{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.180281690140845,
  "eval_steps": 200,
  "global_step": 2200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02682763246143528,
      "grad_norm": 7.5027008056640625,
      "learning_rate": 0.00019991475902800314,
      "loss": 18.1731,
      "step": 50
    },
    {
      "epoch": 0.05365526492287056,
      "grad_norm": 5.68405294418335,
      "learning_rate": 0.0001996521945196495,
      "loss": 16.1431,
      "step": 100
    },
    {
      "epoch": 0.08048289738430583,
      "grad_norm": 5.743220806121826,
      "learning_rate": 0.00019921273704680872,
      "loss": 16.2968,
      "step": 150
    },
    {
      "epoch": 0.10731052984574112,
      "grad_norm": 6.115276336669922,
      "learning_rate": 0.0001985971666920019,
      "loss": 15.9962,
      "step": 200
    },
    {
      "epoch": 0.10731052984574112,
      "eval_loss": 1.7225275039672852,
      "eval_runtime": 27.5115,
      "eval_samples_per_second": 3.635,
      "eval_steps_per_second": 1.817,
      "step": 200
    },
    {
      "epoch": 0.1341381623071764,
      "grad_norm": 8.04736328125,
      "learning_rate": 0.00019780657615635263,
      "loss": 15.9676,
      "step": 250
    },
    {
      "epoch": 0.16096579476861167,
      "grad_norm": 6.840994358062744,
      "learning_rate": 0.0001968423688199291,
      "loss": 15.7539,
      "step": 300
    },
    {
      "epoch": 0.18779342723004694,
      "grad_norm": 8.343657493591309,
      "learning_rate": 0.00019570625625059935,
      "loss": 15.5103,
      "step": 350
    },
    {
      "epoch": 0.21462105969148224,
      "grad_norm": 6.539078712463379,
      "learning_rate": 0.00019440025516582107,
      "loss": 15.4896,
      "step": 400
    },
    {
      "epoch": 0.21462105969148224,
      "eval_loss": 1.6813037395477295,
      "eval_runtime": 27.4264,
      "eval_samples_per_second": 3.646,
      "eval_steps_per_second": 1.823,
      "step": 400
    },
    {
      "epoch": 0.2414486921529175,
      "grad_norm": 5.919412612915039,
      "learning_rate": 0.00019292668385275914,
      "loss": 15.7171,
      "step": 450
    },
    {
      "epoch": 0.2682763246143528,
      "grad_norm": 8.476408958435059,
      "learning_rate": 0.00019128815805308596,
      "loss": 15.6568,
      "step": 500
    },
    {
      "epoch": 0.29510395707578807,
      "grad_norm": 6.3846330642700195,
      "learning_rate": 0.00018948758631976906,
      "loss": 15.5006,
      "step": 550
    },
    {
      "epoch": 0.32193158953722334,
      "grad_norm": 9.207799911499023,
      "learning_rate": 0.00018752816485408843,
      "loss": 15.3622,
      "step": 600
    },
    {
      "epoch": 0.32193158953722334,
      "eval_loss": 1.657413363456726,
      "eval_runtime": 27.4485,
      "eval_samples_per_second": 3.643,
      "eval_steps_per_second": 1.822,
      "step": 600
    },
    {
      "epoch": 0.3487592219986586,
      "grad_norm": 8.288525581359863,
      "learning_rate": 0.00018541337183204833,
      "loss": 15.1776,
      "step": 650
    },
    {
      "epoch": 0.3755868544600939,
      "grad_norm": 6.99819278717041,
      "learning_rate": 0.00018314696123025454,
      "loss": 15.2676,
      "step": 700
    },
    {
      "epoch": 0.4024144869215292,
      "grad_norm": 6.276946544647217,
      "learning_rate": 0.0001807329561622173,
      "loss": 15.4822,
      "step": 750
    },
    {
      "epoch": 0.42924211938296447,
