "grad_norm": 0.3339288514169548, "learning_rate": 2.4458294942686528e-05, "loss": 0.4814, "step": 600 }, { "epoch": 2.4331983805668016, "grad_norm": 0.34264497279341205, "learning_rate": 2.440314589184958e-05, "loss": 0.4786, "step": 601 }, { "epoch": 2.437246963562753, "grad_norm": 0.3468404858143123, "learning_rate": 2.434796163357541e-05, "loss": 0.4753, "step": 602 }, { "epoch": 2.4412955465587043, "grad_norm": 0.3278089134234505, "learning_rate": 2.429274260911588e-05, "loss": 0.4675, "step": 603 }, { "epoch": 2.445344129554656, "grad_norm": 0.3263041100720379, "learning_rate": 2.423748926000084e-05, "loss": 0.4878, "step": 604 }, { "epoch": 2.4493927125506074, "grad_norm": 0.29905751871566927, "learning_rate": 2.418220202803459e-05, "loss": 0.4807, "step": 605 }, { "epoch": 2.4534412955465585, "grad_norm": 0.3237934702125469, "learning_rate": 2.412688135529237e-05, "loss": 0.4712, "step": 606 }, { "epoch": 2.45748987854251, "grad_norm": 0.31548884066561833, "learning_rate": 2.4071527684116807e-05, "loss": 0.4806, "step": 607 }, { "epoch": 2.4615384615384617, "grad_norm": 0.32768325790789393, "learning_rate": 2.4016141457114372e-05, "loss": 0.4857, "step": 608 }, { "epoch": 2.465587044534413, "grad_norm": 0.3117071963535657, "learning_rate": 2.396072311715187e-05, "loss": 0.4748, "step": 609 }, { "epoch": 2.4696356275303644, "grad_norm": 0.2972590009022893, "learning_rate": 2.3905273107352863e-05, "loss": 0.4795, "step": 610 }, { "epoch": 2.473684210526316, "grad_norm": 0.346434921776769, "learning_rate": 2.3849791871094157e-05, "loss": 0.4874, "step": 611 }, { "epoch": 2.477732793522267, "grad_norm": 0.29452493053790235, "learning_rate": 2.379427985200223e-05, "loss": 0.4743, "step": 612 }, { "epoch": 2.4817813765182186, "grad_norm": 0.3141032978538841, "learning_rate": 2.373873749394972e-05, "loss": 0.4797, "step": 613 }, { "epoch": 2.48582995951417, "grad_norm": 0.31836380628953004, "learning_rate": 2.3683165241051836e-05, "loss": 0.4692, "step": 614 }, { "epoch": 2.4898785425101213, "grad_norm": 0.29314486771185067, "learning_rate": 2.3627563537662823e-05, "loss": 0.4844, "step": 615 }, { "epoch": 2.493927125506073, "grad_norm": 0.35329085232025664, "learning_rate": 2.3571932828372433e-05, "loss": 0.4711, "step": 616 }, { "epoch": 2.4979757085020244, "grad_norm": 0.3204158246315188, "learning_rate": 2.351627355800233e-05, "loss": 0.476, "step": 617 }, { "epoch": 2.5020242914979756, "grad_norm": 0.3355553179309538, "learning_rate": 2.346058617160256e-05, "loss": 0.473, "step": 618 }, { "epoch": 2.506072874493927, "grad_norm": 0.3047836463357802, "learning_rate": 2.3404871114447976e-05, "loss": 0.4819, "step": 619 }, { "epoch": 2.5101214574898787, "grad_norm": 0.3348659434024021, "learning_rate": 2.334912883203469e-05, "loss": 0.4711, "step": 620 }, { "epoch": 2.51417004048583, "grad_norm": 0.34333020275203624, "learning_rate": 2.3293359770076505e-05, "loss": 0.4857, "step": 621 }, { "epoch": 2.5182186234817814, "grad_norm": 0.3145116528752168, "learning_rate": 2.323756437450136e-05, "loss": 0.4803, "step": 622 }, { "epoch": 2.522267206477733, "grad_norm": 0.30758109462396244, "learning_rate": 2.3181743091447754e-05, "loss": 0.4758, "step": 623 }, { "epoch": 2.526315789473684, "grad_norm": 0.2957319841151819, "learning_rate": 2.3125896367261164e-05, "loss": 0.491, "step": 624 }, { "epoch": 2.5303643724696356, "grad_norm": 0.31994722181579766, "learning_rate": 2.307002464849052e-05, "loss": 0.4779, "step": 625 }, { "epoch": 2.534412955465587, "grad_norm": 0.4076397681452605, "learning_rate": 2.30141283818846e-05, "loss": 0.4588, "step": 626 }, { "epoch": 2.5384615384615383, "grad_norm": 0.2854105147751223, "learning_rate": 2.2958208014388462e-05, "loss": 0.4767, "step": 627 }, { "epoch": 2.54251012145749, "grad_norm": 0.38595797307416, "learning_rate": 2.2902263993139857e-05, "loss": 0.4722, "step": 628 }, { "epoch": 2.5465587044534415, "grad_norm": 0.3366810569829151, "learning_rate": 2.2846296765465708e-05, "loss": 0.4743, "step": 629 }, { "epoch": 2.5506072874493926, "grad_norm": 0.4404479320570098, "learning_rate": 2.2790306778878465e-05, "loss": 0.4833, "step": 630 }, { "epoch": 2.554655870445344, "grad_norm": 0.3663063651791089, "learning_rate": 2.273429448107257e-05, "loss": 0.4831, "step": 631 }, { "epoch": 2.5587044534412957, "grad_norm": 0.34845604778261147, "learning_rate": 2.2678260319920868e-05, "loss": 0.4819, "step": 632 }, { "epoch": 2.562753036437247, "grad_norm": 0.3406750827732109, "learning_rate": 2.262220474347102e-05, "loss": 0.4792, "step": 633 }, { "epoch": 2.5668016194331984, "grad_norm": 0.2885342758080591, "learning_rate": 2.2566128199941918e-05, "loss": 0.4777, "step": 634 }, { "epoch": 2.57085020242915, "grad_norm": 0.3594938249486972, "learning_rate": 2.2510031137720104e-05, "loss": 0.4847, "step": 635 }, { "epoch": 2.574898785425101, "grad_norm": 0.3030077728949297, "learning_rate": 2.2453914005356206e-05, "loss": 0.4768, "step": 636 }, { "epoch": 2.5789473684210527, "grad_norm": 0.29403357313000006, "learning_rate": 2.2397777251561302e-05, "loss": 0.4751, "step": 637 }, { "epoch": 2.582995951417004, "grad_norm": 0.34006130938195006, "learning_rate": 2.2341621325203393e-05, "loss": 0.4799, "step": 638 }, { "epoch": 2.5870445344129553, "grad_norm": 0.3341343950522912, "learning_rate": 2.2285446675303764e-05, "loss": 0.4861, "step": 639 }, { "epoch": 2.591093117408907, "grad_norm": 0.36008910450910775, "learning_rate": 2.2229253751033423e-05, "loss": 0.4705, "step": 640 }, { "epoch": 2.5951417004048585, "grad_norm": 0.350334456981212, "learning_rate": 2.2173043001709492e-05, "loss": 0.4827, "step": 641 }, { "epoch": 2.5991902834008096, "grad_norm": 0.3142314270935604, "learning_rate": 2.2116814876791627e-05, "loss": 0.4794, "step": 642 }, { "epoch": 2.603238866396761, "grad_norm": 0.35562262868636485, "learning_rate": 2.2060569825878413e-05, "loss": 0.4799, "step": 643 }, { "epoch": 2.6072874493927127, "grad_norm": 0.3293370270892062, "learning_rate": 2.2004308298703777e-05, "loss": 0.4635, "step": 644 }, { "epoch": 2.611336032388664, "grad_norm": 0.3614949993327776, "learning_rate": 2.1948030745133396e-05, "loss": 0.4736, "step": 645 }, { "epoch": 2.6153846153846154, "grad_norm": 0.34087099716834274, "learning_rate": 2.1891737615161083e-05, "loss": 0.4691, "step": 646 }, { "epoch": 2.619433198380567, "grad_norm": 0.35863339937631183, "learning_rate": 2.1835429358905218e-05, "loss": 0.4744, "step": 647 }, { "epoch": 2.623481781376518, "grad_norm": 0.3422451781596549, "learning_rate": 2.17791064266051e-05, "loss": 0.4746, "step": 648 }, { "epoch": 2.6275303643724697, "grad_norm": 0.3727906014115159, "learning_rate": 2.172276926861741e-05, "loss": 0.4715, "step": 649 }, { "epoch": 2.6315789473684212, "grad_norm": 0.31215377903823344, "learning_rate": 2.166641833541255e-05, "loss": 0.4776, "step": 650 }, { "epoch": 2.6356275303643724, "grad_norm": 0.3892318098736922, "learning_rate": 2.161005407757109e-05, "loss": 0.4806, "step": 651 }, { "epoch": 2.639676113360324, "grad_norm": 0.276233622528974, "learning_rate": 2.155367694578013e-05, "loss": 0.4807, "step": 652 }, { "epoch": 2.6437246963562755, "grad_norm": 0.37844022652486164, "learning_rate": 2.1497287390829712e-05, "loss": 0.4797, "step": 653 }, { "epoch": 2.6477732793522266, "grad_norm": 0.31748589439086006, "learning_rate": 2.1440885863609208e-05, "loss": 0.483, "step": 654 }, { "epoch": 2.651821862348178, "grad_norm": 0.4112370244594115, "learning_rate": 2.1384472815103737e-05, "loss": 0.486, "step": 655 }, { "epoch": 2.6558704453441297, "grad_norm": 0.3311824303279343, "learning_rate": 2.1328048696390534e-05, "loss": 0.4661, "step": 656 }, { "epoch": 2.659919028340081, "grad_norm": 0.4185567336882972, "learning_rate": 2.1271613958635342e-05, "loss": 0.4857, "step": 657 }, { "epoch": 2.6639676113360324, "grad_norm": 0.30045513022822296, "learning_rate": 2.1215169053088825e-05, "loss": 0.4794, "step": 658 }, { "epoch": 2.668016194331984, "grad_norm": 0.40035495810139504, "learning_rate": 2.1158714431082937e-05, "loss": 0.4779, "step": 659 }, { "epoch": 2.672064777327935, "grad_norm": 0.3092024792000004, "learning_rate": 2.110225054402733e-05, "loss": 0.4875, "step": 660 }, { "epoch": 2.6761133603238867, "grad_norm": 0.33897278923953816, "learning_rate": 2.1045777843405747e-05, "loss": 0.4685, "step": 661 }, { "epoch": 2.6801619433198383, "grad_norm": 0.29574371294037527, "learning_rate": 2.09892967807724e-05, "loss": 0.4682, "step": 662 }, { "epoch": 2.6842105263157894, "grad_norm": 0.3397643562993694, "learning_rate": 2.093280780774835e-05, "loss": 0.4755, "step": 663 }, { "epoch": 2.688259109311741, "grad_norm": 0.26971178505515087, "learning_rate": 2.087631137601793e-05, "loss": 0.4889, "step": 664 }, { "epoch": 2.6923076923076925, "grad_norm": 0.33987249777832035, "learning_rate": 2.0819807937325104e-05, "loss": 0.4605, "step": 665 }, { "epoch": 2.6963562753036436, "grad_norm": 0.281965023586158, "learning_rate": 2.0763297943469847e-05, "loss": 0.4806, "step": 666 }, { "epoch": 2.700404858299595, "grad_norm": 0.3551169805034292, "learning_rate": 2.070678184630458e-05, "loss": 0.4804, "step": 667 }, { "epoch": 2.7044534412955468, "grad_norm": 0.28834992778383317, "learning_rate": 2.06502600977305e-05, "loss": 0.4632, "step": 668 }, { "epoch": 2.708502024291498, "grad_norm": 0.3497422778899552, "learning_rate": 2.0593733149694008e-05, "loss": 0.4869, "step": 669 }, { "epoch": 2.7125506072874495, "grad_norm": 0.29633647883319136, "learning_rate": 2.0537201454183074e-05, "loss": 0.4806, "step": 670 }, { "epoch": 2.716599190283401, "grad_norm": 0.337964865612054, "learning_rate": 2.0480665463223626e-05, "loss": 0.4662, "step": 671 }, { "epoch": 2.720647773279352, "grad_norm": 0.2970052776898006, "learning_rate": 2.042412562887594e-05, "loss": 0.4841, "step": 672 }, { "epoch": 2.7246963562753037, "grad_norm": 0.3443964096081034, "learning_rate": 2.0367582403231033e-05, "loss": 0.4889, "step": 673 }, { "epoch": 2.7287449392712553, "grad_norm": 0.3011451643939557, "learning_rate": 2.0311036238407023e-05, "loss": 0.4752, "step": 674 }, { "epoch": 2.7327935222672064, "grad_norm": 0.33238406497231593, "learning_rate": 2.0254487586545534e-05, "loss": 0.4692, "step": 675 }, { "epoch": 2.736842105263158, "grad_norm": 0.3171521035543131, "learning_rate": 2.0197936899808088e-05, "loss": 0.4643, "step": 676 }, { "epoch": 2.7408906882591095, "grad_norm": 0.3042143165156823, "learning_rate": 2.0141384630372466e-05, "loss": 0.48, "step": 677 }, { "epoch": 2.7449392712550607, "grad_norm": 0.34419655299096547, "learning_rate": 2.0084831230429106e-05, "loss": 0.4731, "step": 678 }, { "epoch": 2.748987854251012, "grad_norm": 0.295478304102149, "learning_rate": 2.0028277152177492e-05, "loss": 0.4697, "step": 679 }, { "epoch": 