{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.14878184861446903,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003719546215361726,
      "eval_loss": 2.9602878093719482,
      "eval_runtime": 91.238,
      "eval_samples_per_second": 12.407,
      "eval_steps_per_second": 6.204,
      "step": 1
    },
    {
      "epoch": 0.001859773107680863,
      "grad_norm": 61.693328857421875,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 8.0223,
      "step": 5
    },
    {
      "epoch": 0.003719546215361726,
      "grad_norm": 75.7999038696289,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 9.8316,
      "step": 10
    },
    {
      "epoch": 0.0055793193230425885,
      "grad_norm": 49.29008102416992,
      "learning_rate": 5e-05,
      "loss": 8.4199,
      "step": 15
    },
    {
      "epoch": 0.007439092430723452,
      "grad_norm": 38.370155334472656,
      "learning_rate": 6.666666666666667e-05,
      "loss": 8.0234,
      "step": 20
    },
    {
      "epoch": 0.009298865538404314,
      "grad_norm": 48.59316635131836,
      "learning_rate": 8.333333333333334e-05,
      "loss": 7.3277,
      "step": 25
    },
    {
      "epoch": 0.011158638646085177,
      "grad_norm": 38.86313247680664,
      "learning_rate": 0.0001,
      "loss": 6.9486,
      "step": 30
    },
    {
      "epoch": 0.01301841175376604,
      "grad_norm": 29.939868927001953,
      "learning_rate": 9.995494831023409e-05,
      "loss": 6.8925,
      "step": 35
    },
    {
      "epoch": 0.014878184861446904,
      "grad_norm": 28.42740821838379,
      "learning_rate": 9.981987442712633e-05,
      "loss": 7.8087,
      "step": 40
    },
    {
      "epoch": 0.016737957969127765,
      "grad_norm": 34.04663848876953,
      "learning_rate": 9.959502176294383e-05,
      "loss": 6.9207,
      "step": 45
    },
    {
      "epoch": 0.018597731076808628,
      "grad_norm": 30.441848754882812,
      "learning_rate": 9.928079551738543e-05,
      "loss": 6.4872,
      "step": 50
    },
    {
      "epoch": 0.02045750418448949,
      "grad_norm": 26.242755889892578,
      "learning_rate": 9.887776194738432e-05,
      "loss": 5.6952,
      "step": 55
    },
    {
      "epoch": 0.022317277292170354,
      "grad_norm": 40.495094299316406,
      "learning_rate": 9.838664734667495e-05,
      "loss": 7.0758,
      "step": 60
    },
    {
      "epoch": 0.024177050399851217,
      "grad_norm": 18.334558486938477,
      "learning_rate": 9.780833673696254e-05,
      "loss": 7.0021,
      "step": 65
    },
    {
      "epoch": 0.02603682350753208,
      "grad_norm": 22.723039627075195,
      "learning_rate": 9.714387227305422e-05,
      "loss": 6.9676,
      "step": 70
    },
    {
      "epoch": 0.027896596615212942,
      "grad_norm": 18.721359252929688,
      "learning_rate": 9.639445136482548e-05,
      "loss": 5.9276,
      "step": 75
    },
    {
      "epoch": 0.02975636972289381,
      "grad_norm": 27.96847915649414,
      "learning_rate": 9.55614245194068e-05,
      "loss": 6.0862,
      "step": 80
    },
    {
      "epoch": 0.03161614283057467,
      "grad_norm": 26.781003952026367,
      "learning_rate": 9.464629290747842e-05,
      "loss": 6.6973,
      "step": 85
    },
    {
      "epoch": 0.03347591593825553,
      "grad_norm": 28.945425033569336,
      "learning_rate": 9.365070565805941e-05,
      "loss": 7.3995,
      "step": 90
    },
    {
      "epoch": 0.0353356890459364,
      "grad_norm": 23.053192138671875,
      "learning_rate": 9.257645688666556e-05,
      "loss": 6.5104,
      "step": 95
    },
    {
      "epoch": 0.037195462153617256,
      "grad_norm": 32.22383499145508,
      "learning_rate": 9.142548246219212e-05,
      "loss": 6.7477,
      "step": 100
    },
    {