      "grad_norm": 7.4382123947143555,
      "learning_rate": 0.00017817564173690811,
      "loss": 15.17,
      "step": 800
    },
    {
      "epoch": 0.42924211938296447,
      "eval_loss": 1.6430630683898926,
      "eval_runtime": 27.4278,
      "eval_samples_per_second": 3.646,
      "eval_steps_per_second": 1.823,
      "step": 800
    },
    {
      "epoch": 0.45606975184439974,
      "grad_norm": 6.525240898132324,
      "learning_rate": 0.00017547955745224783,
      "loss": 15.2127,
      "step": 850
    },
    {
      "epoch": 0.482897384305835,
      "grad_norm": 6.991734027862549,
      "learning_rate": 0.00017264948913702733,
      "loss": 14.9923,
      "step": 900
    },
    {
      "epoch": 0.5097250167672703,
      "grad_norm": 7.74118709564209,
      "learning_rate": 0.0001696904604555664,
      "loss": 14.9959,
      "step": 950
    },
    {
      "epoch": 0.5365526492287056,
      "grad_norm": 8.33617115020752,
      "learning_rate": 0.00016660772399018878,
      "loss": 14.8148,
      "step": 1000
    },
    {
      "epoch": 0.5365526492287056,
      "eval_loss": 1.5783880949020386,
      "eval_runtime": 27.4606,
      "eval_samples_per_second": 3.642,
      "eval_steps_per_second": 1.821,
      "step": 1000
    },
    {
      "epoch": 0.5633802816901409,
      "grad_norm": 7.486099720001221,
      "learning_rate": 0.000163406751917345,
      "loss": 14.7974,
      "step": 1050
    },
    {
      "epoch": 0.5902079141515761,
      "grad_norm": 8.10119342803955,
      "learning_rate": 0.0001600932262939324,
      "loss": 14.5883,
      "step": 1100
    },
    {
      "epoch": 0.6170355466130114,
      "grad_norm": 10.781996726989746,
      "learning_rate": 0.0001566730289710558,
      "loss": 14.2,
      "step": 1150
    },
    {
      "epoch": 0.6438631790744467,
      "grad_norm": 14.64252758026123,
      "learning_rate": 0.00015315223115313262,
      "loss": 11.8162,
      "step": 1200
    },
    {
      "epoch": 0.6438631790744467,
      "eval_loss": 1.005837082862854,
      "eval_runtime": 27.4338,
      "eval_samples_per_second": 3.645,
      "eval_steps_per_second": 1.823,
      "step": 1200
    },
    {
      "epoch": 0.670690811535882,
      "grad_norm": 13.796377182006836,
      "learning_rate": 0.0001495370826208764,
      "loss": 6.8475,
      "step": 1250
    },
    {
      "epoch": 0.6975184439973172,
      "grad_norm": 11.29936408996582,
      "learning_rate": 0.0001458340006372889,
      "loss": 2.4798,
      "step": 1300
    },
    {
      "epoch": 0.7243460764587525,
      "grad_norm": 6.6834492683410645,
      "learning_rate": 0.0001420495585563536,
      "loss": 1.6183,
      "step": 1350
    },
    {
      "epoch": 0.7511737089201878,
      "grad_norm": 5.344634532928467,
      "learning_rate": 0.00013819047415465196,
      "loss": 1.4575,
      "step": 1400
    },
    {
      "epoch": 0.7511737089201878,
      "eval_loss": 0.19598053395748138,
      "eval_runtime": 27.4448,
      "eval_samples_per_second": 3.644,
      "eval_steps_per_second": 1.822,
      "step": 1400
    },
    {
      "epoch": 0.778001341381623,
      "grad_norm": 8.362627029418945,
      "learning_rate": 0.00013426359770661405,
      "loss": 1.2922,
      "step": 1450
    },
    {
      "epoch": 0.8048289738430584,
      "grad_norm": 4.9234418869018555,
      "learning_rate": 0.00013027589982457228,
      "loss": 1.2766,
      "step": 1500
    },
    {
