{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.008073794481561472,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.073794481561473e-05,
      "grad_norm": 1.4461750984191895,
      "learning_rate": 0.0,
      "loss": 1.2972,
      "step": 1
    },
    {
      "epoch": 0.00016147588963122945,
      "grad_norm": 1.5243606567382812,
      "learning_rate": 4e-05,
      "loss": 1.3534,
      "step": 2
    },
    {
      "epoch": 0.00024221383444684416,
      "grad_norm": 0.8831276893615723,
      "learning_rate": 8e-05,
      "loss": 1.2616,
      "step": 3
    },
    {
      "epoch": 0.0003229517792624589,
      "grad_norm": 0.7445989847183228,
      "learning_rate": 0.00012,
      "loss": 1.1603,
      "step": 4
    },
    {
      "epoch": 0.0004036897240780736,
      "grad_norm": 0.7170802354812622,
      "learning_rate": 0.00016,
      "loss": 1.0995,
      "step": 5
    },
    {
      "epoch": 0.0004844276688936883,
      "grad_norm": 0.6993922591209412,
      "learning_rate": 0.0002,
      "loss": 1.0422,
      "step": 6
    },
    {
      "epoch": 0.0005651656137093031,
      "grad_norm": 0.8005324006080627,
      "learning_rate": 0.00019789473684210526,
      "loss": 0.9699,
      "step": 7
    },
    {
      "epoch": 0.0006459035585249178,
      "grad_norm": 0.7599121928215027,
      "learning_rate": 0.00019578947368421054,
      "loss": 0.8233,
      "step": 8
    },
    {
      "epoch": 0.0007266415033405324,
      "grad_norm": 0.6091116070747375,
      "learning_rate": 0.0001936842105263158,
      "loss": 0.7983,
      "step": 9
    },
    {
      "epoch": 0.0008073794481561472,
      "grad_norm": 0.5224089622497559,
      "learning_rate": 0.00019157894736842104,
      "loss": 0.7462,
      "step": 10
    },
    {
      "epoch": 0.0008881173929717619,
      "grad_norm": 0.45331522822380066,
      "learning_rate": 0.00018947368421052632,
      "loss": 0.756,
      "step": 11
    },
    {
      "epoch": 0.0009688553377873766,
      "grad_norm": 0.4153309166431427,
      "learning_rate": 0.0001873684210526316,
      "loss": 0.7931,
      "step": 12
    },
    {
      "epoch": 0.0010495932826029913,
      "grad_norm": 0.3990932106971741,
      "learning_rate": 0.00018526315789473685,
      "loss": 0.7383,
      "step": 13
    },
    {
      "epoch": 0.0011303312274186061,
      "grad_norm": 0.39721938967704773,
      "learning_rate": 0.0001831578947368421,
      "loss": 0.7421,
      "step": 14
    },
    {
      "epoch": 0.0012110691722342208,
      "grad_norm": 0.37865254282951355,
      "learning_rate": 0.00018105263157894739,
      "loss": 0.7693,
      "step": 15
    },
    {
      "epoch": 0.0012918071170498356,
      "grad_norm": 0.3562251627445221,
      "learning_rate": 0.00017894736842105264,
      "loss": 0.7291,
      "step": 16
    },
    {
      "epoch": 0.0013725450618654502,
      "grad_norm": 0.3385823965072632,
      "learning_rate": 0.0001768421052631579,
      "loss": 0.7434,
      "step": 17
    },
    {
      "epoch": 0.0014532830066810649,
      "grad_norm": 0.3341878652572632,
      "learning_rate": 0.00017473684210526317,
      "loss": 0.7304,
      "step": 18
    },
    {
      "epoch": 0.0015340209514966797,
      "grad_norm": 0.3336416184902191,
      "learning_rate": 0.00017263157894736842,
      "loss": 0.7086,
      "step": 19
    },
    {
      "epoch": 0.0016147588963122943,
      "grad_norm": 0.33498045802116394,
      "learning_rate": 0.0001705263157894737,
      "loss": 0.6607,
      "step": 20
    },
    {
      "epoch": 0.0016954968411279092,
      "grad_norm": 0.34477856755256653,
      "learning_rate": 0.00016842105263157895,
      "loss": 0.714,
      "step": 21
    },
    {
      "epoch": 0.0017762347859435238,
      "grad_norm": 0.3235958218574524,
      "learning_rate": 0.00016631578947368423,
      "loss": 0.7085,
      "step": 22
    },
    {
      "epoch": 0.0018569727307591385,
      "grad_norm": 0.35956770181655884,
      "learning_rate": 0.00016421052631578948,
      "loss": 0.7186,
      "step": 23
    },
    {
      "epoch": 0.0019377106755747533,
      "grad_norm": 0.317914754152298,
      "learning_rate": 0.00016210526315789473,
      "loss": 0.6949,
      "step": 24
    },
    {
      "epoch": 0.002018448620390368,
      "grad_norm": 0.3337765336036682,
      "learning_rate": 0.00016,
      "loss": 0.6955,
      "step": 25
    },
    {
      "epoch": 0.0020991865652059826,
      "grad_norm": 0.34514784812927246,
      "learning_rate": 0.00015789473684210527,
      "loss": 0.6717,
      "step": 26
    },
    {
      "epoch": 0.002179924510021597,
      "grad_norm": 0.3283939063549042,
      "learning_rate": 0.00015578947368421052,
      "loss": 0.6593,
      "step": 27
    },
    {
      "epoch": 0.0022606624548372123,
      "grad_norm": 0.33200809359550476,
      "learning_rate": 0.0001536842105263158,
      "loss": 0.693,
      "step": 28
    },
    {
      "epoch": 0.002341400399652827,
      "grad_norm": 0.34666284918785095,
      "learning_rate": 0.00015157894736842108,
      "loss": 0.6988,
      "step": 29
    },
    {
      "epoch": 0.0024221383444684415,
      "grad_norm": 0.37149596214294434,
      "learning_rate": 0.00014947368421052633,
      "loss": 0.6954,
      "step": 30
    },
    {
      "epoch": 0.002502876289284056,
      "grad_norm": 0.3310442864894867,
      "learning_rate": 0.00014736842105263158,
      "loss": 0.69,
      "step": 31
    },
    {
      "epoch": 0.002583614234099671,
      "grad_norm": 0.3307671844959259,
      "learning_rate": 0.00014526315789473686,
      "loss": 0.7114,
      "step": 32
    },
    {
      "epoch": 0.002664352178915286,
      "grad_norm": 0.34910285472869873,
      "learning_rate": 0.0001431578947368421,
      "loss": 0.6726,
      "step": 33
    },
    {
      "epoch": 0.0027450901237309005,
      "grad_norm": 0.32629451155662537,
      "learning_rate": 0.00014105263157894736,
      "loss": 0.6627,
      "step": 34
    },
    {
      "epoch": 0.002825828068546515,
      "grad_norm": 0.3132249414920807,
      "learning_rate": 0.00013894736842105264,
      "loss": 0.6676,
      "step": 35
    },
    {
      "epoch": 0.0029065660133621297,
      "grad_norm": 0.3174385130405426,
      "learning_rate": 0.0001368421052631579,
      "loss": 0.6912,
      "step": 36
    },
    {
      "epoch": 0.002987303958177745,
      "grad_norm": 0.32051149010658264,
      "learning_rate": 0.00013473684210526317,
      "loss": 0.7093,
      "step": 37
    },
    {
      "epoch": 0.0030680419029933594,
      "grad_norm": 0.350221186876297,
      "learning_rate": 0.00013263157894736842,
      "loss": 0.6999,
      "step": 38
    },
    {
      "epoch": 0.003148779847808974,
      "grad_norm": 0.33227774500846863,
      "learning_rate": 0.0001305263157894737,
      "loss": 0.6852,
      "step": 39
    },
    {
      "epoch": 0.0032295177926245887,
      "grad_norm": 0.30808618664741516,
      "learning_rate": 0.00012842105263157895,
      "loss": 0.6547,
      "step": 40
    },
    {
