{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.39564787339268054,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003956478733926805,
      "grad_norm": 23.302045822143555,
      "learning_rate": 0.0,
      "loss": 16.2961,
      "step": 1
    },
    {
      "epoch": 0.00791295746785361,
      "grad_norm": 27.37419319152832,
      "learning_rate": 4e-05,
      "loss": 18.4332,
      "step": 2
    },
    {
      "epoch": 0.011869436201780416,
      "grad_norm": 27.051715850830078,
      "learning_rate": 8e-05,
      "loss": 18.1618,
      "step": 3
    },
    {
      "epoch": 0.01582591493570722,
      "grad_norm": 25.241186141967773,
      "learning_rate": 0.00012,
      "loss": 15.8617,
      "step": 4
    },
    {
      "epoch": 0.019782393669634024,
      "grad_norm": 19.574819564819336,
      "learning_rate": 0.00016,
      "loss": 12.3903,
      "step": 5
    },
    {
      "epoch": 0.02373887240356083,
      "grad_norm": 14.805221557617188,
      "learning_rate": 0.0002,
      "loss": 11.0495,
      "step": 6
    },
    {
      "epoch": 0.027695351137487636,
      "grad_norm": 8.009269714355469,
      "learning_rate": 0.00019789473684210526,
      "loss": 8.2391,
      "step": 7
    },
    {
      "epoch": 0.03165182987141444,
      "grad_norm": 6.785006523132324,
      "learning_rate": 0.00019578947368421054,
      "loss": 7.9713,
      "step": 8
    },
    {
      "epoch": 0.03560830860534125,
      "grad_norm": 6.116010665893555,
      "learning_rate": 0.0001936842105263158,
      "loss": 7.2536,
      "step": 9
    },
    {
      "epoch": 0.03956478733926805,
      "grad_norm": 7.095190048217773,
      "learning_rate": 0.00019157894736842104,
      "loss": 7.2029,
      "step": 10
    },
    {
      "epoch": 0.043521266073194856,
      "grad_norm": 6.16122579574585,
      "learning_rate": 0.00018947368421052632,
      "loss": 6.6535,
      "step": 11
    },
    {
      "epoch": 0.04747774480712166,
      "grad_norm": 5.9373626708984375,
      "learning_rate": 0.0001873684210526316,
      "loss": 6.6532,
      "step": 12
    },
    {
      "epoch": 0.051434223541048464,
      "grad_norm": 3.409684896469116,
      "learning_rate": 0.00018526315789473685,
      "loss": 6.1402,
      "step": 13
    },
    {
      "epoch": 0.05539070227497527,
      "grad_norm": 2.748903512954712,
      "learning_rate": 0.0001831578947368421,
      "loss": 5.544,
      "step": 14
    },
    {
      "epoch": 0.05934718100890208,
      "grad_norm": 2.9191884994506836,
      "learning_rate": 0.00018105263157894739,
      "loss": 6.5131,
      "step": 15
    },
    {
      "epoch": 0.06330365974282888,
      "grad_norm": 2.935926675796509,
      "learning_rate": 0.00017894736842105264,
      "loss": 5.0912,
      "step": 16
    },
    {
      "epoch": 0.06726013847675569,
      "grad_norm": 2.6484129428863525,
      "learning_rate": 0.0001768421052631579,
      "loss": 5.4763,
      "step": 17
    },
    {
      "epoch": 0.0712166172106825,
      "grad_norm": 2.2135961055755615,
      "learning_rate": 0.00017473684210526317,
      "loss": 5.1443,
      "step": 18
    },
    {
      "epoch": 0.0751730959446093,
      "grad_norm": 2.2263529300689697,
      "learning_rate": 0.00017263157894736842,
      "loss": 5.6504,
      "step": 19
    },
    {
      "epoch": 0.0791295746785361,
      "grad_norm": 2.599684476852417,
      "learning_rate": 0.0001705263157894737,
      "loss": 4.7292,
      "step": 20
