Files
openthoughts3_100k_qwen25_1…/trainer_state.json
ModelHub XC fdddb0ddbf 初始化项目,由ModelHub XC社区提供模型
Model: mlfoundations-dev/openthoughts3_100k_qwen25_1b_bsz256_lr2e5_epochs5
Source: Original Platform
2026-06-26 19:33:13 +08:00

13728 lines
333 KiB
JSON

{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 5.0,
"eval_steps": 500,
"global_step": 1955,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0025575447570332483,
"grad_norm": 2.9562953287143814,
"learning_rate": 1.0204081632653061e-07,
"loss": 1.5213,
"step": 1
},
{
"epoch": 0.005115089514066497,
"grad_norm": 2.957074977095288,
"learning_rate": 2.0408163265306121e-07,
"loss": 1.4742,
"step": 2
},
{
"epoch": 0.0076726342710997444,
"grad_norm": 3.0195943091843875,
"learning_rate": 3.0612244897959183e-07,
"loss": 1.4948,
"step": 3
},
{
"epoch": 0.010230179028132993,
"grad_norm": 2.955601772064438,
"learning_rate": 4.0816326530612243e-07,
"loss": 1.4841,
"step": 4
},
{
"epoch": 0.01278772378516624,
"grad_norm": 2.9724831486674437,
"learning_rate": 5.102040816326531e-07,
"loss": 1.494,
"step": 5
},
{
"epoch": 0.015345268542199489,
"grad_norm": 2.9891106307727844,
"learning_rate": 6.122448979591837e-07,
"loss": 1.5063,
"step": 6
},
{
"epoch": 0.017902813299232736,
"grad_norm": 2.9117659939526934,
"learning_rate": 7.142857142857143e-07,
"loss": 1.4791,
"step": 7
},
{
"epoch": 0.020460358056265986,
"grad_norm": 2.90337467558492,
"learning_rate": 8.163265306122449e-07,
"loss": 1.4882,
"step": 8
},
{
"epoch": 0.023017902813299233,
"grad_norm": 2.872454943973889,
"learning_rate": 9.183673469387756e-07,
"loss": 1.5228,
"step": 9
},
{
"epoch": 0.02557544757033248,
"grad_norm": 2.8716382761013697,
"learning_rate": 1.0204081632653063e-06,
"loss": 1.5153,
"step": 10
},
{
"epoch": 0.028132992327365727,
"grad_norm": 2.6360453721548796,
"learning_rate": 1.122448979591837e-06,
"loss": 1.5046,
"step": 11
},
{
"epoch": 0.030690537084398978,
"grad_norm": 2.659598355667714,
"learning_rate": 1.2244897959183673e-06,
"loss": 1.4692,
"step": 12
},
{
"epoch": 0.03324808184143223,
"grad_norm": 2.5783985084733634,
"learning_rate": 1.3265306122448982e-06,
"loss": 1.5132,
"step": 13
},
{
"epoch": 0.03580562659846547,
"grad_norm": 2.049467948851294,
"learning_rate": 1.4285714285714286e-06,
"loss": 1.4473,
"step": 14
},
{
"epoch": 0.03836317135549872,
"grad_norm": 2.025687601863481,
"learning_rate": 1.5306122448979593e-06,
"loss": 1.4862,
"step": 15
},
{
"epoch": 0.04092071611253197,
"grad_norm": 1.9646128905085123,
"learning_rate": 1.6326530612244897e-06,
"loss": 1.4457,
"step": 16
},
{
"epoch": 0.043478260869565216,
"grad_norm": 1.9191066854928391,
"learning_rate": 1.7346938775510206e-06,
"loss": 1.4699,
"step": 17
},
{
"epoch": 0.04603580562659847,
"grad_norm": 1.8754519688248819,
"learning_rate": 1.8367346938775512e-06,
"loss": 1.4732,
"step": 18
},
{
"epoch": 0.04859335038363171,
"grad_norm": 1.3012814301728521,
"learning_rate": 1.938775510204082e-06,
"loss": 1.4474,
"step": 19
},
{
"epoch": 0.05115089514066496,
"grad_norm": 1.5591794317282675,
"learning_rate": 2.0408163265306125e-06,
"loss": 1.4366,
"step": 20
},
{
"epoch": 0.05370843989769821,
"grad_norm": 1.6331695295496573,
"learning_rate": 2.1428571428571427e-06,
"loss": 1.4239,
"step": 21
},
{
"epoch": 0.056265984654731455,
"grad_norm": 1.5966167406736418,
"learning_rate": 2.244897959183674e-06,
"loss": 1.4529,
"step": 22
},
{
"epoch": 0.058823529411764705,
"grad_norm": 1.4373932142776844,
"learning_rate": 2.3469387755102044e-06,
"loss": 1.4073,
"step": 23
},
{
"epoch": 0.061381074168797956,
"grad_norm": 1.3276581212533325,
"learning_rate": 2.4489795918367347e-06,
"loss": 1.4322,
"step": 24
},
{
"epoch": 0.0639386189258312,
"grad_norm": 1.0731846564216336,
"learning_rate": 2.5510204081632657e-06,
"loss": 1.4073,
"step": 25
},
{
"epoch": 0.06649616368286446,
"grad_norm": 1.238876393241825,
"learning_rate": 2.6530612244897964e-06,
"loss": 1.3989,
"step": 26
},
{
"epoch": 0.06905370843989769,
"grad_norm": 1.2629836696521368,
"learning_rate": 2.7551020408163266e-06,
"loss": 1.3804,
"step": 27
},
{
"epoch": 0.07161125319693094,
"grad_norm": 1.2621269804030673,
"learning_rate": 2.8571428571428573e-06,
"loss": 1.4052,
"step": 28
},
{
"epoch": 0.0741687979539642,
"grad_norm": 1.213554923104541,
"learning_rate": 2.959183673469388e-06,
"loss": 1.382,
"step": 29
},
{
"epoch": 0.07672634271099744,
"grad_norm": 1.1050135745029126,
"learning_rate": 3.0612244897959185e-06,
"loss": 1.3963,
"step": 30
},
{
"epoch": 0.0792838874680307,
"grad_norm": 0.9715895015186999,
"learning_rate": 3.1632653061224496e-06,
"loss": 1.3901,
"step": 31
},
{
"epoch": 0.08184143222506395,
"grad_norm": 0.8825544463358136,
"learning_rate": 3.2653061224489794e-06,
"loss": 1.363,
"step": 32
},
{
"epoch": 0.08439897698209718,
"grad_norm": 0.763331787510912,
"learning_rate": 3.3673469387755105e-06,
"loss": 1.3952,
"step": 33
},
{
"epoch": 0.08695652173913043,
"grad_norm": 0.6415924907748566,
"learning_rate": 3.469387755102041e-06,
"loss": 1.4103,
"step": 34
},
{
"epoch": 0.08951406649616368,
"grad_norm": 0.6967464439584855,
"learning_rate": 3.5714285714285718e-06,
"loss": 1.3459,
"step": 35
},
{
"epoch": 0.09207161125319693,
"grad_norm": 0.8908075465264809,
"learning_rate": 3.6734693877551024e-06,
"loss": 1.3561,
"step": 36
},
{
"epoch": 0.09462915601023018,
"grad_norm": 0.8747631888662198,
"learning_rate": 3.7755102040816327e-06,
"loss": 1.3694,
"step": 37
},
{
"epoch": 0.09718670076726342,
"grad_norm": 0.7588066982535068,
"learning_rate": 3.877551020408164e-06,
"loss": 1.3415,
"step": 38
},
{
"epoch": 0.09974424552429667,
"grad_norm": 0.6706725405381729,
"learning_rate": 3.979591836734694e-06,
"loss": 1.3571,
"step": 39
},
{
"epoch": 0.10230179028132992,
"grad_norm": 0.5639131487544589,
"learning_rate": 4.081632653061225e-06,
"loss": 1.2958,
"step": 40
},
{
"epoch": 0.10485933503836317,
"grad_norm": 0.5328548178092433,
"learning_rate": 4.183673469387755e-06,
"loss": 1.3227,
"step": 41
},
{
"epoch": 0.10741687979539642,
"grad_norm": 0.5772938103545907,
"learning_rate": 4.2857142857142855e-06,
"loss": 1.3212,
"step": 42
},
{
"epoch": 0.10997442455242967,
"grad_norm": 0.5924144289895023,
"learning_rate": 4.3877551020408165e-06,
"loss": 1.2923,
"step": 43
},
{
"epoch": 0.11253196930946291,
"grad_norm": 0.5904192016449847,
"learning_rate": 4.489795918367348e-06,
"loss": 1.3017,
"step": 44
},
{
"epoch": 0.11508951406649616,
"grad_norm": 0.5201728742501257,
"learning_rate": 4.591836734693878e-06,
"loss": 1.3013,
"step": 45
},
{
"epoch": 0.11764705882352941,
"grad_norm": 0.46964109225255846,
"learning_rate": 4.693877551020409e-06,
"loss": 1.3225,
"step": 46
},
{
"epoch": 0.12020460358056266,
"grad_norm": 0.4610564873689024,
"learning_rate": 4.795918367346939e-06,
"loss": 1.3221,
"step": 47
},
{
"epoch": 0.12276214833759591,
"grad_norm": 0.37401415057004755,
"learning_rate": 4.897959183673469e-06,
"loss": 1.291,
"step": 48
},
{
"epoch": 0.12531969309462915,
"grad_norm": 0.4024917885366837,
"learning_rate": 5e-06,
"loss": 1.304,
"step": 49
},
{
"epoch": 0.1278772378516624,
"grad_norm": 0.4489807884401599,
"learning_rate": 5.1020408163265315e-06,
"loss": 1.2735,
"step": 50
},
{
"epoch": 0.13043478260869565,
"grad_norm": 0.4407916383861822,
"learning_rate": 5.204081632653062e-06,
"loss": 1.2796,
"step": 51
},
{
"epoch": 0.1329923273657289,
"grad_norm": 0.3755938325328462,
"learning_rate": 5.306122448979593e-06,
"loss": 1.2591,
"step": 52
},
{
"epoch": 0.13554987212276215,
"grad_norm": 0.3579863910557438,
"learning_rate": 5.408163265306123e-06,
"loss": 1.2592,
"step": 53
},
{
"epoch": 0.13810741687979539,
"grad_norm": 0.36590626112420677,
"learning_rate": 5.510204081632653e-06,
"loss": 1.2958,
"step": 54
},
{
"epoch": 0.14066496163682865,
"grad_norm": 0.33001691546050266,
"learning_rate": 5.6122448979591834e-06,
"loss": 1.3075,
"step": 55
},
{
"epoch": 0.1432225063938619,
"grad_norm": 0.3442007478055813,
"learning_rate": 5.7142857142857145e-06,
"loss": 1.2947,
"step": 56
},
{
"epoch": 0.14578005115089515,
"grad_norm": 0.31990892696809964,
"learning_rate": 5.816326530612246e-06,
"loss": 1.2764,
"step": 57
},
{
"epoch": 0.1483375959079284,
"grad_norm": 0.29610380122523694,
"learning_rate": 5.918367346938776e-06,
"loss": 1.2911,
"step": 58
},
{
"epoch": 0.15089514066496162,
"grad_norm": 0.2800791150063646,
"learning_rate": 6.020408163265307e-06,
"loss": 1.2564,
"step": 59
},
{
"epoch": 0.1534526854219949,
"grad_norm": 0.24883718330799656,
"learning_rate": 6.122448979591837e-06,
"loss": 1.2802,
"step": 60
},
{
"epoch": 0.15601023017902813,
"grad_norm": 0.2689712120019464,
"learning_rate": 6.224489795918368e-06,
"loss": 1.2673,
"step": 61
},
{
"epoch": 0.1585677749360614,
"grad_norm": 0.274815756586181,
"learning_rate": 6.326530612244899e-06,
"loss": 1.2984,
"step": 62
},
{
"epoch": 0.16112531969309463,
"grad_norm": 0.24511037552821183,
"learning_rate": 6.4285714285714295e-06,
"loss": 1.2811,
"step": 63
},
{
"epoch": 0.1636828644501279,
"grad_norm": 0.2585673848534428,
"learning_rate": 6.530612244897959e-06,
"loss": 1.2752,
"step": 64
},
{
"epoch": 0.16624040920716113,
"grad_norm": 0.24726403234369912,
"learning_rate": 6.63265306122449e-06,
"loss": 1.2667,
"step": 65
},
{
"epoch": 0.16879795396419436,
"grad_norm": 0.2436298587258828,
"learning_rate": 6.734693877551021e-06,
"loss": 1.2279,
"step": 66
},
{
"epoch": 0.17135549872122763,
"grad_norm": 0.24268854362503556,
"learning_rate": 6.836734693877551e-06,
"loss": 1.2517,
"step": 67
},
{
"epoch": 0.17391304347826086,
"grad_norm": 0.2554114966704654,
"learning_rate": 6.938775510204082e-06,
"loss": 1.2277,
"step": 68
},
{
"epoch": 0.17647058823529413,
"grad_norm": 0.19396655425261772,
"learning_rate": 7.0408163265306125e-06,
"loss": 1.2119,
"step": 69
},
{
"epoch": 0.17902813299232737,
"grad_norm": 0.19737858451227866,
"learning_rate": 7.1428571428571436e-06,
"loss": 1.2234,
"step": 70
},
{
"epoch": 0.1815856777493606,
"grad_norm": 0.21921420023094632,
"learning_rate": 7.244897959183675e-06,
"loss": 1.2332,
"step": 71
},
{
"epoch": 0.18414322250639387,
"grad_norm": 0.20918098542181962,
"learning_rate": 7.346938775510205e-06,
"loss": 1.2476,
"step": 72
},
{
"epoch": 0.1867007672634271,
"grad_norm": 0.20509174967917101,
"learning_rate": 7.448979591836736e-06,
"loss": 1.2809,
"step": 73
},
{
"epoch": 0.18925831202046037,
"grad_norm": 0.20157359497446836,
"learning_rate": 7.551020408163265e-06,
"loss": 1.228,
"step": 74
},
{
"epoch": 0.1918158567774936,
"grad_norm": 0.2030800764293693,
"learning_rate": 7.653061224489796e-06,
"loss": 1.2256,
"step": 75
},
{
"epoch": 0.19437340153452684,
"grad_norm": 0.22457010766510804,
"learning_rate": 7.755102040816327e-06,
"loss": 1.2277,
"step": 76
},
{
"epoch": 0.1969309462915601,
"grad_norm": 0.192665701729149,
"learning_rate": 7.857142857142858e-06,
"loss": 1.2383,
"step": 77
},
{
"epoch": 0.19948849104859334,
"grad_norm": 0.19152870646216824,
"learning_rate": 7.959183673469388e-06,
"loss": 1.2176,
"step": 78
},
{
"epoch": 0.2020460358056266,
"grad_norm": 0.19648868962913657,
"learning_rate": 8.06122448979592e-06,
"loss": 1.2119,
"step": 79
},
{
"epoch": 0.20460358056265984,
"grad_norm": 0.20421924729381744,
"learning_rate": 8.16326530612245e-06,
"loss": 1.2285,
"step": 80
},
{
"epoch": 0.2071611253196931,
"grad_norm": 0.18789494211610624,
"learning_rate": 8.26530612244898e-06,
"loss": 1.212,
"step": 81
},
{
"epoch": 0.20971867007672634,
"grad_norm": 0.2092465434891838,
"learning_rate": 8.36734693877551e-06,
"loss": 1.2091,
"step": 82
},
{
"epoch": 0.21227621483375958,
"grad_norm": 0.20515739317387488,
"learning_rate": 8.469387755102042e-06,
"loss": 1.2235,
"step": 83
},
{
"epoch": 0.21483375959079284,
"grad_norm": 0.20337541481235902,
"learning_rate": 8.571428571428571e-06,
"loss": 1.2183,
"step": 84
},
{
"epoch": 0.21739130434782608,
"grad_norm": 0.1802747600910944,
"learning_rate": 8.673469387755103e-06,
"loss": 1.2682,
"step": 85
},
{
"epoch": 0.21994884910485935,
"grad_norm": 0.18621854583865133,
"learning_rate": 8.775510204081633e-06,
"loss": 1.2185,
"step": 86
},
{
"epoch": 0.22250639386189258,
"grad_norm": 0.1982015852510532,
"learning_rate": 8.877551020408163e-06,
"loss": 1.2255,
"step": 87
},
{
"epoch": 0.22506393861892582,
"grad_norm": 0.16662352110298306,
"learning_rate": 8.979591836734695e-06,
"loss": 1.2494,
"step": 88
},
{
"epoch": 0.22762148337595908,
"grad_norm": 0.20033046650600175,
"learning_rate": 9.081632653061225e-06,
"loss": 1.2099,
"step": 89
},
{
"epoch": 0.23017902813299232,
"grad_norm": 0.19772324219486356,
"learning_rate": 9.183673469387756e-06,
"loss": 1.2398,
"step": 90
},
{
"epoch": 0.23273657289002558,
"grad_norm": 0.17627317445341492,
"learning_rate": 9.285714285714288e-06,
"loss": 1.2359,
"step": 91
},
{
"epoch": 0.23529411764705882,
"grad_norm": 0.2000488853272216,
"learning_rate": 9.387755102040818e-06,
"loss": 1.2377,
"step": 92
},
{
"epoch": 0.23785166240409208,
"grad_norm": 0.18512197433512323,
"learning_rate": 9.489795918367348e-06,
"loss": 1.2204,
"step": 93
},
{
"epoch": 0.24040920716112532,
"grad_norm": 0.21513166102817025,
"learning_rate": 9.591836734693878e-06,
"loss": 1.2414,
"step": 94
},
{
"epoch": 0.24296675191815856,
"grad_norm": 0.18497143829689744,
"learning_rate": 9.693877551020408e-06,
"loss": 1.1886,
"step": 95
},
{
"epoch": 0.24552429667519182,
"grad_norm": 0.2045160941166778,
"learning_rate": 9.795918367346939e-06,
"loss": 1.2282,
"step": 96
},
{
"epoch": 0.24808184143222506,
"grad_norm": 0.19235390291361945,
"learning_rate": 9.89795918367347e-06,
"loss": 1.2296,
"step": 97
},
{
"epoch": 0.2506393861892583,
"grad_norm": 0.21361682704534116,
"learning_rate": 1e-05,
"loss": 1.2001,
"step": 98
},
{
"epoch": 0.2531969309462916,
"grad_norm": 0.17195039095079748,
"learning_rate": 1.0102040816326531e-05,
"loss": 1.1982,
"step": 99
},
{
"epoch": 0.2557544757033248,
"grad_norm": 0.19990564719956827,
"learning_rate": 1.0204081632653063e-05,
"loss": 1.1914,
"step": 100
},
{
"epoch": 0.25831202046035806,
"grad_norm": 0.18409790697604989,
"learning_rate": 1.0306122448979591e-05,
"loss": 1.2125,
"step": 101
},
{
"epoch": 0.2608695652173913,
"grad_norm": 0.2010207370883571,
"learning_rate": 1.0408163265306123e-05,
"loss": 1.2192,
"step": 102
},
{
"epoch": 0.26342710997442453,
"grad_norm": 0.24154477700771743,
"learning_rate": 1.0510204081632654e-05,
"loss": 1.189,
"step": 103
},
{
"epoch": 0.2659846547314578,
"grad_norm": 0.19539728509614046,
"learning_rate": 1.0612244897959186e-05,
"loss": 1.1791,
"step": 104
},
{
"epoch": 0.26854219948849106,
"grad_norm": 0.2809106862940922,
"learning_rate": 1.0714285714285714e-05,
"loss": 1.1866,
"step": 105
},
{
"epoch": 0.2710997442455243,
"grad_norm": 0.18139724102505636,
"learning_rate": 1.0816326530612246e-05,
"loss": 1.1772,
"step": 106
},
{
"epoch": 0.27365728900255754,
"grad_norm": 0.2944051456882037,
"learning_rate": 1.0918367346938776e-05,
"loss": 1.2043,
"step": 107
},
{
"epoch": 0.27621483375959077,
"grad_norm": 0.18837903247625115,
"learning_rate": 1.1020408163265306e-05,
"loss": 1.1831,
"step": 108
},
{
"epoch": 0.27877237851662406,
"grad_norm": 0.24490442547474545,
"learning_rate": 1.1122448979591838e-05,
"loss": 1.2072,
"step": 109
},
{
"epoch": 0.2813299232736573,
"grad_norm": 0.18434497663730703,
"learning_rate": 1.1224489795918367e-05,
"loss": 1.2077,
"step": 110
},
{
"epoch": 0.28388746803069054,
"grad_norm": 0.2023995573064504,
"learning_rate": 1.1326530612244899e-05,
"loss": 1.2113,
"step": 111
},
{
"epoch": 0.2864450127877238,
"grad_norm": 0.2232631442545948,
"learning_rate": 1.1428571428571429e-05,
"loss": 1.199,
"step": 112
},
{
"epoch": 0.289002557544757,
"grad_norm": 0.19538302737828642,
"learning_rate": 1.1530612244897961e-05,
"loss": 1.1707,
"step": 113
},
{
"epoch": 0.2915601023017903,
"grad_norm": 0.2076715375956596,
"learning_rate": 1.1632653061224491e-05,
"loss": 1.1996,
"step": 114
},
{
"epoch": 0.29411764705882354,
"grad_norm": 0.2291360055402482,
"learning_rate": 1.1734693877551021e-05,
"loss": 1.1818,
"step": 115
},
{
"epoch": 0.2966751918158568,
"grad_norm": 0.22247638512056675,
"learning_rate": 1.1836734693877552e-05,
"loss": 1.1899,
"step": 116
},
{
"epoch": 0.29923273657289,
"grad_norm": 0.23191223669707034,
"learning_rate": 1.1938775510204084e-05,
"loss": 1.1822,
"step": 117
},
{
"epoch": 0.30179028132992325,
"grad_norm": 0.2705601798192164,
"learning_rate": 1.2040816326530614e-05,
"loss": 1.2338,
"step": 118
},
{
"epoch": 0.30434782608695654,
"grad_norm": 0.2474348689952774,
"learning_rate": 1.2142857142857142e-05,
"loss": 1.1949,
"step": 119
},
{
"epoch": 0.3069053708439898,
"grad_norm": 0.20663103569329155,
"learning_rate": 1.2244897959183674e-05,
"loss": 1.2006,
"step": 120
},
{
"epoch": 0.309462915601023,
"grad_norm": 0.2605886951080686,
"learning_rate": 1.2346938775510204e-05,
"loss": 1.2164,
"step": 121
},
{
"epoch": 0.31202046035805625,
"grad_norm": 0.2181457069786774,
"learning_rate": 1.2448979591836736e-05,
"loss": 1.1664,
"step": 122
},
{
"epoch": 0.3145780051150895,
"grad_norm": 0.3157714554732324,
"learning_rate": 1.2551020408163267e-05,
"loss": 1.1875,
"step": 123
},
{
"epoch": 0.3171355498721228,
"grad_norm": 0.2775822065984946,
"learning_rate": 1.2653061224489798e-05,
"loss": 1.1822,
"step": 124
},
{
"epoch": 0.319693094629156,
"grad_norm": 0.25536478737195145,
"learning_rate": 1.2755102040816327e-05,
"loss": 1.1623,
"step": 125
},
{
"epoch": 0.32225063938618925,
"grad_norm": 0.38468633827614823,
"learning_rate": 1.2857142857142859e-05,
"loss": 1.2188,
"step": 126
},
{
"epoch": 0.3248081841432225,
"grad_norm": 0.287878457956867,
"learning_rate": 1.2959183673469389e-05,
"loss": 1.1605,
"step": 127
},
{
"epoch": 0.3273657289002558,
"grad_norm": 0.3074138761550165,
"learning_rate": 1.3061224489795918e-05,
"loss": 1.1804,
"step": 128
},
{
"epoch": 0.329923273657289,
"grad_norm": 0.2866479879938462,
"learning_rate": 1.316326530612245e-05,
"loss": 1.1733,
"step": 129
},
{
"epoch": 0.33248081841432225,
"grad_norm": 0.32148222861310927,
"learning_rate": 1.326530612244898e-05,
"loss": 1.2038,
"step": 130
},
{
"epoch": 0.3350383631713555,
"grad_norm": 0.22529099781853634,
"learning_rate": 1.3367346938775512e-05,
"loss": 1.1673,
"step": 131
},
{
"epoch": 0.3375959079283887,
"grad_norm": 0.2609715115506065,
"learning_rate": 1.3469387755102042e-05,
"loss": 1.2253,
"step": 132
},
{
"epoch": 0.340153452685422,
"grad_norm": 0.3063675380420315,
"learning_rate": 1.3571428571428574e-05,
"loss": 1.198,
"step": 133
},
{
"epoch": 0.34271099744245526,
"grad_norm": 0.22973985204151504,
"learning_rate": 1.3673469387755102e-05,
"loss": 1.1671,
"step": 134
},
{
"epoch": 0.3452685421994885,
"grad_norm": 0.20757849081036897,
"learning_rate": 1.3775510204081634e-05,
"loss": 1.2261,
"step": 135
},
{
"epoch": 0.34782608695652173,
"grad_norm": 0.239418122200512,
"learning_rate": 1.3877551020408165e-05,
"loss": 1.1854,
"step": 136
},
{
"epoch": 0.35038363171355497,
"grad_norm": 0.2373110786708978,
"learning_rate": 1.3979591836734696e-05,
"loss": 1.1972,
"step": 137
},
{
"epoch": 0.35294117647058826,
"grad_norm": 0.21952289616465737,
"learning_rate": 1.4081632653061225e-05,
"loss": 1.1841,
"step": 138
},
{
"epoch": 0.3554987212276215,
"grad_norm": 0.24365294125993373,
"learning_rate": 1.4183673469387755e-05,
"loss": 1.1582,
"step": 139
},
{
"epoch": 0.35805626598465473,
"grad_norm": 0.28057490691552545,
"learning_rate": 1.4285714285714287e-05,
"loss": 1.217,
"step": 140
},
{
"epoch": 0.36061381074168797,
"grad_norm": 0.2858217046456728,
"learning_rate": 1.4387755102040817e-05,
"loss": 1.1303,
"step": 141
},
{
"epoch": 0.3631713554987212,
"grad_norm": 0.25139449669336106,
"learning_rate": 1.448979591836735e-05,
"loss": 1.1808,
"step": 142
},
{
"epoch": 0.3657289002557545,
"grad_norm": 0.264472202641012,
"learning_rate": 1.4591836734693878e-05,
"loss": 1.2083,
"step": 143
},
{
"epoch": 0.36828644501278773,
"grad_norm": 0.3298441325989216,
"learning_rate": 1.469387755102041e-05,
"loss": 1.1761,
"step": 144
},
{
"epoch": 0.37084398976982097,
"grad_norm": 0.26597491650333793,
"learning_rate": 1.479591836734694e-05,
"loss": 1.1887,
"step": 145
},
{
"epoch": 0.3734015345268542,
"grad_norm": 0.21965241642758554,
"learning_rate": 1.4897959183673472e-05,
"loss": 1.1735,
"step": 146
},
{
"epoch": 0.37595907928388744,
"grad_norm": 0.25221490386812995,
"learning_rate": 1.5000000000000002e-05,
"loss": 1.2087,
"step": 147
},
{
"epoch": 0.37851662404092073,
"grad_norm": 0.2393195787833758,
"learning_rate": 1.510204081632653e-05,
"loss": 1.1688,
"step": 148
},
{
"epoch": 0.38107416879795397,
"grad_norm": 0.2753716321794055,
"learning_rate": 1.5204081632653063e-05,
"loss": 1.1553,
"step": 149
},
{
"epoch": 0.3836317135549872,
"grad_norm": 0.21247095213573716,
"learning_rate": 1.530612244897959e-05,
"loss": 1.1664,
"step": 150
},
{
"epoch": 0.38618925831202044,
"grad_norm": 0.2339506540148249,
"learning_rate": 1.5408163265306123e-05,
"loss": 1.17,
"step": 151
},
{
"epoch": 0.3887468030690537,
"grad_norm": 0.26795973798728384,
"learning_rate": 1.5510204081632655e-05,
"loss": 1.175,
"step": 152
},
{
"epoch": 0.391304347826087,
"grad_norm": 0.2583891394938216,
"learning_rate": 1.5612244897959187e-05,
"loss": 1.1646,
"step": 153
},
{
"epoch": 0.3938618925831202,
"grad_norm": 0.2686074219032705,
"learning_rate": 1.5714285714285715e-05,
"loss": 1.1698,
"step": 154
},
{
"epoch": 0.39641943734015345,
"grad_norm": 0.2286828659609244,
"learning_rate": 1.5816326530612247e-05,
"loss": 1.1821,
"step": 155
},
{
"epoch": 0.3989769820971867,
"grad_norm": 0.2476552598028532,
"learning_rate": 1.5918367346938776e-05,
"loss": 1.1864,
"step": 156
},
{
"epoch": 0.40153452685422,
"grad_norm": 0.3028181273764634,
"learning_rate": 1.6020408163265308e-05,
"loss": 1.1999,
"step": 157
},
{
"epoch": 0.4040920716112532,
"grad_norm": 0.3392361145642557,
"learning_rate": 1.612244897959184e-05,
"loss": 1.1928,
"step": 158
},
{
"epoch": 0.40664961636828645,
"grad_norm": 0.23749781222599484,
"learning_rate": 1.6224489795918368e-05,
"loss": 1.1455,
"step": 159
},
{
"epoch": 0.4092071611253197,
"grad_norm": 0.27301888454203366,
"learning_rate": 1.63265306122449e-05,
"loss": 1.1657,
"step": 160
},
{
"epoch": 0.4117647058823529,
"grad_norm": 0.3292983030079545,
"learning_rate": 1.642857142857143e-05,
"loss": 1.1598,
"step": 161
},
{
"epoch": 0.4143222506393862,
"grad_norm": 0.5337081556820991,
"learning_rate": 1.653061224489796e-05,
"loss": 1.1565,
"step": 162
},
{
"epoch": 0.41687979539641945,
"grad_norm": 0.45293962184506315,
"learning_rate": 1.6632653061224492e-05,
"loss": 1.1594,
"step": 163
},
{
"epoch": 0.4194373401534527,
"grad_norm": 0.4328651118135115,
"learning_rate": 1.673469387755102e-05,
"loss": 1.1699,
"step": 164
},
{
"epoch": 0.4219948849104859,
"grad_norm": 0.3432892281672048,
"learning_rate": 1.6836734693877553e-05,
"loss": 1.1459,
"step": 165
},
{
"epoch": 0.42455242966751916,
"grad_norm": 0.2730126122517006,
"learning_rate": 1.6938775510204085e-05,
"loss": 1.1667,
"step": 166
},
{
"epoch": 0.42710997442455245,
"grad_norm": 0.306031348484845,
"learning_rate": 1.7040816326530613e-05,
"loss": 1.1642,
"step": 167
},
{
"epoch": 0.4296675191815857,
"grad_norm": 0.3825044478602271,
"learning_rate": 1.7142857142857142e-05,
"loss": 1.1741,
"step": 168
},
{
"epoch": 0.4322250639386189,
"grad_norm": 0.3319946152258406,
"learning_rate": 1.7244897959183674e-05,
"loss": 1.1722,
"step": 169
},
{
"epoch": 0.43478260869565216,
"grad_norm": 0.21336378841100664,
"learning_rate": 1.7346938775510206e-05,
"loss": 1.1513,
"step": 170
},
{
"epoch": 0.4373401534526854,
"grad_norm": 0.2584789415828712,
"learning_rate": 1.7448979591836738e-05,
"loss": 1.1641,
"step": 171
},
{
"epoch": 0.4398976982097187,
"grad_norm": 0.3035587738680554,
"learning_rate": 1.7551020408163266e-05,
"loss": 1.1615,
"step": 172
},
{
"epoch": 0.4424552429667519,
"grad_norm": 0.3150232598756255,
"learning_rate": 1.7653061224489798e-05,
"loss": 1.1808,
"step": 173
},
{
"epoch": 0.44501278772378516,
"grad_norm": 0.3546603428284164,
"learning_rate": 1.7755102040816327e-05,
"loss": 1.1897,
"step": 174
},
{
"epoch": 0.4475703324808184,
"grad_norm": 0.34889584036889865,
"learning_rate": 1.785714285714286e-05,
"loss": 1.161,
"step": 175
},
{
"epoch": 0.45012787723785164,
"grad_norm": 0.29454291072360017,
"learning_rate": 1.795918367346939e-05,
"loss": 1.1912,
"step": 176
},
{
"epoch": 0.45268542199488493,
"grad_norm": 0.40100102719618086,
"learning_rate": 1.806122448979592e-05,
"loss": 1.1648,
"step": 177
},
{
"epoch": 0.45524296675191817,
"grad_norm": 0.4059968451876151,
"learning_rate": 1.816326530612245e-05,
"loss": 1.1639,
"step": 178
},
{
"epoch": 0.4578005115089514,
"grad_norm": 0.37064317174148603,
"learning_rate": 1.826530612244898e-05,
"loss": 1.1479,
"step": 179
},
{
"epoch": 0.46035805626598464,
"grad_norm": 0.37396234314183074,
"learning_rate": 1.836734693877551e-05,
"loss": 1.1568,
"step": 180
},
{
"epoch": 0.4629156010230179,
"grad_norm": 0.45716162446267244,
"learning_rate": 1.8469387755102043e-05,
"loss": 1.1822,
"step": 181
},
{
"epoch": 0.46547314578005117,
"grad_norm": 0.36679016991278174,
"learning_rate": 1.8571428571428575e-05,
"loss": 1.1579,
"step": 182
},
{
"epoch": 0.4680306905370844,
"grad_norm": 0.35413758345531376,
"learning_rate": 1.8673469387755104e-05,
"loss": 1.17,
"step": 183
},
{
"epoch": 0.47058823529411764,
"grad_norm": 0.357746233671763,
"learning_rate": 1.8775510204081636e-05,
"loss": 1.1657,
"step": 184
},
{
"epoch": 0.4731457800511509,
"grad_norm": 0.30987744196180955,
"learning_rate": 1.8877551020408164e-05,
"loss": 1.1727,
"step": 185
},
{
"epoch": 0.47570332480818417,
"grad_norm": 0.3008253966047084,
"learning_rate": 1.8979591836734696e-05,
"loss": 1.1697,
"step": 186
},
{
"epoch": 0.4782608695652174,
"grad_norm": 0.26780657180049305,
"learning_rate": 1.9081632653061225e-05,
"loss": 1.1504,
"step": 187
},
{
"epoch": 0.48081841432225064,
"grad_norm": 0.3041554719196245,
"learning_rate": 1.9183673469387756e-05,
"loss": 1.1771,
"step": 188
},
{
"epoch": 0.4833759590792839,
"grad_norm": 0.28069002744383614,
"learning_rate": 1.928571428571429e-05,
"loss": 1.1576,
"step": 189
},
{
"epoch": 0.4859335038363171,
"grad_norm": 0.2468377630882404,
"learning_rate": 1.9387755102040817e-05,
"loss": 1.1597,
"step": 190
},
{
"epoch": 0.4884910485933504,
"grad_norm": 0.30179882714603656,
"learning_rate": 1.948979591836735e-05,
"loss": 1.1084,
"step": 191
},
{
"epoch": 0.49104859335038364,
"grad_norm": 0.37503237335205775,
"learning_rate": 1.9591836734693877e-05,
"loss": 1.1505,
"step": 192
},
{
"epoch": 0.4936061381074169,
"grad_norm": 0.44233118769859003,
"learning_rate": 1.969387755102041e-05,
"loss": 1.1214,
"step": 193
},
{
"epoch": 0.4961636828644501,
"grad_norm": 0.5601563317495414,
"learning_rate": 1.979591836734694e-05,
"loss": 1.1197,
"step": 194
},
{
"epoch": 0.49872122762148335,
"grad_norm": 0.5687537323400834,
"learning_rate": 1.9897959183673473e-05,
"loss": 1.195,
"step": 195
},
{
"epoch": 0.5012787723785166,
"grad_norm": 0.4873305401442818,
"learning_rate": 2e-05,
"loss": 1.1522,
"step": 196
},
{
"epoch": 0.5038363171355499,
"grad_norm": 0.3556383631744906,
"learning_rate": 1.9999984050834843e-05,
"loss": 1.1393,
"step": 197
},
{
"epoch": 0.5063938618925832,
"grad_norm": 0.3842008338970268,
"learning_rate": 1.999993620339024e-05,
"loss": 1.172,
"step": 198
},
{
"epoch": 0.5089514066496164,
"grad_norm": 0.4125503709774857,
"learning_rate": 1.9999856457818812e-05,
"loss": 1.1374,
"step": 199
},
{
"epoch": 0.5115089514066496,
"grad_norm": 0.3795131034135739,
"learning_rate": 1.9999744814374943e-05,
"loss": 1.1511,
"step": 200
},
{
"epoch": 0.5140664961636828,
"grad_norm": 0.37179713266984565,
"learning_rate": 1.999960127341475e-05,
"loss": 1.1342,
"step": 201
},
{
"epoch": 0.5166240409207161,
"grad_norm": 0.36464040525697683,
"learning_rate": 1.9999425835396113e-05,
"loss": 1.1282,
"step": 202
},
{
"epoch": 0.5191815856777494,
"grad_norm": 0.2913800358603054,
"learning_rate": 1.9999218500878645e-05,
"loss": 1.1589,
"step": 203
},
{
"epoch": 0.5217391304347826,
"grad_norm": 0.2591052993661217,
"learning_rate": 1.9998979270523704e-05,
"loss": 1.1291,
"step": 204
},
{
"epoch": 0.5242966751918159,
"grad_norm": 0.337615514356955,
"learning_rate": 1.99987081450944e-05,
"loss": 1.1529,
"step": 205
},
{
"epoch": 0.5268542199488491,
"grad_norm": 0.28380607304098043,
"learning_rate": 1.999840512545558e-05,
"loss": 1.1418,
"step": 206
},
{
"epoch": 0.5294117647058824,
"grad_norm": 0.2806782620501295,
"learning_rate": 1.9998070212573823e-05,
"loss": 1.1596,
"step": 207
},
{
"epoch": 0.5319693094629157,
"grad_norm": 0.3717899217291509,
"learning_rate": 1.9997703407517442e-05,
"loss": 1.1457,
"step": 208
},
{
"epoch": 0.5345268542199488,
"grad_norm": 0.322823080295276,
"learning_rate": 1.999730471145649e-05,
"loss": 1.135,
"step": 209
},
{
"epoch": 0.5370843989769821,
"grad_norm": 0.45281566817756946,
"learning_rate": 1.999687412566274e-05,
"loss": 1.1286,
"step": 210
},
{
"epoch": 0.5396419437340153,
"grad_norm": 0.46661955735695343,
"learning_rate": 1.9996411651509683e-05,
"loss": 1.1488,
"step": 211
},
{
"epoch": 0.5421994884910486,
"grad_norm": 0.507809212839347,
"learning_rate": 1.999591729047254e-05,
"loss": 1.1172,
"step": 212
},
{
"epoch": 0.5447570332480819,
"grad_norm": 0.5943303015975859,
"learning_rate": 1.9995391044128242e-05,
"loss": 1.162,
"step": 213
},
{
"epoch": 0.5473145780051151,
"grad_norm": 0.6223689255513681,
"learning_rate": 1.9994832914155417e-05,
"loss": 1.1111,
"step": 214
},
{
"epoch": 0.5498721227621484,
"grad_norm": 0.5867365176554278,
"learning_rate": 1.9994242902334418e-05,
"loss": 1.118,
"step": 215
},
{
"epoch": 0.5524296675191815,
"grad_norm": 0.4772422762081861,
"learning_rate": 1.9993621010547277e-05,
"loss": 1.1515,
"step": 216
},
{
"epoch": 0.5549872122762148,
"grad_norm": 0.2593743678758839,
"learning_rate": 1.9992967240777727e-05,
"loss": 1.125,
"step": 217
},
{
"epoch": 0.5575447570332481,
"grad_norm": 0.37039422327125837,
"learning_rate": 1.9992281595111186e-05,
"loss": 1.0982,
"step": 218
},
{
"epoch": 0.5601023017902813,
"grad_norm": 0.43886132426547786,
"learning_rate": 1.9991564075734746e-05,
"loss": 1.121,
"step": 219
},
{
"epoch": 0.5626598465473146,
"grad_norm": 0.5436094329934847,
"learning_rate": 1.9990814684937177e-05,
"loss": 1.1759,
"step": 220
},
{
"epoch": 0.5652173913043478,
"grad_norm": 0.4981980358292973,
"learning_rate": 1.9990033425108906e-05,
"loss": 1.1183,
"step": 221
},
{
"epoch": 0.5677749360613811,
"grad_norm": 0.3910510290404881,
"learning_rate": 1.998922029874203e-05,
"loss": 1.1193,
"step": 222
},
{
"epoch": 0.5703324808184144,
"grad_norm": 0.390896851403731,
"learning_rate": 1.9988375308430275e-05,
"loss": 1.1249,
"step": 223
},
{
"epoch": 0.5728900255754475,
"grad_norm": 0.6251368420646798,
"learning_rate": 1.9987498456869025e-05,
"loss": 1.1553,
"step": 224
},
{
"epoch": 0.5754475703324808,
"grad_norm": 0.5868353015562519,
"learning_rate": 1.9986589746855295e-05,
"loss": 1.1531,
"step": 225
},
{
"epoch": 0.578005115089514,
"grad_norm": 0.3394930524201935,
"learning_rate": 1.998564918128771e-05,
"loss": 1.1252,
"step": 226
},
{
"epoch": 0.5805626598465473,
"grad_norm": 0.3795419225049313,
"learning_rate": 1.998467676316652e-05,
"loss": 1.1352,
"step": 227
},
{
"epoch": 0.5831202046035806,
"grad_norm": 0.5793565342648433,
"learning_rate": 1.9983672495593577e-05,
"loss": 1.1211,
"step": 228
},
{
"epoch": 0.5856777493606138,
"grad_norm": 0.4466950715738831,
"learning_rate": 1.9982636381772328e-05,
"loss": 1.14,
"step": 229
},
{
"epoch": 0.5882352941176471,
"grad_norm": 0.2812697561922094,
"learning_rate": 1.99815684250078e-05,
"loss": 1.1445,
"step": 230
},
{
"epoch": 0.5907928388746803,
"grad_norm": 0.29831474191094953,
"learning_rate": 1.9980468628706606e-05,
"loss": 1.1456,
"step": 231
},
{
"epoch": 0.5933503836317136,
"grad_norm": 0.32451111550319006,
"learning_rate": 1.9979336996376896e-05,
"loss": 1.1299,
"step": 232
},
{
"epoch": 0.5959079283887468,
"grad_norm": 0.2784540337914921,
"learning_rate": 1.99781735316284e-05,
"loss": 1.1344,
"step": 233
},
{
"epoch": 0.59846547314578,
"grad_norm": 0.2539011792274416,
"learning_rate": 1.997697823817237e-05,
"loss": 1.0922,
"step": 234
},
{
"epoch": 0.6010230179028133,
"grad_norm": 0.29497931492258306,
"learning_rate": 1.99757511198216e-05,
"loss": 1.1096,
"step": 235
},
{
"epoch": 0.6035805626598465,
"grad_norm": 0.35829886118674764,
"learning_rate": 1.997449218049039e-05,
"loss": 1.1395,
"step": 236
},
{
"epoch": 0.6061381074168798,
"grad_norm": 0.2898322186591816,
"learning_rate": 1.9973201424194544e-05,
"loss": 1.1245,
"step": 237
},
{
"epoch": 0.6086956521739131,
"grad_norm": 0.31225838552243906,
"learning_rate": 1.997187885505136e-05,
"loss": 1.1064,
"step": 238
},
{
"epoch": 0.6112531969309463,
"grad_norm": 0.3245053547418433,
"learning_rate": 1.997052447727961e-05,
"loss": 1.1517,
"step": 239
},
{
"epoch": 0.6138107416879796,
"grad_norm": 0.3043163987443152,
"learning_rate": 1.996913829519954e-05,
"loss": 1.1178,
"step": 240
},
{
"epoch": 0.6163682864450127,
"grad_norm": 0.354199627134913,
"learning_rate": 1.996772031323283e-05,
"loss": 1.1105,
"step": 241
},
{
"epoch": 0.618925831202046,
"grad_norm": 0.46016480703794116,
"learning_rate": 1.9966270535902618e-05,
"loss": 1.1373,
"step": 242
},
{
"epoch": 0.6214833759590793,
"grad_norm": 0.42309562067979195,
"learning_rate": 1.9964788967833438e-05,