2.753036437246964, "grad_norm": 0.3376524306854277, "learning_rate": 1.9971722847822518e-05, "loss": 0.4843, "step": 680 }, { "epoch": 2.757085020242915, "grad_norm": 0.381405337548351, "learning_rate": 1.99151687695709e-05, "loss": 0.4653, "step": 681 }, { "epoch": 2.7611336032388665, "grad_norm": 0.30793720401471397, "learning_rate": 1.9858615369627537e-05, "loss": 0.4818, "step": 682 }, { "epoch": 2.765182186234818, "grad_norm": 0.4228070014807715, "learning_rate": 1.9802063100191916e-05, "loss": 0.4762, "step": 683 }, { "epoch": 2.769230769230769, "grad_norm": 0.3131625857981098, "learning_rate": 1.974551241345447e-05, "loss": 0.4796, "step": 684 }, { "epoch": 2.7732793522267207, "grad_norm": 0.36623854469345724, "learning_rate": 1.9688963761592984e-05, "loss": 0.4749, "step": 685 }, { "epoch": 2.7773279352226723, "grad_norm": 0.3342827612777551, "learning_rate": 1.963241759676897e-05, "loss": 0.475, "step": 686 }, { "epoch": 2.7813765182186234, "grad_norm": 0.290642202211403, "learning_rate": 1.9575874371124066e-05, "loss": 0.4806, "step": 687 }, { "epoch": 2.785425101214575, "grad_norm": 0.3603216076619947, "learning_rate": 1.951933453677638e-05, "loss": 0.4924, "step": 688 }, { "epoch": 2.7894736842105265, "grad_norm": 0.26733113538284503, "learning_rate": 1.9462798545816932e-05, "loss": 0.4646, "step": 689 }, { "epoch": 2.7935222672064777, "grad_norm": 0.301306197534448, "learning_rate": 1.9406266850305996e-05, "loss": 0.4761, "step": 690 }, { "epoch": 2.7975708502024292, "grad_norm": 0.30158539457709355, "learning_rate": 1.9349739902269503e-05, "loss": 0.4972, "step": 691 }, { "epoch": 2.801619433198381, "grad_norm": 0.29194383080536257, "learning_rate": 1.9293218153695425e-05, "loss": 0.4649, "step": 692 }, { "epoch": 2.805668016194332, "grad_norm": 0.2917678127297476, "learning_rate": 1.9236702056530153e-05, "loss": 0.4815, "step": 693 }, { "epoch": 2.8097165991902835, "grad_norm": 0.27442755634109195, "learning_rate": 1.9180192062674907e-05, "loss": 0.4856, "step": 694 }, { "epoch": 2.813765182186235, "grad_norm": 0.30032349230889094, "learning_rate": 1.9123688623982076e-05, "loss": 0.4747, "step": 695 }, { "epoch": 2.817813765182186, "grad_norm": 0.2844405663008209, "learning_rate": 1.906719219225165e-05, "loss": 0.4699, "step": 696 }, { "epoch": 2.8218623481781377, "grad_norm": 0.2943213842894866, "learning_rate": 1.9010703219227603e-05, "loss": 0.4767, "step": 697 }, { "epoch": 2.8259109311740893, "grad_norm": 0.30044722267875473, "learning_rate": 1.8954222156594256e-05, "loss": 0.4863, "step": 698 }, { "epoch": 2.8299595141700404, "grad_norm": 0.38105898340285294, "learning_rate": 1.8897749455972673e-05, "loss": 0.4823, "step": 699 }, { "epoch": 2.834008097165992, "grad_norm": 0.30448315454027874, "learning_rate": 1.884128556891707e-05, "loss": 0.4837, "step": 700 }, { "epoch": 2.8380566801619436, "grad_norm": 0.2822001612773342, "learning_rate": 1.878483094691119e-05, "loss": 0.4721, "step": 701 }, { "epoch": 2.8421052631578947, "grad_norm": 0.29942899304603826, "learning_rate": 1.8728386041364664e-05, "loss": 0.4718, "step": 702 }, { "epoch": 2.8461538461538463, "grad_norm": 0.30227524160751446, "learning_rate": 1.867195130360947e-05, "loss": 0.4785, "step": 703 }, { "epoch": 2.850202429149798, "grad_norm": 0.28204314405853853, "learning_rate": 1.8615527184896263e-05, "loss": 0.4738, "step": 704 }, { "epoch": 2.854251012145749, "grad_norm": 0.29188228106698927, "learning_rate": 1.8559114136390795e-05, "loss": 0.4736, "step": 705 }, { "epoch": 2.8582995951417005, "grad_norm": 0.27737394785015224, "learning_rate": 1.8502712609170298e-05, "loss": 0.4861, "step": 706 }, { "epoch": 2.862348178137652, "grad_norm": 0.3038140178109647, "learning_rate": 1.8446323054219876e-05, "loss": 0.4826, "step": 707 }, { "epoch": 2.866396761133603, "grad_norm": 0.32930635431361943, "learning_rate": 1.838994592242891e-05, "loss": 0.4669, "step": 708 }, { "epoch": 2.8704453441295548, "grad_norm": 0.29532509342675656, "learning_rate": 1.8333581664587453e-05, "loss": 0.4778, "step": 709 }, { "epoch": 2.8744939271255063, "grad_norm": 0.2626136482399595, "learning_rate": 1.8277230731382593e-05, "loss": 0.4866, "step": 710 }, { "epoch": 2.8785425101214575, "grad_norm": 0.3037429662940355, "learning_rate": 1.82208935733949e-05, "loss": 0.469, "step": 711 }, { "epoch": 2.882591093117409, "grad_norm": 0.2876196398182829, "learning_rate": 1.8164570641094793e-05, "loss": 0.4693, "step": 712 }, { "epoch": 2.8866396761133606, "grad_norm": 0.32555369990994815, "learning_rate": 1.810826238483892e-05, "loss": 0.4753, "step": 713 }, { "epoch": 2.8906882591093117, "grad_norm": 0.29089382392718416, "learning_rate": 1.8051969254866608e-05, "loss": 0.4736, "step": 714 }, { "epoch": 2.8947368421052633, "grad_norm": 0.3037231427299137, "learning_rate": 1.7995691701296226e-05, "loss": 0.4804, "step": 715 }, { "epoch": 2.898785425101215, "grad_norm": 0.30019889842069974, "learning_rate": 1.7939430174121593e-05, "loss": 0.4778, "step": 716 }, { "epoch": 2.902834008097166, "grad_norm": 0.2634879057570485, "learning_rate": 1.788318512320838e-05, "loss": 0.4908, "step": 717 }, { "epoch": 2.9068825910931175, "grad_norm": 0.27734631336061893, "learning_rate": 1.782695699829051e-05, "loss": 0.4805, "step": 718 }, { "epoch": 2.910931174089069, "grad_norm": 0.2937566474315327, "learning_rate": 1.7770746248966587e-05, "loss": 0.4796, "step": 719 }, { "epoch": 2.91497975708502, "grad_norm": 0.2850471440895132, "learning_rate": 1.7714553324696243e-05, "loss": 0.4866, "step": 720 }, { "epoch": 2.919028340080972, "grad_norm": 0.31043238229944237, "learning_rate": 1.7658378674796614e-05, "loss": 0.4759, "step": 721 }, { "epoch": 2.9230769230769234, "grad_norm": 0.3034274931019074, "learning_rate": 1.76022227484387e-05, "loss": 0.4753, "step": 722 }, { "epoch": 2.9271255060728745, "grad_norm": 0.253964648729469, "learning_rate": 1.7546085994643807e-05, "loss": 0.4665, "step": 723 }, { "epoch": 2.931174089068826, "grad_norm": 0.2663453974296999, "learning_rate": 1.7489968862279902e-05, "loss": 0.48, "step": 724 }, { "epoch": 2.9352226720647776, "grad_norm": 0.2620867476583453, "learning_rate": 1.743387180005809e-05, "loss": 0.478, "step": 725 }, { "epoch": 2.9392712550607287, "grad_norm": 0.268895875405905, "learning_rate": 1.737779525652899e-05, "loss": 0.4761, "step": 726 }, { "epoch": 2.9433198380566803, "grad_norm": 0.2852678342938203, "learning_rate": 1.732173968007914e-05, "loss": 0.4729, "step": 727 }, { "epoch": 2.9473684210526314, "grad_norm": 0.2673678960704307, "learning_rate": 1.7265705518927437e-05, "loss": 0.4727, "step": 728 }, { "epoch": 2.951417004048583, "grad_norm": 0.32954391850046333, "learning_rate": 1.7209693221121542e-05, "loss": 0.4721, "step": 729 }, { "epoch": 2.9554655870445345, "grad_norm": 0.26703268792179263, "learning_rate": 1.7153703234534302e-05, "loss": 0.4753, "step": 730 }, { "epoch": 2.9595141700404857, "grad_norm": 0.29197631498411536, "learning_rate": 1.709773600686015e-05, "loss": 0.4727, "step": 731 }, { "epoch": 2.9635627530364372, "grad_norm": 0.308313465639037, "learning_rate": 1.7041791985611548e-05, "loss": 0.4767, "step": 732 }, { "epoch": 2.967611336032389, "grad_norm": 0.26012137626163345, "learning_rate": 1.69858716181154e-05, "loss": 0.4584, "step": 733 }, { "epoch": 2.97165991902834, "grad_norm": 0.33659835187295334, "learning_rate": 1.692997535150948e-05, "loss": 0.4887, "step": 734 }, { "epoch": 2.9757085020242915, "grad_norm": 0.2491323866104856, "learning_rate": 1.687410363273884e-05, "loss": 0.4892, "step": 735 }, { "epoch": 2.979757085020243, "grad_norm": 0.28043709883969076, "learning_rate": 1.6818256908552257e-05, "loss": 0.4788, "step": 736 }, { "epoch": 2.983805668016194, "grad_norm": 0.27700343954591927, "learning_rate": 1.6762435625498646e-05, "loss": 0.4716, "step": 737 }, { "epoch": 2.9878542510121457, "grad_norm": 0.28987522552789136, "learning_rate": 1.67066402299235e-05, "loss": 0.4672, "step": 738 }, { "epoch": 2.9919028340080973, "grad_norm": 0.29969750460397526, "learning_rate": 1.6650871167965313e-05, "loss": 0.4862, "step": 739 }, { "epoch": 2.9959514170040484, "grad_norm": 0.3174915731528427, "learning_rate": 1.6595128885552028e-05, "loss": 0.471, "step": 740 }, { "epoch": 3.0, "grad_norm": 0.269006378360245, "learning_rate": 1.653941382839745e-05, "loss": 0.4586, "step": 741 }, { "epoch": 3.0040485829959516, "grad_norm": 0.46878784415983055, "learning_rate": 1.6483726441997673e-05, "loss": 0.4224, "step": 742 }, { "epoch": 3.0080971659919027, "grad_norm": 0.36111646935468245, "learning_rate": 1.642806717162757e-05, "loss": 0.4045, "step": 743 }, { "epoch": 3.0121457489878543, "grad_norm": 0.574047879570976, "learning_rate": 1.637243646233718e-05, "loss": 0.4181, "step": 744 }, { "epoch": 3.016194331983806, "grad_norm": 0.4211055522897407, "learning_rate": 1.6316834758948174e-05, "loss": 0.4282, "step": 745 }, { "epoch": 3.020242914979757, "grad_norm": 0.4508838725487655, "learning_rate": 1.6261262506050282e-05, "loss": 0.4165, "step": 746 }, { "epoch": 3.0242914979757085, "grad_norm": 0.38420752729443924, "learning_rate": 1.620572014799777e-05, "loss": 0.4086, "step": 747 }, { "epoch": 3.02834008097166, "grad_norm": 0.41750554916480737, "learning_rate": 1.6150208128905857e-05, "loss": 0.4297, "step": 748 }, { "epoch": 3.032388663967611, "grad_norm": 0.36901575089205707, "learning_rate": 1.6094726892647147e-05, "loss": 0.392, "step": 749 }, { "epoch": 3.0364372469635628, "grad_norm": 0.38410893903692783, "learning_rate": 1.6039276882848135e-05, "loss": 0.4001, "step": 750 }, { "epoch": 3.0404858299595143, "grad_norm": 0.37898792910450363, "learning_rate": 1.5983858542885635e-05, "loss": 0.411, "step": 751 }, { "epoch": 3.0445344129554655, "grad_norm": 0.40333652376189677, "learning_rate": 1.5928472315883203e-05, "loss": 0.3911, "step": 752 }, { "epoch": 3.048582995951417, "grad_norm": 0.39144047913362057, "learning_rate": 1.5873118644707633e-05, "loss": 0.3952, "step": 753 }, { "epoch": 3.0526315789473686, "grad_norm": 0.39768620420301015, "learning_rate": 1.5817797971965413e-05, "loss": 0.3991, "step": 754 }, { "epoch": 3.0566801619433197, "grad_norm": 0.4122062197386415, "learning_rate": 1.576251073999917e-05, "loss": 0.3978, "step": 755 }, { "epoch": 3.0607287449392713, "grad_norm": 0.33531151445692564, "learning_rate": 1.5707257390884126e-05, "loss": 0.4056, "step": 756 }, { "epoch": 3.064777327935223, "grad_norm": 0.45299118879239825, "learning_rate": 1.5652038366424595e-05, "loss": 0.3903, "step": 757 }, { "epoch": 3.068825910931174, "grad_norm": 0.3277510324783923, "learning_rate": 1.5596854108150424e-05, "loss": 0.409, "step": 758 }, { "epoch": 3.0728744939271255, "grad_norm": 0.40594981470945013, "learning_rate": 1.5541705057313476e-05, "loss": 0.409, "step": 759 }, { "epoch": 3.076923076923077, "grad_norm": 0.3225765003218631, "learning_rate": 1.5486591654884086e-05, "loss": 0.413, "step": 760 }, { "epoch": 3.080971659919028, "grad_norm": 0.36467220050938604, "learning_rate": 1.543151434154755e-05, "loss": 0.4055, "step": 761 }, { "epoch": 3.08502024291498, "grad_norm": 0.34536513827214427, "learning_rate": 1.5376473557700615e-05, "loss": 0.3955, "step": 762 }, { "epoch": 3.0890688259109313, "grad_norm": 0.36246670341974857, "learning_rate": 1.5321469743447893e-05, "loss": 0.396, "step": 763 }, { "epoch": 3.0931174089068825, "grad_norm": 0.31237715016290274, "learning_rate": 1.5266503338598434e-05, "loss": 0.4157, "step": 764 }, { "epoch": 3.097165991902834, "grad_norm": 0.3306735239159288, "learning_rate": 1.5211574782662149e-05, "loss": 0.4075, "step": 765 }, { "epoch": 3.1012145748987856, "grad_norm": 0.3214581755096417, "learning_rate": 1.5156684514846307e-05, "loss": 0.4166, "step": 766 }, { "epoch": 3.1052631578947367, "grad_norm": 0.2781697135547792, "learning_rate": 1.5101832974052012e-05, "loss": 0.407, "step": 767 }, { "epoch": 3.1093117408906883, "grad_norm": 0.2884096632530699, "learning_rate": 1.5047020598870737e-05, "loss": 0.4215, "step": 768 }, { "epoch": 3.11336032388664, "grad_norm": 0.2910888937871113, "learning_rate": 1.4992247827580778e-05, "loss": 0.412, "step": 769 }, { "epoch": 3.117408906882591, "grad_norm": 0.277246708936718, "learning_rate": 1.493751509814374e-05, "loss": 0.4105, "step": 770 }, { "epoch": 3.1214574898785425, "grad_norm": 0.29664319529872385, "learning_rate": 1.4882822848201073e-05, "loss": 0.4097, "step": 771 }, { "epoch": 3.125506072874494, "grad_norm": 0.3184538780338561, "learning_rate": 1.4828171515070553e-05, "loss": 0.4041, "step": 772 }, { "epoch": 3.1295546558704452, "grad_norm": 0.2811738570960624, "learning_rate": 1.4773561535742793e-05, "loss": 0.3993, "step": 773 }, { "epoch": 3.133603238866397, "grad_norm": 0.3563257134414738, "learning_rate": 1.4718993346877715e-05, "loss": 0.4098, "step": 774 }, { "epoch": 3.1376518218623484, "grad_norm": 0.29647588103948663, "learning_rate": 1.466446738480111e-05, "loss": 0.4021, "step": 775 }, { "epoch": 3.1417004048582995, "grad_norm": 0.3040674312085155, "learning_rate": 1.460998408550112e-05, "loss": 0.3926, "step": 776 }, { "epoch": 3.145748987854251, "grad_norm": 0.31248903332577826, "learning_rate": 1.4555543884624751e-05, "loss": 0.4006, "step": 777 }, { "epoch": 3.1497975708502026, "grad_norm": 0.29383711163097637, "learning_rate": 1.4501147217474402e-05, "loss": 0.4186, "step": 778 }, { "epoch": 3.1538461538461537, "grad_norm": 0.29155491177696935, "learning_rate": 1.444679451900437e-05, "loss": 0.4053, "step": 779 }, { "epoch": 3.1578947368421053, "grad_norm": 0.3231245436276154, "learning_rate": 1.4392486223817397e-05, "loss": 0.4125, "step": 780 }, { "epoch": 3.161943319838057, "grad_norm": 0.2765990147669568, "learning_rate": 1.4338222766161143e-05, "loss": 0.4028, "step": 781 }, { "epoch": 3.165991902834008, "grad_norm": 0.2901779167796087, "learning_rate": 1.4284004579924777e-05, "loss": 0.4058, "step": 782 }, { "epoch": 3.1700404858299596, "grad_norm": 0.2887135049383075, "learning_rate": 1.4229832098635479e-05, "loss": 0.4107, "step": 783 }, { "epoch": 3.174089068825911, "grad_norm": 0.26563992735361314, "learning_rate": 1.4175705755454963e-05, "loss": 0.4074, "step": 784 }, { "epoch": 3.1781376518218623, "grad_norm": 0.2991253362076454, "learning_rate": 1.412162598317602e-05, "loss": 0.4321, "step": 785 }, { "epoch": 3.182186234817814, "grad_norm": 0.2646761026030942, "learning_rate": 1.406759321421907e-05, "loss": 0.415, "step": 786 }, { "epoch": 3.1862348178137654, "grad_norm": 0.2695275851295119, "learning_rate": 1.401360788062871e-05, "loss": 0.414, "step": 787 }, { "epoch": 3.1902834008097165, "grad_norm": 0.27363597807813905, "learning_rate": 1.3959670414070204e-05, "loss": 0.4187, "step": 788 }, { "epoch": 3.194331983805668, "grad_norm": 0.28185547898188196, "learning_rate": 1.3905781245826108e-05, "loss": 0.4087, "step": 789 }, { "epoch": 3.1983805668016196, "grad_norm": 0.24847116750134995, "learning_rate": 1.3851940806792778e-05, "loss": 0.3955, "step": 790 }, { "epoch": 3.2024291497975708, "grad_norm": 0.2721828585507585, "learning_rate": 1.379814952747693e-05, "loss": 0.4065, "step": 791 }, { "epoch": 3.2064777327935223, "grad_norm": 0.27222995034166314, "learning_rate": 1.3744407837992193e-05, "loss": 0.4174, "step": 792 }, { "epoch": 3.2105263157894735, "grad_norm": 0.24209536491725406, "learning_rate": 1.3690716168055692e-05, "loss": 0.4108, "step": 793 }, { "epoch": 3.214574898785425, "grad_norm": 0.26429108395915274, "learning_rate": 1.363707494698459e-05, "loss": 0.4134, "step": 794 }, { "epoch": 3.2186234817813766, "grad_norm": 0.27223117118067186, "learning_rate": 1.358348460369265e-05, "loss": 0.4127, "step": 795 }, { "epoch": 3.2226720647773277, "grad_norm": 0.2461825717863725, "learning_rate": 1.352994556668684e-05, "loss": 0.4112, "step": 796 }, { "epoch": 3.2267206477732793, "grad_norm": 0.27647857695899, "learning_rate": 1.3476458264063865e-05, "loss": 0.4053, "step": 797 }, { "epoch": 3.230769230769231, "grad_norm": 0.23746807088474745, "learning_rate": 1.342302312350678e-05, "loss": 0.4141, "step": 798 }, { "epoch": 3.234817813765182, "grad_norm": 0.2601805177051441, "learning_rate": 1.3369640572281537e-05, "loss": 0.433, "step": 799 }, { "epoch": 3.2388663967611335, "grad_norm": 0.27006753220621943, "learning_rate": 1.3316311037233596e-05, "loss": 0.4172, "step": 800 }, { "epoch": 3.242914979757085, "grad_norm": 0.24886133824854803, "learning_rate": 1.326303494478451e-05, "loss": 0.4086, "step": 801 }, { "epoch": 3.246963562753036, "grad_norm": 0.271001910840245, "learning_rate": 1.3209812720928472e-05, "loss": 0.4136, "step": 802 }, { "epoch": 3.251012145748988, "grad_norm": 0.25486263129213277, "learning_rate": 1.315664479122898e-05, "loss": 0.4178, "step": 803 }, { "epoch": 3.2550607287449393, "grad_norm": 0.28631431507576627, "learning_rate": 1.3103531580815378e-05, "loss": 0.4147, "step": 804 }, { "epoch": 3.2591093117408905, "grad_norm": 0.26202222132029485, "learning_rate": 1.3050473514379488e-05, "loss": 0.409, "step": 805 }, { "epoch": 3.263157894736842, "grad_norm": 0.25236665292803445, "learning_rate": 1.2997471016172188e-05, "loss": 0.3861, "step": 806 }, { "epoch": 3.2672064777327936, "grad_norm": 0.2606312289924814, "learning_rate": 1.2944524510000042e-05, "loss": 0.4005, "step": 807 }, { "epoch": 3.2712550607287447, "grad_norm": 0.25675152395648554, "learning_rate": 1.2891634419221908e-05, "loss": 0.4059, "step": 808 }, { "epoch": 3.2753036437246963, "grad_norm": 0.2519111882482748, "learning_rate": 1.2838801166745545e-05, "loss": 0.418, "step": 809 }, { "epoch": 3.279352226720648, "grad_norm": 0.2601388615946849, "learning_rate": 1.2786025175024216e-05, "loss": 0.3858, "step": 810 }, { "epoch": 3.283400809716599, "grad_norm": 0.2624380020185769, "learning_rate": 1.2733306866053357e-05, "loss": 0.3996, "step": 811 }, { "epoch": 3.2874493927125505, "grad_norm": 0.2492068831393845, "learning_rate": 1.2680646661367163e-05, "loss": 0.3859, "step": 812 }, { "epoch": 3.291497975708502, "grad_norm": 0.26875681165961973, "learning_rate": 1.2628044982035219e-05, "loss": 0.4056, "step": 813 }, { "epoch": 3.2955465587044532, "grad_norm": 0.26836794179879264, "learning_rate": 1.2575502248659155e-05, "loss": 0.418, "step": 814 }, { "epoch": 3.299595141700405, "grad_norm": 0.2578008749134932, "learning_rate": 1.2523018881369269e-05, "loss": 0.4126, "step": 815 }, { "epoch": 3.3036437246963564, "grad_norm": 0.298786850395357, "learning_rate": 1.2470595299821176e-05, "loss": 0.4098, "step": 816 }, { "epoch": 3.3076923076923075, "grad_norm": 0.24934447253125477, "learning_rate": 1.2418231923192416e-05, "loss": 0.4075, "step": 817 }, { "epoch": 3.311740890688259, "grad_norm": 0.27514460515519473, "learning_rate": 1.2365929170179165e-05, "loss": 0.3974, "step": 818 }, { "epoch": 3.3157894736842106, "grad_norm": 0.30150094153858853, "learning_rate": 1.2313687458992848e-05, "loss": 0.4024, "step": 819 }, { "epoch": 3.3198380566801617, "grad_norm": 0.28445110240554744, "learning_rate": 1.2261507207356785e-05, "loss": 0.4085, "step": 820 }, { "epoch": 3.3238866396761133, "grad_norm": 0.2896491123112618, "learning_rate": 1.220938883250288e-05, "loss": 0.4007, "step": 821 }, { "epoch": 3.327935222672065, "grad_norm": 0.2859299106044386, "learning_rate": 1.215733275116827e-05, "loss": 0.4054, "step": 822 }, { "epoch": 3.331983805668016, "grad_norm": 0.2970288890179051, "learning_rate": 1.2105339379592005e-05, "loss": 0.4082, "step": 823 }, { "epoch": 3.3360323886639676, "grad_norm": 0.27979713082885427, "learning_rate": 1.2053409133511681e-05, "loss": 0.4217, "step": 824 }, { "epoch": 3.340080971659919, "grad_norm": 0.26731859188359547, "learning_rate": 1.2001542428160173e-05, "loss": 0.3954, "step": 825 }, { "epoch": 3.3441295546558703, "grad_norm": 0.2746787151878742, "learning_rate": 1.1949739678262278e-05, "loss": 0.4177, "step": 826 }, { "epoch": 3.348178137651822, "grad_norm": 0.252863169086355, "learning_rate": 1.189800129803139e-05, "loss": 0.3914, "step": 827 }, { "epoch": 3.3522267206477734, "grad_norm": 0.28361721501476234, "learning_rate": 1.1846327701166228e-05, "loss": 0.4072, "step": 828 }, { "epoch": 3.3562753036437245, "grad_norm": 0.2727985670763498, "learning_rate": 1.1794719300847493e-05, "loss": 0.4102, "step": 829 }, { "epoch": 3.360323886639676, "grad_norm": 0.24611747174049892, "learning_rate": 1.1743176509734582e-05, "loss": 0.4162, "step": 830 }, { "epoch": 3.3643724696356276, "grad_norm": 0.29428500371990257, "learning_rate": 1.1691699739962275e-05, "loss": 0.4056, "step": 831 }, { "epoch": 3.3684210526315788, "grad_norm": 0.24637143426249408, "learning_rate": 1.1640289403137456e-05, "loss": 0.4015, "step": 832 }, { "epoch": 3.3724696356275303, "grad_norm": 0.27360387446727585, "learning_rate": 1.1588945910335802e-05, "loss": 0.406, "step": 833 }, { "epoch": 3.376518218623482, "grad_norm": 0.259726166602685, "learning_rate": 1.1537669672098517e-05, "loss": 0.4111, "step": 834 }, { "epoch": 3.380566801619433, "grad_norm": 0.29914082450892254, "learning_rate": 1.1486461098429036e-05, "loss": 0.4036, "step": 835 }, { "epoch": 3.3846153846153846, "grad_norm": 0.2465256485974932, "learning_rate": 1.1435320598789747e-05, "loss": 0.4065, "step": 836 }, { "epoch": 3.388663967611336, "grad_norm": 0.2790058432513043, "learning_rate": 1.1384248582098736e-05, "loss": 0.3992, "step": 837 }, { "epoch": 3.3927125506072873, "grad_norm": 0.28551225084968584, "learning_rate": 1.1333245456726467e-05, "loss": 0.4033, "step": 838 }, { "epoch": 3.396761133603239, "grad_norm": 0.233131043444867, "learning_rate": 