      "epoch": 0.037195462153617256,
      "eval_loss": 1.5658334493637085,
      "eval_runtime": 92.4739,
      "eval_samples_per_second": 12.241,
      "eval_steps_per_second": 6.121,
      "step": 100
    },
    {
      "epoch": 0.03905523526129812,
      "grad_norm": 19.549184799194336,
      "learning_rate": 9.019985651834703e-05,
      "loss": 6.3479,
      "step": 105
    },
    {
      "epoch": 0.04091500836897898,
      "grad_norm": 22.8968563079834,
      "learning_rate": 8.890178771592199e-05,
      "loss": 6.7531,
      "step": 110
    },
    {
      "epoch": 0.04277478147665985,
      "grad_norm": 25.42777442932129,
      "learning_rate": 8.753361526263621e-05,
      "loss": 6.657,
      "step": 115
    },
    {
      "epoch": 0.04463455458434071,
      "grad_norm": 26.26284408569336,
      "learning_rate": 8.609780469772623e-05,
      "loss": 6.164,
      "step": 120
    },
    {
      "epoch": 0.046494327692021574,
      "grad_norm": 20.49610710144043,
      "learning_rate": 8.459694344887732e-05,
      "loss": 6.4586,
      "step": 125
    },
    {
      "epoch": 0.04835410079970243,
      "grad_norm": 24.12810707092285,
      "learning_rate": 8.303373616950408e-05,
      "loss": 6.2246,
      "step": 130
    },
    {
      "epoch": 0.0502138739073833,
      "grad_norm": 15.526240348815918,
      "learning_rate": 8.141099986478212e-05,
      "loss": 6.283,
      "step": 135
    },
    {
      "epoch": 0.05207364701506416,
      "grad_norm": 23.493165969848633,
      "learning_rate": 7.973165881521434e-05,
      "loss": 6.6471,
      "step": 140
    },
    {
      "epoch": 0.053933420122745025,
      "grad_norm": 21.8200626373291,
      "learning_rate": 7.799873930687978e-05,
      "loss": 6.3004,
      "step": 145
    },
    {
      "epoch": 0.055793193230425885,
      "grad_norm": 33.01738357543945,
      "learning_rate": 7.621536417786159e-05,
      "loss": 6.7252,
      "step": 150
    },
    {
      "epoch": 0.05765296633810675,
      "grad_norm": 12.76673698425293,
      "learning_rate": 7.438474719068173e-05,
      "loss": 4.8642,
      "step": 155
    },
    {
      "epoch": 0.05951273944578762,
      "grad_norm": 17.795074462890625,
      "learning_rate": 7.251018724088367e-05,
      "loss": 5.8487,
      "step": 160
    },
    {
      "epoch": 0.061372512553468477,
      "grad_norm": 18.770000457763672,
      "learning_rate": 7.059506241219965e-05,
      "loss": 6.1819,
      "step": 165
    },
    {
      "epoch": 0.06323228566114934,
      "grad_norm": 15.56336784362793,
      "learning_rate": 6.864282388901544e-05,
      "loss": 6.5113,
      "step": 170
    },
    {
      "epoch": 0.0650920587688302,
      "grad_norm": 20.163333892822266,
      "learning_rate": 6.665698973710288e-05,
      "loss": 6.9107,
      "step": 175
    },
    {
      "epoch": 0.06695183187651106,
      "grad_norm": 26.037216186523438,
      "learning_rate": 6.464113856382752e-05,
      "loss": 5.7699,
      "step": 180
    },
    {
      "epoch": 0.06881160498419193,
      "grad_norm": 21.532278060913086,
      "learning_rate": 6.259890306925627e-05,
      "loss": 6.4571,
      "step": 185
    },
    {
      "epoch": 0.0706713780918728,
      "grad_norm": 20.172101974487305,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 6.3829,
      "step": 190
    },
    {
      "epoch": 0.07253115119955365,
      "grad_norm": 23.37173080444336,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 5.9205,
      "step": 195
    },
    {
      "epoch": 0.07439092430723451,
      "grad_norm": 23.12742805480957,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 6.2874,
      "step": 200
    },
    {
      "epoch": 0.07439092430723451,
      "eval_loss": 1.5162262916564941,
      "eval_runtime": 92.4658,