    },
    {
      "epoch": 0.0830860534124629,
      "grad_norm": 2.9603826999664307,
      "learning_rate": 0.00016842105263157895,
      "loss": 5.4304,
      "step": 21
    },
    {
      "epoch": 0.08704253214638971,
      "grad_norm": 2.178344249725342,
      "learning_rate": 0.00016631578947368423,
      "loss": 6.4425,
      "step": 22
    },
    {
      "epoch": 0.09099901088031652,
      "grad_norm": 2.872128963470459,
      "learning_rate": 0.00016421052631578948,
      "loss": 5.4385,
      "step": 23
    },
    {
      "epoch": 0.09495548961424333,
      "grad_norm": 2.738940715789795,
      "learning_rate": 0.00016210526315789473,
      "loss": 5.4402,
      "step": 24
    },
    {
      "epoch": 0.09891196834817013,
      "grad_norm": 3.214587688446045,
      "learning_rate": 0.00016,
      "loss": 4.7338,
      "step": 25
    },
    {
      "epoch": 0.10286844708209693,
      "grad_norm": 2.9738221168518066,
      "learning_rate": 0.00015789473684210527,
      "loss": 5.4748,
      "step": 26
    },
    {
      "epoch": 0.10682492581602374,
      "grad_norm": 3.050741195678711,
      "learning_rate": 0.00015578947368421052,
      "loss": 5.1201,
      "step": 27
    },
    {
      "epoch": 0.11078140454995054,
      "grad_norm": 3.187633991241455,
      "learning_rate": 0.0001536842105263158,
      "loss": 5.3061,
      "step": 28
    },
    {
      "epoch": 0.11473788328387735,
      "grad_norm": 2.965158700942993,
      "learning_rate": 0.00015157894736842108,
      "loss": 4.9141,
      "step": 29
    },
    {
      "epoch": 0.11869436201780416,
      "grad_norm": 2.6440789699554443,
      "learning_rate": 0.00014947368421052633,
      "loss": 4.4023,
      "step": 30
    },
    {
      "epoch": 0.12265084075173097,
      "grad_norm": 4.033472061157227,
      "learning_rate": 0.00014736842105263158,
      "loss": 7.4582,
      "step": 31
    },
    {
      "epoch": 0.12660731948565776,
      "grad_norm": 3.3675754070281982,
      "learning_rate": 0.00014526315789473686,
      "loss": 4.6167,
      "step": 32
    },
    {
      "epoch": 0.13056379821958458,
      "grad_norm": 3.0074822902679443,
      "learning_rate": 0.0001431578947368421,
      "loss": 4.8099,
      "step": 33
    },
    {
      "epoch": 0.13452027695351138,
      "grad_norm": 2.872875690460205,
      "learning_rate": 0.00014105263157894736,
      "loss": 4.8146,
      "step": 34
    },
    {
      "epoch": 0.13847675568743817,
      "grad_norm": 3.0648305416107178,
      "learning_rate": 0.00013894736842105264,
      "loss": 5.9663,
      "step": 35
    },
    {
      "epoch": 0.142433234421365,
      "grad_norm": 3.0596470832824707,
      "learning_rate": 0.0001368421052631579,
      "loss": 4.8893,
      "step": 36
    },
    {
      "epoch": 0.14638971315529178,
      "grad_norm": 3.099954843521118,
      "learning_rate": 0.00013473684210526317,
      "loss": 5.9515,
      "step": 37
    },
    {
      "epoch": 0.1503461918892186,
      "grad_norm": 2.4886155128479004,
      "learning_rate": 0.00013263157894736842,
      "loss": 4.1192,
      "step": 38
    },
    {
      "epoch": 0.1543026706231454,
      "grad_norm": 3.0190577507019043,
      "learning_rate": 0.0001305263157894737,
      "loss": 6.2374,
      "step": 39
    },
    {
      "epoch": 0.1582591493570722,
      "grad_norm": 3.001729726791382,
      "learning_rate": 0.00012842105263157895,
      "loss": 5.051,
      "step": 40
    },
    {
