diff --git "a/checkpoint-1272/trainer_state.json" "b/checkpoint-1272/trainer_state.json"
new file mode 100644--- /dev/null
+++ "b/checkpoint-1272/trainer_state.json"
@@ -0,0 +1,9065 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.9556340793089912,
+  "eval_steps": 80,
+  "global_step": 1272,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0031409501374165686,
+      "grad_norm": 5.125,
+      "learning_rate": 2e-05,
+      "loss": 10.7953,
+      "step": 1
+    },
+    {
+      "epoch": 0.0031409501374165686,
+      "eval_loss": 10.810359001159668,
+      "eval_runtime": 65.1601,
+      "eval_samples_per_second": 39.917,
+      "eval_steps_per_second": 39.917,
+      "step": 1
+    },
+    {
+      "epoch": 0.006281900274833137,
+      "grad_norm": 4.59375,
+      "learning_rate": 4e-05,
+      "loss": 10.599,
+      "step": 2
+    },
+    {
+      "epoch": 0.009422850412249705,
+      "grad_norm": 5.65625,
+      "learning_rate": 6e-05,
+      "loss": 10.8341,
+      "step": 3
+    },
+    {
+      "epoch": 0.012563800549666274,
+      "grad_norm": 4.59375,
+      "learning_rate": 8e-05,
+      "loss": 10.2321,
+      "step": 4
+    },
+    {
+      "epoch": 0.015704750687082842,
+      "grad_norm": 5.09375,
+      "learning_rate": 0.0001,
+      "loss": 9.926,
+      "step": 5
+    },
+    {
+      "epoch": 0.01884570082449941,
+      "grad_norm": 5.09375,
+      "learning_rate": 0.00012,
+      "loss": 9.2807,
+      "step": 6
+    },
+    {
+      "epoch": 0.02198665096191598,
+      "grad_norm": 5.21875,
+      "learning_rate": 0.00014,
+      "loss": 8.7401,
+      "step": 7
+    },
+    {
+      "epoch": 0.02512760109933255,
+      "grad_norm": 5.3125,
+      "learning_rate": 0.00016,
+      "loss": 7.7479,
+      "step": 8
+    },
+    {
+      "epoch": 0.028268551236749116,
+      "grad_norm": 3.78125,
+      "learning_rate": 0.00018,
+      "loss": 7.3356,
+      "step": 9
+    },
+    {
+      "epoch": 0.031409501374165684,
+      "grad_norm": 4.15625,
+      "learning_rate": 0.0002,
+      "loss": 6.8649,
+      "step": 10
+    },
+    {
+      "epoch": 0.03455045151158225,
+      "grad_norm": 1.9296875,
+      "learning_rate": 0.00019999969015048862,
+      "loss": 6.7994,
+      "step": 11
+    },
+    {
+      "epoch": 0.03769140164899882,
+      "grad_norm": 1.2265625,
+      "learning_rate": 0.0001999987606038746,
+      "loss": 6.2436,
+      "step": 12
+    },
+    {
+      "epoch": 0.040832351786415394,
+      "grad_norm": 2.125,
+      "learning_rate": 0.0001999972113659183,
+      "loss": 6.6684,
+      "step": 13
+    },
+    {
+      "epoch": 0.04397330192383196,
+      "grad_norm": 0.9921875,
+      "learning_rate": 0.00019999504244622043,
+      "loss": 6.4968,
+      "step": 14
+    },
+    {
+      "epoch": 0.04711425206124853,
+      "grad_norm": 1.0625,
+      "learning_rate": 0.00019999225385822165,
+      "loss": 6.3331,
+      "step": 15
+    },
+    {
+      "epoch": 0.0502552021986651,
+      "grad_norm": 0.88671875,
+      "learning_rate": 0.00019998884561920284,
+      "loss": 6.3441,
+      "step": 16
+    },
+    {
+      "epoch": 0.053396152336081665,
+      "grad_norm": 1.171875,
+      "learning_rate": 0.00019998481775028491,
+      "loss": 5.8419,
+      "step": 17
+    },
+    {
+      "epoch": 0.05653710247349823,
+      "grad_norm": 1.3203125,
+      "learning_rate": 0.0001999801702764284,
+      "loss": 6.1942,
+      "step": 18
+    },
+    {
+      "epoch": 0.0596780526109148,
+      "grad_norm": 1.75,
+      "learning_rate": 0.00019997490322643376,
+      "loss": 6.017,
+      "step": 19
+    },
+    {
+      "epoch": 0.06281900274833137,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.00019996901663294078,
+      "loss": 6.2501,
+      "step": 20
+    },
+    {
+      "epoch": 0.06595995288574794,
+      "grad_norm": 0.9296875,
+      "learning_rate": 0.00019996251053242865,
+      "loss": 5.9597,
+      "step": 21
+    },
+    {
+      "epoch": 0.0691009030231645,
+      "grad_norm": 1.8984375,
+      "learning_rate": 0.0001999553849652156,
+      "loss": 6.0591,
+      "step": 22
+    },
+    {
+      "epoch": 0.07224185316058107,
+      "grad_norm": 1.265625,
+      "learning_rate": 0.00019994763997545874,
+      "loss": 6.2802,
+      "step": 23
+    },
+    {
+      "epoch": 0.07538280329799764,
+      "grad_norm": 1.7265625,
+      "learning_rate": 0.00019993927561115366,
+      "loss": 6.082,
+      "step": 24
+    },
+    {
+      "epoch": 0.0785237534354142,
+      "grad_norm": 1.0,
+      "learning_rate": 0.00019993029192413424,
+      "loss": 6.1596,
+      "step": 25
+    },
+    {
+      "epoch": 0.08166470357283079,
+      "grad_norm": 1.609375,
+      "learning_rate": 0.00019992068897007232,
+      "loss": 5.9254,
+      "step": 26
+    },
+    {
+      "epoch": 0.08480565371024736,
+      "grad_norm": 1.5234375,
+      "learning_rate": 0.0001999104668084773,
+      "loss": 5.893,
+      "step": 27
+    },
+    {
+      "epoch": 0.08794660384766392,
+      "grad_norm": 0.90234375,
+      "learning_rate": 0.00019989962550269583,
+      "loss": 6.1184,
+      "step": 28
+    },
+    {
+      "epoch": 0.09108755398508049,
+      "grad_norm": 0.88671875,
+      "learning_rate": 0.00019988816511991135,
+      "loss": 5.9582,
+      "step": 29
+    },
+    {
+      "epoch": 0.09422850412249706,
+      "grad_norm": 1.0078125,
+      "learning_rate": 0.00019987608573114376,
+      "loss": 5.8845,
+      "step": 30
+    },
+    {
+      "epoch": 0.09736945425991363,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.0001998633874112489,
+      "loss": 6.1202,
+      "step": 31
+    },
+    {
+      "epoch": 0.1005104043973302,
+      "grad_norm": 1.1015625,
+      "learning_rate": 0.00019985007023891815,
+      "loss": 5.7627,
+      "step": 32
+    },
+    {
+      "epoch": 0.10365135453474676,
+      "grad_norm": 0.8828125,
+      "learning_rate": 0.00019983613429667792,
+      "loss": 6.0619,
+      "step": 33
+    },
+    {
+      "epoch": 0.10679230467216333,
+      "grad_norm": 1.0078125,
+      "learning_rate": 0.00019982157967088904,
+      "loss": 5.683,
+      "step": 34
+    },
+    {
+      "epoch": 0.1099332548095799,
+      "grad_norm": 1.1640625,
+      "learning_rate": 0.0001998064064517464,
+      "loss": 5.8008,
+      "step": 35
+    },
+    {
+      "epoch": 0.11307420494699646,
+      "grad_norm": 1.375,
+      "learning_rate": 0.00019979061473327837,
+      "loss": 5.8867,
+      "step": 36
+    },
+    {
+      "epoch": 0.11621515508441303,
+      "grad_norm": 1.671875,
+      "learning_rate": 0.000199774204613346,
+      "loss": 5.9331,
+      "step": 37
+    },
+    {
+      "epoch": 0.1193561052218296,
+      "grad_norm": 1.4375,
+      "learning_rate": 0.00019975717619364263,
+      "loss": 5.4695,
+      "step": 38
+    },
+    {
+      "epoch": 0.12249705535924617,
+      "grad_norm": 1.4765625,
+      "learning_rate": 0.0001997395295796933,
+      "loss": 5.9711,
+      "step": 39
+    },
+    {
+      "epoch": 0.12563800549666274,
+      "grad_norm": 1.2421875,
+      "learning_rate": 0.00019972126488085378,
+      "loss": 5.7401,
+      "step": 40
+    },
+    {
+      "epoch": 0.12877895563407932,
+      "grad_norm": 1.390625,
+      "learning_rate": 0.00019970238221031034,
+      "loss": 5.7064,
+      "step": 41
+    },
+    {
+      "epoch": 0.13191990577149587,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.00019968288168507864,
+      "loss": 5.6272,
+      "step": 42
+    },
+    {
+      "epoch": 0.13506085590891245,
+      "grad_norm": 1.8359375,
+      "learning_rate": 0.00019966276342600327,
+      "loss": 5.4439,
+      "step": 43
+    },
+    {
+      "epoch": 0.138201806046329,
+      "grad_norm": 1.265625,
+      "learning_rate": 0.0001996420275577569,
+      "loss": 5.9631,
+      "step": 44
+    },
+    {
+      "epoch": 0.1413427561837456,
+      "grad_norm": 1.6796875,
+      "learning_rate": 0.00019962067420883944,
+      "loss": 5.8393,
+      "step": 45
+    },
+    {
+      "epoch": 0.14448370632116214,
+      "grad_norm": 1.53125,
+      "learning_rate": 0.00019959870351157747,
+      "loss": 5.7997,
+      "step": 46
+    },
+    {
+      "epoch": 0.14762465645857872,
+      "grad_norm": 1.3984375,
+      "learning_rate": 0.0001995761156021231,
+      "loss": 5.656,
+      "step": 47
+    },
+    {
+      "epoch": 0.15076560659599528,
+      "grad_norm": 1.4921875,
+      "learning_rate": 0.00019955291062045345,
+      "loss": 5.7152,
+      "step": 48
+    },
+    {
+      "epoch": 0.15390655673341186,
+      "grad_norm": 1.828125,
+      "learning_rate": 0.00019952908871036956,
+      "loss": 5.7215,
+      "step": 49
+    },
+    {
+      "epoch": 0.1570475068708284,
+      "grad_norm": 1.0,
+      "learning_rate": 0.0001995046500194955,
+      "loss": 5.6857,
+      "step": 50
+    },
+    {
+      "epoch": 0.160188457008245,
+      "grad_norm": 1.3984375,
+      "learning_rate": 0.00019947959469927772,
+      "loss": 5.6698,
+      "step": 51
+    },
+    {
+      "epoch": 0.16332940714566158,
+      "grad_norm": 1.3515625,
+      "learning_rate": 0.0001994539229049837,
+      "loss": 5.2906,
+      "step": 52
+    },
+    {
+      "epoch": 0.16647035728307813,
+      "grad_norm": 1.25,
+      "learning_rate": 0.00019942763479570132,
+      "loss": 5.4673,
+      "step": 53
+    },
+    {
+      "epoch": 0.1696113074204947,
+      "grad_norm": 0.890625,
+      "learning_rate": 0.00019940073053433777,
+      "loss": 5.5959,
+      "step": 54
+    },
+    {
+      "epoch": 0.17275225755791127,
+      "grad_norm": 1.59375,
+      "learning_rate": 0.00019937321028761846,
+      "loss": 5.9431,
+      "step": 55
+    },
+    {
+      "epoch": 0.17589320769532785,
+      "grad_norm": 1.59375,
+      "learning_rate": 0.00019934507422608608,
+      "loss": 5.754,
+      "step": 56
+    },
+    {
+      "epoch": 0.1790341578327444,
+      "grad_norm": 0.984375,
+      "learning_rate": 0.00019931632252409955,
+      "loss": 5.405,
+      "step": 57
+    },
+    {
+      "epoch": 0.18217510797016098,
+      "grad_norm": 1.03125,
+      "learning_rate": 0.00019928695535983287,
+      "loss": 5.5907,
+      "step": 58
+    },
+    {
+      "epoch": 0.18531605810757754,
+      "grad_norm": 1.2265625,
+      "learning_rate": 0.00019925697291527415,
+      "loss": 5.7941,
+      "step": 59
+    },
+    {
+      "epoch": 0.18845700824499412,
+      "grad_norm": 1.0078125,
+      "learning_rate": 0.00019922637537622418,
+      "loss": 5.6169,
+      "step": 60
+    },
+    {
+      "epoch": 0.19159795838241067,
+      "grad_norm": 1.5,
+      "learning_rate": 0.00019919516293229569,
+      "loss": 5.5379,
+      "step": 61
+    },
+    {
+      "epoch": 0.19473890851982725,
+      "grad_norm": 0.8203125,
+      "learning_rate": 0.00019916333577691184,
+      "loss": 5.6157,
+      "step": 62
+    },
+    {
+      "epoch": 0.1978798586572438,
+      "grad_norm": 1.484375,
+      "learning_rate": 0.00019913089410730526,
+      "loss": 5.5043,
+      "step": 63
+    },
+    {
+      "epoch": 0.2010208087946604,
+      "grad_norm": 0.98046875,
+      "learning_rate": 0.00019909783812451664,
+      "loss": 5.7083,
+      "step": 64
+    },
+    {
+      "epoch": 0.20416175893207694,
+      "grad_norm": 1.125,
+      "learning_rate": 0.00019906416803339353,
+      "loss": 5.5739,
+      "step": 65
+    },
+    {
+      "epoch": 0.20730270906949352,
+      "grad_norm": 1.375,
+      "learning_rate": 0.00019902988404258922,
+      "loss": 5.5447,
+      "step": 66
+    },
+    {
+      "epoch": 0.21044365920691008,
+      "grad_norm": 1.2109375,
+      "learning_rate": 0.00019899498636456126,
+      "loss": 5.3392,
+      "step": 67
+    },
+    {
+      "epoch": 0.21358460934432666,
+      "grad_norm": 1.1171875,
+      "learning_rate": 0.0001989594752155702,
+      "loss": 5.3176,
+      "step": 68
+    },
+    {
+      "epoch": 0.21672555948174324,
+      "grad_norm": 0.93359375,
+      "learning_rate": 0.00019892335081567826,
+      "loss": 5.1688,
+      "step": 69
+    },
+    {
+      "epoch": 0.2198665096191598,
+      "grad_norm": 0.953125,
+      "learning_rate": 0.00019888661338874803,
+      "loss": 5.5142,
+      "step": 70
+    },
+    {
+      "epoch": 0.22300745975657638,
+      "grad_norm": 1.1484375,
+      "learning_rate": 0.000198849263162441,
+      "loss": 5.3004,
+      "step": 71
+    },
+    {
+      "epoch": 0.22614840989399293,
+      "grad_norm": 0.7890625,
+      "learning_rate": 0.0001988113003682161,
+      "loss": 5.5914,
+      "step": 72
+    },
+    {
+      "epoch": 0.2292893600314095,
+      "grad_norm": 0.71484375,
+      "learning_rate": 0.00019877272524132847,
+      "loss": 5.4175,
+      "step": 73
+    },
+    {
+      "epoch": 0.23243031016882607,
+      "grad_norm": 0.99609375,
+      "learning_rate": 0.00019873353802082771,
+      "loss": 5.0854,
+      "step": 74
+    },
+    {
+      "epoch": 0.23557126030624265,
+      "grad_norm": 1.046875,
+      "learning_rate": 0.00019869373894955669,
+      "loss": 5.5772,
+      "step": 75
+    },
+    {
+      "epoch": 0.2387122104436592,
+      "grad_norm": 1.390625,
+      "learning_rate": 0.00019865332827414988,
+      "loss": 5.4289,
+      "step": 76
+    },
+    {
+      "epoch": 0.24185316058107578,
+      "grad_norm": 1.3203125,
+      "learning_rate": 0.0001986123062450318,
+      "loss": 5.5427,
+      "step": 77
+    },
+    {
+      "epoch": 0.24499411071849234,
+      "grad_norm": 0.82421875,
+      "learning_rate": 0.0001985706731164156,
+      "loss": 5.3294,
+      "step": 78
+    },
+    {
+      "epoch": 0.24813506085590892,
+      "grad_norm": 1.4921875,
+      "learning_rate": 0.00019852842914630137,
+      "loss": 5.3756,
+      "step": 79
+    },
+    {
+      "epoch": 0.25127601099332547,
+      "grad_norm": 1.375,
+      "learning_rate": 0.00019848557459647455,
+      "loss": 5.4963,
+      "step": 80
+    },
+    {
+      "epoch": 0.25127601099332547,
+      "eval_loss": 5.410098075866699,
+      "eval_runtime": 66.9514,
+      "eval_samples_per_second": 38.849,
+      "eval_steps_per_second": 38.849,
+      "step": 80
+    },
+    {
+      "epoch": 0.254416961130742,
+      "grad_norm": 1.0703125,
+      "learning_rate": 0.00019844210973250437,
+      "loss": 5.4053,
+      "step": 81
+    },
+    {
+      "epoch": 0.25755791126815863,
+      "grad_norm": 1.3359375,
+      "learning_rate": 0.0001983980348237422,
+      "loss": 5.3084,
+      "step": 82
+    },
+    {
+      "epoch": 0.2606988614055752,
+      "grad_norm": 0.95703125,
+      "learning_rate": 0.00019835335014331976,
+      "loss": 5.4774,
+      "step": 83
+    },
+    {
+      "epoch": 0.26383981154299174,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.00019830805596814766,
+      "loss": 5.3591,
+      "step": 84
+    },
+    {
+      "epoch": 0.2669807616804083,
+      "grad_norm": 1.46875,
+      "learning_rate": 0.00019826215257891342,
+      "loss": 5.2504,
+      "step": 85
+    },
+    {
+      "epoch": 0.2701217118178249,
+      "grad_norm": 1.1171875,
+      "learning_rate": 0.00019821564026007988,
+      "loss": 5.2333,
+      "step": 86
+    },
+    {
+      "epoch": 0.27326266195524146,
+      "grad_norm": 1.4765625,
+      "learning_rate": 0.0001981685192998834,
+      "loss": 5.4557,
+      "step": 87
+    },
+    {
+      "epoch": 0.276403612092658,
+      "grad_norm": 1.1171875,
+      "learning_rate": 0.00019812078999033222,
+      "loss": 5.5066,
+      "step": 88
+    },
+    {
+      "epoch": 0.2795445622300746,
+      "grad_norm": 1.0234375,
+      "learning_rate": 0.00019807245262720426,
+      "loss": 5.3617,
+      "step": 89
+    },
+    {
+      "epoch": 0.2826855123674912,
+      "grad_norm": 1.0234375,
+      "learning_rate": 0.0001980235075100458,
+      "loss": 5.4076,
+      "step": 90
+    },
+    {
+      "epoch": 0.28582646250490773,
+      "grad_norm": 0.921875,
+      "learning_rate": 0.00019797395494216923,
+      "loss": 5.2482,
+      "step": 91
+    },
+    {
+      "epoch": 0.2889674126423243,
+      "grad_norm": 1.1640625,
+      "learning_rate": 0.00019792379523065126,
+      "loss": 5.1448,
+      "step": 92
+    },
+    {
+      "epoch": 0.2921083627797409,
+      "grad_norm": 1.1015625,
+      "learning_rate": 0.0001978730286863312,
+      "loss": 5.2483,
+      "step": 93
+    },
+    {
+      "epoch": 0.29524931291715745,
+      "grad_norm": 1.0234375,
+      "learning_rate": 0.0001978216556238088,
+      "loss": 5.1698,
+      "step": 94
+    },
+    {
+      "epoch": 0.298390263054574,
+      "grad_norm": 0.91015625,
+      "learning_rate": 0.00019776967636144245,
+      "loss": 5.3225,
+      "step": 95
+    },
+    {
+      "epoch": 0.30153121319199055,
+      "grad_norm": 0.80859375,
+      "learning_rate": 0.00019771709122134713,
+      "loss": 5.3077,
+      "step": 96
+    },
+    {
+      "epoch": 0.30467216332940716,
+      "grad_norm": 0.76953125,
+      "learning_rate": 0.00019766390052939242,
+      "loss": 5.2636,
+      "step": 97
+    },
+    {
+      "epoch": 0.3078131134668237,
+      "grad_norm": 1.0390625,
+      "learning_rate": 0.00019761010461520054,
+      "loss": 5.4547,
+      "step": 98
+    },
+    {
+      "epoch": 0.31095406360424027,
+      "grad_norm": 0.85546875,
+      "learning_rate": 0.0001975557038121442,
+      "loss": 5.2564,
+      "step": 99
+    },
+    {
+      "epoch": 0.3140950137416568,
+      "grad_norm": 1.1484375,
+      "learning_rate": 0.00019750069845734473,
+      "loss": 4.9768,
+      "step": 100
+    },
+    {
+      "epoch": 0.31723596387907343,
+      "grad_norm": 1.0703125,
+      "learning_rate": 0.00019744508889166966,
+      "loss": 5.2283,
+      "step": 101
+    },
+    {
+      "epoch": 0.32037691401649,
+      "grad_norm": 1.34375,
+      "learning_rate": 0.00019738887545973102,
+      "loss": 5.4258,
+      "step": 102
+    },
+    {
+      "epoch": 0.32351786415390654,
+      "grad_norm": 1.2109375,
+      "learning_rate": 0.00019733205850988285,
+      "loss": 5.2331,
+      "step": 103
+    },
+    {
+      "epoch": 0.32665881429132315,
+      "grad_norm": 0.828125,
+      "learning_rate": 0.00019727463839421926,
+      "loss": 5.1852,
+      "step": 104
+    },
+    {
+      "epoch": 0.3297997644287397,
+      "grad_norm": 1.109375,
+      "learning_rate": 0.00019721661546857213,
+      "loss": 5.4063,
+      "step": 105
+    },
+    {
+      "epoch": 0.33294071456615626,
+      "grad_norm": 0.8359375,
+      "learning_rate": 0.000197157990092509,
+      "loss": 5.2671,
+      "step": 106
+    },
+    {
+      "epoch": 0.3360816647035728,
+      "grad_norm": 0.94140625,
+      "learning_rate": 0.00019709876262933066,
+      "loss": 5.3544,
+      "step": 107
+    },
+    {
+      "epoch": 0.3392226148409894,
+      "grad_norm": 0.9609375,
+      "learning_rate": 0.0001970389334460692,
+      "loss": 5.1728,
+      "step": 108
+    },
+    {
+      "epoch": 0.342363564978406,
+      "grad_norm": 0.921875,
+      "learning_rate": 0.00019697850291348548,
+      "loss": 5.3887,
+      "step": 109
+    },
+    {
+      "epoch": 0.34550451511582253,
+      "grad_norm": 0.8984375,
+      "learning_rate": 0.00019691747140606692,
+      "loss": 5.1095,
+      "step": 110
+    },
+    {
+      "epoch": 0.3486454652532391,
+      "grad_norm": 0.96875,
+      "learning_rate": 0.00019685583930202514,
+      "loss": 5.1703,
+      "step": 111
+    },
+    {
+      "epoch": 0.3517864153906557,
+      "grad_norm": 0.81640625,
+      "learning_rate": 0.0001967936069832937,
+      "loss": 5.17,
+      "step": 112
+    },
+    {
+      "epoch": 0.35492736552807225,
+      "grad_norm": 1.0625,
+      "learning_rate": 0.00019673077483552568,
+      "loss": 5.0519,
+      "step": 113
+    },
+    {
+      "epoch": 0.3580683156654888,
+      "grad_norm": 0.87109375,
+      "learning_rate": 0.00019666734324809125,
+      "loss": 5.186,
+      "step": 114
+    },
+    {
+      "epoch": 0.36120926580290535,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.00019660331261407544,
+      "loss": 5.0202,
+      "step": 115
+    },
+    {
+      "epoch": 0.36435021594032196,
+      "grad_norm": 0.70703125,
+      "learning_rate": 0.00019653868333027535,
+      "loss": 5.1102,
+      "step": 116
+    },
+    {
+      "epoch": 0.3674911660777385,
+      "grad_norm": 0.85546875,
+      "learning_rate": 0.00019647345579719807,
+      "loss": 5.1,
+      "step": 117
+    },
+    {
+      "epoch": 0.37063211621515507,
+      "grad_norm": 1.078125,
+      "learning_rate": 0.000196407630419058,
+      "loss": 5.0466,
+      "step": 118
+    },
+    {
+      "epoch": 0.3737730663525716,
+      "grad_norm": 1.1328125,
+      "learning_rate": 0.00019634120760377428,
+      "loss": 5.3088,
+      "step": 119
+    },
+    {
+      "epoch": 0.37691401648998824,
+      "grad_norm": 1.1796875,
+      "learning_rate": 0.00019627418776296858,
+      "loss": 5.2293,
+      "step": 120
+    },
+    {
+      "epoch": 0.3800549666274048,
+      "grad_norm": 1.1171875,
+      "learning_rate": 0.00019620657131196208,
+      "loss": 5.2738,
+      "step": 121
+    },
+    {
+      "epoch": 0.38319591676482134,
+      "grad_norm": 1.1171875,
+      "learning_rate": 0.00019613835866977335,
+      "loss": 4.9497,
+      "step": 122
+    },
+    {
+      "epoch": 0.38633686690223795,
+      "grad_norm": 0.9375,
+      "learning_rate": 0.00019606955025911542,
+      "loss": 5.2231,
+      "step": 123
+    },
+    {
+      "epoch": 0.3894778170396545,
+      "grad_norm": 0.93359375,
+      "learning_rate": 0.00019600014650639333,
+      "loss": 5.3426,
+      "step": 124
+    },
+    {
+      "epoch": 0.39261876717707106,
+      "grad_norm": 0.76953125,
+      "learning_rate": 0.00019593014784170153,
+      "loss": 5.0717,
+      "step": 125
+    },
+    {
+      "epoch": 0.3957597173144876,
+      "grad_norm": 0.9140625,
+      "learning_rate": 0.00019585955469882097,
+      "loss": 5.1569,
+      "step": 126
+    },
+    {
+      "epoch": 0.3989006674519042,
+      "grad_norm": 0.75390625,
+      "learning_rate": 0.0001957883675152167,
+      "loss": 4.9017,
+      "step": 127
+    },
+    {
+      "epoch": 0.4020416175893208,
+      "grad_norm": 0.96484375,
+      "learning_rate": 0.00019571658673203502,
+      "loss": 5.1124,
+      "step": 128
+    },
+    {
+      "epoch": 0.40518256772673733,
+      "grad_norm": 0.953125,
+      "learning_rate": 0.00019564421279410075,
+      "loss": 4.7849,
+      "step": 129
+    },
+    {
+      "epoch": 0.4083235178641539,
+      "grad_norm": 0.90234375,
+      "learning_rate": 0.00019557124614991443,
+      "loss": 5.1534,
+      "step": 130
+    },
+    {
+      "epoch": 0.4114644680015705,
+      "grad_norm": 1.015625,
+      "learning_rate": 0.00019549768725164967,
+      "loss": 5.2731,
+      "step": 131
+    },
+    {
+      "epoch": 0.41460541813898705,
+      "grad_norm": 1.0,
+      "learning_rate": 0.00019542353655515023,
+      "loss": 5.0467,
+      "step": 132
+    },
+    {
+      "epoch": 0.4177463682764036,
+      "grad_norm": 0.8671875,
+      "learning_rate": 0.00019534879451992728,
+      "loss": 4.8911,
+      "step": 133
+    },
+    {
+      "epoch": 0.42088731841382016,
+      "grad_norm": 0.875,
+      "learning_rate": 0.00019527346160915646,
+      "loss": 5.2338,
+      "step": 134
+    },
+    {
+      "epoch": 0.42402826855123676,
+      "grad_norm": 1.1171875,
+      "learning_rate": 0.00019519753828967508,
+      "loss": 5.1705,
+      "step": 135
+    },
+    {
+      "epoch": 0.4271692186886533,
+      "grad_norm": 0.96484375,
+      "learning_rate": 0.00019512102503197923,
+      "loss": 5.3178,
+      "step": 136
+    },
+    {
+      "epoch": 0.43031016882606987,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.00019504392231022076,
+      "loss": 5.1462,
+      "step": 137
+    },
+    {
+      "epoch": 0.4334511189634865,
+      "grad_norm": 1.0546875,
+      "learning_rate": 0.00019496623060220457,
+      "loss": 5.0293,
+      "step": 138
+    },
+    {
+      "epoch": 0.43659206910090304,
+      "grad_norm": 1.046875,
+      "learning_rate": 0.00019488795038938536,
+      "loss": 5.0523,
+      "step": 139
+    },
+    {
+      "epoch": 0.4397330192383196,
+      "grad_norm": 1.7421875,
+      "learning_rate": 0.00019480908215686486,
+      "loss": 5.0893,
+      "step": 140
+    },
+    {
+      "epoch": 0.44287396937573614,
+      "grad_norm": 0.79296875,
+      "learning_rate": 0.00019472962639338875,
+      "loss": 5.0682,
+      "step": 141
+    },
+    {
+      "epoch": 0.44601491951315275,
+      "grad_norm": 1.265625,
+      "learning_rate": 0.00019464958359134354,
+      "loss": 5.1261,
+      "step": 142
+    },
+    {
+      "epoch": 0.4491558696505693,
+      "grad_norm": 1.09375,
+      "learning_rate": 0.00019456895424675382,
+      "loss": 5.2513,
+      "step": 143
+    },
+    {
+      "epoch": 0.45229681978798586,
+      "grad_norm": 0.87890625,
+      "learning_rate": 0.00019448773885927877,
+      "loss": 5.0248,
+      "step": 144
+    },
+    {
+      "epoch": 0.4554377699254024,
+      "grad_norm": 1.1484375,
+      "learning_rate": 0.00019440593793220936,
+      "loss": 4.9527,
+      "step": 145
+    },
+    {
+      "epoch": 0.458578720062819,
+      "grad_norm": 0.93359375,
+      "learning_rate": 0.00019432355197246515,
+      "loss": 5.1182,
+      "step": 146
+    },
+    {
+      "epoch": 0.4617196702002356,
+      "grad_norm": 1.125,
+      "learning_rate": 0.00019424058149059112,
+      "loss": 5.043,
+      "step": 147
+    },
+    {
+      "epoch": 0.46486062033765213,
+      "grad_norm": 0.98828125,
+      "learning_rate": 0.00019415702700075453,
+      "loss": 5.1351,
+      "step": 148
+    },
+    {
+      "epoch": 0.4680015704750687,
+      "grad_norm": 1.234375,
+      "learning_rate": 0.00019407288902074176,
+      "loss": 5.0489,
+      "step": 149
+    },
+    {
+      "epoch": 0.4711425206124853,
+      "grad_norm": 1.265625,
+      "learning_rate": 0.00019398816807195498,
+      "loss": 4.8494,
+      "step": 150
+    },
+    {
+      "epoch": 0.47428347074990185,
+      "grad_norm": 0.9140625,
+      "learning_rate": 0.00019390286467940918,
+      "loss": 5.196,
+      "step": 151
+    },
+    {
+      "epoch": 0.4774244208873184,
+      "grad_norm": 1.0859375,
+      "learning_rate": 0.0001938169793717286,
+      "loss": 4.9598,
+      "step": 152
+    },
+    {
+      "epoch": 0.48056537102473496,
+      "grad_norm": 1.15625,
+      "learning_rate": 0.0001937305126811437,
+      "loss": 5.1067,
+      "step": 153
+    },
+    {
+      "epoch": 0.48370632116215156,
+      "grad_norm": 0.7890625,
+      "learning_rate": 0.0001936434651434876,
+      "loss": 5.1599,
+      "step": 154
+    },
+    {
+      "epoch": 0.4868472712995681,
+      "grad_norm": 1.109375,
+      "learning_rate": 0.00019355583729819317,
+      "loss": 4.9971,
+      "step": 155
+    },
+    {
+      "epoch": 0.48998822143698467,
+      "grad_norm": 1.25,
+      "learning_rate": 0.0001934676296882892,
+      "loss": 5.0528,
+      "step": 156
+    },
+    {
+      "epoch": 0.4931291715744013,
+      "grad_norm": 1.0390625,
+      "learning_rate": 0.00019337884286039746,
+      "loss": 5.2021,
+      "step": 157
+    },
+    {
+      "epoch": 0.49627012171181784,
+      "grad_norm": 1.015625,
