{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 19,
  "global_step": 98,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02040816326530612,
      "grad_norm": 0.37130826711654663,
      "learning_rate": 0.0,
      "loss": 0.96337890625,
      "step": 1
    },
    {
      "epoch": 0.04081632653061224,
      "grad_norm": 0.37363889813423157,
      "learning_rate": 2e-05,
      "loss": 0.92333984375,
      "step": 2
    },
    {
      "epoch": 0.061224489795918366,
      "grad_norm": 0.35044315457344055,
      "learning_rate": 4e-05,
      "loss": 0.9033203125,
      "step": 3
    },
    {
      "epoch": 0.08163265306122448,
      "grad_norm": 0.3328283429145813,
      "learning_rate": 6e-05,
      "loss": 0.94482421875,
      "step": 4
    },
    {
      "epoch": 0.10204081632653061,
      "grad_norm": 0.24160979688167572,
      "learning_rate": 8e-05,
      "loss": 0.843994140625,
      "step": 5
    },
    {
      "epoch": 0.12244897959183673,
      "grad_norm": 0.2086843103170395,
      "learning_rate": 0.0001,
      "loss": 0.841796875,
      "step": 6
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 0.3343663513660431,
      "learning_rate": 9.99743270918373e-05,
      "loss": 0.83251953125,
      "step": 7
    },
    {
      "epoch": 0.16326530612244897,
      "grad_norm": 0.2831439673900604,
      "learning_rate": 9.989733766060318e-05,
      "loss": 0.7796630859375,
      "step": 8
    },
    {
      "epoch": 0.1836734693877551,
      "grad_norm": 0.2235320657491684,
      "learning_rate": 9.976911955263529e-05,
      "loss": 0.76806640625,
      "step": 9
    },
    {
      "epoch": 0.20408163265306123,
      "grad_norm": 0.17578648030757904,
      "learning_rate": 9.958981906712077e-05,
      "loss": 0.7412109375,
      "step": 10
    },
    {
      "epoch": 0.22448979591836735,
      "grad_norm": 0.14320515096187592,
      "learning_rate": 9.935964078916618e-05,
      "loss": 0.70947265625,
      "step": 11
    },
    {
      "epoch": 0.24489795918367346,
      "grad_norm": 0.12199477106332779,
      "learning_rate": 9.907884735636226e-05,
      "loss": 0.6806640625,
      "step": 12
    },
    {
      "epoch": 0.2653061224489796,
      "grad_norm": 0.11599483340978622,
      "learning_rate": 9.87477591591096e-05,
      "loss": 0.65771484375,
      "step": 13
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.1294860541820526,
      "learning_rate": 9.836675397504734e-05,
      "loss": 0.67333984375,
      "step": 14
    },
    {
      "epoch": 0.30612244897959184,
      "grad_norm": 0.11584243178367615,
      "learning_rate": 9.793626653800219e-05,
      "loss": 0.64208984375,
      "step": 15
    },
    {
      "epoch": 0.32653061224489793,
      "grad_norm": 0.13311445713043213,
      "learning_rate": 9.745678804194912e-05,
      "loss": 0.6708984375,
      "step": 16
    },
    {
      "epoch": 0.3469387755102041,
      "grad_norm": 0.10174882411956787,
      "learning_rate": 9.692886558055007e-05,
      "loss": 0.6181640625,
      "step": 17
    },
    {
      "epoch": 0.3673469387755102,
      "grad_norm": 0.10500331223011017,
      "learning_rate": 9.635310152291039e-05,
      "loss": 0.63427734375,
      "step": 18
    },
    {
      "epoch": 0.3877551020408163,
      "grad_norm": 0.09124942868947983,
      "learning_rate": 9.573015282626447e-05,
      "loss": 0.61376953125,
      "step": 19
    },
    {
      "epoch": 0.40816326530612246,
      "grad_norm": 0.10712587833404541,
      "learning_rate": 9.506073028637583e-05,
      "loss": 0.653564453125,
      "step": 20
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.08602163940668106,
      "learning_rate": 9.43455977265062e-05,
      "loss": 0.6064453125,
      "step": 21
