{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.009939369843951893,
  "eval_steps": 13,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00019878739687903787,
      "grad_norm": 2.5984435081481934,
      "learning_rate": 5e-06,
      "loss": 13.1525,
      "step": 1
    },
    {
      "epoch": 0.00019878739687903787,
      "eval_loss": 3.2820167541503906,
      "eval_runtime": 78.0374,
      "eval_samples_per_second": 27.154,
      "eval_steps_per_second": 13.583,
      "step": 1
    },
    {
      "epoch": 0.00039757479375807575,
      "grad_norm": 2.336440324783325,
      "learning_rate": 1e-05,
      "loss": 13.7228,
      "step": 2
    },
    {
      "epoch": 0.0005963621906371136,
      "grad_norm": 2.69608998298645,
      "learning_rate": 1.5e-05,
      "loss": 14.2389,
      "step": 3
    },
    {
      "epoch": 0.0007951495875161515,
      "grad_norm": 2.53593111038208,
      "learning_rate": 2e-05,
      "loss": 12.0966,
      "step": 4
    },
    {
      "epoch": 0.0009939369843951894,
      "grad_norm": 3.020933151245117,
      "learning_rate": 2.5e-05,
      "loss": 13.396,
      "step": 5
    },
    {
      "epoch": 0.0011927243812742273,
      "grad_norm": 2.3294146060943604,
      "learning_rate": 3e-05,
      "loss": 13.276,
      "step": 6
    },
    {
      "epoch": 0.0013915117781532651,
      "grad_norm": 2.662527322769165,
      "learning_rate": 3.5e-05,
      "loss": 14.1702,
      "step": 7
    },
    {
      "epoch": 0.001590299175032303,
      "grad_norm": 2.230471611022949,
      "learning_rate": 4e-05,
      "loss": 13.6173,
      "step": 8
    },
    {
      "epoch": 0.0017890865719113408,
      "grad_norm": 3.186838150024414,
      "learning_rate": 4.5e-05,
      "loss": 15.6249,
      "step": 9
    },
    {
      "epoch": 0.001987873968790379,
      "grad_norm": 2.705491542816162,
      "learning_rate": 5e-05,
      "loss": 14.0928,
      "step": 10
    },
    {
      "epoch": 0.0021866613656694165,
      "grad_norm": 3.163905382156372,
      "learning_rate": 4.99229333433282e-05,
      "loss": 13.9178,
      "step": 11
    },
    {
      "epoch": 0.0023854487625484546,
      "grad_norm": 3.664141893386841,
      "learning_rate": 4.9692208514878444e-05,
      "loss": 13.3966,
      "step": 12
    },
    {
      "epoch": 0.002584236159427492,
      "grad_norm": 3.0179429054260254,
      "learning_rate": 4.9309248009941914e-05,
      "loss": 11.8172,
      "step": 13
    },
    {
      "epoch": 0.002584236159427492,
      "eval_loss": 3.2313973903656006,
      "eval_runtime": 77.613,
      "eval_samples_per_second": 27.302,
      "eval_steps_per_second": 13.658,
      "step": 13
    },
    {
      "epoch": 0.0027830235563065303,
      "grad_norm": 3.568173885345459,
      "learning_rate": 4.877641290737884e-05,
      "loss": 13.0556,
      "step": 14
    },
    {
      "epoch": 0.002981810953185568,
      "grad_norm": 4.340553283691406,
      "learning_rate": 4.8096988312782174e-05,
      "loss": 13.3655,
      "step": 15
    },
    {
      "epoch": 0.003180598350064606,
      "grad_norm": 3.275731325149536,
      "learning_rate": 4.72751631047092e-05,
      "loss": 12.1498,
      "step": 16
    },
    {
      "epoch": 0.0033793857469436436,
      "grad_norm": 3.076188564300537,
      "learning_rate": 4.6316004108852305e-05,
      "loss": 12.0674,
      "step": 17
    },
    {
      "epoch": 0.0035781731438226817,
      "grad_norm": 5.818179130554199,
      "learning_rate": 4.522542485937369e-05,
      "loss": 14.4302,
      "step": 18
    },
    {
      "epoch": 0.0037769605407017197,
      "grad_norm": 3.2982187271118164,
      "learning_rate": 4.401014914000078e-05,
      "loss": 11.2277,
      "step": 19
    },
    {
      "epoch": 0.003975747937580758,
      "grad_norm": 2.596877098083496,
      "learning_rate": 4.267766952966369e-05,
      "loss": 12.7767,
      "step": 20
    },
    {
      "epoch": 0.004174535334459795,
      "grad_norm": 3.128573417663574,
      "learning_rate": 4.123620120825459e-05,
      "loss": 13.4153,
      "step": 21
    },
    {
      "epoch": 0.004373322731338833,
      "grad_norm": 3.395514965057373,
      "learning_rate": 3.969463130731183e-05,
      "loss": 11.9203,
      "step": 22
    },
    {
      "epoch": 0.004572110128217871,
      "grad_norm": 3.388470411300659,
      "learning_rate": 3.8062464117898724e-05,
      "loss": 11.5329,
      "step": 23
    },
    {
      "epoch": 0.004770897525096909,
      "grad_norm": 3.08424711227417,
      "learning_rate": 3.634976249348867e-05,
      "loss": 12.0117,
      "step": 24
    },
    {
      "epoch": 0.004969684921975946,
      "grad_norm": 3.288663148880005,
      "learning_rate": 3.456708580912725e-05,
      "loss": 11.7711,
      "step": 25
    },
    {
      "epoch": 0.005168472318854984,
      "grad_norm": 2.7411789894104004,