      "eval_samples_per_second": 12.242,
      "eval_steps_per_second": 6.121,
      "step": 200
    },
    {
      "epoch": 0.07625069741491539,
      "grad_norm": 15.594170570373535,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 4.7487,
      "step": 205
    },
    {
      "epoch": 0.07811047052259625,
      "grad_norm": 20.116409301757812,
      "learning_rate": 5.212206015980742e-05,
      "loss": 4.89,
      "step": 210
    },
    {
      "epoch": 0.0799702436302771,
      "grad_norm": 17.264711380004883,
      "learning_rate": 5e-05,
      "loss": 6.4847,
      "step": 215
    },
    {
      "epoch": 0.08183001673795796,
      "grad_norm": 17.66196060180664,
      "learning_rate": 4.78779398401926e-05,
      "loss": 6.3116,
      "step": 220
    },
    {
      "epoch": 0.08368978984563884,
      "grad_norm": 16.622299194335938,
      "learning_rate": 4.575970377622456e-05,
      "loss": 6.1618,
      "step": 225
    },
    {
      "epoch": 0.0855495629533197,
      "grad_norm": 19.501249313354492,
      "learning_rate": 4.364910901265606e-05,
      "loss": 6.2765,
      "step": 230
    },
    {
      "epoch": 0.08740933606100056,
      "grad_norm": 17.714876174926758,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 6.649,
      "step": 235
    },
    {
      "epoch": 0.08926910916868142,
      "grad_norm": 22.967084884643555,
      "learning_rate": 3.94660365002137e-05,
      "loss": 6.1832,
      "step": 240
    },
    {
      "epoch": 0.09112888227636229,
      "grad_norm": 21.215139389038086,
      "learning_rate": 3.740109693074375e-05,
      "loss": 5.8375,
      "step": 245
    },
    {
      "epoch": 0.09298865538404315,
      "grad_norm": 26.07053565979004,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 5.9886,
      "step": 250
    },
    {
      "epoch": 0.09484842849172401,
      "grad_norm": 19.14733123779297,
      "learning_rate": 3.334301026289712e-05,
      "loss": 4.8415,
      "step": 255
    },
    {
      "epoch": 0.09670820159940487,
      "grad_norm": 17.448036193847656,
      "learning_rate": 3.135717611098458e-05,
      "loss": 6.3217,
      "step": 260
    },
    {
      "epoch": 0.09856797470708574,
      "grad_norm": 22.950471878051758,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 6.5765,
      "step": 265
    },
    {
      "epoch": 0.1004277478147666,
      "grad_norm": 20.232675552368164,
      "learning_rate": 2.748981275911633e-05,
      "loss": 5.6822,
      "step": 270
    },
    {
      "epoch": 0.10228752092244746,
      "grad_norm": 16.764389038085938,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 6.7146,
      "step": 275
    },
    {
      "epoch": 0.10414729403012832,
      "grad_norm": 14.853644371032715,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 5.9485,
      "step": 280
    },
    {
      "epoch": 0.10600706713780919,
      "grad_norm": 22.9636173248291,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 6.4764,
      "step": 285
    },
    {
      "epoch": 0.10786684024549005,
      "grad_norm": 31.075511932373047,
      "learning_rate": 2.026834118478567e-05,
      "loss": 5.6364,
      "step": 290
    },
    {
      "epoch": 0.10972661335317091,
      "grad_norm": 32.21100616455078,
      "learning_rate": 1.858900013521788e-05,
      "loss": 5.6664,
      "step": 295
    },
    {
      "epoch": 0.11158638646085177,
      "grad_norm": 17.637603759765625,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 5.4562,
      "step": 300
    },
    {
      "epoch": 0.11158638646085177,
      "eval_loss": 1.5176162719726562,
      "eval_runtime": 92.4353,
      "eval_samples_per_second": 12.246,
      "eval_steps_per_second": 6.123,
      "step": 300
    },
    {
      "epoch": 0.11344615956853264,