    },
    {
      "epoch": 0.4489795918367347,
      "grad_norm": 0.07736460864543915,
      "learning_rate": 9.358557112587929e-05,
      "loss": 0.607421875,
      "step": 22
    },
    {
      "epoch": 0.4489795918367347,
      "eval_loss": 0.60791015625,
      "eval_runtime": 2.1186,
      "eval_samples_per_second": 1.416,
      "eval_steps_per_second": 0.472,
      "step": 22
    },
    {
      "epoch": 0.46938775510204084,
      "grad_norm": 0.07570677995681763,
      "learning_rate": 9.278151768863376e-05,
      "loss": 0.62548828125,
      "step": 23
    },
    {
      "epoch": 0.4897959183673469,
      "grad_norm": 0.09275470674037933,
      "learning_rate": 9.193435485432745e-05,
      "loss": 0.63427734375,
      "step": 24
    },
    {
      "epoch": 0.5102040816326531,
      "grad_norm": 0.07329649478197098,
      "learning_rate": 9.104504925112231e-05,
      "loss": 0.5771484375,
      "step": 25
    },
    {
      "epoch": 0.5306122448979592,
      "grad_norm": 0.07164300978183746,
      "learning_rate": 9.011461559284413e-05,
      "loss": 0.5673828125,
      "step": 26
    },
    {
      "epoch": 0.5510204081632653,
      "grad_norm": 0.06667683273553848,
      "learning_rate": 8.914411552117559e-05,
      "loss": 0.583251953125,
      "step": 27
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.0545831061899662,
      "learning_rate": 8.813465639430387e-05,
      "loss": 0.5517578125,
      "step": 28
    },
    {
      "epoch": 0.5918367346938775,
      "grad_norm": 0.05903055518865585,
      "learning_rate": 8.708739002340492e-05,
      "loss": 0.556640625,
      "step": 29
    },
    {
      "epoch": 0.6122448979591837,
      "grad_norm": 0.055395714938640594,
      "learning_rate": 8.600351135840589e-05,
      "loss": 0.542724609375,
      "step": 30
    },
    {
      "epoch": 0.6326530612244898,
      "grad_norm": 0.05440191179513931,
      "learning_rate": 8.488425712452577e-05,
      "loss": 0.54833984375,
      "step": 31
    },
    {
      "epoch": 0.6530612244897959,
      "grad_norm": 0.07592244446277618,
      "learning_rate": 8.373090441114926e-05,
      "loss": 0.5849609375,
      "step": 32
    },
    {
      "epoch": 0.673469387755102,
      "grad_norm": 0.057455625385046005,
      "learning_rate": 8.254476921464484e-05,
      "loss": 0.55517578125,
      "step": 33
    },
    {
      "epoch": 0.6938775510204082,
      "grad_norm": 0.059540897607803345,
      "learning_rate": 8.132720493678884e-05,
      "loss": 0.5380859375,
      "step": 34
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.06859797984361649,
      "learning_rate": 8.007960084050963e-05,
      "loss": 0.56640625,
      "step": 35
    },
    {
      "epoch": 0.7346938775510204,
      "grad_norm": 0.04753356799483299,
      "learning_rate": 7.880338046471331e-05,
      "loss": 0.518310546875,
      "step": 36
    },
    {
      "epoch": 0.7551020408163265,
      "grad_norm": 0.049659762531518936,
      "learning_rate": 7.75e-05,
      "loss": 0.52392578125,
      "step": 37
    },
    {
      "epoch": 0.7755102040816326,
      "grad_norm": 0.04813021793961525,
      "learning_rate": 7.6170946627124e-05,
      "loss": 0.52197265625,
      "step": 38
    },
    {
      "epoch": 0.7959183673469388,
      "grad_norm": 0.05200834572315216,
      "learning_rate": 7.481773682009356e-05,
      "loss": 0.525146484375,
      "step": 39
    },
    {
      "epoch": 0.8163265306122449,
      "grad_norm": 0.05049646645784378,
      "learning_rate": 7.344191461584644e-05,
      "loss": 0.5218505859375,
      "step": 40
    },
    {
      "epoch": 0.8367346938775511,
      "grad_norm": 0.05078901723027229,
      "learning_rate": 7.204504985247593e-05,
