{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.012678288431061807,
  "eval_steps": 13,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00025356576862123613,
      "grad_norm": 4.366250991821289,
      "learning_rate": 5e-06,
      "loss": 2.8246,
      "step": 1
    },
    {
      "epoch": 0.00025356576862123613,
      "eval_loss": 3.051912546157837,
      "eval_runtime": 29.8011,
      "eval_samples_per_second": 55.736,
      "eval_steps_per_second": 27.885,
      "step": 1
    },
    {
      "epoch": 0.0005071315372424723,
      "grad_norm": 5.3694586753845215,
      "learning_rate": 1e-05,
      "loss": 2.8737,
      "step": 2
    },
    {
      "epoch": 0.0007606973058637085,
      "grad_norm": 4.844220161437988,
      "learning_rate": 1.5e-05,
      "loss": 2.9516,
      "step": 3
    },
    {
      "epoch": 0.0010142630744849445,
      "grad_norm": 4.557978630065918,
      "learning_rate": 2e-05,
      "loss": 2.8019,
      "step": 4
    },
    {
      "epoch": 0.0012678288431061807,
      "grad_norm": 4.6637067794799805,
      "learning_rate": 2.5e-05,
      "loss": 2.454,
      "step": 5
    },
    {
      "epoch": 0.001521394611727417,
      "grad_norm": 4.577850341796875,
      "learning_rate": 3e-05,
      "loss": 2.6732,
      "step": 6
    },
    {
      "epoch": 0.0017749603803486529,
      "grad_norm": 5.005636692047119,
      "learning_rate": 3.5e-05,
      "loss": 3.3313,
      "step": 7
    },
    {
      "epoch": 0.002028526148969889,
      "grad_norm": 5.796531677246094,
      "learning_rate": 4e-05,
      "loss": 3.2833,
      "step": 8
    },
    {
      "epoch": 0.002282091917591125,
      "grad_norm": 3.107450008392334,
      "learning_rate": 4.5e-05,
      "loss": 2.3397,
      "step": 9
    },
    {
      "epoch": 0.0025356576862123614,
      "grad_norm": 7.156716823577881,
      "learning_rate": 5e-05,
      "loss": 3.6226,
      "step": 10
    },
    {
      "epoch": 0.0027892234548335974,
      "grad_norm": 4.584049224853516,
      "learning_rate": 4.99229333433282e-05,
      "loss": 2.6042,
      "step": 11
    },
    {
      "epoch": 0.003042789223454834,
      "grad_norm": 3.333683967590332,
      "learning_rate": 4.9692208514878444e-05,
      "loss": 2.0151,
      "step": 12
    },
    {
      "epoch": 0.0032963549920760698,
      "grad_norm": 3.9281270503997803,
      "learning_rate": 4.9309248009941914e-05,
      "loss": 1.8472,
      "step": 13
    },
    {
      "epoch": 0.0032963549920760698,
      "eval_loss": 2.7022249698638916,
      "eval_runtime": 29.6852,
      "eval_samples_per_second": 55.954,
      "eval_steps_per_second": 27.994,
      "step": 13
    },
    {
      "epoch": 0.0035499207606973057,
      "grad_norm": 4.814737796783447,
      "learning_rate": 4.877641290737884e-05,
      "loss": 2.6184,
      "step": 14
    },
    {
      "epoch": 0.003803486529318542,
      "grad_norm": 5.34513521194458,
      "learning_rate": 4.8096988312782174e-05,
      "loss": 3.0137,
      "step": 15
    },
    {
      "epoch": 0.004057052297939778,
      "grad_norm": 4.943324089050293,
      "learning_rate": 4.72751631047092e-05,
      "loss": 2.4551,
      "step": 16
    },
    {
      "epoch": 0.004310618066561014,
      "grad_norm": 3.6852900981903076,
      "learning_rate": 4.6316004108852305e-05,
      "loss": 2.2364,
      "step": 17
    },
    {
      "epoch": 0.00456418383518225,
      "grad_norm": 5.414399147033691,
      "learning_rate": 4.522542485937369e-05,
      "loss": 2.6977,
      "step": 18
    },
    {
      "epoch": 0.004817749603803487,
      "grad_norm": 5.027890682220459,
      "learning_rate": 4.401014914000078e-05,
      "loss": 2.4592,
      "step": 19
    },
    {
      "epoch": 0.005071315372424723,
      "grad_norm": 4.726078510284424,
      "learning_rate": 4.267766952966369e-05,
      "loss": 2.2819,
      "step": 20
    },
    {
      "epoch": 0.005324881141045959,
      "grad_norm": 4.246105194091797,
      "learning_rate": 4.123620120825459e-05,
      "loss": 2.0941,
      "step": 21
    },
    {
      "epoch": 0.005578446909667195,
      "grad_norm": 3.622349739074707,
      "learning_rate": 3.969463130731183e-05,
      "loss": 1.541,
      "step": 22
    },
    {
      "epoch": 0.005832012678288431,
      "grad_norm": 4.364040374755859,
      "learning_rate": 3.8062464117898724e-05,
      "loss": 1.9722,
      "step": 23
    },
    {
      "epoch": 0.006085578446909668,
      "grad_norm": 5.084831714630127,
      "learning_rate": 3.634976249348867e-05,
      "loss": 2.5547,
      "step": 24
    },
    {
      "epoch": 0.006339144215530904,
      "grad_norm": 5.228572368621826,
      "learning_rate": 3.456708580912725e-05,
      "loss": 2.5758,
      "step": 25
    },
    {
      "epoch": 0.0065927099841521395,
