{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.995850622406639,
  "eval_steps": 500,
  "global_step": 120,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008298755186721992,
      "grad_norm": 0.80859375,
      "learning_rate": 8.695652173913044e-06,
      "loss": 2.3455,
      "step": 1
    },
    {
      "epoch": 0.016597510373443983,
      "grad_norm": 0.78125,
      "learning_rate": 1.739130434782609e-05,
      "loss": 2.2601,
      "step": 2
    },
    {
      "epoch": 0.024896265560165973,
      "grad_norm": 0.75390625,
      "learning_rate": 2.608695652173913e-05,
      "loss": 2.2494,
      "step": 3
    },
    {
      "epoch": 0.03319502074688797,
      "grad_norm": 0.8046875,
      "learning_rate": 3.478260869565218e-05,
      "loss": 2.2988,
      "step": 4
    },
    {
      "epoch": 0.04149377593360996,
      "grad_norm": 0.95703125,
      "learning_rate": 4.347826086956522e-05,
      "loss": 3.0938,
      "step": 5
    },
    {
      "epoch": 0.04979253112033195,
      "grad_norm": 0.7578125,
      "learning_rate": 5.217391304347826e-05,
      "loss": 2.1633,
      "step": 6
    },
    {
      "epoch": 0.058091286307053944,
      "grad_norm": 0.7421875,
      "learning_rate": 6.086956521739131e-05,
      "loss": 2.1488,
      "step": 7
    },
    {
      "epoch": 0.06639004149377593,
      "grad_norm": 0.62109375,
      "learning_rate": 6.956521739130436e-05,
      "loss": 2.0031,
      "step": 8
    },
    {
      "epoch": 0.07468879668049792,
      "grad_norm": 0.52734375,
      "learning_rate": 7.82608695652174e-05,
      "loss": 1.9347,
      "step": 9
    },
    {
      "epoch": 0.08298755186721991,
      "grad_norm": 0.369140625,
      "learning_rate": 8.695652173913044e-05,
      "loss": 1.8457,
      "step": 10
    },
    {
      "epoch": 0.0912863070539419,
      "grad_norm": 0.357421875,
      "learning_rate": 9.565217391304348e-05,
      "loss": 1.7273,
      "step": 11
    },
    {
      "epoch": 0.0995850622406639,
      "grad_norm": 0.376953125,
      "learning_rate": 0.00010434782608695653,
      "loss": 1.7584,
      "step": 12
    },
    {
      "epoch": 0.1078838174273859,
      "grad_norm": 0.39453125,
      "learning_rate": 0.00011304347826086956,
      "loss": 1.6387,
      "step": 13
    },
    {
      "epoch": 0.11618257261410789,
      "grad_norm": 0.458984375,
      "learning_rate": 0.00012173913043478263,
      "loss": 1.6614,
      "step": 14
    },
    {
      "epoch": 0.12448132780082988,
      "grad_norm": 0.482421875,
      "learning_rate": 0.00013043478260869567,
      "loss": 1.648,
      "step": 15
    },
    {
      "epoch": 0.13278008298755187,
      "grad_norm": 0.447265625,
      "learning_rate": 0.0001391304347826087,
      "loss": 1.6337,
      "step": 16
    },
    {
      "epoch": 0.14107883817427386,
      "grad_norm": 0.37109375,
      "learning_rate": 0.00014782608695652173,
      "loss": 1.6004,
      "step": 17
    },
    {
      "epoch": 0.14937759336099585,
      "grad_norm": 0.41796875,
      "learning_rate": 0.0001565217391304348,
      "loss": 1.6146,
      "step": 18
    },
    {
      "epoch": 0.15767634854771784,
      "grad_norm": 0.38671875,
      "learning_rate": 0.00016521739130434784,
      "loss": 1.4754,
      "step": 19
    },
    {
      "epoch": 0.16597510373443983,
      "grad_norm": 1.890625,