      "loss": 0.50732421875,
      "step": 41
    },
    {
      "epoch": 0.8367346938775511,
      "eval_loss": 0.52587890625,
      "eval_runtime": 2.1176,
      "eval_samples_per_second": 1.417,
      "eval_steps_per_second": 0.472,
      "step": 41
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.052566539496183395,
      "learning_rate": 7.062873637801692e-05,
      "loss": 0.550048828125,
      "step": 42
    },
    {
      "epoch": 0.8775510204081632,
      "grad_norm": 0.05154574662446976,
      "learning_rate": 6.919459023183651e-05,
      "loss": 0.5185546875,
      "step": 43
    },
    {
      "epoch": 0.8979591836734694,
      "grad_norm": 0.04407985880970955,
      "learning_rate": 6.774424780070367e-05,
      "loss": 0.495361328125,
      "step": 44
    },
    {
      "epoch": 0.9183673469387755,
      "grad_norm": 0.052091024816036224,
      "learning_rate": 6.627936395164243e-05,
      "loss": 0.5224609375,
      "step": 45
    },
    {
      "epoch": 0.9387755102040817,
      "grad_norm": 0.044904496520757675,
      "learning_rate": 6.480161014369832e-05,
      "loss": 0.510498046875,
      "step": 46
    },
    {
      "epoch": 0.9591836734693877,
      "grad_norm": 0.045833226293325424,
      "learning_rate": 6.331267252077353e-05,
      "loss": 0.498046875,
      "step": 47
    },
    {
      "epoch": 0.9795918367346939,
      "grad_norm": 0.044260744005441666,
      "learning_rate": 6.181424998770595e-05,
      "loss": 0.50927734375,
      "step": 48
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.04452819749712944,
      "learning_rate": 6.030805227178809e-05,
      "loss": 0.49609375,
      "step": 49
    },
    {
      "epoch": 1.0204081632653061,
      "grad_norm": 0.044995374977588654,
      "learning_rate": 5.879579797193702e-05,
      "loss": 0.50439453125,
      "step": 50
    },
    {
      "epoch": 1.0408163265306123,
      "grad_norm": 0.04924507066607475,
      "learning_rate": 5.727921259774208e-05,
      "loss": 0.487060546875,
      "step": 51
    },
    {
      "epoch": 1.0612244897959184,
      "grad_norm": 0.04312204197049141,
      "learning_rate": 5.57600266006269e-05,
      "loss": 0.47119140625,
      "step": 52
    },
    {
      "epoch": 1.0816326530612246,
      "grad_norm": 0.0489010252058506,
      "learning_rate": 5.423997339937311e-05,
      "loss": 0.511962890625,
      "step": 53
    },
    {
      "epoch": 1.1020408163265305,
      "grad_norm": 0.046135224401950836,
      "learning_rate": 5.2720787402257935e-05,
      "loss": 0.479736328125,
      "step": 54
    },
    {
      "epoch": 1.1224489795918366,
      "grad_norm": 0.04888031631708145,
      "learning_rate": 5.1204202028063e-05,
      "loss": 0.504638671875,
      "step": 55
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.05575020983815193,
      "learning_rate": 4.969194772821194e-05,
      "loss": 0.508544921875,
      "step": 56
    },
    {
      "epoch": 1.163265306122449,
      "grad_norm": 0.04905897006392479,
      "learning_rate": 4.8185750012294065e-05,
      "loss": 0.4876708984375,
      "step": 57
    },
    {
      "epoch": 1.183673469387755,
      "grad_norm": 0.04896201193332672,
      "learning_rate": 4.66873274792265e-05,
      "loss": 0.50244140625,
      "step": 58
    },
    {
      "epoch": 1.2040816326530612,
      "grad_norm": 0.04815675690770149,
      "learning_rate": 4.5198389856301684e-05,
      "loss": 0.5048828125,
      "step": 59
    },
    {
      "epoch": 1.2244897959183674,
      "grad_norm": 0.04719199240207672,
      "learning_rate": 4.372063604835758e-05,
      "loss": 0.48876953125,
      "step": 60
    },
    {
      "epoch": 1.2244897959183674,
      "eval_loss": 0.489013671875,
      "eval_runtime": 2.134,