      "grad_norm": 22.75035858154297,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 5.7324,
      "step": 305
    },
    {
      "epoch": 0.1153059326762135,
      "grad_norm": 15.614346504211426,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 6.1359,
      "step": 310
    },
    {
      "epoch": 0.11716570578389436,
      "grad_norm": 16.038312911987305,
      "learning_rate": 1.246638473736378e-05,
      "loss": 6.6932,
      "step": 315
    },
    {
      "epoch": 0.11902547889157523,
      "grad_norm": 16.996204376220703,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 5.9517,
      "step": 320
    },
    {
      "epoch": 0.1208852519992561,
      "grad_norm": 17.03664207458496,
      "learning_rate": 9.800143481652979e-06,
      "loss": 5.8918,
      "step": 325
    },
    {
      "epoch": 0.12274502510693695,
      "grad_norm": 17.947437286376953,
      "learning_rate": 8.574517537807897e-06,
      "loss": 6.2059,
      "step": 330
    },
    {
      "epoch": 0.12460479821461781,
      "grad_norm": 20.978199005126953,
      "learning_rate": 7.423543113334436e-06,
      "loss": 6.6856,
      "step": 335
    },
    {
      "epoch": 0.12646457132229869,
      "grad_norm": 19.61482048034668,
      "learning_rate": 6.349294341940593e-06,
      "loss": 5.6831,
      "step": 340
    },
    {
      "epoch": 0.12832434442997953,
      "grad_norm": 20.240877151489258,
      "learning_rate": 5.353707092521582e-06,
      "loss": 5.7745,
      "step": 345
    },
    {
      "epoch": 0.1301841175376604,
      "grad_norm": 16.882625579833984,
      "learning_rate": 4.43857548059321e-06,
      "loss": 5.3504,
      "step": 350
    },
    {
      "epoch": 0.13204389064534128,
      "grad_norm": 17.49921417236328,
      "learning_rate": 3.605548635174533e-06,
      "loss": 4.7735,
      "step": 355
    },
    {
      "epoch": 0.13390366375302212,
      "grad_norm": 22.028711318969727,
      "learning_rate": 2.85612772694579e-06,
      "loss": 6.265,
      "step": 360
    },
    {
      "epoch": 0.135763436860703,
      "grad_norm": 15.451027870178223,
      "learning_rate": 2.191663263037458e-06,
      "loss": 5.6532,
      "step": 365
    },
    {
      "epoch": 0.13762320996838387,
      "grad_norm": 20.007116317749023,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 5.9359,
      "step": 370
    },
    {
      "epoch": 0.13948298307606471,
      "grad_norm": 14.0477294921875,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 6.4376,
      "step": 375
    },
    {
      "epoch": 0.1413427561837456,
      "grad_norm": 17.337631225585938,
      "learning_rate": 7.192044826145771e-07,
      "loss": 6.4755,
      "step": 380
    },
    {
      "epoch": 0.14320252929142643,
      "grad_norm": 18.371578216552734,
      "learning_rate": 4.049782370561583e-07,
      "loss": 6.1232,
      "step": 385
    },
    {
      "epoch": 0.1450623023991073,
      "grad_norm": 14.091248512268066,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 5.7881,
      "step": 390
    },
    {
      "epoch": 0.14692207550678818,
      "grad_norm": 18.428977966308594,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 6.1315,
      "step": 395
    },
    {
      "epoch": 0.14878184861446903,
      "grad_norm": 21.504026412963867,
      "learning_rate": 0.0,
      "loss": 7.0047,
      "step": 400
    },
    {
      "epoch": 0.14878184861446903,
      "eval_loss": 1.4846231937408447,
      "eval_runtime": 92.4321,
      "eval_samples_per_second": 12.247,
      "eval_steps_per_second": 6.123,
      "step": 400
    }
  ],
  "logging_steps": 5,
  "max_steps": 400,
  "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": 1.403890111170478e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}