{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004348109659325608,
  "eval_steps": 30,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.3481096593256084e-05,
      "grad_norm": 0.18313416838645935,
      "learning_rate": 5e-05,
      "loss": 1.493,
      "step": 1
    },
    {
      "epoch": 4.3481096593256084e-05,
      "eval_loss": 1.558142066001892,
      "eval_runtime": 203.2579,
      "eval_samples_per_second": 47.644,
      "eval_steps_per_second": 23.822,
      "step": 1
    },
    {
      "epoch": 8.696219318651217e-05,
      "grad_norm": 0.12069936841726303,
      "learning_rate": 0.0001,
      "loss": 1.3439,
      "step": 2
    },
    {
      "epoch": 0.00013044328977976824,
      "grad_norm": 0.1665075421333313,
      "learning_rate": 0.00015,
      "loss": 1.6835,
      "step": 3
    },
    {
      "epoch": 0.00017392438637302434,
      "grad_norm": 0.1442747563123703,
      "learning_rate": 0.0002,
      "loss": 1.4464,
      "step": 4
    },
    {
      "epoch": 0.0002174054829662804,
      "grad_norm": 0.1848307102918625,
      "learning_rate": 0.00025,
      "loss": 1.5088,
      "step": 5
    },
    {
      "epoch": 0.0002608865795595365,
      "grad_norm": 0.17121705412864685,
      "learning_rate": 0.0003,
      "loss": 1.4742,
      "step": 6
    },
    {
      "epoch": 0.00030436767615279255,
      "grad_norm": 0.18226021528244019,
      "learning_rate": 0.00035,
      "loss": 1.5433,
      "step": 7
    },
    {
      "epoch": 0.0003478487727460487,
      "grad_norm": 0.17033541202545166,
      "learning_rate": 0.0004,
      "loss": 1.6514,
      "step": 8
    },
    {
      "epoch": 0.00039132986933930475,
      "grad_norm": 0.1377723217010498,
      "learning_rate": 0.00045000000000000004,
      "loss": 1.4088,
      "step": 9
    },
    {
      "epoch": 0.0004348109659325608,
      "grad_norm": 0.20755314826965332,
      "learning_rate": 0.0005,
      "loss": 1.5676,
      "step": 10
    },
    {
      "epoch": 0.0004782920625258169,
      "grad_norm": 0.2286653220653534,
      "learning_rate": 0.0004998477067547739,
      "loss": 1.4479,
      "step": 11
    },
    {
      "epoch": 0.000521773159119073,
      "grad_norm": 0.18399114906787872,
      "learning_rate": 0.0004993910125649561,
      "loss": 1.3011,
      "step": 12
    },
    {
      "epoch": 0.0005652542557123291,
      "grad_norm": 0.22670575976371765,
      "learning_rate": 0.0004986304738420684,
      "loss": 1.496,
      "step": 13
    },
    {
      "epoch": 0.0006087353523055851,
      "grad_norm": 0.2062467783689499,
      "learning_rate": 0.0004975670171853926,
      "loss": 1.5314,
      "step": 14
    },
    {
      "epoch": 0.0006522164488988412,
      "grad_norm": 0.2885122299194336,
      "learning_rate": 0.000496201938253052,
      "loss": 1.66,
      "step": 15
    },
    {
      "epoch": 0.0006956975454920974,
      "grad_norm": 0.28001096844673157,
      "learning_rate": 0.0004945369001834514,
      "loss": 1.426,
      "step": 16
    },
    {
      "epoch": 0.0007391786420853534,
      "grad_norm": 0.25424984097480774,
      "learning_rate": 0.0004925739315689991,
      "loss": 1.4973,
      "step": 17
    },
    {
      "epoch": 0.0007826597386786095,
      "grad_norm": 0.24345117807388306,
      "learning_rate": 0.0004903154239845797,
      "loss": 1.4445,
      "step": 18
    },
    {
      "epoch": 0.0008261408352718655,
      "grad_norm": 0.2889419496059418,
      "learning_rate": 0.0004877641290737884,
      "loss": 1.6269,
      "step": 19
    },
    {
      "epoch": 0.0008696219318651216,
      "grad_norm": 0.20728595554828644,
      "learning_rate": 0.0004849231551964771,
      "loss": 1.3378,
      "step": 20
    },
    {
      "epoch": 0.0009131030284583778,
      "grad_norm": 0.24365362524986267,
      "learning_rate": 0.00048179596364169685,
      "loss": 1.2675,
      "step": 21
    },
    {
      "epoch": 0.0009565841250516338,
      "grad_norm": 0.26219597458839417,
      "learning_rate": 0.0004783863644106502,
      "loss": 1.3657,
      "step": 22
    },
    {
      "epoch": 0.0010000652216448898,
      "grad_norm": 0.3147345185279846,
      "learning_rate": 0.00047469851157479177,
      "loss": 1.3907,
      "step": 23
    },
    {
      "epoch": 0.001043546318238146,
      "grad_norm": 0.3428747057914734,
      "learning_rate": 0.00047073689821473173,
      "loss": 1.2839,
      "step": 24
    },
    {
      "epoch": 0.001087027414831402,
      "grad_norm": 0.2819852828979492,
      "learning_rate": 0.00046650635094610973,
      "loss": 1.4352,
      "step": 25
    },
    {
      "epoch": 0.0011305085114246582,
      "grad_norm": 0.2961019277572632,
      "learning_rate": 0.00046201202403910646,
      "loss": 1.3407,
      "step": 26
    },
    {
      "epoch": 0.0011739896080179143,
      "grad_norm": 0.22638189792633057,
      "learning_rate": 0.00045725939313876043,
      "loss": 1.2414,
      "step": 27
    },
    {
      "epoch": 0.0012174707046111702,
      "grad_norm": 0.3246627151966095,
      "learning_rate": 0.0004522542485937369,
      "loss": 1.3744,
      "step": 28
    },
    {
      "epoch": 0.0012609518012044263,
      "grad_norm": 0.2994436025619507,
      "learning_rate": 0.00044700268840168044,
      "loss": 1.3283,
      "step": 29
    },
    {
      "epoch": 0.0013044328977976825,
      "grad_norm": 0.3261086344718933,
      "learning_rate": 0.0004415111107797445,
      "loss": 1.6176,
      "step": 30
    },
    {
      "epoch": 0.0013044328977976825,
      "eval_loss": 1.4312220811843872,
      "eval_runtime": 200.7889,
      "eval_samples_per_second": 48.23,
      "eval_steps_per_second": 24.115,
      "step": 30
    },
    {
      "epoch": 0.0013479139943909386,
      "grad_norm": 0.3720364570617676,
      "learning_rate": 0.00043578620636934855,
      "loss": 1.6106,
      "step": 31
    },
    {
      "epoch": 0.0013913950909841947,
      "grad_norm": 0.3748486042022705,
      "learning_rate": 0.0004298349500846628,
      "loss": 1.5618,
      "step": 32
    },
    {
      "epoch": 0.0014348761875774506,
      "grad_norm": 0.3934083580970764,
      "learning_rate": 0.00042366459261474935,
      "loss": 1.5262,
      "step": 33
    },
    {
      "epoch": 0.0014783572841707067,
      "grad_norm": 0.2756959795951843,
      "learning_rate": 0.0004172826515897146,
      "loss": 1.3536,
      "step": 34
    },
    {
      "epoch": 0.0015218383807639629,
      "grad_norm": 0.26335471868515015,
      "learning_rate": 0.0004106969024216348,
      "loss": 1.2083,
      "step": 35
    },
    {
      "epoch": 0.001565319477357219,
      "grad_norm": 0.3875220715999603,
      "learning_rate": 0.00040391536883141455,
      "loss": 1.63,
      "step": 36
    },
    {
      "epoch": 0.0016088005739504751,
      "grad_norm": 0.32246655225753784,
      "learning_rate": 0.0003969463130731183,
      "loss": 1.2869,
      "step": 37
    },
    {
      "epoch": 0.001652281670543731,
      "grad_norm": 0.34290939569473267,
      "learning_rate": 0.0003897982258676867,
      "loss": 1.4369,
      "step": 38
    },
    {
      "epoch": 0.0016957627671369871,
      "grad_norm": 0.3700267970561981,
      "learning_rate": 0.00038247981605830125,
      "loss": 1.5842,
      "step": 39
    },
    {
      "epoch": 0.0017392438637302433,
      "grad_norm": 0.34299805760383606,
      "learning_rate": 0.000375,
      "loss": 1.4267,
