{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3148986419996064,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000787246604999016,
      "eval_loss": 4.341583728790283,
      "eval_runtime": 39.2665,
      "eval_samples_per_second": 13.625,
      "eval_steps_per_second": 6.825,
      "step": 1
    },
    {
      "epoch": 0.00393623302499508,
      "grad_norm": 3.287663698196411,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 2.5476,
      "step": 5
    },
    {
      "epoch": 0.00787246604999016,
      "grad_norm": 3.3073341846466064,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 3.0789,
      "step": 10
    },
    {
      "epoch": 0.011808699074985239,
      "grad_norm": 4.236186504364014,
      "learning_rate": 5e-05,
      "loss": 3.3087,
      "step": 15
    },
    {
      "epoch": 0.01574493209998032,
      "grad_norm": 5.51737117767334,
      "learning_rate": 6.666666666666667e-05,
      "loss": 3.0456,
      "step": 20
    },
    {
      "epoch": 0.0196811651249754,
      "grad_norm": 3.676185369491577,
      "learning_rate": 8.333333333333334e-05,
      "loss": 2.3899,
      "step": 25
    },
    {
      "epoch": 0.023617398149970478,
      "grad_norm": 6.131873607635498,
      "learning_rate": 0.0001,
      "loss": 1.7705,
      "step": 30
    },
    {
      "epoch": 0.027553631174965558,
      "grad_norm": 5.308169364929199,
      "learning_rate": 9.995494831023409e-05,
      "loss": 1.3751,
      "step": 35
    },
    {
      "epoch": 0.03148986419996064,
      "grad_norm": 6.609120845794678,
      "learning_rate": 9.981987442712633e-05,
      "loss": 1.092,
      "step": 40
    },
    {
      "epoch": 0.03542609722495572,
      "grad_norm": 7.438577175140381,
      "learning_rate": 9.959502176294383e-05,
      "loss": 1.2124,
      "step": 45
    },
    {
      "epoch": 0.0393623302499508,
      "grad_norm": 15.855297088623047,
      "learning_rate": 9.928079551738543e-05,
      "loss": 1.8589,
      "step": 50
    },
    {
      "epoch": 0.04329856327494588,
      "grad_norm": 2.7602858543395996,
      "learning_rate": 9.887776194738432e-05,
      "loss": 1.017,
      "step": 55
    },
    {
      "epoch": 0.047234796299940957,
      "grad_norm": 4.690028190612793,
      "learning_rate": 9.838664734667495e-05,
      "loss": 0.8812,
      "step": 60
    },
    {
      "epoch": 0.051171029324936036,
      "grad_norm": 2.759033203125,
      "learning_rate": 9.780833673696254e-05,
      "loss": 0.744,
      "step": 65
    },
    {
      "epoch": 0.055107262349931116,
      "grad_norm": 2.8672986030578613,
      "learning_rate": 9.714387227305422e-05,
      "loss": 0.8014,
      "step": 70
    },
    {
      "epoch": 0.059043495374926196,
      "grad_norm": 5.7079691886901855,
      "learning_rate": 9.639445136482548e-05,
      "loss": 0.6077,
      "step": 75
    },
    {
      "epoch": 0.06297972839992128,
      "grad_norm": 3.614234685897827,
      "learning_rate": 9.55614245194068e-05,
      "loss": 0.6716,
      "step": 80
    },
    {
      "epoch": 0.06691596142491635,
      "grad_norm": 4.64866304397583,
      "learning_rate": 9.464629290747842e-05,
      "loss": 0.832,
      "step": 85
    },
    {
      "epoch": 0.07085219444991143,
      "grad_norm": 58.108211517333984,
      "learning_rate": 9.365070565805941e-05,
      "loss": 0.6935,
      "step": 90
    },
    {
      "epoch": 0.07478842747490651,
      "grad_norm": 8.722001075744629,
      "learning_rate": 9.257645688666556e-05,
      "loss": 0.8135,
      "step": 95
    },
    {
      "epoch": 0.0787246604999016,
      "grad_norm": 12.210494041442871,
      "learning_rate": 9.142548246219212e-05,
      "loss": 1.0976,
      "step": 100
    },
    {
      "epoch": 0.0787246604999016,
      "eval_loss": 0.7595570683479309,
      "eval_runtime": 40.0211,
      "eval_samples_per_second": 13.368,
      "eval_steps_per_second": 6.696,
      "step": 100
    },
    {
      "epoch": 0.08266089352489667,
      "grad_norm": 3.2335689067840576,
      "learning_rate": 9.019985651834703e-05,
      "loss": 0.63,
      "step": 105
    },
    {
      "epoch": 0.08659712654989175,
      "grad_norm": 2.137996196746826,
      "learning_rate": 8.890178771592199e-05,
      "loss": 0.6481,
      "step": 110
    },
    {
      "epoch": 0.09053335957488683,
      "grad_norm": 1.6560288667678833,
      "learning_rate": 8.753361526263621e-05,
      "loss": 0.5692,
      "step": 115
    },
    {
      "epoch": 0.09446959259988191,
      "grad_norm": 3.019510507583618,
      "learning_rate": 8.609780469772623e-05,
