{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.11533193973906149,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002883298493476537,
      "eval_loss": 0.8066914081573486,
      "eval_runtime": 230.0868,
      "eval_samples_per_second": 6.35,
      "eval_steps_per_second": 3.177,
      "step": 1
    },
    {
      "epoch": 0.0014416492467382686,
      "grad_norm": 2.8629841804504395,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 3.7011,
      "step": 5
    },
    {
      "epoch": 0.0028832984934765373,
      "grad_norm": 2.9777753353118896,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.9463,
      "step": 10
    },
    {
      "epoch": 0.004324947740214806,
      "grad_norm": 2.402409553527832,
      "learning_rate": 5e-05,
      "loss": 2.9867,
      "step": 15
    },
    {
      "epoch": 0.0057665969869530745,
      "grad_norm": 5.7486252784729,
      "learning_rate": 6.666666666666667e-05,
      "loss": 2.6301,
      "step": 20
    },
    {
      "epoch": 0.007208246233691343,
      "grad_norm": 2.579139232635498,
      "learning_rate": 8.333333333333334e-05,
      "loss": 2.6941,
      "step": 25
    },
    {
      "epoch": 0.008649895480429612,
      "grad_norm": 2.965322256088257,
      "learning_rate": 0.0001,
      "loss": 2.5461,
      "step": 30
    },
    {
      "epoch": 0.01009154472716788,
      "grad_norm": 2.260119915008545,
      "learning_rate": 9.995494831023409e-05,
      "loss": 2.8797,
      "step": 35
    },
    {
      "epoch": 0.011533193973906149,
      "grad_norm": 2.610872745513916,
      "learning_rate": 9.981987442712633e-05,
      "loss": 2.6554,
      "step": 40
    },
    {
      "epoch": 0.012974843220644417,
      "grad_norm": 2.4740097522735596,
      "learning_rate": 9.959502176294383e-05,
      "loss": 2.8629,
      "step": 45
    },
    {
      "epoch": 0.014416492467382686,
      "grad_norm": 2.1658761501312256,
      "learning_rate": 9.928079551738543e-05,
      "loss": 2.5093,
      "step": 50
    },
    {
      "epoch": 0.015858141714120956,
      "grad_norm": 2.2830867767333984,
      "learning_rate": 9.887776194738432e-05,
      "loss": 2.6503,
      "step": 55
    },
    {
      "epoch": 0.017299790960859224,
      "grad_norm": 2.0611510276794434,
      "learning_rate": 9.838664734667495e-05,
      "loss": 2.7094,
      "step": 60
    },
    {
      "epoch": 0.018741440207597493,
      "grad_norm": 2.929940700531006,
      "learning_rate": 9.780833673696254e-05,
      "loss": 2.7529,
      "step": 65
    },
    {
      "epoch": 0.02018308945433576,
      "grad_norm": 2.0682194232940674,
      "learning_rate": 9.714387227305422e-05,
      "loss": 3.08,
      "step": 70
    },
    {
      "epoch": 0.02162473870107403,
      "grad_norm": 2.8449878692626953,
      "learning_rate": 9.639445136482548e-05,
      "loss": 2.7717,
      "step": 75
    },
    {
      "epoch": 0.023066387947812298,
      "grad_norm": 3.2146430015563965,
      "learning_rate": 9.55614245194068e-05,
      "loss": 2.6265,
      "step": 80
    },
    {
      "epoch": 0.024508037194550567,
      "grad_norm": 2.071394443511963,
      "learning_rate": 9.464629290747842e-05,
      "loss": 2.795,
      "step": 85
    },
    {
      "epoch": 0.025949686441288835,
      "grad_norm": 1.8428181409835815,
      "learning_rate": 9.365070565805941e-05,
      "loss": 2.4166,
      "step": 90
    },
    {
      "epoch": 0.027391335688027103,
      "grad_norm": 2.301480770111084,
      "learning_rate": 9.257645688666556e-05,
      "loss": 2.5041,
      "step": 95
    },
    {
      "epoch": 0.028832984934765372,
      "grad_norm": 2.6278109550476074,
      "learning_rate": 9.142548246219212e-05,
      "loss": 2.3521,
      "step": 100
    },