      "step": 40
    },
    {
      "epoch": 0.0017827249603234994,
      "grad_norm": 0.35160815715789795,
      "learning_rate": 0.0003673678906964727,
      "loss": 1.5085,
      "step": 41
    },
    {
      "epoch": 0.0018262060569167555,
      "grad_norm": 0.3201915919780731,
      "learning_rate": 0.00035959278669726934,
      "loss": 1.3796,
      "step": 42
    },
    {
      "epoch": 0.0018696871535100114,
      "grad_norm": 0.3105376362800598,
      "learning_rate": 0.0003516841607689501,
      "loss": 1.3575,
      "step": 43
    },
    {
      "epoch": 0.0019131682501032676,
      "grad_norm": 0.33102554082870483,
      "learning_rate": 0.00034365164835397803,
      "loss": 1.3367,
      "step": 44
    },
    {
      "epoch": 0.001956649346696524,
      "grad_norm": 0.27141764760017395,
      "learning_rate": 0.0003355050358314172,
      "loss": 1.3298,
      "step": 45
    },
    {
      "epoch": 0.0020001304432897796,
      "grad_norm": 0.31761887669563293,
      "learning_rate": 0.00032725424859373687,
      "loss": 1.2937,
      "step": 46
    },
    {
      "epoch": 0.0020436115398830357,
      "grad_norm": 0.4434088170528412,
      "learning_rate": 0.0003189093389542498,
      "loss": 1.4619,
      "step": 47
    },
    {
      "epoch": 0.002087092636476292,
      "grad_norm": 0.311277836561203,
      "learning_rate": 0.0003104804738999169,
      "loss": 1.2116,
      "step": 48
    },
    {
      "epoch": 0.002130573733069548,
      "grad_norm": 0.41048505902290344,
      "learning_rate": 0.0003019779227044398,
      "loss": 1.671,
      "step": 49
    },
    {
      "epoch": 0.002174054829662804,
      "grad_norm": 0.35352006554603577,
      "learning_rate": 0.00029341204441673266,
      "loss": 1.3945,
      "step": 50
    },
    {
      "epoch": 0.00221753592625606,
      "grad_norm": 0.2824205458164215,
      "learning_rate": 0.00028479327524001636,
      "loss": 1.4224,
      "step": 51
    },
    {
      "epoch": 0.0022610170228493163,
      "grad_norm": 0.3808979094028473,
      "learning_rate": 0.0002761321158169134,
      "loss": 1.5042,
      "step": 52
    },
    {
      "epoch": 0.0023044981194425725,
      "grad_norm": 0.35385096073150635,
      "learning_rate": 0.0002674391184360313,
      "loss": 1.4235,
      "step": 53
    },
    {
      "epoch": 0.0023479792160358286,
      "grad_norm": 0.391770601272583,
      "learning_rate": 0.0002587248741756253,
      "loss": 1.3811,
      "step": 54
    },
    {
      "epoch": 0.0023914603126290847,
      "grad_norm": 0.36259493231773376,
      "learning_rate": 0.00025,
      "loss": 1.3041,
      "step": 55
    },
    {
      "epoch": 0.0024349414092223404,
      "grad_norm": 0.2583346664905548,
      "learning_rate": 0.00024127512582437484,
      "loss": 1.1937,
      "step": 56
    },
    {
      "epoch": 0.0024784225058155965,
      "grad_norm": 0.2702741324901581,
      "learning_rate": 0.00023256088156396867,
      "loss": 1.4001,
      "step": 57
    },
    {
      "epoch": 0.0025219036024088527,
      "grad_norm": 0.3438343107700348,
      "learning_rate": 0.00022386788418308668,
      "loss": 1.4159,
      "step": 58
    },
    {
      "epoch": 0.0025653846990021088,
      "grad_norm": 0.39195516705513,
      "learning_rate": 0.0002152067247599837,
      "loss": 1.5909,
      "step": 59
    },
    {
      "epoch": 0.002608865795595365,
      "grad_norm": 0.3367631137371063,
      "learning_rate": 0.00020658795558326743,
      "loss": 1.3235,
      "step": 60
    },
    {
      "epoch": 0.002608865795595365,
      "eval_loss": 1.3859906196594238,
      "eval_runtime": 200.6528,
      "eval_samples_per_second": 48.262,
      "eval_steps_per_second": 24.131,