1.128231163049258e-05, "loss": 0.4118, "step": 839 }, { "epoch": 3.4008097165991904, "grad_norm": 0.31195010502521503, "learning_rate": 1.123144751066259e-05, "loss": 0.3975, "step": 840 }, { "epoch": 3.4048582995951415, "grad_norm": 0.24937899568435615, "learning_rate": 1.1180653503944657e-05, "loss": 0.4102, "step": 841 }, { "epoch": 3.408906882591093, "grad_norm": 0.24937863516876563, "learning_rate": 1.1129930016486287e-05, "loss": 0.4161, "step": 842 }, { "epoch": 3.4129554655870447, "grad_norm": 0.2573502689309083, "learning_rate": 1.107927745387114e-05, "loss": 0.4077, "step": 843 }, { "epoch": 3.417004048582996, "grad_norm": 0.26054212435712043, "learning_rate": 1.1028696221115766e-05, "loss": 0.409, "step": 844 }, { "epoch": 3.4210526315789473, "grad_norm": 0.252063740431174, "learning_rate": 1.0978186722666341e-05, "loss": 0.4063, "step": 845 }, { "epoch": 3.425101214574899, "grad_norm": 0.23852729616825133, "learning_rate": 1.0927749362395475e-05, "loss": 0.4059, "step": 846 }, { "epoch": 3.42914979757085, "grad_norm": 0.25501390919428446, "learning_rate": 1.0877384543598954e-05, "loss": 0.4117, "step": 847 }, { "epoch": 3.4331983805668016, "grad_norm": 0.22924271967628135, "learning_rate": 1.0827092668992529e-05, "loss": 0.4062, "step": 848 }, { "epoch": 3.437246963562753, "grad_norm": 0.27355561146597246, "learning_rate": 1.077687414070869e-05, "loss": 0.4153, "step": 849 }, { "epoch": 3.4412955465587043, "grad_norm": 0.23581591571676566, "learning_rate": 1.0726729360293451e-05, "loss": 0.4207, "step": 850 }, { "epoch": 3.445344129554656, "grad_norm": 0.23304592433637977, "learning_rate": 1.0676658728703147e-05, "loss": 0.4114, "step": 851 }, { "epoch": 3.4493927125506074, "grad_norm": 0.2404432693875887, "learning_rate": 1.0626662646301198e-05, "loss": 0.4057, "step": 852 }, { "epoch": 3.4534412955465585, "grad_norm": 0.23948030098953021, "learning_rate": 1.0576741512854958e-05, "loss": 0.3974, "step": 853 }, { "epoch": 3.45748987854251, "grad_norm": 0.24260977307329898, "learning_rate": 1.052689572753247e-05, "loss": 0.4094, "step": 854 }, { "epoch": 3.4615384615384617, "grad_norm": 0.2572028992502913, "learning_rate": 1.0477125688899328e-05, "loss": 0.4093, "step": 855 }, { "epoch": 3.465587044534413, "grad_norm": 0.22780666157327956, "learning_rate": 1.0427431794915406e-05, "loss": 0.4079, "step": 856 }, { "epoch": 3.4696356275303644, "grad_norm": 0.257255618771628, "learning_rate": 1.0377814442931769e-05, "loss": 0.4063, "step": 857 }, { "epoch": 3.473684210526316, "grad_norm": 0.2528830892995696, "learning_rate": 1.0328274029687439e-05, "loss": 0.402, "step": 858 }, { "epoch": 3.477732793522267, "grad_norm": 0.2372979879658858, "learning_rate": 1.0278810951306253e-05, "loss": 0.4119, "step": 859 }, { "epoch": 3.4817813765182186, "grad_norm": 0.25138544011891034, "learning_rate": 1.0229425603293647e-05, "loss": 0.422, "step": 860 }, { "epoch": 3.48582995951417, "grad_norm": 0.2338109019924508, "learning_rate": 1.0180118380533558e-05, "loss": 0.3986, "step": 861 }, { "epoch": 3.4898785425101213, "grad_norm": 0.2494054341232639, "learning_rate": 1.0130889677285225e-05, "loss": 0.4024, "step": 862 }, { "epoch": 3.493927125506073, "grad_norm": 0.23684175649282221, "learning_rate": 1.008173988718005e-05, "loss": 0.4054, "step": 863 }, { "epoch": 3.4979757085020244, "grad_norm": 0.2359508603520688, "learning_rate": 1.0032669403218439e-05, "loss": 0.4164, "step": 864 }, { "epoch": 3.5020242914979756, "grad_norm": 0.24980185405343894, "learning_rate": 9.983678617766677e-06, "loss": 0.4144, "step": 865 }, { "epoch": 3.506072874493927, "grad_norm": 0.24055945072084794, "learning_rate": 9.934767922553788e-06, "loss": 0.4, "step": 866 }, { "epoch": 3.5101214574898787, "grad_norm": 0.23637602877359742, "learning_rate": 9.885937708668371e-06, "loss": 0.4024, "step": 867 }, { "epoch": 3.51417004048583, "grad_norm": 0.25936396924630706, "learning_rate": 9.837188366555524e-06, "loss": 0.4132, "step": 868 }, { "epoch": 3.5182186234817814, "grad_norm": 0.23334070710327062, "learning_rate": 9.788520286013691e-06, "loss": 0.4097, "step": 869 }, { "epoch": 3.522267206477733, "grad_norm": 0.25623919389782435, "learning_rate": 9.739933856191537e-06, "loss": 0.4146, "step": 870 }, { "epoch": 3.526315789473684, "grad_norm": 0.268714562623498, "learning_rate": 9.691429465584866e-06, "loss": 0.396, "step": 871 }, { "epoch": 3.5303643724696356, "grad_norm": 0.24358050071034948, "learning_rate": 9.643007502033492e-06, "loss": 0.4029, "step": 872 }, { "epoch": 3.534412955465587, "grad_norm": 0.25161250417141495, "learning_rate": 9.594668352718152e-06, "loss": 0.3975, "step": 873 }, { "epoch": 3.5384615384615383, "grad_norm": 0.23771092168078042, "learning_rate": 9.546412404157383e-06, "loss": 0.4186, "step": 874 }, { "epoch": 3.54251012145749, "grad_norm": 0.24027195764865217, "learning_rate": 9.498240042204471e-06, "loss": 0.4006, "step": 875 }, { "epoch": 3.5465587044534415, "grad_norm": 0.25036715889032185, "learning_rate": 9.450151652044339e-06, "loss": 0.4041, "step": 876 }, { "epoch": 3.5506072874493926, "grad_norm": 0.2307596621604765, "learning_rate": 9.402147618190472e-06, "loss": 0.4038, "step": 877 }, { "epoch": 3.554655870445344, "grad_norm": 0.25502233812665354, "learning_rate": 9.354228324481841e-06, "loss": 0.4321, "step": 878 }, { "epoch": 3.5587044534412957, "grad_norm": 0.23856833907258332, "learning_rate": 9.306394154079852e-06, "loss": 0.4025, "step": 879 }, { "epoch": 3.562753036437247, "grad_norm": 0.24550299347510648, "learning_rate": 9.258645489465254e-06, "loss": 0.4147, "step": 880 }, { "epoch": 3.5668016194331984, "grad_norm": 0.24204322245050944, "learning_rate": 9.21098271243509e-06, "loss": 0.4012, "step": 881 }, { "epoch": 3.57085020242915, "grad_norm": 0.25898462331325756, "learning_rate": 9.163406204099659e-06, "loss": 0.4085, "step": 882 }, { "epoch": 3.574898785425101, "grad_norm": 0.22647580087599523, "learning_rate": 9.115916344879452e-06, "loss": 0.415, "step": 883 }, { "epoch": 3.5789473684210527, "grad_norm": 0.23646449937471417, "learning_rate": 9.068513514502126e-06, "loss": 0.4059, "step": 884 }, { "epoch": 3.582995951417004, "grad_norm": 0.23561667650110008, "learning_rate": 9.021198091999439e-06, "loss": 0.4144, "step": 885 }, { "epoch": 3.5870445344129553, "grad_norm": 0.23921536288595333, "learning_rate": 8.973970455704251e-06, "loss": 0.4193, "step": 886 }, { "epoch": 3.591093117408907, "grad_norm": 0.21544985910689401, "learning_rate": 8.926830983247495e-06, "loss": 0.4121, "step": 887 }, { "epoch": 3.5951417004048585, "grad_norm": 0.2541379516690231, "learning_rate": 8.879780051555116e-06, "loss": 0.4105, "step": 888 }, { "epoch": 3.5991902834008096, "grad_norm": 0.2359348174081354, "learning_rate": 8.83281803684512e-06, "loss": 0.4108, "step": 889 }, { "epoch": 3.603238866396761, "grad_norm": 0.21937531101765914, "learning_rate": 8.785945314624532e-06, "loss": 0.4106, "step": 890 }, { "epoch": 3.6072874493927127, "grad_norm": 0.2347335128223411, "learning_rate": 8.739162259686385e-06, "loss": 0.4112, "step": 891 }, { "epoch": 3.611336032388664, "grad_norm": 0.2348556349158817, "learning_rate": 8.692469246106734e-06, "loss": 0.4103, "step": 892 }, { "epoch": 3.6153846153846154, "grad_norm": 0.22746112514009165, "learning_rate": 8.645866647241677e-06, "loss": 0.4043, "step": 893 }, { "epoch": 3.619433198380567, "grad_norm": 0.2351809950215179, "learning_rate": 8.599354835724348e-06, "loss": 0.4062, "step": 894 }, { "epoch": 3.623481781376518, "grad_norm": 0.22775122762016972, "learning_rate": 8.552934183461958e-06, "loss": 0.4141, "step": 895 }, { "epoch": 3.6275303643724697, "grad_norm": 0.21577594685681611, "learning_rate": 8.506605061632805e-06, "loss": 0.4172, "step": 896 }, { "epoch": 3.6315789473684212, "grad_norm": 0.22022096670496918, "learning_rate": 8.460367840683308e-06, "loss": 0.4143, "step": 897 }, { "epoch": 3.6356275303643724, "grad_norm": 0.2312985833340785, "learning_rate": 8.414222890325065e-06, "loss": 0.4208, "step": 898 }, { "epoch": 3.639676113360324, "grad_norm": 0.23273420170909462, "learning_rate": 8.368170579531855e-06, "loss": 0.3981, "step": 899 }, { "epoch": 3.6437246963562755, "grad_norm": 0.23164891317460898, "learning_rate": 8.322211276536733e-06, "loss": 0.4076, "step": 900 }, { "epoch": 3.6477732793522266, "grad_norm": 0.23457867508296112, "learning_rate": 8.27634534882907e-06, "loss": 0.3973, "step": 901 }, { "epoch": 3.651821862348178, "grad_norm": 0.23340410922570004, "learning_rate": 8.230573163151585e-06, "loss": 0.4053, "step": 902 }, { "epoch": 3.6558704453441297, "grad_norm": 0.23999882117039412, "learning_rate": 8.184895085497466e-06, "loss": 0.3995, "step": 903 }, { "epoch": 3.659919028340081, "grad_norm": 0.23029243241601335, "learning_rate": 8.139311481107401e-06, "loss": 0.3987, "step": 904 }, { "epoch": 3.6639676113360324, "grad_norm": 0.23536778783076884, "learning_rate": 8.093822714466686e-06, "loss": 0.4176, "step": 905 }, { "epoch": 3.668016194331984, "grad_norm": 0.22695677881534457, "learning_rate": 8.048429149302271e-06, "loss": 0.4008, "step": 906 }, { "epoch": 3.672064777327935, "grad_norm": 0.23388428623536073, "learning_rate": 8.003131148579902e-06, "loss": 0.4078, "step": 907 }, { "epoch": 3.6761133603238867, "grad_norm": 0.22773823666665208, "learning_rate": 7.957929074501182e-06, "loss": 0.4165, "step": 908 }, { "epoch": 3.6801619433198383, "grad_norm": 0.246131111428996, "learning_rate": 7.912823288500695e-06, "loss": 0.406, "step": 909 }, { "epoch": 3.6842105263157894, "grad_norm": 0.24240884443561633, "learning_rate": 7.867814151243102e-06, "loss": 0.3971, "step": 910 }, { "epoch": 3.688259109311741, "grad_norm": 0.2516549192181807, "learning_rate": 7.822902022620267e-06, "loss": 0.4173, "step": 911 }, { "epoch": 3.6923076923076925, "grad_norm": 0.23946352208604169, "learning_rate": 7.778087261748377e-06, "loss": 0.4008, "step": 912 }, { "epoch": 3.6963562753036436, "grad_norm": 0.22947184837777054, "learning_rate": 7.733370226965056e-06, "loss": 0.4065, "step": 913 }, { "epoch": 3.700404858299595, "grad_norm": 0.24054681002831652, "learning_rate": 7.688751275826527e-06, "loss": 0.4015, "step": 914 }, { "epoch": 3.7044534412955468, "grad_norm": 0.2402202161457565, "learning_rate": 7.644230765104735e-06, "loss": 0.4042, "step": 915 }, { "epoch": 3.708502024291498, "grad_norm": 0.21789874629068637, "learning_rate": 7.599809050784502e-06, "loss": 0.4096, "step": 916 }, { "epoch": 3.7125506072874495, "grad_norm": 0.21850109243398955, "learning_rate": 7.555486488060661e-06, "loss": 0.4228, "step": 917 }, { "epoch": 3.716599190283401, "grad_norm": 0.22861936031454616, "learning_rate": 7.511263431335249e-06, "loss": 0.4093, "step": 918 }, { "epoch": 3.720647773279352, "grad_norm": 0.23590302875254107, "learning_rate": 