      "grad_norm": 5.716057300567627,
      "learning_rate": 3.272542485937369e-05,
      "loss": 2.3082,
      "step": 26
    },
    {
      "epoch": 0.0065927099841521395,
      "eval_loss": 2.223238945007324,
      "eval_runtime": 29.5892,
      "eval_samples_per_second": 56.135,
      "eval_steps_per_second": 28.085,
      "step": 26
    },
    {
      "epoch": 0.0068462757527733755,
      "grad_norm": 4.186709880828857,
      "learning_rate": 3.083613409639764e-05,
      "loss": 2.2258,
      "step": 27
    },
    {
      "epoch": 0.0070998415213946115,
      "grad_norm": 4.709568023681641,
      "learning_rate": 2.8910861626005776e-05,
      "loss": 2.1151,
      "step": 28
    },
    {
      "epoch": 0.0073534072900158474,
      "grad_norm": 5.5850324630737305,
      "learning_rate": 2.6961477393196126e-05,
      "loss": 2.3268,
      "step": 29
    },
    {
      "epoch": 0.007606973058637084,
      "grad_norm": 4.681593894958496,
      "learning_rate": 2.5e-05,
      "loss": 2.2149,
      "step": 30
    },
    {
      "epoch": 0.00786053882725832,
      "grad_norm": 4.2647385597229,
      "learning_rate": 2.303852260680388e-05,
      "loss": 1.7992,
      "step": 31
    },
    {
      "epoch": 0.008114104595879556,
      "grad_norm": 5.252506256103516,
      "learning_rate": 2.1089138373994223e-05,
      "loss": 2.1147,
      "step": 32
    },
    {
      "epoch": 0.008367670364500793,
      "grad_norm": 4.948132038116455,
      "learning_rate": 1.9163865903602374e-05,
      "loss": 2.2296,
      "step": 33
    },
    {
      "epoch": 0.008621236133122028,
      "grad_norm": 4.569683074951172,
      "learning_rate": 1.7274575140626318e-05,
      "loss": 1.9374,
      "step": 34
    },
    {
      "epoch": 0.008874801901743265,
      "grad_norm": 3.1598641872406006,
      "learning_rate": 1.5432914190872757e-05,
      "loss": 1.676,
      "step": 35
    },
    {
      "epoch": 0.0091283676703645,
      "grad_norm": 3.269890069961548,
      "learning_rate": 1.3650237506511331e-05,
      "loss": 2.0945,
      "step": 36
    },
    {
      "epoch": 0.009381933438985737,
      "grad_norm": 4.205365180969238,
      "learning_rate": 1.1937535882101281e-05,
      "loss": 2.1506,
      "step": 37
    },
    {
      "epoch": 0.009635499207606974,
      "grad_norm": 4.201732158660889,
      "learning_rate": 1.0305368692688174e-05,
      "loss": 2.0079,
      "step": 38
    },
    {
      "epoch": 0.009889064976228209,
      "grad_norm": 3.54046893119812,
      "learning_rate": 8.763798791745411e-06,
      "loss": 1.6886,
      "step": 39
    },
    {
      "epoch": 0.009889064976228209,
      "eval_loss": 2.080566167831421,
      "eval_runtime": 29.4661,
      "eval_samples_per_second": 56.37,
      "eval_steps_per_second": 28.202,
      "step": 39
    },
    {
      "epoch": 0.010142630744849446,
      "grad_norm": 4.151251792907715,
      "learning_rate": 7.3223304703363135e-06,
      "loss": 1.9259,
      "step": 40
    },
    {
      "epoch": 0.01039619651347068,
      "grad_norm": 3.8641293048858643,
      "learning_rate": 5.989850859999227e-06,
      "loss": 1.8639,
      "step": 41
    },
    {
      "epoch": 0.010649762282091918,
      "grad_norm": 4.853936672210693,
      "learning_rate": 4.7745751406263165e-06,
      "loss": 2.2364,
      "step": 42
    },
    {
      "epoch": 0.010903328050713154,
      "grad_norm": 4.689719200134277,
      "learning_rate": 3.6839958911476957e-06,
      "loss": 1.9994,
      "step": 43
    },
    {
      "epoch": 0.01115689381933439,
      "grad_norm": 4.530834674835205,
      "learning_rate": 2.7248368952908053e-06,
      "loss": 1.9659,
      "step": 44
    },
    {
      "epoch": 0.011410459587955626,
      "grad_norm": 4.6177825927734375,
      "learning_rate": 1.9030116872178316e-06,
      "loss": 1.8617,
      "step": 45
    },
    {
      "epoch": 0.011664025356576862,
      "grad_norm": 4.972818374633789,
      "learning_rate": 1.2235870926211619e-06,
      "loss": 1.9799,
      "step": 46
    },
    {
      "epoch": 0.011917591125198098,
      "grad_norm": 5.976642608642578,
      "learning_rate": 6.907519900580861e-07,
      "loss": 2.0939,
      "step": 47
    },
    {
      "epoch": 0.012171156893819335,
      "grad_norm": 3.2281494140625,
      "learning_rate": 3.077914851215585e-07,
      "loss": 1.5168,
      "step": 48
    },
    {
      "epoch": 0.01242472266244057,
      "grad_norm": 4.77769660949707,
      "learning_rate": 7.706665667180091e-08,
      "loss": 2.4263,
      "step": 49
    },
    {
      "epoch": 0.012678288431061807,
      "grad_norm": 4.587887763977051,
      "learning_rate": 0.0,
      "loss": 1.9408,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2484099801415680.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}