    {
      "epoch": 0.028832984934765372,
      "eval_loss": 0.6489478945732117,
      "eval_runtime": 232.2501,
      "eval_samples_per_second": 6.291,
      "eval_steps_per_second": 3.147,
      "step": 100
    },
    {
      "epoch": 0.03027463418150364,
      "grad_norm": 3.011148452758789,
      "learning_rate": 9.019985651834703e-05,
      "loss": 2.8982,
      "step": 105
    },
    {
      "epoch": 0.03171628342824191,
      "grad_norm": 2.338167428970337,
      "learning_rate": 8.890178771592199e-05,
      "loss": 2.7675,
      "step": 110
    },
    {
      "epoch": 0.03315793267498018,
      "grad_norm": 1.683278203010559,
      "learning_rate": 8.753361526263621e-05,
      "loss": 2.0754,
      "step": 115
    },
    {
      "epoch": 0.03459958192171845,
      "grad_norm": 2.0816845893859863,
      "learning_rate": 8.609780469772623e-05,
      "loss": 2.6878,
      "step": 120
    },
    {
      "epoch": 0.036041231168456714,
      "grad_norm": 1.9449472427368164,
      "learning_rate": 8.459694344887732e-05,
      "loss": 2.5088,
      "step": 125
    },
    {
      "epoch": 0.037482880415194986,
      "grad_norm": 3.2148945331573486,
      "learning_rate": 8.303373616950408e-05,
      "loss": 2.3728,
      "step": 130
    },
    {
      "epoch": 0.03892452966193325,
      "grad_norm": 2.0440514087677,
      "learning_rate": 8.141099986478212e-05,
      "loss": 2.7105,
      "step": 135
    },
    {
      "epoch": 0.04036617890867152,
      "grad_norm": 2.3115408420562744,
      "learning_rate": 7.973165881521434e-05,
      "loss": 2.7877,
      "step": 140
    },
    {
      "epoch": 0.04180782815540979,
      "grad_norm": 2.4646363258361816,
      "learning_rate": 7.799873930687978e-05,
      "loss": 2.3042,
      "step": 145
    },
    {
      "epoch": 0.04324947740214806,
      "grad_norm": 2.0529026985168457,
      "learning_rate": 7.621536417786159e-05,
      "loss": 2.1666,
      "step": 150
    },
    {
      "epoch": 0.044691126648886324,
      "grad_norm": 2.708082914352417,
      "learning_rate": 7.438474719068173e-05,
      "loss": 2.4795,
      "step": 155
    },
    {
      "epoch": 0.046132775895624596,
      "grad_norm": 2.6128344535827637,
      "learning_rate": 7.251018724088367e-05,
      "loss": 2.6347,
      "step": 160
    },
    {
      "epoch": 0.04757442514236286,
      "grad_norm": 2.3222455978393555,
      "learning_rate": 7.059506241219965e-05,
      "loss": 2.5229,
      "step": 165
    },
    {
      "epoch": 0.04901607438910113,
      "grad_norm": 2.3687586784362793,
      "learning_rate": 6.864282388901544e-05,
      "loss": 2.1619,
      "step": 170
    },
    {
      "epoch": 0.0504577236358394,
      "grad_norm": 2.1631596088409424,
      "learning_rate": 6.665698973710288e-05,
      "loss": 2.608,
      "step": 175
    },
    {
      "epoch": 0.05189937288257767,
      "grad_norm": 2.542854070663452,
      "learning_rate": 6.464113856382752e-05,
      "loss": 2.4161,
      "step": 180
    },
    {
      "epoch": 0.053341022129315935,
      "grad_norm": 1.9485701322555542,
      "learning_rate": 6.259890306925627e-05,
      "loss": 2.7054,
      "step": 185
    },
    {
      "epoch": 0.05478267137605421,
      "grad_norm": 2.0567824840545654,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 2.5283,
      "step": 190
    },
    {
      "epoch": 0.05622432062279247,
      "grad_norm": 2.237706184387207,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 2.5936,
      "step": 195
    },
    {
      "epoch": 0.057665969869530743,
      "grad_norm": 2.4279816150665283,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 2.2478,
      "step": 200
    },
    {
      "epoch": 0.057665969869530743,
      "eval_loss": 0.6299009323120117,