      "epoch": 0.8316566063044937,
      "grad_norm": 5.768574237823486,
      "learning_rate": 0.00012623445908520258,
      "loss": 1.1293,
      "step": 1550
    },
    {
      "epoch": 0.8584842387659289,
      "grad_norm": 5.284246444702148,
      "learning_rate": 0.00012214644946431785,
      "loss": 1.1295,
      "step": 1600
    },
    {
      "epoch": 0.8584842387659289,
      "eval_loss": 0.16764384508132935,
      "eval_runtime": 27.4111,
      "eval_samples_per_second": 3.648,
      "eval_steps_per_second": 1.824,
      "step": 1600
    },
    {
      "epoch": 0.8853118712273642,
      "grad_norm": 5.7961225509643555,
      "learning_rate": 0.00011801912760231802,
      "loss": 1.0936,
      "step": 1650
    },
    {
      "epoch": 0.9121395036887995,
      "grad_norm": 4.642612934112549,
      "learning_rate": 0.0001138598199229018,
      "loss": 1.0898,
      "step": 1700
    },
    {
      "epoch": 0.9389671361502347,
      "grad_norm": 5.459797382354736,
      "learning_rate": 0.0001096759096279061,
      "loss": 1.0331,
      "step": 1750
    },
    {
      "epoch": 0.96579476861167,
      "grad_norm": 4.336981773376465,
      "learning_rate": 0.00010547482359135805,
      "loss": 1.0427,
      "step": 1800
    },
    {
      "epoch": 0.96579476861167,
      "eval_loss": 0.15734320878982544,
      "eval_runtime": 27.4537,
      "eval_samples_per_second": 3.642,
      "eval_steps_per_second": 1.821,
      "step": 1800
    },
    {
      "epoch": 0.9926224010731053,
      "grad_norm": 4.62598991394043,
      "learning_rate": 0.00010126401917600476,
      "loss": 1.0167,
      "step": 1850
    },
    {
      "epoch": 1.0193158953722334,
      "grad_norm": 3.739978551864624,
      "learning_rate": 9.705097099572197e-05,
      "loss": 0.818,
      "step": 1900
    },
    {
      "epoch": 1.0461435278336686,
      "grad_norm": 3.3912863731384277,
      "learning_rate": 9.284315764730047e-05,
      "loss": 0.9189,
      "step": 1950
    },
    {
      "epoch": 1.072971160295104,
      "grad_norm": 3.9238812923431396,
      "learning_rate": 8.864804843516263e-05,
      "loss": 0.8213,
      "step": 2000
    },
    {
      "epoch": 1.072971160295104,
      "eval_loss": 0.15182910859584808,
      "eval_runtime": 27.4216,
      "eval_samples_per_second": 3.647,
      "eval_steps_per_second": 1.823,
      "step": 2000
    },
    {
      "epoch": 1.0997987927565391,
      "grad_norm": 3.6631221771240234,
      "learning_rate": 8.447309011257313e-05,
      "loss": 0.8213,
      "step": 2050
    },
    {
      "epoch": 1.1266264252179745,
      "grad_norm": 3.994750499725342,
      "learning_rate": 8.032569366288115e-05,
      "loss": 0.9157,
      "step": 2100
    },
    {
      "epoch": 1.1534540576794097,
      "grad_norm": 4.084840297698975,
      "learning_rate": 7.621322114425742e-05,
      "loss": 0.827,
      "step": 2150
    },
    {
      "epoch": 1.180281690140845,
      "grad_norm": 3.7172036170959473,
      "learning_rate": 7.214297262127847e-05,
      "loss": 0.8447,
      "step": 2200
    },
    {
      "epoch": 1.180281690140845,
      "eval_loss": 0.14608320593833923,
      "eval_runtime": 27.4428,
      "eval_samples_per_second": 3.644,
      "eval_steps_per_second": 1.822,
      "step": 2200
    }
  ],
  "logging_steps": 50,
  "max_steps": 3728,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5950289413921587e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}