7.467140234214656e-06, "loss": 0.4148, "step": 919 }, { "epoch": 3.7246963562753037, "grad_norm": 0.25455310408436704, "learning_rate": 7.423117249506777e-06, "loss": 0.4263, "step": 920 }, { "epoch": 3.7287449392712553, "grad_norm": 0.22041918191784218, "learning_rate": 7.379194829218231e-06, "loss": 0.3925, "step": 921 }, { "epoch": 3.7327935222672064, "grad_norm": 0.2496930432011372, "learning_rate": 7.335373324551518e-06, "loss": 0.4059, "step": 922 }, { "epoch": 3.736842105263158, "grad_norm": 0.23808408145745083, "learning_rate": 7.291653085902224e-06, "loss": 0.4057, "step": 923 }, { "epoch": 3.7408906882591095, "grad_norm": 0.23386285828040734, "learning_rate": 7.248034462856213e-06, "loss": 0.4133, "step": 924 }, { "epoch": 3.7449392712550607, "grad_norm": 0.23573520008908352, "learning_rate": 7.20451780418683e-06, "loss": 0.4072, "step": 925 }, { "epoch": 3.748987854251012, "grad_norm": 0.22368574775131617, "learning_rate": 7.161103457852128e-06, "loss": 0.4054, "step": 926 }, { "epoch": 3.753036437246964, "grad_norm": 0.23574142873643586, "learning_rate": 7.117791770992046e-06, "loss": 0.3878, "step": 927 }, { "epoch": 3.757085020242915, "grad_norm": 0.24063663004921826, "learning_rate": 7.074583089925688e-06, "loss": 0.4004, "step": 928 }, { "epoch": 3.7611336032388665, "grad_norm": 0.24815017559321711, "learning_rate": 7.0314777601485155e-06, "loss": 0.3982, "step": 929 }, { "epoch": 3.765182186234818, "grad_norm": 0.23800919673794338, "learning_rate": 6.988476126329604e-06, "loss": 0.4111, "step": 930 }, { "epoch": 3.769230769230769, "grad_norm": 0.22855396917241713, "learning_rate": 6.945578532308857e-06, "loss": 0.4102, "step": 931 }, { "epoch": 3.7732793522267207, "grad_norm": 0.24383922489047802, "learning_rate": 6.902785321094301e-06, "loss": 0.401, "step": 932 }, { "epoch": 3.7773279352226723, "grad_norm": 0.23687452557144933, "learning_rate": 6.8600968348593115e-06, "loss": 0.3737, "step": 933 }, { "epoch": 3.7813765182186234, "grad_norm": 0.23621594578057004, "learning_rate": 6.817513414939892e-06, "loss": 0.408, "step": 934 }, { "epoch": 3.785425101214575, "grad_norm": 0.22948512214679453, "learning_rate": 6.775035401831924e-06, "loss": 0.3976, "step": 935 }, { "epoch": 3.7894736842105265, "grad_norm": 0.231079682760772, "learning_rate": 6.732663135188473e-06, "loss": 0.4136, "step": 936 }, { "epoch": 3.7935222672064777, "grad_norm": 0.22500665163056238, "learning_rate": 6.690396953817055e-06, "loss": 0.4056, "step": 937 }, { "epoch": 3.7975708502024292, "grad_norm": 0.232089522227748, "learning_rate": 6.648237195676927e-06, "loss": 0.3998, "step": 938 }, { "epoch": 3.801619433198381, "grad_norm": 0.22226420402442282, "learning_rate": 6.606184197876395e-06, "loss": 0.4026, "step": 939 }, { "epoch": 3.805668016194332, "grad_norm": 0.24794825212178587, "learning_rate": 6.564238296670109e-06, "loss": 0.4059, "step": 940 }, { "epoch": 3.8097165991902835, "grad_norm": 0.2314262543992352, "learning_rate": 6.52239982745638e-06, "loss": 0.4244, "step": 941 }, { "epoch": 3.813765182186235, "grad_norm": 0.21540982393400424, "learning_rate": 6.480669124774484e-06, "loss": 0.4208, "step": 942 }, { "epoch": 3.817813765182186, "grad_norm": 0.22399107398321552, "learning_rate": 6.439046522302013e-06, "loss": 0.4211, "step": 943 }, { "epoch": 3.8218623481781377, "grad_norm": 0.2288551367506436, "learning_rate": 6.397532352852191e-06, "loss": 0.4131, "step": 944 }, { "epoch": 3.8259109311740893, "grad_norm": 0.2148357458049372, "learning_rate": 6.356126948371202e-06, "loss": 0.4209, "step": 945 }, { "epoch": 3.8299595141700404, "grad_norm": 0.22420392863216373, "learning_rate": 6.314830639935559e-06, "loss": 0.4002, "step": 946 }, { "epoch": 3.834008097165992, "grad_norm": 0.2502302996961316, "learning_rate": 6.273643757749448e-06, "loss": 0.4199, "step": 947 }, { "epoch": 3.8380566801619436, "grad_norm": 0.22200640424637347, "learning_rate": 6.2325666311420856e-06, "loss": 0.4202, "step": 948 }, { "epoch": 3.8421052631578947, "grad_norm": 0.23854507825922489, "learning_rate": 6.1915995885650675e-06, "loss": 0.4073, "step": 949 }, { "epoch": 3.8461538461538463, "grad_norm": 0.22447775629954916, "learning_rate": 6.150742957589784e-06, "loss": 0.4156, "step": 950 }, { "epoch": 3.850202429149798, "grad_norm": 0.2536548191208915, "learning_rate": 6.109997064904774e-06, "loss": 0.3945, "step": 951 }, { "epoch": 3.854251012145749, "grad_norm": 0.22804644063890545, "learning_rate": 6.069362236313092e-06, "loss": 0.3971, "step": 952 }, { "epoch": 3.8582995951417005, "grad_norm": 0.24339277028422146, "learning_rate": 6.0288387967297565e-06, "loss": 0.393, "step": 953 }, { "epoch": 3.862348178137652, "grad_norm": 0.2531444858715686, "learning_rate": 5.988427070179108e-06, "loss": 0.4089, "step": 954 }, { "epoch": 3.866396761133603, "grad_norm": 0.2336068843307022, "learning_rate": 5.948127379792234e-06, "loss": 0.4133, "step": 955 }, { "epoch": 3.8704453441295548, "grad_norm": 0.22202941879783783, "learning_rate": 5.90794004780439e-06, "loss": 0.4162, "step": 956 }, { "epoch": 3.8744939271255063, "grad_norm": 0.23710567828063797, "learning_rate": 5.867865395552405e-06, "loss": 0.4109, "step": 957 }, { "epoch": 3.8785425101214575, "grad_norm": 0.24259635244520292, "learning_rate": 5.8279037434721364e-06, "loss": 0.4106, "step": 958 }, { "epoch": 3.882591093117409, "grad_norm": 0.21617340531326673, "learning_rate": 5.788055411095892e-06, "loss": 0.4267, "step": 959 }, { "epoch": 3.8866396761133606, "grad_norm": 0.2236602620479327, "learning_rate": 5.7483207170498625e-06, "loss": 0.4014, "step": 960 }, { "epoch": 3.8906882591093117, "grad_norm": 0.2524652496257598, "learning_rate": 5.708699979051613e-06, "loss": 0.3981, "step": 961 }, { "epoch": 3.8947368421052633, "grad_norm": 0.2235293517034645, "learning_rate": 5.66919351390751e-06, "loss": 0.4169, "step": 962 }, { "epoch": 3.898785425101215, "grad_norm": 0.22574799958244765, "learning_rate": 5.629801637510188e-06, "loss": 0.4033, "step": 963 }, { "epoch": 3.902834008097166, "grad_norm": 0.22400692845219186, "learning_rate": 5.590524664836043e-06, "loss": 0.421, "step": 964 }, { "epoch": 3.9068825910931175, "grad_norm": 0.22120035846011749, "learning_rate": 5.551362909942708e-06, "loss": 0.4176, "step": 965 }, { "epoch": 3.910931174089069, "grad_norm": 0.23687215794587463, "learning_rate": 5.51231668596653e-06, "loss": 0.4207, "step": 966 }, { "epoch": 3.91497975708502, "grad_norm": 0.2355918569183402, "learning_rate": 5.47338630512007e-06, "loss": 0.3934, "step": 967 }, { "epoch": 3.919028340080972, "grad_norm": 0.2243100680213142, "learning_rate": 5.434572078689617e-06, "loss": 0.4043, "step": 968 }, { "epoch": 3.9230769230769234, "grad_norm": 0.233696536972873, "learning_rate": 5.395874317032694e-06, "loss": 0.4241, "step": 969 }, { "epoch": 3.9271255060728745, "grad_norm": 0.24121052932647916, "learning_rate": 5.357293329575573e-06, "loss": 0.3877, "step": 970 }, { "epoch": 3.931174089068826, "grad_norm": 0.2181772779320247, "learning_rate": 5.318829424810797e-06, "loss": 0.4182, "step": 971 }, { "epoch": 3.9352226720647776, "grad_norm": 0.22319929576084674, "learning_rate": 5.280482910294728e-06, "loss": 0.3876, "step": 972 }, { "epoch": 3.9392712550607287, "grad_norm": 0.22049225310855214, "learning_rate": 5.242254092645078e-06, "loss": 0.399, "step": 973 }, { "epoch": 3.9433198380566803, "grad_norm": 0.2141651303360859, "learning_rate": 5.2041432775384445e-06, "loss": 0.4109, "step": 974 }, { "epoch": 3.9473684210526314, "grad_norm": 0.21214565236441177, "learning_rate": 5.166150769707892e-06, "loss": 0.4158, "step": 975 }, { "epoch": 3.951417004048583, "grad_norm": 0.2355714857810855, "learning_rate": 5.128276872940503e-06, "loss": 0.4034, "step": 976 }, { "epoch": 3.9554655870445345, "grad_norm": 0.2246189480818322, "learning_rate": 5.090521890074953e-06, "loss": 0.4067, "step": 977 }, { "epoch": 3.9595141700404857, "grad_norm": 0.2257616325025795, "learning_rate": 5.0528861229990675e-06, "loss": 0.417, "step": 978 }, { "epoch": 3.9635627530364372, "grad_norm": 0.25026920141235776, "learning_rate": 5.015369872647442e-06, "loss": 0.3973, "step": 979 }, { "epoch": 3.967611336032389, "grad_norm": 0.2268149759148954, "learning_rate": 4.9779734389990195e-06, "loss": 0.4035, "step": 980 }, { "epoch": 3.97165991902834, "grad_norm": 0.22082391600264717, "learning_rate": 4.940697121074675e-06, "loss": 0.4156, "step": 981 }, { "epoch": 3.9757085020242915, "grad_norm": 0.2272752261308304, "learning_rate": 4.903541216934864e-06, "loss": 0.4236, "step": 982 }, { "epoch": 3.979757085020243, "grad_norm": 0.22714780693068737, "learning_rate": 4.8665060236772e-06, "loss": 0.4086, "step": 983 }, { "epoch": 3.983805668016194, "grad_norm": 0.2169599236062276, "learning_rate": 4.829591837434102e-06, "loss": 0.4198, "step": 984 }, { "epoch": 3.9878542510121457, "grad_norm": 0.23392771327083461, "learning_rate": 4.792798953370424e-06, "loss": 0.3921, "step": 985 }, { "epoch": 3.9919028340080973, "grad_norm": 0.23134445263537412, "learning_rate": 4.756127665681083e-06, "loss": 0.4237, "step": 986 }, { "epoch": 3.9959514170040484, "grad_norm": 0.2350597032940397, "learning_rate": 4.719578267588725e-06, "loss": 0.4064, "step": 987 }, { "epoch": 4.0, "grad_norm": 0.23049756838157767, "learning_rate": 4.6831510513413525e-06, "loss": 0.4165, "step": 988 }, { "epoch": 4.004048582995951, "grad_norm": 0.3969289971745824, "learning_rate": 4.6468463082100176e-06, "loss": 0.3539, "step": 989 }, { "epoch": 4.008097165991903, "grad_norm": 0.3365264983442337, "learning_rate": 4.610664328486485e-06, "loss": 0.328, "step": 990 }, { "epoch": 4.012145748987854, "grad_norm": 0.29533690834492166, "learning_rate": 4.5746054014809e-06, "loss": 0.3685, "step": 991 }, { "epoch": 4.016194331983805, "grad_norm": 0.4919574190816867, "learning_rate": 4.5386698155194766e-06, "loss": 0.3636, "step": 992 }, { "epoch": 4.020242914979757, "grad_norm": 0.3071223472262399, "learning_rate": 4.502857857942204e-06, "loss": 0.3445, "step": 993 }, { "epoch": 4.0242914979757085, "grad_norm": 0.3341002819889646, "learning_rate": 4.467169815100549e-06, "loss": 0.3665, "step": 994 }, { "epoch": 4.02834008097166, "grad_norm": 0.39494034300465053, "learning_rate": 4.431605972355137e-06, "loss": 0.3661, "step": 995 }, { "epoch": 4.032388663967612, "grad_norm": 0.3159583679446243, "learning_rate": 4.396166614073516e-06, "loss": 0.3572, "step": 996 }, { "epoch": 4.036437246963563, "grad_norm": 0.23525896544690753, "learning_rate": 4.360852023627846e-06, "loss": 0.3622, "step": 997 }, { "epoch": 4.040485829959514, "grad_norm": 0.3174534292678477, "learning_rate": 4.325662483392656e-06, "loss": 0.3582, "step": 998 }, { "epoch": 4.044534412955466, "grad_norm": 0.3327245386074619, "learning_rate": 4.29059827474257e-06, "loss": 