"loss": 1.1335,
"step": 243
},
{
"epoch": 0.6240409207161125,
"grad_norm": 0.33036623410100835,
"learning_rate": 1.9963275613751255e-05,
"loss": 1.1791,
"step": 244
},
{
"epoch": 0.6265984654731458,
"grad_norm": 0.30006259434395505,
"learning_rate": 1.996173047848341e-05,
"loss": 1.138,
"step": 245
},
{
"epoch": 0.629156010230179,
"grad_norm": 0.32437525688350793,
"learning_rate": 1.996015356695863e-05,
"loss": 1.1343,
"step": 246
},
{
"epoch": 0.6317135549872123,
"grad_norm": 0.41288631390208946,
"learning_rate": 1.9958544884207e-05,
"loss": 1.127,
"step": 247
},
{
"epoch": 0.6342710997442456,
"grad_norm": 0.3784448720424316,
"learning_rate": 1.9956904435359945e-05,
"loss": 1.1735,
"step": 248
},
{
"epoch": 0.6368286445012787,
"grad_norm": 0.41447667455758297,
"learning_rate": 1.9955232225650223e-05,
"loss": 1.1535,
"step": 249
},
{
"epoch": 0.639386189258312,
"grad_norm": 0.43590429505717426,
"learning_rate": 1.9953528260411912e-05,
"loss": 1.1335,
"step": 250
},
{
"epoch": 0.6419437340153452,
"grad_norm": 0.34398920147187817,
"learning_rate": 1.9951792545080368e-05,
"loss": 1.1401,
"step": 251
},
{
"epoch": 0.6445012787723785,
"grad_norm": 0.4905800118095281,
"learning_rate": 1.995002508519223e-05,
"loss": 1.1454,
"step": 252
},
{
"epoch": 0.6470588235294118,
"grad_norm": 0.5410347720983003,
"learning_rate": 1.9948225886385415e-05,
"loss": 1.124,
"step": 253
},
{
"epoch": 0.649616368286445,
"grad_norm": 0.31072613789563314,
"learning_rate": 1.9946394954399055e-05,
"loss": 1.1745,
"step": 254
},
{
"epoch": 0.6521739130434783,
"grad_norm": 0.4693794451014107,
"learning_rate": 1.994453229507352e-05,
"loss": 1.1316,
"step": 255
},
{
"epoch": 0.6547314578005116,
"grad_norm": 0.5861071321893766,
"learning_rate": 1.9942637914350378e-05,
"loss": 1.1208,
"step": 256
},
{
"epoch": 0.6572890025575447,
"grad_norm": 0.4821820368779032,
"learning_rate": 1.9940711818272395e-05,
"loss": 1.156,
"step": 257
},
{
"epoch": 0.659846547314578,
"grad_norm": 0.34305622387894413,
"learning_rate": 1.993875401298349e-05,
"loss": 1.1182,
"step": 258
},
{
"epoch": 0.6624040920716112,
"grad_norm": 0.32785265355630766,
"learning_rate": 1.993676450472874e-05,
"loss": 1.1447,
"step": 259
},
{
"epoch": 0.6649616368286445,
"grad_norm": 0.31389753052349284,
"learning_rate": 1.993474329985434e-05,
"loss": 1.1273,
"step": 260
},
{
"epoch": 0.6675191815856778,
"grad_norm": 0.3970391405357666,
"learning_rate": 1.99326904048076e-05,
"loss": 1.0992,
"step": 261
},
{
"epoch": 0.670076726342711,
"grad_norm": 0.38002058368690567,
"learning_rate": 1.9930605826136904e-05,
"loss": 1.1151,
"step": 262
},
{
"epoch": 0.6726342710997443,
"grad_norm": 0.41881643054155515,
"learning_rate": 1.992848957049172e-05,
"loss": 1.1594,
"step": 263
},
{
"epoch": 0.6751918158567775,
"grad_norm": 0.4432367430176361,
"learning_rate": 1.9926341644622544e-05,
"loss": 1.1374,
"step": 264
},
{
"epoch": 0.6777493606138107,
"grad_norm": 0.29540032341942135,
"learning_rate": 1.9924162055380905e-05,
"loss": 1.1654,
"step": 265
},
{
"epoch": 0.680306905370844,
"grad_norm": 0.42262678251523295,
"learning_rate": 1.9921950809719326e-05,
"loss": 1.1324,
"step": 266
},
{
"epoch": 0.6828644501278772,
"grad_norm": 0.46439800650172125,
"learning_rate": 1.991970791469131e-05,
"loss": 1.0858,
"step": 267
},
{
"epoch": 0.6854219948849105,
"grad_norm": 0.4545225924725631,
"learning_rate": 1.991743337745132e-05,
"loss": 1.13,
"step": 268
},
{
"epoch": 0.6879795396419437,
"grad_norm": 0.4503197148218845,
"learning_rate": 1.991512720525475e-05,
"loss": 1.1065,
"step": 269
},
{
"epoch": 0.690537084398977,
"grad_norm": 0.345808256647908,
"learning_rate": 1.9912789405457907e-05,
"loss": 1.1469,
"step": 270
},
{
"epoch": 0.6930946291560103,
"grad_norm": 0.45309494180778404,
"learning_rate": 1.9910419985517976e-05,
"loss": 1.1456,
"step": 271
},
{
"epoch": 0.6956521739130435,
"grad_norm": 0.5979768056972147,
"learning_rate": 1.9908018952993017e-05,
"loss": 1.1063,
"step": 272
},
{
"epoch": 0.6982097186700768,
"grad_norm": 0.4235080476193215,
"learning_rate": 1.9905586315541917e-05,
"loss": 1.1221,
"step": 273
},
{
"epoch": 0.7007672634271099,
"grad_norm": 0.4371176178919167,
"learning_rate": 1.9903122080924385e-05,
"loss": 1.1442,
"step": 274
},
{
"epoch": 0.7033248081841432,
"grad_norm": 0.5421093135936572,
"learning_rate": 1.9900626257000924e-05,
"loss": 1.1211,
"step": 275
},
{
"epoch": 0.7058823529411765,
"grad_norm": 0.5254257134289397,
"learning_rate": 1.9898098851732787e-05,
"loss": 1.1387,
"step": 276
},
{
"epoch": 0.7084398976982097,
"grad_norm": 0.43013120307542063,
"learning_rate": 1.989553987318198e-05,
"loss": 1.1531,
"step": 277
},
{
"epoch": 0.710997442455243,
"grad_norm": 0.3719236734452485,
"learning_rate": 1.9892949329511213e-05,
"loss": 1.119,
"step": 278
},
{
"epoch": 0.7135549872122762,
"grad_norm": 0.4460019794088031,
"learning_rate": 1.989032722898389e-05,
"loss": 1.1492,
"step": 279
},
{
"epoch": 0.7161125319693095,
"grad_norm": 0.46677512285334416,
"learning_rate": 1.988767357996408e-05,
"loss": 1.1162,
"step": 280
},
{
"epoch": 0.7186700767263428,
"grad_norm": 0.4083748664929053,
"learning_rate": 1.988498839091647e-05,
"loss": 1.1092,
"step": 281
},
{
"epoch": 0.7212276214833759,
"grad_norm": 0.3564940325688949,
"learning_rate": 1.9882271670406373e-05,
"loss": 1.1357,
"step": 282
},
{
"epoch": 0.7237851662404092,
"grad_norm": 0.30028785539914044,
"learning_rate": 1.9879523427099668e-05,
"loss": 1.0653,
"step": 283
},
{
"epoch": 0.7263427109974424,
"grad_norm": 0.27869590816680806,
"learning_rate": 1.9876743669762795e-05,
"loss": 1.131,
"step": 284
},
{
"epoch": 0.7289002557544757,
"grad_norm": 0.2884828038008038,
"learning_rate": 1.9873932407262715e-05,
"loss": 1.1131,
"step": 285
},
{
"epoch": 0.731457800511509,
"grad_norm": 0.2884307017453047,
"learning_rate": 1.9871089648566887e-05,
"loss": 1.1392,
"step": 286
},
{
"epoch": 0.7340153452685422,
"grad_norm": 0.2783149887312821,
"learning_rate": 1.9868215402743236e-05,
"loss": 1.1369,
"step": 287
},
{
"epoch": 0.7365728900255755,
"grad_norm": 0.25240825307315373,
"learning_rate": 1.9865309678960125e-05,
"loss": 1.0986,
"step": 288
},
{
"epoch": 0.7391304347826086,
"grad_norm": 0.27833150890437497,
"learning_rate": 1.986237248648633e-05,
"loss": 1.1309,
"step": 289
},
{
"epoch": 0.7416879795396419,
"grad_norm": 0.3397738537561161,
"learning_rate": 1.9859403834691006e-05,
"loss": 1.1421,
"step": 290
},
{
"epoch": 0.7442455242966752,
"grad_norm": 0.31909191699373507,
"learning_rate": 1.985640373304365e-05,
"loss": 1.1239,
"step": 291
},
{
"epoch": 0.7468030690537084,
"grad_norm": 0.3160261198555746,
"learning_rate": 1.985337219111409e-05,
"loss": 1.0883,
"step": 292
},
{
"epoch": 0.7493606138107417,
"grad_norm": 0.31947473180563374,
"learning_rate": 1.9850309218572437e-05,
"loss": 1.1165,
"step": 293
},
{
"epoch": 0.7519181585677749,
"grad_norm": 0.28206583491018894,
"learning_rate": 1.984721482518907e-05,
"loss": 1.1125,
"step": 294
},
{
"epoch": 0.7544757033248082,
"grad_norm": 0.3087007877058229,
"learning_rate": 1.9844089020834573e-05,
"loss": 1.1041,
"step": 295
},
{
"epoch": 0.7570332480818415,
"grad_norm": 0.2900775892483009,
"learning_rate": 1.9840931815479747e-05,
"loss": 1.1122,
"step": 296
},
{
"epoch": 0.7595907928388747,
"grad_norm": 0.3049429227172959,
"learning_rate": 1.9837743219195554e-05,
"loss": 1.1508,
"step": 297
},
{
"epoch": 0.7621483375959079,
"grad_norm": 0.2702621520802534,
"learning_rate": 1.983452324215308e-05,
"loss": 1.1296,
"step": 298
},
{
"epoch": 0.7647058823529411,
"grad_norm": 0.27935338606011506,
"learning_rate": 1.983127189462351e-05,
"loss": 1.1396,
"step": 299
},
{
"epoch": 0.7672634271099744,
"grad_norm": 0.2806678661873222,
"learning_rate": 1.9827989186978105e-05,
"loss": 1.1025,
"step": 300
},
{
"epoch": 0.7698209718670077,
"grad_norm": 0.2424376386995265,
"learning_rate": 1.9824675129688152e-05,
"loss": 1.1349,
"step": 301
},
{
"epoch": 0.7723785166240409,
"grad_norm": 0.25294422720974147,
"learning_rate": 1.9821329733324943e-05,
"loss": 1.1333,
"step": 302
},
{
"epoch": 0.7749360613810742,
"grad_norm": 0.2996335354330534,
"learning_rate": 1.9817953008559733e-05,
"loss": 1.1024,
"step": 303
},
{
"epoch": 0.7774936061381074,
"grad_norm": 0.25368934438638874,
"learning_rate": 1.9814544966163708e-05,
"loss": 1.1046,
"step": 304
},
{
"epoch": 0.7800511508951407,
"grad_norm": 0.29925585101340996,
"learning_rate": 1.9811105617007958e-05,
"loss": 1.1209,
"step": 305
},
{
"epoch": 0.782608695652174,
"grad_norm": 0.2857142531264863,
"learning_rate": 1.980763497206343e-05,
"loss": 1.1121,
"step": 306
},
{
"epoch": 0.7851662404092071,
"grad_norm": 0.28949765605838534,
"learning_rate": 1.98041330424009e-05,
"loss": 1.0798,
"step": 307
},
{
"epoch": 0.7877237851662404,
"grad_norm": 0.39212069215270606,
"learning_rate": 1.9800599839190942e-05,
"loss": 1.1121,
"step": 308
},
{
"epoch": 0.7902813299232737,
"grad_norm": 0.42549878552407905,
"learning_rate": 1.979703537370388e-05,
"loss": 1.1301,
"step": 309
},
{
"epoch": 0.7928388746803069,
"grad_norm": 0.34373356520749754,
"learning_rate": 1.979343965730977e-05,
"loss": 1.0972,
"step": 310
},
{
"epoch": 0.7953964194373402,
"grad_norm": 0.28788024425928377,
"learning_rate": 1.9789812701478346e-05,
"loss": 1.1292,
"step": 311
},
{
"epoch": 0.7979539641943734,
"grad_norm": 0.3235972078049142,
"learning_rate": 1.9786154517778987e-05,
"loss": 1.1467,
"step": 312
},
{
"epoch": 0.8005115089514067,
"grad_norm": 0.4417301333695989,
"learning_rate": 1.9782465117880694e-05,
"loss": 1.109,
"step": 313
},
{
"epoch": 0.80306905370844,
"grad_norm": 0.3742518224113521,
"learning_rate": 1.977874451355203e-05,
"loss": 1.1127,
"step": 314
},
{
"epoch": 0.8056265984654731,
"grad_norm": 0.2796776192545452,
"learning_rate": 1.9774992716661106e-05,
"loss": 1.1059,
"step": 315
},
{
"epoch": 0.8081841432225064,
"grad_norm": 0.29748665489937487,
"learning_rate": 1.9771209739175522e-05,
"loss": 1.102,
"step": 316
},
{
"epoch": 0.8107416879795396,
"grad_norm": 0.3560790006624538,
"learning_rate": 1.9767395593162356e-05,
"loss": 1.131,
"step": 317
},
{
"epoch": 0.8132992327365729,
"grad_norm": 0.28183796528203187,
"learning_rate": 1.9763550290788086e-05,
"loss": 1.1236,
"step": 318
},
{
"epoch": 0.8158567774936062,
"grad_norm": 0.2767624292955607,
"learning_rate": 1.9759673844318592e-05,
"loss": 1.0826,
"step": 319
},
{
"epoch": 0.8184143222506394,
"grad_norm": 0.24323449746418016,
"learning_rate": 1.9755766266119085e-05,
"loss": 1.1101,
"step": 320
},
{
"epoch": 0.8209718670076727,
"grad_norm": 0.30635322192890063,
"learning_rate": 1.975182756865409e-05,
"loss": 1.0896,
"step": 321
},
{
"epoch": 0.8235294117647058,
"grad_norm": 0.31827256506593926,
"learning_rate": 1.9747857764487395e-05,
"loss": 1.119,
"step": 322
},
{
"epoch": 0.8260869565217391,
"grad_norm": 0.2714890499396325,
"learning_rate": 1.974385686628201e-05,
"loss": 1.139,
"step": 323
},
{
"epoch": 0.8286445012787724,
"grad_norm": 0.2617887796548345,
"learning_rate": 1.9739824886800134e-05,
"loss": 1.1387,
"step": 324
},
{
"epoch": 0.8312020460358056,
"grad_norm": 0.2799625411152913,
"learning_rate": 1.9735761838903106e-05,
"loss": 1.0992,
"step": 325
},
{
"epoch": 0.8337595907928389,
"grad_norm": 0.3045162427185304,
"learning_rate": 1.9731667735551376e-05,
"loss": 1.1099,
"step": 326
},
{
"epoch": 0.8363171355498721,
"grad_norm": 0.30841493149512844,
"learning_rate": 1.9727542589804446e-05,
"loss": 1.1504,
"step": 327
},
{
"epoch": 0.8388746803069054,
"grad_norm": 0.26580510867255863,
"learning_rate": 1.9723386414820844e-05,
"loss": 1.1214,
"step": 328
},
{
"epoch": 0.8414322250639387,
"grad_norm": 0.3102926749875895,
"learning_rate": 1.971919922385807e-05,
"loss": 1.1606,
"step": 329
},
{
"epoch": 0.8439897698209718,
"grad_norm": 0.23808182814042947,
"learning_rate": 1.9714981030272566e-05,
"loss": 1.1306,
"step": 330
},
{
"epoch": 0.8465473145780051,
"grad_norm": 0.3332758895370011,
"learning_rate": 1.9710731847519665e-05,
"loss": 1.1045,
"step": 331
},
{
"epoch": 0.8491048593350383,
"grad_norm": 0.3331468308085816,
"learning_rate": 1.9706451689153556e-05,
"loss": 1.0964,
"step": 332
},
{
"epoch": 0.8516624040920716,
"grad_norm": 0.29500865696422174,
"learning_rate": 1.9702140568827224e-05,
"loss": 1.1434,
"step": 333
},
{
"epoch": 0.8542199488491049,
"grad_norm": 0.28839237064630785,
"learning_rate": 1.9697798500292422e-05,
"loss": 1.0752,
"step": 334
},
{
"epoch": 0.8567774936061381,
"grad_norm": 0.2796744909651119,
"learning_rate": 1.969342549739963e-05,
"loss": 1.102,
"step": 335
},
{
"epoch": 0.8593350383631714,
"grad_norm": 0.3120222134152984,
"learning_rate": 1.9689021574097988e-05,
"loss": 1.1016,
"step": 336
},
{
"epoch": 0.8618925831202046,
"grad_norm": 0.3114585821970581,
"learning_rate": 1.9684586744435285e-05,
"loss": 1.125,
"step": 337
},
{
"epoch": 0.8644501278772379,
"grad_norm": 0.38630267959141373,
"learning_rate": 1.9680121022557882e-05,
"loss": 1.1295,
"step": 338
},
{
"epoch": 0.8670076726342711,
"grad_norm": 0.4245255400950163,
"learning_rate": 1.9675624422710685e-05,
"loss": 1.0954,
"step": 339
},
{
"epoch": 0.8695652173913043,
"grad_norm": 0.35097053556774704,
"learning_rate": 1.9671096959237102e-05,
"loss": 1.1348,
"step": 340
},
{
"epoch": 0.8721227621483376,
"grad_norm": 0.30986958941628523,
"learning_rate": 1.9666538646578978e-05,
"loss": 1.091,
"step": 341
},
{
"epoch": 0.8746803069053708,
"grad_norm": 0.3077968967678069,
"learning_rate": 1.9661949499276577e-05,
"loss": 1.1175,
"step": 342
},
{
"epoch": 0.8772378516624041,
"grad_norm": 0.2985995156361193,
"learning_rate": 1.965732953196851e-05,
"loss": 1.1149,
"step": 343
},
{
"epoch": 0.8797953964194374,
"grad_norm": 0.3167214536166744,
"learning_rate": 1.96526787593917e-05,
"loss": 1.1224,
"step": 344
},
{
"epoch": 0.8823529411764706,
"grad_norm": 0.318814842450484,
"learning_rate": 1.964799719638134e-05,
"loss": 1.1039,
"step": 345
},
{
"epoch": 0.8849104859335039,
"grad_norm": 0.35420843208500646,
"learning_rate": 1.9643284857870824e-05,
"loss": 1.1686,
"step": 346
},
{
"epoch": 0.887468030690537,
"grad_norm": 0.2815662324657919,
"learning_rate": 1.9638541758891733e-05,
"loss": 1.0509,
"step": 347
},
{
"epoch": 0.8900255754475703,
"grad_norm": 0.3284996290945278,
"learning_rate": 1.963376791457376e-05,
"loss": 1.1162,
"step": 348
},
{
"epoch": 0.8925831202046036,
"grad_norm": 0.33970062669533485,
"learning_rate": 1.962896334014467e-05,
"loss": 1.1,
"step": 349
},
{
"epoch": 0.8951406649616368,
"grad_norm": 0.32747244832244676,
"learning_rate": 1.9624128050930252e-05,
"loss": 1.1228,
"step": 350
},
{
"epoch": 0.8976982097186701,
"grad_norm": 0.27048623218728324,
"learning_rate": 1.9619262062354273e-05,
"loss": 1.1403,
"step": 351
},
{
"epoch": 0.9002557544757033,
"grad_norm": 0.2972853292863894,
"learning_rate": 1.9614365389938425e-05,
"loss": 1.0943,
"step": 352
},
{
"epoch": 0.9028132992327366,
"grad_norm": 0.34260939469670293,
"learning_rate": 1.9609438049302274e-05,
"loss": 1.1167,
"step": 353
},
{
"epoch": 0.9053708439897699,
"grad_norm": 0.38264563083677083,
"learning_rate": 1.9604480056163215e-05,
"loss": 1.1109,
"step": 354
},
{
"epoch": 0.907928388746803,
"grad_norm": 0.28234436041490374,
"learning_rate": 1.9599491426336415e-05,
"loss": 1.0884,
"step": 355
},
{
"epoch": 0.9104859335038363,
"grad_norm": 0.2708061459988167,
"learning_rate": 1.9594472175734776e-05,
"loss": 1.1013,
"step": 356
},
{
"epoch": 0.9130434782608695,
"grad_norm": 0.25976263313561604,
"learning_rate": 1.9589422320368863e-05,
"loss": 1.112,
"step": 357
},
{
"epoch": 0.9156010230179028,
"grad_norm": 0.33058002121583785,
"learning_rate": 1.9584341876346874e-05,
"loss": 1.1338,
"step": 358
},
{
"epoch": 0.9181585677749361,
"grad_norm": 0.32807990736066434,
"learning_rate": 1.957923085987458e-05,
"loss": 1.115,
"step": 359
},
{
"epoch": 0.9207161125319693,
"grad_norm": 0.3514992497926305,
"learning_rate": 1.957408928725527e-05,
"loss": 1.0819,
"step": 360
},
{
"epoch": 0.9232736572890026,
"grad_norm": 0.377909885361285,
"learning_rate": 1.9568917174889696e-05,
"loss": 1.1301,
"step": 361
},
{
"epoch": 0.9258312020460358,
"grad_norm": 0.2561753671305042,
"learning_rate": 1.9563714539276037e-05,
"loss": 1.0582,
"step": 362
},
{
"epoch": 0.928388746803069,
"grad_norm": 0.33150365566832235,
"learning_rate": 1.9558481397009832e-05,
"loss": 1.1201,
"step": 363
},
{
"epoch": 0.9309462915601023,
"grad_norm": 0.41073130363857413,
"learning_rate": 1.9553217764783928e-05,
"loss": 1.1031,
"step": 364
},
{
"epoch": 0.9335038363171355,
"grad_norm": 0.44385440148457334,
"learning_rate": 1.954792365938844e-05,
"loss": 1.1201,
"step": 365
},
{
"epoch": 0.9360613810741688,
"grad_norm": 0.3694394788747904,
"learning_rate": 1.9542599097710677e-05,
"loss": 1.1431,
"step": 366
},
{
"epoch": 0.9386189258312021,
"grad_norm": 0.3652537164671811,
"learning_rate": 1.9537244096735096e-05,
"loss": 1.1213,
"step": 367
},
{
"epoch": 0.9411764705882353,
"grad_norm": 0.3951831465406744,
"learning_rate": 1.9531858673543266e-05,
"loss": 1.1147,
"step": 368
},
{
"epoch": 0.9437340153452686,
"grad_norm": 0.5451604935646901,
"learning_rate": 1.952644284531378e-05,
"loss": 1.1096,
"step": 369
},
{
"epoch": 0.9462915601023018,
"grad_norm": 0.4328674219635996,
"learning_rate": 1.9520996629322228e-05,
"loss": 1.1056,
"step": 370
},
{
"epoch": 0.948849104859335,
"grad_norm": 0.34768509118734625,
"learning_rate": 1.9515520042941133e-05,
"loss": 1.1329,
"step": 371
},
{
"epoch": 0.9514066496163683,
"grad_norm": 0.33694594098800845,
"learning_rate": 1.9510013103639885e-05,
"loss": 1.1139,
"step": 372
},
{
"epoch": 0.9539641943734015,
"grad_norm": 0.2816891577865245,
"learning_rate": 1.9504475828984706e-05,
"loss": 1.1172,
"step": 373
},
{
"epoch": 0.9565217391304348,
"grad_norm": 0.2726181598335772,
"learning_rate": 1.9498908236638572e-05,
"loss": 1.117,
"step": 374
},
{
"epoch": 0.959079283887468,
"grad_norm": 0.2725400027413373,
"learning_rate": 1.949331034436118e-05,
"loss": 1.1392,
"step": 375
},
{
"epoch": 0.9616368286445013,
"grad_norm": 0.24708596308833097,
"learning_rate": 1.9487682170008864e-05,
"loss": 1.0888,
"step": 376
},
{
"epoch": 0.9641943734015346,
"grad_norm": 0.24611853998964667,
"learning_rate": 1.948202373153457e-05,
"loss": 1.1222,
"step": 377
},
{
"epoch": 0.9667519181585678,
"grad_norm": 0.2748730983230991,
"learning_rate": 1.9476335046987765e-05,
"loss": 1.1274,
"step": 378
},
{
"epoch": 0.969309462915601,
"grad_norm": 0.23212979863877406,
"learning_rate": 1.9470616134514405e-05,
"loss": 1.0955,
"step": 379
},
{
"epoch": 0.9718670076726342,
"grad_norm": 0.24862661491603566,
"learning_rate": 1.9464867012356866e-05,
"loss": 1.0795,
"step": 380
},
{
"epoch": 0.9744245524296675,
"grad_norm": 0.28519808751496534,
"learning_rate": 1.9459087698853884e-05,
"loss": 1.1092,
"step": 381
},
{
"epoch": 0.9769820971867008,
"grad_norm": 0.2794622526427573,
"learning_rate": 1.945327821244051e-05,
"loss": 1.113,
"step": 382
},
{
"epoch": 0.979539641943734,
"grad_norm": 0.27278224425786757,
"learning_rate": 1.944743857164803e-05,
"loss": 1.1169,
"step": 383
},
{
"epoch": 0.9820971867007673,
"grad_norm": 0.27611615092251324,
"learning_rate": 1.9441568795103932e-05,
"loss": 1.0704,
"step": 384
},
{
"epoch": 0.9846547314578005,
"grad_norm": 0.26697361837596756,
"learning_rate": 1.9435668901531813e-05,
"loss": 1.1517,
"step": 385
},
{
"epoch": 0.9872122762148338,
"grad_norm": 0.3629600651937476,
"learning_rate": 1.9429738909751355e-05,
"loss": 1.1052,
"step": 386
},
{
"epoch": 0.989769820971867,
"grad_norm": 0.30179358680215773,
"learning_rate": 1.9423778838678236e-05,
"loss": 1.1192,
"step": 387
},
{
"epoch": 0.9923273657289002,
"grad_norm": 0.3006384503184647,
"learning_rate": 1.9417788707324095e-05,
"loss": 1.133,
"step": 388
},
{
"epoch": 0.9948849104859335,
"grad_norm": 0.2894724527823374,
"learning_rate": 1.9411768534796445e-05,
"loss": 1.1161,
"step": 389
},
{
"epoch": 0.9974424552429667,
"grad_norm": 0.2807180282095206,
"learning_rate": 1.9405718340298633e-05,
"loss": 1.0955,
"step": 390
},
{
"epoch": 1.0,
"grad_norm": 0.348947561667452,
"learning_rate": 1.9399638143129768e-05,
"loss": 1.1251,
"step": 391
},
{
"epoch": 1.0025575447570332,
"grad_norm": 0.2782036837933627,
"learning_rate": 1.9393527962684665e-05,
"loss": 1.1002,
"step": 392
},
{
"epoch": 1.0051150895140666,
"grad_norm": 0.3519574703494421,
"learning_rate": 1.938738781845378e-05,
"loss": 1.1167,
"step": 393
},
{
"epoch": 1.0076726342710998,
"grad_norm": 0.4580624378113774,
"learning_rate": 1.938121773002315e-05,
"loss": 1.0882,
"step": 394
},
{
"epoch": 1.010230179028133,
"grad_norm": 0.40810589155384597,
"learning_rate": 1.9375017717074322e-05,
"loss": 1.0969,
"step": 395
},
{
"epoch": 1.0127877237851663,
"grad_norm": 0.36602089723011694,
"learning_rate": 1.9368787799384303e-05,
"loss": 1.1139,
"step": 396
},
{
"epoch": 1.0153452685421995,
"grad_norm": 0.35535572252914266,
"learning_rate": 1.936252799682549e-05,
"loss": 1.1153,
"step": 397
},
{
"epoch": 1.0179028132992327,
"grad_norm": 0.30429749075329415,
"learning_rate": 1.9356238329365614e-05,
"loss": 1.1053,
"step": 398
},
{
"epoch": 1.020460358056266,
"grad_norm": 0.3229547174327428,
"learning_rate": 1.9349918817067658e-05,
"loss": 1.0765,
"step": 399
},
{
"epoch": 1.0230179028132993,
"grad_norm": 0.41127178125569,
"learning_rate": 1.934356948008981e-05,
"loss": 1.1314,
"step": 400
},
{
"epoch": 1.0255754475703325,
"grad_norm": 0.45751355203161004,
"learning_rate": 1.93371903386854e-05,
"loss": 1.11,
"step": 401
},
{
"epoch": 1.0281329923273657,
"grad_norm": 0.3986059039543531,
"learning_rate": 1.933078141320282e-05,
"loss": 1.1286,
"step": 402
},
{
"epoch": 1.030690537084399,
"grad_norm": 0.3213433170159458,
"learning_rate": 1.9324342724085473e-05,
"loss": 1.0938,
"step": 403
},
{
"epoch": 1.0332480818414322,
"grad_norm": 0.2940898456275506,
"learning_rate": 1.9317874291871703e-05,
"loss": 1.1004,
"step": 404
},
{
"epoch": 1.0358056265984654,
"grad_norm": 0.32488534442637107,
"learning_rate": 1.931137613719473e-05,
"loss": 1.0987,
"step": 405
},
{
"epoch": 1.0383631713554988,
"grad_norm": 0.4137853980303429,
"learning_rate": 1.9304848280782582e-05,
"loss": 1.1313,
"step": 406
},
{
"epoch": 1.040920716112532,
"grad_norm": 0.4264194369796108,
"learning_rate": 1.9298290743458027e-05,
"loss": 1.0649,
"step": 407
},
{
"epoch": 1.0434782608695652,
"grad_norm": 0.45590348437434036,
"learning_rate": 1.929170354613852e-05,
"loss": 1.0967,
"step": 408
},
{
"epoch": 1.0460358056265984,
"grad_norm": 0.33156329123437867,
"learning_rate": 1.9285086709836115e-05,
"loss": 1.0775,
"step": 409
},
{
"epoch": 1.0485933503836318,
"grad_norm": 0.3704005026550043,
"learning_rate": 1.927844025565742e-05,
"loss": 1.0716,
"step": 410
},
{
"epoch": 1.051150895140665,
"grad_norm": 0.3169006666927623,
"learning_rate": 1.9271764204803512e-05,
"loss": 1.0984,
"step": 411
},
{
"epoch": 1.0537084398976981,
"grad_norm": 0.3295513943189194,
"learning_rate": 1.9265058578569878e-05,
"loss": 1.079,
"step": 412
},
{
"epoch": 1.0562659846547315,
"grad_norm": 0.3297315773374301,
"learning_rate": 1.9258323398346345e-05,
"loss": 1.0881,
"step": 413
},
{
"epoch": 1.0588235294117647,
"grad_norm": 0.3173169155920823,
"learning_rate": 1.9251558685617015e-05,
"loss": 1.1338,
"step": 414
},
{
"epoch": 1.061381074168798,
"grad_norm": 0.3993520424000351,
"learning_rate": 1.9244764461960193e-05,
"loss": 1.1055,
"step": 415
},
{
"epoch": 1.0639386189258313,
"grad_norm": 0.27163667354634313,
"learning_rate": 1.923794074904832e-05,
"loss": 1.0866,
"step": 416
},
{
"epoch": 1.0664961636828645,
"grad_norm": 0.3514844689560382,
"learning_rate": 1.9231087568647892e-05,
"loss": 1.0705,
"step": 417
},
{
"epoch": 1.0690537084398977,
"grad_norm": 0.2854882940594379,
"learning_rate": 1.9224204942619418e-05,
"loss": 1.0802,
"step": 418
},
{
"epoch": 1.0716112531969308,
"grad_norm": 0.33059120925775853,
"learning_rate": 1.9217292892917326e-05,
"loss": 1.1369,
"step": 419
},
{
"epoch": 1.0741687979539642,
"grad_norm": 0.28470692158693056,
"learning_rate": 1.9210351441589898e-05,
"loss": 1.0851,
"step": 420
},
{
"epoch": 1.0767263427109974,
"grad_norm": 0.27607260051782767,
"learning_rate": 1.92033806107792e-05,
"loss": 1.0983,
"step": 421
},
{
"epoch": 1.0792838874680306,
"grad_norm": 0.27376802007793644,
"learning_rate": 1.919638042272103e-05,
"loss": 1.0899,
"step": 422
},
{
"epoch": 1.081841432225064,
"grad_norm": 0.24273577112968892,
"learning_rate": 1.9189350899744807e-05,
"loss": 1.0748,
"step": 423
},
{
"epoch": 1.0843989769820972,
"grad_norm": 0.32941305876089433,
"learning_rate": 1.9182292064273544e-05,
"loss": 1.1209,
"step": 424
},
{
"epoch": 1.0869565217391304,
"grad_norm": 0.226985402664926,
"learning_rate": 1.9175203938823747e-05,
"loss": 1.0853,
"step": 425
},
{
"epoch": 1.0895140664961638,
"grad_norm": 0.30079073449406646,
"learning_rate": 1.9168086546005348e-05,
"loss": 1.0746,
"step": 426
},
{
"epoch": 1.092071611253197,
"grad_norm": 0.33309434785775865,
"learning_rate": 1.9160939908521642e-05,
"loss": 1.0991,
"step": 427
},
{
"epoch": 1.0946291560102301,
"grad_norm": 0.4305882959246417,
"learning_rate": 1.9153764049169213e-05,
"loss": 1.0799,
"step": 428
},
{
"epoch": 1.0971867007672633,
"grad_norm": 0.32261776654673774,
"learning_rate": 1.9146558990837853e-05,
"loss": 1.1098,
"step": 429
},
{
"epoch": 1.0997442455242967,
"grad_norm": 0.3043949510529127,
"learning_rate": 1.9139324756510496e-05,
"loss": 1.0854,
"step": 430
},
{
"epoch": 1.10230179028133,
"grad_norm": 0.25743020242945314,
"learning_rate": 1.913206136926314e-05,
"loss": 1.1157,
"step": 431
},
{
"epoch": 1.104859335038363,
"grad_norm": 0.3310331033148412,
"learning_rate": 1.9124768852264774e-05,
"loss": 1.134,
"step": 432
},
{
"epoch": 1.1074168797953965,
"grad_norm": 0.4154810782539844,
"learning_rate": 1.9117447228777317e-05,
"loss": 1.1111,
"step": 433
},
{
"epoch": 1.1099744245524297,
"grad_norm": 0.33867417586438353,
"learning_rate": 1.9110096522155525e-05,
"loss": 1.0996,
"step": 434
},
{
"epoch": 1.1125319693094629,
"grad_norm": 0.2859884267480265,
"learning_rate": 1.9102716755846916e-05,
"loss": 1.0916,
"step": 435
},
{
"epoch": 1.1150895140664963,
"grad_norm": 0.3892200070495796,
"learning_rate": 1.909530795339172e-05,
"loss": 1.0894,
"step": 436
},
{
"epoch": 1.1176470588235294,
"grad_norm": 0.48792801105881567,
"learning_rate": 1.9087870138422777e-05,
"loss": 1.0702,
"step": 437
},
{
"epoch": 1.1202046035805626,
"grad_norm": 0.4392749429122809,
"learning_rate": 1.9080403334665475e-05,
"loss": 1.0831,
"step": 438
},
{
"epoch": 1.1227621483375958,
"grad_norm": 0.31693271658453487,
"learning_rate": 1.9072907565937675e-05,
"loss": 1.1038,
"step": 439
},
{
"epoch": 1.1253196930946292,
"grad_norm": 0.3404612161405027,
"learning_rate": 1.9065382856149623e-05,
"loss": 1.0813,
"step": 440
},
{
"epoch": 1.1278772378516624,
"grad_norm": 0.36566368828973633,
"learning_rate": 1.905782922930389e-05,
"loss": 1.1008,
"step": 441
},
{
"epoch": 1.1304347826086956,
"grad_norm": 0.3310584074847857,
"learning_rate": 1.9050246709495283e-05,
"loss": 1.0811,
"step": 442
},
{
"epoch": 1.132992327365729,
"grad_norm": 0.2708409903975629,
"learning_rate": 1.904263532091077e-05,
"loss": 1.1057,
"step": 443
},
{
"epoch": 1.1355498721227621,
"grad_norm": 0.3139293999297133,
"learning_rate": 1.903499508782942e-05,
"loss": 1.0716,
"step": 444
},
{
"epoch": 1.1381074168797953,
"grad_norm": 0.39095800156714283,
"learning_rate": 1.902732603462229e-05,
"loss": 1.0921,
"step": 445
},
{
"epoch": 1.1406649616368287,
"grad_norm": 0.30908518133076435,
"learning_rate": 1.9019628185752384e-05,
"loss": 1.0648,
"step": 446
},
{
"epoch": 1.143222506393862,
"grad_norm": 0.3805637372734307,
"learning_rate": 1.9011901565774555e-05,
"loss": 1.0533,
"step": 447
},
{
"epoch": 1.145780051150895,
"grad_norm": 0.3775382301483175,
"learning_rate": 1.900414619933543e-05,
"loss": 1.0858,
"step": 448
},
{
"epoch": 1.1483375959079285,
"grad_norm": 0.41861102880335493,
"learning_rate": 1.8996362111173338e-05,
"loss": 1.0772,
"step": 449
},
{
"epoch": 1.1508951406649617,
"grad_norm": 0.3783086482998166,
"learning_rate": 1.898854932611821e-05,
"loss": 1.1276,
"step": 450
},
{
"epoch": 1.1534526854219949,
"grad_norm": 0.3167462811218851,
"learning_rate": 1.8980707869091534e-05,
"loss": 1.1,
"step": 451
},
{
"epoch": 1.156010230179028,
"grad_norm": 0.2569091030662843,
"learning_rate": 1.8972837765106244e-05,
"loss": 1.1032,
"step": 452
},
{
"epoch": 1.1585677749360614,
"grad_norm": 0.42403134602315007,
"learning_rate": 1.896493903926666e-05,
"loss": 1.1185,
"step": 453
},
{
"epoch": 1.1611253196930946,
"grad_norm": 0.4524020606510499,
"learning_rate": 1.8957011716768403e-05,
"loss": 1.0895,
"step": 454
},
{
"epoch": 1.1636828644501278,
"grad_norm": 0.30454573206724117,
"learning_rate": 1.89490558228983e-05,
"loss": 1.0851,
"step": 455
},
{
"epoch": 1.1662404092071612,
"grad_norm": 0.25991176813435285,
"learning_rate": 1.8941071383034328e-05,
"loss": 1.0773,
"step": 456
},
{
"epoch": 1.1687979539641944,
"grad_norm": 0.3886268706724371,
"learning_rate": 1.8933058422645516e-05,
"loss": 1.0699,
"step": 457
},
{
"epoch": 1.1713554987212276,
"grad_norm": 0.36471960792817715,
"learning_rate": 1.8925016967291873e-05,
"loss": 1.0742,
"step": 458
},
{
"epoch": 1.1739130434782608,
"grad_norm": 0.26625088784429024,
"learning_rate": 1.8916947042624294e-05,
"loss": 1.0827,
"step": 459
},
{
"epoch": 1.1764705882352942,
"grad_norm": 0.32264462408411615,
"learning_rate": 1.8908848674384494e-05,
"loss": 1.1101,
"step": 460
},
{
"epoch": 1.1790281329923273,
"grad_norm": 0.36503412806400276,
"learning_rate": 1.8900721888404917e-05,
"loss": 1.1335,
"step": 461
},
{
"epoch": 1.1815856777493605,
"grad_norm": 0.2719728070020309,
"learning_rate": 1.8892566710608648e-05,
"loss": 1.0758,
"step": 462
},
{
"epoch": 1.184143222506394,
"grad_norm": 0.2553303942221017,
"learning_rate": 1.888438316700935e-05,
"loss": 1.0658,
"step": 463
},
{
"epoch": 1.186700767263427,
"grad_norm": 0.295046080413778,
"learning_rate": 1.8876171283711153e-05,
"loss": 1.0937,
"step": 464
},
{
"epoch": 1.1892583120204603,
"grad_norm": 0.28953986695793527,
"learning_rate": 1.88679310869086e-05,
"loss": 1.1014,
"step": 465
},
{
"epoch": 1.1918158567774937,
"grad_norm": 0.2826951705156822,
"learning_rate": 1.885966260288654e-05,
"loss": 1.0993,
"step": 466
},
{
"epoch": 1.1943734015345269,
"grad_norm": 0.2944678860725613,
"learning_rate": 1.8851365858020054e-05,
"loss": 1.0761,
"step": 467
},
{
"epoch": 1.19693094629156,
"grad_norm": 0.27240534403446576,
"learning_rate": 1.884304087877438e-05,
"loss": 1.1276,
"step": 468
},
{
"epoch": 1.1994884910485935,
"grad_norm": 0.27201496505406125,
"learning_rate": 1.8834687691704807e-05,
"loss": 1.0915,
"step": 469
},
{
"epoch": 1.2020460358056266,
"grad_norm": 0.2627060324507912,
"learning_rate": 1.8826306323456603e-05,
"loss": 1.1133,
"step": 470
},
{
"epoch": 1.2046035805626598,
"grad_norm": 0.2639617835117496,
"learning_rate": 1.881789680076494e-05,
"loss": 1.085,
"step": 471
},
{
"epoch": 1.207161125319693,
"grad_norm": 0.2664271870627373,
"learning_rate": 1.8809459150454788e-05,
"loss": 1.0432,
"step": 472
},
{
"epoch": 1.2097186700767264,
"grad_norm": 0.27593650483499654,
"learning_rate": 1.8800993399440845e-05,
"loss": 1.0998,
"step": 473
},
{
"epoch": 1.2122762148337596,
"grad_norm": 0.24702077068855108,
"learning_rate": 1.879249957472744e-05,
"loss": 1.0828,
"step": 474
},
{
"epoch": 1.2148337595907928,
"grad_norm": 0.27099736060394275,
"learning_rate": 1.878397770340846e-05,
"loss": 1.0979,
"step": 475
},
{
"epoch": 1.2173913043478262,
"grad_norm": 0.33819417373799127,
"learning_rate": 1.877542781266725e-05,
"loss": 1.0667,
"step": 476
},
{
"epoch": 1.2199488491048593,
"grad_norm": 0.375994886329379,
"learning_rate": 1.876684992977653e-05,
"loss": 1.1219,
"step": 477
},
{
"epoch": 1.2225063938618925,
"grad_norm": 0.3006928865582519,
"learning_rate": 1.875824408209832e-05,
"loss": 1.1044,
"step": 478
},
{
"epoch": 1.2250639386189257,
"grad_norm": 0.2967546177260049,
"learning_rate": 1.874961029708383e-05,
"loss": 1.113,
"step": 479
},
{
"epoch": 1.227621483375959,
"grad_norm": 0.2721644513681839,
"learning_rate": 1.8740948602273402e-05,
"loss": 1.064,
"step": 480
},
{
"epoch": 1.2301790281329923,
"grad_norm": 0.2626448539398862,
"learning_rate": 1.873225902529639e-05,
"loss": 1.0728,
"step": 481
},
{
"epoch": 1.2327365728900257,
"grad_norm": 0.3026172920619992,
"learning_rate": 1.872354159387109e-05,
"loss": 1.0938,
"step": 482
},
{
"epoch": 1.2352941176470589,
"grad_norm": 0.34601754375875127,
"learning_rate": 1.8714796335804665e-05,
"loss": 1.0849,
"step": 483
},
{
"epoch": 1.237851662404092,
"grad_norm": 0.3327308153807525,
"learning_rate": 1.8706023278993015e-05,
"loss": 1.1004,
"step": 484
},
{
"epoch": 1.2404092071611252,
"grad_norm": 0.3106025965315927,
"learning_rate": 1.8697222451420735e-05,
"loss": 1.1043,
"step": 485
},
{
"epoch": 1.2429667519181586,
"grad_norm": 0.34912290055883255,
"learning_rate": 1.8688393881160992e-05,
"loss": 1.0987,
"step": 486
},
{
"epoch": 1.2455242966751918,
"grad_norm": 0.25322300465901393,
"learning_rate": 1.867953759637545e-05,
"loss": 1.0696,
"step": 487
},
{
"epoch": 1.248081841432225,
"grad_norm": 0.2535966365326748,
"learning_rate": 1.8670653625314184e-05,
"loss": 1.0895,
"step": 488
},
{
"epoch": 1.2506393861892584,
"grad_norm": 0.30478536911118187,
"learning_rate": 1.8661741996315572e-05,
"loss": 1.0975,
"step": 489
},
{
"epoch": 1.2531969309462916,
"grad_norm": 0.3154046265606216,
"learning_rate": 1.8652802737806227e-05,
"loss": 1.119,
"step": 490
},
{
"epoch": 1.2557544757033248,
"grad_norm": 0.33453327155185647,
"learning_rate": 1.864383587830089e-05,
"loss": 1.0881,
"step": 491
},
{
"epoch": 1.258312020460358,
"grad_norm": 0.2727533150638851,
"learning_rate": 1.8634841446402344e-05,
"loss": 1.1145,
"step": 492
},
{
"epoch": 1.2608695652173914,
"grad_norm": 0.36121948622829403,
"learning_rate": 1.862581947080132e-05,
"loss": 1.0836,
"step": 493
},
{
"epoch": 1.2634271099744245,
"grad_norm": 0.43540568550818237,
"learning_rate": 1.8616769980276427e-05,
"loss": 1.0817,
"step": 494
},
{
"epoch": 1.265984654731458,
"grad_norm": 0.43519257410113654,
"learning_rate": 1.860769300369402e-05,
"loss": 1.1064,
"step": 495
},
{
"epoch": 1.2685421994884911,
"grad_norm": 0.28730988243979366,
"learning_rate": 1.859858857000814e-05,
"loss": 1.0948,
"step": 496
},
{
"epoch": 1.2710997442455243,
"grad_norm": 0.3115117836172728,
"learning_rate": 1.858945670826041e-05,
"loss": 1.0867,
"step": 497
},
{
"epoch": 1.2736572890025575,
"grad_norm": 0.37248383339237146,
"learning_rate": 1.858029744757995e-05,
"loss": 1.0731,
"step": 498
},
{
"epoch": 1.2762148337595907,
"grad_norm": 0.3888532232815489,
"learning_rate": 1.857111081718326e-05,
"loss": 1.0876,
"step": 499
},
{
"epoch": 1.278772378516624,
"grad_norm": 0.3244399041871337,
"learning_rate": 1.8561896846374167e-05,
"loss": 1.0621,
"step": 500
},
{
"epoch": 1.2813299232736572,
"grad_norm": 0.2633849807180457,
"learning_rate": 1.8552655564543695e-05,
"loss": 1.0828,
"step": 501
},
{
"epoch": 1.2838874680306906,
"grad_norm": 0.30310812918802343,
"learning_rate": 1.8543387001169994e-05,
"loss": 1.0869,
"step": 502
},
{
"epoch": 1.2864450127877238,
"grad_norm": 0.38986142912075833,
"learning_rate": 1.853409118581823e-05,
"loss": 1.1069,
"step": 503
},
{
"epoch": 1.289002557544757,
"grad_norm": 0.2920169315779173,
"learning_rate": 1.8524768148140504e-05,
"loss": 1.0826,
"step": 504
},
{
"epoch": 1.2915601023017902,
"grad_norm": 0.2574557432611984,
"learning_rate": 1.851541791787575e-05,
"loss": 1.0964,
"step": 505
},
{
"epoch": 1.2941176470588236,
"grad_norm": 0.2828254579434041,
"learning_rate": 1.850604052484964e-05,
"loss": 1.0721,
"step": 506
},
{
"epoch": 1.2966751918158568,
"grad_norm": 0.3701320049597822,
"learning_rate": 1.8496635998974487e-05,
"loss": 1.1063,
"step": 507
},
{
"epoch": 1.29923273657289,
"grad_norm": 0.3423233955071227,
"learning_rate": 1.848720437024917e-05,
"loss": 1.0664,
"step": 508
},
{
"epoch": 1.3017902813299234,
"grad_norm": 0.2178713925167967,
"learning_rate": 1.8477745668758998e-05,
"loss": 1.1,
"step": 509
},
{
"epoch": 1.3043478260869565,
"grad_norm": 0.2826697186052642,
"learning_rate": 1.8468259924675655e-05,
"loss": 1.068,
"step": 510
},
{
"epoch": 1.3069053708439897,
"grad_norm": 0.30593309813937236,
"learning_rate": 1.8458747168257086e-05,
"loss": 1.0768,
"step": 511
},
{
"epoch": 1.309462915601023,
"grad_norm": 0.32702026057465294,
"learning_rate": 1.8449207429847383e-05,
"loss": 1.1078,
"step": 512
},
{
"epoch": 1.3120204603580563,
"grad_norm": 0.2947477975017397,
"learning_rate": 1.8439640739876732e-05,
"loss": 1.0634,
"step": 513
},
{
"epoch": 1.3145780051150895,
"grad_norm": 0.3621645781464773,
"learning_rate": 1.8430047128861267e-05,
"loss": 1.0846,
"step": 514
},
{
"epoch": 1.317135549872123,
"grad_norm": 0.3135575999432535,
"learning_rate": 1.8420426627403008e-05,
"loss": 1.076,
"step": 515
},
{
"epoch": 1.319693094629156,
"grad_norm": 0.3227803754151594,
"learning_rate": 1.8410779266189752e-05,
"loss": 1.0715,
"step": 516
},
{
"epoch": 1.3222506393861893,
"grad_norm": 0.2571799145689103,
"learning_rate": 1.840110507599497e-05,
"loss": 1.0676,
"step": 517
},
{
"epoch": 1.3248081841432224,
"grad_norm": 0.30888680030870047,
"learning_rate": 1.8391404087677704e-05,
"loss": 1.0847,
"step": 518
},
{
"epoch": 1.3273657289002558,
"grad_norm": 0.29428683307499354,
"learning_rate": 1.8381676332182498e-05,
"loss": 1.0749,
"step": 519
},
{
"epoch": 1.329923273657289,
"grad_norm": 0.28408204459805186,
"learning_rate": 1.8371921840539264e-05,
"loss": 1.1205,
"step": 520
},
{
"epoch": 1.3324808184143222,
"grad_norm": 0.356882249127386,
"learning_rate": 1.83621406438632e-05,
"loss": 1.1202,
"step": 521
},
{
"epoch": 1.3350383631713556,
"grad_norm": 0.37405650968529813,
"learning_rate": 1.8352332773354696e-05,
"loss": 1.0973,
"step": 522
},
{
"epoch": 1.3375959079283888,
"grad_norm": 0.39837269879026094,
"learning_rate": 1.8342498260299212e-05,
"loss": 1.0864,
"step": 523
},
{
"epoch": 1.340153452685422,
"grad_norm": 0.38120725373511777,
"learning_rate": 1.833263713606721e-05,
"loss": 1.1128,
"step": 524
},
{
"epoch": 1.3427109974424551,
"grad_norm": 0.2376913907862642,
"learning_rate": 1.8322749432114028e-05,
"loss": 1.083,
"step": 525
},
{
"epoch": 1.3452685421994885,
"grad_norm": 0.33071151652108544,
"learning_rate": 1.8312835179979788e-05,
"loss": 1.1089,
"step": 526
},
{
"epoch": 1.3478260869565217,
"grad_norm": 0.4571075110202611,
"learning_rate": 1.8302894411289303e-05,
"loss": 1.0576,
"step": 527
},
{
"epoch": 1.350383631713555,
"grad_norm": 0.4136171758085541,
"learning_rate": 1.8292927157751964e-05,
"loss": 1.1227,
"step": 528
},
{
"epoch": 1.3529411764705883,
"grad_norm": 0.32738816543873817,
"learning_rate": 1.8282933451161645e-05,
"loss": 1.0839,
"step": 529
},
{
"epoch": 1.3554987212276215,
"grad_norm": 0.263019612016907,
"learning_rate": 1.8272913323396598e-05,
"loss": 1.0556,
"step": 530
},
{
"epoch": 1.3580562659846547,
"grad_norm": 0.2915540173192062,
"learning_rate": 1.8262866806419365e-05,
"loss": 1.0941,
"step": 531
},
{
"epoch": 1.3606138107416879,
"grad_norm": 0.3503149189432805,
"learning_rate": 1.8252793932276652e-05,
"loss": 1.0782,
"step": 532
},
{
"epoch": 1.3631713554987213,
"grad_norm": 0.3642123746279616,
"learning_rate": 1.8242694733099248e-05,
"loss": 1.1175,
"step": 533
},
{
"epoch": 1.3657289002557544,
"grad_norm": 0.25071410695368307,
"learning_rate": 1.823256924110191e-05,
"loss": 1.0834,
"step": 534
},
{
"epoch": 1.3682864450127878,
"grad_norm": 0.3177321847491843,
"learning_rate": 1.822241748858327e-05,
"loss": 1.0943,
"step": 535
},
{
"epoch": 1.370843989769821,
"grad_norm": 0.404922841317797,
"learning_rate": 1.821223950792572e-05,
"loss": 1.1287,
"step": 536
},
{
"epoch": 1.3734015345268542,
"grad_norm": 0.3420279383578445,
"learning_rate": 1.8202035331595322e-05,
"loss": 1.0849,
"step": 537
},
{
"epoch": 1.3759590792838874,
"grad_norm": 0.2634701796758814,
"learning_rate": 1.8191804992141694e-05,
"loss": 1.0976,
"step": 538
},
{
"epoch": 1.3785166240409208,
"grad_norm": 0.2444475712273965,
"learning_rate": 1.818154852219791e-05,
"loss": 1.082,
"step": 539
},
{
"epoch": 1.381074168797954,
"grad_norm": 0.26246699977104565,
"learning_rate": 1.8171265954480396e-05,
"loss": 1.0908,
"step": 540
},
{
"epoch": 1.3836317135549872,
"grad_norm": 0.2779279537467054,
"learning_rate": 1.8160957321788826e-05,
"loss": 1.1171,
"step": 541
},
{
"epoch": 1.3861892583120206,
"grad_norm": 0.28014567822266767,
"learning_rate": 1.8150622657006017e-05,
"loss": 1.1102,
"step": 542
},
{
"epoch": 1.3887468030690537,
"grad_norm": 0.252626441198564,
"learning_rate": 1.814026199309783e-05,
"loss": 1.0649,
"step": 543
},
{
"epoch": 1.391304347826087,
"grad_norm": 0.2177931908988342,
"learning_rate": 1.8129875363113045e-05,
"loss": 1.0855,
"step": 544
},
{
"epoch": 1.39386189258312,
"grad_norm": 0.3025811951941802,
"learning_rate": 1.811946280018328e-05,
"loss": 1.074,
"step": 545
},
{
"epoch": 1.3964194373401535,
"grad_norm": 0.3295849163261702,
"learning_rate": 1.8109024337522875e-05,
"loss": 1.053,
"step": 546
},
{
"epoch": 1.3989769820971867,
"grad_norm": 0.24317934869172414,
"learning_rate": 1.8098560008428778e-05,
"loss": 1.0931,
"step": 547
},
{
"epoch": 1.40153452685422,
"grad_norm": 0.2760178217098737,
"learning_rate": 1.8088069846280456e-05,
"loss": 1.0836,
"step": 548
},
{
"epoch": 1.4040920716112533,
"grad_norm": 0.31057489529721605,
"learning_rate": 1.8077553884539772e-05,
"loss": 1.1068,
"step": 549
},
{
"epoch": 1.4066496163682864,
"grad_norm": 0.30877701785098377,
"learning_rate": 1.8067012156750892e-05,
"loss": 1.0469,
"step": 550
},
{
"epoch": 1.4092071611253196,
"grad_norm": 0.24875376222756798,
"learning_rate": 1.8056444696540162e-05,
"loss": 1.0579,
"step": 551
},
{
"epoch": 1.4117647058823528,
"grad_norm": 0.300038374330651,
"learning_rate": 1.804585153761602e-05,
"loss": 1.1032,
"step": 552
},
{
"epoch": 1.4143222506393862,
"grad_norm": 0.26562355653772984,
"learning_rate": 1.803523271376887e-05,
"loss": 1.087,
"step": 553
},
{
"epoch": 1.4168797953964194,
"grad_norm": 0.27772856419594794,
"learning_rate": 1.802458825887099e-05,
"loss": 1.0976,
"step": 554
},
{
"epoch": 1.4194373401534528,
"grad_norm": 0.27940847480468906,
"learning_rate": 1.8013918206876416e-05,
"loss": 1.1109,
"step": 555
},
{
"epoch": 1.421994884910486,
"grad_norm": 0.23839863723478302,
"learning_rate": 1.8003222591820827e-05,
"loss": 1.0955,
"step": 556
},
{
"epoch": 1.4245524296675192,
"grad_norm": 0.3544376729040761,
"learning_rate": 1.7992501447821454e-05,
"loss": 1.0815,
"step": 557
},
{
"epoch": 1.4271099744245523,
"grad_norm": 0.3190990432271867,
"learning_rate": 1.7981754809076952e-05,
"loss": 1.0743,
"step": 558
},
{
"epoch": 1.4296675191815857,
"grad_norm": 0.30878135684811764,
"learning_rate": 1.7970982709867307e-05,
"loss": 1.0665,
"step": 559
},
{
"epoch": 1.432225063938619,
"grad_norm": 0.2667660845147987,
"learning_rate": 1.7960185184553717e-05,
"loss": 1.0576,
"step": 560
},
{
"epoch": 1.434782608695652,
"grad_norm": 0.27959465142572,
"learning_rate": 1.7949362267578485e-05,
"loss": 1.07,
"step": 561
},
{
"epoch": 1.4373401534526855,
"grad_norm": 0.3088308257405165,
"learning_rate": 1.793851399346491e-05,
"loss": 1.0837,
"step": 562
},
{
"epoch": 1.4398976982097187,
"grad_norm": 0.23954634942810205,
"learning_rate": 1.7927640396817172e-05,
"loss": 1.1108,
"step": 563
},
{
"epoch": 1.4424552429667519,
"grad_norm": 0.3054367971170986,
"learning_rate": 1.7916741512320227e-05,
"loss": 1.109,
"step": 564
},
{
"epoch": 1.445012787723785,
"grad_norm": 0.30343643697738276,
"learning_rate": 1.7905817374739706e-05,
"loss": 1.1167,
"step": 565
},
{
"epoch": 1.4475703324808185,
"grad_norm": 0.2863389806141574,
"learning_rate": 1.789486801892177e-05,
"loss": 1.0784,
"step": 566
},
{
"epoch": 1.4501278772378516,
"grad_norm": 0.21449179573185784,
"learning_rate": 1.7883893479793052e-05,
"loss": 1.0596,
"step": 567
},
{
"epoch": 1.452685421994885,
"grad_norm": 0.281747796628926,
"learning_rate": 1.7872893792360488e-05,
"loss": 1.0907,
"step": 568
},
{
"epoch": 1.4552429667519182,
"grad_norm": 0.3606611327789867,
"learning_rate": 1.7861868991711245e-05,
"loss": 1.0833,
"step": 569
},
{
"epoch": 1.4578005115089514,
"grad_norm": 0.29103388553102216,
"learning_rate": 1.78508191130126e-05,
"loss": 1.0702,
"step": 570
},
{
"epoch": 1.4603580562659846,
"grad_norm": 0.2515965600824205,
"learning_rate": 1.783974419151182e-05,
"loss": 1.092,
"step": 571
},
{
"epoch": 1.4629156010230178,
"grad_norm": 0.3852115976211409,
"learning_rate": 1.782864426253606e-05,
"loss": 1.0969,
"step": 572
},
{
"epoch": 1.4654731457800512,
"grad_norm": 0.4829141442027968,
"learning_rate": 1.7817519361492227e-05,
"loss": 1.0826,
"step": 573
},
{
"epoch": 1.4680306905370843,
"grad_norm": 0.3459344778256553,
"learning_rate": 1.7806369523866914e-05,
"loss": 1.0674,
"step": 574
},
{
"epoch": 1.4705882352941178,
"grad_norm": 0.29132112478633115,
"learning_rate": 1.779519478522623e-05,
"loss": 1.1002,
"step": 575
},
{
"epoch": 1.473145780051151,
"grad_norm": 0.2968482079990474,
"learning_rate": 1.7783995181215727e-05,
"loss": 1.1042,
"step": 576
},
{
"epoch": 1.4757033248081841,
"grad_norm": 0.27855659630768903,
"learning_rate": 1.7772770747560276e-05,
"loss": 1.0958,
"step": 577
},
{
"epoch": 1.4782608695652173,
"grad_norm": 0.2800062391704218,
"learning_rate": 1.7761521520063945e-05,
"loss": 1.0857,
"step": 578
},
{
"epoch": 1.4808184143222507,
"grad_norm": 0.3422253981462545,
"learning_rate": 1.775024753460989e-05,
"loss": 1.0638,
"step": 579
},
{
"epoch": 1.4833759590792839,
"grad_norm": 0.3042841136396043,
"learning_rate": 1.773894882716024e-05,
"loss": 1.081,
"step": 580
},
{
"epoch": 1.485933503836317,
"grad_norm": 0.3584276848759106,
"learning_rate": 1.7727625433755992e-05,
"loss": 1.0979,
"step": 581
},
{
"epoch": 1.4884910485933505,
"grad_norm": 0.4132176697960573,
"learning_rate": 1.7716277390516875e-05,
"loss": 1.0872,
"step": 582
},
{
"epoch": 1.4910485933503836,
"grad_norm": 0.39456958648721346,
"learning_rate": 1.7704904733641255e-05,
"loss": 1.1129,
"step": 583
},
{
"epoch": 1.4936061381074168,
"grad_norm": 0.3047880364961936,
"learning_rate": 1.7693507499406003e-05,
"loss": 1.1183,
"step": 584
},
{
"epoch": 1.49616368286445,
"grad_norm": 0.27995089336581735,
"learning_rate": 1.76820857241664e-05,
"loss": 1.0564,
"step": 585
},
{
"epoch": 1.4987212276214834,
"grad_norm": 0.4582307602852646,
"learning_rate": 1.7670639444355998e-05,
"loss": 1.0723,
"step": 586
},
{
"epoch": 1.5012787723785166,
"grad_norm": 0.3974212413813853,
"learning_rate": 1.7659168696486523e-05,
"loss": 1.0807,
"step": 587
},
{
"epoch": 1.50383631713555,
"grad_norm": 0.26098921400780506,
"learning_rate": 1.764767351714774e-05,
"loss": 1.1072,
"step": 588
},
{
"epoch": 1.5063938618925832,
"grad_norm": 0.3073004608853978,
"learning_rate": 1.763615394300735e-05,
"loss": 1.048,
"step": 589
},
{
"epoch": 1.5089514066496164,
"grad_norm": 0.3496180311318968,
"learning_rate": 1.762461001081088e-05,
"loss": 1.0773,
"step": 590
},
{
"epoch": 1.5115089514066495,
"grad_norm": 0.3459451539906394,
"learning_rate": 1.7613041757381538e-05,
"loss": 1.0509,
"step": 591
},
{
"epoch": 1.5140664961636827,
"grad_norm": 0.2883593584409338,
"learning_rate": 1.7601449219620127e-05,
"loss": 1.1046,
"step": 592
},
{
"epoch": 1.5166240409207161,
"grad_norm": 0.3418272120044329,
"learning_rate": 1.7589832434504903e-05,
"loss": 1.0329,
"step": 593
},
{
"epoch": 1.5191815856777495,
"grad_norm": 0.3955352555839306,
"learning_rate": 1.757819143909147e-05,
"loss": 1.1,
"step": 594
},
{
"epoch": 1.5217391304347827,
"grad_norm": 0.28213312623631964,
"learning_rate": 1.7566526270512663e-05,
"loss": 1.0706,
"step": 595
},
{
"epoch": 1.5242966751918159,
"grad_norm": 0.2723059300728885,
"learning_rate": 1.755483696597842e-05,
"loss": 1.0811,
"step": 596
},
{
"epoch": 1.526854219948849,
"grad_norm": 0.3521368659597091,
"learning_rate": 1.754312356277567e-05,
"loss": 1.0892,
"step": 597
},
{
"epoch": 1.5294117647058822,
"grad_norm": 0.31456673262803825,
"learning_rate": 1.753138609826822e-05,
"loss": 1.0919,
"step": 598
},
{
"epoch": 1.5319693094629157,
"grad_norm": 0.2616348598492441,
"learning_rate": 1.7519624609896614e-05,
"loss": 1.0679,
"step": 599
},
{
"epoch": 1.5345268542199488,
"grad_norm": 0.2813410383684714,
"learning_rate": 1.750783913517804e-05,
"loss": 1.1173,
"step": 600
},
{
"epoch": 1.5370843989769822,
"grad_norm": 0.21204624924930726,
"learning_rate": 1.749602971170619e-05,
"loss": 1.065,
"step": 601
},
{
"epoch": 1.5396419437340154,
"grad_norm": 0.28741509553485445,
"learning_rate": 1.748419637715116e-05,
"loss": 1.0628,
"step": 602
},
{
"epoch": 1.5421994884910486,
"grad_norm": 0.38267662644256223,
"learning_rate": 1.7472339169259306e-05,
"loss": 1.0757,
"step": 603
},
{
"epoch": 1.5447570332480818,
"grad_norm": 0.29841393332702054,
"learning_rate": 1.7460458125853143e-05,
"loss": 1.0865,
"step": 604
},
{
"epoch": 1.547314578005115,
"grad_norm": 0.2530976843608534,
"learning_rate": 1.744855328483122e-05,
"loss": 1.0731,
"step": 605
},
{
"epoch": 1.5498721227621484,
"grad_norm": 0.32358407442808673,
"learning_rate": 1.7436624684167984e-05,
"loss": 1.0495,
"step": 606
},
{
"epoch": 1.5524296675191815,
"grad_norm": 0.31348665372322687,
"learning_rate": 1.7424672361913685e-05,
"loss": 1.0736,
"step": 607
},
{
"epoch": 1.554987212276215,
"grad_norm": 0.2418916979845008,
"learning_rate": 1.7412696356194233e-05,
"loss": 1.0983,
"step": 608
},
{
"epoch": 1.5575447570332481,
"grad_norm": 0.2946315527683715,
"learning_rate": 1.740069670521109e-05,
"loss": 1.0942,
"step": 609
},
{
"epoch": 1.5601023017902813,
"grad_norm": 0.26418886749171827,
"learning_rate": 1.738867344724114e-05,
"loss": 1.0643,
"step": 610
},
{
"epoch": 1.5626598465473145,
"grad_norm": 0.2375625195085471,
"learning_rate": 1.7376626620636558e-05,
"loss": 1.0981,
"step": 611
},
{
"epoch": 1.5652173913043477,
"grad_norm": 0.30919626032852776,
"learning_rate": 1.7364556263824718e-05,
"loss": 1.0884,
"step": 612
},
{
"epoch": 1.567774936061381,
"grad_norm": 0.2723698903787219,
"learning_rate": 1.7352462415308043e-05,
"loss": 1.0784,
"step": 613
},
{
"epoch": 1.5703324808184145,
"grad_norm": 0.22887874198225955,
"learning_rate": 1.734034511366389e-05,
"loss": 1.0824,
"step": 614
},
{
"epoch": 1.5728900255754477,
"grad_norm": 0.29550746740956296,
"learning_rate": 1.7328204397544426e-05,
"loss": 1.1013,
"step": 615
},
{
"epoch": 1.5754475703324808,
"grad_norm": 0.28314944714751183,
"learning_rate": 1.731604030567651e-05,
"loss": 1.0553,
"step": 616
},
{
"epoch": 1.578005115089514,
"grad_norm": 0.2504546352702014,
"learning_rate": 1.730385287686156e-05,
"loss": 1.0892,
"step": 617
},
{
"epoch": 1.5805626598465472,
"grad_norm": 0.2461609364517437,
"learning_rate": 1.7291642149975447e-05,
"loss": 1.0825,
"step": 618
},
{
"epoch": 1.5831202046035806,
"grad_norm": 0.3290342905968507,
"learning_rate": 1.7279408163968344e-05,
"loss": 1.0682,
"step": 619
},
{
"epoch": 1.5856777493606138,
"grad_norm": 0.35081666137815004,
"learning_rate": 1.7267150957864626e-05,
"loss": 1.0562,
"step": 620
},
{
"epoch": 1.5882352941176472,
"grad_norm": 0.28999486002511976,
"learning_rate": 1.7254870570762734e-05,
"loss": 1.0859,
"step": 621
},
{
"epoch": 1.5907928388746804,
"grad_norm": 0.20775563782106674,
"learning_rate": 1.724256704183505e-05,
"loss": 1.0983,
"step": 622
},
{
"epoch": 1.5933503836317136,
"grad_norm": 0.25046303669870285,
"learning_rate": 1.7230240410327784e-05,
"loss": 1.0722,
"step": 623
},
{
"epoch": 1.5959079283887467,
"grad_norm": 0.3120122500057057,
"learning_rate": 1.7217890715560822e-05,
"loss": 1.1117,
"step": 624
},
{
"epoch": 1.59846547314578,
"grad_norm": 0.23438996871875717,
"learning_rate": 1.720551799692764e-05,
"loss": 1.1324,
"step": 625
},
{
"epoch": 1.6010230179028133,
"grad_norm": 0.20904515546827102,
"learning_rate": 1.7193122293895137e-05,
"loss": 1.0592,
"step": 626
},
{
"epoch": 1.6035805626598465,
"grad_norm": 0.32914062124072535,
"learning_rate": 1.7180703646003536e-05,
"loss": 1.0697,
"step": 627
},
{
"epoch": 1.60613810741688,
"grad_norm": 0.37833542302745304,
"learning_rate": 1.7168262092866252e-05,
"loss": 1.1086,
"step": 628
},
{
"epoch": 1.608695652173913,
"grad_norm": 0.2633777304132735,
"learning_rate": 1.715579767416976e-05,
"loss": 1.0619,
"step": 629
},
{
"epoch": 1.6112531969309463,
"grad_norm": 0.26093223398559484,
"learning_rate": 1.714331042967348e-05,
"loss": 1.0676,
"step": 630
},
{
"epoch": 1.6138107416879794,
"grad_norm": 0.31095342245005936,
"learning_rate": 1.7130800399209632e-05,
"loss": 1.0759,
"step": 631
},
{
"epoch": 1.6163682864450126,
"grad_norm": 0.4055927660522638,
"learning_rate": 1.7118267622683123e-05,
"loss": 1.0696,
"step": 632
},
{
"epoch": 1.618925831202046,
"grad_norm": 0.38006329300781394,
"learning_rate": 1.7105712140071427e-05,
"loss": 1.052,
"step": 633
},
{
"epoch": 1.6214833759590794,
"grad_norm": 0.25696206250183334,
"learning_rate": 1.7093133991424425e-05,
"loss": 1.1003,
"step": 634
},
{
"epoch": 1.6240409207161126,
"grad_norm": 0.4045520870520815,
"learning_rate": 1.7080533216864318e-05,
"loss": 1.053,
"step": 635
},
{
"epoch": 1.6265984654731458,
"grad_norm": 0.3944457103687557,
"learning_rate": 1.7067909856585474e-05,
"loss": 1.0994,
"step": 636
},
{
"epoch": 1.629156010230179,
"grad_norm": 0.28734017232782005,
"learning_rate": 1.70552639508543e-05,
"loss": 1.0932,
"step": 637
},
{
"epoch": 1.6317135549872122,
"grad_norm": 0.30914836592137274,
"learning_rate": 1.7042595540009123e-05,
"loss": 1.0777,
"step": 638
},
{
"epoch": 1.6342710997442456,
"grad_norm": 0.3249860111231293,
"learning_rate": 1.7029904664460066e-05,
"loss": 1.1112,
"step": 639
},
{
"epoch": 1.6368286445012787,
"grad_norm": 0.31287350836163863,
"learning_rate": 1.7017191364688896e-05,
"loss": 1.0452,
"step": 640
},
{
"epoch": 1.6393861892583121,
"grad_norm": 0.33833362239628567,
"learning_rate": 1.7004455681248918e-05,
"loss": 1.0658,
"step": 641
},
{
"epoch": 1.6419437340153453,
"grad_norm": 0.242559004260857,
"learning_rate": 1.699169765476484e-05,
"loss": 1.0679,
"step": 642
},
{
"epoch": 1.6445012787723785,
"grad_norm": 0.2790491473058214,
"learning_rate": 1.6978917325932628e-05,
"loss": 1.0833,
"step": 643
},
{
"epoch": 1.6470588235294117,
"grad_norm": 0.23663508280237597,
"learning_rate": 1.6966114735519408e-05,
"loss": 1.1294,
"step": 644
},
{
"epoch": 1.6496163682864449,
"grad_norm": 0.19911244010343537,
"learning_rate": 1.6953289924363297e-05,
"loss": 1.0381,
"step": 645
},
{
"epoch": 1.6521739130434783,
"grad_norm": 0.25134030034591326,
"learning_rate": 1.6940442933373305e-05,
"loss": 1.0953,
"step": 646
},
{
"epoch": 1.6547314578005117,
"grad_norm": 0.2548060423300198,
"learning_rate": 1.6927573803529186e-05,
"loss": 1.0531,
"step": 647
},
{
"epoch": 1.6572890025575449,
"grad_norm": 0.25550208965898963,
"learning_rate": 1.6914682575881312e-05,
"loss": 1.0712,
"step": 648
},
{
"epoch": 1.659846547314578,
"grad_norm": 0.28172858056396866,
"learning_rate": 1.690176929155056e-05,
"loss": 1.0762,
"step": 649
},
{
"epoch": 1.6624040920716112,
"grad_norm": 0.22586367515717168,
"learning_rate": 1.6888833991728137e-05,
"loss": 1.0598,
"step": 650
},
{
"epoch": 1.6649616368286444,
"grad_norm": 0.23131122480912064,
"learning_rate": 1.68758767176755e-05,
"loss": 1.0865,
"step": 651
},
{
"epoch": 1.6675191815856778,
"grad_norm": 0.25447757509954316,
"learning_rate": 1.6862897510724176e-05,
"loss": 1.1109,
"step": 652
},
{
"epoch": 1.670076726342711,
"grad_norm": 0.2553359805367843,
"learning_rate": 1.6849896412275684e-05,
"loss": 1.086,
"step": 653
},
{
"epoch": 1.6726342710997444,
"grad_norm": 0.2745541400801621,
"learning_rate": 1.6836873463801348e-05,
"loss": 1.0907,
"step": 654
},
{
"epoch": 1.6751918158567776,
"grad_norm": 0.2730286942160579,
"learning_rate": 1.68238287068422e-05,
"loss": 1.0798,
"step": 655
},
{
"epoch": 1.6777493606138107,
"grad_norm": 0.26706214928876043,
"learning_rate": 1.6810762183008845e-05,
"loss": 1.0662,
"step": 656
},
{
"epoch": 1.680306905370844,
"grad_norm": 0.2690779370594318,
"learning_rate": 1.67976739339813e-05,
"loss": 1.0685,
"step": 657
},
{
"epoch": 1.682864450127877,
"grad_norm": 0.24513041409636943,
"learning_rate": 1.67845640015089e-05,
"loss": 1.0904,
"step": 658
},
{
"epoch": 1.6854219948849105,
"grad_norm": 0.2808465989622888,
"learning_rate": 1.6771432427410136e-05,
"loss": 1.09,
"step": 659
},
{
"epoch": 1.6879795396419437,
"grad_norm": 0.3142220119591379,
"learning_rate": 1.6758279253572548e-05,
"loss": 1.107,
"step": 660
},
{
"epoch": 1.690537084398977,
"grad_norm": 0.23175871520363883,
"learning_rate": 1.6745104521952552e-05,
"loss": 1.0859,
"step": 661
},
{
"epoch": 1.6930946291560103,
"grad_norm": 0.24672930460906686,
"learning_rate": 1.673190827457535e-05,
"loss": 1.078,
"step": 662
},
{
"epoch": 1.6956521739130435,
"grad_norm": 0.2601230359714199,
"learning_rate": 1.6718690553534766e-05,
"loss": 1.0998,
"step": 663
},
{
"epoch": 1.6982097186700766,
"grad_norm": 0.27044003845983056,
"learning_rate": 1.670545140099312e-05,
"loss": 1.0856,
"step": 664
},
{
"epoch": 1.7007672634271098,
"grad_norm": 0.2323455396605389,
"learning_rate": 1.6692190859181102e-05,
"loss": 1.0898,
"step": 665
},
{
"epoch": 1.7033248081841432,
"grad_norm": 0.24195265129162116,
"learning_rate": 1.6678908970397623e-05,
"loss": 1.0609,
"step": 666
},
{
"epoch": 1.7058823529411766,
"grad_norm": 0.2417510214052941,
"learning_rate": 1.6665605777009698e-05,
"loss": 1.0816,
"step": 667
},
{
"epoch": 1.7084398976982098,
"grad_norm": 0.2651395518131203,
"learning_rate": 1.665228132145228e-05,
"loss": 1.0705,
"step": 668
},
{
"epoch": 1.710997442455243,
"grad_norm": 0.22279503342335966,
"learning_rate": 1.6638935646228168e-05,
"loss": 1.0969,
"step": 669
},
{
"epoch": 1.7135549872122762,
"grad_norm": 0.27626190830784103,
"learning_rate": 1.6625568793907835e-05,
"loss": 1.0758,
"step": 670
},
{
"epoch": 1.7161125319693094,
"grad_norm": 0.293354770533148,
"learning_rate": 1.6612180807129305e-05,
"loss": 1.0928,
"step": 671
},
{
"epoch": 1.7186700767263428,
"grad_norm": 0.22212142950085934,
"learning_rate": 1.6598771728598024e-05,
"loss": 1.0943,
"step": 672
},
{
"epoch": 1.721227621483376,
"grad_norm": 0.23025373127686816,
"learning_rate": 1.6585341601086713e-05,
"loss": 1.0714,
"step": 673
},
{
"epoch": 1.7237851662404093,
"grad_norm": 0.3137233490884019,
"learning_rate": 1.6571890467435233e-05,
"loss": 1.1156,
"step": 674
},
{
"epoch": 1.7263427109974425,
"grad_norm": 0.2496052608065762,
"learning_rate": 1.655841837055046e-05,
"loss": 1.0854,
"step": 675
},
{
"epoch": 1.7289002557544757,
"grad_norm": 0.240092026635267,
"learning_rate": 1.6544925353406127e-05,
"loss": 1.0516,
"step": 676
},
{
"epoch": 1.7314578005115089,
"grad_norm": 0.3007943197702808,
"learning_rate": 1.653141145904271e-05,
"loss": 1.0684,
"step": 677
},
{
"epoch": 1.734015345268542,
"grad_norm": 0.25757031156270827,
"learning_rate": 1.651787673056728e-05,
"loss": 1.07,
"step": 678
},
{
"epoch": 1.7365728900255755,
"grad_norm": 0.27328963709800014,
"learning_rate": 1.6504321211153355e-05,
"loss": 1.0711,
"step": 679
},
{
"epoch": 1.7391304347826086,
"grad_norm": 0.33112287394739875,
"learning_rate": 1.6490744944040776e-05,
"loss": 1.0726,
"step": 680
},
{
"epoch": 1.741687979539642,
"grad_norm": 0.3214662959562765,
"learning_rate": 1.6477147972535577e-05,
"loss": 1.061,
"step": 681
},
{
"epoch": 1.7442455242966752,
"grad_norm": 0.3027544525583265,
"learning_rate": 1.6463530340009817e-05,
"loss": 1.1065,
"step": 682
},
{
"epoch": 1.7468030690537084,
"grad_norm": 0.2609885345467691,
"learning_rate": 1.644989208990148e-05,
"loss": 1.0993,
"step": 683
},
{
"epoch": 1.7493606138107416,
"grad_norm": 0.2993893219580389,
"learning_rate": 1.6436233265714297e-05,
"loss": 1.084,
"step": 684
},
{
"epoch": 1.7519181585677748,
"grad_norm": 0.24875924140149924,
"learning_rate": 1.6422553911017642e-05,
"loss": 1.0761,
"step": 685
},
{
"epoch": 1.7544757033248082,
"grad_norm": 0.2749545983405175,
"learning_rate": 1.6408854069446374e-05,
"loss": 1.1069,
"step": 686
},
{
"epoch": 1.7570332480818416,
"grad_norm": 0.25348934595842737,
"learning_rate": 1.6395133784700696e-05,
"loss": 1.0813,
"step": 687
},
{
"epoch": 1.7595907928388748,
"grad_norm": 0.29036852249839945,
"learning_rate": 1.638139310054603e-05,
"loss": 1.0692,
"step": 688
},
{
"epoch": 1.762148337595908,
"grad_norm": 0.2420069325944099,
"learning_rate": 1.6367632060812856e-05,
"loss": 1.0506,
"step": 689
},
{
"epoch": 1.7647058823529411,
"grad_norm": 0.19405618601521618,
"learning_rate": 1.6353850709396605e-05,
"loss": 1.0764,
"step": 690
},
{
"epoch": 1.7672634271099743,
"grad_norm": 0.22821864695269162,
"learning_rate": 1.6340049090257476e-05,
"loss": 1.0887,
"step": 691
},
{
"epoch": 1.7698209718670077,
"grad_norm": 0.2561864664730904,
"learning_rate": 1.6326227247420337e-05,
"loss": 1.0812,
"step": 692
},
{
"epoch": 1.772378516624041,
"grad_norm": 0.23401055500498363,
"learning_rate": 1.6312385224974555e-05,
"loss": 1.0971,
"step": 693
},
{
"epoch": 1.7749360613810743,
"grad_norm": 0.2810618748667006,
"learning_rate": 1.6298523067073872e-05,
"loss": 1.0485,
"step": 694
},
{
"epoch": 1.7774936061381075,
"grad_norm": 0.23900591068457366,
"learning_rate": 1.6284640817936254e-05,
"loss": 1.0629,
"step": 695
},
{
"epoch": 1.7800511508951407,
"grad_norm": 0.307631766044326,
"learning_rate": 1.6270738521843762e-05,
"loss": 1.097,
"step": 696
},
{
"epoch": 1.7826086956521738,
"grad_norm": 0.23849786656568,
"learning_rate": 1.62568162231424e-05,
"loss": 1.074,
"step": 697
},
{
"epoch": 1.785166240409207,
"grad_norm": 0.3363422147425774,
"learning_rate": 1.6242873966241975e-05,
"loss": 1.09,
"step": 698
},
{
"epoch": 1.7877237851662404,
"grad_norm": 0.2785499919723351,
"learning_rate": 1.6228911795615953e-05,
"loss": 1.0786,
"step": 699
},
{
"epoch": 1.7902813299232738,
"grad_norm": 0.2592472181350103,
"learning_rate": 1.6214929755801335e-05,
"loss": 1.0959,
"step": 700
},
{
"epoch": 1.792838874680307,
"grad_norm": 0.27675406867952207,
"learning_rate": 1.6200927891398486e-05,
"loss": 1.0617,
"step": 701
},
{
"epoch": 1.7953964194373402,
"grad_norm": 0.2707725171412112,
"learning_rate": 1.6186906247071026e-05,
"loss": 1.082,
"step": 702
},
{
"epoch": 1.7979539641943734,
"grad_norm": 0.23850993661114755,
"learning_rate": 1.6172864867545653e-05,
"loss": 1.0842,
"step": 703
},
{
"epoch": 1.8005115089514065,
"grad_norm": 0.26668294516379776,
"learning_rate": 1.615880379761202e-05,
"loss": 1.0643,
"step": 704
},
{
"epoch": 1.80306905370844,
"grad_norm": 0.22065847889215587,
"learning_rate": 1.6144723082122596e-05,
"loss": 1.0953,
"step": 705
},
{
"epoch": 1.8056265984654731,
"grad_norm": 0.22726046087383975,
"learning_rate": 1.613062276599251e-05,
"loss": 1.0457,
"step": 706
},
{
"epoch": 1.8081841432225065,
"grad_norm": 0.2592104058900014,
"learning_rate": 1.611650289419942e-05,
"loss": 1.0503,
"step": 707
},
{
"epoch": 1.8107416879795397,
"grad_norm": 0.2336564349302167,
"learning_rate": 1.610236351178336e-05,
"loss": 1.0763,
"step": 708
},
{
"epoch": 1.813299232736573,
"grad_norm": 0.2528721298539705,
"learning_rate": 1.6088204663846596e-05,
"loss": 1.0253,
"step": 709
},
{
"epoch": 1.815856777493606,
"grad_norm": 0.2206997256192134,
"learning_rate": 1.6074026395553487e-05,
"loss": 1.0709,
"step": 710
},
{
"epoch": 1.8184143222506393,
"grad_norm": 0.27638089805935434,
"learning_rate": 1.6059828752130347e-05,
"loss": 1.1258,
"step": 711
},
{
"epoch": 1.8209718670076727,
"grad_norm": 0.22616837000778253,
"learning_rate": 1.6045611778865282e-05,
"loss": 1.0728,
"step": 712
},
{
"epoch": 1.8235294117647058,
"grad_norm": 0.2494603672128,
"learning_rate": 1.6031375521108068e-05,
"loss": 1.0817,
"step": 713
},
{
"epoch": 1.8260869565217392,
"grad_norm": 0.20041954468789,
"learning_rate": 1.601712002426999e-05,
"loss": 1.0707,
"step": 714
},
{
"epoch": 1.8286445012787724,
"grad_norm": 0.2148146257062548,
"learning_rate": 1.6002845333823696e-05,
"loss": 1.0537,
"step": 715
},
{
"epoch": 1.8312020460358056,
"grad_norm": 0.22346033453757363,
"learning_rate": 1.5988551495303072e-05,
"loss": 1.0707,
"step": 716
},
{
"epoch": 1.8337595907928388,
"grad_norm": 0.2066902162333923,
"learning_rate": 1.5974238554303078e-05,
"loss": 1.041,
"step": 717
},
{
"epoch": 1.836317135549872,
"grad_norm": 0.2813820556225397,
"learning_rate": 1.5959906556479595e-05,
"loss": 1.0912,
"step": 718
},
{
"epoch": 1.8388746803069054,
"grad_norm": 0.2509331071041519,
"learning_rate": 1.5945555547549316e-05,
"loss": 1.0905,
"step": 719
},
{
"epoch": 1.8414322250639388,
"grad_norm": 0.26806908429404896,
"learning_rate": 1.5931185573289557e-05,
"loss": 1.0977,
"step": 720
},
{
"epoch": 1.843989769820972,
"grad_norm": 0.2456487155316564,
"learning_rate": 1.5916796679538137e-05,
"loss": 1.0983,
"step": 721
},
{
"epoch": 1.8465473145780051,
"grad_norm": 0.25480301698890395,
"learning_rate": 1.5902388912193223e-05,
"loss": 1.0538,
"step": 722
},
{
"epoch": 1.8491048593350383,
"grad_norm": 0.23153697687225744,
"learning_rate": 1.588796231721319e-05,
"loss": 1.0815,
"step": 723
},
{
"epoch": 1.8516624040920715,
"grad_norm": 0.21914721485154337,
"learning_rate": 1.5873516940616468e-05,
"loss": 1.0713,
"step": 724
},
{
"epoch": 1.854219948849105,
"grad_norm": 0.24748552983182054,
"learning_rate": 1.5859052828481395e-05,
"loss": 1.1034,
"step": 725
},
{
"epoch": 1.856777493606138,
"grad_norm": 0.24836286711397054,
"learning_rate": 1.5844570026946068e-05,
"loss": 1.0254,
"step": 726
},
{
"epoch": 1.8593350383631715,
"grad_norm": 0.2477358959532818,
"learning_rate": 1.5830068582208217e-05,
"loss": 1.0513,
"step": 727
},
{
"epoch": 1.8618925831202047,
"grad_norm": 0.22729630350906133,
"learning_rate": 1.581554854052502e-05,
"loss": 1.0559,
"step": 728
},
{
"epoch": 1.8644501278772379,
"grad_norm": 0.2527375012776645,
"learning_rate": 1.5801009948212992e-05,
"loss": 1.1154,
"step": 729
},
{
"epoch": 1.867007672634271,
"grad_norm": 0.2430437408352163,
"learning_rate": 1.578645285164781e-05,
"loss": 1.0687,
"step": 730
},
{
"epoch": 1.8695652173913042,
"grad_norm": 0.20727173935167562,
"learning_rate": 1.5771877297264184e-05,
"loss": 1.0398,
"step": 731
},
{
"epoch": 1.8721227621483376,
"grad_norm": 0.21679809470270497,
"learning_rate": 1.5757283331555698e-05,
"loss": 1.0769,
"step": 732
},
{
"epoch": 1.8746803069053708,
"grad_norm": 0.23176747130476263,
"learning_rate": 1.5742671001074666e-05,
"loss": 1.0889,
"step": 733
},
{
"epoch": 1.8772378516624042,
"grad_norm": 0.23200124479221654,
"learning_rate": 1.5728040352431983e-05,
"loss": 1.0472,
"step": 734
},
{
"epoch": 1.8797953964194374,
"grad_norm": 0.2227788458921205,
"learning_rate": 1.5713391432296976e-05,
"loss": 1.0766,
"step": 735
},
{
"epoch": 1.8823529411764706,
"grad_norm": 0.2355356583350579,
"learning_rate": 1.5698724287397254e-05,
"loss": 1.1086,
"step": 736
},
{
"epoch": 1.8849104859335037,
"grad_norm": 0.24042677593727868,
"learning_rate": 1.5684038964518557e-05,
"loss": 1.0814,
"step": 737
},
{
"epoch": 1.887468030690537,
"grad_norm": 0.19933827334366755,
"learning_rate": 1.566933551050462e-05,
"loss": 1.0886,
"step": 738
},
{
"epoch": 1.8900255754475703,
"grad_norm": 0.2591080445820066,
"learning_rate": 1.5654613972256997e-05,
"loss": 1.0723,
"step": 739
},
{
"epoch": 1.8925831202046037,
"grad_norm": 0.2774761431017259,
"learning_rate": 1.5639874396734943e-05,
"loss": 1.0432,
"step": 740
},
{
"epoch": 1.895140664961637,
"grad_norm": 0.22087846289480834,
"learning_rate": 1.5625116830955246e-05,
"loss": 1.0531,
"step": 741
},
{
"epoch": 1.89769820971867,
"grad_norm": 0.27029341996359707,
"learning_rate": 1.5610341321992068e-05,
"loss": 1.0597,
"step": 742
},
{
"epoch": 1.9002557544757033,
"grad_norm": 0.25764475336363896,
"learning_rate": 1.559554791697682e-05,
"loss": 1.0988,
"step": 743
},
{
"epoch": 1.9028132992327365,
"grad_norm": 0.2587858950265225,
"learning_rate": 1.5580736663097998e-05,
"loss": 1.0533,
"step": 744
},
{
"epoch": 1.9053708439897699,
"grad_norm": 0.2416978562367689,
"learning_rate": 1.5565907607601025e-05,
"loss": 1.0502,
"step": 745
},
{
"epoch": 1.907928388746803,
"grad_norm": 0.2772485628569736,
"learning_rate": 1.5551060797788107e-05,
"loss": 1.0742,
"step": 746
},
{
"epoch": 1.9104859335038364,
"grad_norm": 0.2636514324137545,
"learning_rate": 1.5536196281018096e-05,
"loss": 1.0656,
"step": 747
},
{
"epoch": 1.9130434782608696,
"grad_norm": 0.2488817318322834,
"learning_rate": 1.5521314104706318e-05,
"loss": 1.0813,
"step": 748
},
{
"epoch": 1.9156010230179028,
"grad_norm": 0.2607950822000825,
"learning_rate": 1.5506414316324426e-05,
"loss": 1.1034,
"step": 749
},
{
"epoch": 1.918158567774936,
"grad_norm": 0.22986661833547864,
"learning_rate": 1.549149696340026e-05,
"loss": 1.0563,
"step": 750
},
{
"epoch": 1.9207161125319692,
"grad_norm": 0.2531299090639568,
"learning_rate": 1.547656209351769e-05,
"loss": 1.1094,
"step": 751
},
{
"epoch": 1.9232736572890026,
"grad_norm": 0.2362443082311155,
"learning_rate": 1.5461609754316446e-05,
"loss": 1.0598,
"step": 752
},
{
"epoch": 1.9258312020460358,
"grad_norm": 0.2879220642694635,
"learning_rate": 1.5446639993492003e-05,
"loss": 1.0752,
"step": 753
},
{
"epoch": 1.9283887468030692,
"grad_norm": 0.3209490019435245,
"learning_rate": 1.5431652858795394e-05,
"loss": 1.0701,
"step": 754
},
{
"epoch": 1.9309462915601023,
"grad_norm": 0.2510875490823265,
"learning_rate": 1.5416648398033076e-05,
"loss": 1.0393,
"step": 755
},
{
"epoch": 1.9335038363171355,
"grad_norm": 0.31573886950529617,
"learning_rate": 1.5401626659066774e-05,
"loss": 1.0779,
"step": 756
},
{
"epoch": 1.9360613810741687,
"grad_norm": 0.2876023977996849,
"learning_rate": 1.5386587689813333e-05,
"loss": 1.0741,
"step": 757
},
{
"epoch": 1.938618925831202,
"grad_norm": 0.26378670917157787,
"learning_rate": 1.5371531538244547e-05,
"loss": 1.0554,
"step": 758
},
{
"epoch": 1.9411764705882353,
"grad_norm": 0.26374981252096197,
"learning_rate": 1.5356458252387025e-05,
"loss": 1.102,
"step": 759
},
{
"epoch": 1.9437340153452687,
"grad_norm": 0.251595744088401,
"learning_rate": 1.534136788032204e-05,
"loss": 1.1062,
"step": 760
},
{
"epoch": 1.9462915601023019,
"grad_norm": 0.2926779701415132,
"learning_rate": 1.5326260470185353e-05,
"loss": 1.1062,
"step": 761
},
{
"epoch": 1.948849104859335,
"grad_norm": 0.2568048616159297,
"learning_rate": 1.5311136070167076e-05,
"loss": 1.0834,
"step": 762
},
{
"epoch": 1.9514066496163682,
"grad_norm": 0.20314175224340375,
"learning_rate": 1.529599472851153e-05,
"loss": 1.0716,
"step": 763
},
{
"epoch": 1.9539641943734014,
"grad_norm": 0.23750489185611817,
"learning_rate": 1.5280836493517058e-05,
"loss": 1.0872,
"step": 764
},
{
"epoch": 1.9565217391304348,
"grad_norm": 0.21282755180586768,
"learning_rate": 1.5265661413535907e-05,
"loss": 1.0184,
"step": 765
},
{
"epoch": 1.959079283887468,
"grad_norm": 0.24625497205334856,
"learning_rate": 1.5250469536974043e-05,
"loss": 1.0848,
"step": 766
},
{
"epoch": 1.9616368286445014,
"grad_norm": 0.21996647040639863,
"learning_rate": 1.5235260912291012e-05,
"loss": 1.0531,
"step": 767
},
{
"epoch": 1.9641943734015346,
"grad_norm": 0.19256607977575677,
"learning_rate": 1.5220035587999795e-05,
"loss": 1.0798,
"step": 768
},
{
"epoch": 1.9667519181585678,
"grad_norm": 0.23024008315602099,
"learning_rate": 1.5204793612666628e-05,
"loss": 1.0884,
"step": 769
},
{
"epoch": 1.969309462915601,
"grad_norm": 0.2129496532170118,
"learning_rate": 1.5189535034910874e-05,
"loss": 1.07,
"step": 770
},
{
"epoch": 1.9718670076726341,
"grad_norm": 0.20545579206254114,
"learning_rate": 1.5174259903404844e-05,
"loss": 1.0618,
"step": 771
},
{
"epoch": 1.9744245524296675,
"grad_norm": 0.2576111775510631,
"learning_rate": 1.5158968266873657e-05,
"loss": 1.0774,
"step": 772
},
{
"epoch": 1.976982097186701,
"grad_norm": 0.22350592963669672,
"learning_rate": 1.514366017409508e-05,
"loss": 1.0865,
"step": 773
},
{
"epoch": 1.979539641943734,
"grad_norm": 0.2207879071877279,
"learning_rate": 1.5128335673899377e-05,
"loss": 1.0534,
"step": 774
},
{
"epoch": 1.9820971867007673,
"grad_norm": 0.24592252516616664,
"learning_rate": 1.5112994815169143e-05,
"loss": 1.0643,
"step": 775
},
{
"epoch": 1.9846547314578005,
"grad_norm": 0.24493501976628093,
"learning_rate": 1.509763764683915e-05,
"loss": 1.0827,
"step": 776
},
{
"epoch": 1.9872122762148337,
"grad_norm": 0.23172692279011306,
"learning_rate": 1.5082264217896208e-05,
"loss": 1.0622,
"step": 777
},
{
"epoch": 1.989769820971867,
"grad_norm": 0.252231827090011,
"learning_rate": 1.5066874577378987e-05,
"loss": 1.1021,
"step": 778
},
{
"epoch": 1.9923273657289002,
"grad_norm": 0.26229178894088223,
"learning_rate": 1.5051468774377868e-05,
"loss": 1.0833,
"step": 779
},
{
"epoch": 1.9948849104859336,
"grad_norm": 0.28506988516984694,
"learning_rate": 1.5036046858034796e-05,
"loss": 1.0656,
"step": 780
},
{
"epoch": 1.9974424552429668,
"grad_norm": 0.3078431102413717,
"learning_rate": 1.5020608877543103e-05,
"loss": 1.0718,
"step": 781
},
{
"epoch": 2.0,
"grad_norm": 0.21345572776509852,
"learning_rate": 1.5005154882147373e-05,
"loss": 1.0498,
"step": 782
},
{
"epoch": 2.002557544757033,
"grad_norm": 0.34751524748697765,
"learning_rate": 1.4989684921143268e-05,
"loss": 1.0568,
"step": 783
},
{
"epoch": 2.0051150895140664,
"grad_norm": 0.2632901250486642,
"learning_rate": 1.4974199043877383e-05,
"loss": 1.044,
"step": 784
},
{
"epoch": 2.0076726342710995,
"grad_norm": 0.2710330496616998,
"learning_rate": 1.495869729974708e-05,
"loss": 1.0467,
"step": 785
},
{
"epoch": 2.010230179028133,
"grad_norm": 0.23547876798507567,
"learning_rate": 1.4943179738200334e-05,
"loss": 1.1337,
"step": 786
},
{
"epoch": 2.0127877237851663,
"grad_norm": 0.24663671849680985,
"learning_rate": 1.4927646408735576e-05,
"loss": 1.0676,
"step": 787
},
{
"epoch": 2.0153452685421995,
"grad_norm": 0.21964612551270962,
"learning_rate": 1.4912097360901534e-05,
"loss": 1.0775,
"step": 788
},
{
"epoch": 2.0179028132992327,
"grad_norm": 0.20575727001469502,
"learning_rate": 1.489653264429707e-05,
"loss": 1.0604,
"step": 789
},
{
"epoch": 2.020460358056266,
"grad_norm": 0.21546616580679193,
"learning_rate": 1.4880952308571039e-05,
"loss": 1.0497,
"step": 790
},
{
"epoch": 2.023017902813299,
"grad_norm": 0.21519990807634928,
"learning_rate": 1.4865356403422104e-05,
"loss": 1.0481,
"step": 791
},
{
"epoch": 2.0255754475703327,
"grad_norm": 0.23762776400824376,
"learning_rate": 1.4849744978598604e-05,
"loss": 1.0529,
"step": 792
},
{
"epoch": 2.028132992327366,
"grad_norm": 0.22687488068426334,
"learning_rate": 1.4834118083898373e-05,
"loss": 1.0449,
"step": 793
},
{
"epoch": 2.030690537084399,
"grad_norm": 0.2712907192245646,
"learning_rate": 1.4818475769168594e-05,
"loss": 1.0448,
"step": 794
},
{
"epoch": 2.0332480818414322,
"grad_norm": 0.25795810211644293,
"learning_rate": 1.4802818084305646e-05,
"loss": 1.0491,
"step": 795
},
{
"epoch": 2.0358056265984654,
"grad_norm": 0.2276186453417444,
"learning_rate": 1.4787145079254926e-05,
"loss": 1.0631,
"step": 796
},
{
"epoch": 2.0383631713554986,
"grad_norm": 0.2853584063467578,
"learning_rate": 1.4771456804010703e-05,
"loss": 1.0844,
"step": 797
},
{
"epoch": 2.040920716112532,
"grad_norm": 0.24492230560921283,
"learning_rate": 1.4755753308615953e-05,
"loss": 1.0561,
"step": 798
},
{
"epoch": 2.0434782608695654,
"grad_norm": 0.23340351705875467,
"learning_rate": 1.474003464316221e-05,
"loss": 1.0572,
"step": 799
},
{
"epoch": 2.0460358056265986,
"grad_norm": 0.2825027758244028,
"learning_rate": 1.4724300857789387e-05,
"loss": 1.1033,
"step": 800
},
{
"epoch": 2.0485933503836318,
"grad_norm": 0.2499570786028914,
"learning_rate": 1.4708552002685634e-05,
"loss": 1.0545,
"step": 801
},
{
"epoch": 2.051150895140665,
"grad_norm": 0.24594618416181435,
"learning_rate": 1.4692788128087174e-05,
"loss": 1.06,
"step": 802
},
{
"epoch": 2.053708439897698,
"grad_norm": 0.20776683930789736,
"learning_rate": 1.4677009284278128e-05,
"loss": 1.0685,
"step": 803
},
{
"epoch": 2.0562659846547313,
"grad_norm": 0.24408797497104165,
"learning_rate": 1.4661215521590375e-05,
"loss": 1.0969,
"step": 804
},
{
"epoch": 2.0588235294117645,
"grad_norm": 0.2398442146389859,
"learning_rate": 1.4645406890403384e-05,
"loss": 1.0437,
"step": 805
},
{
"epoch": 2.061381074168798,
"grad_norm": 0.27459743419840466,
"learning_rate": 1.4629583441144044e-05,
"loss": 1.0571,
"step": 806
},
{
"epoch": 2.0639386189258313,
"grad_norm": 0.32419594005338426,
"learning_rate": 1.4613745224286523e-05,
"loss": 1.0992,
"step": 807
},
{
"epoch": 2.0664961636828645,
"grad_norm": 0.24865801570827994,
"learning_rate": 1.459789229035208e-05,
"loss": 1.071,
"step": 808
},
{
"epoch": 2.0690537084398977,
"grad_norm": 0.2805482334848806,
"learning_rate": 1.4582024689908933e-05,
"loss": 1.0472,
"step": 809
},
{
"epoch": 2.071611253196931,
"grad_norm": 0.27730449859404743,
"learning_rate": 1.456614247357208e-05,
"loss": 1.0509,
"step": 810
},
{
"epoch": 2.074168797953964,
"grad_norm": 0.21758995784556315,
"learning_rate": 1.455024569200313e-05,
"loss": 1.0754,
"step": 811
},
{
"epoch": 2.0767263427109977,
"grad_norm": 0.30576610905327345,
"learning_rate": 1.4534334395910173e-05,
"loss": 1.0487,
"step": 812
},
{
"epoch": 2.079283887468031,
"grad_norm": 0.2685773932095298,
"learning_rate": 1.4518408636047579e-05,
"loss": 1.049,
"step": 813
},
{
"epoch": 2.081841432225064,
"grad_norm": 0.2752647553950956,
"learning_rate": 1.4502468463215866e-05,
"loss": 1.111,
"step": 814
},
{
"epoch": 2.084398976982097,
"grad_norm": 0.2228850184143428,
"learning_rate": 1.4486513928261525e-05,
"loss": 1.0377,
"step": 815
},
{
"epoch": 2.0869565217391304,
"grad_norm": 0.2791891115513624,
"learning_rate": 1.4470545082076855e-05,
"loss": 1.0498,
"step": 816
},
{
"epoch": 2.0895140664961636,
"grad_norm": 0.24096614975523328,
"learning_rate": 1.445456197559981e-05,
"loss": 1.0612,
"step": 817
},
{
"epoch": 2.0920716112531967,
"grad_norm": 0.22086178812552099,
"learning_rate": 1.4438564659813833e-05,
"loss": 1.0406,
"step": 818
},
{
"epoch": 2.0946291560102304,
"grad_norm": 0.23208084745447222,
"learning_rate": 1.4422553185747693e-05,
"loss": 1.0436,
"step": 819
},
{
"epoch": 2.0971867007672635,
"grad_norm": 0.25938781713310394,
"learning_rate": 1.4406527604475309e-05,
"loss": 1.0457,
"step": 820
},
{
"epoch": 2.0997442455242967,
"grad_norm": 0.2298859593490135,
"learning_rate": 1.4390487967115619e-05,
"loss": 1.0576,
"step": 821
},
{
"epoch": 2.10230179028133,
"grad_norm": 0.2440313535649294,
"learning_rate": 1.4374434324832386e-05,
"loss": 1.0421,
"step": 822
},
{
"epoch": 2.104859335038363,
"grad_norm": 0.21648476955247134,
"learning_rate": 1.4358366728834043e-05,
"loss": 1.0737,
"step": 823
},
{
"epoch": 2.1074168797953963,
"grad_norm": 0.27334150818408187,
"learning_rate": 1.434228523037355e-05,
"loss": 1.067,
"step": 824
},
{
"epoch": 2.10997442455243,
"grad_norm": 0.2339298799419931,
"learning_rate": 1.4326189880748187e-05,
"loss": 1.067,
"step": 825
},
{
"epoch": 2.112531969309463,
"grad_norm": 0.2439620002391159,
"learning_rate": 1.4310080731299443e-05,
"loss": 1.0641,
"step": 826
},
{
"epoch": 2.1150895140664963,
"grad_norm": 0.19808496444753365,
"learning_rate": 1.4293957833412813e-05,
"loss": 1.0547,
"step": 827
},
{
"epoch": 2.1176470588235294,
"grad_norm": 0.23889835747137905,
"learning_rate": 1.4277821238517644e-05,
"loss": 1.066,
"step": 828
},
{
"epoch": 2.1202046035805626,
"grad_norm": 0.23925379076145686,
"learning_rate": 1.4261670998086988e-05,
"loss": 1.0691,
"step": 829
},
{
"epoch": 2.122762148337596,
"grad_norm": 0.22622163591866712,
"learning_rate": 1.4245507163637406e-05,
"loss": 1.0967,
"step": 830
},
{
"epoch": 2.125319693094629,
"grad_norm": 0.24493596074293522,
"learning_rate": 1.4229329786728839e-05,
"loss": 1.0879,
"step": 831
},
{
"epoch": 2.1278772378516626,
"grad_norm": 0.2952728967619172,
"learning_rate": 1.4213138918964415e-05,
"loss": 1.0847,
"step": 832
},
{
"epoch": 2.130434782608696,
"grad_norm": 0.2422929005577866,
"learning_rate": 1.4196934611990296e-05,
"loss": 1.0836,
"step": 833
},
{
"epoch": 2.132992327365729,
"grad_norm": 0.21959782576337455,
"learning_rate": 1.4180716917495521e-05,
"loss": 1.0431,
"step": 834
},
{
"epoch": 2.135549872122762,
"grad_norm": 0.24719640294214473,
"learning_rate": 1.4164485887211825e-05,
"loss": 1.0748,
"step": 835
},
{
"epoch": 2.1381074168797953,
"grad_norm": 0.2856624330721336,
"learning_rate": 1.4148241572913482e-05,
"loss": 1.0915,
"step": 836
},
{
"epoch": 2.1406649616368285,
"grad_norm": 0.20175687613571772,
"learning_rate": 1.4131984026417147e-05,
"loss": 1.0289,
"step": 837
},
{
"epoch": 2.1432225063938617,
"grad_norm": 0.24838388258268573,
"learning_rate": 1.4115713299581677e-05,
"loss": 1.0898,
"step": 838
},
{
"epoch": 2.1457800511508953,
"grad_norm": 0.26748186697500365,
"learning_rate": 1.4099429444307973e-05,
"loss": 1.067,
"step": 839
},
{
"epoch": 2.1483375959079285,
"grad_norm": 0.2586912877126989,
"learning_rate": 1.4083132512538815e-05,
"loss": 1.0905,
"step": 840
},
{
"epoch": 2.1508951406649617,
"grad_norm": 0.24121340420048135,
"learning_rate": 1.4066822556258694e-05,
"loss": 1.0666,
"step": 841
},
{
"epoch": 2.153452685421995,
"grad_norm": 0.2639059153532029,
"learning_rate": 1.4050499627493648e-05,
"loss": 1.0798,
"step": 842
},
{
"epoch": 2.156010230179028,
"grad_norm": 0.27343712262396147,
"learning_rate": 1.4034163778311096e-05,
"loss": 1.0529,
"step": 843
},
{
"epoch": 2.1585677749360612,
"grad_norm": 0.24142653515867196,
"learning_rate": 1.4017815060819667e-05,
"loss": 1.1025,
"step": 844
},
{
"epoch": 2.1611253196930944,
"grad_norm": 0.32920032155082907,
"learning_rate": 1.4001453527169035e-05,
"loss": 1.0612,
"step": 845
},
{
"epoch": 2.163682864450128,
"grad_norm": 0.3015833792100841,
"learning_rate": 1.3985079229549771e-05,
"loss": 1.0569,
"step": 846
},
{
"epoch": 2.166240409207161,
"grad_norm": 0.2522803636771771,
"learning_rate": 1.3968692220193145e-05,
"loss": 1.0174,
"step": 847
},
{
"epoch": 2.1687979539641944,
"grad_norm": 0.26162844295546517,
"learning_rate": 1.3952292551370978e-05,
"loss": 1.11,
"step": 848
},
{
"epoch": 2.1713554987212276,
"grad_norm": 0.27023676278734887,
"learning_rate": 1.3935880275395483e-05,
"loss": 1.0695,
"step": 849
},
{
"epoch": 2.1739130434782608,
"grad_norm": 0.23810673971999766,
"learning_rate": 1.3919455444619074e-05,
"loss": 1.07,
"step": 850
},
{
"epoch": 2.176470588235294,
"grad_norm": 0.2371489539651306,
"learning_rate": 1.390301811143422e-05,
"loss": 1.0748,
"step": 851
},
{
"epoch": 2.1790281329923276,
"grad_norm": 0.24704910714072092,
"learning_rate": 1.388656832827327e-05,
"loss": 1.0886,
"step": 852
},
{
"epoch": 2.1815856777493607,
"grad_norm": 0.25821013482512084,
"learning_rate": 1.3870106147608282e-05,
"loss": 1.026,
"step": 853
},
{
"epoch": 2.184143222506394,
"grad_norm": 0.2595892420977119,
"learning_rate": 1.385363162195087e-05,
"loss": 1.0095,
"step": 854
},
{
"epoch": 2.186700767263427,
"grad_norm": 0.2751769970647654,
"learning_rate": 1.3837144803852016e-05,
"loss": 1.0625,
"step": 855
},
{
"epoch": 2.1892583120204603,
"grad_norm": 0.2611393387522944,
"learning_rate": 1.3820645745901917e-05,
"loss": 1.0819,
"step": 856
},
{
"epoch": 2.1918158567774935,
"grad_norm": 0.2329077525103117,
"learning_rate": 1.3804134500729817e-05,
"loss": 1.0987,
"step": 857
},
{
"epoch": 2.1943734015345266,
"grad_norm": 0.2443911678779139,
"learning_rate": 1.3787611121003825e-05,
"loss": 1.091,
"step": 858
},
{
"epoch": 2.1969309462915603,
"grad_norm": 0.23687678853190128,
"learning_rate": 1.377107565943077e-05,
"loss": 1.0872,
"step": 859
},
{
"epoch": 2.1994884910485935,
"grad_norm": 0.2576015050852838,
"learning_rate": 1.3754528168756007e-05,
"loss": 1.0834,
"step": 860
},
{
"epoch": 2.2020460358056266,
"grad_norm": 0.2599012056741005,
"learning_rate": 1.3737968701763275e-05,
"loss": 1.0766,
"step": 861
},
{
"epoch": 2.20460358056266,
"grad_norm": 0.209435005291082,
"learning_rate": 1.3721397311274505e-05,
"loss": 1.0488,
"step": 862
},
{
"epoch": 2.207161125319693,
"grad_norm": 0.25527194953058974,
"learning_rate": 1.3704814050149664e-05,
"loss": 1.0714,
"step": 863
},
{
"epoch": 2.209718670076726,
"grad_norm": 0.2353445658736852,
"learning_rate": 1.3688218971286588e-05,
"loss": 1.0745,
"step": 864
},
{
"epoch": 2.21227621483376,
"grad_norm": 0.26020939155181216,
"learning_rate": 1.367161212762081e-05,
"loss": 1.0298,
"step": 865
},
{
"epoch": 2.214833759590793,
"grad_norm": 0.23209974209064985,
"learning_rate": 1.3654993572125385e-05,
"loss": 1.0609,
"step": 866
},
{
"epoch": 2.217391304347826,
"grad_norm": 0.2953990139308075,
"learning_rate": 1.3638363357810734e-05,
"loss": 1.1041,
"step": 867
},
{
"epoch": 2.2199488491048593,
"grad_norm": 0.30464352233125175,
"learning_rate": 1.362172153772446e-05,
"loss": 1.0437,
"step": 868
},
{
"epoch": 2.2225063938618925,
"grad_norm": 0.23970358266125305,
"learning_rate": 1.3605068164951195e-05,
"loss": 1.0818,
"step": 869
},
{
"epoch": 2.2250639386189257,
"grad_norm": 0.2974010740237724,
"learning_rate": 1.3588403292612409e-05,
"loss": 1.0667,
"step": 870
},
{
"epoch": 2.227621483375959,
"grad_norm": 0.2986189698714367,
"learning_rate": 1.3571726973866275e-05,
"loss": 1.0468,
"step": 871
},
{
"epoch": 2.2301790281329925,
"grad_norm": 0.22393515546922488,
"learning_rate": 1.3555039261907452e-05,
"loss": 1.0681,
"step": 872
},
{
"epoch": 2.2327365728900257,
"grad_norm": 0.26982155718376244,
"learning_rate": 1.3538340209966965e-05,
"loss": 1.0846,
"step": 873
},
{
"epoch": 2.235294117647059,
"grad_norm": 0.2421804429950771,
"learning_rate": 1.3521629871311997e-05,
"loss": 1.0731,
"step": 874
},
{
"epoch": 2.237851662404092,
"grad_norm": 0.21568056876105401,
"learning_rate": 1.3504908299245738e-05,
"loss": 1.0393,
"step": 875
},
{
"epoch": 2.2404092071611252,
"grad_norm": 0.2820400540340047,
"learning_rate": 1.3488175547107214e-05,
"loss": 1.0592,
"step": 876
},
{
"epoch": 2.2429667519181584,
"grad_norm": 0.2415975374420239,
"learning_rate": 1.3471431668271105e-05,
"loss": 1.0488,
"step": 877
},
{
"epoch": 2.2455242966751916,
"grad_norm": 0.2066593963187682,
"learning_rate": 1.3454676716147595e-05,
"loss": 1.0557,
"step": 878
},
{
"epoch": 2.2480818414322252,
"grad_norm": 0.2835186467703053,
"learning_rate": 1.343791074418218e-05,
"loss": 1.0557,
"step": 879
},
{
"epoch": 2.2506393861892584,
"grad_norm": 0.2038398858990616,
"learning_rate": 1.342113380585551e-05,
"loss": 1.0305,
"step": 880
},
{
"epoch": 2.2531969309462916,
"grad_norm": 0.2467659045058108,
"learning_rate": 1.3404345954683223e-05,
"loss": 1.0502,
"step": 881
},
{
"epoch": 2.2557544757033248,
"grad_norm": 0.23271887429473748,
"learning_rate": 1.3387547244215755e-05,
"loss": 1.017,
"step": 882
},
{
"epoch": 2.258312020460358,
"grad_norm": 0.23672669602819807,
"learning_rate": 1.337073772803819e-05,
"loss": 1.0577,
"step": 883
},
{
"epoch": 2.260869565217391,
"grad_norm": 0.20836338901899323,
"learning_rate": 1.3353917459770078e-05,
"loss": 1.0523,
"step": 884
},
{
"epoch": 2.2634271099744243,
"grad_norm": 0.2689164014770486,
"learning_rate": 1.3337086493065266e-05,
"loss": 1.0727,
"step": 885
},
{
"epoch": 2.265984654731458,
"grad_norm": 0.20010892395917804,
"learning_rate": 1.3320244881611728e-05,
"loss": 1.0801,
"step": 886
},
{
"epoch": 2.268542199488491,
"grad_norm": 0.21502634804444792,
"learning_rate": 1.3303392679131393e-05,
"loss": 1.0342,
"step": 887
},
{
"epoch": 2.2710997442455243,
"grad_norm": 0.22292944251420502,
"learning_rate": 1.3286529939379969e-05,
"loss": 1.0403,
"step": 888
},
{
"epoch": 2.2736572890025575,
"grad_norm": 0.1889567658964355,
"learning_rate": 1.3269656716146786e-05,
"loss": 1.0657,
"step": 889
},
{
"epoch": 2.2762148337595907,
"grad_norm": 0.22240068914596578,
"learning_rate": 1.3252773063254609e-05,
"loss": 1.0996,
"step": 890
},
{
"epoch": 2.2787723785166243,
"grad_norm": 0.20078276182072644,
"learning_rate": 1.3235879034559467e-05,
"loss": 1.0756,
"step": 891
},
{
"epoch": 2.2813299232736575,
"grad_norm": 0.20342234409609955,
"learning_rate": 1.321897468395049e-05,
"loss": 1.0592,
"step": 892
},
{
"epoch": 2.2838874680306906,
"grad_norm": 0.20922107317317695,
"learning_rate": 1.320206006534974e-05,
"loss": 1.0656,
"step": 893
},
{
"epoch": 2.286445012787724,
"grad_norm": 0.19491180577509853,
"learning_rate": 1.3185135232712024e-05,
"loss": 1.0862,
"step": 894
},
{
"epoch": 2.289002557544757,
"grad_norm": 0.21756827855179173,
"learning_rate": 1.316820024002473e-05,
"loss": 1.0757,
"step": 895
},
{
"epoch": 2.29156010230179,
"grad_norm": 0.19452656906284796,
"learning_rate": 1.3151255141307658e-05,
"loss": 1.0618,
"step": 896
},
{
"epoch": 2.2941176470588234,
"grad_norm": 0.23416160900137958,
"learning_rate": 1.3134299990612843e-05,
"loss": 1.0607,
"step": 897
},
{
"epoch": 2.296675191815857,
"grad_norm": 0.20712138927673676,
"learning_rate": 1.3117334842024386e-05,
"loss": 1.036,
"step": 898
},
{
"epoch": 2.29923273657289,
"grad_norm": 0.21330832703203775,
"learning_rate": 1.310035974965828e-05,
"loss": 1.0722,
"step": 899
},
{
"epoch": 2.3017902813299234,
"grad_norm": 0.21219344261681405,
"learning_rate": 1.308337476766223e-05,
"loss": 1.0559,
"step": 900
},
{
"epoch": 2.3043478260869565,
"grad_norm": 0.2258939301473968,
"learning_rate": 1.3066379950215499e-05,
"loss": 1.0473,
"step": 901
},
{
"epoch": 2.3069053708439897,
"grad_norm": 0.19516875187667224,
"learning_rate": 1.3049375351528713e-05,
"loss": 1.0525,
"step": 902
},
{
"epoch": 2.309462915601023,
"grad_norm": 0.21614015553918936,
"learning_rate": 1.3032361025843704e-05,
"loss": 1.0763,
"step": 903
},
{
"epoch": 2.312020460358056,
"grad_norm": 0.20862663707679718,
"learning_rate": 1.301533702743333e-05,
"loss": 0.9991,
"step": 904
},
{
"epoch": 2.3145780051150897,
"grad_norm": 0.2379949878093605,
"learning_rate": 1.29983034106013e-05,
"loss": 1.0369,
"step": 905
},
{
"epoch": 2.317135549872123,
"grad_norm": 0.2447808238713185,
"learning_rate": 1.2981260229682018e-05,
"loss": 1.0461,
"step": 906
},
{
"epoch": 2.319693094629156,
"grad_norm": 0.27684254724066776,
"learning_rate": 1.2964207539040373e-05,
"loss": 1.0505,
"step": 907
},
{
"epoch": 2.3222506393861893,
"grad_norm": 0.2078769477308904,
"learning_rate": 1.2947145393071607e-05,
"loss": 1.0912,
"step": 908
},
{
"epoch": 2.3248081841432224,
"grad_norm": 0.2108719484786227,
"learning_rate": 1.2930073846201116e-05,
"loss": 1.0261,
"step": 909
},
{
"epoch": 2.3273657289002556,
"grad_norm": 0.21718674615633884,
"learning_rate": 1.2912992952884283e-05,
"loss": 1.1043,
"step": 910
},
{
"epoch": 2.329923273657289,
"grad_norm": 0.22685276306972108,
"learning_rate": 1.289590276760631e-05,
"loss": 1.0806,
"step": 911
},
{
"epoch": 2.3324808184143224,
"grad_norm": 0.23081228405085022,
"learning_rate": 1.2878803344882029e-05,
"loss": 1.0392,
"step": 912
},
{
"epoch": 2.3350383631713556,
"grad_norm": 0.2011412522246678,
"learning_rate": 1.2861694739255746e-05,
"loss": 1.0713,
"step": 913
},
{
"epoch": 2.337595907928389,
"grad_norm": 0.23619794732179872,
"learning_rate": 1.2844577005301055e-05,
"loss": 1.0704,
"step": 914
},
{
"epoch": 2.340153452685422,
"grad_norm": 0.2698850856720426,
"learning_rate": 1.2827450197620673e-05,
"loss": 1.0685,
"step": 915
},
{
"epoch": 2.342710997442455,
"grad_norm": 0.19779154874996993,
"learning_rate": 1.2810314370846252e-05,
"loss": 1.0895,
"step": 916
},
{
"epoch": 2.3452685421994883,
"grad_norm": 0.2579605967239507,
"learning_rate": 1.2793169579638222e-05,
"loss": 1.0299,
"step": 917
},
{
"epoch": 2.3478260869565215,
"grad_norm": 0.22140608359673922,
"learning_rate": 1.2776015878685603e-05,
"loss": 1.0582,
"step": 918
},
{
"epoch": 2.350383631713555,
"grad_norm": 0.21371909171227776,
"learning_rate": 1.2758853322705835e-05,
"loss": 1.0451,
"step": 919
},
{
"epoch": 2.3529411764705883,
"grad_norm": 0.23474961790937948,
"learning_rate": 1.2741681966444608e-05,
"loss": 1.045,
"step": 920
},
{
"epoch": 2.3554987212276215,
"grad_norm": 0.19870860509615906,
"learning_rate": 1.2724501864675682e-05,
"loss": 1.0487,
"step": 921
},
{
"epoch": 2.3580562659846547,
"grad_norm": 0.20253838337881694,
"learning_rate": 1.270731307220071e-05,
"loss": 1.0481,
"step": 922
},
{
"epoch": 2.360613810741688,
"grad_norm": 0.23011797101382442,
"learning_rate": 1.269011564384908e-05,
"loss": 1.0515,
"step": 923
},
{
"epoch": 2.363171355498721,
"grad_norm": 0.22374354187112894,
"learning_rate": 1.2672909634477701e-05,
"loss": 1.0593,
"step": 924
},
{
"epoch": 2.3657289002557547,
"grad_norm": 0.2500406678934162,
"learning_rate": 1.2655695098970881e-05,
"loss": 1.0468,
"step": 925
},
{
"epoch": 2.368286445012788,
"grad_norm": 0.21282680432072176,
"learning_rate": 1.2638472092240112e-05,
"loss": 1.0224,
"step": 926
},
{
"epoch": 2.370843989769821,
"grad_norm": 0.2631854118749461,
"learning_rate": 1.2621240669223906e-05,
"loss": 1.0799,
"step": 927
},
{
"epoch": 2.373401534526854,
"grad_norm": 0.21209069180980092,
"learning_rate": 1.2604000884887636e-05,
"loss": 1.0855,
"step": 928
},
{
"epoch": 2.3759590792838874,
"grad_norm": 0.2433054732140672,
"learning_rate": 1.2586752794223321e-05,
"loss": 1.0541,
"step": 929
},
{
"epoch": 2.3785166240409206,
"grad_norm": 0.2630201541116053,
"learning_rate": 1.25694964522495e-05,
"loss": 1.0786,
"step": 930
},
{
"epoch": 2.381074168797954,
"grad_norm": 0.19419910941081836,
"learning_rate": 1.2552231914011017e-05,
"loss": 1.0452,
"step": 931
},
{
"epoch": 2.3836317135549874,
"grad_norm": 0.2699915357205121,
"learning_rate": 1.2534959234578872e-05,
"loss": 1.071,
"step": 932
},
{
"epoch": 2.3861892583120206,
"grad_norm": 0.29724325552356046,
"learning_rate": 1.2517678469050023e-05,
"loss": 1.053,
"step": 933
},
{
"epoch": 2.3887468030690537,
"grad_norm": 0.22602756795970175,
"learning_rate": 1.2500389672547233e-05,
"loss": 1.0411,
"step": 934
},
{
"epoch": 2.391304347826087,
"grad_norm": 0.27261078615742584,
"learning_rate": 1.2483092900218872e-05,
"loss": 1.0397,
"step": 935
},
{
"epoch": 2.39386189258312,
"grad_norm": 0.33769171299450684,
"learning_rate": 1.2465788207238754e-05,
"loss": 1.0579,
"step": 936
},
{
"epoch": 2.3964194373401533,
"grad_norm": 0.24562682326063173,
"learning_rate": 1.2448475648805965e-05,
"loss": 1.06,
"step": 937
},
{
"epoch": 2.398976982097187,
"grad_norm": 0.31976622618763517,
"learning_rate": 1.243115528014467e-05,
"loss": 1.0693,
"step": 938
},
{
"epoch": 2.40153452685422,
"grad_norm": 0.27193293795403,
"learning_rate": 1.2413827156503959e-05,
"loss": 1.0517,
"step": 939
},
{
"epoch": 2.4040920716112533,
"grad_norm": 0.2800053392929295,
"learning_rate": 1.2396491333157653e-05,
"loss": 1.0618,
"step": 940
},
{
"epoch": 2.4066496163682864,
"grad_norm": 0.3288127671391703,
"learning_rate": 1.2379147865404126e-05,
"loss": 1.0503,
"step": 941
},
{
"epoch": 2.4092071611253196,
"grad_norm": 0.21261108528502098,
"learning_rate": 1.2361796808566154e-05,
"loss": 1.0608,
"step": 942
},
{
"epoch": 2.411764705882353,
"grad_norm": 0.2940216342886679,
"learning_rate": 1.2344438217990706e-05,
"loss": 1.0632,
"step": 943
},
{
"epoch": 2.414322250639386,
"grad_norm": 0.2887698618246557,
"learning_rate": 1.2327072149048787e-05,
"loss": 1.0639,
"step": 944
},
{
"epoch": 2.4168797953964196,
"grad_norm": 0.24521223833198755,
"learning_rate": 1.2309698657135263e-05,
"loss": 1.0162,
"step": 945
},
{
"epoch": 2.419437340153453,
"grad_norm": 0.185509429971427,
"learning_rate": 1.2292317797668664e-05,
"loss": 1.0363,
"step": 946
},
{
"epoch": 2.421994884910486,
"grad_norm": 0.25872152655717207,
"learning_rate": 1.2274929626091035e-05,
"loss": 1.0881,
"step": 947
},
{
"epoch": 2.424552429667519,
"grad_norm": 0.18008549030963775,
"learning_rate": 1.2257534197867744e-05,
"loss": 1.0446,
"step": 948
},
{
"epoch": 2.4271099744245523,
"grad_norm": 0.23690086440423483,
"learning_rate": 1.2240131568487292e-05,
"loss": 1.0616,
"step": 949
},
{
"epoch": 2.4296675191815855,
"grad_norm": 0.1983151726827165,
"learning_rate": 1.222272179346117e-05,
"loss": 1.0419,
"step": 950
},
{
"epoch": 2.4322250639386187,
"grad_norm": 0.18747005388252086,
"learning_rate": 1.2205304928323649e-05,
"loss": 1.0595,
"step": 951
},
{
"epoch": 2.4347826086956523,
"grad_norm": 0.20660938308532778,
"learning_rate": 1.2187881028631621e-05,
"loss": 1.022,
"step": 952
},
{
"epoch": 2.4373401534526855,
"grad_norm": 0.20200728083626612,
"learning_rate": 1.2170450149964422e-05,
"loss": 1.0756,
"step": 953
},
{
"epoch": 2.4398976982097187,
"grad_norm": 0.21912464070245444,
"learning_rate": 1.2153012347923635e-05,
"loss": 1.0771,
"step": 954
},
{
"epoch": 2.442455242966752,
"grad_norm": 0.23866041513967645,
"learning_rate": 1.2135567678132942e-05,
"loss": 1.0523,
"step": 955
},
{
"epoch": 2.445012787723785,
"grad_norm": 0.21521617514557267,
"learning_rate": 1.211811619623793e-05,
"loss": 1.059,
"step": 956
},
{
"epoch": 2.4475703324808182,
"grad_norm": 0.24265391190201183,
"learning_rate": 1.2100657957905908e-05,
"loss": 1.0307,
"step": 957
},
{
"epoch": 2.4501278772378514,
"grad_norm": 0.2132548988703794,
"learning_rate": 1.2083193018825745e-05,
"loss": 1.025,
"step": 958
},
{
"epoch": 2.452685421994885,
"grad_norm": 0.22131174672899057,
"learning_rate": 1.2065721434707677e-05,
"loss": 1.0474,
"step": 959
},
{
"epoch": 2.455242966751918,
"grad_norm": 0.19904663813024445,
"learning_rate": 1.2048243261283144e-05,
"loss": 1.0226,
"step": 960
},
{
"epoch": 2.4578005115089514,
"grad_norm": 0.200161353355971,
"learning_rate": 1.2030758554304593e-05,
"loss": 1.0924,
"step": 961
},
{
"epoch": 2.4603580562659846,
"grad_norm": 0.19830084311557072,
"learning_rate": 1.2013267369545329e-05,
"loss": 1.0667,
"step": 962
},
{
"epoch": 2.4629156010230178,
"grad_norm": 0.22835260283972367,
"learning_rate": 1.1995769762799307e-05,
"loss": 1.0754,
"step": 963
},
{
"epoch": 2.4654731457800514,
"grad_norm": 0.210015027120209,
"learning_rate": 1.1978265789880974e-05,
"loss": 1.0808,
"step": 964
},
{
"epoch": 2.4680306905370846,
"grad_norm": 0.2697432497468849,
"learning_rate": 1.1960755506625077e-05,
"loss": 1.0307,
"step": 965
},
{
"epoch": 2.4705882352941178,
"grad_norm": 0.23179650613650557,
"learning_rate": 1.1943238968886492e-05,
"loss": 1.046,
"step": 966
},
{
"epoch": 2.473145780051151,
"grad_norm": 0.24001578621119793,
"learning_rate": 1.1925716232540062e-05,
"loss": 1.0571,
"step": 967
},
{
"epoch": 2.475703324808184,
"grad_norm": 0.23255368408434818,
"learning_rate": 1.1908187353480381e-05,
"loss": 1.0621,
"step": 968
},
{
"epoch": 2.4782608695652173,
"grad_norm": 0.48924197246918594,
"learning_rate": 1.1890652387621645e-05,
"loss": 1.0603,
"step": 969
},
{
"epoch": 2.4808184143222505,
"grad_norm": 0.24215100765578446,
"learning_rate": 1.1873111390897475e-05,
"loss": 1.0301,
"step": 970
},
{
"epoch": 2.483375959079284,
"grad_norm": 0.23579580906631162,
"learning_rate": 1.1855564419260714e-05,
"loss": 1.0531,
"step": 971
},
{
"epoch": 2.4859335038363173,
"grad_norm": 0.21475267684489457,
"learning_rate": 1.1838011528683279e-05,
"loss": 1.074,
"step": 972
},
{
"epoch": 2.4884910485933505,
"grad_norm": 0.2584450023059667,
"learning_rate": 1.1820452775155957e-05,
"loss": 1.0536,
"step": 973
},
{
"epoch": 2.4910485933503836,
"grad_norm": 0.1843171436312304,
"learning_rate": 1.1802888214688235e-05,
"loss": 1.0526,
"step": 974
},
{
"epoch": 2.493606138107417,
"grad_norm": 0.25846478231848835,
"learning_rate": 1.1785317903308138e-05,
"loss": 1.0319,
"step": 975
},
{
"epoch": 2.49616368286445,
"grad_norm": 0.20971255177789871,
"learning_rate": 1.1767741897062018e-05,
"loss": 1.0613,
"step": 976
},
{
"epoch": 2.498721227621483,
"grad_norm": 0.20077211970723166,
"learning_rate": 1.1750160252014401e-05,
"loss": 1.0498,
"step": 977
},
{
"epoch": 2.501278772378517,
"grad_norm": 0.22501567037645762,
"learning_rate": 1.1732573024247803e-05,
"loss": 1.0659,
"step": 978
},
{
"epoch": 2.50383631713555,
"grad_norm": 0.21521993533238856,
"learning_rate": 1.171498026986254e-05,
"loss": 1.0702,
"step": 979
},
{
"epoch": 2.506393861892583,
"grad_norm": 0.2503577565530584,
"learning_rate": 1.1697382044976563e-05,
"loss": 1.0288,
"step": 980
},
{
"epoch": 2.5089514066496164,
"grad_norm": 0.2047302770203722,
"learning_rate": 1.1679778405725274e-05,
"loss": 1.0376,
"step": 981
},
{
"epoch": 2.5115089514066495,
"grad_norm": 0.23939263890617613,
"learning_rate": 1.166216940826134e-05,
"loss": 1.0187,
"step": 982
},
{
"epoch": 2.5140664961636827,
"grad_norm": 0.23761678919939125,
"learning_rate": 1.1644555108754518e-05,
"loss": 1.0308,
"step": 983
},
{
"epoch": 2.516624040920716,
"grad_norm": 0.21248204414574057,
"learning_rate": 1.1626935563391491e-05,
"loss": 1.0618,
"step": 984
},
{
"epoch": 2.5191815856777495,
"grad_norm": 0.24094115122902504,
"learning_rate": 1.1609310828375662e-05,
"loss": 1.0594,
"step": 985
},
{
"epoch": 2.5217391304347827,
"grad_norm": 0.19223099803507016,
"learning_rate": 1.1591680959926994e-05,
"loss": 1.0322,
"step": 986
},
{
"epoch": 2.524296675191816,
"grad_norm": 0.20707448434011191,
"learning_rate": 1.1574046014281823e-05,
"loss": 1.044,
"step": 987
},
{
"epoch": 2.526854219948849,
"grad_norm": 0.24109072712135063,
"learning_rate": 1.1556406047692681e-05,
"loss": 1.0695,
"step": 988
},
{
"epoch": 2.5294117647058822,
"grad_norm": 0.1979569377790155,
"learning_rate": 1.153876111642812e-05,
"loss": 1.0685,
"step": 989
},
{
"epoch": 2.531969309462916,
"grad_norm": 0.2936427182568951,
"learning_rate": 1.1521111276772519e-05,
"loss": 1.0778,
"step": 990
},
{
"epoch": 2.5345268542199486,
"grad_norm": 0.2547622419807327,
"learning_rate": 1.1503456585025918e-05,
"loss": 1.0573,
"step": 991
},
{
"epoch": 2.5370843989769822,
"grad_norm": 0.20636327167754573,
"learning_rate": 1.1485797097503848e-05,
"loss": 1.0753,
"step": 992
},
{
"epoch": 2.5396419437340154,
"grad_norm": 0.23885851857779103,
"learning_rate": 1.1468132870537112e-05,
"loss": 1.0565,
"step": 993
},
{
"epoch": 2.5421994884910486,
"grad_norm": 0.23233207950400891,
"learning_rate": 1.1450463960471652e-05,
"loss": 1.0388,
"step": 994
},
{
"epoch": 2.544757033248082,
"grad_norm": 0.19749031677810552,
"learning_rate": 1.143279042366834e-05,
"loss": 1.0315,
"step": 995
},
{
"epoch": 2.547314578005115,
"grad_norm": 0.21579547394805096,
"learning_rate": 1.1415112316502803e-05,
"loss": 1.0494,
"step": 996
},
{
"epoch": 2.5498721227621486,
"grad_norm": 0.20484578816866386,
"learning_rate": 1.139742969536526e-05,
"loss": 1.0528,
"step": 997
},
{
"epoch": 2.5524296675191813,
"grad_norm": 0.21000639971172463,
"learning_rate": 1.137974261666031e-05,
"loss": 1.0512,
"step": 998
},
{
"epoch": 2.554987212276215,
"grad_norm": 0.21807550593498504,
"learning_rate": 1.1362051136806789e-05,
"loss": 1.0457,
"step": 999
},
{
"epoch": 2.557544757033248,
"grad_norm": 0.21057183954898145,
"learning_rate": 1.134435531223756e-05,
"loss": 1.0489,
"step": 1000
},
{
"epoch": 2.5601023017902813,
"grad_norm": 0.2407874905737883,
"learning_rate": 1.1326655199399345e-05,
"loss": 1.0505,
"step": 1001
},
{
"epoch": 2.5626598465473145,
"grad_norm": 0.18794902645115422,
"learning_rate": 1.1308950854752558e-05,
"loss": 1.0412,
"step": 1002
},
{
"epoch": 2.5652173913043477,
"grad_norm": 0.22621031822986007,
"learning_rate": 1.1291242334771095e-05,
"loss": 1.069,
"step": 1003
},
{
"epoch": 2.5677749360613813,
"grad_norm": 0.23324199109224647,
"learning_rate": 1.1273529695942182e-05,
"loss": 1.0759,
"step": 1004
},
{
"epoch": 2.5703324808184145,
"grad_norm": 0.18313611243360517,
"learning_rate": 1.1255812994766175e-05,
"loss": 1.0684,
"step": 1005
},
{
"epoch": 2.5728900255754477,
"grad_norm": 0.2573525956981243,
"learning_rate": 1.1238092287756398e-05,
"loss": 1.0048,
"step": 1006
},
{
"epoch": 2.575447570332481,
"grad_norm": 0.20054767287206388,
"learning_rate": 1.1220367631438942e-05,
"loss": 1.0829,
"step": 1007
},
{
"epoch": 2.578005115089514,
"grad_norm": 0.24044976517280556,
"learning_rate": 1.1202639082352507e-05,
"loss": 1.0709,
"step": 1008
},
{
"epoch": 2.580562659846547,
"grad_norm": 0.2395771076173231,
"learning_rate": 1.1184906697048202e-05,
"loss": 1.0693,
"step": 1009
},
{
"epoch": 2.5831202046035804,
"grad_norm": 0.20887269846123238,
"learning_rate": 1.1167170532089369e-05,
"loss": 1.0562,
"step": 1010
},
{
"epoch": 2.585677749360614,
"grad_norm": 0.19484085301448842,
"learning_rate": 1.1149430644051424e-05,
"loss": 1.0568,
"step": 1011
},
{
"epoch": 2.588235294117647,
"grad_norm": 0.21120065497048005,
"learning_rate": 1.1131687089521642e-05,
"loss": 1.0614,
"step": 1012
},
{
"epoch": 2.5907928388746804,
"grad_norm": 0.1815853723973056,
"learning_rate": 1.1113939925098997e-05,
"loss": 1.0446,
"step": 1013
},
{
"epoch": 2.5933503836317136,
"grad_norm": 0.2128237313274396,
"learning_rate": 1.1096189207393988e-05,
"loss": 1.062,
"step": 1014
},
{
"epoch": 2.5959079283887467,
"grad_norm": 0.18118399034984362,
"learning_rate": 1.107843499302843e-05,
"loss": 1.0439,
"step": 1015
},
{
"epoch": 2.59846547314578,
"grad_norm": 0.21014691974066443,
"learning_rate": 1.106067733863531e-05,
"loss": 1.044,
"step": 1016
},
{
"epoch": 2.601023017902813,
"grad_norm": 0.2143448693572357,
"learning_rate": 1.1042916300858584e-05,
"loss": 1.0535,
"step": 1017
},
{
"epoch": 2.6035805626598467,
"grad_norm": 0.22800193329799043,
"learning_rate": 1.1025151936352987e-05,
"loss": 1.0573,
"step": 1018
},
{
"epoch": 2.60613810741688,
"grad_norm": 0.16936959510436445,
"learning_rate": 1.1007384301783884e-05,
"loss": 1.0287,
"step": 1019
},
{
"epoch": 2.608695652173913,
"grad_norm": 0.23646633318638022,
"learning_rate": 1.0989613453827058e-05,
"loss": 1.0376,
"step": 1020
},
{
"epoch": 2.6112531969309463,
"grad_norm": 0.20474382321861417,
"learning_rate": 1.0971839449168543e-05,
"loss": 1.05,
"step": 1021
},
{
"epoch": 2.6138107416879794,
"grad_norm": 0.25295508871584677,
"learning_rate": 1.095406234450446e-05,
"loss": 1.0431,
"step": 1022
},
{
"epoch": 2.6163682864450126,
"grad_norm": 0.20284701204586733,
"learning_rate": 1.0936282196540788e-05,
"loss": 1.0668,
"step": 1023
},
{
"epoch": 2.618925831202046,
"grad_norm": 0.23447500011585404,
"learning_rate": 1.0918499061993241e-05,
"loss": 1.0454,
"step": 1024
},
{
"epoch": 2.6214833759590794,
"grad_norm": 0.218326014757165,
"learning_rate": 1.0900712997587048e-05,
"loss": 1.0405,
"step": 1025
},
{
"epoch": 2.6240409207161126,
"grad_norm": 0.19544037134244654,
"learning_rate": 1.0882924060056782e-05,
"loss": 1.0487,
"step": 1026
},
{
"epoch": 2.626598465473146,
"grad_norm": 0.24715529739963063,
"learning_rate": 1.0865132306146182e-05,
"loss": 1.0561,
"step": 1027
},
{
"epoch": 2.629156010230179,
"grad_norm": 0.19894449110120455,
"learning_rate": 1.0847337792607978e-05,
"loss": 1.0662,
"step": 1028
},
{
"epoch": 2.631713554987212,
"grad_norm": 0.21505303389916322,
"learning_rate": 1.0829540576203695e-05,
"loss": 1.069,
"step": 1029
},
{
"epoch": 2.634271099744246,
"grad_norm": 0.18761978697875684,
"learning_rate": 1.0811740713703476e-05,
"loss": 1.0545,
"step": 1030
},
{
"epoch": 2.6368286445012785,
"grad_norm": 0.20721529389957177,
"learning_rate": 1.0793938261885917e-05,
"loss": 1.0598,
"step": 1031
},
{
"epoch": 2.639386189258312,
"grad_norm": 0.20950006821732456,
"learning_rate": 1.0776133277537865e-05,
"loss": 1.0253,
"step": 1032
},
{
"epoch": 2.6419437340153453,
"grad_norm": 0.22635292623674808,
"learning_rate": 1.075832581745425e-05,
"loss": 1.0847,
"step": 1033
},
{
"epoch": 2.6445012787723785,
"grad_norm": 0.19656361617686485,
"learning_rate": 1.074051593843789e-05,
"loss": 1.0618,
"step": 1034
},
{
"epoch": 2.6470588235294117,
"grad_norm": 0.2260452430200194,
"learning_rate": 1.0722703697299328e-05,
"loss": 1.0662,
"step": 1035
},
{
"epoch": 2.649616368286445,
"grad_norm": 0.19750297888085683,
"learning_rate": 1.070488915085664e-05,
"loss": 1.0387,
"step": 1036
},
{
"epoch": 2.6521739130434785,
"grad_norm": 0.1995618558238664,
"learning_rate": 1.0687072355935257e-05,
"loss": 1.0458,
"step": 1037
},
{
"epoch": 2.6547314578005117,
"grad_norm": 0.19344732111610985,
"learning_rate": 1.0669253369367776e-05,
"loss": 1.0501,
"step": 1038
},
{
"epoch": 2.657289002557545,
"grad_norm": 0.21983414069144497,
"learning_rate": 1.0651432247993793e-05,
"loss": 1.0585,
"step": 1039
},
{
"epoch": 2.659846547314578,
"grad_norm": 0.20977798376089846,
"learning_rate": 1.0633609048659706e-05,
"loss": 1.0691,
"step": 1040
},
{
"epoch": 2.662404092071611,
"grad_norm": 0.18193153369079076,
"learning_rate": 1.0615783828218546e-05,
"loss": 1.0482,
"step": 1041
},
{
"epoch": 2.6649616368286444,
"grad_norm": 0.2362607838969862,
"learning_rate": 1.0597956643529789e-05,
"loss": 1.0795,
"step": 1042
},
{
"epoch": 2.6675191815856776,
"grad_norm": 0.18789714832551685,
"learning_rate": 1.0580127551459178e-05,
"loss": 1.0123,
"step": 1043
},
{
"epoch": 2.670076726342711,
"grad_norm": 0.19255681241817454,
"learning_rate": 1.0562296608878546e-05,
"loss": 1.0545,
"step": 1044
},
{
"epoch": 2.6726342710997444,
"grad_norm": 0.1914112200112221,
"learning_rate": 1.0544463872665612e-05,
"loss": 1.0412,
"step": 1045
},
{
"epoch": 2.6751918158567776,
"grad_norm": 0.1956849800060106,
"learning_rate": 1.0526629399703834e-05,
"loss": 1.0252,
"step": 1046
},
{
"epoch": 2.6777493606138107,
"grad_norm": 0.2100982102976319,
"learning_rate": 1.0508793246882202e-05,
"loss": 1.0589,
"step": 1047
},
{
"epoch": 2.680306905370844,
"grad_norm": 0.1915658983950445,
"learning_rate": 1.0490955471095062e-05,
"loss": 1.0584,
"step": 1048
},
{
"epoch": 2.682864450127877,
"grad_norm": 0.23563078056985684,
"learning_rate": 1.0473116129241944e-05,
"loss": 1.0329,
"step": 1049
},
{
"epoch": 2.6854219948849103,
"grad_norm": 0.19242917127297468,
"learning_rate": 1.045527527822737e-05,
"loss": 1.06,
"step": 1050
},
{
"epoch": 2.687979539641944,
"grad_norm": 0.22869967853846762,
"learning_rate": 1.0437432974960676e-05,
"loss": 1.0564,
"step": 1051
},
{
"epoch": 2.690537084398977,
"grad_norm": 0.2133654830434205,
"learning_rate": 1.0419589276355826e-05,
"loss": 1.0475,
"step": 1052
},
{
"epoch": 2.6930946291560103,
"grad_norm": 0.2118696215206806,
"learning_rate": 1.0401744239331244e-05,
"loss": 1.0614,
"step": 1053
},
{
"epoch": 2.6956521739130435,
"grad_norm": 0.19733955046640414,
"learning_rate": 1.0383897920809618e-05,
"loss": 1.0241,
"step": 1054
},
{
"epoch": 2.6982097186700766,
"grad_norm": 0.2155680013638521,
"learning_rate": 1.0366050377717723e-05,
"loss": 1.0386,
"step": 1055
},
{
"epoch": 2.70076726342711,
"grad_norm": 0.21857115127975912,
"learning_rate": 1.0348201666986241e-05,
"loss": 1.0587,
"step": 1056
},
{
"epoch": 2.703324808184143,
"grad_norm": 0.21312799905294016,
"learning_rate": 1.0330351845549577e-05,
"loss": 1.0586,
"step": 1057
},
{
"epoch": 2.7058823529411766,
"grad_norm": 0.21137475767635053,
"learning_rate": 1.031250097034569e-05,
"loss": 1.0476,
"step": 1058
},
{
"epoch": 2.70843989769821,
"grad_norm": 0.1778309692168584,
"learning_rate": 1.029464909831588e-05,
"loss": 1.0758,
"step": 1059
},
{
"epoch": 2.710997442455243,
"grad_norm": 0.20578943102646913,
"learning_rate": 1.0276796286404644e-05,
"loss": 1.0346,
"step": 1060
},
{
"epoch": 2.713554987212276,
"grad_norm": 0.20714284355574877,
"learning_rate": 1.0258942591559475e-05,
"loss": 1.0741,
"step": 1061
},
{
"epoch": 2.7161125319693094,
"grad_norm": 0.18109264555313395,
"learning_rate": 1.024108807073067e-05,
"loss": 1.062,
"step": 1062
},
{
"epoch": 2.718670076726343,
"grad_norm": 0.19624851311668945,
"learning_rate": 1.0223232780871173e-05,
"loss": 1.0958,
"step": 1063
},
{
"epoch": 2.7212276214833757,
"grad_norm": 0.19392717064910245,
"learning_rate": 1.020537677893638e-05,
"loss": 1.0572,
"step": 1064
},
{
"epoch": 2.7237851662404093,
"grad_norm": 0.18070548523837038,
"learning_rate": 1.0187520121883952e-05,
"loss": 1.0266,
"step": 1065
},
{
"epoch": 2.7263427109974425,
"grad_norm": 0.1940777698141172,
"learning_rate": 1.0169662866673647e-05,
"loss": 1.0456,
"step": 1066
},
{
"epoch": 2.7289002557544757,
"grad_norm": 0.19806191898621253,
"learning_rate": 1.0151805070267123e-05,
"loss": 1.0525,
"step": 1067
},
{
"epoch": 2.731457800511509,
"grad_norm": 0.19834077877996045,
"learning_rate": 1.0133946789627773e-05,
"loss": 1.0714,
"step": 1068
},
{
"epoch": 2.734015345268542,
"grad_norm": 0.22704784534870529,
"learning_rate": 1.0116088081720528e-05,
"loss": 1.0476,
"step": 1069
},
{
"epoch": 2.7365728900255757,
"grad_norm": 0.1981045516344043,
"learning_rate": 1.0098229003511684e-05,
"loss": 1.0935,
"step": 1070
},
{
"epoch": 2.7391304347826084,
"grad_norm": 0.21563650872651463,
"learning_rate": 1.0080369611968724e-05,
"loss": 1.042,
"step": 1071
},
{
"epoch": 2.741687979539642,
"grad_norm": 0.21593748692546988,
"learning_rate": 1.0062509964060119e-05,
"loss": 1.0744,
"step": 1072
},
{
"epoch": 2.7442455242966752,
"grad_norm": 0.22642223122270672,
"learning_rate": 1.0044650116755166e-05,
"loss": 1.056,
"step": 1073
},
{
"epoch": 2.7468030690537084,
"grad_norm": 0.19475366026833285,
"learning_rate": 1.0026790127023793e-05,
"loss": 1.0406,
"step": 1074
},
{
"epoch": 2.7493606138107416,
"grad_norm": 0.24030640546026497,
"learning_rate": 1.0008930051836389e-05,
"loss": 1.0957,
"step": 1075
},
{
"epoch": 2.7519181585677748,
"grad_norm": 0.22630901508829493,
"learning_rate": 9.991069948163616e-06,
"loss": 1.0509,
"step": 1076
},
{
"epoch": 2.7544757033248084,
"grad_norm": 0.18042335767327197,
"learning_rate": 9.97320987297621e-06,
"loss": 1.0727,
"step": 1077
},
{
"epoch": 2.7570332480818416,
"grad_norm": 0.22313730186227937,
"learning_rate": 9.955349883244837e-06,
"loss": 1.0343,
"step": 1078
},
{
"epoch": 2.7595907928388748,
"grad_norm": 0.1797662118649205,
"learning_rate": 9.937490035939884e-06,
"loss": 1.0119,
"step": 1079
},
{
"epoch": 2.762148337595908,
"grad_norm": 0.19520318025917605,
"learning_rate": 9.919630388031278e-06,
"loss": 1.0598,
"step": 1080
},
{
"epoch": 2.764705882352941,
"grad_norm": 0.18513277316186183,
"learning_rate": 9.901770996488316e-06,
"loss": 1.0224,
"step": 1081
},
{
"epoch": 2.7672634271099743,
"grad_norm": 0.2448129514637694,
"learning_rate": 9.883911918279476e-06,
"loss": 1.0609,
"step": 1082
},
{
"epoch": 2.7698209718670075,
"grad_norm": 0.17314061842855177,
"learning_rate": 9.86605321037223e-06,
"loss": 1.0578,
"step": 1083
},
{
"epoch": 2.772378516624041,
"grad_norm": 0.24279893745727923,
"learning_rate": 9.84819492973288e-06,
"loss": 1.0606,
"step": 1084
},
{
"epoch": 2.7749360613810743,
"grad_norm": 0.20431457711634385,
"learning_rate": 9.830337133326355e-06,
"loss": 1.0351,
"step": 1085
},
{
"epoch": 2.7774936061381075,
"grad_norm": 0.19458070922054774,
"learning_rate": 9.81247987811605e-06,
"loss": 1.0897,
"step": 1086
},
{
"epoch": 2.7800511508951407,
"grad_norm": 0.2100381247728313,
"learning_rate": 9.794623221063625e-06,
"loss": 1.0146,
"step": 1087
},
{
"epoch": 2.782608695652174,
"grad_norm": 0.2143570049157338,
"learning_rate": 9.776767219128829e-06,
"loss": 1.042,
"step": 1088
},
{
"epoch": 2.785166240409207,
"grad_norm": 0.20143887728169868,
"learning_rate": 9.758911929269334e-06,
"loss": 1.0633,
"step": 1089
},
{
"epoch": 2.78772378516624,
"grad_norm": 0.26056402255926914,
"learning_rate": 9.741057408440527e-06,
"loss": 1.0285,
"step": 1090
},
{
"epoch": 2.790281329923274,
"grad_norm": 0.18543103389813437,
"learning_rate": 9.723203713595356e-06,
"loss": 1.004,
"step": 1091
},
{
"epoch": 2.792838874680307,
"grad_norm": 0.2601236122874053,
"learning_rate": 9.70535090168412e-06,
"loss": 1.0651,
"step": 1092
},
{
"epoch": 2.79539641943734,
"grad_norm": 0.19784218292302086,
"learning_rate": 9.687499029654314e-06,
"loss": 1.068,
"step": 1093
},
{
"epoch": 2.7979539641943734,
"grad_norm": 0.23796716838458418,
"learning_rate": 9.669648154450425e-06,
"loss": 1.0499,
"step": 1094
},
{
"epoch": 2.8005115089514065,
"grad_norm": 0.2120185185123368,
"learning_rate": 9.651798333013762e-06,
"loss": 1.0455,
"step": 1095
},
{
"epoch": 2.80306905370844,
"grad_norm": 0.2105859374042988,
"learning_rate": 9.63394962228228e-06,
"loss": 1.0956,
"step": 1096
},
{
"epoch": 2.805626598465473,
"grad_norm": 0.2191672276731036,
"learning_rate": 9.616102079190382e-06,
"loss": 1.062,
"step": 1097
},
{
"epoch": 2.8081841432225065,
"grad_norm": 0.2119528196350952,
"learning_rate": 9.59825576066876e-06,
"loss": 1.0769,
"step": 1098
},
{
"epoch": 2.8107416879795397,
"grad_norm": 0.21455177436347436,
"learning_rate": 9.580410723644177e-06,
"loss": 1.0665,
"step": 1099
},
{
"epoch": 2.813299232736573,
"grad_norm": 0.18662737672691734,
"learning_rate": 9.562567025039326e-06,
"loss": 1.0403,
"step": 1100
},
{
"epoch": 2.815856777493606,
"grad_norm": 0.22100028069203664,
"learning_rate": 9.544724721772632e-06,
"loss": 1.0679,
"step": 1101
},
{
"epoch": 2.8184143222506393,
"grad_norm": 0.1935799574613574,
"learning_rate": 9.526883870758056e-06,
"loss": 1.0499,
"step": 1102
},
{
"epoch": 2.820971867007673,
"grad_norm": 0.19527712864881602,
"learning_rate": 9.50904452890494e-06,
"loss": 1.0652,
"step": 1103
},
{
"epoch": 2.8235294117647056,
"grad_norm": 0.20509388285010824,
"learning_rate": 9.491206753117803e-06,
"loss": 1.0413,
"step": 1104
},
{
"epoch": 2.8260869565217392,
"grad_norm": 0.1992258084768072,
"learning_rate": 9.47337060029617e-06,
"loss": 1.0316,
"step": 1105
},
{
"epoch": 2.8286445012787724,
"grad_norm": 0.22625008837517527,
"learning_rate": 9.45553612733439e-06,
"loss": 1.0618,
"step": 1106
},
{
"epoch": 2.8312020460358056,
"grad_norm": 0.22423324668003744,
"learning_rate": 9.437703391121457e-06,
"loss": 1.0577,
"step": 1107
},
{
"epoch": 2.833759590792839,
"grad_norm": 0.16927725611399697,
"learning_rate": 9.419872448540821e-06,
"loss": 1.069,
"step": 1108
},
{
"epoch": 2.836317135549872,
"grad_norm": 0.20438283854954223,
"learning_rate": 9.402043356470214e-06,
"loss": 1.073,
"step": 1109
},
{
"epoch": 2.8388746803069056,
"grad_norm": 0.18438606363143578,
"learning_rate": 9.384216171781458e-06,
"loss": 1.0535,
"step": 1110
},
{
"epoch": 2.8414322250639388,
"grad_norm": 0.20553714025032518,
"learning_rate": 9.366390951340298e-06,
"loss": 1.053,
"step": 1111
},
{
"epoch": 2.843989769820972,
"grad_norm": 0.214363275474718,
"learning_rate": 9.348567752006208e-06,
"loss": 1.0618,
"step": 1112
},
{
"epoch": 2.846547314578005,
"grad_norm": 0.20301805224099836,
"learning_rate": 9.330746630632224e-06,
"loss": 1.0511,
"step": 1113
},
{
"epoch": 2.8491048593350383,
"grad_norm": 0.2579128437030396,
"learning_rate": 9.312927644064741e-06,
"loss": 1.0518,
"step": 1114
},
{
"epoch": 2.8516624040920715,
"grad_norm": 0.2181960904834944,
"learning_rate": 9.295110849143361e-06,
"loss": 1.0568,
"step": 1115
},
{
"epoch": 2.8542199488491047,
"grad_norm": 0.19693379707125938,
"learning_rate": 9.277296302700675e-06,
"loss": 1.0484,
"step": 1116
},
{
"epoch": 2.8567774936061383,
"grad_norm": 0.2157310477319499,
"learning_rate": 9.259484061562114e-06,
"loss": 1.0334,
"step": 1117
},
{
"epoch": 2.8593350383631715,
"grad_norm": 0.18163692565811201,
"learning_rate": 9.241674182545755e-06,
"loss": 1.0649,
"step": 1118
},
{
"epoch": 2.8618925831202047,
"grad_norm": 0.22334516764144044,
"learning_rate": 9.223866722462134e-06,
"loss": 1.0379,
"step": 1119
},
{
"epoch": 2.864450127877238,
"grad_norm": 0.18179305778409852,
"learning_rate": 9.206061738114087e-06,
"loss": 1.0941,
"step": 1120
},
{
"epoch": 2.867007672634271,
"grad_norm": 0.22000901646758675,
"learning_rate": 9.188259286296527e-06,
"loss": 1.062,
"step": 1121
},
{
"epoch": 2.869565217391304,
"grad_norm": 0.20132285430691718,
"learning_rate": 9.170459423796309e-06,
"loss": 1.0418,
"step": 1122
},
{
"epoch": 2.8721227621483374,
"grad_norm": 0.18151007124149462,
"learning_rate": 9.152662207392025e-06,
"loss": 1.0117,
"step": 1123
},
{
"epoch": 2.874680306905371,
"grad_norm": 0.20958529291718883,
"learning_rate": 9.134867693853818e-06,
"loss": 1.0953,
"step": 1124
},
{
"epoch": 2.877237851662404,
"grad_norm": 0.22158861933579652,
"learning_rate": 9.11707593994322e-06,
"loss": 1.0714,
"step": 1125
},
{
"epoch": 2.8797953964194374,
"grad_norm": 0.18234147869625544,
"learning_rate": 9.099287002412957e-06,
"loss": 1.0621,
"step": 1126
},
{
"epoch": 2.8823529411764706,
"grad_norm": 0.21232832072702237,
"learning_rate": 9.08150093800676e-06,
"loss": 1.0292,
"step": 1127
},
{
"epoch": 2.8849104859335037,
"grad_norm": 0.22176137811022292,
"learning_rate": 9.063717803459215e-06,
"loss": 1.0336,
"step": 1128
},
{
"epoch": 2.887468030690537,
"grad_norm": 0.2318369191230884,
"learning_rate": 9.045937655495544e-06,
"loss": 1.0408,
"step": 1129
},
{
"epoch": 2.89002557544757,
"grad_norm": 0.21500699732164258,
"learning_rate": 9.028160550831458e-06,
"loss": 1.0667,
"step": 1130
},
{
"epoch": 2.8925831202046037,
"grad_norm": 0.2380668338506343,
"learning_rate": 9.01038654617295e-06,
"loss": 1.0792,
"step": 1131
},
{
"epoch": 2.895140664961637,
"grad_norm": 0.19481533312148408,
"learning_rate": 8.992615698216121e-06,
"loss": 1.015,
"step": 1132
},
{
"epoch": 2.89769820971867,
"grad_norm": 0.21841251935433692,
"learning_rate": 8.974848063647017e-06,
"loss": 1.0342,
"step": 1133
},
{
"epoch": 2.9002557544757033,
"grad_norm": 0.21137856495367685,
"learning_rate": 8.95708369914142e-06,
"loss": 1.0361,
"step": 1134
},
{
"epoch": 2.9028132992327365,
"grad_norm": 0.1946101170447674,
"learning_rate": 8.93932266136469e-06,
"loss": 1.0608,
"step": 1135
},
{
"epoch": 2.90537084398977,
"grad_norm": 0.23628212061281142,
"learning_rate": 8.92156500697157e-06,
"loss": 1.0324,
"step": 1136
},
{
"epoch": 2.907928388746803,
"grad_norm": 0.19457336047499793,
"learning_rate": 8.903810792606019e-06,
"loss": 1.0974,
"step": 1137
},
{
"epoch": 2.9104859335038364,
"grad_norm": 0.23806632883818715,
"learning_rate": 8.886060074901006e-06,
"loss": 1.0339,
"step": 1138
},
{
"epoch": 2.9130434782608696,
"grad_norm": 0.20401432332115726,
"learning_rate": 8.868312910478362e-06,
"loss": 1.0478,
"step": 1139
},
{
"epoch": 2.915601023017903,
"grad_norm": 0.20265994858679084,
"learning_rate": 8.850569355948579e-06,
"loss": 1.0411,
"step": 1140
},
{
"epoch": 2.918158567774936,
"grad_norm": 0.20101667064863665,
"learning_rate": 8.832829467910631e-06,
"loss": 1.0576,
"step": 1141
},
{
"epoch": 2.920716112531969,
"grad_norm": 0.20307554858476298,
"learning_rate": 8.815093302951805e-06,
"loss": 1.0676,
"step": 1142
},
{
"epoch": 2.923273657289003,
"grad_norm": 0.18733836795641187,
"learning_rate": 8.797360917647498e-06,
"loss": 1.0635,
"step": 1143
},
{
"epoch": 2.9258312020460355,
"grad_norm": 0.19358622617848392,
"learning_rate": 8.77963236856106e-06,
"loss": 1.0418,
"step": 1144
},
{
"epoch": 2.928388746803069,
"grad_norm": 0.18883350362824358,
"learning_rate": 8.761907712243606e-06,
"loss": 1.0491,
"step": 1145
},
{
"epoch": 2.9309462915601023,
"grad_norm": 0.16898484877424805,
"learning_rate": 8.744187005233826e-06,
"loss": 1.0361,
"step": 1146
},
{
"epoch": 2.9335038363171355,
"grad_norm": 0.16398622387807313,
"learning_rate": 8.726470304057821e-06,
"loss": 1.0541,
"step": 1147
},
{
"epoch": 2.9360613810741687,
"grad_norm": 0.16164350986788764,
"learning_rate": 8.708757665228909e-06,
"loss": 1.0523,
"step": 1148
},
{
"epoch": 2.938618925831202,
"grad_norm": 0.16164661766952496,
"learning_rate": 8.691049145247446e-06,
"loss": 1.0681,
"step": 1149
},
{
"epoch": 2.9411764705882355,
"grad_norm": 0.15749749181969402,
"learning_rate": 8.673344800600657e-06,
"loss": 1.0573,
"step": 1150
},
{
"epoch": 2.9437340153452687,
"grad_norm": 0.15525122241929215,
"learning_rate": 8.655644687762443e-06,
"loss": 1.0722,
"step": 1151
},
{
"epoch": 2.946291560102302,
"grad_norm": 0.15709889969206967,
"learning_rate": 8.637948863193215e-06,
"loss": 1.0431,
"step": 1152
},
{
"epoch": 2.948849104859335,
"grad_norm": 0.16989598488301447,
"learning_rate": 8.620257383339694e-06,
"loss": 1.0658,
"step": 1153
},
{
"epoch": 2.9514066496163682,
"grad_norm": 0.1595964424160409,
"learning_rate": 8.602570304634745e-06,
"loss": 1.0701,
"step": 1154
},
{
"epoch": 2.9539641943734014,
"grad_norm": 0.16986735433032052,
"learning_rate": 8.5848876834972e-06,
"loss": 1.086,
"step": 1155
},
{
"epoch": 2.9565217391304346,
"grad_norm": 0.19325690151423974,
"learning_rate": 8.567209576331662e-06,
"loss": 1.059,
"step": 1156
},
{
"epoch": 2.959079283887468,
"grad_norm": 0.16112687651565402,
"learning_rate": 8.549536039528351e-06,
"loss": 1.0505,
"step": 1157
},
{
"epoch": 2.9616368286445014,
"grad_norm": 0.18938106017855888,
"learning_rate": 8.53186712946289e-06,
"loss": 1.0448,
"step": 1158
},
{
"epoch": 2.9641943734015346,
"grad_norm": 0.17573092327281262,
"learning_rate": 8.514202902496157e-06,
"loss": 1.045,
"step": 1159
},
{
"epoch": 2.9667519181585678,
"grad_norm": 0.16472675003522239,
"learning_rate": 8.496543414974084e-06,
"loss": 1.0672,
"step": 1160
},
{
"epoch": 2.969309462915601,
"grad_norm": 0.1748756285533725,
"learning_rate": 8.478888723227486e-06,
"loss": 1.0364,
"step": 1161
},
{
"epoch": 2.971867007672634,
"grad_norm": 0.1767205601325944,
"learning_rate": 8.461238883571885e-06,
"loss": 1.0413,
"step": 1162
},
{
"epoch": 2.9744245524296673,
"grad_norm": 0.15740765778773358,
"learning_rate": 8.443593952307319e-06,
"loss": 1.0833,
"step": 1163
},
{
"epoch": 2.976982097186701,
"grad_norm": 0.1896056695064984,
"learning_rate": 8.425953985718182e-06,
"loss": 1.036,
"step": 1164
},
{
"epoch": 2.979539641943734,
"grad_norm": 0.17711517435630209,
"learning_rate": 8.408319040073011e-06,
"loss": 1.0447,
"step": 1165
},
{
"epoch": 2.9820971867007673,
"grad_norm": 0.16635113314658131,
"learning_rate": 8.390689171624341e-06,
"loss": 1.0771,
"step": 1166
},
{
"epoch": 2.9846547314578005,
"grad_norm": 0.17437808910596117,
"learning_rate": 8.373064436608512e-06,
"loss": 1.053,
"step": 1167
},
{
"epoch": 2.9872122762148337,
"grad_norm": 0.17619213607284423,
"learning_rate": 8.355444891245482e-06,
"loss": 1.0684,
"step": 1168
},
{
"epoch": 2.9897698209718673,
"grad_norm": 0.18483592261300663,
"learning_rate": 8.337830591738664e-06,
"loss": 1.0437,
"step": 1169
},
{
"epoch": 2.9923273657289,
"grad_norm": 0.18442193916145447,
"learning_rate": 8.32022159427473e-06,
"loss": 1.0422,
"step": 1170
},
{
"epoch": 2.9948849104859336,
"grad_norm": 0.2119894606858352,
"learning_rate": 8.302617955023438e-06,
"loss": 1.0383,
"step": 1171
},
{
"epoch": 2.997442455242967,
"grad_norm": 0.2113360486461104,
"learning_rate": 8.285019730137462e-06,
"loss": 1.0814,
"step": 1172
},
{
"epoch": 3.0,
"grad_norm": 0.2111827709122195,
"learning_rate": 8.2674269757522e-06,
"loss": 1.0749,
"step": 1173
},
{
"epoch": 3.002557544757033,
"grad_norm": 0.17743968023223414,
"learning_rate": 8.2498397479856e-06,
"loss": 1.0689,
"step": 1174
},
{
"epoch": 3.0051150895140664,
"grad_norm": 0.21230668911328027,
"learning_rate": 8.232258102937987e-06,
"loss": 1.0685,
"step": 1175
},
{
"epoch": 3.0076726342710995,
"grad_norm": 0.18796325619774717,
"learning_rate": 8.214682096691866e-06,
"loss": 1.0474,
"step": 1176
},
{
"epoch": 3.010230179028133,
"grad_norm": 0.1863635190742179,
"learning_rate": 8.197111785311767e-06,
"loss": 1.0858,
"step": 1177
},
{
"epoch": 3.0127877237851663,
"grad_norm": 0.1838798652920452,
"learning_rate": 8.179547224844046e-06,
"loss": 1.0743,
"step": 1178
},
{
"epoch": 3.0153452685421995,
"grad_norm": 0.17485799326659002,
"learning_rate": 8.161988471316723e-06,
"loss": 1.0228,
"step": 1179
},
{
"epoch": 3.0179028132992327,
"grad_norm": 0.21207868945480415,
"learning_rate": 8.144435580739285e-06,
"loss": 1.0336,
"step": 1180
},
{
"epoch": 3.020460358056266,
"grad_norm": 0.16449752076147575,
"learning_rate": 8.12688860910253e-06,
"loss": 1.0455,
"step": 1181
},
{
"epoch": 3.023017902813299,
"grad_norm": 0.19947300226681555,
"learning_rate": 8.109347612378357e-06,
"loss": 1.0395,
"step": 1182
},
{
"epoch": 3.0255754475703327,
"grad_norm": 0.18190648941101212,
"learning_rate": 8.091812646519624e-06,
"loss": 1.0623,
"step": 1183
},
{
"epoch": 3.028132992327366,
"grad_norm": 0.1646190514225652,
"learning_rate": 8.074283767459941e-06,
"loss": 1.0264,
"step": 1184
},
{
"epoch": 3.030690537084399,
"grad_norm": 0.19900332810490962,
"learning_rate": 8.056761031113506e-06,
"loss": 1.0419,
"step": 1185
},
{
"epoch": 3.0332480818414322,
"grad_norm": 0.19790261143418011,
"learning_rate": 8.03924449337493e-06,
"loss": 1.0239,
"step": 1186
},
{
"epoch": 3.0358056265984654,
"grad_norm": 0.1735899464590682,
"learning_rate": 8.021734210119031e-06,
"loss": 1.0482,
"step": 1187
},
{
"epoch": 3.0383631713554986,
"grad_norm": 0.24811292812795957,
"learning_rate": 8.004230237200695e-06,
"loss": 1.0117,
"step": 1188
},
{
"epoch": 3.040920716112532,
"grad_norm": 0.17073008104062196,
"learning_rate": 7.986732630454673e-06,
"loss": 1.0469,
"step": 1189
},
{
"epoch": 3.0434782608695654,
"grad_norm": 0.2528836646880793,
"learning_rate": 7.969241445695407e-06,
"loss": 1.0341,
"step": 1190
},
{
"epoch": 3.0460358056265986,
"grad_norm": 0.19007874013606105,
"learning_rate": 7.951756738716861e-06,
"loss": 1.0147,
"step": 1191
},
{
"epoch": 3.0485933503836318,
"grad_norm": 0.20187206991127415,
"learning_rate": 7.934278565292328e-06,
"loss": 1.0535,
"step": 1192
},
{
"epoch": 3.051150895140665,
"grad_norm": 0.20526762415260827,
"learning_rate": 7.916806981174258e-06,
"loss": 1.0605,
"step": 1193
},
{
"epoch": 3.053708439897698,
"grad_norm": 0.20055119376497793,
"learning_rate": 7.899342042094094e-06,
"loss": 1.0316,
"step": 1194
},
{
"epoch": 3.0562659846547313,
"grad_norm": 0.1968308279791684,
"learning_rate": 7.881883803762071e-06,
"loss": 1.0367,
"step": 1195
},
{
"epoch": 3.0588235294117645,
"grad_norm": 0.18030703210119325,
"learning_rate": 7.864432321867056e-06,
"loss": 1.0504,
"step": 1196
},
{
"epoch": 3.061381074168798,
"grad_norm": 0.18935954626691623,
"learning_rate": 7.846987652076372e-06,
"loss": 1.0511,
"step": 1197
},
{
"epoch": 3.0639386189258313,
"grad_norm": 0.17290346534417522,
"learning_rate": 7.829549850035585e-06,
"loss": 1.0484,
"step": 1198
},
{
"epoch": 3.0664961636828645,
"grad_norm": 0.18722490812221246,
"learning_rate": 7.812118971368384e-06,
"loss": 1.0661,
"step": 1199
},
{
"epoch": 3.0690537084398977,
"grad_norm": 0.20012871337269098,
"learning_rate": 7.794695071676355e-06,
"loss": 1.0245,
"step": 1200
},
{
"epoch": 3.071611253196931,
"grad_norm": 0.21712726425678322,
"learning_rate": 7.777278206538832e-06,
"loss": 1.0368,
"step": 1201
},
{
"epoch": 3.074168797953964,
"grad_norm": 0.18764265039969955,
"learning_rate": 7.75986843151271e-06,
"loss": 1.0603,
"step": 1202
},
{
"epoch": 3.0767263427109977,
"grad_norm": 0.2284378574380906,
"learning_rate": 7.742465802132261e-06,
"loss": 1.0666,
"step": 1203
},
{
"epoch": 3.079283887468031,
"grad_norm": 0.18138326397527504,
"learning_rate": 7.725070373908967e-06,
"loss": 1.0653,
"step": 1204
},
{
"epoch": 3.081841432225064,
"grad_norm": 0.20238266442132807,
"learning_rate": 7.707682202331338e-06,
"loss": 1.0659,
"step": 1205
},
{
"epoch": 3.084398976982097,
"grad_norm": 0.16899939143822162,
"learning_rate": 7.690301342864738e-06,
"loss": 1.0361,
"step": 1206
},
{
"epoch": 3.0869565217391304,
"grad_norm": 0.21399879876961514,
"learning_rate": 7.672927850951213e-06,
"loss": 1.0579,
"step": 1207
},
{
"epoch": 3.0895140664961636,
"grad_norm": 0.16140650557730965,
"learning_rate": 7.6555617820093e-06,
"loss": 1.0867,
"step": 1208
},
{
"epoch": 3.0920716112531967,
"grad_norm": 0.2030576541987284,
"learning_rate": 7.638203191433848e-06,
"loss": 1.0312,
"step": 1209
},
{
"epoch": 3.0946291560102304,
"grad_norm": 0.1653674904692065,
"learning_rate": 7.620852134595875e-06,
"loss": 1.0553,
"step": 1210
},
{
"epoch": 3.0971867007672635,
"grad_norm": 0.21004837372358645,
"learning_rate": 7.60350866684235e-06,
"loss": 1.0566,
"step": 1211
},
{
"epoch": 3.0997442455242967,
"grad_norm": 0.18582555924313174,
"learning_rate": 7.586172843496042e-06,
"loss": 1.0194,
"step": 1212
},
{
"epoch": 3.10230179028133,
"grad_norm": 0.2350752210692893,
"learning_rate": 7.568844719855328e-06,
"loss": 1.0887,
"step": 1213
},
{
"epoch": 3.104859335038363,
"grad_norm": 0.1752787960126917,
"learning_rate": 7.5515243511940395e-06,
"loss": 1.0367,
"step": 1214
},
{
"epoch": 3.1074168797953963,
"grad_norm": 0.20184036652559692,
"learning_rate": 7.534211792761249e-06,
"loss": 1.0784,
"step": 1215
},
{
"epoch": 3.10997442455243,
"grad_norm": 0.19595647838718663,
"learning_rate": 7.516907099781131e-06,
"loss": 1.0298,
"step": 1216
},
{
"epoch": 3.112531969309463,
"grad_norm": 0.20222428308830126,
"learning_rate": 7.49961032745277e-06,
"loss": 1.0678,
"step": 1217
},
{
"epoch": 3.1150895140664963,
"grad_norm": 0.19294563663829822,
"learning_rate": 7.4823215309499766e-06,
"loss": 1.0397,
"step": 1218
},
{
"epoch": 3.1176470588235294,
"grad_norm": 0.19397261170806676,
"learning_rate": 7.465040765421132e-06,
"loss": 1.058,
"step": 1219
},
{
"epoch": 3.1202046035805626,
"grad_norm": 0.22587828052192943,
"learning_rate": 7.447768085988987e-06,
"loss": 1.0461,
"step": 1220
},
{
"epoch": 3.122762148337596,
"grad_norm": 0.2140035097820999,
"learning_rate": 7.430503547750505e-06,
"loss": 1.0425,
"step": 1221
},
{
"epoch": 3.125319693094629,
"grad_norm": 0.20328335993216895,
"learning_rate": 7.413247205776684e-06,
"loss": 0.9899,
"step": 1222
},
{
"epoch": 3.1278772378516626,
"grad_norm": 0.17357867143063074,
"learning_rate": 7.3959991151123685e-06,
"loss": 1.0532,
"step": 1223
},
{
"epoch": 3.130434782608696,
"grad_norm": 0.22322271848597508,
"learning_rate": 7.378759330776093e-06,
"loss": 1.0212,
"step": 1224
},
{
"epoch": 3.132992327365729,
"grad_norm": 0.16810780127137187,
"learning_rate": 7.361527907759893e-06,
"loss": 1.0279,
"step": 1225
},
{
"epoch": 3.135549872122762,
"grad_norm": 0.23876493089254128,
"learning_rate": 7.344304901029121e-06,
"loss": 1.0474,
"step": 1226
},
{
"epoch": 3.1381074168797953,
"grad_norm": 0.1666563839380977,
"learning_rate": 7.327090365522303e-06,
"loss": 1.0457,
"step": 1227
},
{
"epoch": 3.1406649616368285,
"grad_norm": 0.233785304749979,
"learning_rate": 7.309884356150925e-06,
"loss": 1.0644,
"step": 1228
},
{
"epoch": 3.1432225063938617,
"grad_norm": 0.16224260381430458,
"learning_rate": 7.2926869277992884e-06,
"loss": 1.0704,
"step": 1229
},
{
"epoch": 3.1457800511508953,
"grad_norm": 0.213314385450332,
"learning_rate": 7.275498135324322e-06,
"loss": 1.0518,
"step": 1230
},
{
"epoch": 3.1483375959079285,
"grad_norm": 0.1676105524904316,
"learning_rate": 7.258318033555394e-06,
"loss": 1.0622,
"step": 1231
},
{
"epoch": 3.1508951406649617,
"grad_norm": 0.20581044358420533,
"learning_rate": 7.2411466772941684e-06,
"loss": 1.0389,
"step": 1232
},
{
"epoch": 3.153452685421995,
"grad_norm": 0.15515519926002075,
"learning_rate": 7.2239841213144e-06,
"loss": 1.0802,
"step": 1233
},
{
"epoch": 3.156010230179028,
"grad_norm": 0.1937872427855819,
"learning_rate": 7.20683042036178e-06,
"loss": 1.0616,
"step": 1234
},
{
"epoch": 3.1585677749360612,
"grad_norm": 0.16287563642941633,
"learning_rate": 7.189685629153749e-06,
"loss": 1.0518,
"step": 1235
},
{
"epoch": 3.1611253196930944,
"grad_norm": 0.16444450384166215,
"learning_rate": 7.1725498023793305e-06,
"loss": 1.055,
"step": 1236
},
{
"epoch": 3.163682864450128,
"grad_norm": 0.15483746878996799,
"learning_rate": 7.155422994698948e-06,
"loss": 1.044,
"step": 1237
},
{
"epoch": 3.166240409207161,
"grad_norm": 0.16555800371038418,
"learning_rate": 7.138305260744256e-06,
"loss": 1.0489,
"step": 1238
},
{
"epoch": 3.1687979539641944,
"grad_norm": 0.16421185384625095,
"learning_rate": 7.121196655117975e-06,
"loss": 1.0133,
"step": 1239
},
{
"epoch": 3.1713554987212276,
"grad_norm": 0.15905768015523744,
"learning_rate": 7.104097232393692e-06,
"loss": 1.039,
"step": 1240
},
{
"epoch": 3.1739130434782608,
"grad_norm": 0.15268576953010804,
"learning_rate": 7.087007047115719e-06,
"loss": 1.0275,
"step": 1241
},
{
"epoch": 3.176470588235294,
"grad_norm": 0.1710081046719881,
"learning_rate": 7.069926153798889e-06,
"loss": 1.0343,
"step": 1242
},
{
"epoch": 3.1790281329923276,
"grad_norm": 0.16935470183977597,
"learning_rate": 7.052854606928396e-06,
"loss": 1.0442,
"step": 1243
},
{
"epoch": 3.1815856777493607,
"grad_norm": 0.17381989218653407,
"learning_rate": 7.0357924609596305e-06,
"loss": 1.0272,
"step": 1244
},
{
"epoch": 3.184143222506394,
"grad_norm": 0.1809090074415964,
"learning_rate": 7.018739770317985e-06,
"loss": 1.0039,
"step": 1245
},
{
"epoch": 3.186700767263427,
"grad_norm": 0.16405848889955926,
"learning_rate": 7.001696589398699e-06,
"loss": 1.0569,
"step": 1246
},
{
"epoch": 3.1892583120204603,
"grad_norm": 0.19485294563253486,
"learning_rate": 6.984662972566674e-06,
"loss": 1.0636,
"step": 1247
},
{
"epoch": 3.1918158567774935,
"grad_norm": 0.1603872937860603,
"learning_rate": 6.967638974156299e-06,
"loss": 1.0439,
"step": 1248
},
{
"epoch": 3.1943734015345266,
"grad_norm": 0.19115402938555065,
"learning_rate": 6.950624648471289e-06,
"loss": 1.033,
"step": 1249
},
{
"epoch": 3.1969309462915603,
"grad_norm": 0.15897058089861524,
"learning_rate": 6.933620049784502e-06,
"loss": 1.0437,
"step": 1250
},
{
"epoch": 3.1994884910485935,
"grad_norm": 0.1865666397196807,
"learning_rate": 6.9166252323377705e-06,
"loss": 1.0201,
"step": 1251
},
{
"epoch": 3.2020460358056266,
"grad_norm": 0.18005383040199222,
"learning_rate": 6.899640250341726e-06,
"loss": 1.0607,
"step": 1252
},
{
"epoch": 3.20460358056266,
"grad_norm": 0.18667666493469226,
"learning_rate": 6.882665157975617e-06,
"loss": 1.0151,
"step": 1253
},
{
"epoch": 3.207161125319693,
"grad_norm": 0.16755268817909583,
"learning_rate": 6.865700009387161e-06,
"loss": 1.0398,
"step": 1254
},
{
"epoch": 3.209718670076726,
"grad_norm": 0.17489599503934009,
"learning_rate": 6.8487448586923445e-06,
"loss": 1.0411,
"step": 1255
},
{
"epoch": 3.21227621483376,
"grad_norm": 0.19955868168103402,
"learning_rate": 6.831799759975273e-06,
"loss": 1.0312,
"step": 1256
},
{
"epoch": 3.214833759590793,
"grad_norm": 0.17120578080679916,
"learning_rate": 6.814864767287977e-06,
"loss": 1.0364,
"step": 1257
},
{
"epoch": 3.217391304347826,
"grad_norm": 0.20773510702967912,
"learning_rate": 6.797939934650263e-06,
"loss": 1.0324,
"step": 1258
},
{
"epoch": 3.2199488491048593,
"grad_norm": 0.1586496816689849,
"learning_rate": 6.781025316049512e-06,
"loss": 1.0794,
"step": 1259
},
{
"epoch": 3.2225063938618925,
"grad_norm": 0.20969996522100806,
"learning_rate": 6.7641209654405375e-06,
"loss": 1.0463,
"step": 1260
},
{
"epoch": 3.2250639386189257,
"grad_norm": 0.16911339560919933,
"learning_rate": 6.747226936745395e-06,
"loss": 1.0292,
"step": 1261
},
{
"epoch": 3.227621483375959,
"grad_norm": 0.17406389220265206,
"learning_rate": 6.730343283853213e-06,
"loss": 1.0104,
"step": 1262
},
{
"epoch": 3.2301790281329925,
"grad_norm": 0.19086270430612148,
"learning_rate": 6.713470060620033e-06,
"loss": 1.0333,
"step": 1263
},
{
"epoch": 3.2327365728900257,
"grad_norm": 0.15722213977712743,
"learning_rate": 6.6966073208686135e-06,
"loss": 1.0392,
"step": 1264
},
{
"epoch": 3.235294117647059,
"grad_norm": 0.18709369627876488,
"learning_rate": 6.679755118388275e-06,
"loss": 1.0333,
"step": 1265
},
{
"epoch": 3.237851662404092,
"grad_norm": 0.1699678534444773,
"learning_rate": 6.662913506934737e-06,
"loss": 1.0404,
"step": 1266
},
{
"epoch": 3.2404092071611252,
"grad_norm": 0.18697964330748695,
"learning_rate": 6.646082540229923e-06,
"loss": 1.0341,
"step": 1267
},
{
"epoch": 3.2429667519181584,
"grad_norm": 0.16867872295801503,
"learning_rate": 6.629262271961811e-06,
"loss": 0.9955,
"step": 1268
},
{
"epoch": 3.2455242966751916,
"grad_norm": 0.1757388936159618,
"learning_rate": 6.61245275578425e-06,
"loss": 1.0588,
"step": 1269
},
{
"epoch": 3.2480818414322252,
"grad_norm": 0.179354789438552,
"learning_rate": 6.595654045316781e-06,
"loss": 1.0342,
"step": 1270
},
{
"epoch": 3.2506393861892584,
"grad_norm": 0.16261099723737935,
"learning_rate": 6.5788661941444934e-06,
"loss": 1.0512,
"step": 1271
},
{
"epoch": 3.2531969309462916,
"grad_norm": 0.17256463607415848,
"learning_rate": 6.562089255817823e-06,
"loss": 1.0344,
"step": 1272
},
{
"epoch": 3.2557544757033248,
"grad_norm": 0.17074946791571327,
"learning_rate": 6.545323283852407e-06,
"loss": 1.0343,
"step": 1273
},
{
"epoch": 3.258312020460358,
"grad_norm": 0.16871272465633477,
"learning_rate": 6.528568331728895e-06,
"loss": 1.0476,
"step": 1274
},
{
"epoch": 3.260869565217391,
"grad_norm": 0.1578043264468705,
"learning_rate": 6.511824452892791e-06,
"loss": 1.0539,
"step": 1275
},
{
"epoch": 3.2634271099744243,
"grad_norm": 0.16975041042828792,
"learning_rate": 6.495091700754266e-06,
"loss": 1.009,
"step": 1276
},
{
"epoch": 3.265984654731458,
"grad_norm": 0.16784506398603977,
"learning_rate": 6.478370128688005e-06,
"loss": 1.0654,
"step": 1277
},
{
"epoch": 3.268542199488491,
"grad_norm": 0.1573687001595116,
"learning_rate": 6.461659790033038e-06,
"loss": 1.0333,
"step": 1278
},
{
"epoch": 3.2710997442455243,
"grad_norm": 0.15498306536956233,
"learning_rate": 6.444960738092548e-06,
"loss": 1.0848,
"step": 1279
},
{
"epoch": 3.2736572890025575,
"grad_norm": 0.1895685081315579,
"learning_rate": 6.428273026133731e-06,
"loss": 1.0533,
"step": 1280
},
{
"epoch": 3.2762148337595907,
"grad_norm": 0.19242571512113535,
"learning_rate": 6.411596707387594e-06,
"loss": 1.0621,
"step": 1281
},
{
"epoch": 3.2787723785166243,
"grad_norm": 0.15700921828708964,
"learning_rate": 6.39493183504881e-06,
"loss": 1.0477,
"step": 1282
},
{
"epoch": 3.2813299232736575,
"grad_norm": 0.21159038732742347,
"learning_rate": 6.378278462275542e-06,
"loss": 1.0468,
"step": 1283
},
{
"epoch": 3.2838874680306906,
"grad_norm": 0.19962601553872036,
"learning_rate": 6.361636642189269e-06,
"loss": 1.0426,
"step": 1284
},
{
"epoch": 3.286445012787724,
"grad_norm": 0.1763686863110666,
"learning_rate": 6.345006427874616e-06,
"loss": 1.0453,
"step": 1285
},
{
"epoch": 3.289002557544757,
"grad_norm": 0.1776125396661667,
"learning_rate": 6.328387872379193e-06,
"loss": 1.0424,
"step": 1286
},
{
"epoch": 3.29156010230179,
"grad_norm": 0.18658506842064834,
"learning_rate": 6.311781028713414e-06,
"loss": 1.0337,
"step": 1287
},
{
"epoch": 3.2941176470588234,
"grad_norm": 0.15532653749572625,
"learning_rate": 6.29518594985034e-06,
"loss": 1.0185,
"step": 1288
},
{
"epoch": 3.296675191815857,
"grad_norm": 0.20040506008569664,
"learning_rate": 6.278602688725498e-06,
"loss": 1.019,
"step": 1289
},
{
"epoch": 3.29923273657289,
"grad_norm": 0.15024078882430822,
"learning_rate": 6.262031298236728e-06,
"loss": 1.0163,
"step": 1290
},
{
"epoch": 3.3017902813299234,
"grad_norm": 0.187370700502857,
"learning_rate": 6.245471831243997e-06,
"loss": 1.0294,
"step": 1291
},
{
"epoch": 3.3043478260869565,
"grad_norm": 0.1836564928922123,
"learning_rate": 6.228924340569234e-06,
"loss": 1.0576,
"step": 1292
},
{
"epoch": 3.3069053708439897,
"grad_norm": 0.1680090110613116,
"learning_rate": 6.212388878996177e-06,
"loss": 0.9984,
"step": 1293
},
{
"epoch": 3.309462915601023,
"grad_norm": 0.18336870531248498,
"learning_rate": 6.195865499270186e-06,
"loss": 1.0298,
"step": 1294
},
{
"epoch": 3.312020460358056,
"grad_norm": 0.15787805699206167,
"learning_rate": 6.179354254098085e-06,
"loss": 1.0431,
"step": 1295
},
{
"epoch": 3.3145780051150897,
"grad_norm": 0.16543341313363566,
"learning_rate": 6.1628551961479856e-06,
"loss": 1.0544,
"step": 1296
},
{
"epoch": 3.317135549872123,
"grad_norm": 0.17482194497586678,
"learning_rate": 6.146368378049134e-06,
"loss": 1.0098,
"step": 1297
},
{
"epoch": 3.319693094629156,
"grad_norm": 0.15937828046028765,
"learning_rate": 6.129893852391722e-06,
"loss": 1.0294,
"step": 1298
},
{
"epoch": 3.3222506393861893,
"grad_norm": 0.19027583920574043,
"learning_rate": 6.113431671726735e-06,
"loss": 1.0549,
"step": 1299
},
{
"epoch": 3.3248081841432224,
"grad_norm": 0.16857302745550032,
"learning_rate": 6.096981888565784e-06,
"loss": 1.0772,
"step": 1300
},
{
"epoch": 3.3273657289002556,
"grad_norm": 0.16700609829050267,
"learning_rate": 6.080544555380927e-06,
"loss": 1.0184,
"step": 1301
},
{
"epoch": 3.329923273657289,
"grad_norm": 0.1829806527515392,
"learning_rate": 6.06411972460452e-06,
"loss": 1.0503,
"step": 1302
},
{
"epoch": 3.3324808184143224,
"grad_norm": 0.16756778358359,
"learning_rate": 6.047707448629023e-06,
"loss": 1.0294,
"step": 1303
},
{
"epoch": 3.3350383631713556,
"grad_norm": 0.17523646623624167,
"learning_rate": 6.031307779806858e-06,
"loss": 1.045,
"step": 1304
},
{
"epoch": 3.337595907928389,
"grad_norm": 0.16450304941716934,
"learning_rate": 6.014920770450232e-06,
"loss": 1.0194,
"step": 1305
},
{
"epoch": 3.340153452685422,
"grad_norm": 0.1805469762569222,
"learning_rate": 5.998546472830965e-06,
"loss": 1.0541,
"step": 1306
},
{
"epoch": 3.342710997442455,
"grad_norm": 0.1419264397187406,
"learning_rate": 5.982184939180337e-06,
"loss": 1.007,
"step": 1307
},
{
"epoch": 3.3452685421994883,
"grad_norm": 0.1604620222757409,
"learning_rate": 5.96583622168891e-06,
"loss": 1.0498,
"step": 1308
},
{
"epoch": 3.3478260869565215,
"grad_norm": 0.15382052852134748,
"learning_rate": 5.949500372506354e-06,
"loss": 1.0339,
"step": 1309
},
{
"epoch": 3.350383631713555,
"grad_norm": 0.1492360356034545,
"learning_rate": 5.9331774437413095e-06,
"loss": 1.0739,
"step": 1310
},
{
"epoch": 3.3529411764705883,
"grad_norm": 0.16403001997456812,
"learning_rate": 5.916867487461186e-06,
"loss": 1.0416,
"step": 1311
},
{
"epoch": 3.3554987212276215,
"grad_norm": 0.1614357839239018,
"learning_rate": 5.900570555692029e-06,
"loss": 1.0338,
"step": 1312
},
{
"epoch": 3.3580562659846547,
"grad_norm": 0.16872463368760673,
"learning_rate": 5.884286700418328e-06,
"loss": 1.0369,
"step": 1313
},
{
"epoch": 3.360613810741688,
"grad_norm": 0.18005310056772503,
"learning_rate": 5.868015973582856e-06,
"loss": 1.0474,
"step": 1314
},
{
"epoch": 3.363171355498721,
"grad_norm": 0.18096998826427219,
"learning_rate": 5.85175842708652e-06,
"loss": 1.0168,
"step": 1315
},
{
"epoch": 3.3657289002557547,
"grad_norm": 0.15348669875527965,
"learning_rate": 5.835514112788178e-06,
"loss": 1.0404,
"step": 1316
},
{
"epoch": 3.368286445012788,
"grad_norm": 0.18543116172669075,
"learning_rate": 5.819283082504482e-06,
"loss": 1.0501,
"step": 1317
},
{
"epoch": 3.370843989769821,
"grad_norm": 0.19694837114442768,
"learning_rate": 5.803065388009707e-06,
"loss": 1.047,
"step": 1318
},
{
"epoch": 3.373401534526854,
"grad_norm": 0.1550062877849358,
"learning_rate": 5.78686108103559e-06,
"loss": 1.0459,
"step": 1319
},
{
"epoch": 3.3759590792838874,
"grad_norm": 0.18130690935498406,
"learning_rate": 5.770670213271166e-06,
"loss": 1.0203,
"step": 1320
},
{
"epoch": 3.3785166240409206,
"grad_norm": 0.1791636691198155,
"learning_rate": 5.754492836362597e-06,
"loss": 1.0211,
"step": 1321
},
{
"epoch": 3.381074168797954,
"grad_norm": 0.1648503792031205,
"learning_rate": 5.7383290019130145e-06,
"loss": 1.0312,
"step": 1322
},
{
"epoch": 3.3836317135549874,
"grad_norm": 0.1796907978935755,
"learning_rate": 5.722178761482357e-06,
"loss": 1.0233,
"step": 1323
},
{
"epoch": 3.3861892583120206,
"grad_norm": 0.18399008293027794,
"learning_rate": 5.706042166587194e-06,
"loss": 1.038,
"step": 1324
},
{
"epoch": 3.3887468030690537,
"grad_norm": 0.14911113859818034,
"learning_rate": 5.689919268700559e-06,
"loss": 1.0401,
"step": 1325
},
{
"epoch": 3.391304347826087,
"grad_norm": 0.1721196020218365,
"learning_rate": 5.673810119251815e-06,
"loss": 1.042,
"step": 1326
},
{
"epoch": 3.39386189258312,
"grad_norm": 0.16271756082297875,
"learning_rate": 5.657714769626456e-06,
"loss": 1.028,
"step": 1327
},
{
"epoch": 3.3964194373401533,
"grad_norm": 0.16838385908481096,
"learning_rate": 5.641633271165955e-06,
"loss": 1.0164,
"step": 1328
},
{
"epoch": 3.398976982097187,
"grad_norm": 0.16460071206345933,
"learning_rate": 5.625565675167614e-06,
"loss": 1.0785,
"step": 1329
},
{
"epoch": 3.40153452685422,
"grad_norm": 0.15708748073278123,
"learning_rate": 5.609512032884385e-06,
"loss": 1.0622,
"step": 1330
},
{
"epoch": 3.4040920716112533,
"grad_norm": 0.16538861056024953,
"learning_rate": 5.593472395524692e-06,
"loss": 1.0335,
"step": 1331
},
{
"epoch": 3.4066496163682864,
"grad_norm": 0.17518337046372068,
"learning_rate": 5.577446814252311e-06,
"loss": 1.0527,
"step": 1332
},
{
"epoch": 3.4092071611253196,
"grad_norm": 0.15882089668156443,
"learning_rate": 5.561435340186167e-06,
"loss": 1.0281,
"step": 1333
},
{
"epoch": 3.411764705882353,
"grad_norm": 0.15563095727972648,
"learning_rate": 5.545438024400193e-06,
"loss": 1.0581,
"step": 1334
},
{
"epoch": 3.414322250639386,
"grad_norm": 0.17128623415715957,
"learning_rate": 5.529454917923149e-06,
"loss": 1.0419,
"step": 1335
},
{
"epoch": 3.4168797953964196,
"grad_norm": 0.15167801306485404,
"learning_rate": 5.513486071738481e-06,
"loss": 1.0404,
"step": 1336
},
{
"epoch": 3.419437340153453,
"grad_norm": 0.16952883948633865,
"learning_rate": 5.497531536784138e-06,
"loss": 1.0375,
"step": 1337
},
{
"epoch": 3.421994884910486,
"grad_norm": 0.1630572687589045,
"learning_rate": 5.481591363952421e-06,
"loss": 1.0262,
"step": 1338
},
{
"epoch": 3.424552429667519,
"grad_norm": 0.16085228272090568,
"learning_rate": 5.465665604089829e-06,
"loss": 1.0317,
"step": 1339
},
{
"epoch": 3.4271099744245523,
"grad_norm": 0.19118486517294114,
"learning_rate": 5.449754307996871e-06,
"loss": 1.0867,
"step": 1340
},
{
"epoch": 3.4296675191815855,
"grad_norm": 0.1691680997069369,
"learning_rate": 5.433857526427924e-06,
"loss": 1.0755,
"step": 1341
},
{
"epoch": 3.4322250639386187,
"grad_norm": 0.17086025750717415,
"learning_rate": 5.417975310091068e-06,
"loss": 1.038,
"step": 1342
},
{
"epoch": 3.4347826086956523,
"grad_norm": 0.1547439630691515,
"learning_rate": 5.402107709647921e-06,
"loss": 1.0512,
"step": 1343
},
{
"epoch": 3.4373401534526855,
"grad_norm": 0.18002318829806357,
"learning_rate": 5.386254775713482e-06,
"loss": 1.0333,
"step": 1344
},
{
"epoch": 3.4398976982097187,
"grad_norm": 0.15474642805276234,
"learning_rate": 5.370416558855955e-06,
"loss": 1.0215,
"step": 1345
},
{
"epoch": 3.442455242966752,
"grad_norm": 0.16033707255186253,
"learning_rate": 5.354593109596621e-06,
"loss": 1.0628,
"step": 1346
},
{
"epoch": 3.445012787723785,
"grad_norm": 0.17670977631385593,
"learning_rate": 5.338784478409629e-06,
"loss": 1.0398,
"step": 1347
},
{
"epoch": 3.4475703324808182,
"grad_norm": 0.1659664475684347,
"learning_rate": 5.3229907157218745e-06,
"loss": 1.0603,
"step": 1348
},
{
"epoch": 3.4501278772378514,
"grad_norm": 0.15593100830308165,
"learning_rate": 5.307211871912828e-06,
"loss": 1.0651,
"step": 1349
},
{
"epoch": 3.452685421994885,
"grad_norm": 0.17222844205737484,
"learning_rate": 5.291447997314367e-06,
"loss": 1.0524,
"step": 1350
},
{
"epoch": 3.455242966751918,
"grad_norm": 0.18445018135377744,
"learning_rate": 5.275699142210615e-06,
"loss": 1.0483,
"step": 1351
},
{
"epoch": 3.4578005115089514,
"grad_norm": 0.15254595235934099,
"learning_rate": 5.259965356837795e-06,
"loss": 1.056,
"step": 1352
},
{
"epoch": 3.4603580562659846,
"grad_norm": 0.1681256587998916,
"learning_rate": 5.2442466913840504e-06,
"loss": 1.0201,
"step": 1353
},
{
"epoch": 3.4629156010230178,
"grad_norm": 0.20513309582498962,
"learning_rate": 5.228543195989303e-06,
"loss": 1.042,
"step": 1354
},
{
"epoch": 3.4654731457800514,
"grad_norm": 0.1651579107715655,
"learning_rate": 5.212854920745075e-06,
"loss": 1.0335,
"step": 1355
},
{
"epoch": 3.4680306905370846,
"grad_norm": 0.1672316644360442,
"learning_rate": 5.197181915694355e-06,
"loss": 1.0402,
"step": 1356
},
{
"epoch": 3.4705882352941178,
"grad_norm": 0.18835532310561898,
"learning_rate": 5.18152423083141e-06,
"loss": 1.0441,
"step": 1357
},
{
"epoch": 3.473145780051151,
"grad_norm": 0.15869844025048313,
"learning_rate": 5.1658819161016296e-06,
"loss": 1.0468,
"step": 1358
},
{
"epoch": 3.475703324808184,
"grad_norm": 0.16464692549899385,
"learning_rate": 5.1502550214013994e-06,
"loss": 1.0664,
"step": 1359
},
{
"epoch": 3.4782608695652173,
"grad_norm": 0.15694449028311525,
"learning_rate": 5.134643596577898e-06,
"loss": 1.0536,
"step": 1360
},
{
"epoch": 3.4808184143222505,
"grad_norm": 0.15197955681788783,
"learning_rate": 5.1190476914289645e-06,
"loss": 1.0357,
"step": 1361
},
{
"epoch": 3.483375959079284,
"grad_norm": 0.1666030618291994,
"learning_rate": 5.103467355702928e-06,
"loss": 1.0428,
"step": 1362
},
{
"epoch": 3.4859335038363173,
"grad_norm": 0.15565303487254922,
"learning_rate": 5.087902639098472e-06,
"loss": 1.0586,
"step": 1363
},
{
"epoch": 3.4884910485933505,
"grad_norm": 0.159004503149546,
"learning_rate": 5.072353591264429e-06,
"loss": 1.0271,
"step": 1364
},
{
"epoch": 3.4910485933503836,
"grad_norm": 0.19059651465127486,
"learning_rate": 5.056820261799668e-06,
"loss": 1.0668,
"step": 1365
},
{
"epoch": 3.493606138107417,
"grad_norm": 0.15760115088433216,
"learning_rate": 5.041302700252921e-06,
"loss": 1.0853,
"step": 1366
},
{
"epoch": 3.49616368286445,
"grad_norm": 0.1634157254255831,
"learning_rate": 5.02580095612262e-06,
"loss": 1.0664,
"step": 1367
},
{
"epoch": 3.498721227621483,
"grad_norm": 0.18070651331042822,
"learning_rate": 5.010315078856733e-06,
"loss": 1.0043,
"step": 1368
},
{
"epoch": 3.501278772378517,
"grad_norm": 0.1517363485498429,
"learning_rate": 4.99484511785263e-06,
"loss": 1.0535,
"step": 1369
},
{
"epoch": 3.50383631713555,
"grad_norm": 0.15908324436429314,
"learning_rate": 4.979391122456899e-06,
"loss": 1.0565,
"step": 1370
},
{
"epoch": 3.506393861892583,
"grad_norm": 0.16295413916211288,
"learning_rate": 4.963953141965208e-06,
"loss": 1.0531,
"step": 1371
},
{
"epoch": 3.5089514066496164,
"grad_norm": 0.15384339113595663,
"learning_rate": 4.94853122562213e-06,
"loss": 1.0707,
"step": 1372
},
{
"epoch": 3.5115089514066495,
"grad_norm": 0.1555405750624787,
"learning_rate": 4.9331254226210136e-06,
"loss": 1.0288,
"step": 1373
},
{
"epoch": 3.5140664961636827,
"grad_norm": 0.1574920923229238,
"learning_rate": 4.917735782103796e-06,
"loss": 1.0516,
"step": 1374
},
{
"epoch": 3.516624040920716,
"grad_norm": 0.1685616882842499,
"learning_rate": 4.902362353160851e-06,
"loss": 1.0232,
"step": 1375
},
{
"epoch": 3.5191815856777495,
"grad_norm": 0.14391567303608666,
"learning_rate": 4.887005184830861e-06,
"loss": 1.0296,
"step": 1376
},
{
"epoch": 3.5217391304347827,
"grad_norm": 0.14995128976992425,
"learning_rate": 4.871664326100625e-06,
"loss": 1.0571,
"step": 1377
},
{
"epoch": 3.524296675191816,
"grad_norm": 0.15919702291165838,
"learning_rate": 4.856339825904921e-06,
"loss": 1.0221,
"step": 1378
},
{
"epoch": 3.526854219948849,
"grad_norm": 0.15107002812900702,
"learning_rate": 4.841031733126346e-06,
"loss": 1.0872,
"step": 1379
},
{
"epoch": 3.5294117647058822,
"grad_norm": 0.14144172181733294,
"learning_rate": 4.825740096595159e-06,
"loss": 1.0272,
"step": 1380
},
{
"epoch": 3.531969309462916,
"grad_norm": 0.17206998247154082,
"learning_rate": 4.81046496508913e-06,
"loss": 1.0833,
"step": 1381
},
{
"epoch": 3.5345268542199486,
"grad_norm": 0.1387566110901943,
"learning_rate": 4.795206387333371e-06,
"loss": 1.0531,
"step": 1382
},
{
"epoch": 3.5370843989769822,
"grad_norm": 0.14298771692753376,
"learning_rate": 4.779964412000207e-06,
"loss": 1.0378,
"step": 1383
},
{
"epoch": 3.5396419437340154,
"grad_norm": 0.14816320170562203,
"learning_rate": 4.764739087708988e-06,
"loss": 1.0668,
"step": 1384
},
{
"epoch": 3.5421994884910486,
"grad_norm": 0.1476382719637328,
"learning_rate": 4.749530463025961e-06,
"loss": 1.0448,
"step": 1385
},
{
"epoch": 3.544757033248082,
"grad_norm": 0.14204568545092844,
"learning_rate": 4.734338586464096e-06,
"loss": 1.0647,
"step": 1386
},
{
"epoch": 3.547314578005115,
"grad_norm": 0.13917278007082326,
"learning_rate": 4.719163506482942e-06,
"loss": 1.0165,
"step": 1387
},
{
"epoch": 3.5498721227621486,
"grad_norm": 0.15529645602703832,
"learning_rate": 4.704005271488472e-06,
"loss": 1.0381,
"step": 1388
},
{
"epoch": 3.5524296675191813,
"grad_norm": 0.14796765919906726,
"learning_rate": 4.688863929832922e-06,
"loss": 1.0659,
"step": 1389
},
{
"epoch": 3.554987212276215,
"grad_norm": 0.14135671867370417,
"learning_rate": 4.673739529814653e-06,
"loss": 1.0741,
"step": 1390
},
{
"epoch": 3.557544757033248,
"grad_norm": 0.1387525451398238,
"learning_rate": 4.658632119677965e-06,
"loss": 1.0079,
"step": 1391
},
{
"epoch": 3.5601023017902813,
"grad_norm": 0.15154983652739518,
"learning_rate": 4.6435417476129745e-06,
"loss": 1.0333,
"step": 1392
},
{
"epoch": 3.5626598465473145,
"grad_norm": 0.15835829501275145,
"learning_rate": 4.628468461755456e-06,
"loss": 1.0531,
"step": 1393
},
{
"epoch": 3.5652173913043477,
"grad_norm": 0.14664150937490233,
"learning_rate": 4.613412310186669e-06,
"loss": 1.0541,
"step": 1394
},
{
"epoch": 3.5677749360613813,
"grad_norm": 0.15043461437274602,
"learning_rate": 4.598373340933226e-06,
"loss": 1.0608,
"step": 1395
},
{
"epoch": 3.5703324808184145,
"grad_norm": 0.1452832340949103,
"learning_rate": 4.583351601966928e-06,
"loss": 1.0385,
"step": 1396
},
{
"epoch": 3.5728900255754477,
"grad_norm": 0.13933252151544814,
"learning_rate": 4.568347141204611e-06,
"loss": 1.019,
"step": 1397
},
{
"epoch": 3.575447570332481,
"grad_norm": 0.1522016997768107,
"learning_rate": 4.553360006508003e-06,
"loss": 1.0592,
"step": 1398
},
{
"epoch": 3.578005115089514,
"grad_norm": 0.14375660032866683,
"learning_rate": 4.538390245683555e-06,
"loss": 1.0616,
"step": 1399
},
{
"epoch": 3.580562659846547,
"grad_norm": 0.15304841832573549,
"learning_rate": 4.523437906482313e-06,
"loss": 1.0209,
"step": 1400
},
{
"epoch": 3.5831202046035804,
"grad_norm": 0.16188117769084115,
"learning_rate": 4.508503036599743e-06,
"loss": 1.0308,
"step": 1401
},
{
"epoch": 3.585677749360614,
"grad_norm": 0.14884489221085204,
"learning_rate": 4.493585683675575e-06,
"loss": 1.0512,
"step": 1402
},
{
"epoch": 3.588235294117647,
"grad_norm": 0.13887978241681936,
"learning_rate": 4.478685895293685e-06,
"loss": 1.0459,
"step": 1403
},
{
"epoch": 3.5907928388746804,
"grad_norm": 0.16378567976403613,
"learning_rate": 4.463803718981905e-06,
"loss": 1.0521,
"step": 1404
},
{
"epoch": 3.5933503836317136,
"grad_norm": 0.151640894218935,
"learning_rate": 4.448939202211896e-06,
"loss": 1.0426,
"step": 1405
},
{
"epoch": 3.5959079283887467,
"grad_norm": 0.14699983592365332,
"learning_rate": 4.434092392398978e-06,
"loss": 1.0446,
"step": 1406
},
{
"epoch": 3.59846547314578,
"grad_norm": 0.15099144797792488,
"learning_rate": 4.419263336902006e-06,
"loss": 1.0536,
"step": 1407
},
{
"epoch": 3.601023017902813,
"grad_norm": 0.15653391024407642,
"learning_rate": 4.404452083023183e-06,
"loss": 1.056,
"step": 1408
},
{
"epoch": 3.6035805626598467,
"grad_norm": 0.16221666231166285,
"learning_rate": 4.389658678007933e-06,
"loss": 1.0326,
"step": 1409
},
{
"epoch": 3.60613810741688,
"grad_norm": 0.15454011824050923,
"learning_rate": 4.374883169044757e-06,
"loss": 1.0065,
"step": 1410
},
{
"epoch": 3.608695652173913,
"grad_norm": 0.14534327322247192,
"learning_rate": 4.3601256032650576e-06,
"loss": 1.0487,
"step": 1411
},
{
"epoch": 3.6112531969309463,
"grad_norm": 0.1417228468510155,
"learning_rate": 4.345386027743005e-06,
"loss": 1.067,
"step": 1412
},
{
"epoch": 3.6138107416879794,
"grad_norm": 0.1472202179946865,
"learning_rate": 4.330664489495386e-06,
"loss": 1.0233,
"step": 1413
},
{
"epoch": 3.6163682864450126,
"grad_norm": 0.152838033504761,
"learning_rate": 4.315961035481445e-06,
"loss": 1.0429,
"step": 1414
},
{
"epoch": 3.618925831202046,
"grad_norm": 0.14202501165868497,
"learning_rate": 4.30127571260275e-06,
"loss": 1.0221,
"step": 1415
},
{
"epoch": 3.6214833759590794,
"grad_norm": 0.15558682308936234,
"learning_rate": 4.286608567703025e-06,
"loss": 1.0454,
"step": 1416
},
{
"epoch": 3.6240409207161126,
"grad_norm": 0.15926194693025708,
"learning_rate": 4.271959647568017e-06,
"loss": 1.0208,
"step": 1417
},
{
"epoch": 3.626598465473146,
"grad_norm": 0.1563509007491471,
"learning_rate": 4.257328998925339e-06,
"loss": 1.0575,
"step": 1418
},
{
"epoch": 3.629156010230179,
"grad_norm": 0.14556455028498103,
"learning_rate": 4.242716668444304e-06,
"loss": 1.0486,
"step": 1419
},
{
"epoch": 3.631713554987212,
"grad_norm": 0.1870985092309066,
"learning_rate": 4.228122702735818e-06,
"loss": 1.0511,
"step": 1420
},
{
"epoch": 3.634271099744246,
"grad_norm": 0.1437574000454239,
"learning_rate": 4.213547148352193e-06,
"loss": 1.0664,
"step": 1421
},
{
"epoch": 3.6368286445012785,
"grad_norm": 0.1464730506258114,
"learning_rate": 4.198990051787012e-06,
"loss": 1.0185,
"step": 1422
},
{
"epoch": 3.639386189258312,
"grad_norm": 0.1480513669086599,
"learning_rate": 4.184451459474983e-06,
"loss": 1.0481,
"step": 1423
},
{
"epoch": 3.6419437340153453,
"grad_norm": 0.15929462236223393,
"learning_rate": 4.169931417791788e-06,
"loss": 1.0392,
"step": 1424
},
{
"epoch": 3.6445012787723785,
"grad_norm": 0.14283038176368648,
"learning_rate": 4.155429973053935e-06,
"loss": 1.0682,
"step": 1425
},
{
"epoch": 3.6470588235294117,
"grad_norm": 0.1587622512950815,
"learning_rate": 4.140947171518609e-06,
"loss": 1.0256,
"step": 1426
},
{
"epoch": 3.649616368286445,
"grad_norm": 0.1521708022719752,
"learning_rate": 4.126483059383534e-06,
"loss": 1.0385,
"step": 1427
},
{
"epoch": 3.6521739130434785,
"grad_norm": 0.15273099328180773,
"learning_rate": 4.112037682786811e-06,
"loss": 1.0318,
"step": 1428
},
{
"epoch": 3.6547314578005117,
"grad_norm": 0.15588241294914806,
"learning_rate": 4.097611087806779e-06,
"loss": 1.0216,
"step": 1429
},
{
"epoch": 3.657289002557545,
"grad_norm": 0.13906215524951357,
"learning_rate": 4.083203320461867e-06,
"loss": 1.0534,
"step": 1430
},
{
"epoch": 3.659846547314578,
"grad_norm": 0.13375858888458342,
"learning_rate": 4.068814426710447e-06,
"loss": 1.0466,
"step": 1431
},
{
"epoch": 3.662404092071611,
"grad_norm": 0.14715897307378298,
"learning_rate": 4.054444452450688e-06,
"loss": 1.0511,
"step": 1432
},
{
"epoch": 3.6649616368286444,
"grad_norm": 0.15947927453300095,
"learning_rate": 4.040093443520404e-06,
"loss": 1.0249,
"step": 1433
},
{
"epoch": 3.6675191815856776,
"grad_norm": 0.1387655661713122,
"learning_rate": 4.02576144569693e-06,
"loss": 1.0316,
"step": 1434
},
{
"epoch": 3.670076726342711,
"grad_norm": 0.14307072067989993,
"learning_rate": 4.011448504696933e-06,
"loss": 1.0269,
"step": 1435
},
{
"epoch": 3.6726342710997444,
"grad_norm": 0.15772626616588967,
"learning_rate": 3.997154666176306e-06,
"loss": 1.0582,
"step": 1436
},
{
"epoch": 3.6751918158567776,
"grad_norm": 0.14282292553538378,
"learning_rate": 3.982879975730015e-06,
"loss": 1.0323,
"step": 1437
},
{
"epoch": 3.6777493606138107,
"grad_norm": 0.1534255051225497,
"learning_rate": 3.968624478891935e-06,
"loss": 1.0925,
"step": 1438
},
{
"epoch": 3.680306905370844,
"grad_norm": 0.14321832602712206,
"learning_rate": 3.954388221134721e-06,
"loss": 1.0265,
"step": 1439
},
{
"epoch": 3.682864450127877,
"grad_norm": 0.144382148106992,
"learning_rate": 3.9401712478696584e-06,
"loss": 1.0263,
"step": 1440
},
{
"epoch": 3.6854219948849103,
"grad_norm": 0.15170436155022662,
"learning_rate": 3.9259736044465165e-06,
"loss": 1.0271,
"step": 1441
},
{
"epoch": 3.687979539641944,
"grad_norm": 0.14290531170670692,
"learning_rate": 3.91179533615341e-06,
"loss": 1.0233,
"step": 1442
},
{
"epoch": 3.690537084398977,
"grad_norm": 0.13889175521979244,
"learning_rate": 3.897636488216641e-06,
"loss": 1.0072,
"step": 1443
},
{
"epoch": 3.6930946291560103,
"grad_norm": 0.14619106107662108,
"learning_rate": 3.88349710580058e-06,
"loss": 1.0349,
"step": 1444
},
{
"epoch": 3.6956521739130435,
"grad_norm": 0.14842632075321688,
"learning_rate": 3.8693772340074945e-06,
"loss": 1.057,
"step": 1445
},
{
"epoch": 3.6982097186700766,
"grad_norm": 0.13344432430502018,
"learning_rate": 3.855276917877408e-06,
"loss": 1.0182,
"step": 1446
},
{
"epoch": 3.70076726342711,
"grad_norm": 0.13677433922377288,
"learning_rate": 3.8411962023879844e-06,
"loss": 1.0478,
"step": 1447
},
{
"epoch": 3.703324808184143,
"grad_norm": 0.1519820293465984,
"learning_rate": 3.827135132454351e-06,
"loss": 1.0695,
"step": 1448
},
{
"epoch": 3.7058823529411766,
"grad_norm": 0.1380667164839018,
"learning_rate": 3.8130937529289734e-06,
"loss": 1.0203,
"step": 1449
},
{
"epoch": 3.70843989769821,
"grad_norm": 0.1346633518238781,
"learning_rate": 3.7990721086015114e-06,
"loss": 1.0344,
"step": 1450
},
{
"epoch": 3.710997442455243,
"grad_norm": 0.14686955698606644,
"learning_rate": 3.78507024419867e-06,
"loss": 1.0135,
"step": 1451
},
{
"epoch": 3.713554987212276,
"grad_norm": 0.15250547269977222,
"learning_rate": 3.7710882043840513e-06,
"loss": 1.0443,
"step": 1452
},
{
"epoch": 3.7161125319693094,
"grad_norm": 0.14183857654080673,
"learning_rate": 3.7571260337580283e-06,
"loss": 1.0276,
"step": 1453
},
{
"epoch": 3.718670076726343,
"grad_norm": 0.14830544734060966,
"learning_rate": 3.743183776857602e-06,
"loss": 1.0716,
"step": 1454
},
{
"epoch": 3.7212276214833757,
"grad_norm": 0.1456400419210818,
"learning_rate": 3.7292614781562384e-06,
"loss": 1.026,
"step": 1455
},
{
"epoch": 3.7237851662404093,
"grad_norm": 0.15092175218127304,
"learning_rate": 3.715359182063748e-06,
"loss": 1.0232,
"step": 1456
},
{
"epoch": 3.7263427109974425,
"grad_norm": 0.1699845240726765,
"learning_rate": 3.7014769329261325e-06,
"loss": 1.068,
"step": 1457
},
{
"epoch": 3.7289002557544757,
"grad_norm": 0.15520588635807145,
"learning_rate": 3.68761477502545e-06,
"loss": 1.0256,
"step": 1458
},
{
"epoch": 3.731457800511509,
"grad_norm": 0.14562325712512364,
"learning_rate": 3.673772752579665e-06,
"loss": 1.0607,
"step": 1459
},
{
"epoch": 3.734015345268542,
"grad_norm": 0.15541923560195023,
"learning_rate": 3.6599509097425246e-06,
"loss": 1.0436,
"step": 1460
},
{
"epoch": 3.7365728900255757,
"grad_norm": 0.1607476965680906,
"learning_rate": 3.646149290603398e-06,
"loss": 1.0202,
"step": 1461
},
{
"epoch": 3.7391304347826084,
"grad_norm": 0.14491441420503393,
"learning_rate": 3.6323679391871447e-06,
"loss": 1.0263,
"step": 1462
},
{
"epoch": 3.741687979539642,
"grad_norm": 0.17277986367023201,
"learning_rate": 3.6186068994539746e-06,
"loss": 1.0356,
"step": 1463
},
{
"epoch": 3.7442455242966752,
"grad_norm": 0.16679682898908768,
"learning_rate": 3.6048662152993062e-06,
"loss": 1.0554,
"step": 1464
},
{
"epoch": 3.7468030690537084,
"grad_norm": 0.14727808773917042,
"learning_rate": 3.5911459305536302e-06,
"loss": 1.0428,
"step": 1465
},
{
"epoch": 3.7493606138107416,
"grad_norm": 0.161921935441449,
"learning_rate": 3.577446088982357e-06,
"loss": 1.0384,
"step": 1466
},
{
"epoch": 3.7519181585677748,
"grad_norm": 0.16271933317209,
"learning_rate": 3.563766734285704e-06,
"loss": 1.0403,
"step": 1467
},
{
"epoch": 3.7544757033248084,
"grad_norm": 0.16870928574249397,
"learning_rate": 3.550107910098526e-06,
"loss": 1.036,
"step": 1468
},
{
"epoch": 3.7570332480818416,
"grad_norm": 0.1553381789909288,
"learning_rate": 3.5364696599901837e-06,
"loss": 1.0601,
"step": 1469
},
{
"epoch": 3.7595907928388748,
"grad_norm": 0.14997588844332052,
"learning_rate": 3.5228520274644264e-06,
"loss": 1.016,
"step": 1470
},
{
"epoch": 3.762148337595908,
"grad_norm": 0.17329631324712091,
"learning_rate": 3.5092550559592243e-06,
"loss": 1.0493,
"step": 1471
},
{
"epoch": 3.764705882352941,
"grad_norm": 0.1569662893495077,
"learning_rate": 3.495678788846648e-06,
"loss": 1.0433,
"step": 1472
},
{
"epoch": 3.7672634271099743,
"grad_norm": 0.15139032350205295,
"learning_rate": 3.482123269432722e-06,
"loss": 1.0257,
"step": 1473
},
{
"epoch": 3.7698209718670075,
"grad_norm": 0.15007562912485958,
"learning_rate": 3.4685885409572896e-06,
"loss": 1.0329,
"step": 1474
},
{
"epoch": 3.772378516624041,
"grad_norm": 0.16102630257285133,
"learning_rate": 3.4550746465938754e-06,
"loss": 1.0491,
"step": 1475
},
{
"epoch": 3.7749360613810743,
"grad_norm": 0.16752120082373823,
"learning_rate": 3.441581629449542e-06,
"loss": 1.041,
"step": 1476
},
{
"epoch": 3.7774936061381075,
"grad_norm": 0.1424221688932342,
"learning_rate": 3.4281095325647682e-06,
"loss": 1.009,
"step": 1477
},
{
"epoch": 3.7800511508951407,
"grad_norm": 0.14586125645039055,
"learning_rate": 3.4146583989132897e-06,
"loss": 1.0347,
"step": 1478
},
{
"epoch": 3.782608695652174,
"grad_norm": 0.15136208820123082,
"learning_rate": 3.4012282714019784e-06,
"loss": 1.0205,
"step": 1479
},
{
"epoch": 3.785166240409207,
"grad_norm": 0.1502892464390208,
"learning_rate": 3.387819192870697e-06,
"loss": 1.0289,
"step": 1480
},
{
"epoch": 3.78772378516624,
"grad_norm": 0.1412412642364067,
"learning_rate": 3.374431206092168e-06,
"loss": 1.0305,
"step": 1481
},
{
"epoch": 3.790281329923274,
"grad_norm": 0.13814570417279723,
"learning_rate": 3.3610643537718347e-06,
"loss": 1.0485,
"step": 1482
},
{
"epoch": 3.792838874680307,
"grad_norm": 0.13640331630857278,
"learning_rate": 3.347718678547719e-06,
"loss": 1.1023,
"step": 1483
},
{
"epoch": 3.79539641943734,
"grad_norm": 0.14994268119891938,
"learning_rate": 3.334394222990307e-06,
"loss": 1.0457,
"step": 1484
},
{
"epoch": 3.7979539641943734,
"grad_norm": 0.15575803797953353,
"learning_rate": 3.321091029602378e-06,
"loss": 1.0816,
"step": 1485
},
{
"epoch": 3.8005115089514065,
"grad_norm": 0.13866906616126037,
"learning_rate": 3.3078091408188984e-06,
"loss": 1.0702,
"step": 1486
},
{
"epoch": 3.80306905370844,
"grad_norm": 0.12980796709609282,
"learning_rate": 3.29454859900688e-06,
"loss": 1.0553,
"step": 1487
},
{
"epoch": 3.805626598465473,
"grad_norm": 0.1383223434086824,
"learning_rate": 3.2813094464652362e-06,
"loss": 1.0366,
"step": 1488
},
{
"epoch": 3.8081841432225065,
"grad_norm": 0.1435484790801586,
"learning_rate": 3.2680917254246515e-06,
"loss": 1.0434,
"step": 1489
},
{
"epoch": 3.8107416879795397,
"grad_norm": 0.1429077430292127,
"learning_rate": 3.2548954780474485e-06,
"loss": 1.0465,
"step": 1490
},
{
"epoch": 3.813299232736573,
"grad_norm": 0.1426703166662691,
"learning_rate": 3.241720746427456e-06,
"loss": 1.0458,
"step": 1491
},
{
"epoch": 3.815856777493606,
"grad_norm": 0.14480062983873204,
"learning_rate": 3.228567572589865e-06,
"loss": 1.0407,
"step": 1492
},
{
"epoch": 3.8184143222506393,
"grad_norm": 0.1439275121559339,
"learning_rate": 3.215435998491102e-06,
"loss": 1.0487,
"step": 1493
},
{
"epoch": 3.820971867007673,
"grad_norm": 0.1559869804995835,
"learning_rate": 3.2023260660187018e-06,
"loss": 1.0253,
"step": 1494
},
{
"epoch": 3.8235294117647056,
"grad_norm": 0.13239520801102936,
"learning_rate": 3.189237816991161e-06,
"loss": 1.0735,
"step": 1495
},
{
"epoch": 3.8260869565217392,
"grad_norm": 0.13906138820650482,
"learning_rate": 3.176171293157798e-06,
"loss": 1.0434,
"step": 1496
},
{
"epoch": 3.8286445012787724,
"grad_norm": 0.14386997194374815,
"learning_rate": 3.163126536198653e-06,
"loss": 1.0568,
"step": 1497
},
{
"epoch": 3.8312020460358056,
"grad_norm": 0.13652465945815134,
"learning_rate": 3.150103587724318e-06,
"loss": 1.0244,
"step": 1498
},
{
"epoch": 3.833759590792839,
"grad_norm": 0.14696915009976544,
"learning_rate": 3.137102489275824e-06,
"loss": 1.0333,
"step": 1499
},
{
"epoch": 3.836317135549872,
"grad_norm": 0.14077378579589328,
"learning_rate": 3.124123282324503e-06,
"loss": 1.0618,
"step": 1500
},
{
"epoch": 3.8388746803069056,
"grad_norm": 0.13614318341580398,
"learning_rate": 3.1111660082718666e-06,
"loss": 1.0407,
"step": 1501
},
{
"epoch": 3.8414322250639388,
"grad_norm": 0.13328361531738175,
"learning_rate": 3.0982307084494457e-06,
"loss": 1.0503,
"step": 1502
},
{
"epoch": 3.843989769820972,
"grad_norm": 0.13500227612563093,
"learning_rate": 3.0853174241186867e-06,
"loss": 1.0147,
"step": 1503
},
{
"epoch": 3.846547314578005,
"grad_norm": 0.15319897471724173,
"learning_rate": 3.072426196470818e-06,
"loss": 1.0612,
"step": 1504
},
{
"epoch": 3.8491048593350383,
"grad_norm": 0.13414516138399563,
"learning_rate": 3.0595570666266996e-06,
"loss": 1.0613,
"step": 1505
},
{
"epoch": 3.8516624040920715,
"grad_norm": 0.13525360876497583,
"learning_rate": 3.0467100756367064e-06,
"loss": 1.0379,
"step": 1506
},
{
"epoch": 3.8542199488491047,
"grad_norm": 0.1429209705032719,
"learning_rate": 3.033885264480595e-06,
"loss": 1.0561,
"step": 1507
},
{
"epoch": 3.8567774936061383,
"grad_norm": 0.14899220326181728,
"learning_rate": 3.021082674067373e-06,
"loss": 1.0382,
"step": 1508
},
{
"epoch": 3.8593350383631715,
"grad_norm": 0.1390523791967841,
"learning_rate": 3.0083023452351634e-06,
"loss": 1.0667,
"step": 1509
},
{
"epoch": 3.8618925831202047,
"grad_norm": 0.139515567894694,
"learning_rate": 2.99554431875108e-06,
"loss": 1.0435,
"step": 1510
},
{
"epoch": 3.864450127877238,
"grad_norm": 0.14313433937785855,
"learning_rate": 2.982808635311104e-06,
"loss": 1.0179,
"step": 1511
},
{
"epoch": 3.867007672634271,
"grad_norm": 0.1308603519857462,
"learning_rate": 2.9700953355399385e-06,
"loss": 1.0038,
"step": 1512
},
{
"epoch": 3.869565217391304,
"grad_norm": 0.14459372229041947,
"learning_rate": 2.957404459990877e-06,
"loss": 1.0327,
"step": 1513
},
{
"epoch": 3.8721227621483374,
"grad_norm": 0.1418328836444824,
"learning_rate": 2.9447360491457034e-06,
"loss": 1.0408,
"step": 1514
},
{
"epoch": 3.874680306905371,
"grad_norm": 0.13508377583914918,
"learning_rate": 2.93209014341453e-06,
"loss": 1.0436,
"step": 1515
},
{
"epoch": 3.877237851662404,
"grad_norm": 0.13732362700671252,
"learning_rate": 2.9194667831356837e-06,
"loss": 1.0549,
"step": 1516
},
{
"epoch": 3.8797953964194374,
"grad_norm": 0.13395895878948533,
"learning_rate": 2.9068660085755775e-06,
"loss": 1.0778,
"step": 1517
},
{
"epoch": 3.8823529411764706,
"grad_norm": 0.13299070727246437,
"learning_rate": 2.8942878599285773e-06,
"loss": 1.0495,
"step": 1518
},
{
"epoch": 3.8849104859335037,
"grad_norm": 0.14423958774637266,
"learning_rate": 2.8817323773168783e-06,
"loss": 1.0681,
"step": 1519
},
{
"epoch": 3.887468030690537,
"grad_norm": 0.13441811948188004,
"learning_rate": 2.869199600790369e-06,
"loss": 1.0579,
"step": 1520
},
{
"epoch": 3.89002557544757,
"grad_norm": 0.15663102989889852,
"learning_rate": 2.8566895703265216e-06,
"loss": 1.0345,
"step": 1521
},
{
"epoch": 3.8925831202046037,
"grad_norm": 0.14208764333909965,
"learning_rate": 2.844202325830241e-06,
"loss": 1.0031,
"step": 1522
},
{
"epoch": 3.895140664961637,
"grad_norm": 0.14573616081300186,
"learning_rate": 2.8317379071337515e-06,
"loss": 1.0407,
"step": 1523
},
{
"epoch": 3.89769820971867,
"grad_norm": 0.15711176247504646,
"learning_rate": 2.819296353996468e-06,
"loss": 1.0353,
"step": 1524
},
{
"epoch": 3.9002557544757033,
"grad_norm": 0.13860891537498624,
"learning_rate": 2.806877706104867e-06,
"loss": 1.0584,
"step": 1525
},
{
"epoch": 3.9028132992327365,
"grad_norm": 0.14228002085549987,
"learning_rate": 2.794482003072364e-06,
"loss": 1.0449,
"step": 1526
},
{
"epoch": 3.90537084398977,
"grad_norm": 0.1375210322551571,
"learning_rate": 2.7821092844391762e-06,
"loss": 1.0357,
"step": 1527
},
{
"epoch": 3.907928388746803,
"grad_norm": 0.13889206339574903,
"learning_rate": 2.7697595896722206e-06,
"loss": 1.0499,
"step": 1528
},
{
"epoch": 3.9104859335038364,
"grad_norm": 0.15252492951738833,
"learning_rate": 2.757432958164953e-06,
"loss": 1.0142,
"step": 1529
},
{
"epoch": 3.9130434782608696,
"grad_norm": 0.13347562424578444,
"learning_rate": 2.745129429237269e-06,
"loss": 1.0436,
"step": 1530
},
{
"epoch": 3.915601023017903,
"grad_norm": 0.13176945767052098,
"learning_rate": 2.732849042135377e-06,
"loss": 1.0349,
"step": 1531
},
{
"epoch": 3.918158567774936,
"grad_norm": 0.14363585761020053,
"learning_rate": 2.72059183603166e-06,
"loss": 1.0487,
"step": 1532
},
{
"epoch": 3.920716112531969,
"grad_norm": 0.14363411928958503,
"learning_rate": 2.7083578500245567e-06,
"loss": 1.0467,
"step": 1533
},
{
"epoch": 3.923273657289003,
"grad_norm": 0.13936136441370217,
"learning_rate": 2.696147123138442e-06,
"loss": 1.0586,
"step": 1534
},
{
"epoch": 3.9258312020460355,
"grad_norm": 0.14655776610626794,
"learning_rate": 2.6839596943234948e-06,
"loss": 1.0468,
"step": 1535
},
{
"epoch": 3.928388746803069,
"grad_norm": 0.15051847712859898,
"learning_rate": 2.671795602455578e-06,
"loss": 1.0329,
"step": 1536
},
{
"epoch": 3.9309462915601023,
"grad_norm": 0.13505484364512485,
"learning_rate": 2.6596548863361117e-06,
"loss": 1.0311,
"step": 1537
},
{
"epoch": 3.9335038363171355,
"grad_norm": 0.16238346606896784,
"learning_rate": 2.647537584691957e-06,
"loss": 1.0497,
"step": 1538
},
{
"epoch": 3.9360613810741687,
"grad_norm": 0.14175763037908903,
"learning_rate": 2.635443736175285e-06,
"loss": 1.0308,
"step": 1539
},
{
"epoch": 3.938618925831202,
"grad_norm": 0.13596964536942902,
"learning_rate": 2.6233733793634443e-06,
"loss": 1.0419,
"step": 1540
},
{
"epoch": 3.9411764705882355,
"grad_norm": 0.153459320504519,
"learning_rate": 2.611326552758865e-06,
"loss": 1.0326,
"step": 1541
},
{
"epoch": 3.9437340153452687,
"grad_norm": 0.13805486780739087,
"learning_rate": 2.599303294788912e-06,
"loss": 1.0091,
"step": 1542
},
{
"epoch": 3.946291560102302,
"grad_norm": 0.15471538183539127,
"learning_rate": 2.5873036438057676e-06,
"loss": 1.0337,
"step": 1543
},
{
"epoch": 3.948849104859335,
"grad_norm": 0.13381926520485934,
"learning_rate": 2.5753276380863146e-06,
"loss": 1.0152,
"step": 1544
},
{
"epoch": 3.9514066496163682,
"grad_norm": 0.1526645485398575,
"learning_rate": 2.5633753158320187e-06,
"loss": 1.0528,
"step": 1545
},
{
"epoch": 3.9539641943734014,
"grad_norm": 0.1345563700018159,
"learning_rate": 2.551446715168785e-06,
"loss": 1.0234,
"step": 1546
},
{
"epoch": 3.9565217391304346,
"grad_norm": 0.14109365045502603,
"learning_rate": 2.539541874146857e-06,
"loss": 1.0536,
"step": 1547
},
{
"epoch": 3.959079283887468,
"grad_norm": 0.13079972583954438,
"learning_rate": 2.5276608307406947e-06,
"loss": 1.0312,
"step": 1548
},
{
"epoch": 3.9616368286445014,
"grad_norm": 0.14344519725256097,
"learning_rate": 2.5158036228488426e-06,
"loss": 1.0957,
"step": 1549
},
{
"epoch": 3.9641943734015346,
"grad_norm": 0.1373250552318116,
"learning_rate": 2.503970288293811e-06,
"loss": 1.0625,
"step": 1550
},
{
"epoch": 3.9667519181585678,
"grad_norm": 0.1272077247026377,
"learning_rate": 2.492160864821964e-06,
"loss": 1.0518,
"step": 1551
},
{
"epoch": 3.969309462915601,
"grad_norm": 0.14387184269881323,
"learning_rate": 2.4803753901033887e-06,
"loss": 1.0524,
"step": 1552
},
{
"epoch": 3.971867007672634,
"grad_norm": 0.14549905203239785,
"learning_rate": 2.4686139017317834e-06,
"loss": 1.051,
"step": 1553
},
{
"epoch": 3.9744245524296673,
"grad_norm": 0.1365288629952198,
"learning_rate": 2.456876437224327e-06,
"loss": 1.0372,
"step": 1554
},
{
"epoch": 3.976982097186701,
"grad_norm": 0.13426973718739119,
"learning_rate": 2.4451630340215806e-06,
"loss": 1.0601,
"step": 1555
},
{
"epoch": 3.979539641943734,
"grad_norm": 0.14101312603970495,
"learning_rate": 2.4334737294873412e-06,
"loss": 1.0738,
"step": 1556
},
{
"epoch": 3.9820971867007673,
"grad_norm": 0.13956525094149905,
"learning_rate": 2.4218085609085317e-06,
"loss": 1.041,
"step": 1557
},
{
"epoch": 3.9846547314578005,
"grad_norm": 0.137559865762302,
"learning_rate": 2.4101675654951007e-06,
"loss": 1.0552,
"step": 1558
},
{
"epoch": 3.9872122762148337,
"grad_norm": 0.1451836876243983,
"learning_rate": 2.398550780379877e-06,
"loss": 1.0343,
"step": 1559
},
{
"epoch": 3.9897698209718673,
"grad_norm": 0.13670823609416857,
"learning_rate": 2.3869582426184646e-06,
"loss": 1.0494,
"step": 1560
},
{
"epoch": 3.9923273657289,
"grad_norm": 0.1291970541444472,
"learning_rate": 2.375389989189124e-06,
"loss": 1.0489,
"step": 1561
},
{
"epoch": 3.9948849104859336,
"grad_norm": 0.13910494832994932,
"learning_rate": 2.3638460569926526e-06,
"loss": 1.0628,
"step": 1562
},
{
"epoch": 3.997442455242967,
"grad_norm": 0.14089850988803235,
"learning_rate": 2.3523264828522664e-06,
"loss": 1.0401,
"step": 1563
},
{
"epoch": 4.0,
"grad_norm": 0.13798191201750412,
"learning_rate": 2.34083130351348e-06,
"loss": 1.0511,
"step": 1564
},
{
"epoch": 4.002557544757034,
"grad_norm": 0.1460757819403398,
"learning_rate": 2.3293605556440036e-06,
"loss": 1.0239,
"step": 1565
},
{
"epoch": 4.005115089514066,
"grad_norm": 0.1388523372795974,
"learning_rate": 2.3179142758336025e-06,
"loss": 1.0368,
"step": 1566
},
{
"epoch": 4.0076726342711,
"grad_norm": 0.14222700155961276,
"learning_rate": 2.3064925005939985e-06,
"loss": 1.012,
"step": 1567
},
{
"epoch": 4.010230179028133,
"grad_norm": 0.13819903902418096,
"learning_rate": 2.29509526635875e-06,
"loss": 1.0293,
"step": 1568
},
{
"epoch": 4.012787723785166,
"grad_norm": 0.13498705400952052,
"learning_rate": 2.2837226094831277e-06,
"loss": 1.0415,
"step": 1569
},
{
"epoch": 4.015345268542199,
"grad_norm": 0.13346320464672834,
"learning_rate": 2.272374566244011e-06,
"loss": 1.0438,
"step": 1570
},
{
"epoch": 4.017902813299233,
"grad_norm": 0.13390383794077007,
"learning_rate": 2.261051172839759e-06,
"loss": 1.0397,
"step": 1571
},
{
"epoch": 4.020460358056266,
"grad_norm": 0.1370898771780535,
"learning_rate": 2.249752465390115e-06,
"loss": 1.0257,
"step": 1572
},
{
"epoch": 4.023017902813299,
"grad_norm": 0.13111044024506377,
"learning_rate": 2.2384784799360593e-06,
"loss": 1.0312,
"step": 1573
},
{
"epoch": 4.025575447570333,
"grad_norm": 0.13928353777385094,
"learning_rate": 2.2272292524397256e-06,
"loss": 1.024,
"step": 1574
},
{
"epoch": 4.028132992327365,
"grad_norm": 0.13970299818718698,
"learning_rate": 2.216004818784274e-06,
"loss": 1.0285,
"step": 1575
},
{
"epoch": 4.030690537084399,
"grad_norm": 0.12461772368830429,
"learning_rate": 2.204805214773774e-06,
"loss": 1.0418,
"step": 1576
},
{
"epoch": 4.033248081841432,
"grad_norm": 0.13051534501054377,
"learning_rate": 2.193630476133087e-06,
"loss": 1.0129,
"step": 1577
},
{
"epoch": 4.035805626598465,
"grad_norm": 0.15306722598206782,
"learning_rate": 2.182480638507775e-06,
"loss": 1.0421,
"step": 1578
},
{
"epoch": 4.038363171355499,
"grad_norm": 0.14455268449480663,
"learning_rate": 2.171355737463946e-06,
"loss": 1.0416,
"step": 1579
},
{
"epoch": 4.040920716112532,
"grad_norm": 0.13063652782059365,
"learning_rate": 2.16025580848818e-06,
"loss": 1.0612,
"step": 1580
},
{
"epoch": 4.043478260869565,
"grad_norm": 0.14360502497244268,
"learning_rate": 2.1491808869874007e-06,
"loss": 1.0341,
"step": 1581
},
{
"epoch": 4.046035805626598,
"grad_norm": 0.13201827533910473,
"learning_rate": 2.1381310082887562e-06,
"loss": 1.0201,
"step": 1582
},
{
"epoch": 4.048593350383632,
"grad_norm": 0.13153522938184467,
"learning_rate": 2.127106207639519e-06,
"loss": 1.0124,
"step": 1583
},
{
"epoch": 4.051150895140665,
"grad_norm": 0.13613076423821696,
"learning_rate": 2.116106520206952e-06,
"loss": 1.0319,
"step": 1584
},
{
"epoch": 4.053708439897698,
"grad_norm": 0.13691012590975757,
"learning_rate": 2.10513198107823e-06,
"loss": 1.0276,
"step": 1585
},
{
"epoch": 4.056265984654732,
"grad_norm": 0.12697375062593624,
"learning_rate": 2.0941826252602993e-06,
"loss": 1.0699,
"step": 1586
},
{
"epoch": 4.0588235294117645,
"grad_norm": 0.12622299253237756,
"learning_rate": 2.083258487679772e-06,
"loss": 0.9935,
"step": 1587
},
{
"epoch": 4.061381074168798,
"grad_norm": 0.12883881312565362,
"learning_rate": 2.07235960318283e-06,
"loss": 1.0199,
"step": 1588
},
{
"epoch": 4.063938618925831,
"grad_norm": 0.1433790683750576,
"learning_rate": 2.061486006535095e-06,
"loss": 1.0648,
"step": 1589
},
{
"epoch": 4.0664961636828645,
"grad_norm": 0.1334070559519316,
"learning_rate": 2.0506377324215153e-06,
"loss": 1.0271,
"step": 1590
},
{
"epoch": 4.069053708439898,
"grad_norm": 0.13107810691262306,
"learning_rate": 2.0398148154462826e-06,
"loss": 1.0664,
"step": 1591
},
{
"epoch": 4.071611253196931,
"grad_norm": 0.13064607210418142,
"learning_rate": 2.029017290132693e-06,
"loss": 1.0561,
"step": 1592
},
{
"epoch": 4.0741687979539645,
"grad_norm": 0.13192450653543714,
"learning_rate": 2.0182451909230493e-06,
"loss": 1.0647,
"step": 1593
},
{
"epoch": 4.076726342710997,
"grad_norm": 0.13409898938813986,
"learning_rate": 2.0074985521785496e-06,
"loss": 1.0706,
"step": 1594
},
{
"epoch": 4.079283887468031,
"grad_norm": 0.12098414017807911,
"learning_rate": 1.9967774081791757e-06,
"loss": 1.027,
"step": 1595
},
{
"epoch": 4.081841432225064,
"grad_norm": 0.12932021861152668,
"learning_rate": 1.9860817931235875e-06,
"loss": 1.0564,
"step": 1596
},
{
"epoch": 4.084398976982097,
"grad_norm": 0.13119851497814697,
"learning_rate": 1.9754117411290098e-06,
"loss": 1.04,
"step": 1597
},
{
"epoch": 4.086956521739131,
"grad_norm": 0.12723835341568177,
"learning_rate": 1.964767286231132e-06,
"loss": 1.0075,
"step": 1598
},
{
"epoch": 4.089514066496164,
"grad_norm": 0.1331440706566852,
"learning_rate": 1.9541484623839836e-06,
"loss": 1.0115,
"step": 1599
},
{
"epoch": 4.092071611253197,
"grad_norm": 0.13004369154123793,
"learning_rate": 1.94355530345984e-06,
"loss": 1.0446,
"step": 1600
},
{
"epoch": 4.09462915601023,
"grad_norm": 0.13439541656021142,
"learning_rate": 1.932987843249111e-06,
"loss": 1.0408,
"step": 1601
},
{
"epoch": 4.0971867007672635,
"grad_norm": 0.12617676641867243,
"learning_rate": 1.922446115460229e-06,
"loss": 1.0247,
"step": 1602
},
{
"epoch": 4.099744245524296,
"grad_norm": 0.12373854222060104,
"learning_rate": 1.9119301537195455e-06,
"loss": 1.0107,
"step": 1603
},
{
"epoch": 4.10230179028133,
"grad_norm": 0.12497624014354403,
"learning_rate": 1.9014399915712213e-06,
"loss": 1.0528,
"step": 1604
},
{
"epoch": 4.1048593350383635,
"grad_norm": 0.12786730473206026,
"learning_rate": 1.8909756624771281e-06,
"loss": 1.0375,
"step": 1605
},
{
"epoch": 4.107416879795396,
"grad_norm": 0.12984834445815097,
"learning_rate": 1.880537199816722e-06,
"loss": 1.0422,
"step": 1606
},
{
"epoch": 4.10997442455243,
"grad_norm": 0.1251770868811918,
"learning_rate": 1.8701246368869563e-06,
"loss": 1.0185,
"step": 1607
},
{
"epoch": 4.112531969309463,
"grad_norm": 0.1361892397850472,
"learning_rate": 1.859738006902172e-06,
"loss": 1.0249,
"step": 1608
},
{
"epoch": 4.115089514066496,
"grad_norm": 0.12533127135022198,
"learning_rate": 1.8493773429939822e-06,
"loss": 1.0459,
"step": 1609
},
{
"epoch": 4.117647058823529,
"grad_norm": 0.13786171148092025,
"learning_rate": 1.8390426782111758e-06,
"loss": 1.0397,
"step": 1610
},
{
"epoch": 4.120204603580563,
"grad_norm": 0.12675000210328083,
"learning_rate": 1.8287340455196068e-06,
"loss": 1.0306,
"step": 1611
},
{
"epoch": 4.122762148337596,
"grad_norm": 0.13402518451365739,
"learning_rate": 1.8184514778020935e-06,
"loss": 1.025,
"step": 1612
},
{
"epoch": 4.125319693094629,
"grad_norm": 0.1290845343245023,
"learning_rate": 1.80819500785831e-06,
"loss": 1.0507,
"step": 1613
},
{
"epoch": 4.127877237851663,
"grad_norm": 0.13511534437927844,
"learning_rate": 1.7979646684046782e-06,
"loss": 1.0378,
"step": 1614
},
{
"epoch": 4.130434782608695,
"grad_norm": 0.12639858921905558,
"learning_rate": 1.7877604920742809e-06,
"loss": 1.039,
"step": 1615
},
{
"epoch": 4.132992327365729,
"grad_norm": 0.12601178623729056,
"learning_rate": 1.7775825114167344e-06,
"loss": 1.0381,
"step": 1616
},
{
"epoch": 4.135549872122763,
"grad_norm": 0.12901338885710367,
"learning_rate": 1.767430758898092e-06,
"loss": 1.0339,
"step": 1617
},
{
"epoch": 4.138107416879795,
"grad_norm": 0.13798456507222667,
"learning_rate": 1.757305266900755e-06,
"loss": 1.0328,
"step": 1618
},
{
"epoch": 4.140664961636829,
"grad_norm": 0.12951208934796613,
"learning_rate": 1.7472060677233505e-06,
"loss": 1.0067,
"step": 1619
},
{
"epoch": 4.143222506393862,
"grad_norm": 0.133587178193347,
"learning_rate": 1.737133193580638e-06,
"loss": 1.0633,
"step": 1620
},
{
"epoch": 4.145780051150895,
"grad_norm": 0.14209051304513082,
"learning_rate": 1.7270866766034012e-06,
"loss": 1.045,
"step": 1621
},
{
"epoch": 4.148337595907928,
"grad_norm": 0.12839529485772747,
"learning_rate": 1.7170665488383598e-06,
"loss": 1.0421,
"step": 1622
},
{
"epoch": 4.150895140664962,
"grad_norm": 0.12930109704079273,
"learning_rate": 1.7070728422480397e-06,
"loss": 1.0576,
"step": 1623
},
{
"epoch": 4.153452685421995,
"grad_norm": 0.12789118434710597,
"learning_rate": 1.6971055887106979e-06,
"loss": 1.0206,
"step": 1624
},
{
"epoch": 4.156010230179028,
"grad_norm": 0.13625076201484126,
"learning_rate": 1.687164820020213e-06,
"loss": 1.0331,
"step": 1625
},
{
"epoch": 4.158567774936062,
"grad_norm": 0.12958940476816713,
"learning_rate": 1.677250567885974e-06,
"loss": 1.0466,
"step": 1626
},
{
"epoch": 4.161125319693094,
"grad_norm": 0.13211702039553985,
"learning_rate": 1.667362863932792e-06,
"loss": 1.0373,
"step": 1627
},
{
"epoch": 4.163682864450128,
"grad_norm": 0.13148536889339357,
"learning_rate": 1.6575017397007898e-06,
"loss": 1.0529,
"step": 1628
},
{
"epoch": 4.166240409207161,
"grad_norm": 0.14114126711572433,
"learning_rate": 1.6476672266453087e-06,
"loss": 1.0568,
"step": 1629
},
{
"epoch": 4.168797953964194,
"grad_norm": 0.13504256421222302,
"learning_rate": 1.6378593561368017e-06,
"loss": 1.0424,
"step": 1630
},
{
"epoch": 4.171355498721228,
"grad_norm": 0.12899095401998986,
"learning_rate": 1.6280781594607364e-06,
"loss": 1.0637,
"step": 1631
},
{
"epoch": 4.173913043478261,
"grad_norm": 0.1264131779917514,
"learning_rate": 1.6183236678175029e-06,
"loss": 1.0407,
"step": 1632
},
{
"epoch": 4.176470588235294,
"grad_norm": 0.13782869294761288,
"learning_rate": 1.6085959123222994e-06,
"loss": 1.036,
"step": 1633
},
{
"epoch": 4.179028132992327,
"grad_norm": 0.140891816042728,
"learning_rate": 1.5988949240050344e-06,
"loss": 1.0314,
"step": 1634
},
{
"epoch": 4.181585677749361,
"grad_norm": 0.12917479657781017,
"learning_rate": 1.5892207338102494e-06,
"loss": 1.0493,
"step": 1635
},
{
"epoch": 4.1841432225063935,
"grad_norm": 0.1334411939557938,
"learning_rate": 1.5795733725969931e-06,
"loss": 1.0836,
"step": 1636
},
{
"epoch": 4.186700767263427,
"grad_norm": 0.142993534386663,
"learning_rate": 1.5699528711387358e-06,
"loss": 1.0341,
"step": 1637
},
{
"epoch": 4.189258312020461,
"grad_norm": 0.12912047709199104,
"learning_rate": 1.560359260123272e-06,
"loss": 1.0502,
"step": 1638
},
{
"epoch": 4.1918158567774935,
"grad_norm": 0.12884960069552234,
"learning_rate": 1.5507925701526184e-06,
"loss": 1.0323,
"step": 1639
},
{
"epoch": 4.194373401534527,
"grad_norm": 0.1289892440406385,
"learning_rate": 1.5412528317429197e-06,
"loss": 1.0248,
"step": 1640
},
{
"epoch": 4.19693094629156,
"grad_norm": 0.12221838744224985,
"learning_rate": 1.5317400753243449e-06,
"loss": 1.004,
"step": 1641
},
{
"epoch": 4.1994884910485935,
"grad_norm": 0.13486097471794437,
"learning_rate": 1.5222543312410042e-06,
"loss": 1.0532,
"step": 1642
},
{
"epoch": 4.202046035805626,
"grad_norm": 0.12829008561367278,
"learning_rate": 1.512795629750834e-06,
"loss": 1.009,
"step": 1643
},
{
"epoch": 4.20460358056266,
"grad_norm": 0.13061127802497013,
"learning_rate": 1.5033640010255146e-06,
"loss": 1.0518,
"step": 1644
},
{
"epoch": 4.207161125319693,
"grad_norm": 0.1357231506544221,
"learning_rate": 1.493959475150365e-06,
"loss": 1.0391,
"step": 1645
},
{
"epoch": 4.209718670076726,
"grad_norm": 0.12492335548008021,
"learning_rate": 1.484582082124254e-06,
"loss": 1.0183,
"step": 1646
},
{
"epoch": 4.21227621483376,
"grad_norm": 0.13080607014236745,
"learning_rate": 1.4752318518594988e-06,
"loss": 1.0214,
"step": 1647
},
{
"epoch": 4.2148337595907925,
"grad_norm": 0.13032141745435707,
"learning_rate": 1.4659088141817701e-06,
"loss": 1.0326,
"step": 1648
},
{
"epoch": 4.217391304347826,
"grad_norm": 0.1410760353481451,
"learning_rate": 1.4566129988300094e-06,
"loss": 1.0167,
"step": 1649
},
{
"epoch": 4.21994884910486,
"grad_norm": 0.12878198988086415,
"learning_rate": 1.4473444354563081e-06,
"loss": 1.0201,
"step": 1650
},
{
"epoch": 4.2225063938618925,
"grad_norm": 0.13730461890440382,
"learning_rate": 1.438103153625835e-06,
"loss": 1.0403,
"step": 1651
},
{
"epoch": 4.225063938618926,
"grad_norm": 0.1283690268065539,
"learning_rate": 1.4288891828167428e-06,
"loss": 1.0296,
"step": 1652
},
{
"epoch": 4.227621483375959,
"grad_norm": 0.13230399753509858,
"learning_rate": 1.4197025524200547e-06,
"loss": 1.0436,
"step": 1653
},
{
"epoch": 4.2301790281329925,
"grad_norm": 0.13610939627100485,
"learning_rate": 1.4105432917395912e-06,
"loss": 1.036,
"step": 1654
},
{
"epoch": 4.232736572890025,
"grad_norm": 0.1411030873308251,
"learning_rate": 1.4014114299918613e-06,
"loss": 1.0626,
"step": 1655
},
{
"epoch": 4.235294117647059,
"grad_norm": 0.1360722157833826,
"learning_rate": 1.3923069963059821e-06,
"loss": 1.037,
"step": 1656
},
{
"epoch": 4.2378516624040925,
"grad_norm": 0.13086138342111206,
"learning_rate": 1.3832300197235748e-06,
"loss": 1.0224,
"step": 1657
},
{
"epoch": 4.240409207161125,
"grad_norm": 0.13316912474292783,
"learning_rate": 1.3741805291986787e-06,
"loss": 1.0588,
"step": 1658
},
{
"epoch": 4.242966751918159,
"grad_norm": 0.12776448396795964,
"learning_rate": 1.3651585535976596e-06,
"loss": 1.0416,
"step": 1659
},
{
"epoch": 4.245524296675192,
"grad_norm": 0.13394602718641618,
"learning_rate": 1.3561641216991162e-06,
"loss": 1.0464,
"step": 1660
},
{
"epoch": 4.248081841432225,
"grad_norm": 0.12411528913176928,
"learning_rate": 1.3471972621937757e-06,
"loss": 1.0523,
"step": 1661
},
{
"epoch": 4.250639386189258,
"grad_norm": 0.13483004817710278,
"learning_rate": 1.3382580036844295e-06,
"loss": 1.0461,
"step": 1662
},
{
"epoch": 4.253196930946292,
"grad_norm": 0.13250722022034925,
"learning_rate": 1.3293463746858182e-06,
"loss": 1.027,
"step": 1663
},
{
"epoch": 4.255754475703325,
"grad_norm": 0.13098173123869175,
"learning_rate": 1.3204624036245506e-06,
"loss": 1.0253,
"step": 1664
},
{
"epoch": 4.258312020460358,
"grad_norm": 0.13628427441357657,
"learning_rate": 1.3116061188390084e-06,
"loss": 1.0299,
"step": 1665
},
{
"epoch": 4.260869565217392,
"grad_norm": 0.12506601980421145,
"learning_rate": 1.3027775485792682e-06,
"loss": 1.0309,
"step": 1666
},
{
"epoch": 4.263427109974424,
"grad_norm": 0.12809650463562688,
"learning_rate": 1.2939767210069876e-06,
"loss": 1.0433,
"step": 1667
},
{
"epoch": 4.265984654731458,
"grad_norm": 0.12820756645898626,
"learning_rate": 1.285203664195338e-06,
"loss": 0.9889,
"step": 1668
},
{
"epoch": 4.268542199488491,
"grad_norm": 0.13676696388260404,
"learning_rate": 1.2764584061289098e-06,
"loss": 1.0339,
"step": 1669
},
{
"epoch": 4.271099744245524,
"grad_norm": 0.13840454125887916,
"learning_rate": 1.267740974703614e-06,
"loss": 1.0461,
"step": 1670
},
{
"epoch": 4.273657289002558,
"grad_norm": 0.1154351492718522,
"learning_rate": 1.2590513977266007e-06,
"loss": 1.0214,
"step": 1671
},
{
"epoch": 4.276214833759591,
"grad_norm": 0.13166991117354376,
"learning_rate": 1.2503897029161716e-06,
"loss": 1.0329,
"step": 1672
},
{
"epoch": 4.278772378516624,
"grad_norm": 0.1321979634403043,
"learning_rate": 1.2417559179016835e-06,
"loss": 0.9865,
"step": 1673
},
{
"epoch": 4.281329923273657,
"grad_norm": 0.13877049369386268,
"learning_rate": 1.2331500702234723e-06,
"loss": 1.0293,
"step": 1674
},
{
"epoch": 4.283887468030691,
"grad_norm": 0.12752281245986202,
"learning_rate": 1.2245721873327521e-06,
"loss": 1.0458,
"step": 1675
},
{
"epoch": 4.286445012787723,
"grad_norm": 0.12343044689847779,
"learning_rate": 1.2160222965915404e-06,
"loss": 1.0281,
"step": 1676
},
{
"epoch": 4.289002557544757,
"grad_norm": 0.12611866524321558,
"learning_rate": 1.207500425272562e-06,
"loss": 1.0467,
"step": 1677
},
{
"epoch": 4.291560102301791,
"grad_norm": 0.12003173247581543,
"learning_rate": 1.199006600559156e-06,
"loss": 1.0456,
"step": 1678
},
{
"epoch": 4.294117647058823,
"grad_norm": 0.1307538379654529,
"learning_rate": 1.190540849545213e-06,
"loss": 1.0326,
"step": 1679
},
{
"epoch": 4.296675191815857,
"grad_norm": 0.12722242311205958,
"learning_rate": 1.1821031992350628e-06,
"loss": 1.0506,
"step": 1680
},
{
"epoch": 4.29923273657289,
"grad_norm": 0.12736209379546135,
"learning_rate": 1.1736936765434005e-06,
"loss": 1.0218,
"step": 1681
},
{
"epoch": 4.301790281329923,
"grad_norm": 0.12638559752999246,
"learning_rate": 1.1653123082951968e-06,
"loss": 1.0717,
"step": 1682
},
{
"epoch": 4.304347826086957,
"grad_norm": 0.1383277702988731,
"learning_rate": 1.1569591212256237e-06,
"loss": 1.0487,
"step": 1683
},
{
"epoch": 4.30690537084399,
"grad_norm": 0.12792509279371292,
"learning_rate": 1.1486341419799474e-06,
"loss": 1.0735,
"step": 1684
},
{
"epoch": 4.309462915601023,
"grad_norm": 0.11817435751394731,
"learning_rate": 1.1403373971134623e-06,
"loss": 1.0211,
"step": 1685
},
{
"epoch": 4.312020460358056,
"grad_norm": 0.12075851868919982,
"learning_rate": 1.132068913091402e-06,
"loss": 1.0547,
"step": 1686
},
{
"epoch": 4.31457800511509,
"grad_norm": 0.12419038252191225,
"learning_rate": 1.1238287162888483e-06,
"loss": 1.0141,
"step": 1687
},
{
"epoch": 4.3171355498721224,
"grad_norm": 0.12503779001905366,
"learning_rate": 1.1156168329906536e-06,
"loss": 1.0115,
"step": 1688
},
{
"epoch": 4.319693094629156,
"grad_norm": 0.12357405258717082,
"learning_rate": 1.1074332893913541e-06,
"loss": 1.0183,
"step": 1689
},
{
"epoch": 4.322250639386189,
"grad_norm": 0.12336501389642063,
"learning_rate": 1.0992781115950867e-06,
"loss": 1.0817,
"step": 1690
},
{
"epoch": 4.324808184143222,
"grad_norm": 0.1237037130184548,
"learning_rate": 1.0911513256155094e-06,
"loss": 1.0305,
"step": 1691
},
{
"epoch": 4.327365728900256,
"grad_norm": 0.12122352134815065,
"learning_rate": 1.0830529573757076e-06,
"loss": 1.0271,
"step": 1692
},
{
"epoch": 4.329923273657289,
"grad_norm": 0.125450807160178,
"learning_rate": 1.074983032708129e-06,
"loss": 1.0426,
"step": 1693
},
{
"epoch": 4.332480818414322,
"grad_norm": 0.1331817263523311,
"learning_rate": 1.0669415773544867e-06,
"loss": 1.0339,
"step": 1694
},
{
"epoch": 4.335038363171355,
"grad_norm": 0.12379967651287854,
"learning_rate": 1.0589286169656743e-06,
"loss": 1.021,
"step": 1695
},
{
"epoch": 4.337595907928389,
"grad_norm": 0.1256760216863504,
"learning_rate": 1.0509441771017026e-06,
"loss": 1.063,
"step": 1696
},
{
"epoch": 4.340153452685422,
"grad_norm": 0.12701844597546846,
"learning_rate": 1.0429882832316008e-06,
"loss": 1.0279,
"step": 1697
},
{
"epoch": 4.342710997442455,
"grad_norm": 0.11989925917845673,
"learning_rate": 1.0350609607333384e-06,
"loss": 1.0053,
"step": 1698
},
{
"epoch": 4.345268542199489,
"grad_norm": 0.12375987829879317,
"learning_rate": 1.0271622348937581e-06,
"loss": 1.0438,
"step": 1699
},
{
"epoch": 4.3478260869565215,
"grad_norm": 0.1270476044771331,
"learning_rate": 1.0192921309084703e-06,
"loss": 1.0407,
"step": 1700
},
{
"epoch": 4.350383631713555,
"grad_norm": 0.12555015007408019,
"learning_rate": 1.0114506738817942e-06,
"loss": 1.0031,
"step": 1701
},
{
"epoch": 4.352941176470588,
"grad_norm": 0.12622543787693985,
"learning_rate": 1.0036378888266663e-06,
"loss": 1.0547,
"step": 1702
},
{
"epoch": 4.3554987212276215,
"grad_norm": 0.12762154218606617,
"learning_rate": 9.958538006645702e-07,
"loss": 1.0687,
"step": 1703
},
{
"epoch": 4.358056265984655,
"grad_norm": 0.12475219304030633,
"learning_rate": 9.880984342254462e-07,
"loss": 1.021,
"step": 1704
},
{
"epoch": 4.360613810741688,
"grad_norm": 0.1298726344994412,
"learning_rate": 9.803718142476182e-07,
"loss": 1.0392,
"step": 1705
},
{
"epoch": 4.3631713554987215,
"grad_norm": 0.12364003006997323,
"learning_rate": 9.72673965377714e-07,
"loss": 1.0513,
"step": 1706
},
{
"epoch": 4.365728900255754,
"grad_norm": 0.1285635408520734,
"learning_rate": 9.650049121705851e-07,
"loss": 1.0409,
"step": 1707
},
{
"epoch": 4.368286445012788,
"grad_norm": 0.1258885386792609,
"learning_rate": 9.573646790892299e-07,
"loss": 1.027,
"step": 1708
},
{
"epoch": 4.370843989769821,
"grad_norm": 0.1187303423804672,
"learning_rate": 9.497532905047202e-07,
"loss": 1.0534,
"step": 1709
},
{
"epoch": 4.373401534526854,
"grad_norm": 0.12469445611611187,
"learning_rate": 9.421707706961136e-07,
"loss": 1.0401,
"step": 1710
},
{
"epoch": 4.375959079283888,
"grad_norm": 0.12581258682849217,
"learning_rate": 9.346171438503781e-07,
"loss": 1.0642,
"step": 1711
},
{
"epoch": 4.378516624040921,
"grad_norm": 0.12336801659179744,
"learning_rate": 9.270924340623267e-07,
"loss": 1.0648,
"step": 1712
},
{
"epoch": 4.381074168797954,
"grad_norm": 0.12013777856733562,
"learning_rate": 9.195966653345256e-07,
"loss": 1.0287,
"step": 1713
},
{
"epoch": 4.383631713554987,
"grad_norm": 0.1240880814390023,
"learning_rate": 9.121298615772256e-07,
"loss": 1.0504,
"step": 1714
},
{
"epoch": 4.3861892583120206,
"grad_norm": 0.11807776342242135,
"learning_rate": 9.046920466082809e-07,
"loss": 1.0471,
"step": 1715
},
{
"epoch": 4.388746803069053,
"grad_norm": 0.11769299130070347,
"learning_rate": 8.972832441530876e-07,
"loss": 1.0341,
"step": 1716
},
{
"epoch": 4.391304347826087,
"grad_norm": 0.12193499241391831,
"learning_rate": 8.899034778444804e-07,
"loss": 1.0735,
"step": 1717
},
{
"epoch": 4.3938618925831205,
"grad_norm": 0.12571448070016797,
"learning_rate": 8.825527712226834e-07,
"loss": 1.0145,
"step": 1718
},
{
"epoch": 4.396419437340153,
"grad_norm": 0.11812287728798011,
"learning_rate": 8.75231147735226e-07,
"loss": 1.0255,
"step": 1719
},
{
"epoch": 4.398976982097187,
"grad_norm": 0.11941179582628143,
"learning_rate": 8.679386307368631e-07,
"loss": 1.0486,
"step": 1720
},
{
"epoch": 4.40153452685422,
"grad_norm": 0.1243184329514753,
"learning_rate": 8.60675243489506e-07,
"loss": 1.0663,
"step": 1721
},
{
"epoch": 4.404092071611253,
"grad_norm": 0.11711236888037205,
"learning_rate": 8.534410091621481e-07,
"loss": 1.0517,
"step": 1722
},
{
"epoch": 4.406649616368286,
"grad_norm": 0.12398332201899291,
"learning_rate": 8.462359508307882e-07,
"loss": 1.0563,
"step": 1723
},
{
"epoch": 4.40920716112532,
"grad_norm": 0.12262204617331557,
"learning_rate": 8.390600914783597e-07,
"loss": 1.0228,
"step": 1724
},
{
"epoch": 4.411764705882353,
"grad_norm": 0.1182059276608206,
"learning_rate": 8.319134539946549e-07,
"loss": 1.0391,
"step": 1725
},
{
"epoch": 4.414322250639386,
"grad_norm": 0.12345372785960933,
"learning_rate": 8.247960611762563e-07,
"loss": 1.0388,
"step": 1726
},
{
"epoch": 4.41687979539642,
"grad_norm": 0.12839333147920715,
"learning_rate": 8.177079357264583e-07,
"loss": 1.0282,
"step": 1727
},
{
"epoch": 4.419437340153452,
"grad_norm": 0.12729581387520422,
"learning_rate": 8.106491002551941e-07,
"loss": 1.0262,
"step": 1728
},
{
"epoch": 4.421994884910486,
"grad_norm": 0.12208859639468621,
"learning_rate": 8.036195772789735e-07,
"loss": 1.0334,
"step": 1729
},
{
"epoch": 4.42455242966752,
"grad_norm": 0.12356081440190549,
"learning_rate": 7.966193892208007e-07,
"loss": 1.0738,
"step": 1730
},
{
"epoch": 4.427109974424552,
"grad_norm": 0.1179560690186426,
"learning_rate": 7.896485584101066e-07,
"loss": 1.0214,
"step": 1731
},
{
"epoch": 4.429667519181586,
"grad_norm": 0.12396501408128464,
"learning_rate": 7.827071070826775e-07,
"loss": 1.0101,
"step": 1732
},
{
"epoch": 4.432225063938619,
"grad_norm": 0.120435484140843,
"learning_rate": 7.757950573805839e-07,
"loss": 1.0448,
"step": 1733
},
{
"epoch": 4.434782608695652,
"grad_norm": 0.1288542576587824,
"learning_rate": 7.689124313521112e-07,
"loss": 1.028,
"step": 1734
},
{
"epoch": 4.437340153452685,
"grad_norm": 0.11947326921621014,
"learning_rate": 7.620592509516845e-07,
"loss": 1.0508,
"step": 1735
},
{
"epoch": 4.439897698209719,
"grad_norm": 0.12201218897189074,
"learning_rate": 7.552355380398079e-07,
"loss": 1.0709,
"step": 1736
},
{
"epoch": 4.442455242966752,
"grad_norm": 0.12421373397429394,
"learning_rate": 7.484413143829861e-07,
"loss": 1.0328,
"step": 1737
},
{
"epoch": 4.445012787723785,
"grad_norm": 0.12410163367364695,
"learning_rate": 7.41676601653657e-07,
"loss": 1.034,
"step": 1738
},
{
"epoch": 4.447570332480819,
"grad_norm": 0.1219420965833109,
"learning_rate": 7.349414214301242e-07,
"loss": 1.0525,
"step": 1739
},
{
"epoch": 4.450127877237851,
"grad_norm": 0.11735248664674708,
"learning_rate": 7.282357951964903e-07,
"loss": 1.006,
"step": 1740
},
{
"epoch": 4.452685421994885,
"grad_norm": 0.11694083667726769,
"learning_rate": 7.215597443425815e-07,
"loss": 1.0249,
"step": 1741
},
{
"epoch": 4.455242966751918,
"grad_norm": 0.11713103311193784,
"learning_rate": 7.149132901638844e-07,
"loss": 1.0712,
"step": 1742
},
{
"epoch": 4.457800511508951,
"grad_norm": 0.11740763151594824,
"learning_rate": 7.082964538614823e-07,
"loss": 1.0242,
"step": 1743
},
{
"epoch": 4.460358056265985,
"grad_norm": 0.11802743122673677,
"learning_rate": 7.017092565419748e-07,
"loss": 1.0311,
"step": 1744
},
{
"epoch": 4.462915601023018,
"grad_norm": 0.11497098419518056,
"learning_rate": 6.951517192174195e-07,
"loss": 1.041,
"step": 1745
},
{
"epoch": 4.465473145780051,
"grad_norm": 0.11725056660448066,
"learning_rate": 6.886238628052711e-07,
"loss": 1.0462,
"step": 1746
},
{
"epoch": 4.468030690537084,
"grad_norm": 0.11844411179617265,
"learning_rate": 6.821257081282973e-07,
"loss": 1.0311,
"step": 1747
},
{
"epoch": 4.470588235294118,
"grad_norm": 0.11969749025311724,
"learning_rate": 6.756572759145285e-07,
"loss": 1.0362,
"step": 1748
},
{
"epoch": 4.4731457800511505,
"grad_norm": 0.12100274315376988,
"learning_rate": 6.692185867971834e-07,
"loss": 1.0398,
"step": 1749
},
{
"epoch": 4.475703324808184,
"grad_norm": 0.1189550665367411,
"learning_rate": 6.62809661314604e-07,
"loss": 1.0647,
"step": 1750
},
{
"epoch": 4.478260869565218,
"grad_norm": 0.12364355910534239,
"learning_rate": 6.564305199101939e-07,
"loss": 1.0287,
"step": 1751
},
{
"epoch": 4.4808184143222505,
"grad_norm": 0.11726566582294938,
"learning_rate": 6.500811829323462e-07,
"loss": 1.0455,
"step": 1752
},
{
"epoch": 4.483375959079284,
"grad_norm": 0.11446881967048579,
"learning_rate": 6.437616706343896e-07,
"loss": 1.0569,
"step": 1753
},
{
"epoch": 4.485933503836317,
"grad_norm": 0.12374756246454661,
"learning_rate": 6.374720031745129e-07,
"loss": 1.058,
"step": 1754
},
{
"epoch": 4.4884910485933505,
"grad_norm": 0.1233951395541208,
"learning_rate": 6.312122006157006e-07,
"loss": 1.0319,
"step": 1755
},
{
"epoch": 4.491048593350383,
"grad_norm": 0.11976730576289767,
"learning_rate": 6.249822829256835e-07,
"loss": 1.0455,
"step": 1756
},
{
"epoch": 4.493606138107417,
"grad_norm": 0.11824907431040846,
"learning_rate": 6.187822699768553e-07,
"loss": 1.0464,
"step": 1757
},
{
"epoch": 4.4961636828644505,
"grad_norm": 0.11525969916785428,
"learning_rate": 6.126121815462228e-07,
"loss": 1.0205,
"step": 1758
},
{
"epoch": 4.498721227621483,
"grad_norm": 0.13175731720889955,
"learning_rate": 6.064720373153365e-07,
"loss": 1.0062,
"step": 1759
},
{
"epoch": 4.501278772378517,
"grad_norm": 0.12453743339788283,
"learning_rate": 6.003618568702352e-07,
"loss": 1.0587,
"step": 1760
},
{
"epoch": 4.5038363171355495,
"grad_norm": 0.11732654328622537,
"learning_rate": 5.942816597013712e-07,
"loss": 1.0516,
"step": 1761
},
{
"epoch": 4.506393861892583,
"grad_norm": 0.12027453268886372,
"learning_rate": 5.882314652035582e-07,
"loss": 1.0645,
"step": 1762
},
{
"epoch": 4.508951406649617,
"grad_norm": 0.1233241454074132,
"learning_rate": 5.822112926759072e-07,
"loss": 1.0491,
"step": 1763
},
{
"epoch": 4.5115089514066495,
"grad_norm": 0.11543180230907084,
"learning_rate": 5.762211613217649e-07,
"loss": 1.0235,
"step": 1764
},
{
"epoch": 4.514066496163683,
"grad_norm": 0.1161090396637108,
"learning_rate": 5.702610902486472e-07,
"loss": 1.0396,
"step": 1765
},
{
"epoch": 4.516624040920716,
"grad_norm": 0.11434106483636258,
"learning_rate": 5.643310984681882e-07,
"loss": 1.0253,
"step": 1766
},
{
"epoch": 4.5191815856777495,
"grad_norm": 0.12772671626242307,
"learning_rate": 5.584312048960705e-07,
"loss": 1.0563,
"step": 1767
},
{
"epoch": 4.521739130434782,
"grad_norm": 0.12357938851666896,
"learning_rate": 5.525614283519698e-07,
"loss": 1.054,
"step": 1768
},
{
"epoch": 4.524296675191816,
"grad_norm": 0.12191915599526636,
"learning_rate": 5.46721787559491e-07,
"loss": 1.0103,
"step": 1769
},
{
"epoch": 4.526854219948849,
"grad_norm": 0.11728270071784068,
"learning_rate": 5.40912301146116e-07,
"loss": 1.0371,
"step": 1770
},
{
"epoch": 4.529411764705882,
"grad_norm": 0.1171100966224759,
"learning_rate": 5.351329876431377e-07,
"loss": 1.031,
"step": 1771
},
{
"epoch": 4.531969309462916,
"grad_norm": 0.1205942913894916,
"learning_rate": 5.293838654855965e-07,
"loss": 1.0368,
"step": 1772
},
{
"epoch": 4.534526854219949,
"grad_norm": 0.11538796588212798,
"learning_rate": 5.236649530122362e-07,
"loss": 1.0234,
"step": 1773
},
{
"epoch": 4.537084398976982,
"grad_norm": 0.11552252830049363,
"learning_rate": 5.17976268465431e-07,
"loss": 1.0268,
"step": 1774
},
{
"epoch": 4.539641943734015,
"grad_norm": 0.12030123767608153,
"learning_rate": 5.123178299911357e-07,
"loss": 1.0161,
"step": 1775
},
{
"epoch": 4.542199488491049,
"grad_norm": 0.11733012254657782,
"learning_rate": 5.066896556388223e-07,
"loss": 1.0263,
"step": 1776
},
{
"epoch": 4.544757033248082,
"grad_norm": 0.12261186958150777,
"learning_rate": 5.010917633614298e-07,
"loss": 1.0433,
"step": 1777
},
{
"epoch": 4.547314578005115,
"grad_norm": 0.11969607011170212,
"learning_rate": 4.95524171015298e-07,
"loss": 1.0548,
"step": 1778
},
{
"epoch": 4.549872122762149,
"grad_norm": 0.12029153180895684,
"learning_rate": 4.899868963601173e-07,
"loss": 1.0387,
"step": 1779
},
{
"epoch": 4.552429667519181,
"grad_norm": 0.11614133716710796,
"learning_rate": 4.844799570588699e-07,
"loss": 1.031,
"step": 1780
},
{
"epoch": 4.554987212276215,
"grad_norm": 0.11916764474488396,
"learning_rate": 4.79003370677773e-07,
"loss": 1.0628,
"step": 1781
},
{
"epoch": 4.557544757033249,
"grad_norm": 0.11805084554309808,
"learning_rate": 4.7355715468622164e-07,
"loss": 1.0366,
"step": 1782
},
{
"epoch": 4.560102301790281,
"grad_norm": 0.12003861008176886,
"learning_rate": 4.6814132645673584e-07,
"loss": 1.0908,
"step": 1783
},
{
"epoch": 4.562659846547315,
"grad_norm": 0.1148544867733163,
"learning_rate": 4.6275590326490316e-07,
"loss": 1.0109,
"step": 1784
},
{
"epoch": 4.565217391304348,
"grad_norm": 0.11850485924591762,
"learning_rate": 4.5740090228932554e-07,
"loss": 1.0137,
"step": 1785
},
{
"epoch": 4.567774936061381,
"grad_norm": 0.12073176991107863,
"learning_rate": 4.5207634061155913e-07,
"loss": 1.0203,
"step": 1786
},
{
"epoch": 4.570332480818414,
"grad_norm": 0.11565168377707126,
"learning_rate": 4.467822352160722e-07,
"loss": 1.0322,
"step": 1787
},
{
"epoch": 4.572890025575448,
"grad_norm": 0.11767773542643316,
"learning_rate": 4.415186029901719e-07,
"loss": 1.021,
"step": 1788
},
{
"epoch": 4.57544757033248,
"grad_norm": 0.11903289285879093,
"learning_rate": 4.3628546072396525e-07,
"loss": 1.0747,
"step": 1789
},
{
"epoch": 4.578005115089514,
"grad_norm": 0.12099267853278806,
"learning_rate": 4.310828251103072e-07,
"loss": 1.0488,
"step": 1790
},
{
"epoch": 4.580562659846548,
"grad_norm": 0.11812503754866224,
"learning_rate": 4.2591071274473484e-07,
"loss": 1.0362,
"step": 1791
},
{
"epoch": 4.58312020460358,
"grad_norm": 0.11817672051919005,
"learning_rate": 4.2076914012542105e-07,
"loss": 1.037,
"step": 1792
},
{
"epoch": 4.585677749360614,
"grad_norm": 0.11967377201350358,
"learning_rate": 4.1565812365312654e-07,
"loss": 1.0303,
"step": 1793
},
{
"epoch": 4.588235294117647,
"grad_norm": 0.12091871976659212,
"learning_rate": 4.105776796311389e-07,
"loss": 1.0411,
"step": 1794
},
{
"epoch": 4.59079283887468,
"grad_norm": 0.11889200883802002,
"learning_rate": 4.055278242652272e-07,
"loss": 1.0201,
"step": 1795
},
{
"epoch": 4.593350383631714,
"grad_norm": 0.11404037707431111,
"learning_rate": 4.00508573663585e-07,
"loss": 1.0326,
"step": 1796
},
{
"epoch": 4.595907928388747,
"grad_norm": 0.11895441005803606,
"learning_rate": 3.955199438367874e-07,
"loss": 1.0401,
"step": 1797
},
{
"epoch": 4.59846547314578,
"grad_norm": 0.11452304569258381,
"learning_rate": 3.9056195069772873e-07,
"loss": 1.0168,
"step": 1798
},
{
"epoch": 4.601023017902813,
"grad_norm": 0.11818309537389297,
"learning_rate": 3.85634610061576e-07,
"loss": 1.025,
"step": 1799
},
{
"epoch": 4.603580562659847,
"grad_norm": 0.1177738878198216,
"learning_rate": 3.807379376457276e-07,
"loss": 1.0579,
"step": 1800
},
{
"epoch": 4.6061381074168795,
"grad_norm": 0.11760050731022088,
"learning_rate": 3.758719490697493e-07,
"loss": 1.0162,
"step": 1801
},
{
"epoch": 4.608695652173913,
"grad_norm": 0.11692046035536714,
"learning_rate": 3.710366598553328e-07,
"loss": 1.0064,
"step": 1802
},
{
"epoch": 4.611253196930946,
"grad_norm": 0.11817659321984543,
"learning_rate": 3.6623208542624134e-07,
"loss": 1.0317,
"step": 1803
},
{
"epoch": 4.6138107416879794,
"grad_norm": 0.11416484517518209,
"learning_rate": 3.61458241108269e-07,
"loss": 0.9979,
"step": 1804
},
{
"epoch": 4.616368286445013,
"grad_norm": 0.11317634968030488,
"learning_rate": 3.567151421291781e-07,
"loss": 1.0428,
"step": 1805
},
{
"epoch": 4.618925831202046,
"grad_norm": 0.12015756336365767,
"learning_rate": 3.520028036186629e-07,
"loss": 1.0055,
"step": 1806
},
{
"epoch": 4.621483375959079,
"grad_norm": 0.11708694204425783,
"learning_rate": 3.473212406082993e-07,
"loss": 1.0358,
"step": 1807
},
{
"epoch": 4.624040920716112,
"grad_norm": 0.12291270689470975,
"learning_rate": 3.426704680314896e-07,
"loss": 1.0818,
"step": 1808
},
{
"epoch": 4.626598465473146,
"grad_norm": 0.12218447911853864,
"learning_rate": 3.380505007234225e-07,
"loss": 1.0499,
"step": 1809
},
{
"epoch": 4.629156010230179,
"grad_norm": 0.1197028476607302,
"learning_rate": 3.334613534210218e-07,
"loss": 1.0368,
"step": 1810
},
{
"epoch": 4.631713554987212,
"grad_norm": 0.11611382742011438,
"learning_rate": 3.2890304076290124e-07,
"loss": 1.0364,
"step": 1811
},
{
"epoch": 4.634271099744246,
"grad_norm": 0.11714111776328456,
"learning_rate": 3.2437557728931643e-07,
"loss": 1.0657,
"step": 1812
},
{
"epoch": 4.6368286445012785,
"grad_norm": 0.11376983368069393,
"learning_rate": 3.1987897744212073e-07,
"loss": 1.0011,
"step": 1813
},
{
"epoch": 4.639386189258312,
"grad_norm": 0.11405249072962266,
"learning_rate": 3.154132555647171e-07,
"loss": 1.0713,
"step": 1814
},
{
"epoch": 4.641943734015345,
"grad_norm": 0.1199549787481166,
"learning_rate": 3.1097842590201433e-07,
"loss": 1.0622,
"step": 1815
},
{
"epoch": 4.6445012787723785,
"grad_norm": 0.11926673117091068,
"learning_rate": 3.0657450260037303e-07,
"loss": 1.0629,
"step": 1816
},
{
"epoch": 4.647058823529412,
"grad_norm": 0.12139769893175593,
"learning_rate": 3.022014997075795e-07,
"loss": 1.0594,
"step": 1817
},
{
"epoch": 4.649616368286445,
"grad_norm": 0.11681143235855584,
"learning_rate": 2.9785943117277894e-07,
"loss": 1.0469,
"step": 1818
},
{
"epoch": 4.6521739130434785,
"grad_norm": 0.12421776159811096,
"learning_rate": 2.935483108464465e-07,
"loss": 1.0224,
"step": 1819
},
{
"epoch": 4.654731457800511,
"grad_norm": 0.11231911224982111,
"learning_rate": 2.8926815248033535e-07,
"loss": 1.0112,
"step": 1820
},
{
"epoch": 4.657289002557545,
"grad_norm": 0.11708199653029536,
"learning_rate": 2.8501896972743747e-07,
"loss": 1.0105,
"step": 1821
},
{
"epoch": 4.659846547314578,
"grad_norm": 0.11649971834696357,
"learning_rate": 2.808007761419351e-07,
"loss": 1.0697,
"step": 1822
},
{
"epoch": 4.662404092071611,
"grad_norm": 0.11071167386647211,
"learning_rate": 2.766135851791607e-07,
"loss": 1.0141,
"step": 1823
},
{
"epoch": 4.664961636828645,
"grad_norm": 0.12010263976141954,
"learning_rate": 2.7245741019555573e-07,
"loss": 1.0282,
"step": 1824
},
{
"epoch": 4.667519181585678,
"grad_norm": 0.1151865695779186,
"learning_rate": 2.6833226444862526e-07,
"loss": 1.0299,
"step": 1825
},
{
"epoch": 4.670076726342711,
"grad_norm": 0.11255028443601578,
"learning_rate": 2.642381610968936e-07,
"loss": 1.0267,
"step": 1826
},
{
"epoch": 4.672634271099744,
"grad_norm": 0.11904179423196315,
"learning_rate": 2.6017511319986753e-07,
"loss": 1.029,
"step": 1827
},
{
"epoch": 4.675191815856778,
"grad_norm": 0.11156796619875065,
"learning_rate": 2.5614313371799203e-07,
"loss": 1.0193,
"step": 1828
},
{
"epoch": 4.677749360613811,
"grad_norm": 0.12152103248098621,
"learning_rate": 2.5214223551260686e-07,
"loss": 1.0267,
"step": 1829
},
{
"epoch": 4.680306905370844,
"grad_norm": 0.12044476016060106,
"learning_rate": 2.4817243134591106e-07,
"loss": 1.0524,
"step": 1830
},
{
"epoch": 4.6828644501278776,
"grad_norm": 0.1165747082957651,
"learning_rate": 2.4423373388091755e-07,
"loss": 1.0347,
"step": 1831
},
{
"epoch": 4.68542199488491,
"grad_norm": 0.11850587011434784,
"learning_rate": 2.403261556814118e-07,
"loss": 1.0568,
"step": 1832
},
{
"epoch": 4.687979539641944,
"grad_norm": 0.1162877587424683,
"learning_rate": 2.3644970921191447e-07,
"loss": 1.0266,
"step": 1833
},
{
"epoch": 4.690537084398977,
"grad_norm": 0.12535561464481632,
"learning_rate": 2.3260440683764653e-07,
"loss": 1.0845,
"step": 1834
},
{
"epoch": 4.69309462915601,
"grad_norm": 0.1218176284645347,
"learning_rate": 2.2879026082447743e-07,
"loss": 1.0469,
"step": 1835
},
{
"epoch": 4.695652173913043,
"grad_norm": 0.11820198842847074,
"learning_rate": 2.250072833388972e-07,
"loss": 1.0585,
"step": 1836
},
{
"epoch": 4.698209718670077,
"grad_norm": 0.12029732293646825,
"learning_rate": 2.2125548644797322e-07,
"loss": 1.0422,
"step": 1837
},
{
"epoch": 4.70076726342711,
"grad_norm": 0.11483889783410742,
"learning_rate": 2.1753488211931017e-07,
"loss": 1.0095,
"step": 1838
},
{
"epoch": 4.703324808184143,
"grad_norm": 0.11736543180370013,
"learning_rate": 2.1384548222101342e-07,
"loss": 1.0064,
"step": 1839
},
{
"epoch": 4.705882352941177,
"grad_norm": 0.11729827431422608,
"learning_rate": 2.1018729852165575e-07,
"loss": 1.0682,
"step": 1840
},
{
"epoch": 4.708439897698209,
"grad_norm": 0.11626920918028295,
"learning_rate": 2.0656034269022961e-07,
"loss": 1.0267,
"step": 1841
},
{
"epoch": 4.710997442455243,
"grad_norm": 0.11821893661532155,
"learning_rate": 2.0296462629611934e-07,
"loss": 1.0235,
"step": 1842
},
{
"epoch": 4.713554987212277,
"grad_norm": 0.11027628288597482,
"learning_rate": 1.9940016080906122e-07,
"loss": 1.0249,
"step": 1843
},
{
"epoch": 4.716112531969309,
"grad_norm": 0.11583827201970737,
"learning_rate": 1.9586695759910235e-07,
"loss": 1.0477,
"step": 1844
},
{
"epoch": 4.718670076726343,
"grad_norm": 0.11248702023779261,
"learning_rate": 1.9236502793657297e-07,
"loss": 1.0441,
"step": 1845
},
{
"epoch": 4.721227621483376,
"grad_norm": 0.1240044200990586,
"learning_rate": 1.888943829920431e-07,
"loss": 1.0336,
"step": 1846
},
{
"epoch": 4.723785166240409,
"grad_norm": 0.11690696902623407,
"learning_rate": 1.854550338362915e-07,
"loss": 1.0376,
"step": 1847
},
{
"epoch": 4.726342710997442,
"grad_norm": 0.11486713464937727,
"learning_rate": 1.8204699144026894e-07,
"loss": 1.0689,
"step": 1848
},
{
"epoch": 4.728900255754476,
"grad_norm": 0.11581909664334852,
"learning_rate": 1.7867026667505726e-07,
"loss": 1.0672,
"step": 1849
},
{
"epoch": 4.731457800511509,
"grad_norm": 0.11440636945394728,
"learning_rate": 1.753248703118482e-07,
"loss": 1.034,
"step": 1850
},
{
"epoch": 4.734015345268542,
"grad_norm": 0.1145247227720534,
"learning_rate": 1.720108130218967e-07,
"loss": 1.0355,
"step": 1851
},
{
"epoch": 4.736572890025576,
"grad_norm": 0.11936327466725484,
"learning_rate": 1.6872810537649332e-07,
"loss": 1.0274,
"step": 1852
},
{
"epoch": 4.739130434782608,
"grad_norm": 0.1191110933377237,
"learning_rate": 1.6547675784692517e-07,
"loss": 1.0707,
"step": 1853
},
{
"epoch": 4.741687979539642,
"grad_norm": 0.11898800646585839,
"learning_rate": 1.6225678080444952e-07,
"loss": 1.0631,
"step": 1854
},
{
"epoch": 4.744245524296675,
"grad_norm": 0.11617957331470609,
"learning_rate": 1.5906818452025464e-07,
"loss": 1.0394,
"step": 1855
},
{
"epoch": 4.746803069053708,
"grad_norm": 0.11575268445319527,
"learning_rate": 1.559109791654301e-07,
"loss": 1.0059,
"step": 1856
},
{
"epoch": 4.749360613810742,
"grad_norm": 0.11400146363398818,
"learning_rate": 1.5278517481093436e-07,
"loss": 1.0268,
"step": 1857
},
{
"epoch": 4.751918158567775,
"grad_norm": 0.11361459986982794,
"learning_rate": 1.4969078142756276e-07,
"loss": 1.0565,
"step": 1858
},
{
"epoch": 4.754475703324808,
"grad_norm": 0.11718329814715675,
"learning_rate": 1.4662780888591078e-07,
"loss": 1.0271,
"step": 1859
},
{
"epoch": 4.757033248081841,
"grad_norm": 0.11412559030858926,
"learning_rate": 1.4359626695635176e-07,
"loss": 1.0529,
"step": 1860
},
{
"epoch": 4.759590792838875,
"grad_norm": 0.1149335211731899,
"learning_rate": 1.405961653089971e-07,
"loss": 1.047,
"step": 1861
},
{
"epoch": 4.762148337595908,
"grad_norm": 0.12700071915120056,
"learning_rate": 1.3762751351367066e-07,
"loss": 1.0394,
"step": 1862
},
{
"epoch": 4.764705882352941,
"grad_norm": 0.11612798778465196,
"learning_rate": 1.3469032103987534e-07,
"loss": 1.0545,
"step": 1863
},
{
"epoch": 4.767263427109975,
"grad_norm": 0.12026346999851885,
"learning_rate": 1.3178459725676552e-07,
"loss": 1.0633,
"step": 1864
},
{
"epoch": 4.7698209718670075,
"grad_norm": 0.1154062718622743,
"learning_rate": 1.289103514331147e-07,
"loss": 1.0257,
"step": 1865
},
{
"epoch": 4.772378516624041,
"grad_norm": 0.1196571096618875,
"learning_rate": 1.2606759273728563e-07,
"loss": 1.0532,
"step": 1866
},
{
"epoch": 4.774936061381074,
"grad_norm": 0.11924573106561724,
"learning_rate": 1.2325633023720695e-07,
"loss": 1.0275,
"step": 1867
},
{
"epoch": 4.7774936061381075,
"grad_norm": 0.11270811144881691,
"learning_rate": 1.2047657290033322e-07,
"loss": 1.0286,
"step": 1868
},
{
"epoch": 4.78005115089514,
"grad_norm": 0.1161070504851422,
"learning_rate": 1.1772832959362934e-07,
"loss": 1.0433,
"step": 1869
},
{
"epoch": 4.782608695652174,
"grad_norm": 0.11545585799058032,
"learning_rate": 1.150116090835307e-07,
"loss": 1.0332,
"step": 1870
},
{
"epoch": 4.7851662404092075,
"grad_norm": 0.1152683133795509,
"learning_rate": 1.1232642003592198e-07,
"loss": 1.0849,
"step": 1871
},
{
"epoch": 4.78772378516624,
"grad_norm": 0.11412468149661283,
"learning_rate": 1.096727710161094e-07,
"loss": 1.0167,
"step": 1872
},
{
"epoch": 4.790281329923274,
"grad_norm": 0.1180180215345883,
"learning_rate": 1.0705067048878859e-07,
"loss": 1.0227,
"step": 1873
},
{
"epoch": 4.792838874680307,
"grad_norm": 0.11718614653864518,
"learning_rate": 1.0446012681802342e-07,
"loss": 1.0085,
"step": 1874
},
{
"epoch": 4.79539641943734,
"grad_norm": 0.11364381432368652,
"learning_rate": 1.0190114826721498e-07,
"loss": 1.0399,
"step": 1875
},
{
"epoch": 4.797953964194374,
"grad_norm": 0.11712192627428837,
"learning_rate": 9.937374299907931e-08,
"loss": 1.0065,
"step": 1876
},
{
"epoch": 4.8005115089514065,
"grad_norm": 0.11451658146251059,
"learning_rate": 9.687791907561528e-08,
"loss": 1.0496,
"step": 1877
},
{
"epoch": 4.80306905370844,
"grad_norm": 0.11508044552253341,
"learning_rate": 9.441368445808452e-08,
"loss": 1.0378,
"step": 1878
},
{
"epoch": 4.805626598465473,
"grad_norm": 0.11151643216416461,
"learning_rate": 9.198104700698596e-08,
"loss": 1.0202,
"step": 1879
},
{
"epoch": 4.8081841432225065,
"grad_norm": 0.11464186324553732,
"learning_rate": 8.958001448202358e-08,
"loss": 1.0152,
"step": 1880
},
{
"epoch": 4.810741687979539,
"grad_norm": 0.11662463464886089,
"learning_rate": 8.721059454209424e-08,
"loss": 1.0485,
"step": 1881
},
{
"epoch": 4.813299232736573,
"grad_norm": 0.12464254809498643,
"learning_rate": 8.48727947452499e-08,
"loss": 1.017,
"step": 1882
},
{
"epoch": 4.8158567774936065,
"grad_norm": 0.11127980935947186,
"learning_rate": 8.256662254867986e-08,
"loss": 1.0076,
"step": 1883
},
{
"epoch": 4.818414322250639,
"grad_norm": 0.11536372225589502,
"learning_rate": 8.029208530869081e-08,
"loss": 1.0295,
"step": 1884
},
{
"epoch": 4.820971867007673,
"grad_norm": 0.11600907835953211,
"learning_rate": 7.804919028067681e-08,
"loss": 1.0307,
"step": 1885
},
{
"epoch": 4.823529411764706,
"grad_norm": 0.11464611599367469,
"learning_rate": 7.58379446190971e-08,
"loss": 1.0466,
"step": 1886
},
{
"epoch": 4.826086956521739,
"grad_norm": 0.11686971960574333,
"learning_rate": 7.365835537745724e-08,
"loss": 1.0442,
"step": 1887
},
{
"epoch": 4.828644501278772,
"grad_norm": 0.11487887116386886,
"learning_rate": 7.151042950828247e-08,
"loss": 1.0445,
"step": 1888
},
{
"epoch": 4.831202046035806,
"grad_norm": 0.11340523651243395,
"learning_rate": 6.939417386309765e-08,
"loss": 1.029,
"step": 1889
},
{
"epoch": 4.833759590792839,
"grad_norm": 0.1150493275878801,
"learning_rate": 6.73095951924041e-08,
"loss": 1.0097,
"step": 1890
},
{
"epoch": 4.836317135549872,
"grad_norm": 0.11903827021172662,
"learning_rate": 6.525670014566166e-08,
"loss": 1.0464,
"step": 1891
},
{
"epoch": 4.838874680306906,
"grad_norm": 0.10980997002331325,
"learning_rate": 6.323549527126216e-08,
"loss": 1.0109,
"step": 1892
},
{
"epoch": 4.841432225063938,
"grad_norm": 0.1150321871820009,
"learning_rate": 6.124598701651052e-08,
"loss": 0.9896,
"step": 1893
},
{
"epoch": 4.843989769820972,
"grad_norm": 0.11826635724952957,
"learning_rate": 5.9288181727606976e-08,
"loss": 1.0406,
"step": 1894
},
{
"epoch": 4.846547314578006,
"grad_norm": 0.12341344246437233,
"learning_rate": 5.7362085649622646e-08,
"loss": 1.0292,
"step": 1895
},
{
"epoch": 4.849104859335038,
"grad_norm": 0.11768310013022554,
"learning_rate": 5.546770492648401e-08,
"loss": 1.0641,
"step": 1896
},
{
"epoch": 4.851662404092072,
"grad_norm": 0.1161461545199052,
"learning_rate": 5.360504560094737e-08,
"loss": 1.0278,
"step": 1897
},
{
"epoch": 4.854219948849105,
"grad_norm": 0.1139025404375565,
"learning_rate": 5.1774113614586616e-08,
"loss": 1.0405,
"step": 1898
},
{
"epoch": 4.856777493606138,
"grad_norm": 0.1215131651232801,
"learning_rate": 4.9974914807767724e-08,
"loss": 1.0753,
"step": 1899
},
{
"epoch": 4.859335038363171,
"grad_norm": 0.11755019743640818,
"learning_rate": 4.82074549196343e-08,
"loss": 1.0235,
"step": 1900
},
{
"epoch": 4.861892583120205,
"grad_norm": 0.11408088672302473,
"learning_rate": 4.6471739588089814e-08,
"loss": 1.0253,
"step": 1901
},
{
"epoch": 4.864450127877237,
"grad_norm": 0.11289577037034211,
"learning_rate": 4.4767774349776527e-08,
"loss": 1.0321,
"step": 1902
},
{
"epoch": 4.867007672634271,
"grad_norm": 0.11895648456750522,
"learning_rate": 4.30955646400566e-08,
"loss": 1.043,
"step": 1903
},
{
"epoch": 4.869565217391305,
"grad_norm": 0.1179294889008452,
"learning_rate": 4.14551157930021e-08,
"loss": 1.0538,
"step": 1904
},
{
"epoch": 4.872122762148337,
"grad_norm": 0.11618208912614107,
"learning_rate": 3.984643304136948e-08,
"loss": 1.0476,
"step": 1905
},
{
"epoch": 4.874680306905371,
"grad_norm": 0.11598189775025243,
"learning_rate": 3.826952151658958e-08,
"loss": 1.0356,
"step": 1906
},
{
"epoch": 4.877237851662404,
"grad_norm": 0.11586014435065378,
"learning_rate": 3.6724386248745415e-08,
"loss": 1.0402,
"step": 1907
},
{
"epoch": 4.879795396419437,
"grad_norm": 0.11273964633582521,
"learning_rate": 3.5211032166561075e-08,
"loss": 1.0651,
"step": 1908
},
{
"epoch": 4.882352941176471,
"grad_norm": 0.11553305320282162,
"learning_rate": 3.372946409738398e-08,
"loss": 1.0723,
"step": 1909
},
{
"epoch": 4.884910485933504,
"grad_norm": 0.1164335776440849,
"learning_rate": 3.22796867671682e-08,
"loss": 1.0322,
"step": 1910
},
{
"epoch": 4.887468030690537,
"grad_norm": 0.11551854002367276,
"learning_rate": 3.086170480046114e-08,
"loss": 1.0121,
"step": 1911
},
{
"epoch": 4.89002557544757,
"grad_norm": 0.11890262672457762,
"learning_rate": 2.9475522720389116e-08,
"loss": 1.0571,
"step": 1912
},
{
"epoch": 4.892583120204604,
"grad_norm": 0.11559520376004895,
"learning_rate": 2.8121144948641822e-08,
"loss": 1.0378,
"step": 1913
},
{
"epoch": 4.8951406649616365,
"grad_norm": 0.11021123166347066,
"learning_rate": 2.679857580545786e-08,
"loss": 1.0468,
"step": 1914
},
{
"epoch": 4.89769820971867,
"grad_norm": 0.11314952605469081,
"learning_rate": 2.5507819509610343e-08,
"loss": 1.0388,
"step": 1915
},
{
"epoch": 4.900255754475703,
"grad_norm": 0.11452758417807123,
"learning_rate": 2.4248880178399104e-08,
"loss": 1.0633,
"step": 1916
},
{
"epoch": 4.9028132992327365,
"grad_norm": 0.11870376108345816,
"learning_rate": 2.3021761827628497e-08,
"loss": 1.0193,
"step": 1917
},
{
"epoch": 4.90537084398977,
"grad_norm": 0.11658933357067867,
"learning_rate": 2.182646837160185e-08,
"loss": 0.9916,
"step": 1918
},
{
"epoch": 4.907928388746803,
"grad_norm": 0.11670304567415841,
"learning_rate": 2.0663003623105916e-08,
"loss": 1.0672,
"step": 1919
},
{
"epoch": 4.910485933503836,
"grad_norm": 0.1102254208498854,
"learning_rate": 1.953137129339977e-08,
"loss": 1.0298,
"step": 1920
},
{
"epoch": 4.913043478260869,
"grad_norm": 0.11803357978542595,
"learning_rate": 1.8431574992199276e-08,
"loss": 1.0461,
"step": 1921
},
{
"epoch": 4.915601023017903,
"grad_norm": 0.11020661745660215,
"learning_rate": 1.736361822767263e-08,
"loss": 1.0395,
"step": 1922
},
{
"epoch": 4.918158567774936,
"grad_norm": 0.11305349069484284,
"learning_rate": 1.632750440642261e-08,
"loss": 1.0231,
"step": 1923
},
{
"epoch": 4.920716112531969,
"grad_norm": 0.11510462052686142,
"learning_rate": 1.5323236833479914e-08,
"loss": 1.0259,
"step": 1924
},
{
"epoch": 4.923273657289003,
"grad_norm": 0.11702355777739097,
"learning_rate": 1.4350818712292047e-08,
"loss": 1.0613,
"step": 1925
},
{
"epoch": 4.9258312020460355,
"grad_norm": 0.11292851087049081,
"learning_rate": 1.3410253144707786e-08,
"loss": 1.0592,
"step": 1926
},
{
"epoch": 4.928388746803069,
"grad_norm": 0.11400163077833202,
"learning_rate": 1.2501543130974958e-08,
"loss": 1.062,
"step": 1927
},
{
"epoch": 4.930946291560103,
"grad_norm": 0.1183936881159329,
"learning_rate": 1.162469156972712e-08,
"loss": 1.0245,
"step": 1928
},
{
"epoch": 4.9335038363171355,
"grad_norm": 0.11337241506632771,
"learning_rate": 1.0779701257974672e-08,
"loss": 1.0449,
"step": 1929
},
{
"epoch": 4.936061381074169,
"grad_norm": 0.11376144202297905,
"learning_rate": 9.96657489109487e-09,
"loss": 1.0682,
"step": 1930
},
{
"epoch": 4.938618925831202,
"grad_norm": 0.11795763495218076,
"learning_rate": 9.185315062826272e-09,
"loss": 1.0674,
"step": 1931
},
{
"epoch": 4.9411764705882355,
"grad_norm": 0.11749004694568776,
"learning_rate": 8.435924265256523e-09,
"loss": 1.0479,
"step": 1932
},
{
"epoch": 4.943734015345268,
"grad_norm": 0.10996587345538478,
"learning_rate": 7.718404888816811e-09,
"loss": 1.0148,
"step": 1933
},
{
"epoch": 4.946291560102302,
"grad_norm": 0.11480984252460183,
"learning_rate": 7.032759222274088e-09,
"loss": 1.0408,
"step": 1934
},
{
"epoch": 4.948849104859335,
"grad_norm": 0.11630744934298476,
"learning_rate": 6.378989452724416e-09,
"loss": 1.0236,
"step": 1935
},
{
"epoch": 4.951406649616368,
"grad_norm": 0.1124895154235232,
"learning_rate": 5.757097665584077e-09,
"loss": 1.0335,
"step": 1936
},
{
"epoch": 4.953964194373402,
"grad_norm": 0.11425081997455588,
"learning_rate": 5.16708584458292e-09,
"loss": 1.0354,
"step": 1937
},
{
"epoch": 4.956521739130435,
"grad_norm": 0.11330328401845938,
"learning_rate": 4.608955871761023e-09,
"loss": 1.0077,
"step": 1938
},
{
"epoch": 4.959079283887468,
"grad_norm": 0.11496557714114423,
"learning_rate": 4.0827095274598165e-09,
"loss": 1.0478,
"step": 1939
},
{
"epoch": 4.961636828644501,
"grad_norm": 0.12009777724541458,
"learning_rate": 3.588348490317639e-09,
"loss": 1.0568,
"step": 1940
},
{
"epoch": 4.964194373401535,
"grad_norm": 0.1165369144605732,
"learning_rate": 3.1258743372619693e-09,
"loss": 1.0352,
"step": 1941
},
{
"epoch": 4.966751918158568,
"grad_norm": 0.11826068216824383,
"learning_rate": 2.6952885435105324e-09,
"loss": 1.047,
"step": 1942
},
{
"epoch": 4.969309462915601,
"grad_norm": 0.11246869085468798,
"learning_rate": 2.29659248255798e-09,
"loss": 1.0417,
"step": 1943
},
{
"epoch": 4.971867007672635,
"grad_norm": 0.11023466743258699,
"learning_rate": 1.9297874261792194e-09,
"loss": 1.0137,
"step": 1944
},
{
"epoch": 4.974424552429667,
"grad_norm": 0.11511965541940995,
"learning_rate": 1.594874544421643e-09,
"loss": 1.0311,
"step": 1945
},
{
"epoch": 4.976982097186701,
"grad_norm": 0.124147218545505,
"learning_rate": 1.2918549056006868e-09,
"loss": 1.0719,
"step": 1946
},
{
"epoch": 4.979539641943734,
"grad_norm": 0.11557957987866309,
"learning_rate": 1.0207294762987208e-09,
"loss": 1.0187,
"step": 1947
},
{
"epoch": 4.982097186700767,
"grad_norm": 0.11775087960856384,
"learning_rate": 7.814991213594969e-10,
"loss": 1.0355,
"step": 1948
},
{
"epoch": 4.9846547314578,
"grad_norm": 0.11570647330926523,
"learning_rate": 5.741646038892601e-10,
"loss": 1.0646,
"step": 1949
},
{
"epoch": 4.987212276214834,
"grad_norm": 0.1150012391819302,
"learning_rate": 3.9872658525008654e-10,
"loss": 1.0612,
"step": 1950
},
{
"epoch": 4.989769820971867,
"grad_norm": 0.10963077899170262,
"learning_rate": 2.5518562505988387e-10,
"loss": 1.0244,
"step": 1951
},
{
"epoch": 4.9923273657289,
"grad_norm": 0.1137791798614674,
"learning_rate": 1.435421811901705e-10,
"loss": 1.0499,
"step": 1952
},
{
"epoch": 4.994884910485934,
"grad_norm": 0.11415395430572649,
"learning_rate": 6.37966097649656e-11,
"loss": 1.0107,
"step": 1953
},
{
"epoch": 4.997442455242966,
"grad_norm": 0.11255930720124045,
"learning_rate": 1.5949165159678813e-11,
"loss": 1.0177,
"step": 1954
},
{
"epoch": 5.0,
"grad_norm": 0.11539135868139018,
"learning_rate": 0.0,
"loss": 1.0412,
"step": 1955
},
{
"epoch": 5.0,
"step": 1955,
"total_flos": 7122204608430080.0,
"train_loss": 1.082116018475779,
"train_runtime": 36273.766,
"train_samples_per_second": 13.784,
"train_steps_per_second": 0.054
}
],
"logging_steps": 1.0,
"max_steps": 1955,
"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": 7122204608430080.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}