      "learning_rate": 3.272542485937369e-05,
      "loss": 13.0947,
      "step": 26
    },
    {
      "epoch": 0.005168472318854984,
      "eval_loss": 3.0858662128448486,
      "eval_runtime": 76.1367,
      "eval_samples_per_second": 27.832,
      "eval_steps_per_second": 13.922,
      "step": 26
    },
    {
      "epoch": 0.0053672597157340225,
      "grad_norm": 3.8614823818206787,
      "learning_rate": 3.083613409639764e-05,
      "loss": 13.1261,
      "step": 27
    },
    {
      "epoch": 0.0055660471126130606,
      "grad_norm": 2.7608020305633545,
      "learning_rate": 2.8910861626005776e-05,
      "loss": 14.0752,
      "step": 28
    },
    {
      "epoch": 0.005764834509492099,
      "grad_norm": 3.776360511779785,
      "learning_rate": 2.6961477393196126e-05,
      "loss": 12.0604,
      "step": 29
    },
    {
      "epoch": 0.005963621906371136,
      "grad_norm": 3.3174591064453125,
      "learning_rate": 2.5e-05,
      "loss": 13.3155,
      "step": 30
    },
    {
      "epoch": 0.006162409303250174,
      "grad_norm": 3.493502378463745,
      "learning_rate": 2.303852260680388e-05,
      "loss": 13.7616,
      "step": 31
    },
    {
      "epoch": 0.006361196700129212,
      "grad_norm": 3.398390293121338,
      "learning_rate": 2.1089138373994223e-05,
      "loss": 11.2017,
      "step": 32
    },
    {
      "epoch": 0.00655998409700825,
      "grad_norm": 2.4852347373962402,
      "learning_rate": 1.9163865903602374e-05,
      "loss": 11.3623,
      "step": 33
    },
    {
      "epoch": 0.006758771493887287,
      "grad_norm": 3.126319169998169,
      "learning_rate": 1.7274575140626318e-05,
      "loss": 11.5718,
      "step": 34
    },
    {
      "epoch": 0.006957558890766325,
      "grad_norm": 3.5908548831939697,
      "learning_rate": 1.5432914190872757e-05,
      "loss": 13.374,
      "step": 35
    },
    {
      "epoch": 0.007156346287645363,
      "grad_norm": 4.754377365112305,
      "learning_rate": 1.3650237506511331e-05,
      "loss": 13.9317,
      "step": 36
    },
    {
      "epoch": 0.007355133684524401,
      "grad_norm": 3.6869258880615234,
      "learning_rate": 1.1937535882101281e-05,
      "loss": 12.4569,
      "step": 37
    },
    {
      "epoch": 0.0075539210814034394,
      "grad_norm": 3.3655855655670166,
      "learning_rate": 1.0305368692688174e-05,
      "loss": 11.7599,
      "step": 38
    },
    {
      "epoch": 0.007752708478282477,
      "grad_norm": 2.8551807403564453,
      "learning_rate": 8.763798791745411e-06,
      "loss": 11.8171,
      "step": 39
    },
    {
      "epoch": 0.007752708478282477,
      "eval_loss": 3.0310628414154053,
      "eval_runtime": 75.945,
      "eval_samples_per_second": 27.902,
      "eval_steps_per_second": 13.957,
      "step": 39
    },
    {
      "epoch": 0.007951495875161516,
      "grad_norm": 3.137924909591675,
      "learning_rate": 7.3223304703363135e-06,
      "loss": 12.3101,
      "step": 40
    },
    {
      "epoch": 0.008150283272040553,
      "grad_norm": 2.641319751739502,
      "learning_rate": 5.989850859999227e-06,
      "loss": 11.4512,
      "step": 41
    },
    {
      "epoch": 0.00834907066891959,
      "grad_norm": 3.6729891300201416,
      "learning_rate": 4.7745751406263165e-06,
      "loss": 11.6769,
      "step": 42
    },
    {
      "epoch": 0.008547858065798629,
      "grad_norm": 3.528848648071289,
      "learning_rate": 3.6839958911476957e-06,
      "loss": 11.1653,
      "step": 43
    },
    {
      "epoch": 0.008746645462677666,
      "grad_norm": 3.0228517055511475,
      "learning_rate": 2.7248368952908053e-06,
      "loss": 10.7299,
      "step": 44
    },
    {
      "epoch": 0.008945432859556703,
      "grad_norm": 3.2013304233551025,
      "learning_rate": 1.9030116872178316e-06,
      "loss": 12.7148,
      "step": 45
    },
    {
      "epoch": 0.009144220256435742,
      "grad_norm": 2.7772860527038574,
      "learning_rate": 1.2235870926211619e-06,
      "loss": 11.8285,
      "step": 46
    },
    {
      "epoch": 0.00934300765331478,
      "grad_norm": 3.5433526039123535,
      "learning_rate": 6.907519900580861e-07,
      "loss": 11.6592,
      "step": 47
    },
    {
      "epoch": 0.009541795050193818,
      "grad_norm": 3.839385509490967,
      "learning_rate": 3.077914851215585e-07,
      "loss": 11.4824,
      "step": 48
    },
    {
      "epoch": 0.009740582447072856,
      "grad_norm": 2.9668209552764893,
      "learning_rate": 7.706665667180091e-08,
      "loss": 11.6165,
      "step": 49
    },
    {
      "epoch": 0.009939369843951893,
      "grad_norm": 3.1155428886413574,
      "learning_rate": 0.0,
      "loss": 12.5005,
      "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": 8184384007962624.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}