      "step": 60
    },
    {
      "epoch": 0.002652346892188621,
      "grad_norm": 0.33776378631591797,
      "learning_rate": 0.0001980220772955602,
      "loss": 1.3894,
      "step": 61
    },
    {
      "epoch": 0.002695827988781877,
      "grad_norm": 0.21993590891361237,
      "learning_rate": 0.0001895195261000831,
      "loss": 1.1228,
      "step": 62
    },
    {
      "epoch": 0.0027393090853751333,
      "grad_norm": 0.3446858525276184,
      "learning_rate": 0.00018109066104575022,
      "loss": 1.4563,
      "step": 63
    },
    {
      "epoch": 0.0027827901819683894,
      "grad_norm": 0.27211225032806396,
      "learning_rate": 0.00017274575140626317,
      "loss": 1.2127,
      "step": 64
    },
    {
      "epoch": 0.0028262712785616455,
      "grad_norm": 0.30302250385284424,
      "learning_rate": 0.00016449496416858284,
      "loss": 1.3799,
      "step": 65
    },
    {
      "epoch": 0.0028697523751549012,
      "grad_norm": 0.3473919630050659,
      "learning_rate": 0.00015634835164602198,
      "loss": 1.3698,
      "step": 66
    },
    {
      "epoch": 0.0029132334717481573,
      "grad_norm": 0.32299569249153137,
      "learning_rate": 0.00014831583923105,
      "loss": 1.3153,
      "step": 67
    },
    {
      "epoch": 0.0029567145683414135,
      "grad_norm": 0.32637661695480347,
      "learning_rate": 0.00014040721330273062,
      "loss": 1.2902,
      "step": 68
    },
    {
      "epoch": 0.0030001956649346696,
      "grad_norm": 0.36671000719070435,
      "learning_rate": 0.00013263210930352737,
      "loss": 1.4733,
      "step": 69
    },
    {
      "epoch": 0.0030436767615279257,
      "grad_norm": 0.3126938045024872,
      "learning_rate": 0.00012500000000000006,
      "loss": 1.3166,
      "step": 70
    },
    {
      "epoch": 0.003087157858121182,
      "grad_norm": 0.31965765357017517,
      "learning_rate": 0.0001175201839416988,
      "loss": 1.3395,
      "step": 71
    },
    {
      "epoch": 0.003130638954714438,
      "grad_norm": 0.3339870870113373,
      "learning_rate": 0.00011020177413231333,
      "loss": 1.5952,
      "step": 72
    },
    {
      "epoch": 0.003174120051307694,
      "grad_norm": 0.4062851667404175,
      "learning_rate": 0.00010305368692688174,
      "loss": 1.331,
      "step": 73
    },
    {
      "epoch": 0.0032176011479009502,
      "grad_norm": 0.32616257667541504,
      "learning_rate": 9.608463116858542e-05,
      "loss": 1.2725,
      "step": 74
    },
    {
      "epoch": 0.0032610822444942063,
      "grad_norm": 0.28197285532951355,
      "learning_rate": 8.930309757836516e-05,
      "loss": 1.1204,
      "step": 75
    },
    {
      "epoch": 0.003304563341087462,
      "grad_norm": 0.31098294258117676,
      "learning_rate": 8.271734841028553e-05,
      "loss": 1.2576,
      "step": 76
    },
    {
      "epoch": 0.003348044437680718,
      "grad_norm": 0.3825020492076874,
      "learning_rate": 7.633540738525066e-05,
      "loss": 1.4109,
      "step": 77
    },
    {
      "epoch": 0.0033915255342739743,
      "grad_norm": 0.3050486445426941,
      "learning_rate": 7.016504991533726e-05,
      "loss": 1.2529,
      "step": 78
    },
    {
      "epoch": 0.0034350066308672304,
      "grad_norm": 0.32467782497406006,
      "learning_rate": 6.421379363065141e-05,
      "loss": 1.2961,
      "step": 79
    },
    {
      "epoch": 0.0034784877274604865,
      "grad_norm": 0.3699512481689453,
      "learning_rate": 5.848888922025553e-05,
      "loss": 1.3251,
      "step": 80
    },
    {
      "epoch": 0.0035219688240537427,
      "grad_norm": 0.4555168151855469,
      "learning_rate": 5.299731159831953e-05,
      "loss": 1.651,