0.3676, "step": 999 }, { "epoch": 4.048582995951417, "grad_norm": 0.26279369312657014, "learning_rate": 4.255659678050063e-06, "loss": 0.3621, "step": 1000 }, { "epoch": 4.052631578947368, "grad_norm": 0.23948561739751906, "learning_rate": 4.22084697268323e-06, "loss": 0.36, "step": 1001 }, { "epoch": 4.05668016194332, "grad_norm": 0.28764187132652175, "learning_rate": 4.186160437003535e-06, "loss": 0.3446, "step": 1002 }, { "epoch": 4.060728744939271, "grad_norm": 0.2718997884342733, "learning_rate": 4.151600348363582e-06, "loss": 0.3538, "step": 1003 }, { "epoch": 4.064777327935222, "grad_norm": 0.24182478594065612, "learning_rate": 4.11716698310493e-06, "loss": 0.3726, "step": 1004 }, { "epoch": 4.068825910931174, "grad_norm": 0.25104666267433934, "learning_rate": 4.082860616555848e-06, "loss": 0.3344, "step": 1005 }, { "epoch": 4.0728744939271255, "grad_norm": 0.27235834112491986, "learning_rate": 4.048681523029125e-06, "loss": 0.3622, "step": 1006 }, { "epoch": 4.076923076923077, "grad_norm": 0.2708548157368136, "learning_rate": 4.014629975819882e-06, "loss": 0.3452, "step": 1007 }, { "epoch": 4.080971659919029, "grad_norm": 0.23718441323253076, "learning_rate": 3.9807062472033855e-06, "loss": 0.3604, "step": 1008 }, { "epoch": 4.08502024291498, "grad_norm": 0.25368524563974826, "learning_rate": 3.94691060843287e-06, "loss": 0.3655, "step": 1009 }, { "epoch": 4.089068825910931, "grad_norm": 0.22916321847148333, "learning_rate": 3.913243329737353e-06, "loss": 0.3617, "step": 1010 }, { "epoch": 4.093117408906883, "grad_norm": 0.2430251297940915, "learning_rate": 3.879704680319503e-06, "loss": 0.3496, "step": 1011 }, { "epoch": 4.097165991902834, "grad_norm": 0.22774564518928234, "learning_rate": 3.846294928353471e-06, "loss": 0.3586, "step": 1012 }, { "epoch": 4.101214574898785, "grad_norm": 0.24514218718189387, "learning_rate": 3.8130143409827345e-06, "loss": 0.3544, "step": 1013 }, { "epoch": 4.105263157894737, "grad_norm": 0.23465103029821666, "learning_rate": 3.7798631843179887e-06, "loss": 0.3633, "step": 1014 }, { "epoch": 4.109311740890688, "grad_norm": 0.23571355997525356, "learning_rate": 3.7468417234349973e-06, "loss": 0.3382, "step": 1015 }, { "epoch": 4.113360323886639, "grad_norm": 0.2278794654451849, "learning_rate": 3.7139502223724823e-06, "loss": 0.3711, "step": 1016 }, { "epoch": 4.117408906882591, "grad_norm": 0.24537831243985317, "learning_rate": 3.6811889441300095e-06, "loss": 0.3587, "step": 1017 }, { "epoch": 4.1214574898785425, "grad_norm": 0.25056352709814367, "learning_rate": 3.648558150665886e-06, "loss": 0.3572, "step": 1018 }, { "epoch": 4.125506072874494, "grad_norm": 0.22073092223376756, "learning_rate": 3.616058102895075e-06, "loss": 0.3593, "step": 1019 }, { "epoch": 4.129554655870446, "grad_norm": 0.2234561316471975, "learning_rate": 3.583689060687079e-06, "loss": 0.3558, "step": 1020 }, { "epoch": 4.133603238866397, "grad_norm": 0.22911924945448836, "learning_rate": 3.5514512828639023e-06, "loss": 0.3683, "step": 1021 }, { "epoch": 4.137651821862348, "grad_norm": 0.25873063870435364, "learning_rate": 3.51934502719796e-06, "loss": 0.3626, "step": 1022 }, { "epoch": 4.1417004048583, "grad_norm": 0.22050988083788728, "learning_rate": 3.4873705504100185e-06, "loss": 0.3458, "step": 1023 }, { "epoch": 4.145748987854251, "grad_norm": 0.21928125122413367, "learning_rate": 3.4555281081671345e-06, "loss": 0.3515, "step": 1024 }, { "epoch": 4.149797570850202, "grad_norm": 0.24072631191381483, "learning_rate": 3.4238179550806326e-06, "loss": 0.3637, "step": 1025 }, { "epoch": 4.153846153846154, "grad_norm": 0.23943097313072148, "learning_rate": 3.3922403447040497e-06, "loss": 0.3534, "step": 1026 }, { "epoch": 4.157894736842105, "grad_norm": 0.22756373083487852, "learning_rate": 3.3607955295311247e-06, "loss": 0.3614, "step": 1027 }, { "epoch": 4.161943319838056, "grad_norm": 0.22443871389991146, "learning_rate": 3.32948376099375e-06, "loss": 0.36, "step": 1028 }, { "epoch": 4.165991902834008, "grad_norm": 0.2292544963322967, "learning_rate": 3.2983052894599976e-06, "loss": 0.3591, "step": 1029 }, { "epoch": 4.17004048582996, "grad_norm": 0.236999218825098, "learning_rate": 3.2672603642320945e-06, "loss": 0.3448, "step": 1030 }, { "epoch": 4.174089068825911, "grad_norm": 0.22867261477037817, "learning_rate": 3.236349233544438e-06, "loss": 0.3584, "step": 1031 }, { "epoch": 4.178137651821863, "grad_norm": 0.22153461516895254, "learning_rate": 3.205572144561604e-06, "loss": 0.3632, "step": 1032 }, { "epoch": 4.182186234817814, "grad_norm": 0.22104037078105124, "learning_rate": 3.174929343376374e-06, "loss": 0.3587, "step": 1033 }, { "epoch": 4.186234817813765, "grad_norm": 0.22563918029497596, "learning_rate": 3.1444210750077777e-06, "loss": 0.3322, "step": 1034 }, { "epoch": 4.190283400809717, "grad_norm": 0.2230088781025285, "learning_rate": 3.1140475833991046e-06, "loss": 0.3731, "step": 1035 }, { "epoch": 4.194331983805668, "grad_norm": 0.22437195934408896, "learning_rate": 3.0838091114159895e-06, "loss": 0.3527, "step": 1036 }, { "epoch": 4.198380566801619, "grad_norm": 0.2236515787305972, "learning_rate": 3.0537059008444524e-06, "loss": 0.3535, "step": 1037 }, { "epoch": 4.202429149797571, "grad_norm": 0.23592326619361198, "learning_rate": 3.0237381923889563e-06, "loss": 0.378, "step": 1038 }, { "epoch": 4.206477732793522, "grad_norm": 0.21889525639214014, "learning_rate": 2.9939062256704997e-06, "loss": 0.3559, "step": 1039 }, { "epoch": 4.2105263157894735, "grad_norm": 0.21197858112488593, "learning_rate": 2.964210239224696e-06, "loss": 0.3632, "step": 1040 }, { "epoch": 4.2145748987854255, "grad_norm": 0.22170799421796228, "learning_rate": 2.934650470499869e-06, "loss": 0.3547, "step": 1041 }, { "epoch": 4.218623481781377, "grad_norm": 0.22104664393889234, "learning_rate": 2.905227155855128e-06, "loss": 0.3579, "step": 1042 }, { "epoch": 4.222672064777328, "grad_norm": 0.21455101246567074, "learning_rate": 2.875940530558519e-06, "loss": 0.3756, "step": 1043 }, { "epoch": 4.22672064777328, "grad_norm": 0.2086380407712701, "learning_rate": 2.8467908287851154e-06, "loss": 0.3595, "step": 1044 }, { "epoch": 4.230769230769231, "grad_norm": 0.22222360077271314, "learning_rate": 2.8177782836151603e-06, "loss": 0.3607, "step": 1045 }, { "epoch": 4.234817813765182, "grad_norm": 0.21648838515877863, "learning_rate": 2.7889031270321874e-06, "loss": 0.3647, "step": 1046 }, { "epoch": 4.238866396761134, "grad_norm": 0.21727331286529622, "learning_rate": 2.760165589921184e-06, "loss": 0.3615, "step": 1047 }, { "epoch": 4.242914979757085, "grad_norm": 0.21480745593429093, "learning_rate": 2.7315659020667305e-06, "loss": 0.3669, "step": 1048 }, { "epoch": 4.246963562753036, "grad_norm": 0.21413226547114433, "learning_rate": 2.703104292151164e-06, "loss": 0.3736, "step": 1049 }, { "epoch": 4.251012145748988, "grad_norm": 0.21222992126618598, "learning_rate": 2.6747809877527607e-06, "loss": 0.3634, "step": 1050 }, { "epoch": 4.255060728744939, "grad_norm": 0.20640163175724768, "learning_rate": 2.6465962153439082e-06, "loss": 0.3479, "step": 1051 }, { "epoch": 4.2591093117408905, "grad_norm": 0.20766297024512453, "learning_rate": 2.618550200289303e-06, "loss": 0.3684, "step": 1052 }, { "epoch": 4.2631578947368425, "grad_norm": 0.21597910377601684, "learning_rate": 2.59064316684412e-06, "loss": 0.3584, "step": 1053 }, { "epoch": 4.267206477732794, "grad_norm": 0.21087200191507605, "learning_rate": 2.562875338152264e-06, "loss": 0.3492, "step": 1054 }, { "epoch": 4.271255060728745, "grad_norm": 0.21087076287985362, "learning_rate": 2.5352469362445552e-06, "loss": 0.3682, "step": 1055 }, { "epoch": 4.275303643724697, "grad_norm": 0.23249849333121342, "learning_rate": 2.5077581820369523e-06, "loss": 0.3659, "step": 1056 }, { "epoch": 4.279352226720648, "grad_norm": 0.2110606742182665, "learning_rate": 2.480409295328803e-06, "loss": 0.3507, "step": 1057 }, { "epoch": 4.283400809716599, "grad_norm": 0.21777483649266935, "learning_rate": 2.45320049480108e-06, "loss": 0.3395, "step": 1058 }, { "epoch": 4.287449392712551, "grad_norm": 0.21198268728830907, "learning_rate": 2.4261319980146293e-06, "loss": 0.3578, "step": 1059 }, { "epoch": 4.291497975708502, "grad_norm": 0.21229724184235882, "learning_rate": 2.399204021408421e-06, "loss": 0.3576, "step": 1060 }, { "epoch": 4.295546558704453, "grad_norm": 0.2199633088977379, "learning_rate": 2.3724167802978395e-06, "loss": 0.3511, "step": 1061 }, { "epoch": 4.299595141700405, "grad_norm": 0.22085525673296005, "learning_rate": 2.3457704888729625e-06, "loss": 0.3397, "step": 1062 }, { "epoch": 4.303643724696356, "grad_norm": 0.2057079779259276, "learning_rate": 2.3192653601968162e-06, "loss": 0.3622, "step": 1063 }, { "epoch": 4.3076923076923075, "grad_norm": 0.22598917371562233, "learning_rate": 2.2929016062037057e-06, "loss": 0.3427, "step": 1064 }, { "epoch": 4.3117408906882595, "grad_norm": 0.21653115575451737, "learning_rate": 2.2666794376975055e-06, "loss": 0.3693, "step": 1065 }, { "epoch": 4.315789473684211, "grad_norm": 0.2234290322493484, "learning_rate": 2.24059906434998e-06, "loss": 0.3718, "step": 1066 }, { "epoch": 4.319838056680162, "grad_norm": 0.21633537621452778, "learning_rate": 2.214660694699091e-06, "loss": 0.3663, "step": 1067 }, { "epoch": 4.323886639676114, "grad_norm": 0.21434478685924155, "learning_rate": 2.188864536147355e-06, "loss": 0.3616, "step": 1068 }, { "epoch": 4.327935222672065, "grad_norm": 0.2162455733015031, "learning_rate": 2.1632107949601757e-06, "loss": 0.364, "step": 1069 }, { "epoch": 4.331983805668016, "grad_norm": 0.2089336888367537, "learning_rate": 2.137699676264171e-06, "loss": 0.3656, "step": 1070 }, { "epoch": 4.336032388663968, "grad_norm": 0.21061359036633073, "learning_rate": 2.1123313840455738e-06, "loss": 0.3571, "step": 1071 }, { "epoch": 4.340080971659919, "grad_norm": 0.21338576217303223, "learning_rate": 2.08710612114857e-06, "loss": 0.3504, "step": 1072 }, { "epoch": 4.34412955465587, "grad_norm": 0.21447591805518704, "learning_rate": 2.0620240892736953e-06, "loss": 0.3631, "step": 1073 }, { "epoch": 4.348178137651822, "grad_norm": 0.21623475336529274, "learning_rate": 2.0370854889762e-06, "loss": 0.3719, "step": 1074 }, { "epoch": 4.352226720647773, "grad_norm": 0.2167867737229398, "learning_rate": 2.0122905196644726e-06, "loss": 0.3544, "step": 1075 }, { "epoch": 4.3562753036437245, "grad_norm": 0.22381806189452533, "learning_rate": 1.987639379598427e-06, "loss": 0.358, "step": 1076 }, { "epoch": 4.3603238866396765, "grad_norm": 0.21793250491979782, "learning_rate": 1.963132265887919e-06, "loss": 0.3624, "step": 1077 }, { "epoch": 4.364372469635628, "grad_norm": 0.20920276739627472, "learning_rate": 1.9387693744911784e-06, "loss": 0.3625, "step": 1078 }, { "epoch": 