+      "learning_rate": 0.00019328947736472904,
+      "loss": 4.7814,
+      "step": 158
+    },
+    {
+      "epoch": 0.4994110718492344,
+      "grad_norm": 1.0,
+      "learning_rate": 0.00019319953375508106,
+      "loss": 5.0906,
+      "step": 159
+    },
+    {
+      "epoch": 0.5025520219866509,
+      "grad_norm": 0.91015625,
+      "learning_rate": 0.00019310901258883317,
+      "loss": 5.0323,
+      "step": 160
+    },
+    {
+      "epoch": 0.5025520219866509,
+      "eval_loss": 5.075822353363037,
+      "eval_runtime": 66.934,
+      "eval_samples_per_second": 38.859,
+      "eval_steps_per_second": 38.859,
+      "step": 160
+    },
+    {
+      "epoch": 0.5056929721240675,
+      "grad_norm": 0.921875,
+      "learning_rate": 0.00019301791442694413,
+      "loss": 5.1209,
+      "step": 161
+    },
+    {
+      "epoch": 0.508833922261484,
+      "grad_norm": 2.765625,
+      "learning_rate": 0.00019292623983394838,
+      "loss": 5.0187,
+      "step": 162
+    },
+    {
+      "epoch": 0.5119748723989007,
+      "grad_norm": 1.234375,
+      "learning_rate": 0.0001928339893779525,
+      "loss": 4.9584,
+      "step": 163
+    },
+    {
+      "epoch": 0.5151158225363173,
+      "grad_norm": 1.28125,
+      "learning_rate": 0.00019274116363063163,
+      "loss": 4.9459,
+      "step": 164
+    },
+    {
+      "epoch": 0.5182567726737338,
+      "grad_norm": 0.859375,
+      "learning_rate": 0.00019264776316722603,
+      "loss": 4.7699,
+      "step": 165
+    },
+    {
+      "epoch": 0.5213977228111504,
+      "grad_norm": 1.0625,
+      "learning_rate": 0.00019255378856653746,
+      "loss": 5.0324,
+      "step": 166
+    },
+    {
+      "epoch": 0.5245386729485669,
+      "grad_norm": 1.15625,
+      "learning_rate": 0.00019245924041092562,
+      "loss": 5.2702,
+      "step": 167
+    },
+    {
+      "epoch": 0.5276796230859835,
+      "grad_norm": 1.0703125,
+      "learning_rate": 0.00019236411928630446,
+      "loss": 5.0989,
+      "step": 168
+    },
+    {
+      "epoch": 0.5308205732234,
+      "grad_norm": 0.93359375,
+      "learning_rate": 0.00019226842578213874,
+      "loss": 4.7667,
+      "step": 169
+    },
+    {
+      "epoch": 0.5339615233608166,
+      "grad_norm": 0.99609375,
+      "learning_rate": 0.00019217216049144007,
+      "loss": 4.8303,
+      "step": 170
+    },
+    {
+      "epoch": 0.5371024734982333,
+      "grad_norm": 0.8984375,
+      "learning_rate": 0.00019207532401076358,
+      "loss": 5.0607,
+      "step": 171
+    },
+    {
+      "epoch": 0.5402434236356498,
+      "grad_norm": 1.0390625,
+      "learning_rate": 0.00019197791694020396,
+      "loss": 4.96,
+      "step": 172
+    },
+    {
+      "epoch": 0.5433843737730664,
+      "grad_norm": 0.91796875,
+      "learning_rate": 0.00019187993988339192,
+      "loss": 5.0107,
+      "step": 173
+    },
+    {
+      "epoch": 0.5465253239104829,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.0001917813934474903,
+      "loss": 5.1961,
+      "step": 174
+    },
+    {
+      "epoch": 0.5496662740478995,
+      "grad_norm": 1.0546875,
+      "learning_rate": 0.0001916822782431904,
+      "loss": 5.0727,
+      "step": 175
+    },
+    {
+      "epoch": 0.552807224185316,
+      "grad_norm": 1.203125,
+      "learning_rate": 0.00019158259488470815,
+      "loss": 4.8185,
+      "step": 176
+    },
+    {
+      "epoch": 0.5559481743227326,
+      "grad_norm": 1.59375,
+      "learning_rate": 0.00019148234398978038,
+      "loss": 5.2447,
+      "step": 177
+    },
+    {
+      "epoch": 0.5590891244601492,
+      "grad_norm": 1.25,
+      "learning_rate": 0.0001913815261796609,
+      "loss": 5.0844,
+      "step": 178
+    },
+    {
+      "epoch": 0.5622300745975658,
+      "grad_norm": 1.0390625,
+      "learning_rate": 0.0001912801420791167,
+      "loss": 5.0112,
+      "step": 179
+    },
+    {
+      "epoch": 0.5653710247349824,
+      "grad_norm": 1.3671875,
+      "learning_rate": 0.000191178192316424,
+      "loss": 5.1335,
+      "step": 180
+    },
+    {
+      "epoch": 0.5685119748723989,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.00019107567752336458,
+      "loss": 5.1664,
+      "step": 181
+    },
+    {
+      "epoch": 0.5716529250098155,
+      "grad_norm": 0.90625,
+      "learning_rate": 0.0001909725983352215,
+      "loss": 4.9254,
+      "step": 182
+    },
+    {
+      "epoch": 0.574793875147232,
+      "grad_norm": 0.8515625,
+      "learning_rate": 0.00019086895539077562,
+      "loss": 4.8303,
+      "step": 183
+    },
+    {
+      "epoch": 0.5779348252846486,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.00019076474933230116,
+      "loss": 4.9595,
+      "step": 184
+    },
+    {
+      "epoch": 0.5810757754220651,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.00019065998080556204,
+      "loss": 5.0253,
+      "step": 185
+    },
+    {
+      "epoch": 0.5842167255594818,
+      "grad_norm": 1.078125,
+      "learning_rate": 0.00019055465045980782,
+      "loss": 5.1003,
+      "step": 186
+    },
+    {
+      "epoch": 0.5873576756968983,
+      "grad_norm": 1.0703125,
+      "learning_rate": 0.00019044875894776966,
+      "loss": 4.9631,
+      "step": 187
+    },
+    {
+      "epoch": 0.5904986258343149,
+      "grad_norm": 1.1171875,
+      "learning_rate": 0.00019034230692565614,
+      "loss": 4.9462,
+      "step": 188
+    },
+    {
+      "epoch": 0.5936395759717314,
+      "grad_norm": 1.4453125,
+      "learning_rate": 0.0001902352950531495,
+      "loss": 4.8688,
+      "step": 189
+    },
+    {
+      "epoch": 0.596780526109148,
+      "grad_norm": 1.3359375,
+      "learning_rate": 0.0001901277239934012,
+      "loss": 5.1219,
+      "step": 190
+    },
+    {
+      "epoch": 0.5999214762465646,
+      "grad_norm": 1.2109375,
+      "learning_rate": 0.00019001959441302806,
+      "loss": 5.0382,
+      "step": 191
+    },
+    {
+      "epoch": 0.6030624263839811,
+      "grad_norm": 1.2109375,
+      "learning_rate": 0.00018991090698210802,
+      "loss": 4.9474,
+      "step": 192
+    },
+    {
+      "epoch": 0.6062033765213978,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.00018980166237417606,
+      "loss": 5.034,
+      "step": 193
+    },
+    {
+      "epoch": 0.6093443266588143,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.00018969186126621996,
+      "loss": 5.0142,
+      "step": 194
+    },
+    {
+      "epoch": 0.6124852767962309,
+      "grad_norm": 1.203125,
+      "learning_rate": 0.00018958150433867605,
+      "loss": 4.7944,
+      "step": 195
+    },
+    {
+      "epoch": 0.6156262269336474,
+      "grad_norm": 1.0078125,
+      "learning_rate": 0.0001894705922754252,
+      "loss": 4.7905,
+      "step": 196
+    },
+    {
+      "epoch": 0.618767177071064,
+      "grad_norm": 0.92578125,
+      "learning_rate": 0.0001893591257637883,
+      "loss": 4.8537,
+      "step": 197
+    },
+    {
+      "epoch": 0.6219081272084805,
+      "grad_norm": 1.15625,
+      "learning_rate": 0.00018924710549452232,
+      "loss": 4.8625,
+      "step": 198
+    },
+    {
+      "epoch": 0.6250490773458971,
+      "grad_norm": 1.2421875,
+      "learning_rate": 0.0001891345321618157,
+      "loss": 5.1188,
+      "step": 199
+    },
+    {
+      "epoch": 0.6281900274833137,
+      "grad_norm": 0.9921875,
+      "learning_rate": 0.00018902140646328435,
+      "loss": 4.7798,
+      "step": 200
+    },
+    {
+      "epoch": 0.6313309776207303,
+      "grad_norm": 1.234375,
+      "learning_rate": 0.0001889077290999671,
+      "loss": 4.9184,
+      "step": 201
+    },
+    {
+      "epoch": 0.6344719277581469,
+      "grad_norm": 1.375,
+      "learning_rate": 0.00018879350077632143,
+      "loss": 5.0932,
+      "step": 202
+    },
+    {
+      "epoch": 0.6376128778955634,
+      "grad_norm": 1.0234375,
+      "learning_rate": 0.00018867872220021913,
+      "loss": 4.9846,
+      "step": 203
+    },
+    {
+      "epoch": 0.64075382803298,
+      "grad_norm": 1.3203125,
+      "learning_rate": 0.00018856339408294202,
+      "loss": 4.8107,
+      "step": 204
+    },
+    {
+      "epoch": 0.6438947781703965,
+      "grad_norm": 1.0625,
+      "learning_rate": 0.0001884475171391772,
+      "loss": 4.9413,
+      "step": 205
+    },
+    {
+      "epoch": 0.6470357283078131,
+      "grad_norm": 1.0078125,
+      "learning_rate": 0.00018833109208701298,
+      "loss": 4.9209,
+      "step": 206
+    },
+    {
+      "epoch": 0.6501766784452296,
+      "grad_norm": 1.1171875,
+      "learning_rate": 0.00018821411964793433,
+      "loss": 4.8073,
+      "step": 207
+    },
+    {
+      "epoch": 0.6533176285826463,
+      "grad_norm": 1.1953125,
+      "learning_rate": 0.00018809660054681823,
+      "loss": 4.7729,
+      "step": 208
+    },
+    {
+      "epoch": 0.6564585787200629,
+      "grad_norm": 1.046875,
+      "learning_rate": 0.0001879785355119295,
+      "loss": 5.0412,
+      "step": 209
+    },
+    {
+      "epoch": 0.6595995288574794,
+      "grad_norm": 2.515625,
+      "learning_rate": 0.0001878599252749159,
+      "loss": 4.8707,
+      "step": 210
+    },
+    {
+      "epoch": 0.662740478994896,
+      "grad_norm": 1.6015625,
+      "learning_rate": 0.00018774077057080398,
+      "loss": 4.6271,
+      "step": 211
+    },
+    {
+      "epoch": 0.6658814291323125,
+      "grad_norm": 1.359375,
+      "learning_rate": 0.00018762107213799427,
+      "loss": 4.8702,
+      "step": 212
+    },
+    {
+      "epoch": 0.6690223792697291,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.00018750083071825677,
+      "loss": 4.8727,
+      "step": 213
+    },
+    {
+      "epoch": 0.6721633294071456,
+      "grad_norm": 1.71875,
+      "learning_rate": 0.0001873800470567264,
+      "loss": 4.8376,
+      "step": 214
+    },
+    {
+      "epoch": 0.6753042795445622,
+      "grad_norm": 1.7421875,
+      "learning_rate": 0.00018725872190189827,
+      "loss": 4.8666,
+      "step": 215
+    },
+    {
+      "epoch": 0.6784452296819788,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.00018713685600562328,
+      "loss": 5.038,
+      "step": 216
+    },
+    {
+      "epoch": 0.6815861798193954,
+      "grad_norm": 1.0546875,
+      "learning_rate": 0.00018701445012310315,
+      "loss": 4.9007,
+      "step": 217
+    },
+    {
+      "epoch": 0.684727129956812,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.00018689150501288593,
+      "loss": 4.8299,
+      "step": 218
+    },
+    {
+      "epoch": 0.6878680800942285,
+      "grad_norm": 1.3125,
+      "learning_rate": 0.00018676802143686126,
+      "loss": 4.801,
+      "step": 219
+    },
+    {
+      "epoch": 0.6910090302316451,
+      "grad_norm": 1.2109375,
+      "learning_rate": 0.00018664400016025568,
+      "loss": 4.7097,
+      "step": 220
+    },
+    {
+      "epoch": 0.6941499803690616,
+      "grad_norm": 1.6796875,
+      "learning_rate": 0.00018651944195162778,
+      "loss": 4.8088,
+      "step": 221
+    },
+    {
+      "epoch": 0.6972909305064782,
+      "grad_norm": 1.25,
+      "learning_rate": 0.0001863943475828636,
+      "loss": 4.9253,
+      "step": 222
+    },
+    {
+      "epoch": 0.7004318806438948,
+      "grad_norm": 1.40625,
+      "learning_rate": 0.00018626871782917174,
+      "loss": 4.8615,
+      "step": 223
+    },
+    {
+      "epoch": 0.7035728307813114,
+      "grad_norm": 1.1328125,
+      "learning_rate": 0.00018614255346907855,
+      "loss": 4.7592,
+      "step": 224
+    },
+    {
+      "epoch": 0.7067137809187279,
+      "grad_norm": 1.5,
+      "learning_rate": 0.0001860158552844233,
+      "loss": 4.6569,
+      "step": 225
+    },
+    {
+      "epoch": 0.7098547310561445,
+      "grad_norm": 1.59375,
+      "learning_rate": 0.0001858886240603534,
+      "loss": 4.8259,
+      "step": 226
+    },
+    {
+      "epoch": 0.712995681193561,
+      "grad_norm": 1.53125,
+      "learning_rate": 0.00018576086058531957,
+      "loss": 4.8066,
+      "step": 227
+    },
+    {
+      "epoch": 0.7161366313309776,
+      "grad_norm": 1.3828125,
+      "learning_rate": 0.00018563256565107072,
+      "loss": 4.8039,
+      "step": 228
+    },
+    {
+      "epoch": 0.7192775814683942,
+      "grad_norm": 1.390625,
+      "learning_rate": 0.00018550374005264937,
+      "loss": 4.8336,
+      "step": 229
+    },
+    {
+      "epoch": 0.7224185316058107,
+      "grad_norm": 1.4765625,
+      "learning_rate": 0.0001853743845883865,
+      "loss": 4.7032,
+      "step": 230
+    },
+    {
+      "epoch": 0.7255594817432274,
+      "grad_norm": 1.5078125,
+      "learning_rate": 0.0001852445000598966,
+      "loss": 4.827,
+      "step": 231
+    },
+    {
+      "epoch": 0.7287004318806439,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.0001851140872720729,
+      "loss": 4.996,
+      "step": 232
+    },
+    {
+      "epoch": 0.7318413820180605,
+      "grad_norm": 1.7109375,
+      "learning_rate": 0.0001849831470330821,
+      "loss": 4.7288,
+      "step": 233
+    },
+    {
+      "epoch": 0.734982332155477,
+      "grad_norm": 1.6796875,
+      "learning_rate": 0.00018485168015435966,
+      "loss": 4.8204,
+      "step": 234
+    },
+    {
+      "epoch": 0.7381232822928936,
+      "grad_norm": 1.5546875,
+      "learning_rate": 0.00018471968745060444,
+      "loss": 4.8829,
+      "step": 235
+    },
+    {
+      "epoch": 0.7412642324303101,
+      "grad_norm": 1.5234375,
+      "learning_rate": 0.00018458716973977405,
+      "loss": 4.7297,
+      "step": 236
+    },
+    {
+      "epoch": 0.7444051825677267,
+      "grad_norm": 1.6640625,
+      "learning_rate": 0.00018445412784307932,
+      "loss": 4.7916,
+      "step": 237
+    },
+    {
+      "epoch": 0.7475461327051433,
+      "grad_norm": 1.265625,
+      "learning_rate": 0.0001843205625849797,
+      "loss": 4.5585,
+      "step": 238
+    },
+    {
+      "epoch": 0.7506870828425599,
+      "grad_norm": 1.5234375,
+      "learning_rate": 0.00018418647479317776,
+      "loss": 4.9319,
+      "step": 239
+    },
+    {
+      "epoch": 0.7538280329799765,
+      "grad_norm": 1.6796875,
+      "learning_rate": 0.00018405186529861416,
+      "loss": 4.9877,
+      "step": 240
+    },
+    {
+      "epoch": 0.7538280329799765,
+      "eval_loss": 4.841662406921387,
+      "eval_runtime": 66.8839,
+      "eval_samples_per_second": 38.888,
+      "eval_steps_per_second": 38.888,
+      "step": 240
+    },
+    {
+      "epoch": 0.756968983117393,
+      "grad_norm": 1.375,
+      "learning_rate": 0.00018391673493546273,
+      "loss": 4.7421,
+      "step": 241
+    },
+    {
+      "epoch": 0.7601099332548096,
+      "grad_norm": 1.265625,
+      "learning_rate": 0.00018378108454112494,
+      "loss": 4.6469,
+      "step": 242
+    },
+    {
+      "epoch": 0.7632508833922261,
+      "grad_norm": 2.109375,
+      "learning_rate": 0.00018364491495622497,
+      "loss": 4.7609,
+      "step": 243
+    },
+    {
+      "epoch": 0.7663918335296427,
+      "grad_norm": 1.3203125,
+      "learning_rate": 0.00018350822702460444,
+      "loss": 4.737,
+      "step": 244
+    },
+    {
+      "epoch": 0.7695327836670592,
+      "grad_norm": 1.7734375,
+      "learning_rate": 0.0001833710215933171,
+      "loss": 4.7964,
+      "step": 245
+    },
+    {
+      "epoch": 0.7726737338044759,
+      "grad_norm": 1.6640625,
+      "learning_rate": 0.00018323329951262367,
+      "loss": 4.8785,
+      "step": 246
+    },
+    {
+      "epoch": 0.7758146839418925,
+      "grad_norm": 1.7421875,
+      "learning_rate": 0.0001830950616359865,
+      "loss": 4.83,
+      "step": 247
+    },
+    {
+      "epoch": 0.778955634079309,
+      "grad_norm": 1.53125,
+      "learning_rate": 0.00018295630882006445,
+      "loss": 4.9096,
+      "step": 248
+    },
+    {
+      "epoch": 0.7820965842167256,
+      "grad_norm": 1.6484375,
+      "learning_rate": 0.00018281704192470727,
+      "loss": 4.7864,
+      "step": 249
+    },
+    {
+      "epoch": 0.7852375343541421,
+      "grad_norm": 1.5078125,
+      "learning_rate": 0.00018267726181295065,
+      "loss": 4.8557,
+      "step": 250
+    },
+    {
+      "epoch": 0.7883784844915587,
+      "grad_norm": 2.578125,
+      "learning_rate": 0.00018253696935101047,
+      "loss": 4.8157,
+      "step": 251
+    },
+    {
+      "epoch": 0.7915194346289752,
+      "grad_norm": 2.21875,
+      "learning_rate": 0.00018239616540827782,
+      "loss": 4.8016,
+      "step": 252
+    },
+    {
+      "epoch": 0.7946603847663918,
+      "grad_norm": 1.390625,
+      "learning_rate": 0.0001822548508573133,
+      "loss": 4.657,
+      "step": 253
+    },
+    {
+      "epoch": 0.7978013349038084,
+      "grad_norm": 2.21875,
+      "learning_rate": 0.00018211302657384186,
+      "loss": 4.7423,
+      "step": 254
+    },
+    {
+      "epoch": 0.800942285041225,
+      "grad_norm": 2.328125,
+      "learning_rate": 0.00018197069343674715,
+      "loss": 4.8695,
+      "step": 255
+    },
+    {
+      "epoch": 0.8040832351786416,
+      "grad_norm": 1.7421875,
+      "learning_rate": 0.00018182785232806627,
+      "loss": 4.9817,
+      "step": 256
+    },
+    {
+      "epoch": 0.8072241853160581,
+      "grad_norm": 2.125,
+      "learning_rate": 0.00018168450413298416,
+      "loss": 4.794,
+      "step": 257
+    },
+    {
+      "epoch": 0.8103651354534747,
+      "grad_norm": 1.9921875,
+      "learning_rate": 0.00018154064973982816,
+      "loss": 4.9111,
+      "step": 258
+    },
+    {
+      "epoch": 0.8135060855908912,
+      "grad_norm": 2.0625,
+      "learning_rate": 0.0001813962900400626,
+      "loss": 4.9169,
+      "step": 259
+    },
+    {
+      "epoch": 0.8166470357283078,
+      "grad_norm": 1.765625,
+      "learning_rate": 0.00018125142592828307,
+      "loss": 4.7243,
+      "step": 260
+    },
+    {
+      "epoch": 0.8197879858657244,
+      "grad_norm": 2.234375,
+      "learning_rate": 0.00018110605830221104,
+      "loss": 4.8339,
+      "step": 261
+    },
+    {
+      "epoch": 0.822928936003141,
+      "grad_norm": 1.9609375,
+      "learning_rate": 0.00018096018806268834,
+      "loss": 4.6423,
+      "step": 262
+    },
+    {
+      "epoch": 0.8260698861405575,
+      "grad_norm": 1.9453125,
+      "learning_rate": 0.00018081381611367134,
+      "loss": 4.6603,
+      "step": 263
+    },
+    {
+      "epoch": 0.8292108362779741,
+      "grad_norm": 2.359375,
+      "learning_rate": 0.00018066694336222564,
+      "loss": 4.8327,
+      "step": 264
+    },
+    {
+      "epoch": 0.8323517864153906,
+      "grad_norm": 2.765625,
+      "learning_rate": 0.0001805195707185202,
+      "loss": 4.7741,
+      "step": 265
+    },
+    {
+      "epoch": 0.8354927365528072,
+      "grad_norm": 2.453125,
+      "learning_rate": 0.00018037169909582192,
+      "loss": 4.8735,
+      "step": 266
+    },
+    {
+      "epoch": 0.8386336866902238,
+      "grad_norm": 1.9375,
+      "learning_rate": 0.00018022332941048972,
+      "loss": 4.5862,
+      "step": 267
+    },
+    {
+      "epoch": 0.8417746368276403,
+      "grad_norm": 2.453125,
+      "learning_rate": 0.00018007446258196916,
+      "loss": 4.6305,
+      "step": 268
+    },
+    {
+      "epoch": 0.844915586965057,
+      "grad_norm": 1.8046875,
+      "learning_rate": 0.00017992509953278644,
+      "loss": 4.7259,
+      "step": 269
+    },
+    {
+      "epoch": 0.8480565371024735,
+      "grad_norm": 1.9765625,
+      "learning_rate": 0.000179775241188543,
+      "loss": 4.7171,
+      "step": 270
+    },
+    {
+      "epoch": 0.8511974872398901,
+      "grad_norm": 1.8984375,
+      "learning_rate": 0.0001796248884779095,
+      "loss": 4.5035,
+      "step": 271
+    },
+    {
+      "epoch": 0.8543384373773066,
+      "grad_norm": 1.7265625,
+      "learning_rate": 0.0001794740423326202,
+      "loss": 4.5654,
+      "step": 272
+    },
+    {
+      "epoch": 0.8574793875147232,
+      "grad_norm": 2.234375,
+      "learning_rate": 0.00017932270368746723,
+      "loss": 4.7109,
+      "step": 273
+    },
+    {
+      "epoch": 0.8606203376521397,
+      "grad_norm": 2.09375,
+      "learning_rate": 0.00017917087348029464,
+      "loss": 4.6446,
+      "step": 274
+    },
+    {
+      "epoch": 0.8637612877895563,
+      "grad_norm": 2.171875,
+      "learning_rate": 0.0001790185526519928,
+      "loss": 4.6444,
+      "step": 275
+    },
+    {
+      "epoch": 0.866902237926973,
+      "grad_norm": 1.8984375,
+      "learning_rate": 0.00017886574214649235,
+      "loss": 4.6852,
+      "step": 276
+    },
+    {
+      "epoch": 0.8700431880643895,
+      "grad_norm": 2.09375,
+      "learning_rate": 0.0001787124429107585,
+      "loss": 4.6116,
+      "step": 277
+    },
+    {
+      "epoch": 0.8731841382018061,
+      "grad_norm": 1.875,
+      "learning_rate": 0.00017855865589478515,
+      "loss": 4.7119,
+      "step": 278
+    },
+    {
+      "epoch": 0.8763250883392226,
+      "grad_norm": 2.0625,
+      "learning_rate": 0.00017840438205158891,
+      "loss": 4.7154,
+      "step": 279
+    },
+    {
+      "epoch": 0.8794660384766392,
+      "grad_norm": 2.171875,
+      "learning_rate": 0.00017824962233720332,
+      "loss": 4.7945,
+      "step": 280
+    },
+    {
+      "epoch": 0.8826069886140557,
+      "grad_norm": 2.828125,
+      "learning_rate": 0.00017809437771067272,
+      "loss": 4.7312,
+      "step": 281
+    },
+    {
+      "epoch": 0.8857479387514723,
+      "grad_norm": 2.109375,
+      "learning_rate": 0.00017793864913404663,
+      "loss": 4.5674,
+      "step": 282
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 2.203125,
+      "learning_rate": 0.00017778243757237352,
+      "loss": 4.6855,
+      "step": 283
+    },
+    {
+      "epoch": 0.8920298390263055,
+      "grad_norm": 2.40625,
+      "learning_rate": 0.00017762574399369485,
+      "loss": 4.7105,
+      "step": 284
+    },
+    {
+      "epoch": 0.8951707891637221,
+      "grad_norm": 2.171875,
+      "learning_rate": 0.00017746856936903926,
+      "loss": 4.7111,
+      "step": 285
+    },
+    {
+      "epoch": 0.8983117393011386,
+      "grad_norm": 1.984375,
+      "learning_rate": 0.0001773109146724163,
+      "loss": 4.7511,
+      "step": 286
+    },
+    {
+      "epoch": 0.9014526894385552,
+      "grad_norm": 2.34375,
+      "learning_rate": 0.00017715278088081062,
+      "loss": 4.7156,
+      "step": 287
+    },
+    {
+      "epoch": 0.9045936395759717,
+      "grad_norm": 2.796875,
+      "learning_rate": 0.0001769941689741758,
+      "loss": 4.7225,
+      "step": 288
+    },
+    {
+      "epoch": 0.9077345897133883,
+      "grad_norm": 2.703125,
+      "learning_rate": 0.00017683507993542825,
+      "loss": 4.7426,
+      "step": 289
+    },
+    {
+      "epoch": 0.9108755398508048,
+      "grad_norm": 2.4375,
+      "learning_rate": 0.0001766755147504412,
+      "loss": 4.8524,
+      "step": 290
+    },
+    {
+      "epoch": 0.9140164899882215,
+      "grad_norm": 2.65625,
+      "learning_rate": 0.00017651547440803851,
+      "loss": 4.6249,
+      "step": 291
+    },
+    {
+      "epoch": 0.917157440125638,
+      "grad_norm": 3.125,
+      "learning_rate": 0.00017635495989998864,
+      "loss": 4.8815,
+      "step": 292
+    },
+    {
+      "epoch": 0.9202983902630546,
+      "grad_norm": 2.71875,
+      "learning_rate": 0.00017619397222099848,
+      "loss": 4.7107,
+      "step": 293
+    },
+    {
+      "epoch": 0.9234393404004712,
+      "grad_norm": 2.53125,
+      "learning_rate": 0.00017603251236870702,
+      "loss": 4.5988,
+      "step": 294
+    },
+    {
+      "epoch": 0.9265802905378877,
+      "grad_norm": 2.703125,
+      "learning_rate": 0.0001758705813436794,
+      "loss": 4.43,
+      "step": 295
+    },
+    {
+      "epoch": 0.9297212406753043,
+      "grad_norm": 2.84375,
+      "learning_rate": 0.00017570818014940064,
+      "loss": 4.8238,
+      "step": 296
+    },
+    {
+      "epoch": 0.9328621908127208,
+      "grad_norm": 2.578125,
+      "learning_rate": 0.00017554530979226933,
+      "loss": 4.7022,
+      "step": 297
+    },
+    {
+      "epoch": 0.9360031409501374,
+      "grad_norm": 2.96875,
+      "learning_rate": 0.00017538197128159148,
+      "loss": 4.8184,
+      "step": 298
+    },
+    {
+      "epoch": 0.939144091087554,
+      "grad_norm": 2.609375,
+      "learning_rate": 0.00017521816562957428,
+      "loss": 4.4714,
+      "step": 299
+    },
+    {
+      "epoch": 0.9422850412249706,
+      "grad_norm": 2.40625,
+      "learning_rate": 0.00017505389385131972,
+      "loss": 4.4407,
+      "step": 300
+    },
+    {
+      "epoch": 0.9454259913623871,
+      "grad_norm": 3.25,
+      "learning_rate": 0.00017488915696481838,
+      "loss": 4.6623,
+      "step": 301
+    },
+    {
+      "epoch": 0.9485669414998037,
+      "grad_norm": 2.109375,
+      "learning_rate": 0.00017472395599094317,
+      "loss": 4.6181,
+      "step": 302
+    },
+    {
+      "epoch": 0.9517078916372202,
+      "grad_norm": 2.890625,
+      "learning_rate": 0.00017455829195344293,
+      "loss": 4.6449,
+      "step": 303
+    },
+    {
+      "epoch": 0.9548488417746368,
+      "grad_norm": 6.84375,
+      "learning_rate": 0.00017439216587893604,
+      "loss": 4.538,
+      "step": 304
+    },
+    {
+      "epoch": 0.9579897919120534,
+      "grad_norm": 3.5625,
+      "learning_rate": 0.0001742255787969042,
+      "loss": 4.7436,
+      "step": 305
+    },
+    {
+      "epoch": 0.9611307420494699,
+      "grad_norm": 2.234375,
+      "learning_rate": 0.00017405853173968589,
+      "loss": 4.7237,
+      "step": 306
+    },
+    {
+      "epoch": 0.9642716921868866,
+      "grad_norm": 2.3125,
+      "learning_rate": 0.0001738910257424701,
+      "loss": 4.5708,
+      "step": 307
+    },
+    {
+      "epoch": 0.9674126423243031,
+      "grad_norm": 2.78125,
+      "learning_rate": 0.00017372306184328985,
+      "loss": 4.4765,
+      "step": 308
+    },
+    {
+      "epoch": 0.9705535924617197,
+      "grad_norm": 2.109375,
+      "learning_rate": 0.00017355464108301585,
+      "loss": 4.6697,
+      "step": 309
+    },
+    {
+      "epoch": 0.9736945425991362,
+      "grad_norm": 2.421875,
+      "learning_rate": 0.00017338576450534984,
+      "loss": 4.5376,
+      "step": 310
+    },
+    {
+      "epoch": 0.9768354927365528,
+      "grad_norm": 2.671875,
+      "learning_rate": 0.00017321643315681832,
+      "loss": 4.7185,
+      "step": 311
+    },
+    {
+      "epoch": 0.9799764428739693,
+      "grad_norm": 2.421875,
+      "learning_rate": 0.000173046648086766,
+      "loss": 4.6617,
+      "step": 312
+    },
+    {
+      "epoch": 0.9831173930113859,
+      "grad_norm": 3.1875,
+      "learning_rate": 0.00017287641034734934,
+      "loss": 4.7403,
+      "step": 313
+    },
+    {
+      "epoch": 0.9862583431488026,
+      "grad_norm": 2.21875,
+      "learning_rate": 0.00017270572099352993,
+      "loss": 4.5652,
+      "step": 314
+    },
+    {
+      "epoch": 0.9893992932862191,
+      "grad_norm": 2.765625,
+      "learning_rate": 0.000172534581083068,
+      "loss": 4.5723,
+      "step": 315
+    },
+    {
+      "epoch": 0.9925402434236357,
+      "grad_norm": 2.9375,
+      "learning_rate": 0.00017236299167651593,
+      "loss": 4.6485,
+      "step": 316
+    },
+    {
+      "epoch": 0.9956811935610522,
+      "grad_norm": 3.109375,
+      "learning_rate": 0.0001721909538372116,