      "epoch": 0.16221562809099901,
      "grad_norm": 3.3806393146514893,
      "learning_rate": 0.0001263157894736842,
      "loss": 5.2736,
      "step": 41
    },
    {
      "epoch": 0.1661721068249258,
      "grad_norm": 3.381579637527466,
      "learning_rate": 0.00012421052631578949,
      "loss": 5.5759,
      "step": 42
    },
    {
      "epoch": 0.17012858555885263,
      "grad_norm": 3.010310411453247,
      "learning_rate": 0.00012210526315789474,
      "loss": 5.106,
      "step": 43
    },
    {
      "epoch": 0.17408506429277942,
      "grad_norm": 2.5623176097869873,
      "learning_rate": 0.00012,
      "loss": 5.5447,
      "step": 44
    },
    {
      "epoch": 0.17804154302670624,
      "grad_norm": 3.0234758853912354,
      "learning_rate": 0.00011789473684210525,
      "loss": 4.3962,
      "step": 45
    },
    {
      "epoch": 0.18199802176063304,
      "grad_norm": 2.936678886413574,
      "learning_rate": 0.00011578947368421053,
      "loss": 5.5828,
      "step": 46
    },
    {
      "epoch": 0.18595450049455983,
      "grad_norm": 3.5103631019592285,
      "learning_rate": 0.0001136842105263158,
      "loss": 4.3974,
      "step": 47
    },
    {
      "epoch": 0.18991097922848665,
      "grad_norm": 3.447932720184326,
      "learning_rate": 0.00011157894736842105,
      "loss": 5.7814,
      "step": 48
    },
    {
      "epoch": 0.19386745796241345,
      "grad_norm": 2.6578755378723145,
      "learning_rate": 0.00010947368421052633,
      "loss": 4.732,
      "step": 49
    },
    {
      "epoch": 0.19782393669634027,
      "grad_norm": 2.9903833866119385,
      "learning_rate": 0.00010736842105263158,
      "loss": 4.3962,
      "step": 50
    },
    {
      "epoch": 0.20178041543026706,
      "grad_norm": 2.790576696395874,
      "learning_rate": 0.00010526315789473685,
      "loss": 4.8403,
      "step": 51
    },
    {
      "epoch": 0.20573689416419386,
      "grad_norm": 3.302182912826538,
      "learning_rate": 0.00010315789473684211,
      "loss": 4.607,
      "step": 52
    },
    {
      "epoch": 0.20969337289812068,
      "grad_norm": 3.1099631786346436,
      "learning_rate": 0.00010105263157894738,
      "loss": 4.9049,
      "step": 53
    },
    {
      "epoch": 0.21364985163204747,
      "grad_norm": 3.343353509902954,
      "learning_rate": 9.894736842105263e-05,
      "loss": 5.6211,
      "step": 54
    },
    {
      "epoch": 0.2176063303659743,
      "grad_norm": 4.264265060424805,
      "learning_rate": 9.68421052631579e-05,
      "loss": 6.1449,
      "step": 55
    },
    {
      "epoch": 0.2215628090999011,
      "grad_norm": 2.6139657497406006,
      "learning_rate": 9.473684210526316e-05,
      "loss": 5.3725,
      "step": 56
    },
    {
      "epoch": 0.22551928783382788,
      "grad_norm": 3.1093761920928955,
      "learning_rate": 9.263157894736843e-05,
      "loss": 5.158,
      "step": 57
    },
    {
      "epoch": 0.2294757665677547,
      "grad_norm": 2.8728318214416504,
      "learning_rate": 9.052631578947369e-05,
      "loss": 5.2214,
      "step": 58
    },
    {
      "epoch": 0.2334322453016815,
      "grad_norm": 3.1342532634735107,
      "learning_rate": 8.842105263157894e-05,
      "loss": 6.7797,
      "step": 59
    },
    {
      "epoch": 0.23738872403560832,
      "grad_norm": 2.9147534370422363,
      "learning_rate": 8.631578947368421e-05,
      "loss": 4.9591,
      "step": 60
    },
    {
      "epoch": 0.2413452027695351,