      "eval_runtime": 232.2791,
      "eval_samples_per_second": 6.29,
      "eval_steps_per_second": 3.147,
      "step": 200
    },
    {
      "epoch": 0.05910761911626901,
      "grad_norm": 2.3157238960266113,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 2.5239,
      "step": 205
    },
    {
      "epoch": 0.06054926836300728,
      "grad_norm": 2.1027748584747314,
      "learning_rate": 5.212206015980742e-05,
      "loss": 2.5472,
      "step": 210
    },
    {
      "epoch": 0.06199091760974555,
      "grad_norm": 2.006582736968994,
      "learning_rate": 5e-05,
      "loss": 2.4515,
      "step": 215
    },
    {
      "epoch": 0.06343256685648382,
      "grad_norm": 2.642357587814331,
      "learning_rate": 4.78779398401926e-05,
      "loss": 2.4863,
      "step": 220
    },
    {
      "epoch": 0.06487421610322208,
      "grad_norm": 2.00481915473938,
      "learning_rate": 4.575970377622456e-05,
      "loss": 2.2922,
      "step": 225
    },
    {
      "epoch": 0.06631586534996035,
      "grad_norm": 2.7545015811920166,
      "learning_rate": 4.364910901265606e-05,
      "loss": 2.6815,
      "step": 230
    },
    {
      "epoch": 0.06775751459669863,
      "grad_norm": 1.8313714265823364,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 2.5887,
      "step": 235
    },
    {
      "epoch": 0.0691991638434369,
      "grad_norm": 2.634171724319458,
      "learning_rate": 3.94660365002137e-05,
      "loss": 2.6743,
      "step": 240
    },
    {
      "epoch": 0.07064081309017516,
      "grad_norm": 2.0860755443573,
      "learning_rate": 3.740109693074375e-05,
      "loss": 2.4406,
      "step": 245
    },
    {
      "epoch": 0.07208246233691343,
      "grad_norm": 1.9648572206497192,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 2.2171,
      "step": 250
    },
    {
      "epoch": 0.0735241115836517,
      "grad_norm": 2.553926467895508,
      "learning_rate": 3.334301026289712e-05,
      "loss": 2.6093,
      "step": 255
    },
    {
      "epoch": 0.07496576083038997,
      "grad_norm": 2.15262770652771,
      "learning_rate": 3.135717611098458e-05,
      "loss": 2.5061,
      "step": 260
    },
    {
      "epoch": 0.07640741007712823,
      "grad_norm": 2.1403212547302246,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 2.4626,
      "step": 265
    },
    {
      "epoch": 0.0778490593238665,
      "grad_norm": 2.3066139221191406,
      "learning_rate": 2.748981275911633e-05,
      "loss": 2.5797,
      "step": 270
    },
    {
      "epoch": 0.07929070857060477,
      "grad_norm": 2.4364964962005615,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 2.3479,
      "step": 275
    },
    {
      "epoch": 0.08073235781734305,
      "grad_norm": 1.7531434297561646,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 2.1783,
      "step": 280
    },
    {
      "epoch": 0.0821740070640813,
      "grad_norm": 2.306757688522339,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 2.6474,
      "step": 285
    },
    {
      "epoch": 0.08361565631081957,
      "grad_norm": 2.356346368789673,
      "learning_rate": 2.026834118478567e-05,
      "loss": 2.6784,
      "step": 290
    },
    {
      "epoch": 0.08505730555755785,
      "grad_norm": 2.021139144897461,
      "learning_rate": 1.858900013521788e-05,
      "loss": 2.7808,
      "step": 295
    },
    {
      "epoch": 0.08649895480429612,
      "grad_norm": 1.925753116607666,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 2.0863,
      "step": 300
    },
    {
      "epoch": 0.08649895480429612,
      "eval_loss": 0.6235827207565308,
      "eval_runtime": 232.2728,
      "eval_samples_per_second": 6.29,
      "eval_steps_per_second": 3.147,
      "step": 300