      "learning_rate": 0.00017391304347826088,
      "loss": 2.4256,
      "step": 20
    },
    {
      "epoch": 0.17427385892116182,
      "grad_norm": 0.296875,
      "learning_rate": 0.00018260869565217392,
      "loss": 1.4601,
      "step": 21
    },
    {
      "epoch": 0.1825726141078838,
      "grad_norm": 0.291015625,
      "learning_rate": 0.00019130434782608697,
      "loss": 1.4737,
      "step": 22
    },
    {
      "epoch": 0.1908713692946058,
      "grad_norm": 0.27734375,
      "learning_rate": 0.0002,
      "loss": 1.4942,
      "step": 23
    },
    {
      "epoch": 0.1991701244813278,
      "grad_norm": 0.259765625,
      "learning_rate": 0.00019998952044849376,
      "loss": 1.42,
      "step": 24
    },
    {
      "epoch": 0.2074688796680498,
      "grad_norm": 0.255859375,
      "learning_rate": 0.00019995808399039496,
      "loss": 1.4399,
      "step": 25
    },
    {
      "epoch": 0.2157676348547718,
      "grad_norm": 0.41796875,
      "learning_rate": 0.00019990569721450326,
      "loss": 2.1457,
      "step": 26
    },
    {
      "epoch": 0.22406639004149378,
      "grad_norm": 0.302734375,
      "learning_rate": 0.00019983237110061697,
      "loss": 1.4462,
      "step": 27
    },
    {
      "epoch": 0.23236514522821577,
      "grad_norm": 0.2890625,
      "learning_rate": 0.00019973812101723188,
      "loss": 1.3847,
      "step": 28
    },
    {
      "epoch": 0.24066390041493776,
      "grad_norm": 0.2412109375,
      "learning_rate": 0.00019962296671832003,
      "loss": 1.4013,
      "step": 29
    },
    {
      "epoch": 0.24896265560165975,
      "grad_norm": 0.2578125,
      "learning_rate": 0.00019948693233918952,
      "loss": 1.3528,
      "step": 30
    },
    {
      "epoch": 0.2572614107883817,
      "grad_norm": 0.255859375,
      "learning_rate": 0.00019933004639142605,
      "loss": 1.3523,
      "step": 31
    },
    {
      "epoch": 0.26556016597510373,
      "grad_norm": 0.265625,
      "learning_rate": 0.000199152341756917,
      "loss": 1.36,
      "step": 32
    },
    {
      "epoch": 0.27385892116182575,
      "grad_norm": 0.26953125,
      "learning_rate": 0.00019895385568095982,
      "loss": 1.3316,
      "step": 33
    },
    {
      "epoch": 0.2821576763485477,
      "grad_norm": 0.265625,
      "learning_rate": 0.00019873462976445553,
      "loss": 1.371,
      "step": 34
    },
    {
      "epoch": 0.29045643153526973,
      "grad_norm": 0.2578125,
      "learning_rate": 0.00019849470995518992,
      "loss": 1.4089,
      "step": 35
    },
    {
      "epoch": 0.2987551867219917,
      "grad_norm": 0.255859375,
      "learning_rate": 0.0001982341465382029,
      "loss": 1.3663,
      "step": 36
    },
    {
      "epoch": 0.3070539419087137,
      "grad_norm": 0.267578125,
      "learning_rate": 0.00019795299412524945,
      "loss": 1.3573,
      "step": 37
    },
    {
      "epoch": 0.3153526970954357,
      "grad_norm": 0.24609375,
      "learning_rate": 0.00019765131164335345,
      "loss": 1.3048,
      "step": 38
    },
    {
      "epoch": 0.3236514522821577,
      "grad_norm": 0.7734375,
      "learning_rate": 0.000197329162322457,
      "loss": 2.0409,
      "step": 39
    },
    {
      "epoch": 0.33195020746887965,
      "grad_norm": 0.25390625,
      "learning_rate": 0.00019698661368216817,
      "loss": 1.3583,
      "step": 40
    },
    {
      "epoch": 0.34024896265560167,
      "grad_norm": 0.2490234375,
      "learning_rate": 0.00019662373751760934,
      "loss": 1.2915,
      "step": 41
    },
    {
      "epoch": 0.34854771784232363,
      "grad_norm": 0.2578125,
      "learning_rate": 0.00019624060988436966,
      "loss": 1.3238,
      "step": 42
    },
    {
      "epoch": 0.35684647302904565,
      "grad_norm": 0.2294921875,
      "learning_rate": 0.0001958373110825644,
      "loss": 1.3412,
      "step": 43
    },
    {
      "epoch": 0.3651452282157676,
      "grad_norm": 0.236328125,
      "learning_rate": 0.00019541392564000488,
      "loss": 1.2947,
      "step": 44
    },
    {
      "epoch": 0.37344398340248963,
      "grad_norm": 0.2451171875,
      "learning_rate": 0.00019497054229448223,
      "loss": 1.3453,
      "step": 45
    },
    {
      "epoch": 0.3817427385892116,
      "grad_norm": 0.248046875,
      "learning_rate": 0.0001945072539751685,
      "loss": 1.3186,
      "step": 46
    },
    {
      "epoch": 0.3900414937759336,
      "grad_norm": 0.2431640625,
      "learning_rate": 0.00019402415778313977,
      "loss": 1.3524,
      "step": 47
    },
    {
      "epoch": 0.3983402489626556,
      "grad_norm": 0.267578125,
      "learning_rate": 0.00019352135497102463,
      "loss": 1.3403,
      "step": 48
    },
    {
      "epoch": 0.4066390041493776,
      "grad_norm": 0.251953125,
      "learning_rate": 0.0001929989509217824,
      "loss": 1.3266,
      "step": 49
    },
    {
      "epoch": 0.4149377593360996,
      "grad_norm": 0.251953125,
      "learning_rate": 0.0001924570551266159,
      "loss": 1.3373,
      "step": 50
    },
    {
      "epoch": 0.42323651452282157,
      "grad_norm": 0.2412109375,
      "learning_rate": 0.00019189578116202307,
      "loss": 1.268,
      "step": 51
    },
    {
      "epoch": 0.4315352697095436,
      "grad_norm": 0.23828125,
      "learning_rate": 0.00019131524666599233,
      "loss": 1.2878,
      "step": 52
    },
    {
      "epoch": 0.43983402489626555,
      "grad_norm": 0.236328125,
      "learning_rate": 0.00019071557331334669,
      "loss": 1.2968,
      "step": 53
    },
    {
      "epoch": 0.44813278008298757,
      "grad_norm": 0.2353515625,
      "learning_rate": 0.0001900968867902419,
      "loss": 1.3174,
      "step": 54
    },
    {
      "epoch": 0.45643153526970953,
      "grad_norm": 0.2412109375,
      "learning_rate": 0.00018945931676782373,
      "loss": 1.283,
      "step": 55
    },
    {
      "epoch": 0.46473029045643155,
      "grad_norm": 0.248046875,
      "learning_rate": 0.0001888029968750498,
      "loss": 1.279,
      "step": 56
    },
    {
      "epoch": 0.4730290456431535,
      "grad_norm": 0.240234375,
      "learning_rate": 0.00018812806467068268,
      "loss": 1.3151,
      "step": 57
    },
    {
      "epoch": 0.48132780082987553,
      "grad_norm": 0.244140625,
      "learning_rate": 0.00018743466161445823,
      "loss": 1.2763,
      "step": 58
    },
    {
      "epoch": 0.4896265560165975,
      "grad_norm": 0.25390625,
      "learning_rate": 0.00018672293303743738,
      "loss": 1.3259,
      "step": 59
    },
    {
      "epoch": 0.4979253112033195,
      "grad_norm": 0.255859375,
      "learning_rate": 0.00018599302811154572,
      "loss": 1.287,
      "step": 60
    },
    {
      "epoch": 0.5062240663900415,