      "epoch": 0.0033102557374402033,
      "grad_norm": 0.3285318613052368,
      "learning_rate": 0.0001263157894736842,
      "loss": 0.665,
      "step": 41
    },
    {
      "epoch": 0.0033909936822558184,
      "grad_norm": 0.3193379342556,
      "learning_rate": 0.00012421052631578949,
      "loss": 0.6744,
      "step": 42
    },
    {
      "epoch": 0.003471731627071433,
      "grad_norm": 0.29980984330177307,
      "learning_rate": 0.00012210526315789474,
      "loss": 0.6694,
      "step": 43
    },
    {
      "epoch": 0.0035524695718870476,
      "grad_norm": 0.29726454615592957,
      "learning_rate": 0.00012,
      "loss": 0.7009,
      "step": 44
    },
    {
      "epoch": 0.0036332075167026623,
      "grad_norm": 0.3046688139438629,
      "learning_rate": 0.00011789473684210525,
      "loss": 0.6931,
      "step": 45
    },
    {
      "epoch": 0.003713945461518277,
      "grad_norm": 0.30899032950401306,
      "learning_rate": 0.00011578947368421053,
      "loss": 0.6672,
      "step": 46
    },
    {
      "epoch": 0.003794683406333892,
      "grad_norm": 0.32200363278388977,
      "learning_rate": 0.0001136842105263158,
      "loss": 0.6233,
      "step": 47
    },
    {
      "epoch": 0.0038754213511495066,
      "grad_norm": 0.30770131945610046,
      "learning_rate": 0.00011157894736842105,
      "loss": 0.7133,
      "step": 48
    },
    {
      "epoch": 0.003956159295965121,
      "grad_norm": 0.31568217277526855,
      "learning_rate": 0.00010947368421052633,
      "loss": 0.6425,
      "step": 49
    },
    {
      "epoch": 0.004036897240780736,
      "grad_norm": 0.3203376829624176,
      "learning_rate": 0.00010736842105263158,
      "loss": 0.6844,
      "step": 50
    },
    {
      "epoch": 0.0041176351855963505,
      "grad_norm": 0.3009225130081177,
      "learning_rate": 0.00010526315789473685,
      "loss": 0.6549,
      "step": 51
    },
    {
      "epoch": 0.004198373130411965,
      "grad_norm": 0.31444495916366577,
      "learning_rate": 0.00010315789473684211,
      "loss": 0.6583,
      "step": 52
    },
    {
      "epoch": 0.00427911107522758,
      "grad_norm": 0.31305891275405884,
      "learning_rate": 0.00010105263157894738,
      "loss": 0.6635,
      "step": 53
    },
    {
      "epoch": 0.004359849020043194,
      "grad_norm": 0.29481881856918335,
      "learning_rate": 9.894736842105263e-05,
      "loss": 0.6707,
      "step": 54
    },
    {
      "epoch": 0.00444058696485881,
      "grad_norm": 0.31360143423080444,
      "learning_rate": 9.68421052631579e-05,
      "loss": 0.6486,
      "step": 55
    },
    {
      "epoch": 0.0045213249096744245,
      "grad_norm": 0.33028149604797363,
      "learning_rate": 9.473684210526316e-05,
      "loss": 0.6825,
      "step": 56
    },
    {
      "epoch": 0.004602062854490039,
      "grad_norm": 0.3195054233074188,
      "learning_rate": 9.263157894736843e-05,
      "loss": 0.6564,
      "step": 57
    },
    {
      "epoch": 0.004682800799305654,
      "grad_norm": 0.3149634897708893,
      "learning_rate": 9.052631578947369e-05,
      "loss": 0.7034,
      "step": 58
    },
    {
      "epoch": 0.004763538744121268,
      "grad_norm": 0.3093666434288025,
      "learning_rate": 8.842105263157894e-05,
      "loss": 0.7128,
      "step": 59
    },
    {
      "epoch": 0.004844276688936883,
      "grad_norm": 0.3070853054523468,
      "learning_rate": 8.631578947368421e-05,
      "loss": 0.6541,
      "step": 60
    },
    {
      "epoch": 0.004925014633752498,