+      "loss": 4.5751,
+      "step": 317
+    },
+    {
+      "epoch": 0.9988221436984688,
+      "grad_norm": 3.046875,
+      "learning_rate": 0.0001720184686312718,
+      "loss": 4.5623,
+      "step": 318
+    },
+    {
+      "epoch": 1.0019630938358854,
+      "grad_norm": 2.578125,
+      "learning_rate": 0.0001718455371275857,
+      "loss": 4.5953,
+      "step": 319
+    },
+    {
+      "epoch": 1.0051040439733019,
+      "grad_norm": 2.765625,
+      "learning_rate": 0.00017167216039780812,
+      "loss": 4.7408,
+      "step": 320
+    },
+    {
+      "epoch": 1.0051040439733019,
+      "eval_loss": 4.618032932281494,
+      "eval_runtime": 67.0802,
+      "eval_samples_per_second": 38.774,
+      "eval_steps_per_second": 38.774,
+      "step": 320
+    },
+    {
+      "epoch": 1.0082449941107186,
+      "grad_norm": 2.6875,
+      "learning_rate": 0.00017149833951635293,
+      "loss": 4.804,
+      "step": 321
+    },
+    {
+      "epoch": 1.011385944248135,
+      "grad_norm": 2.984375,
+      "learning_rate": 0.00017132407556038644,
+      "loss": 4.5474,
+      "step": 322
+    },
+    {
+      "epoch": 1.0023557126030624,
+      "grad_norm": 3.15625,
+      "learning_rate": 0.00017114936960982072,
+      "loss": 4.5475,
+      "step": 323
+    },
+    {
+      "epoch": 1.0054966627404789,
+      "grad_norm": 2.625,
+      "learning_rate": 0.0001709742227473068,
+      "loss": 4.8615,
+      "step": 324
+    },
+    {
+      "epoch": 1.0086376128778956,
+      "grad_norm": 2.890625,
+      "learning_rate": 0.00017079863605822811,
+      "loss": 4.5709,
+      "step": 325
+    },
+    {
+      "epoch": 1.0117785630153122,
+      "grad_norm": 2.90625,
+      "learning_rate": 0.00017062261063069365,
+      "loss": 4.7747,
+      "step": 326
+    },
+    {
+      "epoch": 1.0149195131527287,
+      "grad_norm": 2.453125,
+      "learning_rate": 0.00017044614755553123,
+      "loss": 4.5197,
+      "step": 327
+    },
+    {
+      "epoch": 1.0180604632901453,
+      "grad_norm": 2.96875,
+      "learning_rate": 0.00017026924792628082,
+      "loss": 4.5271,
+      "step": 328
+    },
+    {
+      "epoch": 1.0212014134275618,
+      "grad_norm": 3.015625,
+      "learning_rate": 0.00017009191283918774,
+      "loss": 4.4289,
+      "step": 329
+    },
+    {
+      "epoch": 1.0243423635649784,
+      "grad_norm": 2.484375,
+      "learning_rate": 0.00016991414339319571,
+      "loss": 4.446,
+      "step": 330
+    },
+    {
+      "epoch": 1.0274833137023949,
+      "grad_norm": 3.328125,
+      "learning_rate": 0.0001697359406899403,
+      "loss": 4.5457,
+      "step": 331
+    },
+    {
+      "epoch": 1.0306242638398115,
+      "grad_norm": 3.3125,
+      "learning_rate": 0.0001695573058337419,
+      "loss": 4.5233,
+      "step": 332
+    },
+    {
+      "epoch": 1.0337652139772282,
+      "grad_norm": 1.9296875,
+      "learning_rate": 0.00016937823993159903,
+      "loss": 4.3562,
+      "step": 333
+    },
+    {
+      "epoch": 1.0369061641146446,
+      "grad_norm": 2.109375,
+      "learning_rate": 0.00016919874409318126,
+      "loss": 4.5259,
+      "step": 334
+    },
+    {
+      "epoch": 1.0400471142520613,
+      "grad_norm": 2.8125,
+      "learning_rate": 0.00016901881943082254,
+      "loss": 4.6123,
+      "step": 335
+    },
+    {
+      "epoch": 1.0431880643894778,
+      "grad_norm": 2.34375,
+      "learning_rate": 0.0001688384670595143,
+      "loss": 4.4088,
+      "step": 336
+    },
+    {
+      "epoch": 1.0463290145268944,
+      "grad_norm": 2.9375,
+      "learning_rate": 0.00016865768809689842,
+      "loss": 4.5822,
+      "step": 337
+    },
+    {
+      "epoch": 1.0494699646643109,
+      "grad_norm": 2.171875,
+      "learning_rate": 0.00016847648366326033,
+      "loss": 4.5317,
+      "step": 338
+    },
+    {
+      "epoch": 1.0526109148017275,
+      "grad_norm": 3.078125,
+      "learning_rate": 0.00016829485488152214,
+      "loss": 4.5681,
+      "step": 339
+    },
+    {
+      "epoch": 1.0557518649391442,
+      "grad_norm": 2.484375,
+      "learning_rate": 0.00016811280287723563,
+      "loss": 4.5301,
+      "step": 340
+    },
+    {
+      "epoch": 1.0588928150765606,
+      "grad_norm": 1.96875,
+      "learning_rate": 0.00016793032877857536,
+      "loss": 4.5032,
+      "step": 341
+    },
+    {
+      "epoch": 1.0620337652139773,
+      "grad_norm": 2.328125,
+      "learning_rate": 0.00016774743371633145,
+      "loss": 4.4028,
+      "step": 342
+    },
+    {
+      "epoch": 1.0651747153513937,
+      "grad_norm": 3.671875,
+      "learning_rate": 0.00016756411882390282,
+      "loss": 4.4828,
+      "step": 343
+    },
+    {
+      "epoch": 1.0683156654888104,
+      "grad_norm": 3.109375,
+      "learning_rate": 0.0001673803852372901,
+      "loss": 4.3682,
+      "step": 344
+    },
+    {
+      "epoch": 1.0714566156262268,
+      "grad_norm": 2.53125,
+      "learning_rate": 0.00016719623409508855,
+      "loss": 4.317,
+      "step": 345
+    },
+    {
+      "epoch": 1.0745975657636435,
+      "grad_norm": 2.6875,
+      "learning_rate": 0.00016701166653848096,
+      "loss": 4.5604,
+      "step": 346
+    },
+    {
+      "epoch": 1.0777385159010602,
+      "grad_norm": 2.546875,
+      "learning_rate": 0.0001668266837112307,
+      "loss": 4.401,
+      "step": 347
+    },
+    {
+      "epoch": 1.0808794660384766,
+      "grad_norm": 2.265625,
+      "learning_rate": 0.0001666412867596745,
+      "loss": 4.4679,
+      "step": 348
+    },
+    {
+      "epoch": 1.0840204161758933,
+      "grad_norm": 2.71875,
+      "learning_rate": 0.00016645547683271552,
+      "loss": 4.5537,
+      "step": 349
+    },
+    {
+      "epoch": 1.0871613663133097,
+      "grad_norm": 2.453125,
+      "learning_rate": 0.000166269255081816,
+      "loss": 4.3402,
+      "step": 350
+    },
+    {
+      "epoch": 1.0903023164507264,
+      "grad_norm": 2.515625,
+      "learning_rate": 0.00016608262266099035,
+      "loss": 4.3527,
+      "step": 351
+    },
+    {
+      "epoch": 1.0934432665881428,
+      "grad_norm": 2.28125,
+      "learning_rate": 0.00016589558072679786,
+      "loss": 4.6239,
+      "step": 352
+    },
+    {
+      "epoch": 1.0965842167255595,
+      "grad_norm": 2.484375,
+      "learning_rate": 0.00016570813043833554,
+      "loss": 4.5686,
+      "step": 353
+    },
+    {
+      "epoch": 1.0997251668629762,
+      "grad_norm": 2.96875,
+      "learning_rate": 0.000165520272957231,
+      "loss": 4.6111,
+      "step": 354
+    },
+    {
+      "epoch": 1.1028661170003926,
+      "grad_norm": 3.0625,
+      "learning_rate": 0.00016533200944763524,
+      "loss": 4.5757,
+      "step": 355
+    },
+    {
+      "epoch": 1.1060070671378093,
+      "grad_norm": 2.203125,
+      "learning_rate": 0.00016514334107621537,
+      "loss": 4.5229,
+      "step": 356
+    },
+    {
+      "epoch": 1.1091480172752257,
+      "grad_norm": 2.890625,
+      "learning_rate": 0.00016495426901214744,
+      "loss": 4.5219,
+      "step": 357
+    },
+    {
+      "epoch": 1.1122889674126424,
+      "grad_norm": 2.390625,
+      "learning_rate": 0.00016476479442710922,
+      "loss": 4.527,
+      "step": 358
+    },
+    {
+      "epoch": 1.1154299175500588,
+      "grad_norm": 2.25,
+      "learning_rate": 0.0001645749184952728,
+      "loss": 4.6095,
+      "step": 359
+    },
+    {
+      "epoch": 1.1185708676874755,
+      "grad_norm": 2.609375,
+      "learning_rate": 0.00016438464239329755,
+      "loss": 4.3415,
+      "step": 360
+    },
+    {
+      "epoch": 1.121711817824892,
+      "grad_norm": 2.921875,
+      "learning_rate": 0.00016419396730032253,
+      "loss": 4.6057,
+      "step": 361
+    },
+    {
+      "epoch": 1.1248527679623086,
+      "grad_norm": 2.765625,
+      "learning_rate": 0.00016400289439795948,
+      "loss": 4.4129,
+      "step": 362
+    },
+    {
+      "epoch": 1.1279937180997253,
+      "grad_norm": 3.296875,
+      "learning_rate": 0.0001638114248702853,
+      "loss": 4.4874,
+      "step": 363
+    },
+    {
+      "epoch": 1.1311346682371417,
+      "grad_norm": 2.90625,
+      "learning_rate": 0.00016361955990383477,
+      "loss": 4.3538,
+      "step": 364
+    },
+    {
+      "epoch": 1.1342756183745584,
+      "grad_norm": 2.921875,
+      "learning_rate": 0.00016342730068759327,
+      "loss": 4.472,
+      "step": 365
+    },
+    {
+      "epoch": 1.1374165685119748,
+      "grad_norm": 2.5625,
+      "learning_rate": 0.00016323464841298918,
+      "loss": 4.1759,
+      "step": 366
+    },
+    {
+      "epoch": 1.1405575186493915,
+      "grad_norm": 2.609375,
+      "learning_rate": 0.00016304160427388684,
+      "loss": 4.5234,
+      "step": 367
+    },
+    {
+      "epoch": 1.143698468786808,
+      "grad_norm": 2.65625,
+      "learning_rate": 0.0001628481694665789,
+      "loss": 4.3641,
+      "step": 368
+    },
+    {
+      "epoch": 1.1468394189242246,
+      "grad_norm": 2.28125,
+      "learning_rate": 0.00016265434518977892,
+      "loss": 4.5628,
+      "step": 369
+    },
+    {
+      "epoch": 1.149980369061641,
+      "grad_norm": 2.4375,
+      "learning_rate": 0.00016246013264461406,
+      "loss": 4.4381,
+      "step": 370
+    },
+    {
+      "epoch": 1.1531213191990577,
+      "grad_norm": 2.671875,
+      "learning_rate": 0.00016226553303461762,
+      "loss": 4.5478,
+      "step": 371
+    },
+    {
+      "epoch": 1.1562622693364744,
+      "grad_norm": 2.875,
+      "learning_rate": 0.00016207054756572141,
+      "loss": 4.4431,
+      "step": 372
+    },
+    {
+      "epoch": 1.1594032194738908,
+      "grad_norm": 2.5,
+      "learning_rate": 0.0001618751774462485,
+      "loss": 4.5903,
+      "step": 373
+    },
+    {
+      "epoch": 1.1625441696113075,
+      "grad_norm": 2.578125,
+      "learning_rate": 0.00016167942388690563,
+      "loss": 4.5634,
+      "step": 374
+    },
+    {
+      "epoch": 1.165685119748724,
+      "grad_norm": 2.5625,
+      "learning_rate": 0.00016148328810077568,
+      "loss": 4.4181,
+      "step": 375
+    },
+    {
+      "epoch": 1.1688260698861406,
+      "grad_norm": 2.53125,
+      "learning_rate": 0.0001612867713033102,
+      "loss": 4.3018,
+      "step": 376
+    },
+    {
+      "epoch": 1.171967020023557,
+      "grad_norm": 3.40625,
+      "learning_rate": 0.00016108987471232184,
+      "loss": 4.6465,
+      "step": 377
+    },
+    {
+      "epoch": 1.1751079701609737,
+      "grad_norm": 2.484375,
+      "learning_rate": 0.0001608925995479769,
+      "loss": 4.3892,
+      "step": 378
+    },
+    {
+      "epoch": 1.1782489202983903,
+      "grad_norm": 2.828125,
+      "learning_rate": 0.0001606949470327876,
+      "loss": 4.5286,
+      "step": 379
+    },
+    {
+      "epoch": 1.1813898704358068,
+      "grad_norm": 3.28125,
+      "learning_rate": 0.0001604969183916047,
+      "loss": 4.4929,
+      "step": 380
+    },
+    {
+      "epoch": 1.1845308205732235,
+      "grad_norm": 2.203125,
+      "learning_rate": 0.00016029851485160966,
+      "loss": 4.4002,
+      "step": 381
+    },
+    {
+      "epoch": 1.18767177071064,
+      "grad_norm": 2.984375,
+      "learning_rate": 0.00016009973764230742,
+      "loss": 4.4586,
+      "step": 382
+    },
+    {
+      "epoch": 1.1908127208480566,
+      "grad_norm": 3.421875,
+      "learning_rate": 0.00015990058799551825,
+      "loss": 4.6185,
+      "step": 383
+    },
+    {
+      "epoch": 1.193953670985473,
+      "grad_norm": 2.453125,
+      "learning_rate": 0.00015970106714537067,
+      "loss": 4.4776,
+      "step": 384
+    },
+    {
+      "epoch": 1.1970946211228897,
+      "grad_norm": 2.765625,
+      "learning_rate": 0.00015950117632829337,
+      "loss": 4.5512,
+      "step": 385
+    },
+    {
+      "epoch": 1.2002355712603063,
+      "grad_norm": 2.5625,
+      "learning_rate": 0.00015930091678300788,
+      "loss": 4.5065,
+      "step": 386
+    },
+    {
+      "epoch": 1.2033765213977228,
+      "grad_norm": 2.78125,
+      "learning_rate": 0.00015910028975052052,
+      "loss": 4.6741,
+      "step": 387
+    },
+    {
+      "epoch": 1.2065174715351394,
+      "grad_norm": 2.609375,
+      "learning_rate": 0.0001588992964741152,
+      "loss": 4.5716,
+      "step": 388
+    },
+    {
+      "epoch": 1.2096584216725559,
+      "grad_norm": 3.171875,
+      "learning_rate": 0.00015869793819934516,
+      "loss": 4.5801,
+      "step": 389
+    },
+    {
+      "epoch": 1.2127993718099725,
+      "grad_norm": 2.609375,
+      "learning_rate": 0.00015849621617402572,
+      "loss": 4.4056,
+      "step": 390
+    },
+    {
+      "epoch": 1.215940321947389,
+      "grad_norm": 2.5,
+      "learning_rate": 0.00015829413164822627,
+      "loss": 4.4631,
+      "step": 391
+    },
+    {
+      "epoch": 1.2190812720848057,
+      "grad_norm": 2.359375,
+      "learning_rate": 0.00015809168587426267,
+      "loss": 4.4807,
+      "step": 392
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 10.25,
+      "learning_rate": 0.00015788888010668942,
+      "loss": 4.4483,
+      "step": 393
+    },
+    {
+      "epoch": 1.2253631723596388,
+      "grad_norm": 3.0625,
+      "learning_rate": 0.00015768571560229185,
+      "loss": 4.3158,
+      "step": 394
+    },
+    {
+      "epoch": 1.2285041224970554,
+      "grad_norm": 5.0625,
+      "learning_rate": 0.00015748219362007838,
+      "loss": 4.5948,
+      "step": 395
+    },
+    {
+      "epoch": 1.2316450726344719,
+      "grad_norm": 3.40625,
+      "learning_rate": 0.0001572783154212728,
+      "loss": 4.503,
+      "step": 396
+    },
+    {
+      "epoch": 1.2347860227718885,
+      "grad_norm": 2.1875,
+      "learning_rate": 0.0001570740822693063,
+      "loss": 4.6138,
+      "step": 397
+    },
+    {
+      "epoch": 1.237926972909305,
+      "grad_norm": 3.328125,
+      "learning_rate": 0.00015686949542980972,
+      "loss": 4.4918,
+      "step": 398
+    },
+    {
+      "epoch": 1.2410679230467216,
+      "grad_norm": 2.90625,
+      "learning_rate": 0.00015666455617060568,
+      "loss": 4.5328,
+      "step": 399
+    },
+    {
+      "epoch": 1.2442088731841383,
+      "grad_norm": 2.484375,
+      "learning_rate": 0.0001564592657617008,
+      "loss": 4.5097,
+      "step": 400
+    },
+    {
+      "epoch": 1.2442088731841383,
+      "eval_loss": 4.506556510925293,
+      "eval_runtime": 67.1701,
+      "eval_samples_per_second": 38.723,
+      "eval_steps_per_second": 38.723,
+      "step": 400
+    },
+    {
+      "epoch": 1.2473498233215548,
+      "grad_norm": 2.171875,
+      "learning_rate": 0.00015625362547527774,
+      "loss": 4.2176,
+      "step": 401
+    },
+    {
+      "epoch": 1.2504907734589714,
+      "grad_norm": 2.265625,
+      "learning_rate": 0.00015604763658568733,
+      "loss": 4.5224,
+      "step": 402
+    },
+    {
+      "epoch": 1.2536317235963879,
+      "grad_norm": 1.7890625,
+      "learning_rate": 0.0001558413003694407,
+      "loss": 4.4113,
+      "step": 403
+    },
+    {
+      "epoch": 1.2567726737338045,
+      "grad_norm": 2.1875,
+      "learning_rate": 0.0001556346181052014,
+      "loss": 4.4202,
+      "step": 404
+    },
+    {
+      "epoch": 1.259913623871221,
+      "grad_norm": 2.875,
+      "learning_rate": 0.00015542759107377738,
+      "loss": 4.3784,
+      "step": 405
+    },
+    {
+      "epoch": 1.2630545740086376,
+      "grad_norm": 3.03125,
+      "learning_rate": 0.00015522022055811308,
+      "loss": 4.5884,
+      "step": 406
+    },
+    {
+      "epoch": 1.2661955241460543,
+      "grad_norm": 2.75,
+      "learning_rate": 0.00015501250784328167,
+      "loss": 4.506,
+      "step": 407
+    },
+    {
+      "epoch": 1.2693364742834707,
+      "grad_norm": 2.828125,
+      "learning_rate": 0.00015480445421647674,
+      "loss": 4.4045,
+      "step": 408
+    },
+    {
+      "epoch": 1.2724774244208872,
+      "grad_norm": 3.0625,
+      "learning_rate": 0.00015459606096700457,
+      "loss": 4.4833,
+      "step": 409
+    },
+    {
+      "epoch": 1.2756183745583038,
+      "grad_norm": 2.609375,
+      "learning_rate": 0.00015438732938627612,
+      "loss": 4.1899,
+      "step": 410
+    },
+    {
+      "epoch": 1.2787593246957205,
+      "grad_norm": 2.96875,
+      "learning_rate": 0.00015417826076779894,
+      "loss": 4.4343,
+      "step": 411
+    },
+    {
+      "epoch": 1.281900274833137,
+      "grad_norm": 2.8125,
+      "learning_rate": 0.00015396885640716926,
+      "loss": 4.3997,
+      "step": 412
+    },
+    {
+      "epoch": 1.2850412249705536,
+      "grad_norm": 2.671875,
+      "learning_rate": 0.0001537591176020638,
+      "loss": 4.3977,
+      "step": 413
+    },
+    {
+      "epoch": 1.2881821751079703,
+      "grad_norm": 1.921875,
+      "learning_rate": 0.0001535490456522319,
+      "loss": 4.3571,
+      "step": 414
+    },
+    {
+      "epoch": 1.2913231252453867,
+      "grad_norm": 2.40625,
+      "learning_rate": 0.0001533386418594874,
+      "loss": 4.37,
+      "step": 415
+    },
+    {
+      "epoch": 1.2944640753828032,
+      "grad_norm": 2.828125,
+      "learning_rate": 0.00015312790752770053,
+      "loss": 4.3312,
+      "step": 416
+    },
+    {
+      "epoch": 1.2976050255202198,
+      "grad_norm": 2.5625,
+      "learning_rate": 0.00015291684396278988,
+      "loss": 4.5376,
+      "step": 417
+    },
+    {
+      "epoch": 1.3007459756576365,
+      "grad_norm": 2.25,
+      "learning_rate": 0.00015270545247271432,
+      "loss": 4.2349,
+      "step": 418
+    },
+    {
+      "epoch": 1.303886925795053,
+      "grad_norm": 2.78125,
+      "learning_rate": 0.00015249373436746483,
+      "loss": 4.5092,
+      "step": 419
+    },
+    {
+      "epoch": 1.3070278759324696,
+      "grad_norm": 3.015625,
+      "learning_rate": 0.00015228169095905648,
+      "loss": 4.4942,
+      "step": 420
+    },
+    {
+      "epoch": 1.3101688260698863,
+      "grad_norm": 2.21875,
+      "learning_rate": 0.00015206932356152012,
+      "loss": 4.3255,
+      "step": 421
+    },
+    {
+      "epoch": 1.3133097762073027,
+      "grad_norm": 2.375,
+      "learning_rate": 0.00015185663349089455,
+      "loss": 4.3089,
+      "step": 422
+    },
+    {
+      "epoch": 1.3164507263447192,
+      "grad_norm": 2.4375,
+      "learning_rate": 0.00015164362206521794,
+      "loss": 4.2816,
+      "step": 423
+    },
+    {
+      "epoch": 1.3195916764821358,
+      "grad_norm": 3.359375,
+      "learning_rate": 0.00015143029060452008,
+      "loss": 4.4565,
+      "step": 424
+    },
+    {
+      "epoch": 1.3227326266195525,
+      "grad_norm": 2.828125,
+      "learning_rate": 0.00015121664043081393,
+      "loss": 4.1987,
+      "step": 425
+    },
+    {
+      "epoch": 1.325873576756969,
+      "grad_norm": 3.1875,
+      "learning_rate": 0.00015100267286808754,
+      "loss": 4.5203,
+      "step": 426
+    },
+    {
+      "epoch": 1.3290145268943856,
+      "grad_norm": 4.09375,
+      "learning_rate": 0.0001507883892422958,
+      "loss": 4.3488,
+      "step": 427
+    },
+    {
+      "epoch": 1.332155477031802,
+      "grad_norm": 2.625,
+      "learning_rate": 0.00015057379088135223,
+      "loss": 4.3254,
+      "step": 428
+    },
+    {
+      "epoch": 1.3352964271692187,
+      "grad_norm": 2.765625,
+      "learning_rate": 0.0001503588791151208,
+      "loss": 4.3639,
+      "step": 429
+    },
+    {
+      "epoch": 1.3384373773066351,
+      "grad_norm": 3.28125,
+      "learning_rate": 0.00015014365527540763,
+      "loss": 4.5418,
+      "step": 430
+    },
+    {
+      "epoch": 1.3415783274440518,
+      "grad_norm": 3.53125,
+      "learning_rate": 0.0001499281206959527,
+      "loss": 4.4342,
+      "step": 431
+    },
+    {
+      "epoch": 1.3447192775814685,
+      "grad_norm": 2.25,
+      "learning_rate": 0.00014971227671242175,
+      "loss": 4.4551,
+      "step": 432
+    },
+    {
+      "epoch": 1.347860227718885,
+      "grad_norm": 2.59375,
+      "learning_rate": 0.0001494961246623978,
+      "loss": 4.4315,
+      "step": 433
+    },
+    {
+      "epoch": 1.3510011778563016,
+      "grad_norm": 2.203125,
+      "learning_rate": 0.000149279665885373,
+      "loss": 4.376,
+      "step": 434
+    },
+    {
+      "epoch": 1.354142127993718,
+      "grad_norm": 2.390625,
+      "learning_rate": 0.00014906290172274033,
+      "loss": 4.3836,
+      "step": 435
+    },
+    {
+      "epoch": 1.3572830781311347,
+      "grad_norm": 2.421875,
+      "learning_rate": 0.00014884583351778508,
+      "loss": 4.5068,
+      "step": 436
+    },
+    {
+      "epoch": 1.3604240282685511,
+      "grad_norm": 2.484375,
+      "learning_rate": 0.0001486284626156769,
+      "loss": 4.3077,
+      "step": 437
+    },
+    {
+      "epoch": 1.3635649784059678,
+      "grad_norm": 2.15625,
+      "learning_rate": 0.00014841079036346106,
+      "loss": 4.3722,
+      "step": 438
+    },
+    {
+      "epoch": 1.3667059285433845,
+      "grad_norm": 2.515625,
+      "learning_rate": 0.00014819281811005047,
+      "loss": 4.362,
+      "step": 439
+    },
+    {
+      "epoch": 1.369846878680801,
+      "grad_norm": 2.53125,
+      "learning_rate": 0.00014797454720621696,
+      "loss": 4.3888,
+      "step": 440
+    },
+    {
+      "epoch": 1.3729878288182176,
+      "grad_norm": 16.625,
+      "learning_rate": 0.00014775597900458325,
+      "loss": 4.1893,
+      "step": 441
+    },
+    {
+      "epoch": 1.376128778955634,
+      "grad_norm": 2.796875,
+      "learning_rate": 0.00014753711485961435,
+      "loss": 4.4122,
+      "step": 442
+    },
+    {
+      "epoch": 1.3792697290930507,
+      "grad_norm": 2.78125,
+      "learning_rate": 0.00014731795612760916,
+      "loss": 4.4664,
+      "step": 443
+    },
+    {
+      "epoch": 1.3824106792304671,
+      "grad_norm": 2.515625,
+      "learning_rate": 0.00014709850416669227,
+      "loss": 4.384,
+      "step": 444
+    },
+    {
+      "epoch": 1.3855516293678838,
+      "grad_norm": 2.171875,
+      "learning_rate": 0.00014687876033680537,
+      "loss": 4.3617,
+      "step": 445
+    },
+    {
+      "epoch": 1.3886925795053005,
+      "grad_norm": 2.78125,
+      "learning_rate": 0.00014665872599969873,
+      "loss": 4.4573,
+      "step": 446
+    },
+    {
+      "epoch": 1.391833529642717,
+      "grad_norm": 2.15625,
+      "learning_rate": 0.00014643840251892301,
+      "loss": 4.5221,
+      "step": 447
+    },
+    {
+      "epoch": 1.3949744797801336,
+      "grad_norm": 1.9296875,
+      "learning_rate": 0.00014621779125982074,
+      "loss": 4.2984,
+      "step": 448
+    },
+    {
+      "epoch": 1.39811542991755,
+      "grad_norm": 2.484375,
+      "learning_rate": 0.00014599689358951764,
+      "loss": 4.4984,
+      "step": 449
+    },
+    {
+      "epoch": 1.4012563800549667,
+      "grad_norm": 2.125,
+      "learning_rate": 0.0001457757108769145,
+      "loss": 4.3669,
+      "step": 450
+    },
+    {
+      "epoch": 1.404397330192383,
+      "grad_norm": 2.453125,
+      "learning_rate": 0.00014555424449267835,
+      "loss": 4.3865,
+      "step": 451
+    },
+    {
+      "epoch": 1.4075382803297998,
+      "grad_norm": 2.546875,
+      "learning_rate": 0.00014533249580923427,
+      "loss": 4.5054,
+      "step": 452
+    },
+    {
+      "epoch": 1.4106792304672164,
+      "grad_norm": 2.390625,
+      "learning_rate": 0.00014511046620075665,
+      "loss": 4.3876,
+      "step": 453
+    },
+    {
+      "epoch": 1.4138201806046329,
+      "grad_norm": 2.484375,
+      "learning_rate": 0.00014488815704316084,
+      "loss": 4.508,
+      "step": 454
+    },
+    {
+      "epoch": 1.4169611307420495,
+      "grad_norm": 2.140625,
+      "learning_rate": 0.00014466556971409443,
+      "loss": 4.3182,
+      "step": 455
+    },
+    {
+      "epoch": 1.420102080879466,
+      "grad_norm": 2.421875,
+      "learning_rate": 0.00014444270559292905,
+      "loss": 4.4394,
+      "step": 456
+    },
+    {
+      "epoch": 1.4232430310168827,
+      "grad_norm": 2.515625,
+      "learning_rate": 0.0001442195660607514,
+      "loss": 4.5104,
+      "step": 457
+    },
+    {
+      "epoch": 1.426383981154299,
+      "grad_norm": 2.59375,
+      "learning_rate": 0.00014399615250035498,
+      "loss": 4.2292,
+      "step": 458
+    },
+    {
+      "epoch": 1.4295249312917158,
+      "grad_norm": 2.140625,
+      "learning_rate": 0.00014377246629623146,
+      "loss": 4.4134,
+      "step": 459
+    },
+    {
+      "epoch": 1.4326658814291324,
+      "grad_norm": 1.9453125,
+      "learning_rate": 0.00014354850883456207,
+      "loss": 4.3794,
+      "step": 460
+    },
+    {
+      "epoch": 1.4358068315665489,
+      "grad_norm": 2.515625,
+      "learning_rate": 0.000143324281503209,
+      "loss": 4.5643,
+      "step": 461
+    },
+    {
+      "epoch": 1.4389477817039653,
+      "grad_norm": 2.09375,
+      "learning_rate": 0.00014309978569170684,
+      "loss": 4.3962,
+      "step": 462
+    },
+    {
+      "epoch": 1.442088731841382,
+      "grad_norm": 2.5625,
+      "learning_rate": 0.0001428750227912539,
+      "loss": 4.3906,
+      "step": 463
+    },
+    {
+      "epoch": 1.4452296819787986,
+      "grad_norm": 2.34375,
+      "learning_rate": 0.00014264999419470373,
+      "loss": 4.5861,
+      "step": 464
+    },
+    {
+      "epoch": 1.448370632116215,
+      "grad_norm": 2.390625,
+      "learning_rate": 0.0001424247012965563,
+      "loss": 4.2325,
+      "step": 465
+    },
+    {
+      "epoch": 1.4515115822536317,
+      "grad_norm": 2.546875,
+      "learning_rate": 0.00014219914549294955,
+      "loss": 4.2783,
+      "step": 466
+    },
+    {
+      "epoch": 1.4546525323910484,
+      "grad_norm": 2.03125,
+      "learning_rate": 0.00014197332818165057,
+      "loss": 4.4554,
+      "step": 467
+    },
+    {
+      "epoch": 1.4577934825284649,
+      "grad_norm": 2.6875,
+      "learning_rate": 0.000141747250762047,
+      "loss": 4.3999,
+      "step": 468
+    },
+    {
+      "epoch": 1.4609344326658813,
+      "grad_norm": 2.265625,
+      "learning_rate": 0.00014152091463513845,
+      "loss": 4.3762,
+      "step": 469
+    },
+    {
+      "epoch": 1.464075382803298,
+      "grad_norm": 2.265625,
+      "learning_rate": 0.0001412943212035276,
+      "loss": 4.4881,
+      "step": 470
+    },
+    {
+      "epoch": 1.4672163329407146,
+      "grad_norm": 2.0625,
+      "learning_rate": 0.00014106747187141183,
+      "loss": 4.3938,
+      "step": 471
+    },
+    {
+      "epoch": 1.470357283078131,
+      "grad_norm": 2.171875,
+      "learning_rate": 0.0001408403680445742,
+      "loss": 4.2371,
+      "step": 472
+    },
+    {
+      "epoch": 1.4734982332155477,
+      "grad_norm": 2.765625,
+      "learning_rate": 0.00014061301113037485,
+      "loss": 4.3863,
+      "step": 473
+    },
+    {
+      "epoch": 1.4766391833529644,
+      "grad_norm": 2.0,
+      "learning_rate": 0.00014038540253774246,
+      "loss": 4.454,
+      "step": 474
+    },
+    {
+      "epoch": 1.4797801334903808,
+      "grad_norm": 2.140625,
+      "learning_rate": 0.00014015754367716518,
+      "loss": 4.2719,
+      "step": 475
+    },
+    {
+      "epoch": 1.4829210836277973,
+      "grad_norm": 2.96875,
+      "learning_rate": 0.00013992943596068217,
+      "loss": 4.5139,
+      "step": 476
+    },
+    {
+      "epoch": 1.486062033765214,