      "eval_samples_per_second": 1.406,
      "eval_steps_per_second": 0.469,
      "step": 60
    },
    {
      "epoch": 1.2448979591836735,
      "grad_norm": 0.04884811490774155,
      "learning_rate": 4.2255752199296314e-05,
      "loss": 0.477783203125,
      "step": 61
    },
    {
      "epoch": 1.2653061224489797,
      "grad_norm": 0.04511122778058052,
      "learning_rate": 4.0805409768163506e-05,
      "loss": 0.462646484375,
      "step": 62
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 0.042237624526023865,
      "learning_rate": 3.93712636219831e-05,
      "loss": 0.47998046875,
      "step": 63
    },
    {
      "epoch": 1.306122448979592,
      "grad_norm": 0.05041330307722092,
      "learning_rate": 3.7954950147524084e-05,
      "loss": 0.461181640625,
      "step": 64
    },
    {
      "epoch": 1.3265306122448979,
      "grad_norm": 0.04858933016657829,
      "learning_rate": 3.6558085384153576e-05,
      "loss": 0.494873046875,
      "step": 65
    },
    {
      "epoch": 1.346938775510204,
      "grad_norm": 0.04199395328760147,
      "learning_rate": 3.518226317990646e-05,
      "loss": 0.455810546875,
      "step": 66
    },
    {
      "epoch": 1.3673469387755102,
      "grad_norm": 0.04436585307121277,
      "learning_rate": 3.382905337287601e-05,
      "loss": 0.478515625,
      "step": 67
    },
    {
      "epoch": 1.3877551020408163,
      "grad_norm": 0.04193197190761566,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.463623046875,
      "step": 68
    },
    {
      "epoch": 1.4081632653061225,
      "grad_norm": 0.05190965533256531,
      "learning_rate": 3.119661953528671e-05,
      "loss": 0.501953125,
      "step": 69
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.04562630131840706,
      "learning_rate": 2.9920399159490364e-05,
      "loss": 0.470947265625,
      "step": 70
    },
    {
      "epoch": 1.4489795918367347,
      "grad_norm": 0.04882175102829933,
      "learning_rate": 2.8672795063211156e-05,
      "loss": 0.4755859375,
      "step": 71
    },
    {
      "epoch": 1.469387755102041,
      "grad_norm": 0.04693262279033661,
      "learning_rate": 2.745523078535517e-05,
      "loss": 0.494140625,
      "step": 72
    },
    {
      "epoch": 1.489795918367347,
      "grad_norm": 0.051169175654649734,
      "learning_rate": 2.6269095588850744e-05,
      "loss": 0.505859375,
      "step": 73
    },
    {
      "epoch": 1.510204081632653,
      "grad_norm": 0.04198864847421646,
      "learning_rate": 2.5115742875474236e-05,
      "loss": 0.461181640625,
      "step": 74
    },
    {
      "epoch": 1.5306122448979593,
      "grad_norm": 0.04316142573952675,
      "learning_rate": 2.39964886415941e-05,
      "loss": 0.457763671875,
      "step": 75
    },
    {
      "epoch": 1.5510204081632653,
      "grad_norm": 0.043992429971694946,
      "learning_rate": 2.2912609976595093e-05,
      "loss": 0.473876953125,
      "step": 76
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 0.04234153777360916,
      "learning_rate": 2.186534360569613e-05,
      "loss": 0.4501953125,
      "step": 77
    },
    {
      "epoch": 1.5918367346938775,
      "grad_norm": 0.04113883152604103,
      "learning_rate": 2.0855884478824412e-05,
      "loss": 0.4580078125,
      "step": 78
    },
    {
      "epoch": 1.6122448979591837,
      "grad_norm": 0.043154243379831314,
      "learning_rate": 1.9885384407155874e-05,
      "loss": 0.448486328125,
      "step": 79
    },
    {
      "epoch": 1.6122448979591837,
      "eval_loss": 0.47314453125,
      "eval_runtime": 2.1369,
      "eval_samples_per_second": 1.404,
      "eval_steps_per_second": 0.468,
      "step": 79
    },
    {
      "epoch": 1.6326530612244898,