      "grad_norm": 0.32141491770744324,
      "learning_rate": 8.421052631578948e-05,
      "loss": 0.6684,
      "step": 61
    },
    {
      "epoch": 0.005005752578568112,
      "grad_norm": 0.32146668434143066,
      "learning_rate": 8.210526315789474e-05,
      "loss": 0.6286,
      "step": 62
    },
    {
      "epoch": 0.005086490523383727,
      "grad_norm": 0.31124749779701233,
      "learning_rate": 8e-05,
      "loss": 0.6426,
      "step": 63
    },
    {
      "epoch": 0.005167228468199342,
      "grad_norm": 0.29654479026794434,
      "learning_rate": 7.789473684210526e-05,
      "loss": 0.6714,
      "step": 64
    },
    {
      "epoch": 0.005247966413014957,
      "grad_norm": 0.30790746212005615,
      "learning_rate": 7.578947368421054e-05,
      "loss": 0.7107,
      "step": 65
    },
    {
      "epoch": 0.005328704357830572,
      "grad_norm": 0.308814138174057,
      "learning_rate": 7.368421052631579e-05,
      "loss": 0.6273,
      "step": 66
    },
    {
      "epoch": 0.005409442302646186,
      "grad_norm": 0.3237323760986328,
      "learning_rate": 7.157894736842105e-05,
      "loss": 0.6641,
      "step": 67
    },
    {
      "epoch": 0.005490180247461801,
      "grad_norm": 0.3249422609806061,
      "learning_rate": 6.947368421052632e-05,
      "loss": 0.696,
      "step": 68
    },
    {
      "epoch": 0.005570918192277416,
      "grad_norm": 0.30125707387924194,
      "learning_rate": 6.736842105263159e-05,
      "loss": 0.6618,
      "step": 69
    },
    {
      "epoch": 0.00565165613709303,
      "grad_norm": 0.317377507686615,
      "learning_rate": 6.526315789473685e-05,
      "loss": 0.6535,
      "step": 70
    },
    {
      "epoch": 0.005732394081908645,
      "grad_norm": 0.32331615686416626,
      "learning_rate": 6.31578947368421e-05,
      "loss": 0.6685,
      "step": 71
    },
    {
      "epoch": 0.0058131320267242595,
      "grad_norm": 0.3125118613243103,
      "learning_rate": 6.105263157894737e-05,
      "loss": 0.6281,
      "step": 72
    },
    {
      "epoch": 0.005893869971539874,
      "grad_norm": 0.32349908351898193,
      "learning_rate": 5.894736842105263e-05,
      "loss": 0.6075,
      "step": 73
    },
    {
      "epoch": 0.00597460791635549,
      "grad_norm": 0.3256225287914276,
      "learning_rate": 5.68421052631579e-05,
      "loss": 0.6647,
      "step": 74
    },
    {
      "epoch": 0.006055345861171104,
      "grad_norm": 0.3693388104438782,
      "learning_rate": 5.4736842105263165e-05,
      "loss": 0.6905,
      "step": 75
    },
    {
      "epoch": 0.006136083805986719,
      "grad_norm": 0.33075031638145447,
      "learning_rate": 5.2631578947368424e-05,
      "loss": 0.6702,
      "step": 76
    },
    {
      "epoch": 0.0062168217508023335,
      "grad_norm": 0.3588313162326813,
      "learning_rate": 5.052631578947369e-05,
      "loss": 0.636,
      "step": 77
    },
    {
      "epoch": 0.006297559695617948,
      "grad_norm": 0.35506919026374817,
      "learning_rate": 4.842105263157895e-05,
      "loss": 0.685,
      "step": 78
    },
    {
      "epoch": 0.006378297640433563,
      "grad_norm": 0.35073211789131165,
      "learning_rate": 4.6315789473684214e-05,
      "loss": 0.6505,
      "step": 79
    },
    {
      "epoch": 0.006459035585249177,
      "grad_norm": 0.36606553196907043,
      "learning_rate": 4.421052631578947e-05,
      "loss": 0.6535,
      "step": 80
    },
    {
      "epoch": 0.006539773530064792,
      "grad_norm": 0.41430118680000305,