+      "grad_norm": 2.53125,
+      "learning_rate": 0.00013970108080187474,
+      "loss": 4.2512,
+      "step": 477
+    },
+    {
+      "epoch": 1.4892029839026306,
+      "grad_norm": 2.15625,
+      "learning_rate": 0.0001394724796158575,
+      "loss": 4.3844,
+      "step": 478
+    },
+    {
+      "epoch": 1.492343934040047,
+      "grad_norm": 2.609375,
+      "learning_rate": 0.00013924363381926985,
+      "loss": 4.4204,
+      "step": 479
+    },
+    {
+      "epoch": 1.4954848841774637,
+      "grad_norm": 2.5625,
+      "learning_rate": 0.0001390145448302669,
+      "loss": 4.3959,
+      "step": 480
+    },
+    {
+      "epoch": 1.4954848841774637,
+      "eval_loss": 4.451333522796631,
+      "eval_runtime": 66.8189,
+      "eval_samples_per_second": 38.926,
+      "eval_steps_per_second": 38.926,
+      "step": 480
+    },
+    {
+      "epoch": 1.4986258343148804,
+      "grad_norm": 2.859375,
+      "learning_rate": 0.0001387852140685109,
+      "loss": 4.3828,
+      "step": 481
+    },
+    {
+      "epoch": 1.5017667844522968,
+      "grad_norm": 1.9921875,
+      "learning_rate": 0.00013855564295516234,
+      "loss": 4.4479,
+      "step": 482
+    },
+    {
+      "epoch": 1.5049077345897133,
+      "grad_norm": 3.1875,
+      "learning_rate": 0.00013832583291287115,
+      "loss": 4.4646,
+      "step": 483
+    },
+    {
+      "epoch": 1.50804868472713,
+      "grad_norm": 2.4375,
+      "learning_rate": 0.00013809578536576797,
+      "loss": 4.2876,
+      "step": 484
+    },
+    {
+      "epoch": 1.5111896348645466,
+      "grad_norm": 2.625,
+      "learning_rate": 0.00013786550173945511,
+      "loss": 4.2475,
+      "step": 485
+    },
+    {
+      "epoch": 1.514330585001963,
+      "grad_norm": 2.15625,
+      "learning_rate": 0.00013763498346099803,
+      "loss": 4.4165,
+      "step": 486
+    },
+    {
+      "epoch": 1.5174715351393797,
+      "grad_norm": 2.390625,
+      "learning_rate": 0.00013740423195891623,
+      "loss": 4.3725,
+      "step": 487
+    },
+    {
+      "epoch": 1.5206124852767964,
+      "grad_norm": 2.5,
+      "learning_rate": 0.00013717324866317448,
+      "loss": 4.4698,
+      "step": 488
+    },
+    {
+      "epoch": 1.5237534354142128,
+      "grad_norm": 2.328125,
+      "learning_rate": 0.00013694203500517403,
+      "loss": 4.31,
+      "step": 489
+    },
+    {
+      "epoch": 1.5268943855516293,
+      "grad_norm": 2.59375,
+      "learning_rate": 0.0001367105924177437,
+      "loss": 4.4086,
+      "step": 490
+    },
+    {
+      "epoch": 1.530035335689046,
+      "grad_norm": 2.421875,
+      "learning_rate": 0.0001364789223351309,
+      "loss": 4.3244,
+      "step": 491
+    },
+    {
+      "epoch": 1.5331762858264626,
+      "grad_norm": 2.78125,
+      "learning_rate": 0.0001362470261929928,
+      "loss": 4.4675,
+      "step": 492
+    },
+    {
+      "epoch": 1.536317235963879,
+      "grad_norm": 2.328125,
+      "learning_rate": 0.00013601490542838765,
+      "loss": 4.363,
+      "step": 493
+    },
+    {
+      "epoch": 1.5394581861012955,
+      "grad_norm": 2.421875,
+      "learning_rate": 0.00013578256147976552,
+      "loss": 4.6301,
+      "step": 494
+    },
+    {
+      "epoch": 1.5425991362387124,
+      "grad_norm": 2.453125,
+      "learning_rate": 0.00013554999578695956,
+      "loss": 4.2604,
+      "step": 495
+    },
+    {
+      "epoch": 1.5457400863761288,
+      "grad_norm": 2.375,
+      "learning_rate": 0.0001353172097911771,
+      "loss": 4.4619,
+      "step": 496
+    },
+    {
+      "epoch": 1.5488810365135453,
+      "grad_norm": 2.015625,
+      "learning_rate": 0.00013508420493499069,
+      "loss": 4.3473,
+      "step": 497
+    },
+    {
+      "epoch": 1.552021986650962,
+      "grad_norm": 2.9375,
+      "learning_rate": 0.0001348509826623292,
+      "loss": 4.5858,
+      "step": 498
+    },
+    {
+      "epoch": 1.5551629367883786,
+      "grad_norm": 2.375,
+      "learning_rate": 0.00013461754441846868,
+      "loss": 4.5726,
+      "step": 499
+    },
+    {
+      "epoch": 1.558303886925795,
+      "grad_norm": 3.015625,
+      "learning_rate": 0.00013438389165002366,
+      "loss": 4.4859,
+      "step": 500
+    },
+    {
+      "epoch": 1.5614448370632115,
+      "grad_norm": 3.078125,
+      "learning_rate": 0.00013415002580493814,
+      "loss": 4.671,
+      "step": 501
+    },
+    {
+      "epoch": 1.5645857872006284,
+      "grad_norm": 2.984375,
+      "learning_rate": 0.00013391594833247642,
+      "loss": 4.282,
+      "step": 502
+    },
+    {
+      "epoch": 1.5677267373380448,
+      "grad_norm": 2.359375,
+      "learning_rate": 0.00013368166068321432,
+      "loss": 4.0765,
+      "step": 503
+    },
+    {
+      "epoch": 1.5708676874754612,
+      "grad_norm": 3.109375,
+      "learning_rate": 0.00013344716430903014,
+      "loss": 4.5436,
+      "step": 504
+    },
+    {
+      "epoch": 1.574008637612878,
+      "grad_norm": 2.890625,
+      "learning_rate": 0.00013321246066309554,
+      "loss": 4.3819,
+      "step": 505
+    },
+    {
+      "epoch": 1.5771495877502946,
+      "grad_norm": 1.6796875,
+      "learning_rate": 0.00013297755119986678,
+      "loss": 4.2561,
+      "step": 506
+    },
+    {
+      "epoch": 1.580290537887711,
+      "grad_norm": 2.296875,
+      "learning_rate": 0.0001327424373750755,
+      "loss": 4.2601,
+      "step": 507
+    },
+    {
+      "epoch": 1.5834314880251275,
+      "grad_norm": 2.34375,
+      "learning_rate": 0.0001325071206457198,
+      "loss": 4.4291,
+      "step": 508
+    },
+    {
+      "epoch": 1.5865724381625441,
+      "grad_norm": 2.25,
+      "learning_rate": 0.00013227160247005512,
+      "loss": 4.2262,
+      "step": 509
+    },
+    {
+      "epoch": 1.5897133882999608,
+      "grad_norm": 2.546875,
+      "learning_rate": 0.00013203588430758532,
+      "loss": 4.5678,
+      "step": 510
+    },
+    {
+      "epoch": 1.5928543384373772,
+      "grad_norm": 2.703125,
+      "learning_rate": 0.0001317999676190535,
+      "loss": 4.197,
+      "step": 511
+    },
+    {
+      "epoch": 1.595995288574794,
+      "grad_norm": 2.703125,
+      "learning_rate": 0.0001315638538664331,
+      "loss": 4.4492,
+      "step": 512
+    },
+    {
+      "epoch": 1.5991362387122106,
+      "grad_norm": 6.21875,
+      "learning_rate": 0.00013132754451291876,
+      "loss": 4.2175,
+      "step": 513
+    },
+    {
+      "epoch": 1.602277188849627,
+      "grad_norm": 2.53125,
+      "learning_rate": 0.0001310910410229172,
+      "loss": 4.343,
+      "step": 514
+    },
+    {
+      "epoch": 1.6054181389870434,
+      "grad_norm": 3.140625,
+      "learning_rate": 0.00013085434486203825,
+      "loss": 4.3108,
+      "step": 515
+    },
+    {
+      "epoch": 1.60855908912446,
+      "grad_norm": 2.0625,
+      "learning_rate": 0.0001306174574970857,
+      "loss": 4.3422,
+      "step": 516
+    },
+    {
+      "epoch": 1.6117000392618768,
+      "grad_norm": 2.0,
+      "learning_rate": 0.00013038038039604822,
+      "loss": 4.4012,
+      "step": 517
+    },
+    {
+      "epoch": 1.6148409893992932,
+      "grad_norm": 2.265625,
+      "learning_rate": 0.00013014311502809037,
+      "loss": 4.4995,
+      "step": 518
+    },
+    {
+      "epoch": 1.6179819395367099,
+      "grad_norm": 2.625,
+      "learning_rate": 0.0001299056628635432,
+      "loss": 4.3733,
+      "step": 519
+    },
+    {
+      "epoch": 1.6211228896741265,
+      "grad_norm": 2.3125,
+      "learning_rate": 0.00012966802537389555,
+      "loss": 4.2762,
+      "step": 520
+    },
+    {
+      "epoch": 1.624263839811543,
+      "grad_norm": 2.171875,
+      "learning_rate": 0.0001294302040317846,
+      "loss": 4.2215,
+      "step": 521
+    },
+    {
+      "epoch": 1.6274047899489594,
+      "grad_norm": 2.265625,
+      "learning_rate": 0.0001291922003109868,
+      "loss": 4.3246,
+      "step": 522
+    },
+    {
+      "epoch": 1.630545740086376,
+      "grad_norm": 1.9296875,
+      "learning_rate": 0.00012895401568640898,
+      "loss": 4.3613,
+      "step": 523
+    },
+    {
+      "epoch": 1.6336866902237928,
+      "grad_norm": 2.296875,
+      "learning_rate": 0.0001287156516340789,
+      "loss": 4.3989,
+      "step": 524
+    },
+    {
+      "epoch": 1.6368276403612092,
+      "grad_norm": 1.953125,
+      "learning_rate": 0.00012847710963113625,
+      "loss": 4.3381,
+      "step": 525
+    },
+    {
+      "epoch": 1.6399685904986259,
+      "grad_norm": 2.15625,
+      "learning_rate": 0.00012823839115582353,
+      "loss": 4.2076,
+      "step": 526
+    },
+    {
+      "epoch": 1.6431095406360425,
+      "grad_norm": 2.359375,
+      "learning_rate": 0.00012799949768747674,
+      "loss": 4.4172,
+      "step": 527
+    },
+    {
+      "epoch": 1.646250490773459,
+      "grad_norm": 2.609375,
+      "learning_rate": 0.00012776043070651641,
+      "loss": 4.3251,
+      "step": 528
+    },
+    {
+      "epoch": 1.6493914409108754,
+      "grad_norm": 2.09375,
+      "learning_rate": 0.00012752119169443828,
+      "loss": 4.4384,
+      "step": 529
+    },
+    {
+      "epoch": 1.652532391048292,
+      "grad_norm": 2.53125,
+      "learning_rate": 0.00012728178213380418,
+      "loss": 4.4118,
+      "step": 530
+    },
+    {
+      "epoch": 1.6556733411857087,
+      "grad_norm": 2.96875,
+      "learning_rate": 0.00012704220350823276,
+      "loss": 4.4677,
+      "step": 531
+    },
+    {
+      "epoch": 1.6588142913231252,
+      "grad_norm": 2.28125,
+      "learning_rate": 0.00012680245730239048,
+      "loss": 4.2893,
+      "step": 532
+    },
+    {
+      "epoch": 1.6619552414605419,
+      "grad_norm": 2.40625,
+      "learning_rate": 0.00012656254500198222,
+      "loss": 4.4359,
+      "step": 533
+    },
+    {
+      "epoch": 1.6650961915979585,
+      "grad_norm": 2.15625,
+      "learning_rate": 0.00012632246809374215,
+      "loss": 4.2847,
+      "step": 534
+    },
+    {
+      "epoch": 1.668237141735375,
+      "grad_norm": 2.375,
+      "learning_rate": 0.00012608222806542455,
+      "loss": 4.4685,
+      "step": 535
+    },
+    {
+      "epoch": 1.6713780918727914,
+      "grad_norm": 2.515625,
+      "learning_rate": 0.0001258418264057945,
+      "loss": 4.5453,
+      "step": 536
+    },
+    {
+      "epoch": 1.674519042010208,
+      "grad_norm": 2.25,
+      "learning_rate": 0.00012560126460461877,
+      "loss": 4.3264,
+      "step": 537
+    },
+    {
+      "epoch": 1.6776599921476247,
+      "grad_norm": 2.203125,
+      "learning_rate": 0.00012536054415265643,
+      "loss": 4.3535,
+      "step": 538
+    },
+    {
+      "epoch": 1.6808009422850412,
+      "grad_norm": 2.3125,
+      "learning_rate": 0.00012511966654164982,
+      "loss": 4.2926,
+      "step": 539
+    },
+    {
+      "epoch": 1.6839418924224578,
+      "grad_norm": 2.46875,
+      "learning_rate": 0.00012487863326431512,
+      "loss": 4.4511,
+      "step": 540
+    },
+    {
+      "epoch": 1.6870828425598745,
+      "grad_norm": 1.8359375,
+      "learning_rate": 0.00012463744581433324,
+      "loss": 4.278,
+      "step": 541
+    },
+    {
+      "epoch": 1.690223792697291,
+      "grad_norm": 1.828125,
+      "learning_rate": 0.00012439610568634038,
+      "loss": 4.3352,
+      "step": 542
+    },
+    {
+      "epoch": 1.6933647428347074,
+      "grad_norm": 2.125,
+      "learning_rate": 0.00012415461437591897,
+      "loss": 4.4679,
+      "step": 543
+    },
+    {
+      "epoch": 1.696505692972124,
+      "grad_norm": 2.46875,
+      "learning_rate": 0.00012391297337958833,
+      "loss": 4.4969,
+      "step": 544
+    },
+    {
+      "epoch": 1.6996466431095407,
+      "grad_norm": 2.140625,
+      "learning_rate": 0.00012367118419479535,
+      "loss": 4.2671,
+      "step": 545
+    },
+    {
+      "epoch": 1.7027875932469572,
+      "grad_norm": 2.375,
+      "learning_rate": 0.00012342924831990526,
+      "loss": 4.4847,
+      "step": 546
+    },
+    {
+      "epoch": 1.7059285433843736,
+      "grad_norm": 2.625,
+      "learning_rate": 0.00012318716725419224,
+      "loss": 4.2947,
+      "step": 547
+    },
+    {
+      "epoch": 1.7090694935217905,
+      "grad_norm": 2.5,
+      "learning_rate": 0.00012294494249783037,
+      "loss": 4.174,
+      "step": 548
+    },
+    {
+      "epoch": 1.712210443659207,
+      "grad_norm": 2.4375,
+      "learning_rate": 0.00012270257555188407,
+      "loss": 4.4681,
+      "step": 549
+    },
+    {
+      "epoch": 1.7153513937966234,
+      "grad_norm": 13.3125,
+      "learning_rate": 0.0001224600679182989,
+      "loss": 4.6303,
+      "step": 550
+    },
+    {
+      "epoch": 1.71849234393404,
+      "grad_norm": 2.515625,
+      "learning_rate": 0.00012221742109989233,
+      "loss": 4.5057,
+      "step": 551
+    },
+    {
+      "epoch": 1.7216332940714567,
+      "grad_norm": 2.4375,
+      "learning_rate": 0.00012197463660034433,
+      "loss": 4.4893,
+      "step": 552
+    },
+    {
+      "epoch": 1.7247742442088732,
+      "grad_norm": 2.234375,
+      "learning_rate": 0.00012173171592418809,
+      "loss": 4.279,
+      "step": 553
+    },
+    {
+      "epoch": 1.7279151943462896,
+      "grad_norm": 2.265625,
+      "learning_rate": 0.00012148866057680058,
+      "loss": 4.4123,
+      "step": 554
+    },
+    {
+      "epoch": 1.7310561444837065,
+      "grad_norm": 2.171875,
+      "learning_rate": 0.0001212454720643935,
+      "loss": 4.2059,
+      "step": 555
+    },
+    {
+      "epoch": 1.734197094621123,
+      "grad_norm": 1.890625,
+      "learning_rate": 0.00012100215189400363,
+      "loss": 4.5014,
+      "step": 556
+    },
+    {
+      "epoch": 1.7373380447585394,
+      "grad_norm": 2.15625,
+      "learning_rate": 0.00012075870157348374,
+      "loss": 4.3094,
+      "step": 557
+    },
+    {
+      "epoch": 1.740478994895956,
+      "grad_norm": 1.984375,
+      "learning_rate": 0.00012051512261149304,
+      "loss": 4.3979,
+      "step": 558
+    },
+    {
+      "epoch": 1.7436199450333727,
+      "grad_norm": 2.234375,
+      "learning_rate": 0.000120271416517488,
+      "loss": 4.3862,
+      "step": 559
+    },
+    {
+      "epoch": 1.7467608951707891,
+      "grad_norm": 2.03125,
+      "learning_rate": 0.0001200275848017129,
+      "loss": 4.2488,
+      "step": 560
+    },
+    {
+      "epoch": 1.7467608951707891,
+      "eval_loss": 4.41070032119751,
+      "eval_runtime": 66.8827,
+      "eval_samples_per_second": 38.889,
+      "eval_steps_per_second": 38.889,
+      "step": 560
+    },
+    {
+      "epoch": 1.7499018453082056,
+      "grad_norm": 2.6875,
+      "learning_rate": 0.00011978362897519048,
+      "loss": 4.3708,
+      "step": 561
+    },
+    {
+      "epoch": 1.7530427954456222,
+      "grad_norm": 2.046875,
+      "learning_rate": 0.00011953955054971267,
+      "loss": 4.3017,
+      "step": 562
+    },
+    {
+      "epoch": 1.756183745583039,
+      "grad_norm": 2.78125,
+      "learning_rate": 0.00011929535103783102,
+      "loss": 4.5012,
+      "step": 563
+    },
+    {
+      "epoch": 1.7593246957204554,
+      "grad_norm": 2.0,
+      "learning_rate": 0.00011905103195284755,
+      "loss": 4.2299,
+      "step": 564
+    },
+    {
+      "epoch": 1.762465645857872,
+      "grad_norm": 2.234375,
+      "learning_rate": 0.00011880659480880526,
+      "loss": 4.3933,
+      "step": 565
+    },
+    {
+      "epoch": 1.7656065959952887,
+      "grad_norm": 2.234375,
+      "learning_rate": 0.0001185620411204787,
+      "loss": 4.2709,
+      "step": 566
+    },
+    {
+      "epoch": 1.7687475461327051,
+      "grad_norm": 2.390625,
+      "learning_rate": 0.00011831737240336474,
+      "loss": 4.4057,
+      "step": 567
+    },
+    {
+      "epoch": 1.7718884962701216,
+      "grad_norm": 2.515625,
+      "learning_rate": 0.00011807259017367298,
+      "loss": 4.4554,
+      "step": 568
+    },
+    {
+      "epoch": 1.7750294464075382,
+      "grad_norm": 2.296875,
+      "learning_rate": 0.00011782769594831654,
+      "loss": 4.3689,
+      "step": 569
+    },
+    {
+      "epoch": 1.778170396544955,
+      "grad_norm": 2.59375,
+      "learning_rate": 0.00011758269124490246,
+      "loss": 4.3838,
+      "step": 570
+    },
+    {
+      "epoch": 1.7813113466823713,
+      "grad_norm": 2.015625,
+      "learning_rate": 0.00011733757758172263,
+      "loss": 4.3976,
+      "step": 571
+    },
+    {
+      "epoch": 1.784452296819788,
+      "grad_norm": 2.140625,
+      "learning_rate": 0.00011709235647774393,
+      "loss": 4.402,
+      "step": 572
+    },
+    {
+      "epoch": 1.7875932469572047,
+      "grad_norm": 3.015625,
+      "learning_rate": 0.00011684702945259917,
+      "loss": 4.2222,
+      "step": 573
+    },
+    {
+      "epoch": 1.7907341970946211,
+      "grad_norm": 2.3125,
+      "learning_rate": 0.00011660159802657751,
+      "loss": 4.4154,
+      "step": 574
+    },
+    {
+      "epoch": 1.7938751472320376,
+      "grad_norm": 2.28125,
+      "learning_rate": 0.00011635606372061514,
+      "loss": 4.4392,
+      "step": 575
+    },
+    {
+      "epoch": 1.7970160973694542,
+      "grad_norm": 2.109375,
+      "learning_rate": 0.00011611042805628569,
+      "loss": 4.4036,
+      "step": 576
+    },
+    {
+      "epoch": 1.8001570475068709,
+      "grad_norm": 2.234375,
+      "learning_rate": 0.00011586469255579105,
+      "loss": 4.4612,
+      "step": 577
+    },
+    {
+      "epoch": 1.8032979976442873,
+      "grad_norm": 2.5625,
+      "learning_rate": 0.00011561885874195168,
+      "loss": 4.4179,
+      "step": 578
+    },
+    {
+      "epoch": 1.806438947781704,
+      "grad_norm": 2.34375,
+      "learning_rate": 0.00011537292813819727,
+      "loss": 4.3832,
+      "step": 579
+    },
+    {
+      "epoch": 1.8095798979191207,
+      "grad_norm": 2.28125,
+      "learning_rate": 0.00011512690226855747,
+      "loss": 4.418,
+      "step": 580
+    },
+    {
+      "epoch": 1.812720848056537,
+      "grad_norm": 2.375,
+      "learning_rate": 0.00011488078265765209,
+      "loss": 4.2513,
+      "step": 581
+    },
+    {
+      "epoch": 1.8158617981939535,
+      "grad_norm": 2.46875,
+      "learning_rate": 0.00011463457083068203,
+      "loss": 4.4319,
+      "step": 582
+    },
+    {
+      "epoch": 1.8190027483313702,
+      "grad_norm": 2.078125,
+      "learning_rate": 0.00011438826831341953,
+      "loss": 4.1437,
+      "step": 583
+    },
+    {
+      "epoch": 1.8221436984687869,
+      "grad_norm": 2.125,
+      "learning_rate": 0.00011414187663219891,
+      "loss": 4.1201,
+      "step": 584
+    },
+    {
+      "epoch": 1.8252846486062033,
+      "grad_norm": 2.78125,
+      "learning_rate": 0.00011389539731390699,
+      "loss": 4.4478,
+      "step": 585
+    },
+    {
+      "epoch": 1.82842559874362,
+      "grad_norm": 2.515625,
+      "learning_rate": 0.00011364883188597369,
+      "loss": 4.3716,
+      "step": 586
+    },
+    {
+      "epoch": 1.8315665488810366,
+      "grad_norm": 2.03125,
+      "learning_rate": 0.0001134021818763626,
+      "loss": 4.2461,
+      "step": 587
+    },
+    {
+      "epoch": 1.834707499018453,
+      "grad_norm": 1.9140625,
+      "learning_rate": 0.0001131554488135614,
+      "loss": 4.3287,
+      "step": 588
+    },
+    {
+      "epoch": 1.8378484491558695,
+      "grad_norm": 2.3125,
+      "learning_rate": 0.00011290863422657241,
+      "loss": 4.3955,
+      "step": 589
+    },
+    {
+      "epoch": 1.8409893992932862,
+      "grad_norm": 1.84375,
+      "learning_rate": 0.00011266173964490332,
+      "loss": 4.0536,
+      "step": 590
+    },
+    {
+      "epoch": 1.8441303494307029,
+      "grad_norm": 1.984375,
+      "learning_rate": 0.00011241476659855736,
+      "loss": 4.3023,
+      "step": 591
+    },
+    {
+      "epoch": 1.8472712995681193,
+      "grad_norm": 2.1875,
+      "learning_rate": 0.00011216771661802412,
+      "loss": 4.3013,
+      "step": 592
+    },
+    {
+      "epoch": 1.850412249705536,
+      "grad_norm": 1.9921875,
+      "learning_rate": 0.00011192059123426987,
+      "loss": 4.5245,
+      "step": 593
+    },
+    {
+      "epoch": 1.8535531998429526,
+      "grad_norm": 2.1875,
+      "learning_rate": 0.00011167339197872828,
+      "loss": 4.4204,
+      "step": 594
+    },
+    {
+      "epoch": 1.856694149980369,
+      "grad_norm": 1.828125,
+      "learning_rate": 0.00011142612038329066,
+      "loss": 4.0721,
+      "step": 595
+    },
+    {
+      "epoch": 1.8598351001177855,
+      "grad_norm": 2.484375,
+      "learning_rate": 0.00011117877798029665,
+      "loss": 4.2945,
+      "step": 596
+    },
+    {
+      "epoch": 1.8629760502552022,
+      "grad_norm": 2.203125,
+      "learning_rate": 0.00011093136630252477,
+      "loss": 4.4501,
+      "step": 597
+    },
+    {
+      "epoch": 1.8661170003926189,
+      "grad_norm": 1.796875,
+      "learning_rate": 0.00011068388688318272,
+      "loss": 4.3144,
+      "step": 598
+    },
+    {
+      "epoch": 1.8692579505300353,
+      "grad_norm": 2.171875,
+      "learning_rate": 0.00011043634125589808,
+      "loss": 4.1987,
+      "step": 599
+    },
+    {
+      "epoch": 1.8723989006674517,
+      "grad_norm": 2.15625,
+      "learning_rate": 0.00011018873095470865,
+      "loss": 4.3245,
+      "step": 600
+    },
+    {
+      "epoch": 1.8755398508048686,
+      "grad_norm": 2.65625,
+      "learning_rate": 0.00010994105751405306,
+      "loss": 4.3071,
+      "step": 601
+    },
+    {
+      "epoch": 1.878680800942285,
+      "grad_norm": 2.171875,
+      "learning_rate": 0.0001096933224687612,
+      "loss": 4.3158,
+      "step": 602
+    },
+    {
+      "epoch": 1.8818217510797015,
+      "grad_norm": 2.140625,
+      "learning_rate": 0.00010944552735404472,
+      "loss": 4.4555,
+      "step": 603
+    },
+    {
+      "epoch": 1.8849627012171182,
+      "grad_norm": 2.515625,
+      "learning_rate": 0.00010919767370548755,
+      "loss": 4.2628,
+      "step": 604
+    },
+    {
+      "epoch": 1.8881036513545348,
+      "grad_norm": 2.53125,
+      "learning_rate": 0.00010894976305903633,
+      "loss": 4.4439,
+      "step": 605
+    },
+    {
+      "epoch": 1.8912446014919513,
+      "grad_norm": 2.640625,
+      "learning_rate": 0.00010870179695099082,
+      "loss": 4.2774,
+      "step": 606
+    },
+    {
+      "epoch": 1.8943855516293677,
+      "grad_norm": 1.9921875,
+      "learning_rate": 0.00010845377691799471,
+      "loss": 4.0835,
+      "step": 607
+    },
+    {
+      "epoch": 1.8975265017667846,
+      "grad_norm": 2.6875,
+      "learning_rate": 0.00010820570449702563,
+      "loss": 4.3015,
+      "step": 608
+    },
+    {
+      "epoch": 1.900667451904201,
+      "grad_norm": 2.1875,
+      "learning_rate": 0.00010795758122538597,
+      "loss": 4.286,
+      "step": 609
+    },
+    {
+      "epoch": 1.9038084020416175,
+      "grad_norm": 2.4375,
+      "learning_rate": 0.0001077094086406932,
+      "loss": 4.403,
+      "step": 610
+    },
+    {
+      "epoch": 1.9069493521790342,
+      "grad_norm": 1.96875,
+      "learning_rate": 0.00010746118828087046,
+      "loss": 4.3406,
+      "step": 611
+    },
+    {
+      "epoch": 1.9100903023164508,
+      "grad_norm": 2.421875,
+      "learning_rate": 0.00010721292168413685,
+      "loss": 4.2346,
+      "step": 612
+    },
+    {
+      "epoch": 1.9132312524538673,
+      "grad_norm": 2.09375,
+      "learning_rate": 0.00010696461038899803,
+      "loss": 4.1966,
+      "step": 613
+    },
+    {
+      "epoch": 1.9163722025912837,
+      "grad_norm": 1.9765625,
+      "learning_rate": 0.00010671625593423671,
+      "loss": 4.3923,
+      "step": 614
+    },
+    {
+      "epoch": 1.9195131527287004,
+      "grad_norm": 2.296875,
+      "learning_rate": 0.00010646785985890297,
+      "loss": 4.5358,
+      "step": 615
+    },
+    {
+      "epoch": 1.922654102866117,
+      "grad_norm": 2.125,
+      "learning_rate": 0.00010621942370230491,
+      "loss": 4.268,
+      "step": 616
+    },
+    {
+      "epoch": 1.9257950530035335,
+      "grad_norm": 2.15625,
+      "learning_rate": 0.00010597094900399894,
+      "loss": 4.1337,
+      "step": 617
+    },
+    {
+      "epoch": 1.9289360031409502,
+      "grad_norm": 1.8515625,
+      "learning_rate": 0.00010572243730378033,
+      "loss": 4.4463,
+      "step": 618
+    },
+    {
+      "epoch": 1.9320769532783668,
+      "grad_norm": 2.375,
+      "learning_rate": 0.00010547389014167368,
+      "loss": 4.4137,
+      "step": 619
+    },
+    {
+      "epoch": 1.9352179034157833,
+      "grad_norm": 1.71875,
+      "learning_rate": 0.00010522530905792333,
+      "loss": 4.1703,
+      "step": 620
+    },
+    {
+      "epoch": 1.9383588535531997,
+      "grad_norm": 2.1875,
+      "learning_rate": 0.00010497669559298377,
+      "loss": 4.4996,
+      "step": 621
+    },
+    {
+      "epoch": 1.9414998036906164,
+      "grad_norm": 1.84375,
+      "learning_rate": 0.00010472805128751028,
+      "loss": 4.3086,
+      "step": 622
+    },
+    {
+      "epoch": 1.944640753828033,
+      "grad_norm": 1.9609375,
+      "learning_rate": 0.00010447937768234917,
+      "loss": 4.3102,
+      "step": 623
+    },
+    {
+      "epoch": 1.9477817039654495,
+      "grad_norm": 2.109375,
+      "learning_rate": 0.00010423067631852834,
+      "loss": 4.2649,
+      "step": 624
+    },
+    {
+      "epoch": 1.9509226541028661,
+      "grad_norm": 1.890625,
+      "learning_rate": 0.00010398194873724766,
+      "loss": 4.3634,
+      "step": 625
+    },
+    {
+      "epoch": 1.9540636042402828,
+      "grad_norm": 2.359375,
+      "learning_rate": 0.00010373319647986964,
+      "loss": 4.4628,
+      "step": 626
+    },
+    {
+      "epoch": 1.9572045543776992,
+      "grad_norm": 2.234375,
+      "learning_rate": 0.00010348442108790948,
+      "loss": 4.1411,
+      "step": 627
+    },
+    {
+      "epoch": 1.9603455045151157,
+      "grad_norm": 2.234375,
+      "learning_rate": 0.00010323562410302587,
+      "loss": 4.211,
+      "step": 628
+    },
+    {
+      "epoch": 1.9634864546525324,
+      "grad_norm": 2.390625,
+      "learning_rate": 0.00010298680706701136,
+      "loss": 4.3108,
+      "step": 629
+    },
+    {
+      "epoch": 1.966627404789949,
+      "grad_norm": 2.125,
+      "learning_rate": 0.00010273797152178262,
+      "loss": 4.4238,
+      "step": 630
+    },
+    {
+      "epoch": 1.9697683549273655,
+      "grad_norm": 2.5625,
+      "learning_rate": 0.00010248911900937112,
+      "loss": 4.3534,
+      "step": 631
+    },
+    {
+      "epoch": 1.9729093050647821,
+      "grad_norm": 1.9453125,
+      "learning_rate": 0.00010224025107191342,
+      "loss": 4.2111,
+      "step": 632
+    },
+    {
+      "epoch": 1.9760502552021988,
+      "grad_norm": 2.078125,
+      "learning_rate": 0.00010199136925164175,
+      "loss": 4.2815,
+      "step": 633
+    },
+    {
+      "epoch": 1.9791912053396152,
+      "grad_norm": 1.6328125,
+      "learning_rate": 0.00010174247509087429,
+      "loss": 4.2197,
+      "step": 634
+    },
+    {
+      "epoch": 1.9823321554770317,
+      "grad_norm": 1.9609375,
+      "learning_rate": 0.00010149357013200569,
+      "loss": 4.3111,
+      "step": 635
+    },
+    {
+      "epoch": 1.9854731056144483,
+      "grad_norm": 1.9609375,
+      "learning_rate": 0.00010124465591749758,
+      "loss": 4.3573,