      "grad_norm": 0.267578125,
      "learning_rate": 0.00018524509981830852,
      "loss": 1.2794,
      "step": 61
    },
    {
      "epoch": 0.5145228215767634,
      "grad_norm": 0.255859375,
      "learning_rate": 0.00018447930491678733,
      "loss": 1.3154,
      "step": 62
    },
    {
      "epoch": 0.5228215767634855,
      "grad_norm": 0.248046875,
      "learning_rate": 0.00018369580391072433,
      "loss": 1.2979,
      "step": 63
    },
    {
      "epoch": 0.5311203319502075,
      "grad_norm": 0.2421875,
      "learning_rate": 0.00018289476101490256,
      "loss": 1.326,
      "step": 64
    },
    {
      "epoch": 0.5394190871369294,
      "grad_norm": 0.24609375,
      "learning_rate": 0.00018207634412072764,
      "loss": 1.2843,
      "step": 65
    },
    {
      "epoch": 0.5477178423236515,
      "grad_norm": 0.2490234375,
      "learning_rate": 0.00018124072476103956,
      "loss": 1.3233,
      "step": 66
    },
    {
      "epoch": 0.5560165975103735,
      "grad_norm": 0.248046875,
      "learning_rate": 0.00018038807807416068,
      "loss": 1.3208,
      "step": 67
    },
    {
      "epoch": 0.5643153526970954,
      "grad_norm": 0.2431640625,
      "learning_rate": 0.00017951858276718844,
      "loss": 1.2949,
      "step": 68
    },
    {
      "epoch": 0.5726141078838174,
      "grad_norm": 0.412109375,
      "learning_rate": 0.00017863242107853995,
      "loss": 1.9205,
      "step": 69
    },
    {
      "epoch": 0.5809128630705395,
      "grad_norm": 0.2578125,
      "learning_rate": 0.0001777297787397563,
      "loss": 1.2847,
      "step": 70
    },
    {
      "epoch": 0.5892116182572614,
      "grad_norm": 0.2578125,
      "learning_rate": 0.00017681084493657525,
      "loss": 1.298,
      "step": 71
    },
    {
      "epoch": 0.5975103734439834,
      "grad_norm": 0.255859375,
      "learning_rate": 0.0001758758122692791,
      "loss": 1.2805,
      "step": 72
    },
    {
      "epoch": 0.6058091286307054,
      "grad_norm": 0.25390625,
      "learning_rate": 0.00017492487671232784,
      "loss": 1.2829,
      "step": 73
    },
    {
      "epoch": 0.6141078838174274,
      "grad_norm": 0.2470703125,
      "learning_rate": 0.00017395823757328444,
      "loss": 1.2523,
      "step": 74
    },
    {
      "epoch": 0.6224066390041494,
      "grad_norm": 0.25,
      "learning_rate": 0.00017297609745104184,
      "loss": 1.2977,
      "step": 75
    },
    {
      "epoch": 0.6307053941908713,
      "grad_norm": 0.25,
      "learning_rate": 0.0001719786621933599,
      "loss": 1.3103,
      "step": 76
    },
    {
      "epoch": 0.6390041493775933,
      "grad_norm": 0.25390625,
      "learning_rate": 0.00017096614085372185,
      "loss": 1.3006,
      "step": 77
    },
    {
      "epoch": 0.6473029045643154,
      "grad_norm": 0.435546875,
      "learning_rate": 0.00016993874564751822,
      "loss": 1.8113,
      "step": 78
    },
    {
      "epoch": 0.6556016597510373,
      "grad_norm": 0.6953125,
      "learning_rate": 0.00016889669190756868,
      "loss": 2.3268,
      "step": 79
    },
    {
      "epoch": 0.6639004149377593,
      "grad_norm": 0.2734375,
      "learning_rate": 0.00016784019803899,
      "loss": 1.2574,
      "step": 80
    },
    {
      "epoch": 0.6721991701244814,
      "grad_norm": 0.259765625,
      "learning_rate": 0.0001667694854734204,