      "learning_rate": 4.210526315789474e-05,
      "loss": 0.6182,
      "step": 81
    },
    {
      "epoch": 0.006620511474880407,
      "grad_norm": 0.3856939673423767,
      "learning_rate": 4e-05,
      "loss": 0.6624,
      "step": 82
    },
    {
      "epoch": 0.006701249419696021,
      "grad_norm": 0.34175869822502136,
      "learning_rate": 3.789473684210527e-05,
      "loss": 0.6408,
      "step": 83
    },
    {
      "epoch": 0.006781987364511637,
      "grad_norm": 0.311293363571167,
      "learning_rate": 3.578947368421053e-05,
      "loss": 0.6058,
      "step": 84
    },
    {
      "epoch": 0.006862725309327251,
      "grad_norm": 0.3751486539840698,
      "learning_rate": 3.368421052631579e-05,
      "loss": 0.6752,
      "step": 85
    },
    {
      "epoch": 0.006943463254142866,
      "grad_norm": 0.40762367844581604,
      "learning_rate": 3.157894736842105e-05,
      "loss": 0.6277,
      "step": 86
    },
    {
      "epoch": 0.007024201198958481,
      "grad_norm": 0.45928341150283813,
      "learning_rate": 2.9473684210526314e-05,
      "loss": 0.622,
      "step": 87
    },
    {
      "epoch": 0.007104939143774095,
      "grad_norm": 0.49499040842056274,
      "learning_rate": 2.7368421052631583e-05,
      "loss": 0.6527,
      "step": 88
    },
    {
      "epoch": 0.00718567708858971,
      "grad_norm": 0.4424061179161072,
      "learning_rate": 2.5263157894736845e-05,
      "loss": 0.6253,
      "step": 89
    },
    {
      "epoch": 0.0072664150334053245,
      "grad_norm": 0.3972907066345215,
      "learning_rate": 2.3157894736842107e-05,
      "loss": 0.6298,
      "step": 90
    },
    {
      "epoch": 0.007347152978220939,
      "grad_norm": 0.33919885754585266,
      "learning_rate": 2.105263157894737e-05,
      "loss": 0.6506,
      "step": 91
    },
    {
      "epoch": 0.007427890923036554,
      "grad_norm": 0.3223676085472107,
      "learning_rate": 1.8947368421052634e-05,
      "loss": 0.6577,
      "step": 92
    },
    {
      "epoch": 0.007508628867852168,
      "grad_norm": 0.3162674009799957,
      "learning_rate": 1.6842105263157896e-05,
      "loss": 0.6765,
      "step": 93
    },
    {
      "epoch": 0.007589366812667784,
      "grad_norm": 0.3220762014389038,
      "learning_rate": 1.4736842105263157e-05,
      "loss": 0.6769,
      "step": 94
    },
    {
      "epoch": 0.0076701047574833986,
      "grad_norm": 0.36191388964653015,
      "learning_rate": 1.2631578947368422e-05,
      "loss": 0.621,
      "step": 95
    },
    {
      "epoch": 0.007750842702299013,
      "grad_norm": 0.37017276883125305,
      "learning_rate": 1.0526315789473684e-05,
      "loss": 0.7032,
      "step": 96
    },
    {
      "epoch": 0.007831580647114627,
      "grad_norm": 0.40599679946899414,
      "learning_rate": 8.421052631578948e-06,
      "loss": 0.5957,
      "step": 97
    },
    {
      "epoch": 0.007912318591930242,
      "grad_norm": 0.3483966290950775,
      "learning_rate": 6.315789473684211e-06,
      "loss": 0.6496,
      "step": 98
    },
    {
      "epoch": 0.007993056536745858,
      "grad_norm": 0.36802637577056885,
      "learning_rate": 4.210526315789474e-06,
      "loss": 0.6846,
      "step": 99
    },
    {
      "epoch": 0.008073794481561472,
      "grad_norm": 0.35597506165504456,
      "learning_rate": 2.105263157894737e-06,
      "loss": 0.6393,
      "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": 4.472992781996851e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}