+      "step": 636
+    },
+    {
+      "epoch": 1.988614055751865,
+      "grad_norm": 2.09375,
+      "learning_rate": 0.00010099573398986894,
+      "loss": 4.2183,
+      "step": 637
+    },
+    {
+      "epoch": 1.9917550058892814,
+      "grad_norm": 2.03125,
+      "learning_rate": 0.00010074680589168646,
+      "loss": 4.3098,
+      "step": 638
+    },
+    {
+      "epoch": 1.9948959560266981,
+      "grad_norm": 2.171875,
+      "learning_rate": 0.00010049787316555518,
+      "loss": 4.3239,
+      "step": 639
+    },
+    {
+      "epoch": 1.9980369061641148,
+      "grad_norm": 1.8515625,
+      "learning_rate": 0.00010024893735410877,
+      "loss": 4.3507,
+      "step": 640
+    },
+    {
+      "epoch": 1.9980369061641148,
+      "eval_loss": 4.378408908843994,
+      "eval_runtime": 66.9323,
+      "eval_samples_per_second": 38.86,
+      "eval_steps_per_second": 38.86,
+      "step": 640
+    },
+    {
+      "epoch": 2.001177856301531,
+      "grad_norm": 2.25,
+      "learning_rate": 0.0001,
+      "loss": 4.2497,
+      "step": 641
+    },
+    {
+      "epoch": 2.004318806438948,
+      "grad_norm": 1.921875,
+      "learning_rate": 9.975106264589126e-05,
+      "loss": 4.2847,
+      "step": 642
+    },
+    {
+      "epoch": 2.007459756576364,
+      "grad_norm": 2.1875,
+      "learning_rate": 9.950212683444484e-05,
+      "loss": 4.4708,
+      "step": 643
+    },
+    {
+      "epoch": 2.010600706713781,
+      "grad_norm": 1.8828125,
+      "learning_rate": 9.925319410831354e-05,
+      "loss": 4.3746,
+      "step": 644
+    },
+    {
+      "epoch": 2.0137416568511974,
+      "grad_norm": 2.34375,
+      "learning_rate": 9.900426601013108e-05,
+      "loss": 4.435,
+      "step": 645
+    },
+    {
+      "epoch": 2.0027483313702397,
+      "grad_norm": 2.09375,
+      "learning_rate": 9.875534408250244e-05,
+      "loss": 4.0501,
+      "step": 646
+    },
+    {
+      "epoch": 2.005889281507656,
+      "grad_norm": 2.203125,
+      "learning_rate": 9.850642986799434e-05,
+      "loss": 4.1968,
+      "step": 647
+    },
+    {
+      "epoch": 2.0090302316450726,
+      "grad_norm": 2.234375,
+      "learning_rate": 9.825752490912576e-05,
+      "loss": 4.285,
+      "step": 648
+    },
+    {
+      "epoch": 2.012171181782489,
+      "grad_norm": 1.9453125,
+      "learning_rate": 9.800863074835828e-05,
+      "loss": 4.1361,
+      "step": 649
+    },
+    {
+      "epoch": 2.015312131919906,
+      "grad_norm": 2.171875,
+      "learning_rate": 9.77597489280866e-05,
+      "loss": 4.361,
+      "step": 650
+    },
+    {
+      "epoch": 2.0184530820573223,
+      "grad_norm": 2.3125,
+      "learning_rate": 9.751088099062891e-05,
+      "loss": 4.1571,
+      "step": 651
+    },
+    {
+      "epoch": 2.0215940321947388,
+      "grad_norm": 2.0625,
+      "learning_rate": 9.72620284782174e-05,
+      "loss": 4.2427,
+      "step": 652
+    },
+    {
+      "epoch": 2.0247349823321557,
+      "grad_norm": 1.9296875,
+      "learning_rate": 9.701319293298868e-05,
+      "loss": 4.1978,
+      "step": 653
+    },
+    {
+      "epoch": 2.027875932469572,
+      "grad_norm": 2.265625,
+      "learning_rate": 9.676437589697411e-05,
+      "loss": 4.4762,
+      "step": 654
+    },
+    {
+      "epoch": 2.0310168826069885,
+      "grad_norm": 2.84375,
+      "learning_rate": 9.651557891209053e-05,
+      "loss": 4.3248,
+      "step": 655
+    },
+    {
+      "epoch": 2.034157832744405,
+      "grad_norm": 2.5625,
+      "learning_rate": 9.626680352013039e-05,
+      "loss": 4.3244,
+      "step": 656
+    },
+    {
+      "epoch": 2.037298782881822,
+      "grad_norm": 2.0,
+      "learning_rate": 9.601805126275235e-05,
+      "loss": 4.2766,
+      "step": 657
+    },
+    {
+      "epoch": 2.0404397330192383,
+      "grad_norm": 2.15625,
+      "learning_rate": 9.57693236814717e-05,
+      "loss": 4.4017,
+      "step": 658
+    },
+    {
+      "epoch": 2.0435806831566548,
+      "grad_norm": 1.9296875,
+      "learning_rate": 9.552062231765083e-05,
+      "loss": 4.3644,
+      "step": 659
+    },
+    {
+      "epoch": 2.0467216332940716,
+      "grad_norm": 2.0625,
+      "learning_rate": 9.527194871248973e-05,
+      "loss": 4.2171,
+      "step": 660
+    },
+    {
+      "epoch": 2.049862583431488,
+      "grad_norm": 3.0,
+      "learning_rate": 9.502330440701625e-05,
+      "loss": 4.2684,
+      "step": 661
+    },
+    {
+      "epoch": 2.0530035335689045,
+      "grad_norm": 1.9609375,
+      "learning_rate": 9.477469094207672e-05,
+      "loss": 4.1105,
+      "step": 662
+    },
+    {
+      "epoch": 2.056144483706321,
+      "grad_norm": 2.65625,
+      "learning_rate": 9.452610985832636e-05,
+      "loss": 4.2526,
+      "step": 663
+    },
+    {
+      "epoch": 2.059285433843738,
+      "grad_norm": 2.015625,
+      "learning_rate": 9.427756269621968e-05,
+      "loss": 4.3674,
+      "step": 664
+    },
+    {
+      "epoch": 2.0624263839811543,
+      "grad_norm": 2.046875,
+      "learning_rate": 9.402905099600107e-05,
+      "loss": 4.306,
+      "step": 665
+    },
+    {
+      "epoch": 2.0655673341185707,
+      "grad_norm": 2.09375,
+      "learning_rate": 9.378057629769513e-05,
+      "loss": 4.2858,
+      "step": 666
+    },
+    {
+      "epoch": 2.0687082842559876,
+      "grad_norm": 2.03125,
+      "learning_rate": 9.353214014109706e-05,
+      "loss": 4.227,
+      "step": 667
+    },
+    {
+      "epoch": 2.071849234393404,
+      "grad_norm": 2.015625,
+      "learning_rate": 9.328374406576334e-05,
+      "loss": 4.1589,
+      "step": 668
+    },
+    {
+      "epoch": 2.0749901845308205,
+      "grad_norm": 2.09375,
+      "learning_rate": 9.3035389611002e-05,
+      "loss": 4.2266,
+      "step": 669
+    },
+    {
+      "epoch": 2.078131134668237,
+      "grad_norm": 1.9765625,
+      "learning_rate": 9.278707831586317e-05,
+      "loss": 4.3633,
+      "step": 670
+    },
+    {
+      "epoch": 2.081272084805654,
+      "grad_norm": 1.6640625,
+      "learning_rate": 9.253881171912955e-05,
+      "loss": 4.3313,
+      "step": 671
+    },
+    {
+      "epoch": 2.0844130349430703,
+      "grad_norm": 1.8828125,
+      "learning_rate": 9.22905913593068e-05,
+      "loss": 4.3141,
+      "step": 672
+    },
+    {
+      "epoch": 2.0875539850804867,
+      "grad_norm": 1.828125,
+      "learning_rate": 9.204241877461406e-05,
+      "loss": 4.1266,
+      "step": 673
+    },
+    {
+      "epoch": 2.0906949352179036,
+      "grad_norm": 1.7890625,
+      "learning_rate": 9.179429550297438e-05,
+      "loss": 4.2483,
+      "step": 674
+    },
+    {
+      "epoch": 2.09383588535532,
+      "grad_norm": 2.265625,
+      "learning_rate": 9.154622308200531e-05,
+      "loss": 4.1809,
+      "step": 675
+    },
+    {
+      "epoch": 2.0969768354927365,
+      "grad_norm": 2.15625,
+      "learning_rate": 9.129820304900919e-05,
+      "loss": 4.3192,
+      "step": 676
+    },
+    {
+      "epoch": 2.100117785630153,
+      "grad_norm": 1.921875,
+      "learning_rate": 9.105023694096373e-05,
+      "loss": 4.2533,
+      "step": 677
+    },
+    {
+      "epoch": 2.10325873576757,
+      "grad_norm": 2.21875,
+      "learning_rate": 9.080232629451243e-05,
+      "loss": 4.2377,
+      "step": 678
+    },
+    {
+      "epoch": 2.1063996859049863,
+      "grad_norm": 2.03125,
+      "learning_rate": 9.055447264595528e-05,
+      "loss": 4.2997,
+      "step": 679
+    },
+    {
+      "epoch": 2.1095406360424027,
+      "grad_norm": 2.4375,
+      "learning_rate": 9.030667753123882e-05,
+      "loss": 4.2221,
+      "step": 680
+    },
+    {
+      "epoch": 2.1126815861798196,
+      "grad_norm": 2.453125,
+      "learning_rate": 9.005894248594698e-05,
+      "loss": 4.3907,
+      "step": 681
+    },
+    {
+      "epoch": 2.115822536317236,
+      "grad_norm": 2.640625,
+      "learning_rate": 8.981126904529139e-05,
+      "loss": 4.2554,
+      "step": 682
+    },
+    {
+      "epoch": 2.1189634864546525,
+      "grad_norm": 2.515625,
+      "learning_rate": 8.956365874410193e-05,
+      "loss": 4.2262,
+      "step": 683
+    },
+    {
+      "epoch": 2.122104436592069,
+      "grad_norm": 2.171875,
+      "learning_rate": 8.931611311681729e-05,
+      "loss": 4.2418,
+      "step": 684
+    },
+    {
+      "epoch": 2.125245386729486,
+      "grad_norm": 2.15625,
+      "learning_rate": 8.906863369747525e-05,
+      "loss": 4.2695,
+      "step": 685
+    },
+    {
+      "epoch": 2.1283863368669023,
+      "grad_norm": 1.875,
+      "learning_rate": 8.882122201970337e-05,
+      "loss": 4.1303,
+      "step": 686
+    },
+    {
+      "epoch": 2.1315272870043187,
+      "grad_norm": 2.1875,
+      "learning_rate": 8.857387961670939e-05,
+      "loss": 4.2731,
+      "step": 687
+    },
+    {
+      "epoch": 2.134668237141735,
+      "grad_norm": 2.328125,
+      "learning_rate": 8.832660802127175e-05,
+      "loss": 4.3843,
+      "step": 688
+    },
+    {
+      "epoch": 2.137809187279152,
+      "grad_norm": 2.046875,
+      "learning_rate": 8.807940876573012e-05,
+      "loss": 4.308,
+      "step": 689
+    },
+    {
+      "epoch": 2.1409501374165685,
+      "grad_norm": 1.953125,
+      "learning_rate": 8.78322833819759e-05,
+      "loss": 4.4037,
+      "step": 690
+    },
+    {
+      "epoch": 2.144091087553985,
+      "grad_norm": 2.25,
+      "learning_rate": 8.758523340144267e-05,
+      "loss": 4.4365,
+      "step": 691
+    },
+    {
+      "epoch": 2.147232037691402,
+      "grad_norm": 1.984375,
+      "learning_rate": 8.733826035509672e-05,
+      "loss": 4.2736,
+      "step": 692
+    },
+    {
+      "epoch": 2.1503729878288182,
+      "grad_norm": 2.21875,
+      "learning_rate": 8.709136577342758e-05,
+      "loss": 4.2869,
+      "step": 693
+    },
+    {
+      "epoch": 2.1535139379662347,
+      "grad_norm": 2.21875,
+      "learning_rate": 8.684455118643864e-05,
+      "loss": 4.3343,
+      "step": 694
+    },
+    {
+      "epoch": 2.1566548881036516,
+      "grad_norm": 2.03125,
+      "learning_rate": 8.659781812363742e-05,
+      "loss": 4.3024,
+      "step": 695
+    },
+    {
+      "epoch": 2.159795838241068,
+      "grad_norm": 1.984375,
+      "learning_rate": 8.635116811402632e-05,
+      "loss": 4.2528,
+      "step": 696
+    },
+    {
+      "epoch": 2.1629367883784845,
+      "grad_norm": 1.828125,
+      "learning_rate": 8.610460268609305e-05,
+      "loss": 4.27,
+      "step": 697
+    },
+    {
+      "epoch": 2.166077738515901,
+      "grad_norm": 2.078125,
+      "learning_rate": 8.58581233678011e-05,
+      "loss": 4.2737,
+      "step": 698
+    },
+    {
+      "epoch": 2.169218688653318,
+      "grad_norm": 2.609375,
+      "learning_rate": 8.561173168658048e-05,
+      "loss": 4.2491,
+      "step": 699
+    },
+    {
+      "epoch": 2.1723596387907342,
+      "grad_norm": 2.375,
+      "learning_rate": 8.5365429169318e-05,
+      "loss": 4.2828,
+      "step": 700
+    },
+    {
+      "epoch": 2.1755005889281507,
+      "grad_norm": 3.171875,
+      "learning_rate": 8.511921734234793e-05,
+      "loss": 4.3355,
+      "step": 701
+    },
+    {
+      "epoch": 2.178641539065567,
+      "grad_norm": 1.6953125,
+      "learning_rate": 8.487309773144258e-05,
+      "loss": 4.3533,
+      "step": 702
+    },
+    {
+      "epoch": 2.181782489202984,
+      "grad_norm": 1.640625,
+      "learning_rate": 8.462707186180272e-05,
+      "loss": 4.4551,
+      "step": 703
+    },
+    {
+      "epoch": 2.1849234393404005,
+      "grad_norm": 2.390625,
+      "learning_rate": 8.438114125804834e-05,
+      "loss": 4.3297,
+      "step": 704
+    },
+    {
+      "epoch": 2.188064389477817,
+      "grad_norm": 2.125,
+      "learning_rate": 8.413530744420896e-05,
+      "loss": 4.2718,
+      "step": 705
+    },
+    {
+      "epoch": 2.191205339615234,
+      "grad_norm": 2.1875,
+      "learning_rate": 8.388957194371432e-05,
+      "loss": 4.3321,
+      "step": 706
+    },
+    {
+      "epoch": 2.1943462897526502,
+      "grad_norm": 1.9296875,
+      "learning_rate": 8.36439362793849e-05,
+      "loss": 4.3013,
+      "step": 707
+    },
+    {
+      "epoch": 2.1974872398900667,
+      "grad_norm": 1.5390625,
+      "learning_rate": 8.339840197342247e-05,
+      "loss": 4.2745,
+      "step": 708
+    },
+    {
+      "epoch": 2.200628190027483,
+      "grad_norm": 1.6328125,
+      "learning_rate": 8.315297054740085e-05,
+      "loss": 4.1138,
+      "step": 709
+    },
+    {
+      "epoch": 2.2037691401649,
+      "grad_norm": 2.078125,
+      "learning_rate": 8.290764352225608e-05,
+      "loss": 4.3779,
+      "step": 710
+    },
+    {
+      "epoch": 2.2069100903023164,
+      "grad_norm": 2.1875,
+      "learning_rate": 8.26624224182774e-05,
+      "loss": 4.298,
+      "step": 711
+    },
+    {
+      "epoch": 2.210051040439733,
+      "grad_norm": 2.1875,
+      "learning_rate": 8.241730875509755e-05,
+      "loss": 4.3853,
+      "step": 712
+    },
+    {
+      "epoch": 2.2131919905771498,
+      "grad_norm": 1.6015625,
+      "learning_rate": 8.21723040516835e-05,
+      "loss": 4.1998,
+      "step": 713
+    },
+    {
+      "epoch": 2.216332940714566,
+      "grad_norm": 1.875,
+      "learning_rate": 8.192740982632705e-05,
+      "loss": 4.4158,
+      "step": 714
+    },
+    {
+      "epoch": 2.2194738908519827,
+      "grad_norm": 2.140625,
+      "learning_rate": 8.16826275966353e-05,
+      "loss": 4.3935,
+      "step": 715
+    },
+    {
+      "epoch": 2.222614840989399,
+      "grad_norm": 1.6953125,
+      "learning_rate": 8.143795887952133e-05,
+      "loss": 4.1111,
+      "step": 716
+    },
+    {
+      "epoch": 2.225755791126816,
+      "grad_norm": 1.859375,
+      "learning_rate": 8.119340519119479e-05,
+      "loss": 4.1346,
+      "step": 717
+    },
+    {
+      "epoch": 2.2288967412642324,
+      "grad_norm": 1.9140625,
+      "learning_rate": 8.094896804715245e-05,
+      "loss": 4.2575,
+      "step": 718
+    },
+    {
+      "epoch": 2.232037691401649,
+      "grad_norm": 1.7421875,
+      "learning_rate": 8.070464896216899e-05,
+      "loss": 4.3729,
+      "step": 719
+    },
+    {
+      "epoch": 2.2351786415390658,
+      "grad_norm": 1.75,
+      "learning_rate": 8.046044945028736e-05,
+      "loss": 4.2352,
+      "step": 720
+    },
+    {
+      "epoch": 2.2351786415390658,
+      "eval_loss": 4.368430137634277,
+      "eval_runtime": 66.9111,
+      "eval_samples_per_second": 38.873,
+      "eval_steps_per_second": 38.873,
+      "step": 720
+    },
+    {
+      "epoch": 2.238319591676482,
+      "grad_norm": 1.8828125,
+      "learning_rate": 8.021637102480953e-05,
+      "loss": 4.262,
+      "step": 721
+    },
+    {
+      "epoch": 2.2414605418138986,
+      "grad_norm": 2.046875,
+      "learning_rate": 7.997241519828713e-05,
+      "loss": 4.2986,
+      "step": 722
+    },
+    {
+      "epoch": 2.244601491951315,
+      "grad_norm": 1.796875,
+      "learning_rate": 7.9728583482512e-05,
+      "loss": 4.2811,
+      "step": 723
+    },
+    {
+      "epoch": 2.247742442088732,
+      "grad_norm": 2.328125,
+      "learning_rate": 7.948487738850697e-05,
+      "loss": 4.1563,
+      "step": 724
+    },
+    {
+      "epoch": 2.2508833922261484,
+      "grad_norm": 2.078125,
+      "learning_rate": 7.924129842651628e-05,
+      "loss": 4.3348,
+      "step": 725
+    },
+    {
+      "epoch": 2.254024342363565,
+      "grad_norm": 1.890625,
+      "learning_rate": 7.899784810599639e-05,
+      "loss": 4.1989,
+      "step": 726
+    },
+    {
+      "epoch": 2.2571652925009813,
+      "grad_norm": 2.09375,
+      "learning_rate": 7.875452793560654e-05,
+      "loss": 4.344,
+      "step": 727
+    },
+    {
+      "epoch": 2.260306242638398,
+      "grad_norm": 2.3125,
+      "learning_rate": 7.851133942319942e-05,
+      "loss": 4.3269,
+      "step": 728
+    },
+    {
+      "epoch": 2.2634471927758146,
+      "grad_norm": 2.109375,
+      "learning_rate": 7.826828407581194e-05,
+      "loss": 4.1932,
+      "step": 729
+    },
+    {
+      "epoch": 2.266588142913231,
+      "grad_norm": 2.046875,
+      "learning_rate": 7.802536339965568e-05,
+      "loss": 4.2621,
+      "step": 730
+    },
+    {
+      "epoch": 2.269729093050648,
+      "grad_norm": 2.1875,
+      "learning_rate": 7.778257890010768e-05,
+      "loss": 4.4467,
+      "step": 731
+    },
+    {
+      "epoch": 2.2728700431880644,
+      "grad_norm": 1.6484375,
+      "learning_rate": 7.753993208170113e-05,
+      "loss": 4.2279,
+      "step": 732
+    },
+    {
+      "epoch": 2.276010993325481,
+      "grad_norm": 1.9140625,
+      "learning_rate": 7.729742444811597e-05,
+      "loss": 4.2004,
+      "step": 733
+    },
+    {
+      "epoch": 2.2791519434628977,
+      "grad_norm": 2.09375,
+      "learning_rate": 7.705505750216965e-05,
+      "loss": 4.3484,
+      "step": 734
+    },
+    {
+      "epoch": 2.282292893600314,
+      "grad_norm": 2.390625,
+      "learning_rate": 7.681283274580779e-05,
+      "loss": 4.3906,
+      "step": 735
+    },
+    {
+      "epoch": 2.2854338437377306,
+      "grad_norm": 1.65625,
+      "learning_rate": 7.657075168009479e-05,
+      "loss": 4.2392,
+      "step": 736
+    },
+    {
+      "epoch": 2.288574793875147,
+      "grad_norm": 1.96875,
+      "learning_rate": 7.632881580520467e-05,
+      "loss": 4.1595,
+      "step": 737
+    },
+    {
+      "epoch": 2.291715744012564,
+      "grad_norm": 2.125,
+      "learning_rate": 7.608702662041168e-05,
+      "loss": 4.2336,
+      "step": 738
+    },
+    {
+      "epoch": 2.2948566941499804,
+      "grad_norm": 2.109375,
+      "learning_rate": 7.584538562408105e-05,
+      "loss": 4.2204,
+      "step": 739
+    },
+    {
+      "epoch": 2.297997644287397,
+      "grad_norm": 2.203125,
+      "learning_rate": 7.560389431365967e-05,
+      "loss": 4.4889,
+      "step": 740
+    },
+    {
+      "epoch": 2.3011385944248133,
+      "grad_norm": 2.53125,
+      "learning_rate": 7.536255418566681e-05,
+      "loss": 4.2681,
+      "step": 741
+    },
+    {
+      "epoch": 2.30427954456223,
+      "grad_norm": 1.859375,
+      "learning_rate": 7.512136673568491e-05,
+      "loss": 4.1897,
+      "step": 742
+    },
+    {
+      "epoch": 2.3074204946996466,
+      "grad_norm": 1.9609375,
+      "learning_rate": 7.488033345835018e-05,
+      "loss": 4.2459,
+      "step": 743
+    },
+    {
+      "epoch": 2.310561444837063,
+      "grad_norm": 2.3125,
+      "learning_rate": 7.463945584734357e-05,
+      "loss": 4.4619,
+      "step": 744
+    },
+    {
+      "epoch": 2.31370239497448,
+      "grad_norm": 2.53125,
+      "learning_rate": 7.439873539538127e-05,
+      "loss": 4.3354,
+      "step": 745
+    },
+    {
+      "epoch": 2.3168433451118964,
+      "grad_norm": 1.8359375,
+      "learning_rate": 7.415817359420552e-05,
+      "loss": 4.1739,
+      "step": 746
+    },
+    {
+      "epoch": 2.319984295249313,
+      "grad_norm": 2.15625,
+      "learning_rate": 7.391777193457544e-05,
+      "loss": 4.2746,
+      "step": 747
+    },
+    {
+      "epoch": 2.3231252453867297,
+      "grad_norm": 2.109375,
+      "learning_rate": 7.367753190625783e-05,
+      "loss": 4.2197,
+      "step": 748
+    },
+    {
+      "epoch": 2.326266195524146,
+      "grad_norm": 2.140625,
+      "learning_rate": 7.343745499801779e-05,
+      "loss": 4.3747,
+      "step": 749
+    },
+    {
+      "epoch": 2.3294071456615626,
+      "grad_norm": 1.90625,
+      "learning_rate": 7.319754269760953e-05,
+      "loss": 4.3387,
+      "step": 750
+    },
+    {
+      "epoch": 2.332548095798979,
+      "grad_norm": 2.234375,
+      "learning_rate": 7.295779649176726e-05,
+      "loss": 4.2909,
+      "step": 751
+    },
+    {
+      "epoch": 2.335689045936396,
+      "grad_norm": 2.265625,
+      "learning_rate": 7.271821786619585e-05,
+      "loss": 4.429,
+      "step": 752
+    },
+    {
+      "epoch": 2.3388299960738124,
+      "grad_norm": 1.5703125,
+      "learning_rate": 7.247880830556173e-05,
+      "loss": 4.0681,
+      "step": 753
+    },
+    {
+      "epoch": 2.341970946211229,
+      "grad_norm": 1.7265625,
+      "learning_rate": 7.223956929348361e-05,
+      "loss": 4.2349,
+      "step": 754
+    },
+    {
+      "epoch": 2.3451118963486453,
+      "grad_norm": 1.8671875,
+      "learning_rate": 7.200050231252328e-05,
+      "loss": 4.1376,
+      "step": 755
+    },
+    {
+      "epoch": 2.348252846486062,
+      "grad_norm": 1.6640625,
+      "learning_rate": 7.176160884417651e-05,
+      "loss": 4.3727,
+      "step": 756
+    },
+    {
+      "epoch": 2.3513937966234786,
+      "grad_norm": 1.890625,
+      "learning_rate": 7.152289036886373e-05,
+      "loss": 4.1016,
+      "step": 757
+    },
+    {
+      "epoch": 2.354534746760895,
+      "grad_norm": 1.8203125,
+      "learning_rate": 7.12843483659211e-05,
+      "loss": 4.3524,
+      "step": 758
+    },
+    {
+      "epoch": 2.357675696898312,
+      "grad_norm": 1.8984375,
+      "learning_rate": 7.104598431359102e-05,
+      "loss": 4.2188,
+      "step": 759
+    },
+    {
+      "epoch": 2.3608166470357284,
+      "grad_norm": 1.7265625,
+      "learning_rate": 7.080779968901323e-05,
+      "loss": 4.2958,
+      "step": 760
+    },
+    {
+      "epoch": 2.363957597173145,
+      "grad_norm": 1.65625,
+      "learning_rate": 7.056979596821547e-05,
+      "loss": 3.9343,
+      "step": 761
+    },
+    {
+      "epoch": 2.3670985473105617,
+      "grad_norm": 1.7421875,
+      "learning_rate": 7.033197462610445e-05,
+      "loss": 4.3702,
+      "step": 762
+    },
+    {
+      "epoch": 2.370239497447978,
+      "grad_norm": 1.90625,
+      "learning_rate": 7.009433713645678e-05,
+      "loss": 4.1558,
+      "step": 763
+    },
+    {
+      "epoch": 2.3733804475853946,
+      "grad_norm": 1.7421875,
+      "learning_rate": 6.985688497190965e-05,
+      "loss": 4.3592,
+      "step": 764
+    },
+    {
+      "epoch": 2.376521397722811,
+      "grad_norm": 2.015625,
+      "learning_rate": 6.961961960395178e-05,
+      "loss": 4.1897,
+      "step": 765
+    },
+    {
+      "epoch": 2.379662347860228,
+      "grad_norm": 2.125,
+      "learning_rate": 6.938254250291434e-05,
+      "loss": 4.291,
+      "step": 766
+    },
+    {
+      "epoch": 2.3828032979976443,
+      "grad_norm": 1.8203125,
+      "learning_rate": 6.914565513796176e-05,
+      "loss": 4.2769,
+      "step": 767
+    },
+    {
+      "epoch": 2.385944248135061,
+      "grad_norm": 2.234375,
+      "learning_rate": 6.890895897708283e-05,
+      "loss": 4.299,
+      "step": 768
+    },
+    {
+      "epoch": 2.3890851982724772,
+      "grad_norm": 1.953125,
+      "learning_rate": 6.867245548708128e-05,
+      "loss": 4.0077,
+      "step": 769
+    },
+    {
+      "epoch": 2.392226148409894,
+      "grad_norm": 1.9375,
+      "learning_rate": 6.843614613356692e-05,
+      "loss": 4.2269,
+      "step": 770
+    },
+    {
+      "epoch": 2.3953670985473106,
+      "grad_norm": 1.6015625,
+      "learning_rate": 6.820003238094655e-05,
+      "loss": 4.3402,
+      "step": 771
+    },
+    {
+      "epoch": 2.398508048684727,
+      "grad_norm": 1.8359375,
+      "learning_rate": 6.79641156924147e-05,
+      "loss": 4.3385,
+      "step": 772
+    },
+    {
+      "epoch": 2.401648998822144,
+      "grad_norm": 2.0,
+      "learning_rate": 6.772839752994489e-05,
+      "loss": 4.3749,
+      "step": 773
+    },
+    {
+      "epoch": 2.4047899489595603,
+      "grad_norm": 1.671875,
+      "learning_rate": 6.749287935428021e-05,
+      "loss": 4.2411,
+      "step": 774
+    },
+    {
+      "epoch": 2.4079308990969768,
+      "grad_norm": 2.125,
+      "learning_rate": 6.725756262492451e-05,
+      "loss": 4.1713,
+      "step": 775
+    },
+    {
+      "epoch": 2.411071849234393,
+      "grad_norm": 1.875,
+      "learning_rate": 6.702244880013322e-05,
+      "loss": 4.3452,
+      "step": 776
+    },
+    {
+      "epoch": 2.41421279937181,
+      "grad_norm": 1.796875,
+      "learning_rate": 6.678753933690447e-05,
+      "loss": 4.3592,
+      "step": 777
+    },
+    {
+      "epoch": 2.4173537495092265,
+      "grad_norm": 2.390625,
+      "learning_rate": 6.65528356909699e-05,
+      "loss": 4.331,
+      "step": 778
+    },
+    {
+      "epoch": 2.420494699646643,
+      "grad_norm": 1.8984375,
+      "learning_rate": 6.63183393167857e-05,
+      "loss": 4.307,
+      "step": 779
+    },
+    {
+      "epoch": 2.4236356497840594,
+      "grad_norm": 1.7890625,
+      "learning_rate": 6.608405166752361e-05,
+      "loss": 4.2504,
+      "step": 780
+    },
+    {
+      "epoch": 2.4267765999214763,
+      "grad_norm": 2.03125,
+      "learning_rate": 6.584997419506189e-05,
+      "loss": 4.0051,
+      "step": 781
+    },
+    {
+      "epoch": 2.4299175500588928,
+      "grad_norm": 1.6640625,
+      "learning_rate": 6.561610834997632e-05,
+      "loss": 4.2427,
+      "step": 782
+    },
+    {
+      "epoch": 2.433058500196309,
+      "grad_norm": 1.8671875,
+      "learning_rate": 6.538245558153135e-05,
+      "loss": 4.1035,
+      "step": 783
+    },
+    {
+      "epoch": 2.436199450333726,
+      "grad_norm": 1.984375,
+      "learning_rate": 6.514901733767085e-05,
+      "loss": 4.2743,
+      "step": 784
+    },
+    {
+      "epoch": 2.4393404004711425,
+      "grad_norm": 1.9765625,
+      "learning_rate": 6.491579506500932e-05,
+      "loss": 4.3169,
+      "step": 785
+    },
+    {
+      "epoch": 2.442481350608559,
+      "grad_norm": 1.96875,
+      "learning_rate": 6.468279020882292e-05,
+      "loss": 4.3702,
+      "step": 786
+    },
+    {
+      "epoch": 2.445622300745976,
+      "grad_norm": 2.015625,
+      "learning_rate": 6.445000421304045e-05,
+      "loss": 4.3215,
+      "step": 787
+    },
+    {
+      "epoch": 2.4487632508833923,
+      "grad_norm": 1.7265625,
+      "learning_rate": 6.42174385202345e-05,
+      "loss": 4.2976,
+      "step": 788
+    },
+    {
+      "epoch": 2.4519042010208087,
+      "grad_norm": 1.6640625,
+      "learning_rate": 6.398509457161235e-05,
+      "loss": 4.0694,
+      "step": 789
+    },
+    {
+      "epoch": 2.455045151158225,
+      "grad_norm": 1.9609375,
+      "learning_rate": 6.37529738070072e-05,
+      "loss": 4.3572,
+      "step": 790
+    },
+    {
+      "epoch": 2.458186101295642,
+      "grad_norm": 1.8046875,
+      "learning_rate": 6.352107766486916e-05,
+      "loss": 4.2869,
+      "step": 791
+    },
+    {
+      "epoch": 2.4613270514330585,
+      "grad_norm": 1.7421875,
+      "learning_rate": 6.328940758225633e-05,
+      "loss": 4.1413,
+      "step": 792
+    },
+    {
+      "epoch": 2.464468001570475,
+      "grad_norm": 2.0,
+      "learning_rate": 6.305796499482597e-05,
+      "loss": 4.2239,
+      "step": 793
+    },
+    {
+      "epoch": 2.4676089517078914,
+      "grad_norm": 1.953125,
+      "learning_rate": 6.282675133682554e-05,
+      "loss": 4.249,
+      "step": 794
+    },
+    {
+      "epoch": 2.4707499018453083,
+      "grad_norm": 3.734375,
+      "learning_rate": 6.259576804108378e-05,
+      "loss": 4.1008,
+      "step": 795
+    },
+    {
+      "epoch": 2.4738908519827247,
+      "grad_norm": 1.53125,
+      "learning_rate": 6.236501653900197e-05,
+      "loss": 4.3174,
+      "step": 796
+    },
+    {
+      "epoch": 2.477031802120141,