      "step": 81
    },
    {
      "epoch": 0.003565449920646999,
      "grad_norm": 0.32544296979904175,
      "learning_rate": 4.7745751406263163e-05,
      "loss": 1.2075,
      "step": 82
    },
    {
      "epoch": 0.003608931017240255,
      "grad_norm": 0.39769333600997925,
      "learning_rate": 4.274060686123959e-05,
      "loss": 1.2517,
      "step": 83
    },
    {
      "epoch": 0.003652412113833511,
      "grad_norm": 0.3152201175689697,
      "learning_rate": 3.798797596089351e-05,
      "loss": 1.2101,
      "step": 84
    },
    {
      "epoch": 0.003695893210426767,
      "grad_norm": 0.316663533449173,
      "learning_rate": 3.3493649053890325e-05,
      "loss": 1.2251,
      "step": 85
    },
    {
      "epoch": 0.003739374307020023,
      "grad_norm": 0.35027015209198,
      "learning_rate": 2.9263101785268254e-05,
      "loss": 1.4636,
      "step": 86
    },
    {
      "epoch": 0.003782855403613279,
      "grad_norm": 0.3649485409259796,
      "learning_rate": 2.5301488425208295e-05,
      "loss": 1.4837,
      "step": 87
    },
    {
      "epoch": 0.003826336500206535,
      "grad_norm": 0.2650792598724365,
      "learning_rate": 2.1613635589349755e-05,
      "loss": 1.2395,
      "step": 88
    },
    {
      "epoch": 0.0038698175967997912,
      "grad_norm": 0.3441864252090454,
      "learning_rate": 1.8204036358303172e-05,
      "loss": 1.4893,
      "step": 89
    },
    {
      "epoch": 0.003913298693393048,
      "grad_norm": 0.3505742847919464,
      "learning_rate": 1.5076844803522921e-05,
      "loss": 1.3992,
      "step": 90
    },
    {
      "epoch": 0.003913298693393048,
      "eval_loss": 1.3718498945236206,
      "eval_runtime": 200.4209,
      "eval_samples_per_second": 48.318,
      "eval_steps_per_second": 24.159,
      "step": 90
    },
    {
      "epoch": 0.0039567797899863035,
      "grad_norm": 0.3765980005264282,
      "learning_rate": 1.2235870926211617e-05,
      "loss": 1.3013,
      "step": 91
    },
    {
      "epoch": 0.004000260886579559,
      "grad_norm": 0.32098492980003357,
      "learning_rate": 9.684576015420277e-06,
      "loss": 1.4673,
      "step": 92
    },
    {
      "epoch": 0.004043741983172816,
      "grad_norm": 0.28441664576530457,
      "learning_rate": 7.426068431000882e-06,
      "loss": 1.296,
      "step": 93
    },
    {
      "epoch": 0.004087223079766071,
      "grad_norm": 0.30115729570388794,
      "learning_rate": 5.463099816548578e-06,
      "loss": 1.2836,
      "step": 94
    },
    {
      "epoch": 0.004130704176359328,
      "grad_norm": 0.3514503836631775,
      "learning_rate": 3.798061746947995e-06,
      "loss": 1.3655,
      "step": 95
    },
    {
      "epoch": 0.004174185272952584,
      "grad_norm": 0.3625047504901886,
      "learning_rate": 2.4329828146074094e-06,
      "loss": 1.4103,
      "step": 96
    },
    {
      "epoch": 0.00421766636954584,
      "grad_norm": 0.29829010367393494,
      "learning_rate": 1.3695261579316775e-06,
      "loss": 1.2565,
      "step": 97
    },
    {
      "epoch": 0.004261147466139096,
      "grad_norm": 0.35181766748428345,
      "learning_rate": 6.089874350439506e-07,
      "loss": 1.4426,
      "step": 98
    },
    {
      "epoch": 0.0043046285627323525,
      "grad_norm": 0.34040647745132446,
      "learning_rate": 1.5229324522605948e-07,
      "loss": 1.5999,
      "step": 99
    },
    {
      "epoch": 0.004348109659325608,
      "grad_norm": 0.38123124837875366,
      "learning_rate": 0.0,
      "loss": 1.4659,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 300,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 862309554585600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}