      "grad_norm": 2.71091365814209,
      "learning_rate": 8.421052631578948e-05,
      "loss": 5.5919,
      "step": 61
    },
    {
      "epoch": 0.24530168150346193,
      "grad_norm": 4.9715681076049805,
      "learning_rate": 8.210526315789474e-05,
      "loss": 7.9325,
      "step": 62
    },
    {
      "epoch": 0.24925816023738873,
      "grad_norm": 3.243007183074951,
      "learning_rate": 8e-05,
      "loss": 4.9809,
      "step": 63
    },
    {
      "epoch": 0.2532146389713155,
      "grad_norm": 2.425530433654785,
      "learning_rate": 7.789473684210526e-05,
      "loss": 4.7267,
      "step": 64
    },
    {
      "epoch": 0.2571711177052423,
      "grad_norm": 2.584341526031494,
      "learning_rate": 7.578947368421054e-05,
      "loss": 5.1655,
      "step": 65
    },
    {
      "epoch": 0.26112759643916916,
      "grad_norm": 2.864600658416748,
      "learning_rate": 7.368421052631579e-05,
      "loss": 4.7094,
      "step": 66
    },
    {
      "epoch": 0.26508407517309596,
      "grad_norm": 2.7184255123138428,
      "learning_rate": 7.157894736842105e-05,
      "loss": 5.0806,
      "step": 67
    },
    {
      "epoch": 0.26904055390702275,
      "grad_norm": 3.3327622413635254,
      "learning_rate": 6.947368421052632e-05,
      "loss": 4.8204,
      "step": 68
    },
    {
      "epoch": 0.27299703264094954,
      "grad_norm": 2.6390984058380127,
      "learning_rate": 6.736842105263159e-05,
      "loss": 4.4369,
      "step": 69
    },
    {
      "epoch": 0.27695351137487634,
      "grad_norm": 2.8620619773864746,
      "learning_rate": 6.526315789473685e-05,
      "loss": 4.8152,
      "step": 70
    },
    {
      "epoch": 0.2809099901088032,
      "grad_norm": 2.886209011077881,
      "learning_rate": 6.31578947368421e-05,
      "loss": 4.5341,
      "step": 71
    },
    {
      "epoch": 0.28486646884273,
      "grad_norm": 3.60684871673584,
      "learning_rate": 6.105263157894737e-05,
      "loss": 5.147,
      "step": 72
    },
    {
      "epoch": 0.2888229475766568,
      "grad_norm": 2.6427412033081055,
      "learning_rate": 5.894736842105263e-05,
      "loss": 5.1367,
      "step": 73
    },
    {
      "epoch": 0.29277942631058357,
      "grad_norm": 3.7594962120056152,
      "learning_rate": 5.68421052631579e-05,
      "loss": 5.821,
      "step": 74
    },
    {
      "epoch": 0.29673590504451036,
      "grad_norm": 2.2990944385528564,
      "learning_rate": 5.4736842105263165e-05,
      "loss": 4.6194,
      "step": 75
    },
    {
      "epoch": 0.3006923837784372,
      "grad_norm": 2.6638574600219727,
      "learning_rate": 5.2631578947368424e-05,
      "loss": 5.8379,
      "step": 76
    },
    {
      "epoch": 0.304648862512364,
      "grad_norm": 3.256946086883545,
      "learning_rate": 5.052631578947369e-05,
      "loss": 5.1437,
      "step": 77
    },
    {
      "epoch": 0.3086053412462908,
      "grad_norm": 2.8275022506713867,
      "learning_rate": 4.842105263157895e-05,
      "loss": 5.0719,
      "step": 78
    },
    {
      "epoch": 0.3125618199802176,
      "grad_norm": 2.6694302558898926,
      "learning_rate": 4.6315789473684214e-05,
      "loss": 4.9186,
      "step": 79
    },
    {
      "epoch": 0.3165182987141444,
      "grad_norm": 3.2759788036346436,
      "learning_rate": 4.421052631578947e-05,
      "loss": 4.7457,
      "step": 80
    },
    {
      "epoch": 0.32047477744807124,
      "grad_norm": 3.3160855770111084,
      "learning_rate": 4.210526315789474e-05,
      "loss": 4.2814,
      "step": 81
    },
    {
      "epoch": 0.32443125618199803,
      "grad_norm": 2.8146486282348633,
      "learning_rate": 4e-05,
      "loss": 4.8129,
      "step": 82
    },
    {
      "epoch": 0.3283877349159248,
      "grad_norm": 2.767481565475464,
      "learning_rate": 3.789473684210527e-05,
      "loss": 5.5585,
      "step": 83
    },
    {
      "epoch": 0.3323442136498516,
      "grad_norm": 3.330084800720215,
      "learning_rate": 3.578947368421053e-05,
      "loss": 5.271,
      "step": 84
    },
    {
      "epoch": 0.3363006923837784,
      "grad_norm": 2.786287546157837,
      "learning_rate": 3.368421052631579e-05,
      "loss": 4.7267,
      "step": 85
    },
    {
      "epoch": 0.34025717111770526,
      "grad_norm": 3.373779296875,
      "learning_rate": 3.157894736842105e-05,
      "loss": 5.3886,
      "step": 86
    },
    {
      "epoch": 0.34421364985163205,
      "grad_norm": 2.731201171875,
      "learning_rate": 2.9473684210526314e-05,
      "loss": 5.1014,
      "step": 87
    },
    {
      "epoch": 0.34817012858555885,
      "grad_norm": 3.213326930999756,
      "learning_rate": 2.7368421052631583e-05,
      "loss": 5.2954,
      "step": 88
    },
    {
      "epoch": 0.35212660731948564,
      "grad_norm": 2.9587507247924805,
      "learning_rate": 2.5263157894736845e-05,
      "loss": 4.9975,
      "step": 89
    },
    {
      "epoch": 0.3560830860534125,
      "grad_norm": 2.7448644638061523,
      "learning_rate": 2.3157894736842107e-05,
      "loss": 4.8342,
      "step": 90
    },
    {
      "epoch": 0.3600395647873393,
      "grad_norm": 3.670548915863037,
      "learning_rate": 2.105263157894737e-05,
      "loss": 5.6434,
      "step": 91
    },
    {
      "epoch": 0.3639960435212661,
      "grad_norm": 3.459158182144165,
      "learning_rate": 1.8947368421052634e-05,
      "loss": 4.0876,
      "step": 92
    },
    {
      "epoch": 0.36795252225519287,
      "grad_norm": 2.871955633163452,
      "learning_rate": 1.6842105263157896e-05,
      "loss": 5.4301,
      "step": 93
    },
    {
      "epoch": 0.37190900098911966,
      "grad_norm": 3.1002166271209717,
      "learning_rate": 1.4736842105263157e-05,
      "loss": 4.7507,
      "step": 94
    },
    {
      "epoch": 0.3758654797230465,
      "grad_norm": 2.540811061859131,
      "learning_rate": 1.2631578947368422e-05,
      "loss": 4.8875,
      "step": 95
    },
    {
      "epoch": 0.3798219584569733,
      "grad_norm": 3.154196262359619,
      "learning_rate": 1.0526315789473684e-05,
      "loss": 5.8064,
      "step": 96
    },
    {
      "epoch": 0.3837784371909001,
      "grad_norm": 2.2360923290252686,
      "learning_rate": 8.421052631578948e-06,
      "loss": 5.1602,
      "step": 97
    },
    {
      "epoch": 0.3877349159248269,
      "grad_norm": 4.483743667602539,
      "learning_rate": 6.315789473684211e-06,
      "loss": 6.253,
      "step": 98
    },
    {
      "epoch": 0.3916913946587537,
      "grad_norm": 2.8893954753875732,
      "learning_rate": 4.210526315789474e-06,
      "loss": 4.7195,
      "step": 99
    },
    {
      "epoch": 0.39564787339268054,
      "grad_norm": 3.337634325027466,
      "learning_rate": 2.105263157894737e-06,
      "loss": 5.5186,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2480523648539904.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}