+      "grad_norm": 2.15625,
+      "learning_rate": 6.21344982605449e-05,
+      "loss": 4.4646,
+      "step": 797
+    },
+    {
+      "epoch": 2.480172752257558,
+      "grad_norm": 2.390625,
+      "learning_rate": 6.190421463423205e-05,
+      "loss": 3.9088,
+      "step": 798
+    },
+    {
+      "epoch": 2.4833137023949745,
+      "grad_norm": 2.234375,
+      "learning_rate": 6.167416708712885e-05,
+      "loss": 4.2834,
+      "step": 799
+    },
+    {
+      "epoch": 2.486454652532391,
+      "grad_norm": 1.609375,
+      "learning_rate": 6.144435704483768e-05,
+      "loss": 4.2141,
+      "step": 800
+    },
+    {
+      "epoch": 2.486454652532391,
+      "eval_loss": 4.3505330085754395,
+      "eval_runtime": 66.8349,
+      "eval_samples_per_second": 38.917,
+      "eval_steps_per_second": 38.917,
+      "step": 800
+    },
+    {
+      "epoch": 2.489595602669808,
+      "grad_norm": 2.0625,
+      "learning_rate": 6.121478593148913e-05,
+      "loss": 4.1911,
+      "step": 801
+    },
+    {
+      "epoch": 2.4927365528072243,
+      "grad_norm": 1.8515625,
+      "learning_rate": 6.098545516973311e-05,
+      "loss": 4.2056,
+      "step": 802
+    },
+    {
+      "epoch": 2.4958775029446407,
+      "grad_norm": 1.65625,
+      "learning_rate": 6.075636618073017e-05,
+      "loss": 4.3309,
+      "step": 803
+    },
+    {
+      "epoch": 2.499018453082057,
+      "grad_norm": 1.75,
+      "learning_rate": 6.052752038414252e-05,
+      "loss": 3.9931,
+      "step": 804
+    },
+    {
+      "epoch": 2.502159403219474,
+      "grad_norm": 1.71875,
+      "learning_rate": 6.0298919198125314e-05,
+      "loss": 4.1427,
+      "step": 805
+    },
+    {
+      "epoch": 2.5053003533568905,
+      "grad_norm": 2.125,
+      "learning_rate": 6.0070564039317855e-05,
+      "loss": 4.3228,
+      "step": 806
+    },
+    {
+      "epoch": 2.508441303494307,
+      "grad_norm": 1.828125,
+      "learning_rate": 5.9842456322834805e-05,
+      "loss": 4.3154,
+      "step": 807
+    },
+    {
+      "epoch": 2.5115822536317234,
+      "grad_norm": 1.984375,
+      "learning_rate": 5.961459746225755e-05,
+      "loss": 4.3673,
+      "step": 808
+    },
+    {
+      "epoch": 2.5147232037691403,
+      "grad_norm": 1.7890625,
+      "learning_rate": 5.938698886962515e-05,
+      "loss": 4.2185,
+      "step": 809
+    },
+    {
+      "epoch": 2.5178641539065567,
+      "grad_norm": 1.7421875,
+      "learning_rate": 5.915963195542584e-05,
+      "loss": 4.1671,
+      "step": 810
+    },
+    {
+      "epoch": 2.521005104043973,
+      "grad_norm": 1.75,
+      "learning_rate": 5.89325281285882e-05,
+      "loss": 4.149,
+      "step": 811
+    },
+    {
+      "epoch": 2.52414605418139,
+      "grad_norm": 1.640625,
+      "learning_rate": 5.870567879647242e-05,
+      "loss": 3.9312,
+      "step": 812
+    },
+    {
+      "epoch": 2.5272870043188065,
+      "grad_norm": 1.8515625,
+      "learning_rate": 5.8479085364861596e-05,
+      "loss": 4.3125,
+      "step": 813
+    },
+    {
+      "epoch": 2.530427954456223,
+      "grad_norm": 2.03125,
+      "learning_rate": 5.8252749237953055e-05,
+      "loss": 4.1334,
+      "step": 814
+    },
+    {
+      "epoch": 2.53356890459364,
+      "grad_norm": 2.078125,
+      "learning_rate": 5.802667181834946e-05,
+      "loss": 4.2653,
+      "step": 815
+    },
+    {
+      "epoch": 2.5367098547310563,
+      "grad_norm": 2.1875,
+      "learning_rate": 5.7800854507050495e-05,
+      "loss": 4.2555,
+      "step": 816
+    },
+    {
+      "epoch": 2.5398508048684727,
+      "grad_norm": 2.078125,
+      "learning_rate": 5.757529870344367e-05,
+      "loss": 4.2792,
+      "step": 817
+    },
+    {
+      "epoch": 2.542991755005889,
+      "grad_norm": 1.703125,
+      "learning_rate": 5.735000580529629e-05,
+      "loss": 4.2288,
+      "step": 818
+    },
+    {
+      "epoch": 2.5461327051433056,
+      "grad_norm": 2.078125,
+      "learning_rate": 5.71249772087461e-05,
+      "loss": 4.1832,
+      "step": 819
+    },
+    {
+      "epoch": 2.5492736552807225,
+      "grad_norm": 1.9140625,
+      "learning_rate": 5.690021430829321e-05,
+      "loss": 4.1672,
+      "step": 820
+    },
+    {
+      "epoch": 2.552414605418139,
+      "grad_norm": 1.9921875,
+      "learning_rate": 5.667571849679103e-05,
+      "loss": 4.0232,
+      "step": 821
+    },
+    {
+      "epoch": 2.5555555555555554,
+      "grad_norm": 2.046875,
+      "learning_rate": 5.645149116543793e-05,
+      "loss": 4.3391,
+      "step": 822
+    },
+    {
+      "epoch": 2.5586965056929722,
+      "grad_norm": 1.5703125,
+      "learning_rate": 5.622753370376852e-05,
+      "loss": 4.26,
+      "step": 823
+    },
+    {
+      "epoch": 2.5618374558303887,
+      "grad_norm": 1.921875,
+      "learning_rate": 5.6003847499645046e-05,
+      "loss": 4.2943,
+      "step": 824
+    },
+    {
+      "epoch": 2.564978405967805,
+      "grad_norm": 1.8828125,
+      "learning_rate": 5.5780433939248613e-05,
+      "loss": 4.1184,
+      "step": 825
+    },
+    {
+      "epoch": 2.568119356105222,
+      "grad_norm": 1.890625,
+      "learning_rate": 5.555729440707095e-05,
+      "loss": 4.156,
+      "step": 826
+    },
+    {
+      "epoch": 2.5712603062426385,
+      "grad_norm": 1.7265625,
+      "learning_rate": 5.533443028590557e-05,
+      "loss": 4.268,
+      "step": 827
+    },
+    {
+      "epoch": 2.574401256380055,
+      "grad_norm": 2.015625,
+      "learning_rate": 5.51118429568392e-05,
+      "loss": 4.284,
+      "step": 828
+    },
+    {
+      "epoch": 2.577542206517472,
+      "grad_norm": 1.515625,
+      "learning_rate": 5.4889533799243396e-05,
+      "loss": 4.0322,
+      "step": 829
+    },
+    {
+      "epoch": 2.5806831566548882,
+      "grad_norm": 2.078125,
+      "learning_rate": 5.466750419076576e-05,
+      "loss": 4.3292,
+      "step": 830
+    },
+    {
+      "epoch": 2.5838241067923047,
+      "grad_norm": 2.046875,
+      "learning_rate": 5.444575550732166e-05,
+      "loss": 4.1284,
+      "step": 831
+    },
+    {
+      "epoch": 2.586965056929721,
+      "grad_norm": 3.265625,
+      "learning_rate": 5.4224289123085514e-05,
+      "loss": 4.4996,
+      "step": 832
+    },
+    {
+      "epoch": 2.5901060070671376,
+      "grad_norm": 2.109375,
+      "learning_rate": 5.4003106410482386e-05,
+      "loss": 4.2499,
+      "step": 833
+    },
+    {
+      "epoch": 2.5932469572045544,
+      "grad_norm": 2.09375,
+      "learning_rate": 5.3782208740179284e-05,
+      "loss": 4.2648,
+      "step": 834
+    },
+    {
+      "epoch": 2.596387907341971,
+      "grad_norm": 1.6640625,
+      "learning_rate": 5.356159748107702e-05,
+      "loss": 4.0824,
+      "step": 835
+    },
+    {
+      "epoch": 2.5995288574793873,
+      "grad_norm": 2.28125,
+      "learning_rate": 5.3341274000301265e-05,
+      "loss": 4.2673,
+      "step": 836
+    },
+    {
+      "epoch": 2.602669807616804,
+      "grad_norm": 2.0,
+      "learning_rate": 5.312123966319467e-05,
+      "loss": 4.2493,
+      "step": 837
+    },
+    {
+      "epoch": 2.6058107577542207,
+      "grad_norm": 2.25,
+      "learning_rate": 5.2901495833307715e-05,
+      "loss": 4.2621,
+      "step": 838
+    },
+    {
+      "epoch": 2.608951707891637,
+      "grad_norm": 2.46875,
+      "learning_rate": 5.268204387239086e-05,
+      "loss": 4.1931,
+      "step": 839
+    },
+    {
+      "epoch": 2.612092658029054,
+      "grad_norm": 2.3125,
+      "learning_rate": 5.246288514038569e-05,
+      "loss": 4.3081,
+      "step": 840
+    },
+    {
+      "epoch": 2.6152336081664704,
+      "grad_norm": 1.6953125,
+      "learning_rate": 5.2244020995416766e-05,
+      "loss": 3.8379,
+      "step": 841
+    },
+    {
+      "epoch": 2.618374558303887,
+      "grad_norm": 2.3125,
+      "learning_rate": 5.2025452793783036e-05,
+      "loss": 4.2765,
+      "step": 842
+    },
+    {
+      "epoch": 2.6215155084413038,
+      "grad_norm": 2.171875,
+      "learning_rate": 5.1807181889949575e-05,
+      "loss": 4.1614,
+      "step": 843
+    },
+    {
+      "epoch": 2.62465645857872,
+      "grad_norm": 1.8046875,
+      "learning_rate": 5.158920963653894e-05,
+      "loss": 4.2581,
+      "step": 844
+    },
+    {
+      "epoch": 2.6277974087161367,
+      "grad_norm": 1.7109375,
+      "learning_rate": 5.137153738432314e-05,
+      "loss": 4.4073,
+      "step": 845
+    },
+    {
+      "epoch": 2.630938358853553,
+      "grad_norm": 2.09375,
+      "learning_rate": 5.115416648221494e-05,
+      "loss": 4.2157,
+      "step": 846
+    },
+    {
+      "epoch": 2.6340793089909695,
+      "grad_norm": 2.21875,
+      "learning_rate": 5.09370982772597e-05,
+      "loss": 4.4356,
+      "step": 847
+    },
+    {
+      "epoch": 2.6372202591283864,
+      "grad_norm": 1.7890625,
+      "learning_rate": 5.072033411462702e-05,
+      "loss": 4.3641,
+      "step": 848
+    },
+    {
+      "epoch": 2.640361209265803,
+      "grad_norm": 1.9765625,
+      "learning_rate": 5.0503875337602214e-05,
+      "loss": 4.2766,
+      "step": 849
+    },
+    {
+      "epoch": 2.6435021594032193,
+      "grad_norm": 1.671875,
+      "learning_rate": 5.02877232875783e-05,
+      "loss": 4.0995,
+      "step": 850
+    },
+    {
+      "epoch": 2.646643109540636,
+      "grad_norm": 2.140625,
+      "learning_rate": 5.007187930404729e-05,
+      "loss": 4.2446,
+      "step": 851
+    },
+    {
+      "epoch": 2.6497840596780526,
+      "grad_norm": 2.046875,
+      "learning_rate": 4.985634472459241e-05,
+      "loss": 4.1347,
+      "step": 852
+    },
+    {
+      "epoch": 2.652925009815469,
+      "grad_norm": 1.953125,
+      "learning_rate": 4.96411208848792e-05,
+      "loss": 4.3555,
+      "step": 853
+    },
+    {
+      "epoch": 2.656065959952886,
+      "grad_norm": 2.265625,
+      "learning_rate": 4.942620911864779e-05,
+      "loss": 4.0435,
+      "step": 854
+    },
+    {
+      "epoch": 2.6592069100903024,
+      "grad_norm": 1.703125,
+      "learning_rate": 4.921161075770422e-05,
+      "loss": 4.3314,
+      "step": 855
+    },
+    {
+      "epoch": 2.662347860227719,
+      "grad_norm": 1.6953125,
+      "learning_rate": 4.8997327131912466e-05,
+      "loss": 4.1421,
+      "step": 856
+    },
+    {
+      "epoch": 2.6654888103651353,
+      "grad_norm": 2.0625,
+      "learning_rate": 4.878335956918606e-05,
+      "loss": 4.3009,
+      "step": 857
+    },
+    {
+      "epoch": 2.668629760502552,
+      "grad_norm": 1.8046875,
+      "learning_rate": 4.856970939547994e-05,
+      "loss": 4.2407,
+      "step": 858
+    },
+    {
+      "epoch": 2.6717707106399686,
+      "grad_norm": 1.765625,
+      "learning_rate": 4.835637793478207e-05,
+      "loss": 4.2586,
+      "step": 859
+    },
+    {
+      "epoch": 2.674911660777385,
+      "grad_norm": 1.734375,
+      "learning_rate": 4.8143366509105505e-05,
+      "loss": 4.163,
+      "step": 860
+    },
+    {
+      "epoch": 2.6780526109148015,
+      "grad_norm": 1.5859375,
+      "learning_rate": 4.793067643847984e-05,
+      "loss": 4.1588,
+      "step": 861
+    },
+    {
+      "epoch": 2.6811935610522184,
+      "grad_norm": 2.0625,
+      "learning_rate": 4.771830904094353e-05,
+      "loss": 4.2601,
+      "step": 862
+    },
+    {
+      "epoch": 2.684334511189635,
+      "grad_norm": 1.796875,
+      "learning_rate": 4.750626563253515e-05,
+      "loss": 4.3308,
+      "step": 863
+    },
+    {
+      "epoch": 2.6874754613270513,
+      "grad_norm": 2.03125,
+      "learning_rate": 4.72945475272857e-05,
+      "loss": 4.278,
+      "step": 864
+    },
+    {
+      "epoch": 2.690616411464468,
+      "grad_norm": 1.625,
+      "learning_rate": 4.708315603721013e-05,
+      "loss": 4.1586,
+      "step": 865
+    },
+    {
+      "epoch": 2.6937573616018846,
+      "grad_norm": 1.6796875,
+      "learning_rate": 4.687209247229948e-05,
+      "loss": 4.2834,
+      "step": 866
+    },
+    {
+      "epoch": 2.696898311739301,
+      "grad_norm": 1.828125,
+      "learning_rate": 4.666135814051265e-05,
+      "loss": 4.2298,
+      "step": 867
+    },
+    {
+      "epoch": 2.700039261876718,
+      "grad_norm": 1.7421875,
+      "learning_rate": 4.645095434776813e-05,
+      "loss": 4.0659,
+      "step": 868
+    },
+    {
+      "epoch": 2.7031802120141344,
+      "grad_norm": 2.296875,
+      "learning_rate": 4.624088239793626e-05,
+      "loss": 4.2207,
+      "step": 869
+    },
+    {
+      "epoch": 2.706321162151551,
+      "grad_norm": 1.6015625,
+      "learning_rate": 4.6031143592830796e-05,
+      "loss": 4.0905,
+      "step": 870
+    },
+    {
+      "epoch": 2.7094621122889673,
+      "grad_norm": 1.953125,
+      "learning_rate": 4.5821739232201074e-05,
+      "loss": 4.344,
+      "step": 871
+    },
+    {
+      "epoch": 2.7126030624263837,
+      "grad_norm": 1.5234375,
+      "learning_rate": 4.56126706137239e-05,
+      "loss": 4.2723,
+      "step": 872
+    },
+    {
+      "epoch": 2.7157440125638006,
+      "grad_norm": 1.6796875,
+      "learning_rate": 4.540393903299548e-05,
+      "loss": 4.2856,
+      "step": 873
+    },
+    {
+      "epoch": 2.718884962701217,
+      "grad_norm": 1.8046875,
+      "learning_rate": 4.5195545783523306e-05,
+      "loss": 4.3361,
+      "step": 874
+    },
+    {
+      "epoch": 2.7220259128386335,
+      "grad_norm": 1.890625,
+      "learning_rate": 4.498749215671838e-05,
+      "loss": 4.1725,
+      "step": 875
+    },
+    {
+      "epoch": 2.7251668629760504,
+      "grad_norm": 1.8984375,
+      "learning_rate": 4.4779779441886894e-05,
+      "loss": 4.1533,
+      "step": 876
+    },
+    {
+      "epoch": 2.728307813113467,
+      "grad_norm": 2.109375,
+      "learning_rate": 4.4572408926222656e-05,
+      "loss": 4.3197,
+      "step": 877
+    },
+    {
+      "epoch": 2.7314487632508833,
+      "grad_norm": 1.9140625,
+      "learning_rate": 4.436538189479861e-05,
+      "loss": 4.2915,
+      "step": 878
+    },
+    {
+      "epoch": 2.7345897133883,
+      "grad_norm": 1.8203125,
+      "learning_rate": 4.415869963055932e-05,
+      "loss": 4.1423,
+      "step": 879
+    },
+    {
+      "epoch": 2.7377306635257166,
+      "grad_norm": 1.90625,
+      "learning_rate": 4.395236341431269e-05,
+      "loss": 4.2739,
+      "step": 880
+    },
+    {
+      "epoch": 2.7377306635257166,
+      "eval_loss": 4.337521553039551,
+      "eval_runtime": 66.9582,
+      "eval_samples_per_second": 38.845,
+      "eval_steps_per_second": 38.845,
+      "step": 880
+    },
+    {
+      "epoch": 2.740871613663133,
+      "grad_norm": 2.015625,
+      "learning_rate": 4.374637452472227e-05,
+      "loss": 4.1914,
+      "step": 881
+    },
+    {
+      "epoch": 2.74401256380055,
+      "grad_norm": 1.71875,
+      "learning_rate": 4.3540734238299195e-05,
+      "loss": 4.2879,
+      "step": 882
+    },
+    {
+      "epoch": 2.7471535139379664,
+      "grad_norm": 1.6796875,
+      "learning_rate": 4.333544382939435e-05,
+      "loss": 4.1838,
+      "step": 883
+    },
+    {
+      "epoch": 2.750294464075383,
+      "grad_norm": 2.078125,
+      "learning_rate": 4.313050457019031e-05,
+      "loss": 4.3045,
+      "step": 884
+    },
+    {
+      "epoch": 2.7534354142127992,
+      "grad_norm": 2.015625,
+      "learning_rate": 4.2925917730693746e-05,
+      "loss": 4.2318,
+      "step": 885
+    },
+    {
+      "epoch": 2.7565763643502157,
+      "grad_norm": 2.140625,
+      "learning_rate": 4.272168457872723e-05,
+      "loss": 4.1443,
+      "step": 886
+    },
+    {
+      "epoch": 2.7597173144876326,
+      "grad_norm": 1.8828125,
+      "learning_rate": 4.251780637992163e-05,
+      "loss": 4.2531,
+      "step": 887
+    },
+    {
+      "epoch": 2.762858264625049,
+      "grad_norm": 1.6328125,
+      "learning_rate": 4.2314284397708205e-05,
+      "loss": 4.2211,
+      "step": 888
+    },
+    {
+      "epoch": 2.7659992147624655,
+      "grad_norm": 1.8203125,
+      "learning_rate": 4.2111119893310615e-05,
+      "loss": 4.3125,
+      "step": 889
+    },
+    {
+      "epoch": 2.7691401648998824,
+      "grad_norm": 1.421875,
+      "learning_rate": 4.1908314125737336e-05,
+      "loss": 4.1638,
+      "step": 890
+    },
+    {
+      "epoch": 2.772281115037299,
+      "grad_norm": 1.7421875,
+      "learning_rate": 4.170586835177373e-05,
+      "loss": 4.2876,
+      "step": 891
+    },
+    {
+      "epoch": 2.7754220651747152,
+      "grad_norm": 2.125,
+      "learning_rate": 4.150378382597432e-05,
+      "loss": 4.2073,
+      "step": 892
+    },
+    {
+      "epoch": 2.778563015312132,
+      "grad_norm": 1.9453125,
+      "learning_rate": 4.130206180065487e-05,
+      "loss": 4.251,
+      "step": 893
+    },
+    {
+      "epoch": 2.7817039654495486,
+      "grad_norm": 1.8359375,
+      "learning_rate": 4.1100703525884857e-05,
+      "loss": 4.1373,
+      "step": 894
+    },
+    {
+      "epoch": 2.784844915586965,
+      "grad_norm": 1.7265625,
+      "learning_rate": 4.089971024947945e-05,
+      "loss": 4.3777,
+      "step": 895
+    },
+    {
+      "epoch": 2.787985865724382,
+      "grad_norm": 1.34375,
+      "learning_rate": 4.069908321699215e-05,
+      "loss": 3.8683,
+      "step": 896
+    },
+    {
+      "epoch": 2.7911268158617983,
+      "grad_norm": 2.078125,
+      "learning_rate": 4.049882367170662e-05,
+      "loss": 4.216,
+      "step": 897
+    },
+    {
+      "epoch": 2.794267765999215,
+      "grad_norm": 1.75,
+      "learning_rate": 4.0298932854629365e-05,
+      "loss": 4.2245,
+      "step": 898
+    },
+    {
+      "epoch": 2.7974087161366312,
+      "grad_norm": 1.890625,
+      "learning_rate": 4.0099412004481764e-05,
+      "loss": 4.0796,
+      "step": 899
+    },
+    {
+      "epoch": 2.8005496662740477,
+      "grad_norm": 2.328125,
+      "learning_rate": 3.9900262357692606e-05,
+      "loss": 4.1913,
+      "step": 900
+    },
+    {
+      "epoch": 2.8036906164114646,
+      "grad_norm": 1.9375,
+      "learning_rate": 3.970148514839032e-05,
+      "loss": 4.0886,
+      "step": 901
+    },
+    {
+      "epoch": 2.806831566548881,
+      "grad_norm": 2.421875,
+      "learning_rate": 3.950308160839533e-05,
+      "loss": 4.2677,
+      "step": 902
+    },
+    {
+      "epoch": 2.8099725166862974,
+      "grad_norm": 1.9765625,
+      "learning_rate": 3.9305052967212394e-05,
+      "loss": 4.2403,
+      "step": 903
+    },
+    {
+      "epoch": 2.8131134668237143,
+      "grad_norm": 1.5390625,
+      "learning_rate": 3.9107400452023135e-05,
+      "loss": 4.0441,
+      "step": 904
+    },
+    {
+      "epoch": 2.8162544169611308,
+      "grad_norm": 1.6796875,
+      "learning_rate": 3.891012528767818e-05,
+      "loss": 4.1853,
+      "step": 905
+    },
+    {
+      "epoch": 2.819395367098547,
+      "grad_norm": 1.8984375,
+      "learning_rate": 3.871322869668982e-05,
+      "loss": 4.3383,
+      "step": 906
+    },
+    {
+      "epoch": 2.822536317235964,
+      "grad_norm": 1.859375,
+      "learning_rate": 3.8516711899224366e-05,
+      "loss": 4.2147,
+      "step": 907
+    },
+    {
+      "epoch": 2.8256772673733805,
+      "grad_norm": 2.265625,
+      "learning_rate": 3.83205761130944e-05,
+      "loss": 4.3001,
+      "step": 908
+    },
+    {
+      "epoch": 2.828818217510797,
+      "grad_norm": 2.296875,
+      "learning_rate": 3.812482255375155e-05,
+      "loss": 4.3215,
+      "step": 909
+    },
+    {
+      "epoch": 2.8319591676482134,
+      "grad_norm": 1.515625,
+      "learning_rate": 3.79294524342786e-05,
+      "loss": 4.1887,
+      "step": 910
+    },
+    {
+      "epoch": 2.8351001177856303,
+      "grad_norm": 1.8515625,
+      "learning_rate": 3.7734466965382406e-05,
+      "loss": 4.3306,
+      "step": 911
+    },
+    {
+      "epoch": 2.8382410679230468,
+      "grad_norm": 1.5390625,
+      "learning_rate": 3.753986735538594e-05,
+      "loss": 4.3131,
+      "step": 912
+    },
+    {
+      "epoch": 2.841382018060463,
+      "grad_norm": 1.953125,
+      "learning_rate": 3.734565481022112e-05,
+      "loss": 4.3618,
+      "step": 913
+    },
+    {
+      "epoch": 2.8445229681978796,
+      "grad_norm": 1.8203125,
+      "learning_rate": 3.715183053342113e-05,
+      "loss": 4.1223,
+      "step": 914
+    },
+    {
+      "epoch": 2.8476639183352965,
+      "grad_norm": 1.921875,
+      "learning_rate": 3.695839572611316e-05,
+      "loss": 4.3063,
+      "step": 915
+    },
+    {
+      "epoch": 2.850804868472713,
+      "grad_norm": 1.578125,
+      "learning_rate": 3.676535158701081e-05,
+      "loss": 4.2102,
+      "step": 916
+    },
+    {
+      "epoch": 2.8539458186101294,
+      "grad_norm": 1.859375,
+      "learning_rate": 3.6572699312406764e-05,
+      "loss": 4.1753,
+      "step": 917
+    },
+    {
+      "epoch": 2.8570867687475463,
+      "grad_norm": 1.6796875,
+      "learning_rate": 3.638044009616523e-05,
+      "loss": 4.1748,
+      "step": 918
+    },
+    {
+      "epoch": 2.8602277188849627,
+      "grad_norm": 1.78125,
+      "learning_rate": 3.618857512971473e-05,
+      "loss": 4.3249,
+      "step": 919
+    },
+    {
+      "epoch": 2.863368669022379,
+      "grad_norm": 1.7578125,
+      "learning_rate": 3.5997105602040514e-05,
+      "loss": 4.2735,
+      "step": 920
+    },
+    {
+      "epoch": 2.866509619159796,
+      "grad_norm": 1.9921875,
+      "learning_rate": 3.5806032699677495e-05,
+      "loss": 4.3388,
+      "step": 921
+    },
+    {
+      "epoch": 2.8696505692972125,
+      "grad_norm": 1.84375,
+      "learning_rate": 3.561535760670247e-05,
+      "loss": 4.2297,
+      "step": 922
+    },
+    {
+      "epoch": 2.872791519434629,
+      "grad_norm": 1.8046875,
+      "learning_rate": 3.542508150472722e-05,
+      "loss": 4.3259,
+      "step": 923
+    },
+    {
+      "epoch": 2.8759324695720454,
+      "grad_norm": 1.9375,
+      "learning_rate": 3.5235205572890806e-05,
+      "loss": 4.2322,
+      "step": 924
+    },
+    {
+      "epoch": 2.879073419709462,
+      "grad_norm": 1.65625,
+      "learning_rate": 3.504573098785255e-05,
+      "loss": 4.2519,
+      "step": 925
+    },
+    {
+      "epoch": 2.8822143698468787,
+      "grad_norm": 1.7734375,
+      "learning_rate": 3.4856658923784655e-05,
+      "loss": 4.3263,
+      "step": 926
+    },
+    {
+      "epoch": 2.885355319984295,
+      "grad_norm": 1.7890625,
+      "learning_rate": 3.466799055236478e-05,
+      "loss": 4.3084,
+      "step": 927
+    },
+    {
+      "epoch": 2.8884962701217116,
+      "grad_norm": 1.90625,
+      "learning_rate": 3.447972704276904e-05,
+      "loss": 4.0587,
+      "step": 928
+    },
+    {
+      "epoch": 2.8916372202591285,
+      "grad_norm": 1.9140625,
+      "learning_rate": 3.42918695616645e-05,
+      "loss": 4.2044,
+      "step": 929
+    },
+    {
+      "epoch": 2.894778170396545,
+      "grad_norm": 1.9296875,
+      "learning_rate": 3.410441927320217e-05,
+      "loss": 4.2748,
+      "step": 930
+    },
+    {
+      "epoch": 2.8979191205339614,
+      "grad_norm": 1.8125,
+      "learning_rate": 3.391737733900965e-05,
+      "loss": 4.2428,
+      "step": 931
+    },
+    {
+      "epoch": 2.9010600706713783,
+      "grad_norm": 1.890625,
+      "learning_rate": 3.373074491818402e-05,
+      "loss": 4.1668,
+      "step": 932
+    },
+    {
+      "epoch": 2.9042010208087947,
+      "grad_norm": 2.421875,
+      "learning_rate": 3.35445231672845e-05,
+      "loss": 4.4141,
+      "step": 933
+    },
+    {
+      "epoch": 2.907341970946211,
+      "grad_norm": 1.5,
+      "learning_rate": 3.335871324032553e-05,
+      "loss": 4.1675,
+      "step": 934
+    },
+    {
+      "epoch": 2.910482921083628,
+      "grad_norm": 1.8125,
+      "learning_rate": 3.317331628876931e-05,
+      "loss": 4.2343,
+      "step": 935
+    },
+    {
+      "epoch": 2.9136238712210445,
+      "grad_norm": 1.5078125,
+      "learning_rate": 3.298833346151905e-05,
+      "loss": 4.0359,
+      "step": 936
+    },
+    {
+      "epoch": 2.916764821358461,
+      "grad_norm": 1.7109375,
+      "learning_rate": 3.280376590491146e-05,
+      "loss": 4.0712,
+      "step": 937
+    },
+    {
+      "epoch": 2.9199057714958774,
+      "grad_norm": 1.625,
+      "learning_rate": 3.2619614762709916e-05,
+      "loss": 4.0523,
+      "step": 938
+    },
+    {
+      "epoch": 2.923046721633294,
+      "grad_norm": 1.625,
+      "learning_rate": 3.243588117609721e-05,
+      "loss": 4.0576,
+      "step": 939
+    },
+    {
+      "epoch": 2.9261876717707107,
+      "grad_norm": 1.734375,
+      "learning_rate": 3.225256628366859e-05,
+      "loss": 4.1502,
+      "step": 940
+    },
+    {
+      "epoch": 2.929328621908127,
+      "grad_norm": 1.796875,
+      "learning_rate": 3.206967122142467e-05,
+      "loss": 4.0622,
+      "step": 941
+    },
+    {
+      "epoch": 2.9324695720455436,
+      "grad_norm": 1.8046875,
+      "learning_rate": 3.188719712276438e-05,
+      "loss": 4.2462,
+      "step": 942
+    },
+    {
+      "epoch": 2.9356105221829605,
+      "grad_norm": 1.84375,
+      "learning_rate": 3.1705145118477885e-05,
+      "loss": 4.3086,
+      "step": 943
+    },
+    {
+      "epoch": 2.938751472320377,
+      "grad_norm": 1.6875,
+      "learning_rate": 3.1523516336739725e-05,
+      "loss": 4.2226,
+      "step": 944
+    },
+    {
+      "epoch": 2.9418924224577934,
+      "grad_norm": 1.8828125,
+      "learning_rate": 3.134231190310162e-05,
+      "loss": 4.2318,
+      "step": 945
+    },
+    {
+      "epoch": 2.9450333725952103,
+      "grad_norm": 1.6796875,
+      "learning_rate": 3.11615329404857e-05,
+      "loss": 4.1399,
+      "step": 946
+    },
+    {
+      "epoch": 2.9481743227326267,
+      "grad_norm": 1.7734375,
+      "learning_rate": 3.098118056917749e-05,
+      "loss": 4.3376,
+      "step": 947
+    },
+    {
+      "epoch": 2.951315272870043,
+      "grad_norm": 1.7109375,
+      "learning_rate": 3.080125590681879e-05,
+      "loss": 4.1966,
+      "step": 948
+    },
+    {
+      "epoch": 2.95445622300746,
+      "grad_norm": 1.7890625,
+      "learning_rate": 3.0621760068401e-05,
+      "loss": 4.3592,
+      "step": 949
+    },
+    {
+      "epoch": 2.9575971731448765,
+      "grad_norm": 1.8125,
+      "learning_rate": 3.044269416625809e-05,
+      "loss": 4.132,
+      "step": 950
+    },
+    {
+      "epoch": 2.960738123282293,
+      "grad_norm": 1.828125,
+      "learning_rate": 3.0264059310059722e-05,
+      "loss": 4.2469,
+      "step": 951
+    },
+    {
+      "epoch": 2.9638790734197094,
+      "grad_norm": 1.7421875,
+      "learning_rate": 3.008585660680431e-05,
+      "loss": 4.2706,
+      "step": 952
+    },
+    {
+      "epoch": 2.967020023557126,
+      "grad_norm": 1.5234375,
+      "learning_rate": 2.9908087160812316e-05,
+      "loss": 4.2353,
+      "step": 953
+    },
+    {
+      "epoch": 2.9701609736945427,
+      "grad_norm": 1.8515625,
+      "learning_rate": 2.9730752073719194e-05,
+      "loss": 4.2077,
+      "step": 954
+    },
+    {
+      "epoch": 2.973301923831959,
+      "grad_norm": 1.7578125,
+      "learning_rate": 2.955385244446879e-05,
+      "loss": 4.1992,
+      "step": 955
+    },
+    {
+      "epoch": 2.9764428739693756,
+      "grad_norm": 1.71875,
+      "learning_rate": 2.9377389369306363e-05,
+      "loss": 4.3838,