4.368421052631579, "grad_norm": 0.2129883144074679, "learning_rate": 1.9145509002132368e-06, "loss": 0.3578, "step": 1079 }, { "epoch": 4.372469635627531, "grad_norm": 0.21614258914163686, "learning_rate": 1.8904770367043723e-06, "loss": 0.3489, "step": 1080 }, { "epoch": 4.376518218623482, "grad_norm": 0.214918164382922, "learning_rate": 1.8665479764585504e-06, "loss": 0.3707, "step": 1081 }, { "epoch": 4.380566801619433, "grad_norm": 0.21434714164956278, "learning_rate": 1.8427639108118977e-06, "loss": 0.3699, "step": 1082 }, { "epoch": 4.384615384615385, "grad_norm": 0.22431779857243714, "learning_rate": 1.8191250299411755e-06, "loss": 0.3494, "step": 1083 }, { "epoch": 4.388663967611336, "grad_norm": 0.21755444513148203, "learning_rate": 1.7956315228622446e-06, "loss": 0.3606, "step": 1084 }, { "epoch": 4.392712550607287, "grad_norm": 0.20826864111062393, "learning_rate": 1.7722835774285553e-06, "loss": 0.3588, "step": 1085 }, { "epoch": 4.396761133603239, "grad_norm": 0.2024063633313913, "learning_rate": 1.7490813803296624e-06, "loss": 0.373, "step": 1086 }, { "epoch": 4.40080971659919, "grad_norm": 0.2067327272627773, "learning_rate": 1.726025117089718e-06, "loss": 0.3433, "step": 1087 }, { "epoch": 4.4048582995951415, "grad_norm": 0.2101718024988836, "learning_rate": 1.70311497206598e-06, "loss": 0.3632, "step": 1088 }, { "epoch": 4.4089068825910935, "grad_norm": 0.2082189389799295, "learning_rate": 1.6803511284473638e-06, "loss": 0.3619, "step": 1089 }, { "epoch": 4.412955465587045, "grad_norm": 0.21137799830503035, "learning_rate": 1.6577337682529538e-06, "loss": 0.3631, "step": 1090 }, { "epoch": 4.417004048582996, "grad_norm": 0.2125030079944347, "learning_rate": 1.6352630723305617e-06, "loss": 0.3498, "step": 1091 }, { "epoch": 4.421052631578947, "grad_norm": 0.20830931904239416, "learning_rate": 1.612939220355272e-06, "loss": 0.3631, "step": 1092 }, { "epoch": 4.425101214574899, "grad_norm": 0.21505580359462462, "learning_rate": 1.5907623908280112e-06, "loss": 0.3536, "step": 1093 }, { "epoch": 4.42914979757085, "grad_norm": 0.20510716770554469, "learning_rate": 1.568732761074121e-06, "loss": 0.3596, "step": 1094 }, { "epoch": 4.433198380566802, "grad_norm": 0.19836729788856472, "learning_rate": 1.5468505072419237e-06, "loss": 0.3789, "step": 1095 }, { "epoch": 4.437246963562753, "grad_norm": 0.2046263645948919, "learning_rate": 1.5251158043013448e-06, "loss": 0.363, "step": 1096 }, { "epoch": 4.441295546558704, "grad_norm": 0.2088133970400613, "learning_rate": 1.5035288260424885e-06, "loss": 0.3676, "step": 1097 }, { "epoch": 4.445344129554655, "grad_norm": 0.20737261698616835, "learning_rate": 1.4820897450742623e-06, "loss": 0.3579, "step": 1098 }, { "epoch": 4.449392712550607, "grad_norm": 0.21486238285266102, "learning_rate": 1.4607987328229767e-06, "loss": 0.359, "step": 1099 }, { "epoch": 4.4534412955465585, "grad_norm": 0.21119005986328246, "learning_rate": 1.4396559595310056e-06, "loss": 0.359, "step": 1100 }, { "epoch": 4.4574898785425106, "grad_norm": 0.21110320994324244, "learning_rate": 1.4186615942553973e-06, "loss": 0.3719, "step": 1101 }, { "epoch": 4.461538461538462, "grad_norm": 0.20521760792263113, "learning_rate": 1.3978158048665424e-06, "loss": 0.3431, "step": 1102 }, { "epoch": 4.465587044534413, "grad_norm": 0.20892263604640648, "learning_rate": 1.3771187580468115e-06, "loss": 0.3538, "step": 1103 }, { "epoch": 4.469635627530364, "grad_norm": 0.2221941902174149, "learning_rate": 1.3565706192892392e-06, "loss": 0.3773, "step": 1104 }, { "epoch": 4.473684210526316, "grad_norm": 0.20370636603604922, "learning_rate": 1.3361715528961993e-06, "loss": 0.3597, "step": 1105 }, { "epoch": 4.477732793522267, "grad_norm": 0.2055871723997163, "learning_rate": 1.3159217219780817e-06, "loss": 0.3607, "step": 1106 }, { "epoch": 4.481781376518219, "grad_norm": 0.20607948412457158, "learning_rate": 1.2958212884519949e-06, "loss": 0.359, "step": 1107 }, { "epoch": 4.48582995951417, "grad_norm": 0.20657434247539155, "learning_rate": 1.2758704130404675e-06, "loss": 0.3637, "step": 1108 }, { "epoch": 4.489878542510121, "grad_norm": 0.20846313451138457, "learning_rate": 1.2560692552701738e-06, "loss": 0.3586, "step": 1109 }, { "epoch": 4.493927125506072, "grad_norm": 0.21671940143148008, "learning_rate": 1.2364179734706382e-06, "loss": 0.3447, "step": 1110 }, { "epoch": 4.497975708502024, "grad_norm": 0.2095359399679134, "learning_rate": 1.2169167247729852e-06, "loss": 0.3667, "step": 1111 }, { "epoch": 4.502024291497976, "grad_norm": 0.20318533402480343, "learning_rate": 1.1975656651086864e-06, "loss": 0.3665, "step": 1112 }, { "epoch": 4.506072874493928, "grad_norm": 0.20954815622640047, "learning_rate": 1.1783649492082926e-06, "loss": 0.3517, "step": 1113 }, { "epoch": 4.510121457489879, "grad_norm": 0.1991049457688837, "learning_rate": 1.1593147306002183e-06, "loss": 0.3632, "step": 1114 }, { "epoch": 4.51417004048583, "grad_norm": 0.21032252253435382, "learning_rate": 1.140415161609505e-06, "loss": 0.372, "step": 1115 }, { "epoch": 4.518218623481781, "grad_norm": 0.21289057606296272, "learning_rate": 1.121666393356604e-06, "loss": 0.3445, "step": 1116 }, { "epoch": 4.522267206477733, "grad_norm": 0.20994292030434153, "learning_rate": 1.1030685757561632e-06, "loss": 0.3502, "step": 1117 }, { "epoch": 4.526315789473684, "grad_norm": 0.20619661517603569, "learning_rate": 1.0846218575158373e-06, "loss": 0.3637, "step": 1118 }, { "epoch": 4.530364372469636, "grad_norm": 0.20937706526320843, "learning_rate": 1.066326386135097e-06, "loss": 0.3593, "step": 1119 }, { "epoch": 4.534412955465587, "grad_norm": 0.21037036169475515, "learning_rate": 1.0481823079040398e-06, "loss": 0.3481, "step": 1120 }, { "epoch": 4.538461538461538, "grad_norm": 0.20525975491401047, "learning_rate": 1.0301897679022344e-06, "loss": 0.3743, "step": 1121 }, { "epoch": 4.5425101214574894, "grad_norm": 0.21407287034754247, "learning_rate": 1.0123489099975491e-06, "loss": 0.3628, "step": 1122 }, { "epoch": 4.5465587044534415, "grad_norm": 0.2088735620179306, "learning_rate": 9.9465987684501e-07, "loss": 0.3533, "step": 1123 }, { "epoch": 4.550607287449393, "grad_norm": 0.20660804517216164, "learning_rate": 9.771228098856534e-07, "loss": 0.3541, "step": 1124 }, { "epoch": 4.554655870445345, "grad_norm": 0.20745360853616424, "learning_rate": 9.597378493454013e-07, "loss": 0.3748, "step": 1125 }, { "epoch": 4.558704453441296, "grad_norm": 0.2138395182828972, "learning_rate": 9.425051342339353e-07, "loss": 0.3467, "step": 1126 }, { "epoch": 4.562753036437247, "grad_norm": 0.2058757179931771, "learning_rate": 9.254248023435864e-07, "loss": 0.3634, "step": 1127 }, { "epoch": 4.566801619433198, "grad_norm": 0.1983140621370018, "learning_rate": 9.084969902482288e-07, "loss": 0.3667, "step": 1128 }, { "epoch": 4.57085020242915, "grad_norm": 0.22021335811062903, "learning_rate": 8.917218333021993e-07, "loss": 0.3625, "step": 1129 }, { "epoch": 4.574898785425101, "grad_norm": 0.20885443769243509, "learning_rate": 8.750994656392109e-07, "loss": 0.3674, "step": 1130 }, { "epoch": 4.578947368421053, "grad_norm": 0.2083693857301574, "learning_rate": 8.58630020171265e-07, "loss": 0.364, "step": 1131 }, { "epoch": 4.582995951417004, "grad_norm": 0.20202525924845033, "learning_rate": 8.423136285876099e-07, "loss": 0.3637, "step": 1132 }, { "epoch": 4.587044534412955, "grad_norm": 0.19998987142116184, "learning_rate": 8.26150421353682e-07, "loss": 0.3651, "step": 1133 }, { "epoch": 4.5910931174089065, "grad_norm": 0.20011325545955777, "learning_rate": 8.101405277100549e-07, "loss": 0.3431, "step": 1134 }, { "epoch": 4.5951417004048585, "grad_norm": 0.206835089450584, "learning_rate": 7.942840756714077e-07, "loss": 0.3813, "step": 1135 }, { "epoch": 4.59919028340081, "grad_norm": 0.2137252576844906, "learning_rate": 7.785811920255093e-07, "loss": 0.3511, "step": 1136 }, { "epoch": 4.603238866396762, "grad_norm": 0.2108688823675208, "learning_rate": 7.630320023322024e-07, "loss": 0.3681, "step": 1137 }, { "epoch": 4.607287449392713, "grad_norm": 0.20410901401936107, "learning_rate": 7.476366309223903e-07, "loss": 0.367, "step": 1138 }, { "epoch": 4.611336032388664, "grad_norm": 0.20231782973075915, "learning_rate": 7.323952008970537e-07, "loss": 0.3642, "step": 1139 }, { "epoch": 4.615384615384615, "grad_norm": 0.2101544484097496, "learning_rate": 7.173078341262618e-07, "loss": 0.3615, "step": 1140 }, { "epoch": 4.619433198380567, "grad_norm": 0.2080987861291101, "learning_rate": 7.023746512481989e-07, "loss": 0.3716, "step": 1141 }, { "epoch": 4.623481781376518, "grad_norm": 0.20349858622114503, "learning_rate": 6.875957716681902e-07, "loss": 0.3627, "step": 1142 }, { "epoch": 4.62753036437247, "grad_norm": 0.20751850107400174, "learning_rate": 6.729713135577687e-07, "loss": 0.353, "step": 1143 }, { "epoch": 4.631578947368421, "grad_norm": 0.2049983931025782, "learning_rate": 6.585013938537143e-07, "loss": 0.3616, "step": 1144 }, { "epoch": 4.635627530364372, "grad_norm": 0.20290134010815988, "learning_rate": 6.441861282571115e-07, "loss": 0.3711, "step": 1145 }, { "epoch": 4.6396761133603235, "grad_norm": 0.21590815102668454, "learning_rate": 6.300256312324471e-07, "loss": 0.3752, "step": 1146 }, { "epoch": 4.6437246963562755, "grad_norm": 0.2091227568936195, "learning_rate": 6.160200160066776e-07, "loss": 0.3546, "step": 1147 }, { "epoch": 4.647773279352227, "grad_norm": 0.20449115680085578, "learning_rate": 6.021693945683327e-07, "loss": 0.3741, "step": 1148 }, { "epoch": 4.651821862348179, "grad_norm": 0.20316694947929986, "learning_rate": 5.884738776666044e-07, "loss": 0.3659, "step": 1149 }, { "epoch": 4.65587044534413, "grad_norm": 0.21098160197244864, "learning_rate": 5.749335748104878e-07, "loss": 0.3498, "step": 1150 }, { "epoch": 4.659919028340081, "grad_norm": 0.20624484203554772, "learning_rate": 5.615485942678778e-07, "loss": 0.3642, "step": 1151 }, { "epoch": 4.663967611336032, "grad_norm": 0.2100831098991778, "learning_rate": 5.483190430647289e-07, "loss": 0.3721, "step": 1152 }, { "epoch": 4.668016194331984, "grad_norm": 0.20500598062032407, "learning_rate": 5.352450269841747e-07, "loss": 0.3577, "step": 1153 }, { "epoch": 4.672064777327935, "grad_norm": 0.19886460534884393, "learning_rate": 5.22326650565701e-07, "loss": 0.3597, "step": 1154 }, { "epoch": 4.676113360323887, "grad_norm": 0.203272340276671, "learning_rate": 5.095640171043048e-07, "loss": 0.356, "step": 1155 }, { "epoch": 4.680161943319838, "grad_norm": 0.20658122055920577, "learning_rate": 4.969572286496594e-07, "loss": 0.3368, "step": 1156 }, { "epoch": 4.684210526315789, "grad_norm": 0.20055206491777025, "learning_rate": 4.845063860053079e-07, "loss": 0.3728, "step": 1157 }, { "epoch": 4.6882591093117405, "grad_norm": 0.2076809236421272, "learning_rate": 