      "loss": 1.2365,
      "step": 81
    },
    {
      "epoch": 0.6804979253112033,
      "grad_norm": 0.26953125,
      "learning_rate": 0.0001656847786226095,
      "loss": 1.2974,
      "step": 82
    },
    {
      "epoch": 0.6887966804979253,
      "grad_norm": 0.267578125,
      "learning_rate": 0.00016458630483138356,
      "loss": 1.2225,
      "step": 83
    },
    {
      "epoch": 0.6970954356846473,
      "grad_norm": 0.2734375,
      "learning_rate": 0.00016347429432999602,
      "loss": 1.2477,
      "step": 84
    },
    {
      "epoch": 0.7053941908713693,
      "grad_norm": 0.28125,
      "learning_rate": 0.00016234898018587337,
      "loss": 1.2872,
      "step": 85
    },
    {
      "epoch": 0.7136929460580913,
      "grad_norm": 0.271484375,
      "learning_rate": 0.0001612105982547663,
      "loss": 1.2824,
      "step": 86
    },
    {
      "epoch": 0.7219917012448133,
      "grad_norm": 0.26171875,
      "learning_rate": 0.00016005938713131642,
      "loss": 1.3056,
      "step": 87
    },
    {
      "epoch": 0.7302904564315352,
      "grad_norm": 0.265625,
      "learning_rate": 0.00015889558809904902,
      "loss": 1.244,
      "step": 88
    },
    {
      "epoch": 0.7385892116182573,
      "grad_norm": 0.267578125,
      "learning_rate": 0.00015771944507980207,
      "loss": 1.2742,
      "step": 89
    },
    {
      "epoch": 0.7468879668049793,
      "grad_norm": 0.259765625,
      "learning_rate": 0.00015653120458260263,
      "loss": 1.3265,
      "step": 90
    },
    {
      "epoch": 0.7551867219917012,
      "grad_norm": 0.25,
      "learning_rate": 0.00015533111565200044,
      "loss": 1.2373,
      "step": 91
    },
    {
      "epoch": 0.7634854771784232,
      "grad_norm": 0.259765625,
      "learning_rate": 0.0001541194298158708,
      "loss": 1.3201,
      "step": 92
    },
    {
      "epoch": 0.7717842323651453,
      "grad_norm": 0.27734375,
      "learning_rate": 0.00015289640103269625,
      "loss": 1.2052,
      "step": 93
    },
    {
      "epoch": 0.7800829875518672,
      "grad_norm": 0.283203125,
      "learning_rate": 0.00015166228563833934,
      "loss": 1.2638,
      "step": 94
    },
    {
      "epoch": 0.7883817427385892,
      "grad_norm": 0.2578125,
      "learning_rate": 0.00015041734229231688,
      "loss": 1.2334,
      "step": 95
    },
    {
      "epoch": 0.7966804979253111,
      "grad_norm": 0.263671875,
      "learning_rate": 0.00014916183192358718,
      "loss": 1.2396,
      "step": 96
    },
    {
      "epoch": 0.8049792531120332,
      "grad_norm": 0.2578125,
      "learning_rate": 0.00014789601767586173,
      "loss": 1.2272,
      "step": 97
    },
    {
      "epoch": 0.8132780082987552,
      "grad_norm": 0.28125,
      "learning_rate": 0.00014662016485245274,
      "loss": 1.2784,
      "step": 98
    },
    {
      "epoch": 0.8215767634854771,
      "grad_norm": 0.275390625,
      "learning_rate": 0.00014533454086066772,
      "loss": 1.2512,
      "step": 99
    },
    {
      "epoch": 0.8298755186721992,
      "grad_norm": 0.275390625,
      "learning_rate": 0.00014403941515576344,
      "loss": 1.2562,
      "step": 100
    },
    {
      "epoch": 0.8381742738589212,
      "grad_norm": 0.267578125,
      "learning_rate": 0.00014273505918447054,
      "loss": 1.3054,
      "step": 101
    },
    {