+      "step": 956
+    },
+    {
+      "epoch": 2.9795838241067925,
+      "grad_norm": 1.5234375,
+      "learning_rate": 2.92013639417719e-05,
+      "loss": 4.1166,
+      "step": 957
+    },
+    {
+      "epoch": 2.982724774244209,
+      "grad_norm": 1.859375,
+      "learning_rate": 2.9025777252693197e-05,
+      "loss": 4.1378,
+      "step": 958
+    },
+    {
+      "epoch": 2.9858657243816253,
+      "grad_norm": 1.921875,
+      "learning_rate": 2.885063039017929e-05,
+      "loss": 4.3515,
+      "step": 959
+    },
+    {
+      "epoch": 2.9890066745190422,
+      "grad_norm": 1.6953125,
+      "learning_rate": 2.8675924439613556e-05,
+      "loss": 4.4037,
+      "step": 960
+    },
+    {
+      "epoch": 2.9890066745190422,
+      "eval_loss": 4.331027984619141,
+      "eval_runtime": 66.8828,
+      "eval_samples_per_second": 38.889,
+      "eval_steps_per_second": 38.889,
+      "step": 960
+    },
+    {
+      "epoch": 2.9921476246564587,
+      "grad_norm": 1.59375,
+      "learning_rate": 2.8501660483647108e-05,
+      "loss": 4.2491,
+      "step": 961
+    },
+    {
+      "epoch": 2.995288574793875,
+      "grad_norm": 1.828125,
+      "learning_rate": 2.8327839602191908e-05,
+      "loss": 4.3474,
+      "step": 962
+    },
+    {
+      "epoch": 2.9984295249312916,
+      "grad_norm": 1.578125,
+      "learning_rate": 2.8154462872414322e-05,
+      "loss": 4.1054,
+      "step": 963
+    },
+    {
+      "epoch": 3.001570475068708,
+      "grad_norm": 2.1875,
+      "learning_rate": 2.79815313687282e-05,
+      "loss": 4.1835,
+      "step": 964
+    },
+    {
+      "epoch": 3.004711425206125,
+      "grad_norm": 1.84375,
+      "learning_rate": 2.78090461627884e-05,
+      "loss": 4.3204,
+      "step": 965
+    },
+    {
+      "epoch": 3.0078523753435413,
+      "grad_norm": 1.8828125,
+      "learning_rate": 2.763700832348406e-05,
+      "loss": 4.3394,
+      "step": 966
+    },
+    {
+      "epoch": 3.0109933254809578,
+      "grad_norm": 2.0,
+      "learning_rate": 2.7465418916932016e-05,
+      "loss": 4.3174,
+      "step": 967
+    },
+    {
+      "epoch": 3.000785237534354,
+      "grad_norm": 1.703125,
+      "learning_rate": 2.729427900647009e-05,
+      "loss": 4.2522,
+      "step": 968
+    },
+    {
+      "epoch": 3.003926187671771,
+      "grad_norm": 1.6015625,
+      "learning_rate": 2.7123589652650662e-05,
+      "loss": 4.11,
+      "step": 969
+    },
+    {
+      "epoch": 3.0070671378091873,
+      "grad_norm": 1.890625,
+      "learning_rate": 2.6953351913234015e-05,
+      "loss": 4.1082,
+      "step": 970
+    },
+    {
+      "epoch": 3.0102080879466038,
+      "grad_norm": 2.265625,
+      "learning_rate": 2.6783566843181708e-05,
+      "loss": 4.2025,
+      "step": 971
+    },
+    {
+      "epoch": 3.01334903808402,
+      "grad_norm": 1.78125,
+      "learning_rate": 2.6614235494650208e-05,
+      "loss": 4.0572,
+      "step": 972
+    },
+    {
+      "epoch": 3.016489988221437,
+      "grad_norm": 1.6640625,
+      "learning_rate": 2.6445358916984175e-05,
+      "loss": 4.2666,
+      "step": 973
+    },
+    {
+      "epoch": 3.0196309383588535,
+      "grad_norm": 1.65625,
+      "learning_rate": 2.627693815671014e-05,
+      "loss": 4.272,
+      "step": 974
+    },
+    {
+      "epoch": 3.02277188849627,
+      "grad_norm": 1.78125,
+      "learning_rate": 2.6108974257529904e-05,
+      "loss": 4.2759,
+      "step": 975
+    },
+    {
+      "epoch": 3.025912838633687,
+      "grad_norm": 1.625,
+      "learning_rate": 2.5941468260314138e-05,
+      "loss": 4.1443,
+      "step": 976
+    },
+    {
+      "epoch": 3.0290537887711033,
+      "grad_norm": 1.65625,
+      "learning_rate": 2.5774421203095823e-05,
+      "loss": 4.3098,
+      "step": 977
+    },
+    {
+      "epoch": 3.0321947389085198,
+      "grad_norm": 1.796875,
+      "learning_rate": 2.560783412106399e-05,
+      "loss": 4.3046,
+      "step": 978
+    },
+    {
+      "epoch": 3.035335689045936,
+      "grad_norm": 1.5234375,
+      "learning_rate": 2.5441708046557057e-05,
+      "loss": 4.1165,
+      "step": 979
+    },
+    {
+      "epoch": 3.038476639183353,
+      "grad_norm": 2.296875,
+      "learning_rate": 2.5276044009056832e-05,
+      "loss": 4.3369,
+      "step": 980
+    },
+    {
+      "epoch": 3.0416175893207695,
+      "grad_norm": 1.765625,
+      "learning_rate": 2.511084303518162e-05,
+      "loss": 4.336,
+      "step": 981
+    },
+    {
+      "epoch": 3.044758539458186,
+      "grad_norm": 1.953125,
+      "learning_rate": 2.4946106148680315e-05,
+      "loss": 4.1296,
+      "step": 982
+    },
+    {
+      "epoch": 3.047899489595603,
+      "grad_norm": 1.8828125,
+      "learning_rate": 2.4781834370425726e-05,
+      "loss": 4.29,
+      "step": 983
+    },
+    {
+      "epoch": 3.0510404397330193,
+      "grad_norm": 1.734375,
+      "learning_rate": 2.4618028718408504e-05,
+      "loss": 4.1741,
+      "step": 984
+    },
+    {
+      "epoch": 3.0541813898704357,
+      "grad_norm": 1.5703125,
+      "learning_rate": 2.4454690207730657e-05,
+      "loss": 4.0973,
+      "step": 985
+    },
+    {
+      "epoch": 3.057322340007852,
+      "grad_norm": 1.9453125,
+      "learning_rate": 2.4291819850599375e-05,
+      "loss": 4.3695,
+      "step": 986
+    },
+    {
+      "epoch": 3.060463290145269,
+      "grad_norm": 1.84375,
+      "learning_rate": 2.41294186563206e-05,
+      "loss": 4.2748,
+      "step": 987
+    },
+    {
+      "epoch": 3.0636042402826855,
+      "grad_norm": 1.890625,
+      "learning_rate": 2.3967487631293017e-05,
+      "loss": 4.3048,
+      "step": 988
+    },
+    {
+      "epoch": 3.066745190420102,
+      "grad_norm": 1.640625,
+      "learning_rate": 2.380602777900155e-05,
+      "loss": 4.2179,
+      "step": 989
+    },
+    {
+      "epoch": 3.069886140557519,
+      "grad_norm": 1.9453125,
+      "learning_rate": 2.364504010001135e-05,
+      "loss": 4.3615,
+      "step": 990
+    },
+    {
+      "epoch": 3.0730270906949353,
+      "grad_norm": 1.6796875,
+      "learning_rate": 2.3484525591961515e-05,
+      "loss": 3.9482,
+      "step": 991
+    },
+    {
+      "epoch": 3.0761680408323517,
+      "grad_norm": 1.546875,
+      "learning_rate": 2.3324485249558826e-05,
+      "loss": 4.262,
+      "step": 992
+    },
+    {
+      "epoch": 3.079308990969768,
+      "grad_norm": 1.703125,
+      "learning_rate": 2.3164920064571782e-05,
+      "loss": 4.2338,
+      "step": 993
+    },
+    {
+      "epoch": 3.082449941107185,
+      "grad_norm": 1.859375,
+      "learning_rate": 2.300583102582419e-05,
+      "loss": 3.8901,
+      "step": 994
+    },
+    {
+      "epoch": 3.0855908912446015,
+      "grad_norm": 1.578125,
+      "learning_rate": 2.284721911918938e-05,
+      "loss": 4.166,
+      "step": 995
+    },
+    {
+      "epoch": 3.088731841382018,
+      "grad_norm": 1.9765625,
+      "learning_rate": 2.2689085327583702e-05,
+      "loss": 4.0596,
+      "step": 996
+    },
+    {
+      "epoch": 3.091872791519435,
+      "grad_norm": 1.5078125,
+      "learning_rate": 2.2531430630960783e-05,
+      "loss": 4.0642,
+      "step": 997
+    },
+    {
+      "epoch": 3.0950137416568513,
+      "grad_norm": 1.6640625,
+      "learning_rate": 2.237425600630516e-05,
+      "loss": 4.1809,
+      "step": 998
+    },
+    {
+      "epoch": 3.0981546917942677,
+      "grad_norm": 1.7265625,
+      "learning_rate": 2.2217562427626493e-05,
+      "loss": 4.3212,
+      "step": 999
+    },
+    {
+      "epoch": 3.101295641931684,
+      "grad_norm": 1.6875,
+      "learning_rate": 2.2061350865953358e-05,
+      "loss": 4.2095,
+      "step": 1000
+    },
+    {
+      "epoch": 3.104436592069101,
+      "grad_norm": 1.5078125,
+      "learning_rate": 2.1905622289327287e-05,
+      "loss": 4.0652,
+      "step": 1001
+    },
+    {
+      "epoch": 3.1075775422065175,
+      "grad_norm": 1.7890625,
+      "learning_rate": 2.1750377662796706e-05,
+      "loss": 4.2749,
+      "step": 1002
+    },
+    {
+      "epoch": 3.110718492343934,
+      "grad_norm": 1.65625,
+      "learning_rate": 2.1595617948411106e-05,
+      "loss": 4.1829,
+      "step": 1003
+    },
+    {
+      "epoch": 3.113859442481351,
+      "grad_norm": 1.71875,
+      "learning_rate": 2.1441344105214832e-05,
+      "loss": 4.2614,
+      "step": 1004
+    },
+    {
+      "epoch": 3.1170003926187673,
+      "grad_norm": 1.8203125,
+      "learning_rate": 2.1287557089241496e-05,
+      "loss": 4.1807,
+      "step": 1005
+    },
+    {
+      "epoch": 3.1201413427561837,
+      "grad_norm": 2.0,
+      "learning_rate": 2.1134257853507655e-05,
+      "loss": 4.2123,
+      "step": 1006
+    },
+    {
+      "epoch": 3.1232822928936,
+      "grad_norm": 1.625,
+      "learning_rate": 2.0981447348007234e-05,
+      "loss": 4.0871,
+      "step": 1007
+    },
+    {
+      "epoch": 3.126423243031017,
+      "grad_norm": 1.625,
+      "learning_rate": 2.0829126519705367e-05,
+      "loss": 4.1424,
+      "step": 1008
+    },
+    {
+      "epoch": 3.1295641931684335,
+      "grad_norm": 1.65625,
+      "learning_rate": 2.0677296312532777e-05,
+      "loss": 3.8041,
+      "step": 1009
+    },
+    {
+      "epoch": 3.13270514330585,
+      "grad_norm": 1.6640625,
+      "learning_rate": 2.0525957667379812e-05,
+      "loss": 4.3112,
+      "step": 1010
+    },
+    {
+      "epoch": 3.1358460934432664,
+      "grad_norm": 2.15625,
+      "learning_rate": 2.0375111522090517e-05,
+      "loss": 4.1517,
+      "step": 1011
+    },
+    {
+      "epoch": 3.1389870435806833,
+      "grad_norm": 1.8046875,
+      "learning_rate": 2.0224758811457023e-05,
+      "loss": 4.1044,
+      "step": 1012
+    },
+    {
+      "epoch": 3.1421279937180997,
+      "grad_norm": 1.6328125,
+      "learning_rate": 2.0074900467213565e-05,
+      "loss": 4.1159,
+      "step": 1013
+    },
+    {
+      "epoch": 3.145268943855516,
+      "grad_norm": 1.453125,
+      "learning_rate": 1.992553741803087e-05,
+      "loss": 4.1007,
+      "step": 1014
+    },
+    {
+      "epoch": 3.148409893992933,
+      "grad_norm": 1.609375,
+      "learning_rate": 1.9776670589510284e-05,
+      "loss": 4.2939,
+      "step": 1015
+    },
+    {
+      "epoch": 3.1515508441303495,
+      "grad_norm": 1.640625,
+      "learning_rate": 1.962830090417811e-05,
+      "loss": 4.241,
+      "step": 1016
+    },
+    {
+      "epoch": 3.154691794267766,
+      "grad_norm": 1.6875,
+      "learning_rate": 1.9480429281479796e-05,
+      "loss": 4.0677,
+      "step": 1017
+    },
+    {
+      "epoch": 3.157832744405183,
+      "grad_norm": 1.71875,
+      "learning_rate": 1.9333056637774395e-05,
+      "loss": 4.0581,
+      "step": 1018
+    },
+    {
+      "epoch": 3.1609736945425992,
+      "grad_norm": 1.8046875,
+      "learning_rate": 1.918618388632866e-05,
+      "loss": 4.2188,
+      "step": 1019
+    },
+    {
+      "epoch": 3.1641146446800157,
+      "grad_norm": 1.8984375,
+      "learning_rate": 1.90398119373117e-05,
+      "loss": 4.3316,
+      "step": 1020
+    },
+    {
+      "epoch": 3.167255594817432,
+      "grad_norm": 1.7734375,
+      "learning_rate": 1.8893941697788975e-05,
+      "loss": 4.3032,
+      "step": 1021
+    },
+    {
+      "epoch": 3.170396544954849,
+      "grad_norm": 1.984375,
+      "learning_rate": 1.8748574071716983e-05,
+      "loss": 4.1387,
+      "step": 1022
+    },
+    {
+      "epoch": 3.1735374950922655,
+      "grad_norm": 1.9921875,
+      "learning_rate": 1.8603709959937432e-05,
+      "loss": 4.2055,
+      "step": 1023
+    },
+    {
+      "epoch": 3.176678445229682,
+      "grad_norm": 1.7578125,
+      "learning_rate": 1.8459350260171836e-05,
+      "loss": 4.1056,
+      "step": 1024
+    },
+    {
+      "epoch": 3.1798193953670983,
+      "grad_norm": 1.3125,
+      "learning_rate": 1.831549586701584e-05,
+      "loss": 4.0395,
+      "step": 1025
+    },
+    {
+      "epoch": 3.1829603455045152,
+      "grad_norm": 2.515625,
+      "learning_rate": 1.8172147671933738e-05,
+      "loss": 4.3442,
+      "step": 1026
+    },
+    {
+      "epoch": 3.1861012956419317,
+      "grad_norm": 1.625,
+      "learning_rate": 1.8029306563252844e-05,
+      "loss": 4.1894,
+      "step": 1027
+    },
+    {
+      "epoch": 3.189242245779348,
+      "grad_norm": 1.4375,
+      "learning_rate": 1.788697342615814e-05,
+      "loss": 4.1217,
+      "step": 1028
+    },
+    {
+      "epoch": 3.192383195916765,
+      "grad_norm": 1.890625,
+      "learning_rate": 1.7745149142686713e-05,
+      "loss": 4.2592,
+      "step": 1029
+    },
+    {
+      "epoch": 3.1955241460541814,
+      "grad_norm": 1.625,
+      "learning_rate": 1.7603834591722203e-05,
+      "loss": 4.3289,
+      "step": 1030
+    },
+    {
+      "epoch": 3.198665096191598,
+      "grad_norm": 1.734375,
+      "learning_rate": 1.7463030648989554e-05,
+      "loss": 4.218,
+      "step": 1031
+    },
+    {
+      "epoch": 3.2018060463290143,
+      "grad_norm": 1.5078125,
+      "learning_rate": 1.732273818704938e-05,
+      "loss": 4.3367,
+      "step": 1032
+    },
+    {
+      "epoch": 3.204946996466431,
+      "grad_norm": 1.984375,
+      "learning_rate": 1.718295807529272e-05,
+      "loss": 4.2902,
+      "step": 1033
+    },
+    {
+      "epoch": 3.2080879466038477,
+      "grad_norm": 1.640625,
+      "learning_rate": 1.704369117993555e-05,
+      "loss": 4.2063,
+      "step": 1034
+    },
+    {
+      "epoch": 3.211228896741264,
+      "grad_norm": 1.640625,
+      "learning_rate": 1.6904938364013502e-05,
+      "loss": 4.1777,
+      "step": 1035
+    },
+    {
+      "epoch": 3.214369846878681,
+      "grad_norm": 1.625,
+      "learning_rate": 1.676670048737635e-05,
+      "loss": 4.15,
+      "step": 1036
+    },
+    {
+      "epoch": 3.2175107970160974,
+      "grad_norm": 1.609375,
+      "learning_rate": 1.6628978406682926e-05,
+      "loss": 4.2386,
+      "step": 1037
+    },
+    {
+      "epoch": 3.220651747153514,
+      "grad_norm": 1.5078125,
+      "learning_rate": 1.649177297539556e-05,
+      "loss": 4.1971,
+      "step": 1038
+    },
+    {
+      "epoch": 3.2237926972909303,
+      "grad_norm": 1.609375,
+      "learning_rate": 1.6355085043775033e-05,
+      "loss": 4.3047,
+      "step": 1039
+    },
+    {
+      "epoch": 3.226933647428347,
+      "grad_norm": 1.8828125,
+      "learning_rate": 1.6218915458875074e-05,
+      "loss": 4.195,
+      "step": 1040
+    },
+    {
+      "epoch": 3.226933647428347,
+      "eval_loss": 4.3286590576171875,
+      "eval_runtime": 66.9622,
+      "eval_samples_per_second": 38.843,
+      "eval_steps_per_second": 38.843,
+      "step": 1040
+    },
+    {
+      "epoch": 3.2300745975657636,
+      "grad_norm": 1.515625,
+      "learning_rate": 1.60832650645373e-05,
+      "loss": 4.2504,
+      "step": 1041
+    },
+    {
+      "epoch": 3.23321554770318,
+      "grad_norm": 1.875,
+      "learning_rate": 1.5948134701385842e-05,
+      "loss": 4.1937,
+      "step": 1042
+    },
+    {
+      "epoch": 3.236356497840597,
+      "grad_norm": 2.03125,
+      "learning_rate": 1.5813525206822266e-05,
+      "loss": 4.2812,
+      "step": 1043
+    },
+    {
+      "epoch": 3.2394974479780134,
+      "grad_norm": 1.71875,
+      "learning_rate": 1.567943741502029e-05,
+      "loss": 4.267,
+      "step": 1044
+    },
+    {
+      "epoch": 3.24263839811543,
+      "grad_norm": 1.9375,
+      "learning_rate": 1.5545872156920683e-05,
+      "loss": 4.1019,
+      "step": 1045
+    },
+    {
+      "epoch": 3.2457793482528463,
+      "grad_norm": 1.75,
+      "learning_rate": 1.5412830260225985e-05,
+      "loss": 4.0383,
+      "step": 1046
+    },
+    {
+      "epoch": 3.248920298390263,
+      "grad_norm": 1.4375,
+      "learning_rate": 1.528031254939558e-05,
+      "loss": 4.0691,
+      "step": 1047
+    },
+    {
+      "epoch": 3.2520612485276796,
+      "grad_norm": 1.578125,
+      "learning_rate": 1.5148319845640368e-05,
+      "loss": 4.2433,
+      "step": 1048
+    },
+    {
+      "epoch": 3.255202198665096,
+      "grad_norm": 1.4609375,
+      "learning_rate": 1.5016852966917893e-05,
+      "loss": 4.1286,
+      "step": 1049
+    },
+    {
+      "epoch": 3.2583431488025125,
+      "grad_norm": 1.6953125,
+      "learning_rate": 1.488591272792712e-05,
+      "loss": 4.1906,
+      "step": 1050
+    },
+    {
+      "epoch": 3.2614840989399294,
+      "grad_norm": 1.8203125,
+      "learning_rate": 1.4755499940103401e-05,
+      "loss": 4.0168,
+      "step": 1051
+    },
+    {
+      "epoch": 3.264625049077346,
+      "grad_norm": 1.7734375,
+      "learning_rate": 1.4625615411613535e-05,
+      "loss": 3.945,
+      "step": 1052
+    },
+    {
+      "epoch": 3.2677659992147623,
+      "grad_norm": 1.7578125,
+      "learning_rate": 1.4496259947350622e-05,
+      "loss": 4.1728,
+      "step": 1053
+    },
+    {
+      "epoch": 3.270906949352179,
+      "grad_norm": 2.28125,
+      "learning_rate": 1.4367434348929299e-05,
+      "loss": 4.2298,
+      "step": 1054
+    },
+    {
+      "epoch": 3.2740478994895956,
+      "grad_norm": 1.625,
+      "learning_rate": 1.4239139414680469e-05,
+      "loss": 4.2794,
+      "step": 1055
+    },
+    {
+      "epoch": 3.277188849627012,
+      "grad_norm": 2.03125,
+      "learning_rate": 1.411137593964662e-05,
+      "loss": 4.238,
+      "step": 1056
+    },
+    {
+      "epoch": 3.280329799764429,
+      "grad_norm": 1.6953125,
+      "learning_rate": 1.398414471557673e-05,
+      "loss": 4.2409,
+      "step": 1057
+    },
+    {
+      "epoch": 3.2834707499018454,
+      "grad_norm": 1.515625,
+      "learning_rate": 1.3857446530921469e-05,
+      "loss": 4.1546,
+      "step": 1058
+    },
+    {
+      "epoch": 3.286611700039262,
+      "grad_norm": 1.6875,
+      "learning_rate": 1.3731282170828252e-05,
+      "loss": 3.9457,
+      "step": 1059
+    },
+    {
+      "epoch": 3.2897526501766783,
+      "grad_norm": 1.4375,
+      "learning_rate": 1.3605652417136406e-05,
+      "loss": 4.1857,
+      "step": 1060
+    },
+    {
+      "epoch": 3.292893600314095,
+      "grad_norm": 1.5390625,
+      "learning_rate": 1.3480558048372238e-05,
+      "loss": 4.1545,
+      "step": 1061
+    },
+    {
+      "epoch": 3.2960345504515116,
+      "grad_norm": 1.71875,
+      "learning_rate": 1.335599983974437e-05,
+      "loss": 4.1146,
+      "step": 1062
+    },
+    {
+      "epoch": 3.299175500588928,
+      "grad_norm": 1.953125,
+      "learning_rate": 1.3231978563138746e-05,
+      "loss": 4.3818,
+      "step": 1063
+    },
+    {
+      "epoch": 3.3023164507263445,
+      "grad_norm": 1.609375,
+      "learning_rate": 1.3108494987114094e-05,
+      "loss": 4.1783,
+      "step": 1064
+    },
+    {
+      "epoch": 3.3054574008637614,
+      "grad_norm": 1.9765625,
+      "learning_rate": 1.2985549876896863e-05,
+      "loss": 4.1311,
+      "step": 1065
+    },
+    {
+      "epoch": 3.308598351001178,
+      "grad_norm": 1.546875,
+      "learning_rate": 1.2863143994376725e-05,
+      "loss": 4.0058,
+      "step": 1066
+    },
+    {
+      "epoch": 3.3117393011385943,
+      "grad_norm": 1.8671875,
+      "learning_rate": 1.2741278098101717e-05,
+      "loss": 4.2044,
+      "step": 1067
+    },
+    {
+      "epoch": 3.314880251276011,
+      "grad_norm": 1.6640625,
+      "learning_rate": 1.2619952943273617e-05,
+      "loss": 4.1373,
+      "step": 1068
+    },
+    {
+      "epoch": 3.3180212014134276,
+      "grad_norm": 1.515625,
+      "learning_rate": 1.249916928174325e-05,
+      "loss": 4.11,
+      "step": 1069
+    },
+    {
+      "epoch": 3.321162151550844,
+      "grad_norm": 1.6875,
+      "learning_rate": 1.237892786200574e-05,
+      "loss": 4.3345,
+      "step": 1070
+    },
+    {
+      "epoch": 3.324303101688261,
+      "grad_norm": 1.5625,
+      "learning_rate": 1.225922942919604e-05,
+      "loss": 4.0787,
+      "step": 1071
+    },
+    {
+      "epoch": 3.3274440518256774,
+      "grad_norm": 1.6640625,
+      "learning_rate": 1.2140074725084116e-05,
+      "loss": 4.2066,
+      "step": 1072
+    },
+    {
+      "epoch": 3.330585001963094,
+      "grad_norm": 1.765625,
+      "learning_rate": 1.2021464488070533e-05,
+      "loss": 4.2442,
+      "step": 1073
+    },
+    {
+      "epoch": 3.3337259521005103,
+      "grad_norm": 1.4765625,
+      "learning_rate": 1.1903399453181762e-05,
+      "loss": 4.0912,
+      "step": 1074
+    },
+    {
+      "epoch": 3.336866902237927,
+      "grad_norm": 1.8203125,
+      "learning_rate": 1.1785880352065704e-05,
+      "loss": 4.4061,
+      "step": 1075
+    },
+    {
+      "epoch": 3.3400078523753436,
+      "grad_norm": 1.84375,
+      "learning_rate": 1.1668907912987037e-05,
+      "loss": 4.2642,
+      "step": 1076
+    },
+    {
+      "epoch": 3.34314880251276,
+      "grad_norm": 1.890625,
+      "learning_rate": 1.1552482860822844e-05,
+      "loss": 4.2815,
+      "step": 1077
+    },
+    {
+      "epoch": 3.3462897526501765,
+      "grad_norm": 1.5703125,
+      "learning_rate": 1.1436605917057996e-05,
+      "loss": 4.2551,
+      "step": 1078
+    },
+    {
+      "epoch": 3.3494307027875934,
+      "grad_norm": 1.7421875,
+      "learning_rate": 1.132127779978086e-05,
+      "loss": 4.0754,
+      "step": 1079
+    },
+    {
+      "epoch": 3.35257165292501,
+      "grad_norm": 1.6328125,
+      "learning_rate": 1.120649922367859e-05,
+      "loss": 4.0919,
+      "step": 1080
+    },
+    {
+      "epoch": 3.3557126030624262,
+      "grad_norm": 1.84375,
+      "learning_rate": 1.109227090003293e-05,
+      "loss": 4.2558,
+      "step": 1081
+    },
+    {
+      "epoch": 3.358853553199843,
+      "grad_norm": 2.03125,
+      "learning_rate": 1.0978593536715654e-05,
+      "loss": 4.2561,
+      "step": 1082
+    },
+    {
+      "epoch": 3.3619945033372596,
+      "grad_norm": 1.8984375,
+      "learning_rate": 1.0865467838184295e-05,
+      "loss": 4.2544,
+      "step": 1083
+    },
+    {
+      "epoch": 3.365135453474676,
+      "grad_norm": 1.6953125,
+      "learning_rate": 1.0752894505477696e-05,
+      "loss": 4.1949,
+      "step": 1084
+    },
+    {
+      "epoch": 3.368276403612093,
+      "grad_norm": 1.953125,
+      "learning_rate": 1.0640874236211718e-05,
+      "loss": 4.1295,
+      "step": 1085
+    },
+    {
+      "epoch": 3.3714173537495093,
+      "grad_norm": 1.4140625,
+      "learning_rate": 1.0529407724574836e-05,
+      "loss": 4.1634,
+      "step": 1086
+    },
+    {
+      "epoch": 3.374558303886926,
+      "grad_norm": 1.71875,
+      "learning_rate": 1.0418495661323979e-05,
+      "loss": 4.2298,
+      "step": 1087
+    },
+    {
+      "epoch": 3.3776992540243422,
+      "grad_norm": 1.890625,
+      "learning_rate": 1.0308138733780071e-05,
+      "loss": 4.1998,
+      "step": 1088
+    },
+    {
+      "epoch": 3.380840204161759,
+      "grad_norm": 1.5703125,
+      "learning_rate": 1.019833762582394e-05,
+      "loss": 4.2761,
+      "step": 1089
+    },
+    {
+      "epoch": 3.3839811542991756,
+      "grad_norm": 1.765625,
+      "learning_rate": 1.0089093017891993e-05,
+      "loss": 4.1777,
+      "step": 1090
+    },
+    {
+      "epoch": 3.387122104436592,
+      "grad_norm": 1.6953125,
+      "learning_rate": 9.980405586971964e-06,
+      "loss": 4.1326,
+      "step": 1091
+    },
+    {
+      "epoch": 3.3902630545740085,
+      "grad_norm": 1.53125,
+      "learning_rate": 9.872276006598823e-06,
+      "loss": 4.0626,
+      "step": 1092
+    },
+    {
+      "epoch": 3.3934040047114253,
+      "grad_norm": 1.390625,
+      "learning_rate": 9.76470494685051e-06,
+      "loss": 4.1737,
+      "step": 1093
+    },
+    {
+      "epoch": 3.396544954848842,
+      "grad_norm": 1.578125,
+      "learning_rate": 9.657693074343865e-06,
+      "loss": 4.1571,
+      "step": 1094
+    },
+    {
+      "epoch": 3.3996859049862582,
+      "grad_norm": 1.609375,
+      "learning_rate": 9.551241052230364e-06,
+      "loss": 4.0783,
+      "step": 1095
+    },
+    {
+      "epoch": 3.402826855123675,
+      "grad_norm": 1.5390625,
+      "learning_rate": 9.445349540192194e-06,
+      "loss": 4.2617,
+      "step": 1096
+    },
+    {
+      "epoch": 3.4059678052610916,
+      "grad_norm": 1.5703125,
+      "learning_rate": 9.340019194437955e-06,
+      "loss": 4.1571,
+      "step": 1097
+    },
+    {
+      "epoch": 3.409108755398508,
+      "grad_norm": 1.5625,
+      "learning_rate": 9.235250667698868e-06,
+      "loss": 4.1136,
+      "step": 1098
+    },
+    {
+      "epoch": 3.4122497055359244,
+      "grad_norm": 1.765625,
+      "learning_rate": 9.131044609224381e-06,
+      "loss": 4.319,
+      "step": 1099
+    },
+    {
+      "epoch": 3.4153906556733413,
+      "grad_norm": 1.65625,
+      "learning_rate": 9.02740166477849e-06,
+      "loss": 4.2387,
+      "step": 1100
+    },
+    {
+      "epoch": 3.4185316058107578,
+      "grad_norm": 1.8203125,
+      "learning_rate": 8.92432247663545e-06,
+      "loss": 4.3449,
+      "step": 1101
+    },
+    {
+      "epoch": 3.421672555948174,
+      "grad_norm": 1.609375,
+      "learning_rate": 8.821807683576e-06,
+      "loss": 4.2561,
+      "step": 1102
+    },
+    {
+      "epoch": 3.4248135060855907,
+      "grad_norm": 1.65625,
+      "learning_rate": 8.719857920883322e-06,
+      "loss": 4.0741,
+      "step": 1103
+    },
+    {
+      "epoch": 3.4279544562230075,
+      "grad_norm": 1.5703125,
+      "learning_rate": 8.618473820339124e-06,
+      "loss": 4.1235,
+      "step": 1104
+    },
+    {
+      "epoch": 3.431095406360424,
+      "grad_norm": 1.78125,
+      "learning_rate": 8.517656010219621e-06,
+      "loss": 4.3383,
+      "step": 1105
+    },
+    {
+      "epoch": 3.4342363564978404,
+      "grad_norm": 1.4609375,
+      "learning_rate": 8.417405115291866e-06,
+      "loss": 4.1615,
+      "step": 1106
+    },
+    {
+      "epoch": 3.4373773066352573,
+      "grad_norm": 1.9296875,
+      "learning_rate": 8.317721756809616e-06,
+      "loss": 4.1065,
+      "step": 1107
+    },
+    {
+      "epoch": 3.4405182567726738,
+      "grad_norm": 1.390625,
+      "learning_rate": 8.2186065525097e-06,
+      "loss": 4.0743,
+      "step": 1108
+    },
+    {
+      "epoch": 3.44365920691009,
+      "grad_norm": 1.734375,
+      "learning_rate": 8.120060116608086e-06,
+      "loss": 4.2119,
+      "step": 1109
+    },
+    {
+      "epoch": 3.446800157047507,
+      "grad_norm": 1.890625,
+      "learning_rate": 8.022083059796038e-06,
+      "loss": 4.0052,
+      "step": 1110
+    },
+    {
+      "epoch": 3.4499411071849235,
+      "grad_norm": 1.8828125,
+      "learning_rate": 7.92467598923643e-06,
+      "loss": 4.0728,
+      "step": 1111
+    },
+    {
+      "epoch": 3.45308205732234,
+      "grad_norm": 2.453125,
+      "learning_rate": 7.827839508559932e-06,
+      "loss": 4.0244,
+      "step": 1112
+    },
+    {
+      "epoch": 3.4562230074597564,
+      "grad_norm": 1.7421875,
+      "learning_rate": 7.731574217861293e-06,
+      "loss": 4.1905,
+      "step": 1113
+    },
+    {
+      "epoch": 3.4593639575971733,
+      "grad_norm": 1.515625,
+      "learning_rate": 7.63588071369553e-06,
+      "loss": 4.0486,
+      "step": 1114
+    },
+    {
+      "epoch": 3.4625049077345897,
+      "grad_norm": 1.59375,
+      "learning_rate": 7.540759589074398e-06,