4.7221158872785997e-07, "loss": 0.3633, "step": 1158 }, { "epoch": 4.6923076923076925, "grad_norm": 0.2065561675380648, "learning_rate": 4.600729351261857e-07, "loss": 0.3537, "step": 1159 }, { "epoch": 4.696356275303644, "grad_norm": 0.2014813010369657, "learning_rate": 4.4809052226063355e-07, "loss": 0.3796, "step": 1160 }, { "epoch": 4.700404858299595, "grad_norm": 0.2103422556842734, "learning_rate": 4.3626444594226046e-07, "loss": 0.3556, "step": 1161 }, { "epoch": 4.704453441295547, "grad_norm": 0.20975365273563693, "learning_rate": 4.245948007320588e-07, "loss": 0.3538, "step": 1162 }, { "epoch": 4.708502024291498, "grad_norm": 0.20592144578643165, "learning_rate": 4.130816799401971e-07, "loss": 0.3596, "step": 1163 }, { "epoch": 4.712550607287449, "grad_norm": 0.2249458176184971, "learning_rate": 4.017251756252827e-07, "loss": 0.36, "step": 1164 }, { "epoch": 4.716599190283401, "grad_norm": 0.21355618124562586, "learning_rate": 3.9052537859362473e-07, "loss": 0.3491, "step": 1165 }, { "epoch": 4.720647773279352, "grad_norm": 0.20312470414731082, "learning_rate": 3.7948237839849687e-07, "loss": 0.3638, "step": 1166 }, { "epoch": 4.724696356275303, "grad_norm": 0.20095179869619115, "learning_rate": 3.6859626333943797e-07, "loss": 0.3553, "step": 1167 }, { "epoch": 4.728744939271255, "grad_norm": 0.20139900954793716, "learning_rate": 3.578671204615347e-07, "loss": 0.3769, "step": 1168 }, { "epoch": 4.732793522267206, "grad_norm": 0.2027947857558985, "learning_rate": 3.472950355547267e-07, "loss": 0.3697, "step": 1169 }, { "epoch": 4.7368421052631575, "grad_norm": 0.20173618927107514, "learning_rate": 3.3688009315312244e-07, "loss": 0.354, "step": 1170 }, { "epoch": 4.7408906882591095, "grad_norm": 0.20166190977055384, "learning_rate": 3.266223765343224e-07, "loss": 0.3621, "step": 1171 }, { "epoch": 4.744939271255061, "grad_norm": 0.2053737695392257, "learning_rate": 3.16521967718757e-07, "loss": 0.363, "step": 1172 }, { "epoch": 4.748987854251012, "grad_norm": 0.2115810563457583, "learning_rate": 3.0657894746902726e-07, "loss": 0.3446, "step": 1173 }, { "epoch": 4.753036437246964, "grad_norm": 0.19615996680025446, "learning_rate": 2.9679339528925654e-07, "loss": 0.3713, "step": 1174 }, { "epoch": 4.757085020242915, "grad_norm": 0.21738431431585634, "learning_rate": 2.871653894244597e-07, "loss": 0.3427, "step": 1175 }, { "epoch": 4.761133603238866, "grad_norm": 0.20728104168808292, "learning_rate": 2.7769500685991266e-07, "loss": 0.3374, "step": 1176 }, { "epoch": 4.765182186234818, "grad_norm": 0.20570717883290845, "learning_rate": 2.683823233205485e-07, "loss": 0.3367, "step": 1177 }, { "epoch": 4.769230769230769, "grad_norm": 0.20085372186512107, "learning_rate": 2.592274132703287e-07, "loss": 0.3685, "step": 1178 }, { "epoch": 4.77327935222672, "grad_norm": 0.2101893092753919, "learning_rate": 2.502303499116754e-07, "loss": 0.3613, "step": 1179 }, { "epoch": 4.777327935222672, "grad_norm": 0.20420356084863633, "learning_rate": 2.413912051848666e-07, "loss": 0.3663, "step": 1180 }, { "epoch": 4.781376518218623, "grad_norm": 0.20779006268632405, "learning_rate": 2.3271004976746613e-07, "loss": 0.3575, "step": 1181 }, { "epoch": 4.7854251012145745, "grad_norm": 0.200851009671006, "learning_rate": 2.2418695307376393e-07, "loss": 0.371, "step": 1182 }, { "epoch": 4.7894736842105265, "grad_norm": 0.20697644478355495, "learning_rate": 2.1582198325420968e-07, "loss": 0.3603, "step": 1183 }, { "epoch": 4.793522267206478, "grad_norm": 0.20457333455526971, "learning_rate": 2.0761520719488447e-07, "loss": 0.3644, "step": 1184 }, { "epoch": 4.797570850202429, "grad_norm": 0.19558144244478223, "learning_rate": 1.9956669051694798e-07, "loss": 0.371, "step": 1185 }, { "epoch": 4.801619433198381, "grad_norm": 0.19486485444532417, "learning_rate": 1.916764975761254e-07, "loss": 0.3683, "step": 1186 }, { "epoch": 4.805668016194332, "grad_norm": 0.21495737831624584, "learning_rate": 1.839446914621923e-07, "loss": 0.3524, "step": 1187 }, { "epoch": 4.809716599190283, "grad_norm": 0.20136001034664658, "learning_rate": 1.7637133399845962e-07, "loss": 0.3512, "step": 1188 }, { "epoch": 4.813765182186235, "grad_norm": 0.19989449691129965, "learning_rate": 1.6895648574129397e-07, "loss": 0.3609, "step": 1189 }, { "epoch": 4.817813765182186, "grad_norm": 0.20226288663887693, "learning_rate": 1.6170020597962465e-07, "loss": 0.3595, "step": 1190 }, { "epoch": 4.821862348178137, "grad_norm": 0.20135003817344102, "learning_rate": 1.5460255273447078e-07, "loss": 0.3714, "step": 1191 }, { "epoch": 4.825910931174089, "grad_norm": 0.20435913337868622, "learning_rate": 1.4766358275847715e-07, "loss": 0.363, "step": 1192 }, { "epoch": 4.82995951417004, "grad_norm": 0.1985735107343003, "learning_rate": 1.4088335153546573e-07, "loss": 0.371, "step": 1193 }, { "epoch": 4.834008097165992, "grad_norm": 0.2065599232536432, "learning_rate": 1.3426191327998496e-07, "loss": 0.3477, "step": 1194 }, { "epoch": 4.838056680161944, "grad_norm": 0.20690159802386002, "learning_rate": 1.277993209368744e-07, "loss": 0.3536, "step": 1195 }, { "epoch": 4.842105263157895, "grad_norm": 0.2005569368997871, "learning_rate": 1.214956261808542e-07, "loss": 0.363, "step": 1196 }, { "epoch": 4.846153846153846, "grad_norm": 0.21395506182066815, "learning_rate": 1.1535087941609846e-07, "loss": 0.3618, "step": 1197 }, { "epoch": 4.850202429149798, "grad_norm": 0.20131097826626188, "learning_rate": 1.0936512977583802e-07, "loss": 0.3656, "step": 1198 }, { "epoch": 4.854251012145749, "grad_norm": 0.197614184450021, "learning_rate": 1.0353842512196732e-07, "loss": 0.3598, "step": 1199 }, { "epoch": 4.8582995951417, "grad_norm": 0.20687230979514037, "learning_rate": 9.787081204466253e-08, "loss": 0.373, "step": 1200 }, { "epoch": 4.862348178137652, "grad_norm": 0.19988792690452403, "learning_rate": 9.236233586200627e-08, "loss": 0.3605, "step": 1201 }, { "epoch": 4.866396761133603, "grad_norm": 0.20230449760896885, "learning_rate": 8.70130406196279e-08, "loss": 0.3713, "step": 1202 }, { "epoch": 4.870445344129554, "grad_norm": 0.2010056481682782, "learning_rate": 8.182296909035047e-08, "loss": 0.3673, "step": 1203 }, { "epoch": 4.874493927125506, "grad_norm": 0.20425352542726513, "learning_rate": 7.679216277384439e-08, "loss": 0.3537, "step": 1204 }, { "epoch": 4.8785425101214575, "grad_norm": 0.20482313236600724, "learning_rate": 7.19206618963053e-08, "loss": 0.3676, "step": 1205 }, { "epoch": 4.882591093117409, "grad_norm": 0.19937544313116598, "learning_rate": 6.720850541012347e-08, "loss": 0.3774, "step": 1206 }, { "epoch": 4.886639676113361, "grad_norm": 0.20785693892201548, "learning_rate": 6.265573099357714e-08, "loss": 0.3375, "step": 1207 }, { "epoch": 4.890688259109312, "grad_norm": 0.2035034717960865, "learning_rate": 5.826237505053067e-08, "loss": 0.3521, "step": 1208 }, { "epoch": 4.894736842105263, "grad_norm": 0.2058622377950747, "learning_rate": 5.4028472710137e-08, "loss": 0.3448, "step": 1209 }, { "epoch": 4.898785425101215, "grad_norm": 0.19830001630186456, "learning_rate": 4.9954057826571146e-08, "loss": 0.3647, "step": 1210 }, { "epoch": 4.902834008097166, "grad_norm": 0.20474815431050483, "learning_rate": 4.6039162978743776e-08, "loss": 0.3562, "step": 1211 }, { "epoch": 4.906882591093117, "grad_norm": 0.2016267025500375, "learning_rate": 4.228381947004812e-08, "loss": 0.3663, "step": 1212 }, { "epoch": 4.910931174089069, "grad_norm": 0.20864061074920467, "learning_rate": 3.868805732811343e-08, "loss": 0.348, "step": 1213 }, { "epoch": 4.91497975708502, "grad_norm": 0.19776178534076033, "learning_rate": 3.525190530455636e-08, "loss": 0.3694, "step": 1214 }, { "epoch": 4.919028340080971, "grad_norm": 0.2176229874107827, "learning_rate": 3.197539087475887e-08, "loss": 0.3474, "step": 1215 }, { "epoch": 4.923076923076923, "grad_norm": 0.2011223472081022, "learning_rate": 2.8858540237641786e-08, "loss": 0.368, "step": 1216 }, { "epoch": 4.9271255060728745, "grad_norm": 0.20316456127204524, "learning_rate": 2.5901378315458247e-08, "loss": 0.3605, "step": 1217 }, { "epoch": 4.931174089068826, "grad_norm": 0.19616686853830112, "learning_rate": 2.3103928753598347e-08, "loss": 0.3751, "step": 1218 }, { "epoch": 4.935222672064778, "grad_norm": 0.20635253481627738, "learning_rate": 2.0466213920393718e-08, "loss": 0.3575, "step": 1219 }, { "epoch": 4.939271255060729, "grad_norm": 0.20746669984601582, "learning_rate": 1.7988254906942115e-08, "loss": 0.357, "step": 1220 }, { "epoch": 4.94331983805668, "grad_norm": 0.2108936233426504, "learning_rate": 1.5670071526936447e-08, "loss": 0.347, "step": 1221 }, { "epoch": 4.947368421052632, "grad_norm": 0.2139167392200068, "learning_rate": 1.3511682316509344e-08, "loss": 0.3511, "step": 1222 }, { "epoch": 4.951417004048583, "grad_norm": 0.1927739219938592, "learning_rate": 1.1513104534086605e-08, "loss": 0.3806, "step": 1223 }, { "epoch": 4.955465587044534, "grad_norm": 0.20488353474776855, "learning_rate": 9.67435416023843e-09, "loss": 0.3585, "step": 1224 }, { "epoch": 4.959514170040486, "grad_norm": 0.20417103117894225, "learning_rate": 7.995445897566178e-09, "loss": 0.3633, "step": 1225 }, { "epoch": 4.963562753036437, "grad_norm": 0.20630851328722893, "learning_rate": 6.476393170578021e-09, "loss": 0.3599, "step": 1226 }, { "epoch": 4.967611336032388, "grad_norm": 0.21325726011387477, "learning_rate": 5.11720812557348e-09, "loss": 0.3436, "step": 1227 }, { "epoch": 4.97165991902834, "grad_norm": 0.21040280743688147, "learning_rate": 3.917901630563492e-09, "loss": 0.3564, "step": 1228 }, { "epoch": 4.9757085020242915, "grad_norm": 0.19944621048687913, "learning_rate": 2.878483275170485e-09, "loss": 0.36, "step": 1229 }, { "epoch": 4.979757085020243, "grad_norm": 0.21043977625691263, "learning_rate": 1.998961370555108e-09, "loss": 0.3585, "step": 1230 }, { "epoch": 4.983805668016195, "grad_norm": 0.20418064856545418, "learning_rate": 1.2793429493518361e-09, "loss": 0.3721, "step": 1231 }, { "epoch": 4.987854251012146, "grad_norm": 0.21055287167829434, "learning_rate": 7.196337656112384e-10, "loss": 0.3472, "step": 1232 }, { "epoch": 4.991902834008097, "grad_norm": 0.21017948721909172, "learning_rate": 3.198382947511292e-10, "loss": 0.3563, "step": 1233 }, { "epoch": 4.995951417004049, "grad_norm": 0.1993477524127353, "learning_rate": 7.995973352770137e-11, "loss": 0.366, "step": 1234 }, { "epoch": 5.0, "grad_norm": 0.19543114127232603, "learning_rate": 0.0, "loss": 0.367, "step": 1235 }, { "epoch": 5.0, "step": 1235, "total_flos": 4.783951705282707e+18, "train_loss": 0.49450628289326964, "train_runtime": 29398.0301, "train_samples_per_second": 5.375, "train_steps_per_second": 0.042 } ], "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": 4.783951705282707e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }