diff --git "a/checkpoint-832/trainer_state.json" "b/checkpoint-832/trainer_state.json"
new file mode 100644--- /dev/null
+++ "b/checkpoint-832/trainer_state.json"
@@ -0,0 +1,5858 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9963985594237696,
+  "eval_steps": 500,
+  "global_step": 832,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0024009603841536613,
+      "grad_norm": 3.307639305281489,
+      "learning_rate": 0.0,
+      "loss": 1.027,
+      "step": 1
+    },
+    {
+      "epoch": 0.004801920768307323,
+      "grad_norm": 3.4815729475698585,
+      "learning_rate": 2.5000000000000004e-07,
+      "loss": 1.0887,
+      "step": 2
+    },
+    {
+      "epoch": 0.007202881152460984,
+      "grad_norm": 3.1919511484422025,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 0.9992,
+      "step": 3
+    },
+    {
+      "epoch": 0.009603841536614645,
+      "grad_norm": 3.192234811391807,
+      "learning_rate": 7.5e-07,
+      "loss": 1.0676,
+      "step": 4
+    },
+    {
+      "epoch": 0.012004801920768308,
+      "grad_norm": 3.147628945570283,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.0932,
+      "step": 5
+    },
+    {
+      "epoch": 0.014405762304921969,
+      "grad_norm": 2.9173656342980085,
+      "learning_rate": 1.25e-06,
+      "loss": 1.0108,
+      "step": 6
+    },
+    {
+      "epoch": 0.01680672268907563,
+      "grad_norm": 2.965584304042035,
+      "learning_rate": 1.5e-06,
+      "loss": 1.0785,
+      "step": 7
+    },
+    {
+      "epoch": 0.01920768307322929,
+      "grad_norm": 2.6367740096927643,
+      "learning_rate": 1.75e-06,
+      "loss": 1.0562,
+      "step": 8
+    },
+    {
+      "epoch": 0.021608643457382955,
+      "grad_norm": 2.468163591370129,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.0243,
+      "step": 9
+    },
+    {
+      "epoch": 0.024009603841536616,
+      "grad_norm": 2.372272215735556,
+      "learning_rate": 2.25e-06,
+      "loss": 1.0174,
+      "step": 10
+    },
+    {
+      "epoch": 0.026410564225690276,
+      "grad_norm": 2.4133969432396736,
+      "learning_rate": 2.5e-06,
+      "loss": 0.9751,
+      "step": 11
+    },
+    {
+      "epoch": 0.028811524609843937,
+      "grad_norm": 1.9294470459831854,
+      "learning_rate": 2.7500000000000004e-06,
+      "loss": 0.9501,
+      "step": 12
+    },
+    {
+      "epoch": 0.031212484993997598,
+      "grad_norm": 1.6356435792199144,
+      "learning_rate": 3e-06,
+      "loss": 0.8964,
+      "step": 13
+    },
+    {
+      "epoch": 0.03361344537815126,
+      "grad_norm": 1.4259278773927042,
+      "learning_rate": 3.2500000000000002e-06,
+      "loss": 0.9262,
+      "step": 14
+    },
+    {
+      "epoch": 0.03601440576230492,
+      "grad_norm": 1.4029510526993147,
+      "learning_rate": 3.5e-06,
+      "loss": 0.8773,
+      "step": 15
+    },
+    {
+      "epoch": 0.03841536614645858,
+      "grad_norm": 1.3072701950591272,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.8863,
+      "step": 16
+    },
+    {
+      "epoch": 0.04081632653061224,
+      "grad_norm": 1.3415661249879083,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.8391,
+      "step": 17
+    },
+    {
+      "epoch": 0.04321728691476591,
+      "grad_norm": 1.2551228414808617,
+      "learning_rate": 4.25e-06,
+      "loss": 0.8391,
+      "step": 18
+    },
+    {
+      "epoch": 0.04561824729891957,
+      "grad_norm": 1.4822117298636246,
+      "learning_rate": 4.5e-06,
+      "loss": 0.9249,
+      "step": 19
+    },
+    {
+      "epoch": 0.04801920768307323,
+      "grad_norm": 2.293387776769893,
+      "learning_rate": 4.75e-06,
+      "loss": 0.8683,
+      "step": 20
+    },
+    {
+      "epoch": 0.05042016806722689,
+      "grad_norm": 1.276527897418368,
+      "learning_rate": 5e-06,
+      "loss": 0.8863,
+      "step": 21
+    },
+    {
+      "epoch": 0.05282112845138055,
+      "grad_norm": 1.205563120747159,
+      "learning_rate": 5.2500000000000006e-06,
+      "loss": 0.8641,
+      "step": 22
+    },
+    {
+      "epoch": 0.055222088835534214,
+      "grad_norm": 1.2341891463491723,
+      "learning_rate": 5.500000000000001e-06,
+      "loss": 0.8741,
+      "step": 23
+    },
+    {
+      "epoch": 0.057623049219687875,
+      "grad_norm": 1.194537311448108,
+      "learning_rate": 5.75e-06,
+      "loss": 0.806,
+      "step": 24
+    },
+    {
+      "epoch": 0.060024009603841535,
+      "grad_norm": 1.2485956345196676,
+      "learning_rate": 6e-06,
+      "loss": 0.8281,
+      "step": 25
+    },
+    {
+      "epoch": 0.062424969987995196,
+      "grad_norm": 1.1779315877632301,
+      "learning_rate": 6.25e-06,
+      "loss": 0.8552,
+      "step": 26
+    },
+    {
+      "epoch": 0.06482593037214886,
+      "grad_norm": 1.4180731528009602,
+      "learning_rate": 6.5000000000000004e-06,
+      "loss": 0.8506,
+      "step": 27
+    },
+    {
+      "epoch": 0.06722689075630252,
+      "grad_norm": 3.041894752350215,
+      "learning_rate": 6.750000000000001e-06,
+      "loss": 0.8885,
+      "step": 28
+    },
+    {
+      "epoch": 0.06962785114045618,
+      "grad_norm": 1.1860989270253326,
+      "learning_rate": 7e-06,
+      "loss": 0.8331,
+      "step": 29
+    },
+    {
+      "epoch": 0.07202881152460984,
+      "grad_norm": 1.206902242271321,
+      "learning_rate": 7.25e-06,
+      "loss": 0.8206,
+      "step": 30
+    },
+    {
+      "epoch": 0.0744297719087635,
+      "grad_norm": 1.1671538322004624,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.8167,
+      "step": 31
+    },
+    {
+      "epoch": 0.07683073229291716,
+      "grad_norm": 1.0422949222046782,
+      "learning_rate": 7.75e-06,
+      "loss": 0.8007,
+      "step": 32
+    },
+    {
+      "epoch": 0.07923169267707082,
+      "grad_norm": 1.8592446673491745,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.8507,
+      "step": 33
+    },
+    {
+      "epoch": 0.08163265306122448,
+      "grad_norm": 1.6612165554220881,
+      "learning_rate": 8.25e-06,
+      "loss": 0.8508,
+      "step": 34
+    },
+    {
+      "epoch": 0.08403361344537816,
+      "grad_norm": 1.0713315873933724,
+      "learning_rate": 8.5e-06,
+      "loss": 0.8605,
+      "step": 35
+    },
+    {
+      "epoch": 0.08643457382953182,
+      "grad_norm": 1.1490421409260716,
+      "learning_rate": 8.750000000000001e-06,
+      "loss": 0.8529,
+      "step": 36
+    },
+    {
+      "epoch": 0.08883553421368548,
+      "grad_norm": 1.1077552226131402,
+      "learning_rate": 9e-06,
+      "loss": 0.8251,
+      "step": 37
+    },
+    {
+      "epoch": 0.09123649459783914,
+      "grad_norm": 0.9873238748489626,
+      "learning_rate": 9.250000000000001e-06,
+      "loss": 0.7978,
+      "step": 38
+    },
+    {
+      "epoch": 0.0936374549819928,
+      "grad_norm": 1.3452579503150184,
+      "learning_rate": 9.5e-06,
+      "loss": 0.8637,
+      "step": 39
+    },
+    {
+      "epoch": 0.09603841536614646,
+      "grad_norm": 1.4631068406573169,
+      "learning_rate": 9.75e-06,
+      "loss": 0.8023,
+      "step": 40
+    },
+    {
+      "epoch": 0.09843937575030012,
+      "grad_norm": 1.265806360917147,
+      "learning_rate": 1e-05,
+      "loss": 0.8345,
+      "step": 41
+    },
+    {
+      "epoch": 0.10084033613445378,
+      "grad_norm": 1.1943330814308766,
+      "learning_rate": 9.999960664124435e-06,
+      "loss": 0.8704,
+      "step": 42
+    },
+    {
+      "epoch": 0.10324129651860744,
+      "grad_norm": 1.061823017754904,
+      "learning_rate": 9.999842657116667e-06,
+      "loss": 0.8463,
+      "step": 43
+    },
+    {
+      "epoch": 0.1056422569027611,
+      "grad_norm": 1.0296226499358687,
+      "learning_rate": 9.999645980833454e-06,
+      "loss": 0.825,
+      "step": 44
+    },
+    {
+      "epoch": 0.10804321728691477,
+      "grad_norm": 1.046275065503394,
+      "learning_rate": 9.999370638369377e-06,
+      "loss": 0.8341,
+      "step": 45
+    },
+    {
+      "epoch": 0.11044417767106843,
+      "grad_norm": 1.0958287099043753,
+      "learning_rate": 9.999016634056764e-06,
+      "loss": 0.7894,
+      "step": 46
+    },
+    {
+      "epoch": 0.11284513805522209,
+      "grad_norm": 1.030922973342192,
+      "learning_rate": 9.998583973465647e-06,
+      "loss": 0.787,
+      "step": 47
+    },
+    {
+      "epoch": 0.11524609843937575,
+      "grad_norm": 1.2421669534880109,
+      "learning_rate": 9.998072663403657e-06,
+      "loss": 0.7978,
+      "step": 48
+    },
+    {
+      "epoch": 0.11764705882352941,
+      "grad_norm": 1.3970247274710101,
+      "learning_rate": 9.997482711915926e-06,
+      "loss": 0.7801,
+      "step": 49
+    },
+    {
+      "epoch": 0.12004801920768307,
+      "grad_norm": 0.9723742502152596,
+      "learning_rate": 9.99681412828496e-06,
+      "loss": 0.7895,
+      "step": 50
+    },
+    {
+      "epoch": 0.12244897959183673,
+      "grad_norm": 1.2807089303778385,
+      "learning_rate": 9.996066923030484e-06,
+      "loss": 0.8543,
+      "step": 51
+    },
+    {
+      "epoch": 0.12484993997599039,
+      "grad_norm": 1.27637006864039,
+      "learning_rate": 9.99524110790929e-06,
+      "loss": 0.8535,
+      "step": 52
+    },
+    {
+      "epoch": 0.12725090036014405,
+      "grad_norm": 0.9583150465246295,
+      "learning_rate": 9.994336695915041e-06,
+      "loss": 0.7819,
+      "step": 53
+    },
+    {
+      "epoch": 0.12965186074429771,
+      "grad_norm": 1.066121996350333,
+      "learning_rate": 9.993353701278072e-06,
+      "loss": 0.7962,
+      "step": 54
+    },
+    {
+      "epoch": 0.13205282112845138,
+      "grad_norm": 1.0321017551908462,
+      "learning_rate": 9.992292139465166e-06,
+      "loss": 0.794,
+      "step": 55
+    },
+    {
+      "epoch": 0.13445378151260504,
+      "grad_norm": 1.1056060968463626,
+      "learning_rate": 9.991152027179307e-06,
+      "loss": 0.8431,
+      "step": 56
+    },
+    {
+      "epoch": 0.1368547418967587,
+      "grad_norm": 1.6782765780764348,
+      "learning_rate": 9.989933382359423e-06,
+      "loss": 0.8303,
+      "step": 57
+    },
+    {
+      "epoch": 0.13925570228091236,
+      "grad_norm": 1.1967331617073076,
+      "learning_rate": 9.988636224180097e-06,
+      "loss": 0.7792,
+      "step": 58
+    },
+    {
+      "epoch": 0.14165666266506602,
+      "grad_norm": 1.8049549266124272,
+      "learning_rate": 9.987260573051268e-06,
+      "loss": 0.7988,
+      "step": 59
+    },
+    {
+      "epoch": 0.14405762304921968,
+      "grad_norm": 1.046695584455822,
+      "learning_rate": 9.985806450617916e-06,
+      "loss": 0.8037,
+      "step": 60
+    },
+    {
+      "epoch": 0.14645858343337334,
+      "grad_norm": 1.2121335142230327,
+      "learning_rate": 9.984273879759713e-06,
+      "loss": 0.8515,
+      "step": 61
+    },
+    {
+      "epoch": 0.148859543817527,
+      "grad_norm": 1.3076719515024817,
+      "learning_rate": 9.982662884590662e-06,
+      "loss": 0.8178,
+      "step": 62
+    },
+    {
+      "epoch": 0.15126050420168066,
+      "grad_norm": 1.2564921607093686,
+      "learning_rate": 9.980973490458728e-06,
+      "loss": 0.8399,
+      "step": 63
+    },
+    {
+      "epoch": 0.15366146458583432,
+      "grad_norm": 1.0641383621124019,
+      "learning_rate": 9.97920572394543e-06,
+      "loss": 0.7677,
+      "step": 64
+    },
+    {
+      "epoch": 0.15606242496998798,
+      "grad_norm": 1.1281926663515902,
+      "learning_rate": 9.977359612865424e-06,
+      "loss": 0.7974,
+      "step": 65
+    },
+    {
+      "epoch": 0.15846338535414164,
+      "grad_norm": 1.0094739962757735,
+      "learning_rate": 9.975435186266069e-06,
+      "loss": 0.7676,
+      "step": 66
+    },
+    {
+      "epoch": 0.1608643457382953,
+      "grad_norm": 1.3602443348603426,
+      "learning_rate": 9.973432474426968e-06,
+      "loss": 0.8171,
+      "step": 67
+    },
+    {
+      "epoch": 0.16326530612244897,
+      "grad_norm": 0.9792328660506742,
+      "learning_rate": 9.971351508859488e-06,
+      "loss": 0.7561,
+      "step": 68
+    },
+    {
+      "epoch": 0.16566626650660263,
+      "grad_norm": 1.397240469672876,
+      "learning_rate": 9.969192322306271e-06,
+      "loss": 0.8365,
+      "step": 69
+    },
+    {
+      "epoch": 0.16806722689075632,
+      "grad_norm": 1.3993747618987225,
+      "learning_rate": 9.966954948740717e-06,
+      "loss": 0.7281,
+      "step": 70
+    },
+    {
+      "epoch": 0.17046818727490998,
+      "grad_norm": 1.0666295786391167,
+      "learning_rate": 9.964639423366442e-06,
+      "loss": 0.8563,
+      "step": 71
+    },
+    {
+      "epoch": 0.17286914765906364,
+      "grad_norm": 1.6098094871731998,
+      "learning_rate": 9.962245782616734e-06,
+      "loss": 0.8027,
+      "step": 72
+    },
+    {
+      "epoch": 0.1752701080432173,
+      "grad_norm": 1.0029300637530163,
+      "learning_rate": 9.959774064153977e-06,
+      "loss": 0.7768,
+      "step": 73
+    },
+    {
+      "epoch": 0.17767106842737096,
+      "grad_norm": 1.1557098402816255,
+      "learning_rate": 9.957224306869053e-06,
+      "loss": 0.7915,
+      "step": 74
+    },
+    {
+      "epoch": 0.18007202881152462,
+      "grad_norm": 1.1411436589531005,
+      "learning_rate": 9.954596550880735e-06,
+      "loss": 0.8207,
+      "step": 75
+    },
+    {
+      "epoch": 0.18247298919567828,
+      "grad_norm": 0.9898519262158086,
+      "learning_rate": 9.951890837535058e-06,
+      "loss": 0.8303,
+      "step": 76
+    },
+    {
+      "epoch": 0.18487394957983194,
+      "grad_norm": 1.015734040263864,
+      "learning_rate": 9.949107209404664e-06,
+      "loss": 0.7928,
+      "step": 77
+    },
+    {
+      "epoch": 0.1872749099639856,
+      "grad_norm": 1.0314783989677847,
+      "learning_rate": 9.946245710288132e-06,
+      "loss": 0.7407,
+      "step": 78
+    },
+    {
+      "epoch": 0.18967587034813926,
+      "grad_norm": 2.1401440917485943,
+      "learning_rate": 9.94330638520929e-06,
+      "loss": 0.7775,
+      "step": 79
+    },
+    {
+      "epoch": 0.19207683073229292,
+      "grad_norm": 0.9890405160925984,
+      "learning_rate": 9.940289280416509e-06,
+      "loss": 0.7566,
+      "step": 80
+    },
+    {
+      "epoch": 0.19447779111644659,
+      "grad_norm": 0.9739543182418596,
+      "learning_rate": 9.937194443381972e-06,
+      "loss": 0.8159,
+      "step": 81
+    },
+    {
+      "epoch": 0.19687875150060025,
+      "grad_norm": 1.1138048276749253,
+      "learning_rate": 9.934021922800931e-06,
+      "loss": 0.7939,
+      "step": 82
+    },
+    {
+      "epoch": 0.1992797118847539,
+      "grad_norm": 1.0939436400008165,
+      "learning_rate": 9.930771768590934e-06,
+      "loss": 0.8144,
+      "step": 83
+    },
+    {
+      "epoch": 0.20168067226890757,
+      "grad_norm": 1.1293648489823769,
+      "learning_rate": 9.927444031891044e-06,
+      "loss": 0.7755,
+      "step": 84
+    },
+    {
+      "epoch": 0.20408163265306123,
+      "grad_norm": 1.0430331448777437,
+      "learning_rate": 9.924038765061042e-06,
+      "loss": 0.8215,
+      "step": 85
+    },
+    {
+      "epoch": 0.2064825930372149,
+      "grad_norm": 1.9537322284504008,
+      "learning_rate": 9.92055602168058e-06,
+      "loss": 0.7563,
+      "step": 86
+    },
+    {
+      "epoch": 0.20888355342136855,
+      "grad_norm": 1.3079086606300951,
+      "learning_rate": 9.916995856548371e-06,
+      "loss": 0.8157,
+      "step": 87
+    },
+    {
+      "epoch": 0.2112845138055222,
+      "grad_norm": 0.9221688539776796,
+      "learning_rate": 9.913358325681292e-06,
+      "loss": 0.782,
+      "step": 88
+    },
+    {
+      "epoch": 0.21368547418967587,
+      "grad_norm": 1.1087405466326585,
+      "learning_rate": 9.909643486313533e-06,
+      "loss": 0.8061,
+      "step": 89
+    },
+    {
+      "epoch": 0.21608643457382953,
+      "grad_norm": 1.2632508204228434,
+      "learning_rate": 9.905851396895679e-06,
+      "loss": 0.7788,
+      "step": 90
+    },
+    {
+      "epoch": 0.2184873949579832,
+      "grad_norm": 1.2841221080352947,
+      "learning_rate": 9.901982117093786e-06,
+      "loss": 0.7707,
+      "step": 91
+    },
+    {
+      "epoch": 0.22088835534213686,
+      "grad_norm": 0.9416571120286465,
+      "learning_rate": 9.898035707788462e-06,
+      "loss": 0.7386,
+      "step": 92
+    },
+    {
+      "epoch": 0.22328931572629052,
+      "grad_norm": 1.0394686320396263,
+      "learning_rate": 9.894012231073895e-06,
+      "loss": 0.7729,
+      "step": 93
+    },
+    {
+      "epoch": 0.22569027611044418,
+      "grad_norm": 1.1642999740100775,
+      "learning_rate": 9.889911750256873e-06,
+      "loss": 0.7667,
+      "step": 94
+    },
+    {
+      "epoch": 0.22809123649459784,
+      "grad_norm": 1.0191501234681113,
+      "learning_rate": 9.885734329855798e-06,
+      "loss": 0.7415,
+      "step": 95
+    },
+    {
+      "epoch": 0.2304921968787515,
+      "grad_norm": 1.1396215768269955,
+      "learning_rate": 9.881480035599667e-06,
+      "loss": 0.846,
+      "step": 96
+    },
+    {
+      "epoch": 0.23289315726290516,
+      "grad_norm": 1.4770430873772629,
+      "learning_rate": 9.877148934427037e-06,
+      "loss": 0.8105,
+      "step": 97
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 1.1245875213463206,
+      "learning_rate": 9.872741094484965e-06,
+      "loss": 0.7857,
+      "step": 98
+    },
+    {
+      "epoch": 0.23769507803121248,
+      "grad_norm": 0.9225248681792048,
+      "learning_rate": 9.868256585127956e-06,
+      "loss": 0.7292,
+      "step": 99
+    },
+    {
+      "epoch": 0.24009603841536614,
+      "grad_norm": 1.0574440145567323,
+      "learning_rate": 9.863695476916846e-06,
+      "loss": 0.8077,
+      "step": 100
+    },
+    {
+      "epoch": 0.2424969987995198,
+      "grad_norm": 1.1365137152954194,
+      "learning_rate": 9.859057841617709e-06,
+      "loss": 0.8066,
+      "step": 101
+    },
+    {
+      "epoch": 0.24489795918367346,
+      "grad_norm": 1.1942946403505255,
+      "learning_rate": 9.854343752200725e-06,
+      "loss": 0.8139,
+      "step": 102
+    },
+    {
+      "epoch": 0.24729891956782712,
+      "grad_norm": 1.0543479220950105,
+      "learning_rate": 9.849553282839025e-06,
+      "loss": 0.7701,
+      "step": 103
+    },
+    {
+      "epoch": 0.24969987995198079,
+      "grad_norm": 0.926743129553519,
+      "learning_rate": 9.844686508907538e-06,
+      "loss": 0.7927,
+      "step": 104
+    },
+    {
+      "epoch": 0.25210084033613445,
+      "grad_norm": 1.011488885523952,
+      "learning_rate": 9.839743506981783e-06,
+      "loss": 0.7914,
+      "step": 105
+    },
+    {
+      "epoch": 0.2545018007202881,
+      "grad_norm": 1.0064857869367891,
+      "learning_rate": 9.834724354836684e-06,
+      "loss": 0.7701,
+      "step": 106
+    },
+    {
+      "epoch": 0.25690276110444177,
+      "grad_norm": 1.2884610797254652,
+      "learning_rate": 9.829629131445342e-06,
+      "loss": 0.7797,
+      "step": 107
+    },
+    {
+      "epoch": 0.25930372148859543,
+      "grad_norm": 1.022923038777103,
+      "learning_rate": 9.824457916977785e-06,
+      "loss": 0.7563,
+      "step": 108
+    },
+    {
+      "epoch": 0.2617046818727491,
+      "grad_norm": 1.3622638931252318,
+      "learning_rate": 9.819210792799711e-06,
+      "loss": 0.791,
+      "step": 109
+    },
+    {
+      "epoch": 0.26410564225690275,
+      "grad_norm": 1.6261815582055081,
+      "learning_rate": 9.81388784147121e-06,
+      "loss": 0.7791,
+      "step": 110
+    },
+    {
+      "epoch": 0.2665066026410564,
+      "grad_norm": 1.3875850558476444,
+      "learning_rate": 9.808489146745466e-06,
+      "loss": 0.8065,
+      "step": 111
+    },
+    {
+      "epoch": 0.2689075630252101,
+      "grad_norm": 1.0566640937075868,
+      "learning_rate": 9.803014793567429e-06,
+      "loss": 0.7662,
+      "step": 112
+    },
+    {
+      "epoch": 0.27130852340936373,
+      "grad_norm": 0.9297104835810871,
+      "learning_rate": 9.797464868072489e-06,
+      "loss": 0.7338,
+      "step": 113
+    },
+    {
+      "epoch": 0.2737094837935174,
+      "grad_norm": 0.9992084910627275,
+      "learning_rate": 9.791839457585118e-06,
+      "loss": 0.7773,
+      "step": 114
+    },
+    {
+      "epoch": 0.27611044417767105,
+      "grad_norm": 1.1581522702903588,
+      "learning_rate": 9.786138650617494e-06,
+      "loss": 0.7929,
+      "step": 115
+    },
+    {
+      "epoch": 0.2785114045618247,
+      "grad_norm": 1.259081791921377,
+      "learning_rate": 9.780362536868113e-06,
+      "loss": 0.7279,
+      "step": 116
+    },
+    {
+      "epoch": 0.2809123649459784,
+      "grad_norm": 1.1510251918441672,
+      "learning_rate": 9.774511207220369e-06,
+      "loss": 0.7412,
+      "step": 117
+    },
+    {
+      "epoch": 0.28331332533013204,
+      "grad_norm": 0.9943579023159135,
+      "learning_rate": 9.768584753741134e-06,
+      "loss": 0.7927,
+      "step": 118
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 1.061487526635317,
+      "learning_rate": 9.762583269679304e-06,
+      "loss": 0.8363,
+      "step": 119
+    },
+    {
+      "epoch": 0.28811524609843936,
+      "grad_norm": 1.1215382733800197,
+      "learning_rate": 9.756506849464327e-06,
+      "loss": 0.8032,
+      "step": 120
+    },
+    {
+      "epoch": 0.290516206482593,
+      "grad_norm": 1.0985810622772545,
+      "learning_rate": 9.750355588704728e-06,
+      "loss": 0.8062,
+      "step": 121
+    },
+    {
+      "epoch": 0.2929171668667467,
+      "grad_norm": 1.0397097160893556,
+      "learning_rate": 9.744129584186599e-06,
+      "loss": 0.7867,
+      "step": 122
+    },
+    {
+      "epoch": 0.29531812725090034,
+      "grad_norm": 1.0985983029789874,
+      "learning_rate": 9.737828933872076e-06,
+      "loss": 0.7645,
+      "step": 123
+    },
+    {
+      "epoch": 0.297719087635054,
+      "grad_norm": 1.0341542778256945,
+      "learning_rate": 9.731453736897796e-06,
+      "loss": 0.7682,
+      "step": 124
+    },
+    {
+      "epoch": 0.30012004801920766,
+      "grad_norm": 0.9637556163656881,
+      "learning_rate": 9.725004093573343e-06,
+      "loss": 0.7819,
+      "step": 125
+    },
+    {
+      "epoch": 0.3025210084033613,
+      "grad_norm": 0.9476489500974398,
+      "learning_rate": 9.718480105379663e-06,
+      "loss": 0.7875,
+      "step": 126
+    },
+    {
+      "epoch": 0.304921968787515,
+      "grad_norm": 1.3085520795980778,
+      "learning_rate": 9.711881874967471e-06,
+      "loss": 0.7908,
+      "step": 127
+    },
+    {
+      "epoch": 0.30732292917166865,
+      "grad_norm": 0.9414082676216773,
+      "learning_rate": 9.705209506155635e-06,
+      "loss": 0.7454,
+      "step": 128
+    },
+    {
+      "epoch": 0.3097238895558223,
+      "grad_norm": 1.2351287282053665,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 0.7813,
+      "step": 129
+    },
+    {
+      "epoch": 0.31212484993997597,
+      "grad_norm": 1.021583176125914,
+      "learning_rate": 9.69164277443945e-06,
+      "loss": 0.8417,
+      "step": 130
+    },
+    {
+      "epoch": 0.31452581032412963,
+      "grad_norm": 1.4089615187590279,
+      "learning_rate": 9.68474862499881e-06,
+      "loss": 0.7358,
+      "step": 131
+    },
+    {
+      "epoch": 0.3169267707082833,
+      "grad_norm": 0.9398428308548782,
+      "learning_rate": 9.677780764082583e-06,
+      "loss": 0.7637,
+      "step": 132
+    },
+    {
+      "epoch": 0.31932773109243695,
+      "grad_norm": 1.1136331841332863,
+      "learning_rate": 9.670739301325534e-06,
+      "loss": 0.7723,
+      "step": 133
+    },
+    {
+      "epoch": 0.3217286914765906,
+      "grad_norm": 1.1992806853517075,
+      "learning_rate": 9.663624347520506e-06,
+      "loss": 0.7788,
+      "step": 134
+    },
+    {
+      "epoch": 0.3241296518607443,
+      "grad_norm": 1.311509502714469,
+      "learning_rate": 9.65643601461667e-06,
+      "loss": 0.7696,
+      "step": 135
+    },
+    {
+      "epoch": 0.32653061224489793,
+      "grad_norm": 0.9623376564123519,
+      "learning_rate": 9.649174415717776e-06,
+      "loss": 0.7414,
+      "step": 136
+    },
+    {
+      "epoch": 0.3289315726290516,
+      "grad_norm": 1.0486840444117425,
+      "learning_rate": 9.641839665080363e-06,
+      "loss": 0.7909,
+      "step": 137
+    },
+    {
+      "epoch": 0.33133253301320525,
+      "grad_norm": 1.172648282688611,
+      "learning_rate": 9.634431878111969e-06,
+      "loss": 0.7684,
+      "step": 138
+    },
+    {
+      "epoch": 0.33373349339735897,
+      "grad_norm": 1.3883931408734287,
+      "learning_rate": 9.626951171369306e-06,
+      "loss": 0.7824,
+      "step": 139
+    },
+    {
+      "epoch": 0.33613445378151263,
+      "grad_norm": 1.0459492696464887,
+      "learning_rate": 9.619397662556434e-06,
+      "loss": 0.7729,
+      "step": 140
+    },
+    {
+      "epoch": 0.3385354141656663,
+      "grad_norm": 1.090681276032822,
+      "learning_rate": 9.611771470522908e-06,
+      "loss": 0.78,
+      "step": 141
+    },
+    {
+      "epoch": 0.34093637454981995,
+      "grad_norm": 1.077439313381409,
+      "learning_rate": 9.604072715261902e-06,
+      "loss": 0.7746,
+      "step": 142
+    },
+    {
+      "epoch": 0.3433373349339736,
+      "grad_norm": 1.0119948107455536,
+      "learning_rate": 9.596301517908329e-06,
+      "loss": 0.7725,
+      "step": 143
+    },
+    {
+      "epoch": 0.3457382953181273,
+      "grad_norm": 1.0261650566322091,
+      "learning_rate": 9.588458000736929e-06,
+      "loss": 0.8126,
+      "step": 144
+    },
+    {
+      "epoch": 0.34813925570228094,
+      "grad_norm": 3.2915968630848296,
+      "learning_rate": 9.580542287160348e-06,
+      "loss": 0.8087,
+      "step": 145
+    },
+    {
+      "epoch": 0.3505402160864346,
+      "grad_norm": 1.1260052143600965,
+      "learning_rate": 9.572554501727198e-06,
+      "loss": 0.7626,
+      "step": 146
+    },
+    {
+      "epoch": 0.35294117647058826,
+      "grad_norm": 1.1992270704321544,
+      "learning_rate": 9.564494770120089e-06,
+      "loss": 0.7942,
+      "step": 147
+    },
+    {
+      "epoch": 0.3553421368547419,
+      "grad_norm": 0.8934279508188496,
+      "learning_rate": 9.556363219153664e-06,
+      "loss": 0.7121,
+      "step": 148
+    },
+    {
+      "epoch": 0.3577430972388956,
+      "grad_norm": 1.627029857609285,
+      "learning_rate": 9.548159976772593e-06,
+      "loss": 0.8305,
+      "step": 149
+    },
+    {
+      "epoch": 0.36014405762304924,
+      "grad_norm": 1.2904112895903999,
+      "learning_rate": 9.539885172049563e-06,
+      "loss": 0.7903,
+      "step": 150
+    },
+    {
+      "epoch": 0.3625450180072029,
+      "grad_norm": 0.9013735933905231,
+      "learning_rate": 9.531538935183252e-06,
+      "loss": 0.7532,
+      "step": 151
+    },
+    {
+      "epoch": 0.36494597839135656,
+      "grad_norm": 1.1957280125341616,
+      "learning_rate": 9.52312139749627e-06,
+      "loss": 0.7654,
+      "step": 152
+    },
+    {
+      "epoch": 0.3673469387755102,
+      "grad_norm": 1.1864890770385386,
+      "learning_rate": 9.514632691433108e-06,
+      "loss": 0.7774,
+      "step": 153
+    },
+    {
+      "epoch": 0.3697478991596639,
+      "grad_norm": 1.2602126687460933,
+      "learning_rate": 9.506072950558036e-06,
+      "loss": 0.7308,
+      "step": 154
+    },
+    {
+      "epoch": 0.37214885954381755,
+      "grad_norm": 0.9838354835983466,
+      "learning_rate": 9.497442309553017e-06,
+      "loss": 0.8117,
+      "step": 155
+    },
+    {
+      "epoch": 0.3745498199279712,
+      "grad_norm": 1.0381143846448244,
+      "learning_rate": 9.488740904215578e-06,
+      "loss": 0.7949,
+      "step": 156
+    },
+    {
+      "epoch": 0.37695078031212487,
+      "grad_norm": 1.0974151220229578,
+      "learning_rate": 9.47996887145668e-06,
+      "loss": 0.8096,
+      "step": 157
+    },
+    {
+      "epoch": 0.3793517406962785,
+      "grad_norm": 1.0644973845655654,
+      "learning_rate": 9.471126349298557e-06,
+      "loss": 0.769,
+      "step": 158
+    },
+    {
+      "epoch": 0.3817527010804322,
+      "grad_norm": 1.0805369220592416,
+      "learning_rate": 9.46221347687255e-06,
+      "loss": 0.7528,
+      "step": 159
+    },
+    {
+      "epoch": 0.38415366146458585,
+      "grad_norm": 1.0244991912422095,
+      "learning_rate": 9.453230394416914e-06,
+      "loss": 0.7883,
+      "step": 160
+    },
+    {
+      "epoch": 0.3865546218487395,
+      "grad_norm": 0.9661371626174572,
+      "learning_rate": 9.444177243274619e-06,
+      "loss": 0.784,
+      "step": 161
+    },
+    {
+      "epoch": 0.38895558223289317,
+      "grad_norm": 1.3148287207686615,
+      "learning_rate": 9.43505416589111e-06,
+      "loss": 0.7656,
+      "step": 162
+    },
+    {
+      "epoch": 0.39135654261704683,
+      "grad_norm": 1.1619055283617015,
+      "learning_rate": 9.425861305812083e-06,
+      "loss": 0.7824,
+      "step": 163
+    },
+    {
+      "epoch": 0.3937575030012005,
+      "grad_norm": 4.651513081191553,
+      "learning_rate": 9.416598807681221e-06,
+      "loss": 0.8066,
+      "step": 164
+    },
+    {
+      "epoch": 0.39615846338535415,
+      "grad_norm": 0.9479957292008633,
+      "learning_rate": 9.40726681723791e-06,
+      "loss": 0.7651,
+      "step": 165
+    },
+    {
+      "epoch": 0.3985594237695078,
+      "grad_norm": 1.1703185690222349,
+      "learning_rate": 9.397865481314959e-06,
+      "loss": 0.7656,
+      "step": 166
+    },
+    {
+      "epoch": 0.4009603841536615,
+      "grad_norm": 1.0368151311067004,
+      "learning_rate": 9.388394947836278e-06,
+      "loss": 0.7917,
+      "step": 167
+    },
+    {
+      "epoch": 0.40336134453781514,
+      "grad_norm": 2.298562774870953,
+      "learning_rate": 9.37885536581456e-06,
+      "loss": 0.762,
+      "step": 168
+    },
+    {
+      "epoch": 0.4057623049219688,
+      "grad_norm": 1.1062217919442925,
+      "learning_rate": 9.369246885348926e-06,
+      "loss": 0.7585,
+      "step": 169
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 1.173156390813293,
+      "learning_rate": 9.359569657622573e-06,
+      "loss": 0.7797,
+      "step": 170
+    },
+    {
+      "epoch": 0.4105642256902761,
+      "grad_norm": 1.109809941134885,
+      "learning_rate": 9.349823834900396e-06,
+      "loss": 0.7588,
+      "step": 171
+    },
+    {
+      "epoch": 0.4129651860744298,
+      "grad_norm": 1.2813177351957437,
+      "learning_rate": 9.340009570526578e-06,
+      "loss": 0.7616,
+      "step": 172
+    },
+    {
+      "epoch": 0.41536614645858344,
+      "grad_norm": 1.0591641661573232,
+      "learning_rate": 9.330127018922195e-06,
+      "loss": 0.7564,
+      "step": 173
+    },
+    {
+      "epoch": 0.4177671068427371,
+      "grad_norm": 2.376914868004014,
+      "learning_rate": 9.320176335582772e-06,
+      "loss": 0.7366,
+      "step": 174
+    },
+    {
+      "epoch": 0.42016806722689076,
+      "grad_norm": 0.9902616640042359,
+      "learning_rate": 9.310157677075847e-06,
+      "loss": 0.7429,
+      "step": 175
+    },
+    {
+      "epoch": 0.4225690276110444,
+      "grad_norm": 1.6847159971307049,
+      "learning_rate": 9.300071201038503e-06,
+      "loss": 0.7825,
+      "step": 176
+    },
+    {
+      "epoch": 0.4249699879951981,
+      "grad_norm": 0.9942879778667437,
+      "learning_rate": 9.289917066174887e-06,
+      "loss": 0.7318,
+      "step": 177
+    },
+    {
+      "epoch": 0.42737094837935174,
+      "grad_norm": 1.1742665576935563,
+      "learning_rate": 9.27969543225371e-06,
+      "loss": 0.7623,
+      "step": 178
+    },
+    {
+      "epoch": 0.4297719087635054,
+      "grad_norm": 1.2676535006378862,
+      "learning_rate": 9.269406460105742e-06,
+      "loss": 0.7583,
+      "step": 179
+    },
+    {
+      "epoch": 0.43217286914765907,
+      "grad_norm": 1.678798458940733,
+      "learning_rate": 9.259050311621274e-06,
+      "loss": 0.7881,
+      "step": 180
+    },
+    {
+      "epoch": 0.4345738295318127,
+      "grad_norm": 1.1441951682044669,
+      "learning_rate": 9.248627149747573e-06,
+      "loss": 0.7455,
+      "step": 181
+    },
+    {
+      "epoch": 0.4369747899159664,
+      "grad_norm": 1.0055990609873005,
+      "learning_rate": 9.238137138486318e-06,
+      "loss": 0.7613,
+      "step": 182
+    },
+    {
+      "epoch": 0.43937575030012005,
+      "grad_norm": 1.0631388873420178,
+      "learning_rate": 9.227580442891022e-06,
+      "loss": 0.7528,
+      "step": 183
+    },
+    {
+      "epoch": 0.4417767106842737,
+      "grad_norm": 1.0811446737171562,
+      "learning_rate": 9.21695722906443e-06,
+      "loss": 0.7988,
+      "step": 184
+    },
+    {
+      "epoch": 0.44417767106842737,
+      "grad_norm": 3.77472894386223,
+      "learning_rate": 9.206267664155906e-06,
+      "loss": 0.7669,
+      "step": 185
+    },
+    {
+      "epoch": 0.44657863145258103,
+      "grad_norm": 2.5440967403332833,
+      "learning_rate": 9.195511916358813e-06,
+      "loss": 0.7478,
+      "step": 186
+    },
+    {
+      "epoch": 0.4489795918367347,
+      "grad_norm": 1.1995260606009623,
+      "learning_rate": 9.18469015490785e-06,
+      "loss": 0.7637,
+      "step": 187
+    },
+    {
+      "epoch": 0.45138055222088835,
+      "grad_norm": 1.087601696720053,
+      "learning_rate": 9.173802550076402e-06,
+      "loss": 0.7122,
+      "step": 188
+    },
+    {
+      "epoch": 0.453781512605042,
+      "grad_norm": 0.859793070085179,
+      "learning_rate": 9.162849273173857e-06,
+      "loss": 0.7237,
+      "step": 189
+    },
+    {
+      "epoch": 0.4561824729891957,
+      "grad_norm": 0.909405499890903,
+      "learning_rate": 9.151830496542912e-06,
+      "loss": 0.7413,
+      "step": 190
+    },
+    {
+      "epoch": 0.45858343337334934,
+      "grad_norm": 1.1698481579798348,
+      "learning_rate": 9.140746393556853e-06,
+      "loss": 0.7686,
+      "step": 191
+    },
+    {
+      "epoch": 0.460984393757503,
+      "grad_norm": 1.4005910755153028,
+      "learning_rate": 9.129597138616845e-06,
+      "loss": 0.7301,
+      "step": 192
+    },
+    {
+      "epoch": 0.46338535414165666,
+      "grad_norm": 6.016086016376545,
+      "learning_rate": 9.118382907149164e-06,
+      "loss": 0.7871,
+      "step": 193
+    },
+    {
+      "epoch": 0.4657863145258103,
+      "grad_norm": 0.9147643453009918,
+      "learning_rate": 9.107103875602458e-06,
+      "loss": 0.7753,
+      "step": 194
+    },
+    {
+      "epoch": 0.468187274909964,
+      "grad_norm": 1.1762754554445651,
+      "learning_rate": 9.09576022144496e-06,
+      "loss": 0.7764,
+      "step": 195
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 1.175295130468933,
+      "learning_rate": 9.084352123161695e-06,
+      "loss": 0.7912,
+      "step": 196
+    },
+    {
+      "epoch": 0.4729891956782713,
+      "grad_norm": 1.0739318228013277,
+      "learning_rate": 9.07287976025168e-06,
+      "loss": 0.762,
+      "step": 197
+    },
+    {
+      "epoch": 0.47539015606242496,
+      "grad_norm": 0.9934440139468771,
+      "learning_rate": 9.061343313225088e-06,
+      "loss": 0.8003,
+      "step": 198
+    },
+    {
+      "epoch": 0.4777911164465786,
+      "grad_norm": 1.0768642208250674,
+      "learning_rate": 9.04974296360042e-06,
+      "loss": 0.7659,
+      "step": 199
+    },
+    {
+      "epoch": 0.4801920768307323,
+      "grad_norm": 1.1273977823886203,
+      "learning_rate": 9.038078893901634e-06,
+      "loss": 0.7992,
+      "step": 200
+    },
+    {
+      "epoch": 0.48259303721488594,
+      "grad_norm": 1.1987531653944965,
+      "learning_rate": 9.026351287655294e-06,
+      "loss": 0.7932,
+      "step": 201
+    },
+    {
+      "epoch": 0.4849939975990396,
+      "grad_norm": 1.4257297426073774,
+      "learning_rate": 9.014560329387661e-06,
+      "loss": 0.7372,
+      "step": 202
+    },
+    {
+      "epoch": 0.48739495798319327,
+      "grad_norm": 0.8935161112029553,
+      "learning_rate": 9.002706204621802e-06,
+      "loss": 0.7701,
+      "step": 203
+    },
+    {
+      "epoch": 0.4897959183673469,
+      "grad_norm": 1.1445504107150832,
+      "learning_rate": 8.99078909987467e-06,
+      "loss": 0.7937,
+      "step": 204
+    },
+    {
+      "epoch": 0.4921968787515006,
+      "grad_norm": 0.9975014914511301,
+      "learning_rate": 8.978809202654161e-06,
+      "loss": 0.7045,
+      "step": 205
+    },
+    {
+      "epoch": 0.49459783913565425,
+      "grad_norm": 1.566224538850411,
+      "learning_rate": 8.966766701456177e-06,
+      "loss": 0.7665,
+      "step": 206
+    },
+    {
+      "epoch": 0.4969987995198079,
+      "grad_norm": 1.0336200728044336,
+      "learning_rate": 8.954661785761648e-06,
+      "loss": 0.7635,
+      "step": 207
+    },
+    {
+      "epoch": 0.49939975990396157,
+      "grad_norm": 1.2720894224504704,
+      "learning_rate": 8.942494646033555e-06,
+      "loss": 0.7546,
+      "step": 208
+    },
+    {
+      "epoch": 0.5018007202881153,
+      "grad_norm": 1.1200134220326137,
+      "learning_rate": 8.930265473713939e-06,
+      "loss": 0.7826,
+      "step": 209
+    },
+    {
+      "epoch": 0.5042016806722689,
+      "grad_norm": 1.2191868527466778,
+      "learning_rate": 8.917974461220877e-06,
+      "loss": 0.761,
+      "step": 210
+    },
+    {
+      "epoch": 0.5066026410564226,
+      "grad_norm": 0.9495968196976812,
+      "learning_rate": 8.905621801945467e-06,
+      "loss": 0.7817,
+      "step": 211
+    },
+    {
+      "epoch": 0.5090036014405762,
+      "grad_norm": 1.2513351813283156,
+      "learning_rate": 8.893207690248776e-06,
+      "loss": 0.812,
+      "step": 212
+    },
+    {
+      "epoch": 0.5114045618247299,
+      "grad_norm": 0.9020644463847227,
+      "learning_rate": 8.880732321458785e-06,
+      "loss": 0.7583,
+      "step": 213
+    },
+    {
+      "epoch": 0.5138055222088835,
+      "grad_norm": 0.8962757996224714,
+      "learning_rate": 8.868195891867315e-06,
+      "loss": 0.7437,
+      "step": 214
+    },
+    {
+      "epoch": 0.5162064825930373,
+      "grad_norm": 1.5860563857675605,
+      "learning_rate": 8.85559859872694e-06,
+      "loss": 0.7707,
+      "step": 215
+    },
+    {
+      "epoch": 0.5186074429771909,
+      "grad_norm": 0.9207750696190705,
+      "learning_rate": 8.84294064024788e-06,
+      "loss": 0.7405,
+      "step": 216
+    },
+    {
+      "epoch": 0.5210084033613446,
+      "grad_norm": 1.3824162672219853,
+      "learning_rate": 8.83022221559489e-06,
+      "loss": 0.7397,
+      "step": 217
+    },
+    {
+      "epoch": 0.5234093637454982,
+      "grad_norm": 1.0847854025433705,
+      "learning_rate": 8.817443524884119e-06,
+      "loss": 0.7825,
+      "step": 218
+    },
+    {
+      "epoch": 0.5258103241296519,
+      "grad_norm": 0.9427904526881725,
+      "learning_rate": 8.804604769179958e-06,
+      "loss": 0.7744,
+      "step": 219
+    },
+    {
+      "epoch": 0.5282112845138055,
+      "grad_norm": 1.2102888029571814,
+      "learning_rate": 8.791706150491887e-06,
+      "loss": 0.7461,
+      "step": 220
+    },
+    {
+      "epoch": 0.5306122448979592,
+      "grad_norm": 2.09508764328467,
+      "learning_rate": 8.778747871771293e-06,
+      "loss": 0.7135,
+      "step": 221
+    },
+    {
+      "epoch": 0.5330132052821128,
+      "grad_norm": 0.8498652434113725,
+      "learning_rate": 8.765730136908266e-06,
+      "loss": 0.7221,
+      "step": 222
+    },
+    {
+      "epoch": 0.5354141656662665,
+      "grad_norm": 1.12017910455628,
+      "learning_rate": 8.752653150728412e-06,
+      "loss": 0.7779,
+      "step": 223
+    },
+    {
+      "epoch": 0.5378151260504201,
+      "grad_norm": 1.0655695849783837,
+      "learning_rate": 8.739517118989606e-06,
+      "loss": 0.7488,
+      "step": 224
+    },
+    {
+      "epoch": 0.5402160864345739,
+      "grad_norm": 1.119471558248057,
+      "learning_rate": 8.726322248378775e-06,
+      "loss": 0.776,
+      "step": 225
+    },
+    {
+      "epoch": 0.5426170468187275,
+      "grad_norm": 1.0220100387555293,
+      "learning_rate": 8.713068746508633e-06,
+      "loss": 0.7736,
+      "step": 226
+    },
+    {
+      "epoch": 0.5450180072028812,
+      "grad_norm": 0.8814645039349688,
+      "learning_rate": 8.69975682191442e-06,
+      "loss": 0.7324,
+      "step": 227
+    },
+    {
+      "epoch": 0.5474189675870348,
+      "grad_norm": 0.8916406208469574,
+      "learning_rate": 8.68638668405062e-06,
+      "loss": 0.779,
+      "step": 228
+    },
+    {
+      "epoch": 0.5498199279711885,
+      "grad_norm": 7.661689497312271,
+      "learning_rate": 8.672958543287666e-06,
+      "loss": 0.8168,
+      "step": 229
+    },
+    {
+      "epoch": 0.5522208883553421,
+      "grad_norm": 1.2594345178659945,
+      "learning_rate": 8.659472610908628e-06,
+      "loss": 0.7909,
+      "step": 230
+    },
+    {
+      "epoch": 0.5546218487394958,
+      "grad_norm": 1.8799499195734866,
+      "learning_rate": 8.645929099105886e-06,
+      "loss": 0.7636,
+      "step": 231
+    },
+    {
+      "epoch": 0.5570228091236494,
+      "grad_norm": 2.1509512791119114,
+      "learning_rate": 8.632328220977801e-06,
+      "loss": 0.7813,
+      "step": 232
+    },
+    {
+      "epoch": 0.5594237695078031,
+      "grad_norm": 0.9752706676825262,
+      "learning_rate": 8.61867019052535e-06,
+      "loss": 0.7061,
+      "step": 233
+    },
+    {
+      "epoch": 0.5618247298919568,
+      "grad_norm": 0.9454915799985201,
+      "learning_rate": 8.604955222648772e-06,
+      "loss": 0.7505,
+      "step": 234
+    },
+    {
+      "epoch": 0.5642256902761105,
+      "grad_norm": 1.000828182837817,
+      "learning_rate": 8.591183533144172e-06,
+      "loss": 0.7546,
+      "step": 235
+    },
+    {
+      "epoch": 0.5666266506602641,
+      "grad_norm": 0.9228939989072429,
+      "learning_rate": 8.577355338700133e-06,
+      "loss": 0.7675,
+      "step": 236
+    },
+    {
+      "epoch": 0.5690276110444178,
+      "grad_norm": 1.184922039267135,
+      "learning_rate": 8.563470856894316e-06,
+      "loss": 0.7254,
+      "step": 237
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.8820446944758044,
+      "learning_rate": 8.549530306190015e-06,
+      "loss": 0.718,
+      "step": 238
+    },
+    {
+      "epoch": 0.5738295318127251,
+      "grad_norm": 1.1040228215856747,
+      "learning_rate": 8.535533905932739e-06,
+      "loss": 0.7741,
+      "step": 239
+    },
+    {
+      "epoch": 0.5762304921968787,
+      "grad_norm": 0.8713050147519229,
+      "learning_rate": 8.521481876346751e-06,
+      "loss": 0.7724,
+      "step": 240
+    },
+    {
+      "epoch": 0.5786314525810324,
+      "grad_norm": 1.261048501283676,
+      "learning_rate": 8.507374438531606e-06,
+      "loss": 0.7346,
+      "step": 241
+    },
+    {
+      "epoch": 0.581032412965186,
+      "grad_norm": 1.025441969049152,
+      "learning_rate": 8.493211814458674e-06,
+      "loss": 0.7434,
+      "step": 242
+    },
+    {
+      "epoch": 0.5834333733493398,
+      "grad_norm": 0.9922731431688747,
+      "learning_rate": 8.478994226967638e-06,
+      "loss": 0.7537,
+      "step": 243
+    },
+    {
+      "epoch": 0.5858343337334934,
+      "grad_norm": 0.9503319984653047,
+      "learning_rate": 8.464721899763003e-06,
+      "loss": 0.7845,
+      "step": 244
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 1.1876236123837647,
+      "learning_rate": 8.450395057410561e-06,
+      "loss": 0.7469,
+      "step": 245
+    },
+    {
+      "epoch": 0.5906362545018007,
+      "grad_norm": 1.7397436732241518,
+      "learning_rate": 8.436013925333868e-06,
+      "loss": 0.7519,
+      "step": 246
+    },
+    {
+      "epoch": 0.5930372148859544,
+      "grad_norm": 3.561635437191525,
+      "learning_rate": 8.421578729810693e-06,
+      "loss": 0.7558,
+      "step": 247
+    },
+    {
+      "epoch": 0.595438175270108,
+      "grad_norm": 0.8957487481226041,
+      "learning_rate": 8.407089697969458e-06,
+      "loss": 0.7337,
+      "step": 248
+    },
+    {
+      "epoch": 0.5978391356542617,
+      "grad_norm": 0.90662629233352,
+      "learning_rate": 8.392547057785662e-06,
+      "loss": 0.7312,
+      "step": 249
+    },
+    {
+      "epoch": 0.6002400960384153,
+      "grad_norm": 1.2695041036651842,
+      "learning_rate": 8.377951038078303e-06,
+      "loss": 0.7751,
+      "step": 250
+    },
+    {
+      "epoch": 0.602641056422569,
+      "grad_norm": 1.345157120613888,
+      "learning_rate": 8.363301868506264e-06,
+      "loss": 0.7401,
+      "step": 251
+    },
+    {
+      "epoch": 0.6050420168067226,
+      "grad_norm": 1.1702437582981216,
+      "learning_rate": 8.34859977956471e-06,
+      "loss": 0.7508,
+      "step": 252
+    },
+    {
+      "epoch": 0.6074429771908764,
+      "grad_norm": 1.0489855923078621,
+      "learning_rate": 8.33384500258146e-06,
+      "loss": 0.7578,
+      "step": 253
+    },
+    {
+      "epoch": 0.60984393757503,
+      "grad_norm": 0.9685408876120875,
+      "learning_rate": 8.319037769713338e-06,
+      "loss": 0.728,
+      "step": 254
+    },
+    {
+      "epoch": 0.6122448979591837,
+      "grad_norm": 1.3885104010614975,
+      "learning_rate": 8.304178313942536e-06,
+      "loss": 0.7346,
+      "step": 255
+    },
+    {
+      "epoch": 0.6146458583433373,
+      "grad_norm": 1.1866044878022257,
+      "learning_rate": 8.289266869072933e-06,
+      "loss": 0.7666,
+      "step": 256
+    },
+    {
+      "epoch": 0.617046818727491,
+      "grad_norm": 1.0305750345887703,
+      "learning_rate": 8.274303669726427e-06,
+      "loss": 0.8051,
+      "step": 257
+    },
+    {
+      "epoch": 0.6194477791116446,
+      "grad_norm": 1.8492085071792421,
+      "learning_rate": 8.259288951339233e-06,
+      "loss": 0.7967,
+      "step": 258
+    },
+    {
+      "epoch": 0.6218487394957983,
+      "grad_norm": 1.1664540722581158,
+      "learning_rate": 8.244222950158194e-06,
+      "loss": 0.7754,
+      "step": 259
+    },
+    {
+      "epoch": 0.6242496998799519,
+      "grad_norm": 1.1540766467381085,
+      "learning_rate": 8.229105903237045e-06,
+      "loss": 0.7439,
+      "step": 260
+    },
+    {
+      "epoch": 0.6266506602641057,
+      "grad_norm": 1.1934705441556062,
+      "learning_rate": 8.213938048432697e-06,
+      "loss": 0.7563,
+      "step": 261
+    },
+    {
+      "epoch": 0.6290516206482593,
+      "grad_norm": 1.146803985370755,
+      "learning_rate": 8.198719624401493e-06,
+      "loss": 0.7798,
+      "step": 262
+    },
+    {
+      "epoch": 0.631452581032413,
+      "grad_norm": 1.0165065570676493,
+      "learning_rate": 8.183450870595443e-06,
+      "loss": 0.7413,
+      "step": 263
+    },
+    {
+      "epoch": 0.6338535414165666,
+      "grad_norm": 1.5262803590995224,
+      "learning_rate": 8.168132027258467e-06,
+      "loss": 0.7941,
+      "step": 264
+    },
+    {
+      "epoch": 0.6362545018007203,
+      "grad_norm": 1.0571414793861305,
+      "learning_rate": 8.152763335422612e-06,
+      "loss": 0.7839,
+      "step": 265
+    },
+    {
+      "epoch": 0.6386554621848739,
+      "grad_norm": 1.0454099741877119,
+      "learning_rate": 8.13734503690426e-06,
+      "loss": 0.7884,
+      "step": 266
+    },
+    {
+      "epoch": 0.6410564225690276,
+      "grad_norm": 1.3245270490543846,
+      "learning_rate": 8.121877374300318e-06,
+      "loss": 0.7618,
+      "step": 267
+    },
+    {
+      "epoch": 0.6434573829531812,
+      "grad_norm": 0.9697059008882367,
+      "learning_rate": 8.106360590984406e-06,
+      "loss": 0.7538,
+      "step": 268
+    },
+    {
+      "epoch": 0.6458583433373349,
+      "grad_norm": 0.9819086681621175,
+      "learning_rate": 8.090794931103026e-06,
+      "loss": 0.802,
+      "step": 269
+    },
+    {
+      "epoch": 0.6482593037214885,
+      "grad_norm": 1.0499699628185923,
+      "learning_rate": 8.075180639571726e-06,
+      "loss": 0.7553,
+      "step": 270
+    },
+    {
+      "epoch": 0.6506602641056423,
+      "grad_norm": 1.1150101137484323,
+      "learning_rate": 8.059517962071234e-06,
+      "loss": 0.7943,
+      "step": 271
+    },
+    {
+      "epoch": 0.6530612244897959,
+      "grad_norm": 1.2142405538485563,
+      "learning_rate": 8.043807145043604e-06,
+      "loss": 0.7731,
+      "step": 272
+    },
+    {
+      "epoch": 0.6554621848739496,
+      "grad_norm": 1.6154134337294808,
+      "learning_rate": 8.028048435688333e-06,
+      "loss": 0.7863,
+      "step": 273
+    },
+    {
+      "epoch": 0.6578631452581032,
+      "grad_norm": 0.9839829711711955,
+      "learning_rate": 8.012242081958477e-06,
+      "loss": 0.7724,
+      "step": 274
+    },
+    {
+      "epoch": 0.6602641056422569,
+      "grad_norm": 1.2594110387151705,
+      "learning_rate": 7.996388332556735e-06,
+      "loss": 0.7519,
+      "step": 275
+    },
+    {
+      "epoch": 0.6626650660264105,
+      "grad_norm": 1.0696851214819196,
+      "learning_rate": 7.980487436931558e-06,
+      "loss": 0.7736,
+      "step": 276
+    },
+    {
+      "epoch": 0.6650660264105642,
+      "grad_norm": 1.007391516874581,
+      "learning_rate": 7.964539645273204e-06,
+      "loss": 0.7803,
+      "step": 277
+    },
+    {
+      "epoch": 0.6674669867947179,
+      "grad_norm": 1.1895821378331923,
+      "learning_rate": 7.948545208509811e-06,
+      "loss": 0.7286,
+      "step": 278
+    },
+    {
+      "epoch": 0.6698679471788715,
+      "grad_norm": 1.1781445386849876,
+      "learning_rate": 7.932504378303452e-06,
+      "loss": 0.7451,
+      "step": 279
+    },
+    {
+      "epoch": 0.6722689075630253,
+      "grad_norm": 0.9004446486986322,
+      "learning_rate": 7.916417407046166e-06,
+      "loss": 0.7744,
+      "step": 280
+    },
+    {
+      "epoch": 0.6746698679471789,
+      "grad_norm": 1.0504636199086463,
+      "learning_rate": 7.900284547855992e-06,
+      "loss": 0.7189,
+      "step": 281
+    },
+    {
+      "epoch": 0.6770708283313326,
+      "grad_norm": 0.9851224240510926,
+      "learning_rate": 7.884106054572987e-06,
+      "loss": 0.7228,
+      "step": 282
+    },
+    {
+      "epoch": 0.6794717887154862,
+      "grad_norm": 0.882730672015069,
+      "learning_rate": 7.86788218175523e-06,
+      "loss": 0.7606,
+      "step": 283
+    },
+    {
+      "epoch": 0.6818727490996399,
+      "grad_norm": 1.134738248618347,
+      "learning_rate": 7.851613184674821e-06,
+      "loss": 0.7453,
+      "step": 284
+    },
+    {
+      "epoch": 0.6842737094837935,
+      "grad_norm": 1.3550122549643175,
+      "learning_rate": 7.835299319313854e-06,
+      "loss": 0.7346,
+      "step": 285
+    },
+    {
+      "epoch": 0.6866746698679472,
+      "grad_norm": 1.1551976950212515,
+      "learning_rate": 7.818940842360404e-06,
+      "loss": 0.7225,
+      "step": 286
+    },
+    {
+      "epoch": 0.6890756302521008,
+      "grad_norm": 1.0596588721021893,
+      "learning_rate": 7.80253801120447e-06,
+      "loss": 0.7729,
+      "step": 287
+    },
+    {
+      "epoch": 0.6914765906362546,
+      "grad_norm": 2.0352142132248483,
+      "learning_rate": 7.78609108393395e-06,
+      "loss": 0.7651,
+      "step": 288
+    },
+    {
+      "epoch": 0.6938775510204082,
+      "grad_norm": 1.0580145696903516,
+      "learning_rate": 7.769600319330553e-06,
+      "loss": 0.7577,
+      "step": 289
+    },
+    {
+      "epoch": 0.6962785114045619,
+      "grad_norm": 0.9327611537310231,
+      "learning_rate": 7.753065976865745e-06,
+      "loss": 0.7345,
+      "step": 290
+    },
+    {
+      "epoch": 0.6986794717887155,
+      "grad_norm": 0.9177655371636081,
+      "learning_rate": 7.736488316696663e-06,
+      "loss": 0.7542,
+      "step": 291
+    },
+    {
+      "epoch": 0.7010804321728692,
+      "grad_norm": 0.9186582304267394,
+      "learning_rate": 7.719867599662017e-06,
+      "loss": 0.7067,
+      "step": 292
+    },
+    {
+      "epoch": 0.7034813925570228,
+      "grad_norm": 1.4851894689768277,
+      "learning_rate": 7.703204087277989e-06,
+      "loss": 0.7895,
+      "step": 293
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 1.3443334645052298,
+      "learning_rate": 7.686498041734121e-06,
+      "loss": 0.7201,
+      "step": 294
+    },
+    {
+      "epoch": 0.7082833133253301,
+      "grad_norm": 0.9541971519404381,
+      "learning_rate": 7.669749725889182e-06,
+      "loss": 0.7078,
+      "step": 295
+    },
+    {
+      "epoch": 0.7106842737094838,
+      "grad_norm": 0.9343509496893679,
+      "learning_rate": 7.65295940326704e-06,
+      "loss": 0.7449,
+      "step": 296
+    },
+    {
+      "epoch": 0.7130852340936374,
+      "grad_norm": 1.0135831282736736,
+      "learning_rate": 7.636127338052513e-06,
+      "loss": 0.7561,
+      "step": 297
+    },
+    {
+      "epoch": 0.7154861944777912,
+      "grad_norm": 1.2913595649693785,
+      "learning_rate": 7.619253795087209e-06,
+      "loss": 0.7582,
+      "step": 298
+    },
+    {
+      "epoch": 0.7178871548619448,
+      "grad_norm": 0.98172249006896,
+      "learning_rate": 7.602339039865362e-06,
+      "loss": 0.7616,
+      "step": 299
+    },
+    {
+      "epoch": 0.7202881152460985,
+      "grad_norm": 0.9737413536629318,
+      "learning_rate": 7.5853833385296545e-06,
+      "loss": 0.767,
+      "step": 300
+    },
+    {
+      "epoch": 0.7226890756302521,
+      "grad_norm": 0.9292017890894759,
+      "learning_rate": 7.568386957867033e-06,
+      "loss": 0.7535,
+      "step": 301
+    },
+    {
+      "epoch": 0.7250900360144058,
+      "grad_norm": 0.8482575432449314,
+      "learning_rate": 7.5513501653045e-06,
+      "loss": 0.7573,
+      "step": 302
+    },
+    {
+      "epoch": 0.7274909963985594,
+      "grad_norm": 0.9964160968006177,
+      "learning_rate": 7.534273228904916e-06,
+      "loss": 0.7487,
+      "step": 303
+    },
+    {
+      "epoch": 0.7298919567827131,
+      "grad_norm": 1.0416855644496446,
+      "learning_rate": 7.5171564173627795e-06,
+      "loss": 0.7472,
+      "step": 304
+    },
+    {
+      "epoch": 0.7322929171668667,
+      "grad_norm": 1.0226595073884834,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.7682,
+      "step": 305
+    },
+    {
+      "epoch": 0.7346938775510204,
+      "grad_norm": 1.0250925918628377,
+      "learning_rate": 7.482804246761657e-06,
+      "loss": 0.819,
+      "step": 306
+    },
+    {
+      "epoch": 0.737094837935174,
+      "grad_norm": 1.0101595190279031,
+      "learning_rate": 7.465569428211752e-06,
+      "loss": 0.7815,
+      "step": 307
+    },
+    {
+      "epoch": 0.7394957983193278,
+      "grad_norm": 1.0375551725741046,
+      "learning_rate": 7.448295815528956e-06,
+      "loss": 0.7546,
+      "step": 308
+    },
+    {
+      "epoch": 0.7418967587034814,
+      "grad_norm": 0.9524297093471641,
+      "learning_rate": 7.430983680502344e-06,
+      "loss": 0.7651,
+      "step": 309
+    },
+    {
+      "epoch": 0.7442977190876351,
+      "grad_norm": 1.0192202418334808,
+      "learning_rate": 7.413633295527109e-06,
+      "loss": 0.7386,
+      "step": 310
+    },
+    {
+      "epoch": 0.7466986794717887,
+      "grad_norm": 0.9486780543314182,
+      "learning_rate": 7.396244933600285e-06,
+      "loss": 0.768,
+      "step": 311
+    },
+    {
+      "epoch": 0.7490996398559424,
+      "grad_norm": 0.9813092444439941,
+      "learning_rate": 7.378818868316449e-06,
+      "loss": 0.7531,
+      "step": 312
+    },
+    {
+      "epoch": 0.751500600240096,
+      "grad_norm": 0.9112662872131286,
+      "learning_rate": 7.361355373863415e-06,
+      "loss": 0.7513,
+      "step": 313
+    },
+    {
+      "epoch": 0.7539015606242497,
+      "grad_norm": 1.058071811604099,
+      "learning_rate": 7.343854725017919e-06,
+      "loss": 0.7757,
+      "step": 314
+    },
+    {
+      "epoch": 0.7563025210084033,
+      "grad_norm": 0.9009387483744434,
+      "learning_rate": 7.326317197141304e-06,
+      "loss": 0.7458,
+      "step": 315
+    },
+    {
+      "epoch": 0.758703481392557,
+      "grad_norm": 1.020248201280368,
+      "learning_rate": 7.308743066175172e-06,
+      "loss": 0.7707,
+      "step": 316
+    },
+    {
+      "epoch": 0.7611044417767107,
+      "grad_norm": 1.0146874125529126,
+      "learning_rate": 7.291132608637053e-06,
+      "loss": 0.7426,
+      "step": 317
+    },
+    {
+      "epoch": 0.7635054021608644,
+      "grad_norm": 1.0743624752190135,
+      "learning_rate": 7.273486101616057e-06,
+      "loss": 0.7998,
+      "step": 318
+    },
+    {
+      "epoch": 0.765906362545018,
+      "grad_norm": 1.7707907807158567,
+      "learning_rate": 7.255803822768504e-06,
+      "loss": 0.7722,
+      "step": 319
+    },
+    {
+      "epoch": 0.7683073229291717,
+      "grad_norm": 1.0121350667327902,
+      "learning_rate": 7.238086050313563e-06,
+      "loss": 0.7313,
+      "step": 320
+    },
+    {
+      "epoch": 0.7707082833133253,
+      "grad_norm": 1.0163182881965183,
+      "learning_rate": 7.2203330630288714e-06,
+      "loss": 0.7435,
+      "step": 321
+    },
+    {
+      "epoch": 0.773109243697479,
+      "grad_norm": 0.9268275302035212,
+      "learning_rate": 7.202545140246148e-06,
+      "loss": 0.7664,
+      "step": 322
+    },
+    {
+      "epoch": 0.7755102040816326,
+      "grad_norm": 1.2563485488363568,
+      "learning_rate": 7.1847225618467975e-06,
+      "loss": 0.7801,
+      "step": 323
+    },
+    {
+      "epoch": 0.7779111644657863,
+      "grad_norm": 1.037881541942287,
+      "learning_rate": 7.166865608257515e-06,
+      "loss": 0.7652,
+      "step": 324
+    },
+    {
+      "epoch": 0.78031212484994,
+      "grad_norm": 1.3383350176718172,
+      "learning_rate": 7.148974560445859e-06,
+      "loss": 0.7226,
+      "step": 325
+    },
+    {
+      "epoch": 0.7827130852340937,
+      "grad_norm": 1.0578449779959211,
+      "learning_rate": 7.131049699915842e-06,
+      "loss": 0.7552,
+      "step": 326
+    },
+    {
+      "epoch": 0.7851140456182473,
+      "grad_norm": 1.0137416729283089,
+      "learning_rate": 7.113091308703498e-06,
+      "loss": 0.7536,
+      "step": 327
+    },
+    {
+      "epoch": 0.787515006002401,
+      "grad_norm": 1.1642800214358668,
+      "learning_rate": 7.095099669372444e-06,
+      "loss": 0.7488,
+      "step": 328
+    },
+    {
+      "epoch": 0.7899159663865546,
+      "grad_norm": 1.057986883568984,
+      "learning_rate": 7.0770750650094335e-06,
+      "loss": 0.7988,
+      "step": 329
+    },
+    {
+      "epoch": 0.7923169267707083,
+      "grad_norm": 1.0658321245710127,
+      "learning_rate": 7.059017779219904e-06,
+      "loss": 0.7202,
+      "step": 330
+    },
+    {
+      "epoch": 0.7947178871548619,
+      "grad_norm": 1.2955485154946214,
+      "learning_rate": 7.040928096123516e-06,
+      "loss": 0.7656,
+      "step": 331
+    },
+    {
+      "epoch": 0.7971188475390156,
+      "grad_norm": 0.8925229800971378,
+      "learning_rate": 7.022806300349676e-06,
+      "loss": 0.716,
+      "step": 332
+    },
+    {
+      "epoch": 0.7995198079231692,
+      "grad_norm": 1.0187499110626825,
+      "learning_rate": 7.004652677033069e-06,
+      "loss": 0.7473,
+      "step": 333
+    },
+    {
+      "epoch": 0.801920768307323,
+      "grad_norm": 1.5751305697768676,
+      "learning_rate": 6.98646751180916e-06,
+      "loss": 0.7509,
+      "step": 334
+    },
+    {
+      "epoch": 0.8043217286914766,
+      "grad_norm": 1.3546230921711813,
+      "learning_rate": 6.968251090809708e-06,
+      "loss": 0.7695,
+      "step": 335
+    },
+    {
+      "epoch": 0.8067226890756303,
+      "grad_norm": 1.069845095442519,
+      "learning_rate": 6.95000370065826e-06,
+      "loss": 0.7435,
+      "step": 336
+    },
+    {
+      "epoch": 0.8091236494597839,
+      "grad_norm": 0.9844453826512336,
+      "learning_rate": 6.931725628465643e-06,
+      "loss": 0.7542,
+      "step": 337
+    },
+    {
+      "epoch": 0.8115246098439376,
+      "grad_norm": 1.247669840020457,
+      "learning_rate": 6.913417161825449e-06,
+      "loss": 0.7366,
+      "step": 338
+    },
+    {
+      "epoch": 0.8139255702280912,
+      "grad_norm": 0.9839530814071178,
+      "learning_rate": 6.895078588809503e-06,
+      "loss": 0.7235,
+      "step": 339
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 0.9114990748369234,
+      "learning_rate": 6.876710197963334e-06,
+      "loss": 0.7584,
+      "step": 340
+    },
+    {
+      "epoch": 0.8187274909963985,
+      "grad_norm": 0.8893953013528672,
+      "learning_rate": 6.858312278301638e-06,
+      "loss": 0.7466,
+      "step": 341
+    },
+    {
+      "epoch": 0.8211284513805522,
+      "grad_norm": 1.3095523002713856,
+      "learning_rate": 6.839885119303726e-06,
+      "loss": 0.8087,
+      "step": 342
+    },
+    {
+      "epoch": 0.8235294117647058,
+      "grad_norm": 0.9225661035820061,
+      "learning_rate": 6.821429010908972e-06,
+      "loss": 0.7372,
+      "step": 343
+    },
+    {
+      "epoch": 0.8259303721488596,
+      "grad_norm": 0.9913169132532897,
+      "learning_rate": 6.802944243512249e-06,
+      "loss": 0.7756,
+      "step": 344
+    },
+    {
+      "epoch": 0.8283313325330132,
+      "grad_norm": 0.9851272669238657,
+      "learning_rate": 6.78443110795936e-06,
+      "loss": 0.7104,
+      "step": 345
+    },
+    {
+      "epoch": 0.8307322929171669,
+      "grad_norm": 0.8690268038644338,
+      "learning_rate": 6.765889895542465e-06,
+      "loss": 0.771,
+      "step": 346
+    },
+    {
+      "epoch": 0.8331332533013205,
+      "grad_norm": 1.0136014295946223,
+      "learning_rate": 6.747320897995493e-06,
+      "loss": 0.7672,
+      "step": 347
+    },
+    {
+      "epoch": 0.8355342136854742,
+      "grad_norm": 0.9009692165583426,
+      "learning_rate": 6.728724407489554e-06,
+      "loss": 0.7566,
+      "step": 348
+    },
+    {
+      "epoch": 0.8379351740696278,
+      "grad_norm": 3.3801588169217225,
+      "learning_rate": 6.710100716628345e-06,
+      "loss": 0.7636,
+      "step": 349
+    },
+    {
+      "epoch": 0.8403361344537815,
+      "grad_norm": 0.8939669513482729,
+      "learning_rate": 6.691450118443538e-06,
+      "loss": 0.7323,
+      "step": 350
+    },
+    {
+      "epoch": 0.8427370948379351,
+      "grad_norm": 1.256771645476368,
+      "learning_rate": 6.672772906390177e-06,
+      "loss": 0.7878,
+      "step": 351
+    },
+    {
+      "epoch": 0.8451380552220888,
+      "grad_norm": 0.9716979576540683,
+      "learning_rate": 6.65406937434206e-06,
+      "loss": 0.746,
+      "step": 352
+    },
+    {
+      "epoch": 0.8475390156062425,
+      "grad_norm": 1.17294825500255,
+      "learning_rate": 6.635339816587109e-06,
+      "loss": 0.8029,
+      "step": 353
+    },
+    {
+      "epoch": 0.8499399759903962,
+      "grad_norm": 1.1320782160419252,
+      "learning_rate": 6.616584527822745e-06,
+      "loss": 0.7398,
+      "step": 354
+    },
+    {
+      "epoch": 0.8523409363745498,
+      "grad_norm": 0.8285295612933271,
+      "learning_rate": 6.5978038031512505e-06,
+      "loss": 0.7413,
+      "step": 355
+    },
+    {
+      "epoch": 0.8547418967587035,
+      "grad_norm": 1.1319688174607296,
+      "learning_rate": 6.578997938075126e-06,
+      "loss": 0.7815,
+      "step": 356
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.8783242447132844,
+      "learning_rate": 6.560167228492436e-06,
+      "loss": 0.734,
+      "step": 357
+    },
+    {
+      "epoch": 0.8595438175270108,
+      "grad_norm": 1.061138411536176,
+      "learning_rate": 6.5413119706921635e-06,
+      "loss": 0.7205,
+      "step": 358
+    },
+    {
+      "epoch": 0.8619447779111644,
+      "grad_norm": 1.9255346896224161,
+      "learning_rate": 6.522432461349536e-06,
+      "loss": 0.7528,
+      "step": 359
+    },
+    {
+      "epoch": 0.8643457382953181,
+      "grad_norm": 0.9835784047836312,
+      "learning_rate": 6.503528997521365e-06,
+      "loss": 0.7188,
+      "step": 360
+    },
+    {
+      "epoch": 0.8667466986794717,
+      "grad_norm": 1.0231868671892967,
+      "learning_rate": 6.484601876641375e-06,
+      "loss": 0.7469,
+      "step": 361
+    },
+    {
+      "epoch": 0.8691476590636255,
+      "grad_norm": 0.9166994445850244,
+      "learning_rate": 6.465651396515511e-06,
+      "loss": 0.7513,
+      "step": 362
+    },
+    {
+      "epoch": 0.8715486194477791,
+      "grad_norm": 0.9766913854228723,
+      "learning_rate": 6.446677855317265e-06,
+      "loss": 0.7955,
+      "step": 363
+    },
+    {
+      "epoch": 0.8739495798319328,
+      "grad_norm": 1.3198005619305515,
+      "learning_rate": 6.427681551582978e-06,
+      "loss": 0.7519,
+      "step": 364
+    },
+    {
+      "epoch": 0.8763505402160864,
+      "grad_norm": 0.9712835770794745,
+      "learning_rate": 6.408662784207149e-06,
+      "loss": 0.7459,
+      "step": 365
+    },
+    {
+      "epoch": 0.8787515006002401,
+      "grad_norm": 1.0163919411898112,
+      "learning_rate": 6.389621852437723e-06,
+      "loss": 0.7759,
+      "step": 366
+    },
+    {
+      "epoch": 0.8811524609843937,
+      "grad_norm": 0.950248653944803,
+      "learning_rate": 6.370559055871389e-06,
+      "loss": 0.7378,
+      "step": 367
+    },
+    {
+      "epoch": 0.8835534213685474,
+      "grad_norm": 1.1181926812558955,
+      "learning_rate": 6.351474694448865e-06,
+      "loss": 0.746,
+      "step": 368
+    },
+    {
+      "epoch": 0.885954381752701,
+      "grad_norm": 1.037686986955754,
+      "learning_rate": 6.332369068450175e-06,
+      "loss": 0.7656,
+      "step": 369
+    },
+    {
+      "epoch": 0.8883553421368547,
+      "grad_norm": 1.072450361306469,
+      "learning_rate": 6.313242478489934e-06,
+      "loss": 0.7104,
+      "step": 370
+    },
+    {
+      "epoch": 0.8907563025210085,
+      "grad_norm": 1.108167091391112,
+      "learning_rate": 6.294095225512604e-06,
+      "loss": 0.8022,
+      "step": 371
+    },
+    {
+      "epoch": 0.8931572629051621,
+      "grad_norm": 1.722491884002692,
+      "learning_rate": 6.274927610787771e-06,
+      "loss": 0.7242,
+      "step": 372
+    },
+    {
+      "epoch": 0.8955582232893158,
+      "grad_norm": 1.0457660283102586,
+      "learning_rate": 6.255739935905396e-06,
+      "loss": 0.7866,
+      "step": 373
+    },
+    {
+      "epoch": 0.8979591836734694,
+      "grad_norm": 1.6184876219177928,
+      "learning_rate": 6.236532502771078e-06,
+      "loss": 0.7439,
+      "step": 374
+    },
+    {
+      "epoch": 0.9003601440576231,
+      "grad_norm": 1.0062644766522555,
+      "learning_rate": 6.217305613601296e-06,
+      "loss": 0.7334,
+      "step": 375
+    },
+    {
+      "epoch": 0.9027611044417767,
+      "grad_norm": 0.9352218251328956,
+      "learning_rate": 6.198059570918656e-06,
+      "loss": 0.7451,
+      "step": 376
+    },
+    {
+      "epoch": 0.9051620648259304,
+      "grad_norm": 0.9116887661426208,
+      "learning_rate": 6.178794677547138e-06,
+      "loss": 0.7324,
+      "step": 377
+    },
+    {
+      "epoch": 0.907563025210084,
+      "grad_norm": 1.183777769058435,
+      "learning_rate": 6.1595112366073164e-06,
+      "loss": 0.7257,
+      "step": 378
+    },
+    {
+      "epoch": 0.9099639855942377,
+      "grad_norm": 0.9545364548686734,
+      "learning_rate": 6.140209551511609e-06,
+      "loss": 0.708,
+      "step": 379
+    },
+    {
+      "epoch": 0.9123649459783914,
+      "grad_norm": 0.9266052219702813,
+      "learning_rate": 6.120889925959486e-06,
+      "loss": 0.7892,
+      "step": 380
+    },
+    {
+      "epoch": 0.9147659063625451,
+      "grad_norm": 0.9080830124340115,
+      "learning_rate": 6.101552663932704e-06,
+      "loss": 0.7016,
+      "step": 381
+    },
+    {
+      "epoch": 0.9171668667466987,
+      "grad_norm": 1.1299134877349652,
+      "learning_rate": 6.0821980696905145e-06,
+      "loss": 0.7674,
+      "step": 382
+    },
+    {
+      "epoch": 0.9195678271308524,
+      "grad_norm": 0.8451340918186704,
+      "learning_rate": 6.062826447764883e-06,
+      "loss": 0.698,
+      "step": 383
+    },
+    {
+      "epoch": 0.921968787515006,
+      "grad_norm": 0.7924589314809064,
+      "learning_rate": 6.0434381029556945e-06,
+      "loss": 0.7397,
+      "step": 384
+    },
+    {
+      "epoch": 0.9243697478991597,
+      "grad_norm": 0.9045434583742306,
+      "learning_rate": 6.024033340325954e-06,
+      "loss": 0.7425,
+      "step": 385
+    },
+    {
+      "epoch": 0.9267707082833133,
+      "grad_norm": 0.9016007393146936,
+      "learning_rate": 6.004612465196994e-06,
+      "loss": 0.7258,
+      "step": 386
+    },
+    {
+      "epoch": 0.929171668667467,
+      "grad_norm": 1.0646113635207004,
+      "learning_rate": 5.985175783143666e-06,
+      "loss": 0.7614,
+      "step": 387
+    },
+    {
+      "epoch": 0.9315726290516206,
+      "grad_norm": 0.9444488037926984,
+      "learning_rate": 5.965723599989529e-06,
+      "loss": 0.7225,
+      "step": 388
+    },
+    {
+      "epoch": 0.9339735894357744,
+      "grad_norm": 1.1421403843804732,
+      "learning_rate": 5.946256221802052e-06,
+      "loss": 0.7859,
+      "step": 389
+    },
+    {
+      "epoch": 0.936374549819928,
+      "grad_norm": 1.083603518417246,
+      "learning_rate": 5.926773954887777e-06,
+      "loss": 0.778,
+      "step": 390
+    },
+    {
+      "epoch": 0.9387755102040817,
+      "grad_norm": 1.0818704239803636,
+      "learning_rate": 5.907277105787513e-06,
+      "loss": 0.7646,
+      "step": 391
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 1.0705981939700056,
+      "learning_rate": 5.887765981271518e-06,
+      "loss": 0.8131,
+      "step": 392
+    },
+    {
+      "epoch": 0.943577430972389,
+      "grad_norm": 2.2203638089853044,
+      "learning_rate": 5.8682408883346535e-06,
+      "loss": 0.7368,
+      "step": 393
+    },
+    {
+      "epoch": 0.9459783913565426,
+      "grad_norm": 1.0437303875045223,
+      "learning_rate": 5.848702134191571e-06,
+      "loss": 0.7742,
+      "step": 394
+    },
+    {
+      "epoch": 0.9483793517406963,
+      "grad_norm": 1.210376504898421,
+      "learning_rate": 5.829150026271871e-06,
+      "loss": 0.7314,
+      "step": 395
+    },
+    {
+      "epoch": 0.9507803121248499,
+      "grad_norm": 1.1286122534398462,
+      "learning_rate": 5.80958487221527e-06,
+      "loss": 0.7788,
+      "step": 396
+    },
+    {
+      "epoch": 0.9531812725090036,
+      "grad_norm": 1.3543601065822313,
+      "learning_rate": 5.79000697986675e-06,
+      "loss": 0.7606,
+      "step": 397
+    },
+    {
+      "epoch": 0.9555822328931572,
+      "grad_norm": 0.9033985285987017,
+      "learning_rate": 5.7704166572717295e-06,
+      "loss": 0.7275,
+      "step": 398
+    },
+    {
+      "epoch": 0.957983193277311,
+      "grad_norm": 1.6202620989820378,
+      "learning_rate": 5.750814212671202e-06,
+      "loss": 0.7501,
+      "step": 399
+    },
+    {
+      "epoch": 0.9603841536614646,
+      "grad_norm": 1.0808376641943391,
+      "learning_rate": 5.731199954496899e-06,
+      "loss": 0.7872,
+      "step": 400
+    },
+    {
+      "epoch": 0.9627851140456183,
+      "grad_norm": 1.2033579507042218,
+      "learning_rate": 5.711574191366427e-06,
+      "loss": 0.7743,
+      "step": 401
+    },
+    {
+      "epoch": 0.9651860744297719,
+      "grad_norm": 0.9090277632343909,
+      "learning_rate": 5.691937232078415e-06,
+      "loss": 0.7538,
+      "step": 402
+    },
+    {
+      "epoch": 0.9675870348139256,
+      "grad_norm": 0.8618200490078318,
+      "learning_rate": 5.6722893856076596e-06,
+      "loss": 0.7009,
+      "step": 403
+    },
+    {
+      "epoch": 0.9699879951980792,
+      "grad_norm": 0.9175641207469445,
+      "learning_rate": 5.65263096110026e-06,
+      "loss": 0.7577,
+      "step": 404
+    },
+    {
+      "epoch": 0.9723889555822329,
+      "grad_norm": 0.8794915802010296,
+      "learning_rate": 5.632962267868747e-06,
+      "loss": 0.7103,
+      "step": 405
+    },
+    {
+      "epoch": 0.9747899159663865,
+      "grad_norm": 1.0573779393835883,
+      "learning_rate": 5.6132836153872335e-06,
+      "loss": 0.7752,
+      "step": 406
+    },
+    {
+      "epoch": 0.9771908763505402,
+      "grad_norm": 1.0016281052861966,
+      "learning_rate": 5.593595313286526e-06,
+      "loss": 0.7634,
+      "step": 407
+    },
+    {
+      "epoch": 0.9795918367346939,
+      "grad_norm": 1.307171807596152,
+      "learning_rate": 5.573897671349269e-06,
+      "loss": 0.7534,
+      "step": 408
+    },
+    {
+      "epoch": 0.9819927971188476,
+      "grad_norm": 1.0143411203734125,
+      "learning_rate": 5.5541909995050554e-06,
+      "loss": 0.7303,
+      "step": 409
+    },
+    {
+      "epoch": 0.9843937575030012,
+      "grad_norm": 1.010734624581804,
+      "learning_rate": 5.534475607825566e-06,
+      "loss": 0.764,
+      "step": 410
+    },
+    {
+      "epoch": 0.9867947178871549,
+      "grad_norm": 1.2154276169872473,
+      "learning_rate": 5.514751806519673e-06,
+      "loss": 0.7378,
+      "step": 411
+    },
+    {
+      "epoch": 0.9891956782713085,
+      "grad_norm": 0.9686457443348316,
+      "learning_rate": 5.495019905928578e-06,
+      "loss": 0.7392,
+      "step": 412
+    },
+    {
+      "epoch": 0.9915966386554622,
+      "grad_norm": 1.0745017643744474,
+      "learning_rate": 5.475280216520913e-06,
+      "loss": 0.7819,
+      "step": 413
+    },
+    {
+      "epoch": 0.9939975990396158,
+      "grad_norm": 0.999983849780639,
+      "learning_rate": 5.455533048887868e-06,
+      "loss": 0.7569,
+      "step": 414
+    },
+    {
+      "epoch": 0.9963985594237695,
+      "grad_norm": 1.02702252315643,
+      "learning_rate": 5.435778713738292e-06,
+      "loss": 0.7627,
+      "step": 415
+    },
+    {
+      "epoch": 0.9987995198079231,
+      "grad_norm": 1.0724028498080733,
+      "learning_rate": 5.416017521893813e-06,
+      "loss": 0.7009,
+      "step": 416
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.0724028498080733,
+      "learning_rate": 5.396249784283943e-06,
+      "loss": 0.8865,
+      "step": 417
+    },
+    {
+      "epoch": 1.0024009603841537,
+      "grad_norm": 2.101877070085442,
+      "learning_rate": 5.3764758119411905e-06,
+      "loss": 0.7009,
+      "step": 418
+    },
+    {
+      "epoch": 1.0048019207683074,
+      "grad_norm": 1.118846557228715,
+      "learning_rate": 5.356695915996162e-06,
+      "loss": 0.7542,
+      "step": 419
+    },
+    {
+      "epoch": 1.007202881152461,
+      "grad_norm": 1.156865195159883,
+      "learning_rate": 5.336910407672668e-06,
+      "loss": 0.6836,
+      "step": 420
+    },
+    {
+      "epoch": 1.0096038415366146,
+      "grad_norm": 0.9278578282699763,
+      "learning_rate": 5.317119598282823e-06,
+      "loss": 0.7363,
+      "step": 421
+    },
+    {
+      "epoch": 1.0120048019207684,
+      "grad_norm": 0.995653093708434,
+      "learning_rate": 5.297323799222156e-06,
+      "loss": 0.7663,
+      "step": 422
+    },
+    {
+      "epoch": 1.014405762304922,
+      "grad_norm": 1.1905262761143818,
+      "learning_rate": 5.277523321964701e-06,
+      "loss": 0.7088,
+      "step": 423
+    },
+    {
+      "epoch": 1.0168067226890756,
+      "grad_norm": 0.8602717681140455,
+      "learning_rate": 5.257718478058105e-06,
+      "loss": 0.7622,
+      "step": 424
+    },
+    {
+      "epoch": 1.0192076830732293,
+      "grad_norm": 1.380911494413432,
+      "learning_rate": 5.237909579118713e-06,
+      "loss": 0.7616,
+      "step": 425
+    },
+    {
+      "epoch": 1.021608643457383,
+      "grad_norm": 8.665839441934292,
+      "learning_rate": 5.218096936826681e-06,
+      "loss": 0.7419,
+      "step": 426
+    },
+    {
+      "epoch": 1.0240096038415367,
+      "grad_norm": 0.9358352128566729,
+      "learning_rate": 5.198280862921062e-06,
+      "loss": 0.7515,
+      "step": 427
+    },
+    {
+      "epoch": 1.0264105642256902,
+      "grad_norm": 1.3142767223698053,
+      "learning_rate": 5.178461669194903e-06,
+      "loss": 0.7266,
+      "step": 428
+    },
+    {
+      "epoch": 1.028811524609844,
+      "grad_norm": 1.050719187044544,
+      "learning_rate": 5.15863966749034e-06,
+      "loss": 0.7296,
+      "step": 429
+    },
+    {
+      "epoch": 1.0312124849939976,
+      "grad_norm": 1.302115134296509,
+      "learning_rate": 5.138815169693687e-06,
+      "loss": 0.6843,
+      "step": 430
+    },
+    {
+      "epoch": 1.0336134453781514,
+      "grad_norm": 0.847885176823766,
+      "learning_rate": 5.118988487730537e-06,
+      "loss": 0.7294,
+      "step": 431
+    },
+    {
+      "epoch": 1.0360144057623049,
+      "grad_norm": 0.9180649724528399,
+      "learning_rate": 5.099159933560851e-06,
+      "loss": 0.6877,
+      "step": 432
+    },
+    {
+      "epoch": 1.0384153661464586,
+      "grad_norm": 0.9090661115202275,
+      "learning_rate": 5.07932981917404e-06,
+      "loss": 0.6987,
+      "step": 433
+    },
+    {
+      "epoch": 1.0408163265306123,
+      "grad_norm": 0.8573995996185877,
+      "learning_rate": 5.059498456584072e-06,
+      "loss": 0.6693,
+      "step": 434
+    },
+    {
+      "epoch": 1.043217286914766,
+      "grad_norm": 0.8185459787831719,
+      "learning_rate": 5.039666157824549e-06,
+      "loss": 0.6714,
+      "step": 435
+    },
+    {
+      "epoch": 1.0456182472989195,
+      "grad_norm": 0.8618136173846955,
+      "learning_rate": 5.019833234943806e-06,
+      "loss": 0.743,
+      "step": 436
+    },
+    {
+      "epoch": 1.0480192076830732,
+      "grad_norm": 1.435576312926133,
+      "learning_rate": 5e-06,
+      "loss": 0.7218,
+      "step": 437
+    },
+    {
+      "epoch": 1.050420168067227,
+      "grad_norm": 0.7341581025321086,
+      "learning_rate": 4.980166765056194e-06,
+      "loss": 0.7147,
+      "step": 438
+    },
+    {
+      "epoch": 1.0528211284513807,
+      "grad_norm": 1.081533239673927,
+      "learning_rate": 4.960333842175453e-06,
+      "loss": 0.6944,
+      "step": 439
+    },
+    {
+      "epoch": 1.0552220888355341,
+      "grad_norm": 0.9479569729309318,
+      "learning_rate": 4.940501543415929e-06,
+      "loss": 0.7085,
+      "step": 440
+    },
+    {
+      "epoch": 1.0576230492196879,
+      "grad_norm": 0.8342266084401958,
+      "learning_rate": 4.9206701808259605e-06,
+      "loss": 0.6474,
+      "step": 441
+    },
+    {
+      "epoch": 1.0600240096038416,
+      "grad_norm": 0.9085685056051219,
+      "learning_rate": 4.900840066439151e-06,
+      "loss": 0.6667,
+      "step": 442
+    },
+    {
+      "epoch": 1.0624249699879953,
+      "grad_norm": 0.8889802086577271,
+      "learning_rate": 4.881011512269464e-06,
+      "loss": 0.6867,
+      "step": 443
+    },
+    {
+      "epoch": 1.0648259303721488,
+      "grad_norm": 0.9332804081329865,
+      "learning_rate": 4.861184830306314e-06,
+      "loss": 0.6801,
+      "step": 444
+    },
+    {
+      "epoch": 1.0672268907563025,
+      "grad_norm": 0.9868828565183504,
+      "learning_rate": 4.841360332509663e-06,
+      "loss": 0.7641,
+      "step": 445
+    },
+    {
+      "epoch": 1.0696278511404562,
+      "grad_norm": 1.2155044715175538,
+      "learning_rate": 4.821538330805098e-06,
+      "loss": 0.6743,
+      "step": 446
+    },
+    {
+      "epoch": 1.07202881152461,
+      "grad_norm": 0.9925350547990021,
+      "learning_rate": 4.801719137078939e-06,
+      "loss": 0.6516,
+      "step": 447
+    },
+    {
+      "epoch": 1.0744297719087634,
+      "grad_norm": 1.0348738488040936,
+      "learning_rate": 4.781903063173321e-06,
+      "loss": 0.6509,
+      "step": 448
+    },
+    {
+      "epoch": 1.0768307322929171,
+      "grad_norm": 0.836392400812354,
+      "learning_rate": 4.762090420881289e-06,
+      "loss": 0.6267,
+      "step": 449
+    },
+    {
+      "epoch": 1.0792316926770709,
+      "grad_norm": 0.9188934737658707,
+      "learning_rate": 4.742281521941897e-06,
+      "loss": 0.6933,
+      "step": 450
+    },
+    {
+      "epoch": 1.0816326530612246,
+      "grad_norm": 1.2483588900096583,
+      "learning_rate": 4.7224766780353005e-06,
+      "loss": 0.701,
+      "step": 451
+    },
+    {
+      "epoch": 1.084033613445378,
+      "grad_norm": 1.099152868995137,
+      "learning_rate": 4.7026762007778455e-06,
+      "loss": 0.6968,
+      "step": 452
+    },
+    {
+      "epoch": 1.0864345738295318,
+      "grad_norm": 0.8641730346092144,
+      "learning_rate": 4.682880401717178e-06,
+      "loss": 0.6913,
+      "step": 453
+    },
+    {
+      "epoch": 1.0888355342136855,
+      "grad_norm": 1.0362371171789713,
+      "learning_rate": 4.663089592327333e-06,
+      "loss": 0.663,
+      "step": 454
+    },
+    {
+      "epoch": 1.0912364945978392,
+      "grad_norm": 1.1665659853493717,
+      "learning_rate": 4.643304084003839e-06,
+      "loss": 0.6402,
+      "step": 455
+    },
+    {
+      "epoch": 1.0936374549819927,
+      "grad_norm": 1.042312121994228,
+      "learning_rate": 4.62352418805881e-06,
+      "loss": 0.6993,
+      "step": 456
+    },
+    {
+      "epoch": 1.0960384153661464,
+      "grad_norm": 1.0156806331552348,
+      "learning_rate": 4.603750215716057e-06,
+      "loss": 0.6469,
+      "step": 457
+    },
+    {
+      "epoch": 1.0984393757503002,
+      "grad_norm": 1.0037418962257996,
+      "learning_rate": 4.583982478106189e-06,
+      "loss": 0.6736,
+      "step": 458
+    },
+    {
+      "epoch": 1.1008403361344539,
+      "grad_norm": 1.0639389320851615,
+      "learning_rate": 4.564221286261709e-06,
+      "loss": 0.6973,
+      "step": 459
+    },
+    {
+      "epoch": 1.1032412965186074,
+      "grad_norm": 6.957024323901044,
+      "learning_rate": 4.544466951112132e-06,
+      "loss": 0.6831,
+      "step": 460
+    },
+    {
+      "epoch": 1.105642256902761,
+      "grad_norm": 0.882371596489962,
+      "learning_rate": 4.524719783479088e-06,
+      "loss": 0.6545,
+      "step": 461
+    },
+    {
+      "epoch": 1.1080432172869148,
+      "grad_norm": 1.0995617865014164,
+      "learning_rate": 4.504980094071424e-06,
+      "loss": 0.675,
+      "step": 462
+    },
+    {
+      "epoch": 1.1104441776710685,
+      "grad_norm": 0.8925989987844686,
+      "learning_rate": 4.485248193480328e-06,
+      "loss": 0.6371,
+      "step": 463
+    },
+    {
+      "epoch": 1.112845138055222,
+      "grad_norm": 1.000513181879756,
+      "learning_rate": 4.465524392174437e-06,
+      "loss": 0.6369,
+      "step": 464
+    },
+    {
+      "epoch": 1.1152460984393757,
+      "grad_norm": 2.259472809190549,
+      "learning_rate": 4.445809000494945e-06,
+      "loss": 0.6465,
+      "step": 465
+    },
+    {
+      "epoch": 1.1176470588235294,
+      "grad_norm": 0.959502156080397,
+      "learning_rate": 4.426102328650732e-06,
+      "loss": 0.6307,
+      "step": 466
+    },
+    {
+      "epoch": 1.1200480192076832,
+      "grad_norm": 1.0884936132184861,
+      "learning_rate": 4.4064046867134755e-06,
+      "loss": 0.6523,
+      "step": 467
+    },
+    {
+      "epoch": 1.1224489795918366,
+      "grad_norm": 1.2362423608257147,
+      "learning_rate": 4.386716384612768e-06,
+      "loss": 0.7073,
+      "step": 468
+    },
+    {
+      "epoch": 1.1248499399759904,
+      "grad_norm": 1.154930197028087,
+      "learning_rate": 4.367037732131254e-06,
+      "loss": 0.6702,
+      "step": 469
+    },
+    {
+      "epoch": 1.127250900360144,
+      "grad_norm": 0.9675716457470993,
+      "learning_rate": 4.347369038899744e-06,
+      "loss": 0.6306,
+      "step": 470
+    },
+    {
+      "epoch": 1.1296518607442978,
+      "grad_norm": 1.2123183177500714,
+      "learning_rate": 4.327710614392341e-06,
+      "loss": 0.6422,
+      "step": 471
+    },
+    {
+      "epoch": 1.1320528211284513,
+      "grad_norm": 0.8783262340992644,
+      "learning_rate": 4.308062767921586e-06,
+      "loss": 0.6408,
+      "step": 472
+    },
+    {
+      "epoch": 1.134453781512605,
+      "grad_norm": 1.0020692197104342,
+      "learning_rate": 4.2884258086335755e-06,
+      "loss": 0.6726,
+      "step": 473
+    },
+    {
+      "epoch": 1.1368547418967587,
+      "grad_norm": 0.9984867727924627,
+      "learning_rate": 4.268800045503102e-06,
+      "loss": 0.6972,
+      "step": 474
+    },
+    {
+      "epoch": 1.1392557022809124,
+      "grad_norm": 0.9177095305540808,
+      "learning_rate": 4.249185787328798e-06,
+      "loss": 0.6482,
+      "step": 475
+    },
+    {
+      "epoch": 1.141656662665066,
+      "grad_norm": 0.9030081661554377,
+      "learning_rate": 4.229583342728273e-06,
+      "loss": 0.6777,
+      "step": 476
+    },
+    {
+      "epoch": 1.1440576230492197,
+      "grad_norm": 0.8540231006160938,
+      "learning_rate": 4.209993020133251e-06,
+      "loss": 0.6577,
+      "step": 477
+    },
+    {
+      "epoch": 1.1464585834333734,
+      "grad_norm": 0.8097479049668175,
+      "learning_rate": 4.190415127784731e-06,
+      "loss": 0.7251,
+      "step": 478
+    },
+    {
+      "epoch": 1.148859543817527,
+      "grad_norm": 0.8970081520393531,
+      "learning_rate": 4.1708499737281305e-06,
+      "loss": 0.6796,
+      "step": 479
+    },
+    {
+      "epoch": 1.1512605042016806,
+      "grad_norm": 0.8654962875772526,
+      "learning_rate": 4.151297865808432e-06,
+      "loss": 0.7018,
+      "step": 480
+    },
+    {
+      "epoch": 1.1536614645858343,
+      "grad_norm": 0.9548312252503125,
+      "learning_rate": 4.131759111665349e-06,
+      "loss": 0.6414,
+      "step": 481
+    },
+    {
+      "epoch": 1.156062424969988,
+      "grad_norm": 0.9134696774056807,
+      "learning_rate": 4.1122340187284845e-06,
+      "loss": 0.6587,
+      "step": 482
+    },
+    {
+      "epoch": 1.1584633853541417,
+      "grad_norm": 1.047296786406303,
+      "learning_rate": 4.092722894212488e-06,
+      "loss": 0.6275,
+      "step": 483
+    },
+    {
+      "epoch": 1.1608643457382952,
+      "grad_norm": 1.3504571393502145,
+      "learning_rate": 4.073226045112225e-06,
+      "loss": 0.6679,
+      "step": 484
+    },
+    {
+      "epoch": 1.163265306122449,
+      "grad_norm": 0.8152705410339258,
+      "learning_rate": 4.053743778197951e-06,
+      "loss": 0.6142,
+      "step": 485
+    },
+    {
+      "epoch": 1.1656662665066027,
+      "grad_norm": 1.0444369910181297,
+      "learning_rate": 4.0342764000104715e-06,
+      "loss": 0.6897,
+      "step": 486
+    },
+    {
+      "epoch": 1.1680672268907564,
+      "grad_norm": 1.2835376928592126,
+      "learning_rate": 4.014824216856336e-06,
+      "loss": 0.6095,
+      "step": 487
+    },
+    {
+      "epoch": 1.1704681872749099,
+      "grad_norm": 0.9870823918768562,
+      "learning_rate": 3.995387534803006e-06,
+      "loss": 0.7001,
+      "step": 488
+    },
+    {
+      "epoch": 1.1728691476590636,
+      "grad_norm": 0.9161419881683542,
+      "learning_rate": 3.975966659674048e-06,
+      "loss": 0.6836,
+      "step": 489
+    },
+    {
+      "epoch": 1.1752701080432173,
+      "grad_norm": 0.8363382965648142,
+      "learning_rate": 3.956561897044306e-06,
+      "loss": 0.6305,
+      "step": 490
+    },
+    {
+      "epoch": 1.177671068427371,
+      "grad_norm": 0.9517408930013426,
+      "learning_rate": 3.937173552235117e-06,
+      "loss": 0.6359,
+      "step": 491
+    },
+    {
+      "epoch": 1.1800720288115247,
+      "grad_norm": 0.960064443656299,
+      "learning_rate": 3.917801930309486e-06,
+      "loss": 0.677,
+      "step": 492
+    },
+    {
+      "epoch": 1.1824729891956782,
+      "grad_norm": 1.0082757605439017,
+      "learning_rate": 3.898447336067297e-06,
+      "loss": 0.6813,
+      "step": 493
+    },
+    {
+      "epoch": 1.184873949579832,
+      "grad_norm": 1.270622611887631,
+      "learning_rate": 3.879110074040515e-06,
+      "loss": 0.6447,
+      "step": 494
+    },
+    {
+      "epoch": 1.1872749099639857,
+      "grad_norm": 0.9018388456061602,
+      "learning_rate": 3.859790448488394e-06,
+      "loss": 0.6143,
+      "step": 495
+    },
+    {
+      "epoch": 1.1896758703481392,
+      "grad_norm": 0.8687733757060934,
+      "learning_rate": 3.840488763392685e-06,
+      "loss": 0.6744,
+      "step": 496
+    },
+    {
+      "epoch": 1.1920768307322929,
+      "grad_norm": 1.0303761890291854,
+      "learning_rate": 3.821205322452863e-06,
+      "loss": 0.6109,
+      "step": 497
+    },
+    {
+      "epoch": 1.1944777911164466,
+      "grad_norm": 1.0063806235226265,
+      "learning_rate": 3.8019404290813456e-06,
+      "loss": 0.6678,
+      "step": 498
+    },
+    {
+      "epoch": 1.1968787515006003,
+      "grad_norm": 0.8611797107872082,
+      "learning_rate": 3.782694386398706e-06,
+      "loss": 0.6521,
+      "step": 499
+    },
+    {
+      "epoch": 1.199279711884754,
+      "grad_norm": 0.8940169915802657,
+      "learning_rate": 3.7634674972289227e-06,
+      "loss": 0.6709,
+      "step": 500
+    },
+    {
+      "epoch": 1.2016806722689075,
+      "grad_norm": 0.9657961801617352,
+      "learning_rate": 3.7442600640946045e-06,
+      "loss": 0.6212,
+      "step": 501
+    },
+    {
+      "epoch": 1.2040816326530612,
+      "grad_norm": 1.1496491496114696,
+      "learning_rate": 3.72507238921223e-06,
+      "loss": 0.6767,
+      "step": 502
+    },
+    {
+      "epoch": 1.206482593037215,
+      "grad_norm": 1.0842958983301503,
+      "learning_rate": 3.705904774487396e-06,
+      "loss": 0.6599,
+      "step": 503
+    },
+    {
+      "epoch": 1.2088835534213684,
+      "grad_norm": 1.0318159594309126,
+      "learning_rate": 3.686757521510068e-06,
+      "loss": 0.6881,
+      "step": 504
+    },
+    {
+      "epoch": 1.2112845138055222,
+      "grad_norm": 0.8003629139237494,
+      "learning_rate": 3.667630931549826e-06,
+      "loss": 0.6486,
+      "step": 505
+    },
+    {
+      "epoch": 1.2136854741896759,
+      "grad_norm": 1.0293538346323636,
+      "learning_rate": 3.648525305551136e-06,
+      "loss": 0.6552,
+      "step": 506
+    },
+    {
+      "epoch": 1.2160864345738296,
+      "grad_norm": 1.1816027470046149,
+      "learning_rate": 3.6294409441286133e-06,
+      "loss": 0.6239,
+      "step": 507
+    },
+    {
+      "epoch": 1.2184873949579833,
+      "grad_norm": 1.2274500784176232,
+      "learning_rate": 3.610378147562279e-06,
+      "loss": 0.6419,
+      "step": 508
+    },
+    {
+      "epoch": 1.2208883553421368,
+      "grad_norm": 0.879327609945451,
+      "learning_rate": 3.5913372157928515e-06,
+      "loss": 0.5977,
+      "step": 509
+    },
+    {
+      "epoch": 1.2232893157262905,
+      "grad_norm": 1.1499847415517088,
+      "learning_rate": 3.572318448417023e-06,
+      "loss": 0.6294,
+      "step": 510
+    },
+    {
+      "epoch": 1.2256902761104442,
+      "grad_norm": 0.9738966730369417,
+      "learning_rate": 3.553322144682737e-06,
+      "loss": 0.6488,
+      "step": 511
+    },
+    {
+      "epoch": 1.2280912364945977,
+      "grad_norm": 0.7975428195744296,
+      "learning_rate": 3.5343486034844897e-06,
+      "loss": 0.612,
+      "step": 512
+    },
+    {
+      "epoch": 1.2304921968787514,
+      "grad_norm": 0.8715338954561731,
+      "learning_rate": 3.5153981233586277e-06,
+      "loss": 0.6948,
+      "step": 513
+    },
+    {
+      "epoch": 1.2328931572629052,
+      "grad_norm": 0.999917456418209,
+      "learning_rate": 3.4964710024786354e-06,
+      "loss": 0.6684,
+      "step": 514
+    },
+    {
+      "epoch": 1.2352941176470589,
+      "grad_norm": 0.8967614161402051,
+      "learning_rate": 3.477567538650466e-06,
+      "loss": 0.6531,
+      "step": 515
+    },
+    {
+      "epoch": 1.2376950780312126,
+      "grad_norm": 1.2866563272030653,
+      "learning_rate": 3.458688029307839e-06,
+      "loss": 0.6038,
+      "step": 516
+    },
+    {
+      "epoch": 1.240096038415366,
+      "grad_norm": 1.2858647511107744,
+      "learning_rate": 3.439832771507565e-06,
+      "loss": 0.6571,
+      "step": 517
+    },
+    {
+      "epoch": 1.2424969987995198,
+      "grad_norm": 1.521910339081235,
+      "learning_rate": 3.4210020619248762e-06,
+      "loss": 0.6566,
+      "step": 518
+    },
+    {
+      "epoch": 1.2448979591836735,
+      "grad_norm": 8.941545760275048,
+      "learning_rate": 3.402196196848751e-06,
+      "loss": 0.6737,
+      "step": 519
+    },
+    {
+      "epoch": 1.247298919567827,
+      "grad_norm": 0.9956406367743204,
+      "learning_rate": 3.383415472177256e-06,
+      "loss": 0.6264,
+      "step": 520
+    },
+    {
+      "epoch": 1.2496998799519807,
+      "grad_norm": 0.8862696839179252,
+      "learning_rate": 3.3646601834128924e-06,
+      "loss": 0.6635,
+      "step": 521
+    },
+    {
+      "epoch": 1.2521008403361344,
+      "grad_norm": 0.9772838899127305,
+      "learning_rate": 3.3459306256579405e-06,
+      "loss": 0.6577,
+      "step": 522
+    },
+    {
+      "epoch": 1.2545018007202882,
+      "grad_norm": 0.9432621976883124,
+      "learning_rate": 3.3272270936098243e-06,
+      "loss": 0.6506,
+      "step": 523
+    },
+    {
+      "epoch": 1.2569027611044419,
+      "grad_norm": 1.9109659903891167,
+      "learning_rate": 3.3085498815564644e-06,
+      "loss": 0.6658,
+      "step": 524
+    },
+    {
+      "epoch": 1.2593037214885954,
+      "grad_norm": 0.8480535123546864,
+      "learning_rate": 3.289899283371657e-06,
+      "loss": 0.6229,
+      "step": 525
+    },
+    {
+      "epoch": 1.261704681872749,
+      "grad_norm": 0.9441953680609311,
+      "learning_rate": 3.2712755925104478e-06,
+      "loss": 0.6811,
+      "step": 526
+    },
+    {
+      "epoch": 1.2641056422569028,
+      "grad_norm": 0.8296489881948692,
+      "learning_rate": 3.252679102004509e-06,
+      "loss": 0.6777,
+      "step": 527
+    },
+    {
+      "epoch": 1.2665066026410563,
+      "grad_norm": 3.3056754185406376,
+      "learning_rate": 3.234110104457536e-06,
+      "loss": 0.6511,
+      "step": 528
+    },
+    {
+      "epoch": 1.26890756302521,
+      "grad_norm": 1.1292461057910061,
+      "learning_rate": 3.2155688920406415e-06,
+      "loss": 0.6316,
+      "step": 529
+    },
+    {
+      "epoch": 1.2713085234093637,
+      "grad_norm": 0.9500459227262518,
+      "learning_rate": 3.1970557564877524e-06,
+      "loss": 0.6055,
+      "step": 530
+    },
+    {
+      "epoch": 1.2737094837935174,
+      "grad_norm": 1.2673542521457937,
+      "learning_rate": 3.178570989091028e-06,
+      "loss": 0.6341,
+      "step": 531
+    },
+    {
+      "epoch": 1.2761104441776712,
+      "grad_norm": 0.9947728211445109,
+      "learning_rate": 3.1601148806962757e-06,
+      "loss": 0.6683,
+      "step": 532
+    },
+    {
+      "epoch": 1.2785114045618247,
+      "grad_norm": 0.9593776784610404,
+      "learning_rate": 3.141687721698363e-06,
+      "loss": 0.5981,
+      "step": 533
+    },
+    {
+      "epoch": 1.2809123649459784,
+      "grad_norm": 1.0033764100278546,
+      "learning_rate": 3.123289802036667e-06,
+      "loss": 0.6233,
+      "step": 534
+    },
+    {
+      "epoch": 1.283313325330132,
+      "grad_norm": 0.9047192571279472,
+      "learning_rate": 3.104921411190499e-06,
+      "loss": 0.6555,
+      "step": 535
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.9716764971679062,
+      "learning_rate": 3.0865828381745515e-06,
+      "loss": 0.709,
+      "step": 536
+    },
+    {
+      "epoch": 1.2881152460984393,
+      "grad_norm": 0.9776107500234306,
+      "learning_rate": 3.0682743715343565e-06,
+      "loss": 0.6639,
+      "step": 537
+    },
+    {
+      "epoch": 1.290516206482593,
+      "grad_norm": 1.2084524925872613,
+      "learning_rate": 3.049996299341742e-06,
+      "loss": 0.6664,
+      "step": 538
+    },
+    {
+      "epoch": 1.2929171668667467,
+      "grad_norm": 1.1629000749386234,
+      "learning_rate": 3.0317489091902936e-06,
+      "loss": 0.6515,
+      "step": 539
+    },
+    {
+      "epoch": 1.2953181272509005,
+      "grad_norm": 0.8738746819122408,
+      "learning_rate": 3.0135324881908405e-06,
+      "loss": 0.6378,
+      "step": 540
+    },
+    {
+      "epoch": 1.297719087635054,
+      "grad_norm": 0.9071468993169257,
+      "learning_rate": 2.995347322966933e-06,
+      "loss": 0.6271,
+      "step": 541
+    },
+    {
+      "epoch": 1.3001200480192077,
+      "grad_norm": 0.8527725942665851,
+      "learning_rate": 2.977193699650325e-06,
+      "loss": 0.6566,
+      "step": 542
+    },
+    {
+      "epoch": 1.3025210084033614,
+      "grad_norm": 1.821515983286086,
+      "learning_rate": 2.959071903876486e-06,
+      "loss": 0.6526,
+      "step": 543
+    },
+    {
+      "epoch": 1.3049219687875149,
+      "grad_norm": 2.6168941096292655,
+      "learning_rate": 2.9409822207800976e-06,
+      "loss": 0.6432,
+      "step": 544
+    },
+    {
+      "epoch": 1.3073229291716686,
+      "grad_norm": 1.1340068418135858,
+      "learning_rate": 2.9229249349905686e-06,
+      "loss": 0.6097,
+      "step": 545
+    },
+    {
+      "epoch": 1.3097238895558223,
+      "grad_norm": 1.065777330021333,
+      "learning_rate": 2.9049003306275575e-06,
+      "loss": 0.6513,
+      "step": 546
+    },
+    {
+      "epoch": 1.312124849939976,
+      "grad_norm": 0.9840631248620156,
+      "learning_rate": 2.886908691296504e-06,
+      "loss": 0.6957,
+      "step": 547
+    },
+    {
+      "epoch": 1.3145258103241297,
+      "grad_norm": 0.9275156432371783,
+      "learning_rate": 2.86895030008416e-06,
+      "loss": 0.6222,
+      "step": 548
+    },
+    {
+      "epoch": 1.3169267707082832,
+      "grad_norm": 1.0694369857718884,
+      "learning_rate": 2.851025439554142e-06,
+      "loss": 0.6292,
+      "step": 549
+    },
+    {
+      "epoch": 1.319327731092437,
+      "grad_norm": 0.9195088026501728,
+      "learning_rate": 2.8331343917424857e-06,
+      "loss": 0.6293,
+      "step": 550
+    },
+    {
+      "epoch": 1.3217286914765907,
+      "grad_norm": 1.0440622673055318,
+      "learning_rate": 2.8152774381532033e-06,
+      "loss": 0.6494,
+      "step": 551
+    },
+    {
+      "epoch": 1.3241296518607442,
+      "grad_norm": 0.9585224467319371,
+      "learning_rate": 2.797454859753853e-06,
+      "loss": 0.6377,
+      "step": 552
+    },
+    {
+      "epoch": 1.3265306122448979,
+      "grad_norm": 0.986356865601444,
+      "learning_rate": 2.7796669369711294e-06,
+      "loss": 0.6078,
+      "step": 553
+    },
+    {
+      "epoch": 1.3289315726290516,
+      "grad_norm": 0.8852031958630902,
+      "learning_rate": 2.761913949686438e-06,
+      "loss": 0.6663,
+      "step": 554
+    },
+    {
+      "epoch": 1.3313325330132053,
+      "grad_norm": 1.0194560710233276,
+      "learning_rate": 2.744196177231498e-06,
+      "loss": 0.6471,
+      "step": 555
+    },
+    {
+      "epoch": 1.333733493397359,
+      "grad_norm": 1.1092428908617034,
+      "learning_rate": 2.726513898383944e-06,
+      "loss": 0.6319,
+      "step": 556
+    },
+    {
+      "epoch": 1.3361344537815127,
+      "grad_norm": 1.046228165586162,
+      "learning_rate": 2.708867391362948e-06,
+      "loss": 0.6316,
+      "step": 557
+    },
+    {
+      "epoch": 1.3385354141656662,
+      "grad_norm": 0.9384421616577757,
+      "learning_rate": 2.6912569338248317e-06,
+      "loss": 0.6404,
+      "step": 558
+    },
+    {
+      "epoch": 1.34093637454982,
+      "grad_norm": 1.0979431829143493,
+      "learning_rate": 2.673682802858697e-06,
+      "loss": 0.6528,
+      "step": 559
+    },
+    {
+      "epoch": 1.3433373349339737,
+      "grad_norm": 0.8782235843379402,
+      "learning_rate": 2.656145274982081e-06,
+      "loss": 0.6455,
+      "step": 560
+    },
+    {
+      "epoch": 1.3457382953181272,
+      "grad_norm": 0.9821501158024878,
+      "learning_rate": 2.6386446261365874e-06,
+      "loss": 0.6829,
+      "step": 561
+    },
+    {
+      "epoch": 1.3481392557022809,
+      "grad_norm": 1.7793178730445558,
+      "learning_rate": 2.621181131683551e-06,
+      "loss": 0.7075,
+      "step": 562
+    },
+    {
+      "epoch": 1.3505402160864346,
+      "grad_norm": 1.1270971633767486,
+      "learning_rate": 2.603755066399718e-06,
+      "loss": 0.6341,
+      "step": 563
+    },
+    {
+      "epoch": 1.3529411764705883,
+      "grad_norm": 0.9286077170161989,
+      "learning_rate": 2.5863667044728924e-06,
+      "loss": 0.6825,
+      "step": 564
+    },
+    {
+      "epoch": 1.355342136854742,
+      "grad_norm": 0.7617565172187906,
+      "learning_rate": 2.5690163194976576e-06,
+      "loss": 0.5877,
+      "step": 565
+    },
+    {
+      "epoch": 1.3577430972388955,
+      "grad_norm": 0.9361260944487725,
+      "learning_rate": 2.5517041844710456e-06,
+      "loss": 0.6975,
+      "step": 566
+    },
+    {
+      "epoch": 1.3601440576230492,
+      "grad_norm": 1.0586142116171426,
+      "learning_rate": 2.5344305717882487e-06,
+      "loss": 0.6781,
+      "step": 567
+    },
+    {
+      "epoch": 1.362545018007203,
+      "grad_norm": 0.8572775669908461,
+      "learning_rate": 2.5171957532383453e-06,
+      "loss": 0.6484,
+      "step": 568
+    },
+    {
+      "epoch": 1.3649459783913565,
+      "grad_norm": 0.8072710536841113,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.6215,
+      "step": 569
+    },
+    {
+      "epoch": 1.3673469387755102,
+      "grad_norm": 1.1210751153626373,
+      "learning_rate": 2.4828435826372204e-06,
+      "loss": 0.6611,
+      "step": 570
+    },
+    {
+      "epoch": 1.3697478991596639,
+      "grad_norm": 0.9536882704959704,
+      "learning_rate": 2.465726771095086e-06,
+      "loss": 0.5999,
+      "step": 571
+    },
+    {
+      "epoch": 1.3721488595438176,
+      "grad_norm": 1.261934257875031,
+      "learning_rate": 2.448649834695503e-06,
+      "loss": 0.6723,
+      "step": 572
+    },
+    {
+      "epoch": 1.3745498199279713,
+      "grad_norm": 0.9371878075006924,
+      "learning_rate": 2.4316130421329696e-06,
+      "loss": 0.6731,
+      "step": 573
+    },
+    {
+      "epoch": 1.3769507803121248,
+      "grad_norm": 0.8608482332532424,
+      "learning_rate": 2.4146166614703454e-06,
+      "loss": 0.6823,
+      "step": 574
+    },
+    {
+      "epoch": 1.3793517406962785,
+      "grad_norm": 0.9664794593332436,
+      "learning_rate": 2.3976609601346395e-06,
+      "loss": 0.6453,
+      "step": 575
+    },
+    {
+      "epoch": 1.3817527010804322,
+      "grad_norm": 0.968355670405567,
+      "learning_rate": 2.3807462049127934e-06,
+      "loss": 0.6024,
+      "step": 576
+    },
+    {
+      "epoch": 1.3841536614645857,
+      "grad_norm": 2.444260082739265,
+      "learning_rate": 2.363872661947488e-06,
+      "loss": 0.6582,
+      "step": 577
+    },
+    {
+      "epoch": 1.3865546218487395,
+      "grad_norm": 0.8703597669538309,
+      "learning_rate": 2.3470405967329605e-06,
+      "loss": 0.6522,
+      "step": 578
+    },
+    {
+      "epoch": 1.3889555822328932,
+      "grad_norm": 0.9906523957085589,
+      "learning_rate": 2.33025027411082e-06,
+      "loss": 0.6417,
+      "step": 579
+    },
+    {
+      "epoch": 1.3913565426170469,
+      "grad_norm": 2.495843697923558,
+      "learning_rate": 2.3135019582658803e-06,
+      "loss": 0.6468,
+      "step": 580
+    },
+    {
+      "epoch": 1.3937575030012006,
+      "grad_norm": 1.062237654307874,
+      "learning_rate": 2.296795912722014e-06,
+      "loss": 0.7482,
+      "step": 581
+    },
+    {
+      "epoch": 1.396158463385354,
+      "grad_norm": 1.2408978869613996,
+      "learning_rate": 2.2801324003379854e-06,
+      "loss": 0.6637,
+      "step": 582
+    },
+    {
+      "epoch": 1.3985594237695078,
+      "grad_norm": 0.9095853615754681,
+      "learning_rate": 2.263511683303339e-06,
+      "loss": 0.6371,
+      "step": 583
+    },
+    {
+      "epoch": 1.4009603841536615,
+      "grad_norm": 0.9690759667373599,
+      "learning_rate": 2.246934023134257e-06,
+      "loss": 0.6622,
+      "step": 584
+    },
+    {
+      "epoch": 1.403361344537815,
+      "grad_norm": 0.9341036768906378,
+      "learning_rate": 2.230399680669449e-06,
+      "loss": 0.6833,
+      "step": 585
+    },
+    {
+      "epoch": 1.4057623049219687,
+      "grad_norm": 0.8871623641888806,
+      "learning_rate": 2.213908916066052e-06,
+      "loss": 0.6327,
+      "step": 586
+    },
+    {
+      "epoch": 1.4081632653061225,
+      "grad_norm": 0.8972465832232572,
+      "learning_rate": 2.1974619887955294e-06,
+      "loss": 0.6534,
+      "step": 587
+    },
+    {
+      "epoch": 1.4105642256902762,
+      "grad_norm": 1.9887286961869182,
+      "learning_rate": 2.1810591576395985e-06,
+      "loss": 0.6357,
+      "step": 588
+    },
+    {
+      "epoch": 1.41296518607443,
+      "grad_norm": 0.899752751900282,
+      "learning_rate": 2.1647006806861472e-06,
+      "loss": 0.6344,
+      "step": 589
+    },
+    {
+      "epoch": 1.4153661464585834,
+      "grad_norm": 2.3738841741244374,
+      "learning_rate": 2.148386815325179e-06,
+      "loss": 0.6297,
+      "step": 590
+    },
+    {
+      "epoch": 1.417767106842737,
+      "grad_norm": 1.1780835394591138,
+      "learning_rate": 2.132117818244771e-06,
+      "loss": 0.6695,
+      "step": 591
+    },
+    {
+      "epoch": 1.4201680672268908,
+      "grad_norm": 0.940256461882646,
+      "learning_rate": 2.1158939454270138e-06,
+      "loss": 0.6213,
+      "step": 592
+    },
+    {
+      "epoch": 1.4225690276110443,
+      "grad_norm": 1.1302731548409901,
+      "learning_rate": 2.09971545214401e-06,
+      "loss": 0.6848,
+      "step": 593
+    },
+    {
+      "epoch": 1.424969987995198,
+      "grad_norm": 0.8890669967126053,
+      "learning_rate": 2.083582592953837e-06,
+      "loss": 0.6168,
+      "step": 594
+    },
+    {
+      "epoch": 1.4273709483793517,
+      "grad_norm": 0.7964330127150799,
+      "learning_rate": 2.0674956216965484e-06,
+      "loss": 0.63,
+      "step": 595
+    },
+    {
+      "epoch": 1.4297719087635055,
+      "grad_norm": 1.0716409115935557,
+      "learning_rate": 2.05145479149019e-06,
+      "loss": 0.6524,
+      "step": 596
+    },
+    {
+      "epoch": 1.4321728691476592,
+      "grad_norm": 1.0124952323959022,
+      "learning_rate": 2.0354603547267985e-06,
+      "loss": 0.6721,
+      "step": 597
+    },
+    {
+      "epoch": 1.4345738295318127,
+      "grad_norm": 0.977022328573683,
+      "learning_rate": 2.019512563068443e-06,
+      "loss": 0.6292,
+      "step": 598
+    },
+    {
+      "epoch": 1.4369747899159664,
+      "grad_norm": 1.1217389949243721,
+      "learning_rate": 2.0036116674432653e-06,
+      "loss": 0.6326,
+      "step": 599
+    },
+    {
+      "epoch": 1.43937575030012,
+      "grad_norm": 0.8774778075409905,
+      "learning_rate": 1.9877579180415252e-06,
+      "loss": 0.6111,
+      "step": 600
+    },
+    {
+      "epoch": 1.4417767106842736,
+      "grad_norm": 0.9297967785330995,
+      "learning_rate": 1.971951564311668e-06,
+      "loss": 0.6636,
+      "step": 601
+    },
+    {
+      "epoch": 1.4441776710684273,
+      "grad_norm": 1.1183920012608857,
+      "learning_rate": 1.956192854956397e-06,
+      "loss": 0.7022,
+      "step": 602
+    },
+    {
+      "epoch": 1.446578631452581,
+      "grad_norm": 0.8658496834568494,
+      "learning_rate": 1.9404820379287677e-06,
+      "loss": 0.6807,
+      "step": 603
+    },
+    {
+      "epoch": 1.4489795918367347,
+      "grad_norm": 0.9111194634371569,
+      "learning_rate": 1.924819360428276e-06,
+      "loss": 0.6499,
+      "step": 604
+    },
+    {
+      "epoch": 1.4513805522208885,
+      "grad_norm": 0.8210926504989612,
+      "learning_rate": 1.9092050688969736e-06,
+      "loss": 0.5997,
+      "step": 605
+    },
+    {
+      "epoch": 1.453781512605042,
+      "grad_norm": 0.9508028705856567,
+      "learning_rate": 1.8936394090155952e-06,
+      "loss": 0.6234,
+      "step": 606
+    },
+    {
+      "epoch": 1.4561824729891957,
+      "grad_norm": 0.8253729688748952,
+      "learning_rate": 1.8781226256996838e-06,
+      "loss": 0.6343,
+      "step": 607
+    },
+    {
+      "epoch": 1.4585834333733494,
+      "grad_norm": 1.1301843863674312,
+      "learning_rate": 1.8626549630957397e-06,
+      "loss": 0.6384,
+      "step": 608
+    },
+    {
+      "epoch": 1.4609843937575029,
+      "grad_norm": 1.005290256520289,
+      "learning_rate": 1.8472366645773892e-06,
+      "loss": 0.6391,
+      "step": 609
+    },
+    {
+      "epoch": 1.4633853541416566,
+      "grad_norm": 1.1339132680403525,
+      "learning_rate": 1.831867972741534e-06,
+      "loss": 0.7299,
+      "step": 610
+    },
+    {
+      "epoch": 1.4657863145258103,
+      "grad_norm": 1.6091153520949204,
+      "learning_rate": 1.8165491294045596e-06,
+      "loss": 0.6607,
+      "step": 611
+    },
+    {
+      "epoch": 1.468187274909964,
+      "grad_norm": 0.8949044081385531,
+      "learning_rate": 1.8012803755985098e-06,
+      "loss": 0.6645,
+      "step": 612
+    },
+    {
+      "epoch": 1.4705882352941178,
+      "grad_norm": 1.0476157250288862,
+      "learning_rate": 1.7860619515673034e-06,
+      "loss": 0.6667,
+      "step": 613
+    },
+    {
+      "epoch": 1.4729891956782712,
+      "grad_norm": 1.0829061637937194,
+      "learning_rate": 1.7708940967629567e-06,
+      "loss": 0.6317,
+      "step": 614
+    },
+    {
+      "epoch": 1.475390156062425,
+      "grad_norm": 0.9370432461748385,
+      "learning_rate": 1.7557770498418087e-06,
+      "loss": 0.6737,
+      "step": 615
+    },
+    {
+      "epoch": 1.4777911164465787,
+      "grad_norm": 1.0882844485223084,
+      "learning_rate": 1.740711048660767e-06,
+      "loss": 0.6478,
+      "step": 616
+    },
+    {
+      "epoch": 1.4801920768307322,
+      "grad_norm": 8.920120491127792,
+      "learning_rate": 1.7256963302735752e-06,
+      "loss": 0.6864,
+      "step": 617
+    },
+    {
+      "epoch": 1.482593037214886,
+      "grad_norm": 0.9549261538889966,
+      "learning_rate": 1.7107331309270686e-06,
+      "loss": 0.651,
+      "step": 618
+    },
+    {
+      "epoch": 1.4849939975990396,
+      "grad_norm": 2.261202226088013,
+      "learning_rate": 1.6958216860574661e-06,
+      "loss": 0.6273,
+      "step": 619
+    },
+    {
+      "epoch": 1.4873949579831933,
+      "grad_norm": 0.930837304019007,
+      "learning_rate": 1.6809622302866623e-06,
+      "loss": 0.6645,
+      "step": 620
+    },
+    {
+      "epoch": 1.489795918367347,
+      "grad_norm": 1.216556634979396,
+      "learning_rate": 1.6661549974185426e-06,
+      "loss": 0.6767,
+      "step": 621
+    },
+    {
+      "epoch": 1.4921968787515005,
+      "grad_norm": 0.8558885688663144,
+      "learning_rate": 1.6514002204352919e-06,
+      "loss": 0.5963,
+      "step": 622
+    },
+    {
+      "epoch": 1.4945978391356542,
+      "grad_norm": 0.8947167354414174,
+      "learning_rate": 1.6366981314937374e-06,
+      "loss": 0.6748,
+      "step": 623
+    },
+    {
+      "epoch": 1.496998799519808,
+      "grad_norm": 0.9245974493657283,
+      "learning_rate": 1.6220489619216988e-06,
+      "loss": 0.6465,
+      "step": 624
+    },
+    {
+      "epoch": 1.4993997599039615,
+      "grad_norm": 0.7421955754193266,
+      "learning_rate": 1.6074529422143398e-06,
+      "loss": 0.6198,
+      "step": 625
+    },
+    {
+      "epoch": 1.5018007202881152,
+      "grad_norm": 1.0226755510539118,
+      "learning_rate": 1.5929103020305441e-06,
+      "loss": 0.6737,
+      "step": 626
+    },
+    {
+      "epoch": 1.504201680672269,
+      "grad_norm": 0.9001021170854256,
+      "learning_rate": 1.5784212701893088e-06,
+      "loss": 0.6197,
+      "step": 627
+    },
+    {
+      "epoch": 1.5066026410564226,
+      "grad_norm": 1.0389230808512446,
+      "learning_rate": 1.5639860746661339e-06,
+      "loss": 0.6617,
+      "step": 628
+    },
+    {
+      "epoch": 1.5090036014405763,
+      "grad_norm": 0.9388777166315837,
+      "learning_rate": 1.549604942589441e-06,
+      "loss": 0.6912,
+      "step": 629
+    },
+    {
+      "epoch": 1.51140456182473,
+      "grad_norm": 0.9751733282640802,
+      "learning_rate": 1.5352781002369976e-06,
+      "loss": 0.6452,
+      "step": 630
+    },
+    {
+      "epoch": 1.5138055222088835,
+      "grad_norm": 0.7877825500209034,
+      "learning_rate": 1.521005773032362e-06,
+      "loss": 0.6328,
+      "step": 631
+    },
+    {
+      "epoch": 1.5162064825930373,
+      "grad_norm": 1.0048986074663675,
+      "learning_rate": 1.5067881855413275e-06,
+      "loss": 0.6717,
+      "step": 632
+    },
+    {
+      "epoch": 1.5186074429771907,
+      "grad_norm": 1.0356464031510044,
+      "learning_rate": 1.4926255614683931e-06,
+      "loss": 0.6301,
+      "step": 633
+    },
+    {
+      "epoch": 1.5210084033613445,
+      "grad_norm": 1.1045877070154857,
+      "learning_rate": 1.4785181236532514e-06,
+      "loss": 0.6495,
+      "step": 634
+    },
+    {
+      "epoch": 1.5234093637454982,
+      "grad_norm": 1.0326108777946468,
+      "learning_rate": 1.4644660940672628e-06,
+      "loss": 0.6601,
+      "step": 635
+    },
+    {
+      "epoch": 1.525810324129652,
+      "grad_norm": 0.8225636887377143,
+      "learning_rate": 1.450469693809986e-06,
+      "loss": 0.6578,
+      "step": 636
+    },
+    {
+      "epoch": 1.5282112845138056,
+      "grad_norm": 1.0518805255531551,
+      "learning_rate": 1.4365291431056871e-06,
+      "loss": 0.6113,
+      "step": 637
+    },
+    {
+      "epoch": 1.5306122448979593,
+      "grad_norm": 2.5860144771962066,
+      "learning_rate": 1.4226446612998673e-06,
+      "loss": 0.6298,
+      "step": 638
+    },
+    {
+      "epoch": 1.5330132052821128,
+      "grad_norm": 1.111493995682213,
+      "learning_rate": 1.4088164668558302e-06,
+      "loss": 0.615,
+      "step": 639
+    },
+    {
+      "epoch": 1.5354141656662665,
+      "grad_norm": 0.9342207765376362,
+      "learning_rate": 1.39504477735123e-06,
+      "loss": 0.6636,
+      "step": 640
+    },
+    {
+      "epoch": 1.53781512605042,
+      "grad_norm": 0.9206445859863835,
+      "learning_rate": 1.3813298094746491e-06,
+      "loss": 0.6278,
+      "step": 641
+    },
+    {
+      "epoch": 1.5402160864345738,
+      "grad_norm": 1.0324765311389028,
+      "learning_rate": 1.3676717790222e-06,
+      "loss": 0.64,
+      "step": 642
+    },
+    {
+      "epoch": 1.5426170468187275,
+      "grad_norm": 1.225786679799285,
+      "learning_rate": 1.354070900894115e-06,
+      "loss": 0.6522,
+      "step": 643
+    },
+    {
+      "epoch": 1.5450180072028812,
+      "grad_norm": 0.9687208223950486,
+      "learning_rate": 1.340527389091374e-06,
+      "loss": 0.6247,
+      "step": 644
+    },
+    {
+      "epoch": 1.547418967587035,
+      "grad_norm": 0.8339357278892652,
+      "learning_rate": 1.3270414567123342e-06,
+      "loss": 0.6777,
+      "step": 645
+    },
+    {
+      "epoch": 1.5498199279711886,
+      "grad_norm": 0.9391801557957058,
+      "learning_rate": 1.3136133159493803e-06,
+      "loss": 0.7764,
+      "step": 646
+    },
+    {
+      "epoch": 1.552220888355342,
+      "grad_norm": 1.1081348736358358,
+      "learning_rate": 1.3002431780855817e-06,
+      "loss": 0.6648,
+      "step": 647
+    },
+    {
+      "epoch": 1.5546218487394958,
+      "grad_norm": 1.2909105123595979,
+      "learning_rate": 1.2869312534913686e-06,
+      "loss": 0.6731,
+      "step": 648
+    },
+    {
+      "epoch": 1.5570228091236493,
+      "grad_norm": 2.0962675285135908,
+      "learning_rate": 1.2736777516212267e-06,
+      "loss": 0.713,
+      "step": 649
+    },
+    {
+      "epoch": 1.559423769507803,
+      "grad_norm": 0.9514467073135442,
+      "learning_rate": 1.260482881010396e-06,
+      "loss": 0.5859,
+      "step": 650
+    },
+    {
+      "epoch": 1.5618247298919568,
+      "grad_norm": 0.8913685423120479,
+      "learning_rate": 1.2473468492715896e-06,
+      "loss": 0.6406,
+      "step": 651
+    },
+    {
+      "epoch": 1.5642256902761105,
+      "grad_norm": 0.9198640943911467,
+      "learning_rate": 1.2342698630917337e-06,
+      "loss": 0.6289,
+      "step": 652
+    },
+    {
+      "epoch": 1.5666266506602642,
+      "grad_norm": 0.9220782597157949,
+      "learning_rate": 1.2212521282287093e-06,
+      "loss": 0.6582,
+      "step": 653
+    },
+    {
+      "epoch": 1.569027611044418,
+      "grad_norm": 1.0495774693223259,
+      "learning_rate": 1.2082938495081143e-06,
+      "loss": 0.6248,
+      "step": 654
+    },
+    {
+      "epoch": 1.5714285714285714,
+      "grad_norm": 1.7192639331315858,
+      "learning_rate": 1.1953952308200428e-06,
+      "loss": 0.6172,
+      "step": 655
+    },
+    {
+      "epoch": 1.5738295318127251,
+      "grad_norm": 0.9156640691230766,
+      "learning_rate": 1.1825564751158825e-06,
+      "loss": 0.6684,
+      "step": 656
+    },
+    {
+      "epoch": 1.5762304921968786,
+      "grad_norm": 0.8912057501633746,
+      "learning_rate": 1.1697777844051105e-06,
+      "loss": 0.6742,
+      "step": 657
+    },
+    {
+      "epoch": 1.5786314525810323,
+      "grad_norm": 0.9486921526679506,
+      "learning_rate": 1.1570593597521201e-06,
+      "loss": 0.6114,
+      "step": 658
+    },
+    {
+      "epoch": 1.581032412965186,
+      "grad_norm": 0.9544253927956883,
+      "learning_rate": 1.144401401273062e-06,
+      "loss": 0.6097,
+      "step": 659
+    },
+    {
+      "epoch": 1.5834333733493398,
+      "grad_norm": 1.3504169424667136,
+      "learning_rate": 1.1318041081326868e-06,
+      "loss": 0.6328,
+      "step": 660
+    },
+    {
+      "epoch": 1.5858343337334935,
+      "grad_norm": 0.8965813935254673,
+      "learning_rate": 1.1192676785412154e-06,
+      "loss": 0.6642,
+      "step": 661
+    },
+    {
+      "epoch": 1.5882352941176472,
+      "grad_norm": 1.0133574586256462,
+      "learning_rate": 1.1067923097512256e-06,
+      "loss": 0.6539,
+      "step": 662
+    },
+    {
+      "epoch": 1.5906362545018007,
+      "grad_norm": 0.9508952698284318,
+      "learning_rate": 1.0943781980545332e-06,
+      "loss": 0.6681,
+      "step": 663
+    },
+    {
+      "epoch": 1.5930372148859544,
+      "grad_norm": 1.472278929509015,
+      "learning_rate": 1.082025538779124e-06,
+      "loss": 0.6957,
+      "step": 664
+    },
+    {
+      "epoch": 1.595438175270108,
+      "grad_norm": 1.030931088954498,
+      "learning_rate": 1.0697345262860638e-06,
+      "loss": 0.6383,
+      "step": 665
+    },
+    {
+      "epoch": 1.5978391356542616,
+      "grad_norm": 1.1342385358407325,
+      "learning_rate": 1.0575053539664465e-06,
+      "loss": 0.616,
+      "step": 666
+    },
+    {
+      "epoch": 1.6002400960384153,
+      "grad_norm": 0.9671979722590744,
+      "learning_rate": 1.0453382142383545e-06,
+      "loss": 0.675,
+      "step": 667
+    },
+    {
+      "epoch": 1.602641056422569,
+      "grad_norm": 0.9287771382738991,
+      "learning_rate": 1.0332332985438248e-06,
+      "loss": 0.6366,
+      "step": 668
+    },
+    {
+      "epoch": 1.6050420168067228,
+      "grad_norm": 0.9472315620503476,
+      "learning_rate": 1.0211907973458391e-06,
+      "loss": 0.6264,
+      "step": 669
+    },
+    {
+      "epoch": 1.6074429771908765,
+      "grad_norm": 1.087340362754727,
+      "learning_rate": 1.0092109001253314e-06,
+      "loss": 0.6398,
+      "step": 670
+    },
+    {
+      "epoch": 1.60984393757503,
+      "grad_norm": 0.8115527735674969,
+      "learning_rate": 9.972937953781985e-07,
+      "loss": 0.6273,
+      "step": 671
+    },
+    {
+      "epoch": 1.6122448979591837,
+      "grad_norm": 0.9337618001262841,
+      "learning_rate": 9.85439670612341e-07,
+      "loss": 0.6363,
+      "step": 672
+    },
+    {
+      "epoch": 1.6146458583433372,
+      "grad_norm": 1.5207042640095867,
+      "learning_rate": 9.73648712344707e-07,
+      "loss": 0.6502,
+      "step": 673
+    },
+    {
+      "epoch": 1.617046818727491,
+      "grad_norm": 1.085665654159603,
+      "learning_rate": 9.619211060983674e-07,
+      "loss": 0.6889,
+      "step": 674
+    },
+    {
+      "epoch": 1.6194477791116446,
+      "grad_norm": 0.9586829488001999,
+      "learning_rate": 9.502570363995839e-07,
+      "loss": 0.7141,
+      "step": 675
+    },
+    {
+      "epoch": 1.6218487394957983,
+      "grad_norm": 1.3208377530379118,
+      "learning_rate": 9.386566867749131e-07,
+      "loss": 0.6788,
+      "step": 676
+    },
+    {
+      "epoch": 1.624249699879952,
+      "grad_norm": 0.9717132751178416,
+      "learning_rate": 9.271202397483214e-07,
+      "loss": 0.6222,
+      "step": 677
+    },
+    {
+      "epoch": 1.6266506602641058,
+      "grad_norm": 0.8691308355211956,
+      "learning_rate": 9.15647876838306e-07,
+      "loss": 0.643,
+      "step": 678
+    },
+    {
+      "epoch": 1.6290516206482593,
+      "grad_norm": 0.9820836736882421,
+      "learning_rate": 9.042397785550405e-07,
+      "loss": 0.681,
+      "step": 679
+    },
+    {
+      "epoch": 1.631452581032413,
+      "grad_norm": 1.0360078246750115,
+      "learning_rate": 8.928961243975437e-07,
+      "loss": 0.628,
+      "step": 680
+    },
+    {
+      "epoch": 1.6338535414165665,
+      "grad_norm": 1.0282198489236734,
+      "learning_rate": 8.816170928508367e-07,
+      "loss": 0.6961,
+      "step": 681
+    },
+    {
+      "epoch": 1.6362545018007202,
+      "grad_norm": 1.4419881007160427,
+      "learning_rate": 8.704028613831561e-07,
+      "loss": 0.657,
+      "step": 682
+    },
+    {
+      "epoch": 1.638655462184874,
+      "grad_norm": 0.9684178540852127,
+      "learning_rate": 8.592536064431467e-07,
+      "loss": 0.6684,
+      "step": 683
+    },
+    {
+      "epoch": 1.6410564225690276,
+      "grad_norm": 0.8737370302144639,
+      "learning_rate": 8.481695034570892e-07,
+      "loss": 0.6826,
+      "step": 684
+    },
+    {
+      "epoch": 1.6434573829531813,
+      "grad_norm": 1.9051074779808914,
+      "learning_rate": 8.371507268261436e-07,
+      "loss": 0.6422,
+      "step": 685
+    },
+    {
+      "epoch": 1.645858343337335,
+      "grad_norm": 5.528134895709504,
+      "learning_rate": 8.261974499235987e-07,
+      "loss": 0.6956,
+      "step": 686
+    },
+    {
+      "epoch": 1.6482593037214885,
+      "grad_norm": 0.9288503984193149,
+      "learning_rate": 8.153098450921514e-07,
+      "loss": 0.6465,
+      "step": 687
+    },
+    {
+      "epoch": 1.6506602641056423,
+      "grad_norm": 0.8890540558215465,
+      "learning_rate": 8.044880836411889e-07,
+      "loss": 0.6786,
+      "step": 688
+    },
+    {
+      "epoch": 1.6530612244897958,
+      "grad_norm": 1.0942079760094963,
+      "learning_rate": 7.937323358440935e-07,
+      "loss": 0.6615,
+      "step": 689
+    },
+    {
+      "epoch": 1.6554621848739495,
+      "grad_norm": 1.3854108815443495,
+      "learning_rate": 7.830427709355726e-07,
+      "loss": 0.6713,
+      "step": 690
+    },
+    {
+      "epoch": 1.6578631452581032,
+      "grad_norm": 1.8458381248660314,
+      "learning_rate": 7.724195571089787e-07,
+      "loss": 0.666,
+      "step": 691
+    },
+    {
+      "epoch": 1.660264105642257,
+      "grad_norm": 0.9665077364422517,
+      "learning_rate": 7.618628615136825e-07,
+      "loss": 0.6585,
+      "step": 692
+    },
+    {
+      "epoch": 1.6626650660264106,
+      "grad_norm": 1.2255421786519085,
+      "learning_rate": 7.513728502524286e-07,
+      "loss": 0.6579,
+      "step": 693
+    },
+    {
+      "epoch": 1.6650660264105643,
+      "grad_norm": 1.0829000788514598,
+      "learning_rate": 7.409496883787276e-07,
+      "loss": 0.6705,
+      "step": 694
+    },
+    {
+      "epoch": 1.667466986794718,
+      "grad_norm": 1.224215492415608,
+      "learning_rate": 7.305935398942598e-07,
+      "loss": 0.6362,
+      "step": 695
+    },
+    {
+      "epoch": 1.6698679471788715,
+      "grad_norm": 1.00281395524098,
+      "learning_rate": 7.203045677462922e-07,
+      "loss": 0.6416,
+      "step": 696
+    },
+    {
+      "epoch": 1.6722689075630253,
+      "grad_norm": 0.8844080649716427,
+      "learning_rate": 7.100829338251147e-07,
+      "loss": 0.6706,
+      "step": 697
+    },
+    {
+      "epoch": 1.6746698679471788,
+      "grad_norm": 1.3784393546774785,
+      "learning_rate": 6.999287989614972e-07,
+      "loss": 0.6008,
+      "step": 698
+    },
+    {
+      "epoch": 1.6770708283313325,
+      "grad_norm": 1.2142211468312185,
+      "learning_rate": 6.898423229241535e-07,
+      "loss": 0.617,
+      "step": 699
+    },
+    {
+      "epoch": 1.6794717887154862,
+      "grad_norm": 0.8926473520136611,
+      "learning_rate": 6.798236644172301e-07,
+      "loss": 0.6651,
+      "step": 700
+    },
+    {
+      "epoch": 1.68187274909964,
+      "grad_norm": 0.7761396023419351,
+      "learning_rate": 6.698729810778065e-07,
+      "loss": 0.6587,
+      "step": 701
+    },
+    {
+      "epoch": 1.6842737094837936,
+      "grad_norm": 0.976405931900423,
+      "learning_rate": 6.599904294734227e-07,
+      "loss": 0.6085,
+      "step": 702
+    },
+    {
+      "epoch": 1.6866746698679473,
+      "grad_norm": 0.9389803284730526,
+      "learning_rate": 6.501761650996052e-07,
+      "loss": 0.6295,
+      "step": 703
+    },
+    {
+      "epoch": 1.6890756302521008,
+      "grad_norm": 1.210248872780046,
+      "learning_rate": 6.404303423774261e-07,
+      "loss": 0.665,
+      "step": 704
+    },
+    {
+      "epoch": 1.6914765906362546,
+      "grad_norm": 0.953540162188805,
+      "learning_rate": 6.307531146510754e-07,
+      "loss": 0.6996,
+      "step": 705
+    },
+    {
+      "epoch": 1.693877551020408,
+      "grad_norm": 0.9906405098922356,
+      "learning_rate": 6.211446341854415e-07,
+      "loss": 0.6568,
+      "step": 706
+    },
+    {
+      "epoch": 1.6962785114045618,
+      "grad_norm": 1.0790486562130543,
+      "learning_rate": 6.116050521637218e-07,
+      "loss": 0.6314,
+      "step": 707
+    },
+    {
+      "epoch": 1.6986794717887155,
+      "grad_norm": 0.8749360312510759,
+      "learning_rate": 6.021345186850419e-07,
+      "loss": 0.6679,
+      "step": 708
+    },
+    {
+      "epoch": 1.7010804321728692,
+      "grad_norm": 0.932641296809523,
+      "learning_rate": 5.927331827620902e-07,
+      "loss": 0.6049,
+      "step": 709
+    },
+    {
+      "epoch": 1.703481392557023,
+      "grad_norm": 1.501148013771617,
+      "learning_rate": 5.834011923187804e-07,
+      "loss": 0.7124,
+      "step": 710
+    },
+    {
+      "epoch": 1.7058823529411766,
+      "grad_norm": 1.0232382065365628,
+      "learning_rate": 5.741386941879179e-07,
+      "loss": 0.6182,
+      "step": 711
+    },
+    {
+      "epoch": 1.7082833133253301,
+      "grad_norm": 0.8493888976027031,
+      "learning_rate": 5.649458341088915e-07,
+      "loss": 0.6098,
+      "step": 712
+    },
+    {
+      "epoch": 1.7106842737094838,
+      "grad_norm": 1.0287417261052827,
+      "learning_rate": 5.558227567253832e-07,
+      "loss": 0.6485,
+      "step": 713
+    },
+    {
+      "epoch": 1.7130852340936373,
+      "grad_norm": 0.9824165450245743,
+      "learning_rate": 5.467696055830862e-07,
+      "loss": 0.6442,
+      "step": 714
+    },
+    {
+      "epoch": 1.715486194477791,
+      "grad_norm": 0.9840054188214199,
+      "learning_rate": 5.377865231274504e-07,
+      "loss": 0.6555,
+      "step": 715
+    },
+    {
+      "epoch": 1.7178871548619448,
+      "grad_norm": 0.9220257833526645,
+      "learning_rate": 5.288736507014436e-07,
+      "loss": 0.6615,
+      "step": 716
+    },
+    {
+      "epoch": 1.7202881152460985,
+      "grad_norm": 1.1631333915971627,
+      "learning_rate": 5.200311285433213e-07,
+      "loss": 0.6667,
+      "step": 717
+    },
+    {
+      "epoch": 1.7226890756302522,
+      "grad_norm": 0.8429719875570699,
+      "learning_rate": 5.112590957844233e-07,
+      "loss": 0.6566,
+      "step": 718
+    },
+    {
+      "epoch": 1.725090036014406,
+      "grad_norm": 1.0799558152581747,
+      "learning_rate": 5.025576904469842e-07,
+      "loss": 0.6693,
+      "step": 719
+    },
+    {
+      "epoch": 1.7274909963985594,
+      "grad_norm": 1.2210942148405586,
+      "learning_rate": 4.939270494419657e-07,
+      "loss": 0.6541,
+      "step": 720
+    },
+    {
+      "epoch": 1.7298919567827131,
+      "grad_norm": 0.9590257367356989,
+      "learning_rate": 4.853673085668947e-07,
+      "loss": 0.6431,
+      "step": 721
+    },
+    {
+      "epoch": 1.7322929171668666,
+      "grad_norm": 1.7775283513181313,
+      "learning_rate": 4.768786025037308e-07,
+      "loss": 0.6626,
+      "step": 722
+    },
+    {
+      "epoch": 1.7346938775510203,
+      "grad_norm": 1.1344818287215155,
+      "learning_rate": 4.6846106481675035e-07,
+      "loss": 0.7145,
+      "step": 723
+    },
+    {
+      "epoch": 1.737094837935174,
+      "grad_norm": 0.8004575138198893,
+      "learning_rate": 4.601148279504386e-07,
+      "loss": 0.6703,
+      "step": 724
+    },
+    {
+      "epoch": 1.7394957983193278,
+      "grad_norm": 1.0048669346768608,
+      "learning_rate": 4.5184002322740784e-07,
+      "loss": 0.6605,
+      "step": 725
+    },
+    {
+      "epoch": 1.7418967587034815,
+      "grad_norm": 1.7963702152633332,
+      "learning_rate": 4.43636780846336e-07,
+      "loss": 0.6642,
+      "step": 726
+    },
+    {
+      "epoch": 1.7442977190876352,
+      "grad_norm": 0.8675050774193321,
+      "learning_rate": 4.355052298799112e-07,
+      "loss": 0.6212,
+      "step": 727
+    },
+    {
+      "epoch": 1.7466986794717887,
+      "grad_norm": 1.1240940409157105,
+      "learning_rate": 4.274454982728032e-07,
+      "loss": 0.6624,
+      "step": 728
+    },
+    {
+      "epoch": 1.7490996398559424,
+      "grad_norm": 0.8849118229552638,
+      "learning_rate": 4.194577128396521e-07,
+      "loss": 0.6643,
+      "step": 729
+    },
+    {
+      "epoch": 1.751500600240096,
+      "grad_norm": 0.9481416953837549,
+      "learning_rate": 4.11541999263072e-07,
+      "loss": 0.6642,
+      "step": 730
+    },
+    {
+      "epoch": 1.7539015606242496,
+      "grad_norm": 0.8446166604341134,
+      "learning_rate": 4.036984820916723e-07,
+      "loss": 0.6813,
+      "step": 731
+    },
+    {
+      "epoch": 1.7563025210084033,
+      "grad_norm": 0.9415777016276731,
+      "learning_rate": 3.959272847380985e-07,
+      "loss": 0.6586,
+      "step": 732
+    },
+    {
+      "epoch": 1.758703481392557,
+      "grad_norm": 3.16162065014156,
+      "learning_rate": 3.882285294770938e-07,
+      "loss": 0.671,
+      "step": 733
+    },
+    {
+      "epoch": 1.7611044417767108,
+      "grad_norm": 0.9046402526532606,
+      "learning_rate": 3.8060233744356634e-07,
+      "loss": 0.6472,
+      "step": 734
+    },
+    {
+      "epoch": 1.7635054021608645,
+      "grad_norm": 1.274276291255798,
+      "learning_rate": 3.730488286306944e-07,
+      "loss": 0.6879,
+      "step": 735
+    },
+    {
+      "epoch": 1.765906362545018,
+      "grad_norm": 0.9266738982390647,
+      "learning_rate": 3.655681218880325e-07,
+      "loss": 0.7006,
+      "step": 736
+    },
+    {
+      "epoch": 1.7683073229291717,
+      "grad_norm": 1.1298270256741265,
+      "learning_rate": 3.581603349196372e-07,
+      "loss": 0.6302,
+      "step": 737
+    },
+    {
+      "epoch": 1.7707082833133252,
+      "grad_norm": 1.4768285811131943,
+      "learning_rate": 3.5082558428222555e-07,
+      "loss": 0.6344,
+      "step": 738
+    },
+    {
+      "epoch": 1.773109243697479,
+      "grad_norm": 1.03574555828318,
+      "learning_rate": 3.435639853833317e-07,
+      "loss": 0.6694,
+      "step": 739
+    },
+    {
+      "epoch": 1.7755102040816326,
+      "grad_norm": 0.9168661600940188,
+      "learning_rate": 3.363756524794959e-07,
+      "loss": 0.6907,
+      "step": 740
+    },
+    {
+      "epoch": 1.7779111644657863,
+      "grad_norm": 1.212035933698864,
+      "learning_rate": 3.2926069867446673e-07,
+      "loss": 0.6557,
+      "step": 741
+    },
+    {
+      "epoch": 1.78031212484994,
+      "grad_norm": 1.0068074581038595,
+      "learning_rate": 3.222192359174181e-07,
+      "loss": 0.6407,
+      "step": 742
+    },
+    {
+      "epoch": 1.7827130852340938,
+      "grad_norm": 1.048679687746833,
+      "learning_rate": 3.1525137500119207e-07,
+      "loss": 0.6423,
+      "step": 743
+    },
+    {
+      "epoch": 1.7851140456182473,
+      "grad_norm": 0.9656449483604257,
+      "learning_rate": 3.0835722556055103e-07,
+      "loss": 0.6629,
+      "step": 744
+    },
+    {
+      "epoch": 1.787515006002401,
+      "grad_norm": 1.428088163085122,
+      "learning_rate": 3.015368960704584e-07,
+      "loss": 0.6633,
+      "step": 745
+    },
+    {
+      "epoch": 1.7899159663865545,
+      "grad_norm": 0.9064014873180054,
+      "learning_rate": 2.947904938443663e-07,
+      "loss": 0.7047,
+      "step": 746
+    },
+    {
+      "epoch": 1.7923169267707082,
+      "grad_norm": 0.9167347266961742,
+      "learning_rate": 2.881181250325299e-07,
+      "loss": 0.6324,
+      "step": 747
+    },
+    {
+      "epoch": 1.794717887154862,
+      "grad_norm": 0.9791642332462065,
+      "learning_rate": 2.815198946203379e-07,
+      "loss": 0.6573,
+      "step": 748
+    },
+    {
+      "epoch": 1.7971188475390156,
+      "grad_norm": 1.7966695794490903,
+      "learning_rate": 2.7499590642665773e-07,
+      "loss": 0.6361,
+      "step": 749
+    },
+    {
+      "epoch": 1.7995198079231693,
+      "grad_norm": 1.0061714167779683,
+      "learning_rate": 2.68546263102204e-07,
+      "loss": 0.6569,
+      "step": 750
+    },
+    {
+      "epoch": 1.801920768307323,
+      "grad_norm": 0.929889297638995,
+      "learning_rate": 2.621710661279253e-07,
+      "loss": 0.6482,
+      "step": 751
+    },
+    {
+      "epoch": 1.8043217286914766,
+      "grad_norm": 1.447901958483443,
+      "learning_rate": 2.5587041581340235e-07,
+      "loss": 0.6727,
+      "step": 752
+    },
+    {
+      "epoch": 1.8067226890756303,
+      "grad_norm": 1.281764423132765,
+      "learning_rate": 2.4964441129527337e-07,
+      "loss": 0.637,
+      "step": 753
+    },
+    {
+      "epoch": 1.8091236494597838,
+      "grad_norm": 1.19823353128569,
+      "learning_rate": 2.4349315053567466e-07,
+      "loss": 0.6666,
+      "step": 754
+    },
+    {
+      "epoch": 1.8115246098439375,
+      "grad_norm": 0.8837247280505467,
+      "learning_rate": 2.3741673032069757e-07,
+      "loss": 0.6884,
+      "step": 755
+    },
+    {
+      "epoch": 1.8139255702280912,
+      "grad_norm": 3.3673813583616514,
+      "learning_rate": 2.314152462588659e-07,
+      "loss": 0.6197,
+      "step": 756
+    },
+    {
+      "epoch": 1.816326530612245,
+      "grad_norm": 0.8669864527827419,
+      "learning_rate": 2.2548879277963065e-07,
+      "loss": 0.6754,
+      "step": 757
+    },
+    {
+      "epoch": 1.8187274909963986,
+      "grad_norm": 0.8557759357976468,
+      "learning_rate": 2.1963746313188762e-07,
+      "loss": 0.6565,
+      "step": 758
+    },
+    {
+      "epoch": 1.8211284513805523,
+      "grad_norm": 0.9835493095940567,
+      "learning_rate": 2.1386134938250645e-07,
+      "loss": 0.7246,
+      "step": 759
+    },
+    {
+      "epoch": 1.8235294117647058,
+      "grad_norm": 0.9486375192086429,
+      "learning_rate": 2.0816054241488358e-07,
+      "loss": 0.6464,
+      "step": 760
+    },
+    {
+      "epoch": 1.8259303721488596,
+      "grad_norm": 0.9939355968419499,
+      "learning_rate": 2.0253513192751374e-07,
+      "loss": 0.6784,
+      "step": 761
+    },
+    {
+      "epoch": 1.828331332533013,
+      "grad_norm": 2.5411064037190214,
+      "learning_rate": 1.9698520643257334e-07,
+      "loss": 0.6171,
+      "step": 762
+    },
+    {
+      "epoch": 1.8307322929171668,
+      "grad_norm": 0.8611234302478261,
+      "learning_rate": 1.9151085325453512e-07,
+      "loss": 0.6915,
+      "step": 763
+    },
+    {
+      "epoch": 1.8331332533013205,
+      "grad_norm": 0.8053015612745882,
+      "learning_rate": 1.8611215852879005e-07,
+      "loss": 0.6687,
+      "step": 764
+    },
+    {
+      "epoch": 1.8355342136854742,
+      "grad_norm": 0.9521324815935206,
+      "learning_rate": 1.807892072002898e-07,
+      "loss": 0.6657,
+      "step": 765
+    },
+    {
+      "epoch": 1.837935174069628,
+      "grad_norm": 1.094466055359716,
+      "learning_rate": 1.7554208302221654e-07,
+      "loss": 0.7215,
+      "step": 766
+    },
+    {
+      "epoch": 1.8403361344537816,
+      "grad_norm": 0.9098193968920033,
+      "learning_rate": 1.7037086855465902e-07,
+      "loss": 0.6497,
+      "step": 767
+    },
+    {
+      "epoch": 1.8427370948379351,
+      "grad_norm": 0.855181562781992,
+      "learning_rate": 1.652756451633164e-07,
+      "loss": 0.7093,
+      "step": 768
+    },
+    {
+      "epoch": 1.8451380552220888,
+      "grad_norm": 0.8565693947802443,
+      "learning_rate": 1.6025649301821877e-07,
+      "loss": 0.6503,
+      "step": 769
+    },
+    {
+      "epoch": 1.8475390156062423,
+      "grad_norm": 0.9679413436421161,
+      "learning_rate": 1.5531349109246364e-07,
+      "loss": 0.7123,
+      "step": 770
+    },
+    {
+      "epoch": 1.849939975990396,
+      "grad_norm": 1.136073654492355,
+      "learning_rate": 1.5044671716097414e-07,
+      "loss": 0.6521,
+      "step": 771
+    },
+    {
+      "epoch": 1.8523409363745498,
+      "grad_norm": 0.7992798585720682,
+      "learning_rate": 1.4565624779927568e-07,
+      "loss": 0.6681,
+      "step": 772
+    },
+    {
+      "epoch": 1.8547418967587035,
+      "grad_norm": 1.677902937262838,
+      "learning_rate": 1.4094215838229176e-07,
+      "loss": 0.6913,
+      "step": 773
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 1.5737946583536535,
+      "learning_rate": 1.3630452308315557e-07,
+      "loss": 0.6543,
+      "step": 774
+    },
+    {
+      "epoch": 1.859543817527011,
+      "grad_norm": 1.1481025211558338,
+      "learning_rate": 1.3174341487204478e-07,
+      "loss": 0.6267,
+      "step": 775
+    },
+    {
+      "epoch": 1.8619447779111644,
+      "grad_norm": 0.8965017224592727,
+      "learning_rate": 1.2725890551503472e-07,
+      "loss": 0.6994,
+      "step": 776
+    },
+    {
+      "epoch": 1.8643457382953181,
+      "grad_norm": 0.867766283089291,
+      "learning_rate": 1.2285106557296479e-07,
+      "loss": 0.6322,
+      "step": 777
+    },
+    {
+      "epoch": 1.8667466986794716,
+      "grad_norm": 0.9421735003405503,
+      "learning_rate": 1.185199644003332e-07,
+      "loss": 0.6507,
+      "step": 778
+    },
+    {
+      "epoch": 1.8691476590636253,
+      "grad_norm": 1.0906617292381764,
+      "learning_rate": 1.1426567014420297e-07,
+      "loss": 0.672,
+      "step": 779
+    },
+    {
+      "epoch": 1.871548619447779,
+      "grad_norm": 1.247937633242823,
+      "learning_rate": 1.1008824974312827e-07,
+      "loss": 0.697,
+      "step": 780
+    },
+    {
+      "epoch": 1.8739495798319328,
+      "grad_norm": 1.1670307684913883,
+      "learning_rate": 1.0598776892610685e-07,
+      "loss": 0.6856,
+      "step": 781
+    },
+    {
+      "epoch": 1.8763505402160865,
+      "grad_norm": 1.3271471671208666,
+      "learning_rate": 1.0196429221153825e-07,
+      "loss": 0.6622,
+      "step": 782
+    },
+    {
+      "epoch": 1.8787515006002402,
+      "grad_norm": 0.886398633773095,
+      "learning_rate": 9.801788290621505e-08,
+      "loss": 0.6898,
+      "step": 783
+    },
+    {
+      "epoch": 1.8811524609843937,
+      "grad_norm": 0.877392618889072,
+      "learning_rate": 9.414860310432317e-08,
+      "loss": 0.6508,
+      "step": 784
+    },
+    {
+      "epoch": 1.8835534213685474,
+      "grad_norm": 1.1906859503017138,
+      "learning_rate": 9.035651368646647e-08,
+      "loss": 0.6489,
+      "step": 785
+    },
+    {
+      "epoch": 1.885954381752701,
+      "grad_norm": 1.9798044799116112,
+      "learning_rate": 8.664167431870762e-08,
+      "loss": 0.6719,
+      "step": 786
+    },
+    {
+      "epoch": 1.8883553421368546,
+      "grad_norm": 1.1006110013842414,
+      "learning_rate": 8.300414345163043e-08,
+      "loss": 0.642,
+      "step": 787
+    },
+    {
+      "epoch": 1.8907563025210083,
+      "grad_norm": 0.7974940942674409,
+      "learning_rate": 7.944397831941952e-08,
+      "loss": 0.7165,
+      "step": 788
+    },
+    {
+      "epoch": 1.893157262905162,
+      "grad_norm": 1.1280785375939588,
+      "learning_rate": 7.59612349389599e-08,
+      "loss": 0.6431,
+      "step": 789
+    },
+    {
+      "epoch": 1.8955582232893158,
+      "grad_norm": 1.1144184023534176,
+      "learning_rate": 7.255596810895548e-08,
+      "loss": 0.7046,
+      "step": 790
+    },
+    {
+      "epoch": 1.8979591836734695,
+      "grad_norm": 1.138147657830953,
+      "learning_rate": 6.922823140906754e-08,
+      "loss": 0.6698,
+      "step": 791
+    },
+    {
+      "epoch": 1.9003601440576232,
+      "grad_norm": 0.9217680993318809,
+      "learning_rate": 6.597807719907034e-08,
+      "loss": 0.6496,
+      "step": 792
+    },
+    {
+      "epoch": 1.9027611044417767,
+      "grad_norm": 1.186007338823389,
+      "learning_rate": 6.280555661802857e-08,
+      "loss": 0.6649,
+      "step": 793
+    },
+    {
+      "epoch": 1.9051620648259304,
+      "grad_norm": 1.0174742125343583,
+      "learning_rate": 5.971071958349229e-08,
+      "loss": 0.6568,
+      "step": 794
+    },
+    {
+      "epoch": 1.907563025210084,
+      "grad_norm": 0.8438893439006977,
+      "learning_rate": 5.669361479071156e-08,
+      "loss": 0.6654,
+      "step": 795
+    },
+    {
+      "epoch": 1.9099639855942376,
+      "grad_norm": 0.7499962846971833,
+      "learning_rate": 5.375428971186925e-08,
+      "loss": 0.6276,
+      "step": 796
+    },
+    {
+      "epoch": 1.9123649459783914,
+      "grad_norm": 0.8717461451446198,
+      "learning_rate": 5.089279059533658e-08,
+      "loss": 0.7107,
+      "step": 797
+    },
+    {
+      "epoch": 1.914765906362545,
+      "grad_norm": 0.9116003950294865,
+      "learning_rate": 4.810916246494157e-08,
+      "loss": 0.6244,
+      "step": 798
+    },
+    {
+      "epoch": 1.9171668667466988,
+      "grad_norm": 0.8645440990234077,
+      "learning_rate": 4.5403449119265085e-08,
+      "loss": 0.683,
+      "step": 799
+    },
+    {
+      "epoch": 1.9195678271308525,
+      "grad_norm": 0.9080233023711938,
+      "learning_rate": 4.2775693130948094e-08,
+      "loss": 0.6298,
+      "step": 800
+    },
+    {
+      "epoch": 1.921968787515006,
+      "grad_norm": 0.8210413108402735,
+      "learning_rate": 4.02259358460233e-08,
+      "loss": 0.6709,
+      "step": 801
+    },
+    {
+      "epoch": 1.9243697478991597,
+      "grad_norm": 0.8285484827144454,
+      "learning_rate": 3.775421738326568e-08,
+      "loss": 0.6655,
+      "step": 802
+    },
+    {
+      "epoch": 1.9267707082833132,
+      "grad_norm": 0.9586228743335077,
+      "learning_rate": 3.536057663355852e-08,
+      "loss": 0.6507,
+      "step": 803
+    },
+    {
+      "epoch": 1.929171668667467,
+      "grad_norm": 1.04816127232883,
+      "learning_rate": 3.304505125928392e-08,
+      "loss": 0.6765,
+      "step": 804
+    },
+    {
+      "epoch": 1.9315726290516206,
+      "grad_norm": 0.8425194752265788,
+      "learning_rate": 3.080767769372939e-08,
+      "loss": 0.6534,
+      "step": 805
+    },
+    {
+      "epoch": 1.9339735894357744,
+      "grad_norm": 1.896719832014499,
+      "learning_rate": 2.8648491140513267e-08,
+      "loss": 0.6904,
+      "step": 806
+    },
+    {
+      "epoch": 1.936374549819928,
+      "grad_norm": 1.0062088432432506,
+      "learning_rate": 2.6567525573034102e-08,
+      "loss": 0.6954,
+      "step": 807
+    },
+    {
+      "epoch": 1.9387755102040818,
+      "grad_norm": 0.8975562417272989,
+      "learning_rate": 2.4564813733932157e-08,
+      "loss": 0.6849,
+      "step": 808
+    },
+    {
+      "epoch": 1.9411764705882353,
+      "grad_norm": 0.975794376499767,
+      "learning_rate": 2.264038713457706e-08,
+      "loss": 0.7237,
+      "step": 809
+    },
+    {
+      "epoch": 1.943577430972389,
+      "grad_norm": 1.0524644516102524,
+      "learning_rate": 2.079427605457096e-08,
+      "loss": 0.6941,
+      "step": 810
+    },
+    {
+      "epoch": 1.9459783913565425,
+      "grad_norm": 0.9611491587591614,
+      "learning_rate": 1.9026509541272276e-08,
+      "loss": 0.6858,
+      "step": 811
+    },
+    {
+      "epoch": 1.9483793517406962,
+      "grad_norm": 1.0000196792745963,
+      "learning_rate": 1.7337115409338246e-08,
+      "loss": 0.6309,
+      "step": 812
+    },
+    {
+      "epoch": 1.95078031212485,
+      "grad_norm": 1.0920655370481793,
+      "learning_rate": 1.5726120240288632e-08,
+      "loss": 0.694,
+      "step": 813
+    },
+    {
+      "epoch": 1.9531812725090036,
+      "grad_norm": 0.9748896970825864,
+      "learning_rate": 1.4193549382083837e-08,
+      "loss": 0.6893,
+      "step": 814
+    },
+    {
+      "epoch": 1.9555822328931574,
+      "grad_norm": 1.0771011273317628,
+      "learning_rate": 1.2739426948732426e-08,
+      "loss": 0.6638,
+      "step": 815
+    },
+    {
+      "epoch": 1.957983193277311,
+      "grad_norm": 0.8882200571103428,
+      "learning_rate": 1.1363775819904776e-08,
+      "loss": 0.6955,
+      "step": 816
+    },
+    {
+      "epoch": 1.9603841536614646,
+      "grad_norm": 1.090762803675368,
+      "learning_rate": 1.006661764057837e-08,
+      "loss": 0.6966,
+      "step": 817
+    },
+    {
+      "epoch": 1.9627851140456183,
+      "grad_norm": 1.0696035526291576,
+      "learning_rate": 8.847972820693052e-09,
+      "loss": 0.703,
+      "step": 818
+    },
+    {
+      "epoch": 1.9651860744297718,
+      "grad_norm": 1.1819203209196956,
+      "learning_rate": 7.707860534834632e-09,
+      "loss": 0.6827,
+      "step": 819
+    },
+    {
+      "epoch": 1.9675870348139255,
+      "grad_norm": 1.3716127907201827,
+      "learning_rate": 6.646298721928457e-09,
+      "loss": 0.6391,
+      "step": 820
+    },
+    {
+      "epoch": 1.9699879951980792,
+      "grad_norm": 0.8540501179543823,
+      "learning_rate": 5.6633040849601865e-09,
+      "loss": 0.6845,
+      "step": 821
+    },
+    {
+      "epoch": 1.972388955582233,
+      "grad_norm": 0.9224613846938693,
+      "learning_rate": 4.758892090711009e-09,
+      "loss": 0.6393,
+      "step": 822
+    },
+    {
+      "epoch": 1.9747899159663866,
+      "grad_norm": 0.9721797003258046,
+      "learning_rate": 3.9330769695167245e-09,
+      "loss": 0.6922,
+      "step": 823
+    },
+    {
+      "epoch": 1.9771908763505404,
+      "grad_norm": 0.9272860464428038,
+      "learning_rate": 3.1858717150412554e-09,
+      "loss": 0.68,
+      "step": 824
+    },
+    {
+      "epoch": 1.9795918367346939,
+      "grad_norm": 0.9109986729531275,
+      "learning_rate": 2.5172880840745873e-09,
+      "loss": 0.6996,
+      "step": 825
+    },
+    {
+      "epoch": 1.9819927971188476,
+      "grad_norm": 0.9142879218161498,
+      "learning_rate": 1.9273365963440315e-09,
+      "loss": 0.6439,
+      "step": 826
+    },
+    {
+      "epoch": 1.984393757503001,
+      "grad_norm": 0.9184253994662968,
+      "learning_rate": 1.4160265343549084e-09,
+      "loss": 0.6819,
+      "step": 827
+    },
+    {
+      "epoch": 1.9867947178871548,
+      "grad_norm": 0.929916491589975,
+      "learning_rate": 9.833659432367803e-10,
+      "loss": 0.6725,
+      "step": 828
+    },
+    {
+      "epoch": 1.9891956782713085,
+      "grad_norm": 1.4953561604837144,
+      "learning_rate": 6.293616306246586e-10,
+      "loss": 0.6642,
+      "step": 829
+    },
+    {
+      "epoch": 1.9915966386554622,
+      "grad_norm": 0.9372999860644707,
+      "learning_rate": 3.540191665457604e-10,
+      "loss": 0.7112,
+      "step": 830
+    },
+    {
+      "epoch": 1.993997599039616,
+      "grad_norm": 0.9716377415350187,
+      "learning_rate": 1.5734288333457692e-10,
+      "loss": 0.6803,
+      "step": 831
+    },
+    {
+      "epoch": 1.9963985594237696,
+      "grad_norm": 0.8051855934219595,
+      "learning_rate": 3.9335875564594505e-11,
+      "loss": 0.6748,
+      "step": 832
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 832,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 208,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.326067610943488e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}