+      "loss": 4.1157,
+      "step": 1115
+    },
+    {
+      "epoch": 3.465645857872006,
+      "grad_norm": 1.71875,
+      "learning_rate": 7.446211433462535e-06,
+      "loss": 3.9553,
+      "step": 1116
+    },
+    {
+      "epoch": 3.4687868080094226,
+      "grad_norm": 1.453125,
+      "learning_rate": 7.352236832773973e-06,
+      "loss": 4.1804,
+      "step": 1117
+    },
+    {
+      "epoch": 3.4719277581468395,
+      "grad_norm": 1.5234375,
+      "learning_rate": 7.258836369368371e-06,
+      "loss": 4.0565,
+      "step": 1118
+    },
+    {
+      "epoch": 3.475068708284256,
+      "grad_norm": 2.0625,
+      "learning_rate": 7.166010622047515e-06,
+      "loss": 4.3231,
+      "step": 1119
+    },
+    {
+      "epoch": 3.4782096584216724,
+      "grad_norm": 1.9140625,
+      "learning_rate": 7.073760166051613e-06,
+      "loss": 4.1996,
+      "step": 1120
+    },
+    {
+      "epoch": 3.4782096584216724,
+      "eval_loss": 4.326785564422607,
+      "eval_runtime": 66.7757,
+      "eval_samples_per_second": 38.951,
+      "eval_steps_per_second": 38.951,
+      "step": 1120
+    },
+    {
+      "epoch": 3.4813506085590893,
+      "grad_norm": 1.5234375,
+      "learning_rate": 6.982085573055885e-06,
+      "loss": 4.1893,
+      "step": 1121
+    },
+    {
+      "epoch": 3.4844915586965057,
+      "grad_norm": 1.65625,
+      "learning_rate": 6.890987411166838e-06,
+      "loss": 4.2086,
+      "step": 1122
+    },
+    {
+      "epoch": 3.487632508833922,
+      "grad_norm": 1.8203125,
+      "learning_rate": 6.800466244918946e-06,
+      "loss": 4.3012,
+      "step": 1123
+    },
+    {
+      "epoch": 3.490773458971339,
+      "grad_norm": 1.5703125,
+      "learning_rate": 6.710522635270943e-06,
+      "loss": 3.8971,
+      "step": 1124
+    },
+    {
+      "epoch": 3.4939144091087555,
+      "grad_norm": 1.7578125,
+      "learning_rate": 6.621157139602552e-06,
+      "loss": 4.2582,
+      "step": 1125
+    },
+    {
+      "epoch": 3.497055359246172,
+      "grad_norm": 1.40625,
+      "learning_rate": 6.532370311710811e-06,
+      "loss": 4.168,
+      "step": 1126
+    },
+    {
+      "epoch": 3.5001963093835884,
+      "grad_norm": 1.890625,
+      "learning_rate": 6.444162701806866e-06,
+      "loss": 4.1039,
+      "step": 1127
+    },
+    {
+      "epoch": 3.503337259521005,
+      "grad_norm": 1.4921875,
+      "learning_rate": 6.35653485651242e-06,
+      "loss": 4.1259,
+      "step": 1128
+    },
+    {
+      "epoch": 3.5064782096584217,
+      "grad_norm": 1.5,
+      "learning_rate": 6.269487318856348e-06,
+      "loss": 3.8226,
+      "step": 1129
+    },
+    {
+      "epoch": 3.509619159795838,
+      "grad_norm": 1.9375,
+      "learning_rate": 6.183020628271397e-06,
+      "loss": 4.2257,
+      "step": 1130
+    },
+    {
+      "epoch": 3.5127601099332546,
+      "grad_norm": 1.625,
+      "learning_rate": 6.09713532059083e-06,
+      "loss": 4.024,
+      "step": 1131
+    },
+    {
+      "epoch": 3.5159010600706715,
+      "grad_norm": 1.53125,
+      "learning_rate": 6.011831928045019e-06,
+      "loss": 3.7863,
+      "step": 1132
+    },
+    {
+      "epoch": 3.519042010208088,
+      "grad_norm": 1.4609375,
+      "learning_rate": 5.927110979258266e-06,
+      "loss": 4.1759,
+      "step": 1133
+    },
+    {
+      "epoch": 3.5221829603455044,
+      "grad_norm": 1.453125,
+      "learning_rate": 5.8429729992455e-06,
+      "loss": 4.2777,
+      "step": 1134
+    },
+    {
+      "epoch": 3.5253239104829213,
+      "grad_norm": 1.53125,
+      "learning_rate": 5.759418509408898e-06,
+      "loss": 4.2055,
+      "step": 1135
+    },
+    {
+      "epoch": 3.5284648606203377,
+      "grad_norm": 1.3671875,
+      "learning_rate": 5.676448027534875e-06,
+      "loss": 4.1961,
+      "step": 1136
+    },
+    {
+      "epoch": 3.531605810757754,
+      "grad_norm": 1.8359375,
+      "learning_rate": 5.594062067790639e-06,
+      "loss": 4.2919,
+      "step": 1137
+    },
+    {
+      "epoch": 3.534746760895171,
+      "grad_norm": 1.625,
+      "learning_rate": 5.512261140721242e-06,
+      "loss": 4.1412,
+      "step": 1138
+    },
+    {
+      "epoch": 3.5378877110325875,
+      "grad_norm": 1.7734375,
+      "learning_rate": 5.431045753246178e-06,
+      "loss": 4.2442,
+      "step": 1139
+    },
+    {
+      "epoch": 3.541028661170004,
+      "grad_norm": 1.6796875,
+      "learning_rate": 5.3504164086564555e-06,
+      "loss": 4.2496,
+      "step": 1140
+    },
+    {
+      "epoch": 3.5441696113074204,
+      "grad_norm": 1.8984375,
+      "learning_rate": 5.270373606611279e-06,
+      "loss": 4.2678,
+      "step": 1141
+    },
+    {
+      "epoch": 3.547310561444837,
+      "grad_norm": 1.7265625,
+      "learning_rate": 5.190917843135146e-06,
+      "loss": 4.2066,
+      "step": 1142
+    },
+    {
+      "epoch": 3.5504515115822537,
+      "grad_norm": 1.6796875,
+      "learning_rate": 5.112049610614633e-06,
+      "loss": 4.0248,
+      "step": 1143
+    },
+    {
+      "epoch": 3.55359246171967,
+      "grad_norm": 1.5546875,
+      "learning_rate": 5.03376939779544e-06,
+      "loss": 4.177,
+      "step": 1144
+    },
+    {
+      "epoch": 3.5567334118570866,
+      "grad_norm": 1.546875,
+      "learning_rate": 4.956077689779226e-06,
+      "loss": 4.1477,
+      "step": 1145
+    },
+    {
+      "epoch": 3.5598743619945035,
+      "grad_norm": 1.6328125,
+      "learning_rate": 4.8789749680208e-06,
+      "loss": 4.1964,
+      "step": 1146
+    },
+    {
+      "epoch": 3.56301531213192,
+      "grad_norm": 1.3984375,
+      "learning_rate": 4.802461710324935e-06,
+      "loss": 4.2276,
+      "step": 1147
+    },
+    {
+      "epoch": 3.5661562622693364,
+      "grad_norm": 1.7421875,
+      "learning_rate": 4.726538390843549e-06,
+      "loss": 4.3629,
+      "step": 1148
+    },
+    {
+      "epoch": 3.5692972124067532,
+      "grad_norm": 1.6640625,
+      "learning_rate": 4.651205480072718e-06,
+      "loss": 4.2507,
+      "step": 1149
+    },
+    {
+      "epoch": 3.5724381625441697,
+      "grad_norm": 1.578125,
+      "learning_rate": 4.576463444849777e-06,
+      "loss": 4.1543,
+      "step": 1150
+    },
+    {
+      "epoch": 3.575579112681586,
+      "grad_norm": 1.8046875,
+      "learning_rate": 4.502312748350346e-06,
+      "loss": 4.0743,
+      "step": 1151
+    },
+    {
+      "epoch": 3.578720062819003,
+      "grad_norm": 1.75,
+      "learning_rate": 4.4287538500855765e-06,
+      "loss": 4.328,
+      "step": 1152
+    },
+    {
+      "epoch": 3.5818610129564195,
+      "grad_norm": 1.6796875,
+      "learning_rate": 4.355787205899275e-06,
+      "loss": 4.1289,
+      "step": 1153
+    },
+    {
+      "epoch": 3.585001963093836,
+      "grad_norm": 1.765625,
+      "learning_rate": 4.283413267964986e-06,
+      "loss": 4.2617,
+      "step": 1154
+    },
+    {
+      "epoch": 3.5881429132312523,
+      "grad_norm": 1.4296875,
+      "learning_rate": 4.2116324847833125e-06,
+      "loss": 4.1358,
+      "step": 1155
+    },
+    {
+      "epoch": 3.591283863368669,
+      "grad_norm": 1.8046875,
+      "learning_rate": 4.140445301179052e-06,
+      "loss": 4.22,
+      "step": 1156
+    },
+    {
+      "epoch": 3.5944248135060857,
+      "grad_norm": 1.546875,
+      "learning_rate": 4.069852158298493e-06,
+      "loss": 4.3349,
+      "step": 1157
+    },
+    {
+      "epoch": 3.597565763643502,
+      "grad_norm": 1.6328125,
+      "learning_rate": 3.999853493606665e-06,
+      "loss": 4.2548,
+      "step": 1158
+    },
+    {
+      "epoch": 3.6007067137809186,
+      "grad_norm": 1.7109375,
+      "learning_rate": 3.930449740884601e-06,
+      "loss": 4.2736,
+      "step": 1159
+    },
+    {
+      "epoch": 3.6038476639183354,
+      "grad_norm": 1.515625,
+      "learning_rate": 3.861641330226673e-06,
+      "loss": 4.2242,
+      "step": 1160
+    },
+    {
+      "epoch": 3.606988614055752,
+      "grad_norm": 1.484375,
+      "learning_rate": 3.7934286880379368e-06,
+      "loss": 4.1619,
+      "step": 1161
+    },
+    {
+      "epoch": 3.6101295641931683,
+      "grad_norm": 1.78125,
+      "learning_rate": 3.725812237031445e-06,
+      "loss": 4.0524,
+      "step": 1162
+    },
+    {
+      "epoch": 3.613270514330585,
+      "grad_norm": 1.65625,
+      "learning_rate": 3.6587923962257186e-06,
+      "loss": 4.2704,
+      "step": 1163
+    },
+    {
+      "epoch": 3.6164114644680017,
+      "grad_norm": 1.6953125,
+      "learning_rate": 3.5923695809420454e-06,
+      "loss": 4.1879,
+      "step": 1164
+    },
+    {
+      "epoch": 3.619552414605418,
+      "grad_norm": 2.03125,
+      "learning_rate": 3.5265442028019514e-06,
+      "loss": 4.2741,
+      "step": 1165
+    },
+    {
+      "epoch": 3.6226933647428345,
+      "grad_norm": 1.5390625,
+      "learning_rate": 3.461316669724668e-06,
+      "loss": 4.0975,
+      "step": 1166
+    },
+    {
+      "epoch": 3.6258343148802514,
+      "grad_norm": 1.5234375,
+      "learning_rate": 3.3966873859245796e-06,
+      "loss": 4.2496,
+      "step": 1167
+    },
+    {
+      "epoch": 3.628975265017668,
+      "grad_norm": 1.625,
+      "learning_rate": 3.332656751908736e-06,
+      "loss": 4.2043,
+      "step": 1168
+    },
+    {
+      "epoch": 3.6321162151550843,
+      "grad_norm": 2.09375,
+      "learning_rate": 3.2692251644743433e-06,
+      "loss": 4.0308,
+      "step": 1169
+    },
+    {
+      "epoch": 3.6352571652925008,
+      "grad_norm": 1.5078125,
+      "learning_rate": 3.2063930167063217e-06,
+      "loss": 4.2563,
+      "step": 1170
+    },
+    {
+      "epoch": 3.6383981154299176,
+      "grad_norm": 1.7265625,
+      "learning_rate": 3.144160697974885e-06,
+      "loss": 4.149,
+      "step": 1171
+    },
+    {
+      "epoch": 3.641539065567334,
+      "grad_norm": 1.5234375,
+      "learning_rate": 3.0825285939331093e-06,
+      "loss": 4.254,
+      "step": 1172
+    },
+    {
+      "epoch": 3.6446800157047505,
+      "grad_norm": 1.5,
+      "learning_rate": 3.0214970865145242e-06,
+      "loss": 4.144,
+      "step": 1173
+    },
+    {
+      "epoch": 3.6478209658421674,
+      "grad_norm": 1.703125,
+      "learning_rate": 2.9610665539308024e-06,
+      "loss": 4.2406,
+      "step": 1174
+    },
+    {
+      "epoch": 3.650961915979584,
+      "grad_norm": 1.8671875,
+      "learning_rate": 2.901237370669352e-06,
+      "loss": 4.2183,
+      "step": 1175
+    },
+    {
+      "epoch": 3.6541028661170003,
+      "grad_norm": 1.5625,
+      "learning_rate": 2.842009907491039e-06,
+      "loss": 4.2395,
+      "step": 1176
+    },
+    {
+      "epoch": 3.657243816254417,
+      "grad_norm": 1.7109375,
+      "learning_rate": 2.7833845314278683e-06,
+      "loss": 4.0188,
+      "step": 1177
+    },
+    {
+      "epoch": 3.6603847663918336,
+      "grad_norm": 1.703125,
+      "learning_rate": 2.725361605780752e-06,
+      "loss": 4.034,
+      "step": 1178
+    },
+    {
+      "epoch": 3.66352571652925,
+      "grad_norm": 1.6640625,
+      "learning_rate": 2.667941490117154e-06,
+      "loss": 3.9543,
+      "step": 1179
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "grad_norm": 1.8125,
+      "learning_rate": 2.6111245402689943e-06,
+      "loss": 4.0805,
+      "step": 1180
+    },
+    {
+      "epoch": 3.669807616804083,
+      "grad_norm": 1.765625,
+      "learning_rate": 2.5549111083303377e-06,
+      "loss": 4.2029,
+      "step": 1181
+    },
+    {
+      "epoch": 3.6729485669415,
+      "grad_norm": 1.703125,
+      "learning_rate": 2.4993015426552967e-06,
+      "loss": 4.2688,
+      "step": 1182
+    },
+    {
+      "epoch": 3.6760895170789163,
+      "grad_norm": 1.46875,
+      "learning_rate": 2.4442961878557877e-06,
+      "loss": 4.1201,
+      "step": 1183
+    },
+    {
+      "epoch": 3.6792304672163327,
+      "grad_norm": 1.5078125,
+      "learning_rate": 2.3898953847994788e-06,
+      "loss": 4.2067,
+      "step": 1184
+    },
+    {
+      "epoch": 3.6823714173537496,
+      "grad_norm": 1.578125,
+      "learning_rate": 2.336099470607578e-06,
+      "loss": 4.1945,
+      "step": 1185
+    },
+    {
+      "epoch": 3.685512367491166,
+      "grad_norm": 1.6328125,
+      "learning_rate": 2.28290877865287e-06,
+      "loss": 4.172,
+      "step": 1186
+    },
+    {
+      "epoch": 3.6886533176285825,
+      "grad_norm": 1.5625,
+      "learning_rate": 2.230323638557541e-06,
+      "loss": 4.2327,
+      "step": 1187
+    },
+    {
+      "epoch": 3.6917942677659994,
+      "grad_norm": 1.515625,
+      "learning_rate": 2.178344376191199e-06,
+      "loss": 3.9384,
+      "step": 1188
+    },
+    {
+      "epoch": 3.694935217903416,
+      "grad_norm": 1.59375,
+      "learning_rate": 2.126971313668813e-06,
+      "loss": 4.1515,
+      "step": 1189
+    },
+    {
+      "epoch": 3.6980761680408323,
+      "grad_norm": 1.71875,
+      "learning_rate": 2.076204769348766e-06,
+      "loss": 4.0155,
+      "step": 1190
+    },
+    {
+      "epoch": 3.701217118178249,
+      "grad_norm": 1.6640625,
+      "learning_rate": 2.0260450578308165e-06,
+      "loss": 4.2448,
+      "step": 1191
+    },
+    {
+      "epoch": 3.7043580683156656,
+      "grad_norm": 1.59375,
+      "learning_rate": 1.976492489954207e-06,
+      "loss": 4.0541,
+      "step": 1192
+    },
+    {
+      "epoch": 3.707499018453082,
+      "grad_norm": 1.8671875,
+      "learning_rate": 1.927547372795746e-06,
+      "loss": 4.3356,
+      "step": 1193
+    },
+    {
+      "epoch": 3.7106399685904985,
+      "grad_norm": 1.703125,
+      "learning_rate": 1.87921000966782e-06,
+      "loss": 4.2553,
+      "step": 1194
+    },
+    {
+      "epoch": 3.713780918727915,
+      "grad_norm": 1.7109375,
+      "learning_rate": 1.8314807001165945e-06,
+      "loss": 4.375,
+      "step": 1195
+    },
+    {
+      "epoch": 3.716921868865332,
+      "grad_norm": 1.6015625,
+      "learning_rate": 1.7843597399201384e-06,
+      "loss": 4.1357,
+      "step": 1196
+    },
+    {
+      "epoch": 3.7200628190027483,
+      "grad_norm": 1.984375,
+      "learning_rate": 1.7378474210866024e-06,
+      "loss": 4.2837,
+      "step": 1197
+    },
+    {
+      "epoch": 3.7232037691401647,
+      "grad_norm": 1.796875,
+      "learning_rate": 1.6919440318523439e-06,
+      "loss": 3.9198,
+      "step": 1198
+    },
+    {
+      "epoch": 3.7263447192775816,
+      "grad_norm": 1.9609375,
+      "learning_rate": 1.646649856680238e-06,
+      "loss": 4.3536,
+      "step": 1199
+    },
+    {
+      "epoch": 3.729485669414998,
+      "grad_norm": 1.6171875,
+      "learning_rate": 1.6019651762578247e-06,
+      "loss": 4.1353,
+      "step": 1200
+    },
+    {
+      "epoch": 3.729485669414998,
+      "eval_loss": 4.326460838317871,
+      "eval_runtime": 66.997,
+      "eval_samples_per_second": 38.823,
+      "eval_steps_per_second": 38.823,
+      "step": 1200
+    },
+    {
+      "epoch": 3.7326266195524145,
+      "grad_norm": 1.6953125,
+      "learning_rate": 1.5578902674956431e-06,
+      "loss": 4.1998,
+      "step": 1201
+    },
+    {
+      "epoch": 3.7357675696898314,
+      "grad_norm": 1.9453125,
+      "learning_rate": 1.5144254035254658e-06,
+      "loss": 4.3635,
+      "step": 1202
+    },
+    {
+      "epoch": 3.738908519827248,
+      "grad_norm": 1.6796875,
+      "learning_rate": 1.4715708536986561e-06,
+      "loss": 4.1042,
+      "step": 1203
+    },
+    {
+      "epoch": 3.7420494699646643,
+      "grad_norm": 1.4375,
+      "learning_rate": 1.4293268835844032e-06,
+      "loss": 4.148,
+      "step": 1204
+    },
+    {
+      "epoch": 3.745190420102081,
+      "grad_norm": 1.875,
+      "learning_rate": 1.3876937549682e-06,
+      "loss": 4.1733,
+      "step": 1205
+    },
+    {
+      "epoch": 3.7483313702394976,
+      "grad_norm": 1.84375,
+      "learning_rate": 1.3466717258501238e-06,
+      "loss": 4.3636,
+      "step": 1206
+    },
+    {
+      "epoch": 3.751472320376914,
+      "grad_norm": 1.515625,
+      "learning_rate": 1.3062610504433138e-06,
+      "loss": 4.2977,
+      "step": 1207
+    },
+    {
+      "epoch": 3.7546132705143305,
+      "grad_norm": 1.4453125,
+      "learning_rate": 1.2664619791723065e-06,
+      "loss": 4.1444,
+      "step": 1208
+    },
+    {
+      "epoch": 3.757754220651747,
+      "grad_norm": 1.8671875,
+      "learning_rate": 1.2272747586715595e-06,
+      "loss": 4.3564,
+      "step": 1209
+    },
+    {
+      "epoch": 3.760895170789164,
+      "grad_norm": 1.765625,
+      "learning_rate": 1.1886996317839072e-06,
+      "loss": 4.3292,
+      "step": 1210
+    },
+    {
+      "epoch": 3.7640361209265802,
+      "grad_norm": 1.890625,
+      "learning_rate": 1.1507368375590188e-06,
+      "loss": 4.27,
+      "step": 1211
+    },
+    {
+      "epoch": 3.7671770710639967,
+      "grad_norm": 1.7421875,
+      "learning_rate": 1.1133866112519765e-06,
+      "loss": 4.3166,
+      "step": 1212
+    },
+    {
+      "epoch": 3.7703180212014136,
+      "grad_norm": 1.515625,
+      "learning_rate": 1.076649184321754e-06,
+      "loss": 4.1983,
+      "step": 1213
+    },
+    {
+      "epoch": 3.77345897133883,
+      "grad_norm": 1.640625,
+      "learning_rate": 1.0405247844298304e-06,
+      "loss": 4.206,
+      "step": 1214
+    },
+    {
+      "epoch": 3.7765999214762465,
+      "grad_norm": 1.59375,
+      "learning_rate": 1.0050136354387562e-06,
+      "loss": 4.2733,
+      "step": 1215
+    },
+    {
+      "epoch": 3.7797408716136633,
+      "grad_norm": 1.3203125,
+      "learning_rate": 9.701159574107888e-07,
+      "loss": 3.8592,
+      "step": 1216
+    },
+    {
+      "epoch": 3.78288182175108,
+      "grad_norm": 1.5703125,
+      "learning_rate": 9.358319666064707e-07,
+      "loss": 4.3302,
+      "step": 1217
+    },
+    {
+      "epoch": 3.7860227718884962,
+      "grad_norm": 1.828125,
+      "learning_rate": 9.021618754833872e-07,
+      "loss": 4.2051,
+      "step": 1218
+    },
+    {
+      "epoch": 3.7891637220259127,
+      "grad_norm": 1.5390625,
+      "learning_rate": 8.691058926947548e-07,
+      "loss": 4.0777,
+      "step": 1219
+    },
+    {
+      "epoch": 3.7923046721633296,
+      "grad_norm": 1.5546875,
+      "learning_rate": 8.366642230881683e-07,
+      "loss": 4.3087,
+      "step": 1220
+    },
+    {
+      "epoch": 3.795445622300746,
+      "grad_norm": 1.59375,
+      "learning_rate": 8.048370677043337e-07,
+      "loss": 4.1274,
+      "step": 1221
+    },
+    {
+      "epoch": 3.7985865724381624,
+      "grad_norm": 1.703125,
+      "learning_rate": 7.736246237758371e-07,
+      "loss": 4.0938,
+      "step": 1222
+    },
+    {
+      "epoch": 3.801727522575579,
+      "grad_norm": 1.6171875,
+      "learning_rate": 7.43027084725878e-07,
+      "loss": 3.9833,
+      "step": 1223
+    },
+    {
+      "epoch": 3.8048684727129958,
+      "grad_norm": 1.84375,
+      "learning_rate": 7.130446401671154e-07,
+      "loss": 4.0335,
+      "step": 1224
+    },
+    {
+      "epoch": 3.808009422850412,
+      "grad_norm": 1.7734375,
+      "learning_rate": 6.836774759004572e-07,
+      "loss": 4.2315,
+      "step": 1225
+    },
+    {
+      "epoch": 3.8111503729878287,
+      "grad_norm": 1.6640625,
+      "learning_rate": 6.549257739139281e-07,
+      "loss": 4.0972,
+      "step": 1226
+    },
+    {
+      "epoch": 3.8142913231252455,
+      "grad_norm": 1.5546875,
+      "learning_rate": 6.267897123815592e-07,
+      "loss": 4.1666,
+      "step": 1227
+    },
+    {
+      "epoch": 3.817432273262662,
+      "grad_norm": 2.046875,
+      "learning_rate": 5.992694656622444e-07,
+      "loss": 4.2027,
+      "step": 1228
+    },
+    {
+      "epoch": 3.8205732234000784,
+      "grad_norm": 1.7109375,
+      "learning_rate": 5.723652042986749e-07,
+      "loss": 4.1349,
+      "step": 1229
+    },
+    {
+      "epoch": 3.8237141735374953,
+      "grad_norm": 1.609375,
+      "learning_rate": 5.460770950163063e-07,
+      "loss": 4.2145,
+      "step": 1230
+    },
+    {
+      "epoch": 3.8268551236749118,
+      "grad_norm": 2.078125,
+      "learning_rate": 5.204053007222931e-07,
+      "loss": 4.3372,
+      "step": 1231
+    },
+    {
+      "epoch": 3.829996073812328,
+      "grad_norm": 1.671875,
+      "learning_rate": 4.953499805044781e-07,
+      "loss": 4.149,
+      "step": 1232
+    },
+    {
+      "epoch": 3.8331370239497446,
+      "grad_norm": 1.796875,
+      "learning_rate": 4.7091128963046017e-07,
+      "loss": 4.2256,
+      "step": 1233
+    },
+    {
+      "epoch": 3.836277974087161,
+      "grad_norm": 1.8125,
+      "learning_rate": 4.4708937954655027e-07,
+      "loss": 4.2696,
+      "step": 1234
+    },
+    {
+      "epoch": 3.839418924224578,
+      "grad_norm": 1.6328125,
+      "learning_rate": 4.238843978769058e-07,
+      "loss": 4.2011,
+      "step": 1235
+    },
+    {
+      "epoch": 3.8425598743619944,
+      "grad_norm": 1.5703125,
+      "learning_rate": 4.012964884225534e-07,
+      "loss": 4.3169,
+      "step": 1236
+    },
+    {
+      "epoch": 3.845700824499411,
+      "grad_norm": 1.640625,
+      "learning_rate": 3.7932579116056746e-07,
+      "loss": 4.073,
+      "step": 1237
+    },
+    {
+      "epoch": 3.8488417746368278,
+      "grad_norm": 1.5703125,
+      "learning_rate": 3.5797244224312634e-07,
+      "loss": 4.1951,
+      "step": 1238
+    },
+    {
+      "epoch": 3.851982724774244,
+      "grad_norm": 1.453125,
+      "learning_rate": 3.372365739967465e-07,
+      "loss": 4.0191,
+      "step": 1239
+    },
+    {
+      "epoch": 3.8551236749116606,
+      "grad_norm": 1.453125,
+      "learning_rate": 3.171183149213719e-07,
+      "loss": 4.2124,
+      "step": 1240
+    },
+    {
+      "epoch": 3.8582646250490775,
+      "grad_norm": 2.203125,
+      "learning_rate": 2.976177896896748e-07,
+      "loss": 4.0027,
+      "step": 1241
+    },
+    {
+      "epoch": 3.861405575186494,
+      "grad_norm": 1.609375,
+      "learning_rate": 2.7873511914622287e-07,
+      "loss": 4.1294,
+      "step": 1242
+    },
+    {
+      "epoch": 3.8645465253239104,
+      "grad_norm": 1.6328125,
+      "learning_rate": 2.604704203067354e-07,
+      "loss": 4.1489,
+      "step": 1243
+    },
+    {
+      "epoch": 3.8676874754613273,
+      "grad_norm": 1.4453125,
+      "learning_rate": 2.428238063573618e-07,
+      "loss": 4.0815,
+      "step": 1244
+    },
+    {
+      "epoch": 3.8708284255987437,
+      "grad_norm": 1.484375,
+      "learning_rate": 2.2579538665401522e-07,
+      "loss": 4.2234,
+      "step": 1245
+    },
+    {
+      "epoch": 3.87396937573616,
+      "grad_norm": 1.65625,
+      "learning_rate": 2.0938526672164005e-07,
+      "loss": 4.1228,
+      "step": 1246
+    },
+    {
+      "epoch": 3.8771103258735766,
+      "grad_norm": 1.6796875,
+      "learning_rate": 1.9359354825359e-07,
+      "loss": 4.1091,
+      "step": 1247
+    },
+    {
+      "epoch": 3.880251276010993,
+      "grad_norm": 1.8203125,
+      "learning_rate": 1.7842032911097318e-07,
+      "loss": 4.1812,
+      "step": 1248
+    },
+    {
+      "epoch": 3.88339222614841,
+      "grad_norm": 1.390625,
+      "learning_rate": 1.6386570332210805e-07,
+      "loss": 4.2918,
+      "step": 1249
+    },
+    {
+      "epoch": 3.8865331762858264,
+      "grad_norm": 1.6328125,
+      "learning_rate": 1.499297610818573e-07,
+      "loss": 4.2765,
+      "step": 1250
+    },
+    {
+      "epoch": 3.889674126423243,
+      "grad_norm": 1.4140625,
+      "learning_rate": 1.3661258875110606e-07,
+      "loss": 4.1765,
+      "step": 1251
+    },
+    {
+      "epoch": 3.8928150765606597,
+      "grad_norm": 1.640625,
+      "learning_rate": 1.2391426885625113e-07,
+      "loss": 4.1201,
+      "step": 1252
+    },
+    {
+      "epoch": 3.895956026698076,
+      "grad_norm": 1.71875,
+      "learning_rate": 1.1183488008865706e-07,
+      "loss": 4.046,
+      "step": 1253
+    },
+    {
+      "epoch": 3.8990969768354926,
+      "grad_norm": 1.7421875,
+      "learning_rate": 1.0037449730418979e-07,
+      "loss": 4.2988,
+      "step": 1254
+    },
+    {
+      "epoch": 3.9022379269729095,
+      "grad_norm": 1.71875,
+      "learning_rate": 8.953319152270601e-08,
+      "loss": 4.27,
+      "step": 1255
+    },
+    {
+      "epoch": 3.905378877110326,
+      "grad_norm": 1.4375,
+      "learning_rate": 7.931102992768668e-08,
+      "loss": 4.2225,
+      "step": 1256
+    },
+    {
+      "epoch": 3.9085198272477424,
+      "grad_norm": 1.84375,
+      "learning_rate": 6.970807586575979e-08,
+      "loss": 4.1857,
+      "step": 1257
+    },
+    {
+      "epoch": 3.9116607773851593,
+      "grad_norm": 1.7734375,
+      "learning_rate": 6.07243888463449e-08,
+      "loss": 4.1805,
+      "step": 1258
+    },
+    {
+      "epoch": 3.9148017275225757,
+      "grad_norm": 1.59375,
+      "learning_rate": 5.236002454126476e-08,
+      "loss": 4.2557,
+      "step": 1259
+    },
+    {
+      "epoch": 3.917942677659992,
+      "grad_norm": 1.640625,
+      "learning_rate": 4.461503478438989e-08,
+      "loss": 4.2616,
+      "step": 1260
+    },
+    {
+      "epoch": 3.9210836277974086,
+      "grad_norm": 1.6796875,
+      "learning_rate": 3.748946757136107e-08,
+      "loss": 4.3122,
+      "step": 1261
+    },
+    {
+      "epoch": 3.924224577934825,
+      "grad_norm": 1.84375,
+      "learning_rate": 3.09833670592341e-08,
+      "loss": 4.1215,
+      "step": 1262
+    },
+    {
+      "epoch": 3.927365528072242,
+      "grad_norm": 1.46875,
+      "learning_rate": 2.509677356626883e-08,
+      "loss": 4.114,
+      "step": 1263
+    },
+    {
+      "epoch": 3.9305064782096584,
+      "grad_norm": 1.7578125,
+      "learning_rate": 1.9829723571607172e-08,
+      "loss": 4.1706,
+      "step": 1264
+    },
+    {
+      "epoch": 3.933647428347075,
+      "grad_norm": 1.46875,
+      "learning_rate": 1.5182249715117723e-08,
+      "loss": 4.0536,
+      "step": 1265
+    },
+    {
+      "epoch": 3.9367883784844917,
+      "grad_norm": 2.03125,
+      "learning_rate": 1.1154380797151475e-08,
+      "loss": 4.2994,
+      "step": 1266
+    },
+    {
+      "epoch": 3.939929328621908,
+      "grad_norm": 1.578125,
+      "learning_rate": 7.746141778375293e-09,
+      "loss": 4.0,
+      "step": 1267
+    },
+    {
+      "epoch": 3.9430702787593246,
+      "grad_norm": 1.5,
+      "learning_rate": 4.957553779594282e-09,
+      "loss": 4.1225,
+      "step": 1268
+    },
+    {
+      "epoch": 3.9462112288967415,
+      "grad_norm": 1.4921875,
+      "learning_rate": 2.788634081685171e-09,
+      "loss": 4.1343,
+      "step": 1269
+    },
+    {
+      "epoch": 3.949352179034158,
+      "grad_norm": 1.609375,
+      "learning_rate": 1.2393961254186792e-09,
+      "loss": 4.2058,
+      "step": 1270
+    },
+    {
+      "epoch": 3.9524931291715744,
+      "grad_norm": 1.6171875,
+      "learning_rate": 3.0984951138179897e-10,
+      "loss": 4.2778,
+      "step": 1271
+    },
+    {
+      "epoch": 3.9556340793089912,
+      "grad_norm": 1.4140625,
+      "learning_rate": 0.0,
+      "loss": 4.0657,
+      "step": 1272
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1272,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 318,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.942252132338237e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}