      "epoch": 0.8464730290456431,
      "grad_norm": 0.263671875,
      "learning_rate": 0.00014142174632810072,
      "loss": 1.2831,
      "step": 102
    },
    {
      "epoch": 0.8547717842323651,
      "grad_norm": 0.279296875,
      "learning_rate": 0.0001400997518452484,
      "loss": 1.31,
      "step": 103
    },
    {
      "epoch": 0.8630705394190872,
      "grad_norm": 0.25,
      "learning_rate": 0.00013876935281409907,
      "loss": 1.2472,
      "step": 104
    },
    {
      "epoch": 0.8713692946058091,
      "grad_norm": 0.28515625,
      "learning_rate": 0.00013743082807435615,
      "loss": 1.2792,
      "step": 105
    },
    {
      "epoch": 0.8796680497925311,
      "grad_norm": 0.267578125,
      "learning_rate": 0.00013608445816879866,
      "loss": 1.2853,
      "step": 106
    },
    {
      "epoch": 0.8879668049792531,
      "grad_norm": 0.265625,
      "learning_rate": 0.00013473052528448201,
      "loss": 1.2923,
      "step": 107
    },
    {
      "epoch": 0.8962655601659751,
      "grad_norm": 0.275390625,
      "learning_rate": 0.00013336931319359426,
      "loss": 1.2768,
      "step": 108
    },
    {
      "epoch": 0.9045643153526971,
      "grad_norm": 0.267578125,
      "learning_rate": 0.00013200110719397968,
      "loss": 1.2701,
      "step": 109
    },
    {
      "epoch": 0.9128630705394191,
      "grad_norm": 0.25390625,
      "learning_rate": 0.00013062619404934317,
      "loss": 1.21,
      "step": 110
    },
    {
      "epoch": 0.921161825726141,
      "grad_norm": 0.255859375,
      "learning_rate": 0.00012924486192914705,
      "loss": 1.2808,
      "step": 111
    },
    {
      "epoch": 0.9294605809128631,
      "grad_norm": 0.26171875,
      "learning_rate": 0.00012785740034821329,
      "loss": 1.2616,
      "step": 112
    },
    {
      "epoch": 0.9377593360995851,
      "grad_norm": 0.265625,
      "learning_rate": 0.00012646410010604397,
      "loss": 1.2094,
      "step": 113
    },
    {
      "epoch": 0.946058091286307,
      "grad_norm": 0.267578125,
      "learning_rate": 0.00012506525322587207,
      "loss": 1.2128,
      "step": 114
    },
    {
      "epoch": 0.9543568464730291,
      "grad_norm": 0.267578125,
      "learning_rate": 0.0001236611528934562,
      "loss": 1.2573,
      "step": 115
    },
    {
      "epoch": 0.9626556016597511,
      "grad_norm": 0.259765625,
      "learning_rate": 0.00012225209339563145,
      "loss": 1.2367,
      "step": 116
    },
    {
      "epoch": 0.970954356846473,
      "grad_norm": 0.263671875,
      "learning_rate": 0.00012083837005862946,
      "loss": 1.2313,
      "step": 117
    },
    {
      "epoch": 0.979253112033195,
      "grad_norm": 0.265625,
      "learning_rate": 0.00011942027918618074,
      "loss": 1.2495,
      "step": 118
    },
    {
      "epoch": 0.9875518672199171,
      "grad_norm": 0.259765625,
      "learning_rate": 0.0001179981179974121,
      "loss": 1.2225,
      "step": 119
    },
    {
      "epoch": 0.995850622406639,
      "grad_norm": 0.28125,
      "learning_rate": 0.00011657218456455206,
      "loss": 1.2869,
      "step": 120
    }
  ],
  "logging_steps": 1,
  "max_steps": 240,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 120,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.97353639329792e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}