      "grad_norm": 0.045340314507484436,
      "learning_rate": 1.8954950748877703e-05,
      "loss": 0.456298828125,
      "step": 80
    },
    {
      "epoch": 1.6530612244897958,
      "grad_norm": 0.04856802523136139,
      "learning_rate": 1.806564514567258e-05,
      "loss": 0.491943359375,
      "step": 81
    },
    {
      "epoch": 1.6734693877551021,
      "grad_norm": 0.04405174031853676,
      "learning_rate": 1.7218482311366247e-05,
      "loss": 0.470703125,
      "step": 82
    },
    {
      "epoch": 1.693877551020408,
      "grad_norm": 0.04074881970882416,
      "learning_rate": 1.64144288741207e-05,
      "loss": 0.457763671875,
      "step": 83
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.04805354028940201,
      "learning_rate": 1.5654402273493805e-05,
      "loss": 0.484130859375,
      "step": 84
    },
    {
      "epoch": 1.7346938775510203,
      "grad_norm": 0.040051426738500595,
      "learning_rate": 1.4939269713624182e-05,
      "loss": 0.4443359375,
      "step": 85
    },
    {
      "epoch": 1.7551020408163265,
      "grad_norm": 0.04109072685241699,
      "learning_rate": 1.4269847173735545e-05,
      "loss": 0.4521484375,
      "step": 86
    },
    {
      "epoch": 1.7755102040816326,
      "grad_norm": 0.04129721596837044,
      "learning_rate": 1.3646898477089626e-05,
      "loss": 0.45166015625,
      "step": 87
    },
    {
      "epoch": 1.7959183673469388,
      "grad_norm": 0.04394122585654259,
      "learning_rate": 1.3071134419449922e-05,
      "loss": 0.4521484375,
      "step": 88
    },
    {
      "epoch": 1.816326530612245,
      "grad_norm": 0.043181195855140686,
      "learning_rate": 1.2543211958050897e-05,
      "loss": 0.45703125,
      "step": 89
    },
    {
      "epoch": 1.836734693877551,
      "grad_norm": 0.045303259044885635,
      "learning_rate": 1.2063733461997805e-05,
      "loss": 0.443603515625,
      "step": 90
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.05049462243914604,
      "learning_rate": 1.1633246024952662e-05,
      "loss": 0.486083984375,
      "step": 91
    },
    {
      "epoch": 1.8775510204081631,
      "grad_norm": 0.04673405736684799,
      "learning_rate": 1.1252240840890425e-05,
      "loss": 0.460693359375,
      "step": 92
    },
    {
      "epoch": 1.8979591836734695,
      "grad_norm": 0.04047442227602005,
      "learning_rate": 1.092115264363775e-05,
      "loss": 0.441162109375,
      "step": 93
    },
    {
      "epoch": 1.9183673469387754,
      "grad_norm": 0.04289766028523445,
      "learning_rate": 1.0640359210833831e-05,
      "loss": 0.467529296875,
      "step": 94
    },
    {
      "epoch": 1.9387755102040818,
      "grad_norm": 0.04440499469637871,
      "learning_rate": 1.0410180932879253e-05,
      "loss": 0.457275390625,
      "step": 95
    },
    {
      "epoch": 1.9591836734693877,
      "grad_norm": 0.042831044644117355,
      "learning_rate": 1.023088044736472e-05,
      "loss": 0.448486328125,
      "step": 96
    },
    {
      "epoch": 1.9795918367346939,
      "grad_norm": 0.042945656925439835,
      "learning_rate": 1.0102662339396819e-05,
      "loss": 0.459716796875,
      "step": 97
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.0437617264688015,
      "learning_rate": 1.0025672908162691e-05,
      "loss": 0.450439453125,
      "step": 98
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.466552734375,
      "eval_runtime": 2.1311,
      "eval_samples_per_second": 1.408,
      "eval_steps_per_second": 0.469,
      "step": 98
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 98,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7668330488814633e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}