    },
    {
      "epoch": 0.08794060405103438,
      "grad_norm": 1.981512427330017,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 2.3868,
      "step": 305
    },
    {
      "epoch": 0.08938225329777265,
      "grad_norm": 2.808793544769287,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 2.6536,
      "step": 310
    },
    {
      "epoch": 0.09082390254451092,
      "grad_norm": 1.8927634954452515,
      "learning_rate": 1.246638473736378e-05,
      "loss": 2.4549,
      "step": 315
    },
    {
      "epoch": 0.09226555179124919,
      "grad_norm": 1.5640909671783447,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 2.3759,
      "step": 320
    },
    {
      "epoch": 0.09370720103798746,
      "grad_norm": 2.3104989528656006,
      "learning_rate": 9.800143481652979e-06,
      "loss": 2.48,
      "step": 325
    },
    {
      "epoch": 0.09514885028472572,
      "grad_norm": 2.1639902591705322,
      "learning_rate": 8.574517537807897e-06,
      "loss": 2.7076,
      "step": 330
    },
    {
      "epoch": 0.096590499531464,
      "grad_norm": 2.3075921535491943,
      "learning_rate": 7.423543113334436e-06,
      "loss": 2.8997,
      "step": 335
    },
    {
      "epoch": 0.09803214877820227,
      "grad_norm": 2.313678503036499,
      "learning_rate": 6.349294341940593e-06,
      "loss": 2.7808,
      "step": 340
    },
    {
      "epoch": 0.09947379802494054,
      "grad_norm": 2.103289842605591,
      "learning_rate": 5.353707092521582e-06,
      "loss": 2.6406,
      "step": 345
    },
    {
      "epoch": 0.1009154472716788,
      "grad_norm": 2.329012870788574,
      "learning_rate": 4.43857548059321e-06,
      "loss": 2.4586,
      "step": 350
    },
    {
      "epoch": 0.10235709651841707,
      "grad_norm": 1.8864246606826782,
      "learning_rate": 3.605548635174533e-06,
      "loss": 2.6252,
      "step": 355
    },
    {
      "epoch": 0.10379874576515534,
      "grad_norm": 2.0503783226013184,
      "learning_rate": 2.85612772694579e-06,
      "loss": 2.7678,
      "step": 360
    },
    {
      "epoch": 0.10524039501189361,
      "grad_norm": 1.6099926233291626,
      "learning_rate": 2.191663263037458e-06,
      "loss": 2.3372,
      "step": 365
    },
    {
      "epoch": 0.10668204425863187,
      "grad_norm": 1.768552541732788,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 2.5533,
      "step": 370
    },
    {
      "epoch": 0.10812369350537014,
      "grad_norm": 2.1435041427612305,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 2.5535,
      "step": 375
    },
    {
      "epoch": 0.10956534275210841,
      "grad_norm": 1.6894549131393433,
      "learning_rate": 7.192044826145771e-07,
      "loss": 2.5319,
      "step": 380
    },
    {
      "epoch": 0.11100699199884669,
      "grad_norm": 1.8937331438064575,
      "learning_rate": 4.049782370561583e-07,
      "loss": 2.5789,
      "step": 385
    },
    {
      "epoch": 0.11244864124558494,
      "grad_norm": 2.080510139465332,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 2.4853,
      "step": 390
    },
    {
      "epoch": 0.11389029049232322,
      "grad_norm": 2.1903302669525146,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 2.4425,
      "step": 395
    },
    {
      "epoch": 0.11533193973906149,
      "grad_norm": 2.601141929626465,
      "learning_rate": 0.0,
      "loss": 1.9008,
      "step": 400
    },
    {
      "epoch": 0.11533193973906149,
      "eval_loss": 0.6221744418144226,
      "eval_runtime": 232.3152,
      "eval_samples_per_second": 6.289,
      "eval_steps_per_second": 3.147,
      "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": 2.804271657517056e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}