      "loss": 0.6044,
      "step": 120
    },
    {
      "epoch": 0.09840582562487699,
      "grad_norm": 7.847659587860107,
      "learning_rate": 8.459694344887732e-05,
      "loss": 0.7648,
      "step": 125
    },
    {
      "epoch": 0.10234205864987207,
      "grad_norm": 3.2211923599243164,
      "learning_rate": 8.303373616950408e-05,
      "loss": 0.5977,
      "step": 130
    },
    {
      "epoch": 0.10627829167486715,
      "grad_norm": 2.080706834793091,
      "learning_rate": 8.141099986478212e-05,
      "loss": 0.829,
      "step": 135
    },
    {
      "epoch": 0.11021452469986223,
      "grad_norm": 2.824303388595581,
      "learning_rate": 7.973165881521434e-05,
      "loss": 0.5698,
      "step": 140
    },
    {
      "epoch": 0.1141507577248573,
      "grad_norm": 2.651510715484619,
      "learning_rate": 7.799873930687978e-05,
      "loss": 0.5823,
      "step": 145
    },
    {
      "epoch": 0.11808699074985239,
      "grad_norm": 5.05307149887085,
      "learning_rate": 7.621536417786159e-05,
      "loss": 0.7616,
      "step": 150
    },
    {
      "epoch": 0.12202322377484746,
      "grad_norm": 2.359443426132202,
      "learning_rate": 7.438474719068173e-05,
      "loss": 0.6418,
      "step": 155
    },
    {
      "epoch": 0.12595945679984255,
      "grad_norm": 2.4412314891815186,
      "learning_rate": 7.251018724088367e-05,
      "loss": 0.7099,
      "step": 160
    },
    {
      "epoch": 0.12989568982483762,
      "grad_norm": 2.074559211730957,
      "learning_rate": 7.059506241219965e-05,
      "loss": 0.5721,
      "step": 165
    },
    {
      "epoch": 0.1338319228498327,
      "grad_norm": 1.9991369247436523,
      "learning_rate": 6.864282388901544e-05,
      "loss": 0.5368,
      "step": 170
    },
    {
      "epoch": 0.1377681558748278,
      "grad_norm": 3.027350664138794,
      "learning_rate": 6.665698973710288e-05,
      "loss": 0.6703,
      "step": 175
    },
    {
      "epoch": 0.14170438889982287,
      "grad_norm": 4.630465030670166,
      "learning_rate": 6.464113856382752e-05,
      "loss": 0.6782,
      "step": 180
    },
    {
      "epoch": 0.14564062192481794,
      "grad_norm": 3.2505524158477783,
      "learning_rate": 6.259890306925627e-05,
      "loss": 0.5771,
      "step": 185
    },
    {
      "epoch": 0.14957685494981302,
      "grad_norm": 3.7799837589263916,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 0.4793,
      "step": 190
    },
    {
      "epoch": 0.15351308797480812,
      "grad_norm": 4.813235282897949,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 0.6911,
      "step": 195
    },
    {
      "epoch": 0.1574493209998032,
      "grad_norm": 6.90015172958374,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 0.8213,
      "step": 200
    },
    {
      "epoch": 0.1574493209998032,
      "eval_loss": 0.6632534265518188,
      "eval_runtime": 40.0398,
      "eval_samples_per_second": 13.362,
      "eval_steps_per_second": 6.693,
      "step": 200
    },
    {
      "epoch": 0.16138555402479826,
      "grad_norm": 2.0634400844573975,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 0.5963,
      "step": 205
    },
    {
      "epoch": 0.16532178704979333,
      "grad_norm": 2.014413595199585,
      "learning_rate": 5.212206015980742e-05,
      "loss": 0.5964,
      "step": 210
    },
    {
      "epoch": 0.16925802007478843,
      "grad_norm": 2.681185483932495,
      "learning_rate": 5e-05,
      "loss": 0.5487,
      "step": 215
    },
    {
      "epoch": 0.1731942530997835,
      "grad_norm": 2.315053701400757,
      "learning_rate": 4.78779398401926e-05,
      "loss": 0.6144,
      "step": 220
    },
    {
      "epoch": 0.17713048612477858,
      "grad_norm": 1.8942983150482178,
      "learning_rate": 4.575970377622456e-05,
      "loss": 0.5265,
      "step": 225
    },
    {
      "epoch": 0.18106671914977365,
      "grad_norm": 2.6972315311431885,
      "learning_rate": 4.364910901265606e-05,
      "loss": 0.5905,
      "step": 230
    },
    {
      "epoch": 0.18500295217476875,
      "grad_norm": 4.619275093078613,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 0.4446,
      "step": 235
    },
    {
      "epoch": 0.18893918519976383,
      "grad_norm": 4.710716724395752,
      "learning_rate": 3.94660365002137e-05,
      "loss": 0.7013,
      "step": 240
    },
    {
      "epoch": 0.1928754182247589,
      "grad_norm": 5.614984512329102,
      "learning_rate": 3.740109693074375e-05,
      "loss": 0.7568,
      "step": 245
    },
    {
      "epoch": 0.19681165124975397,
      "grad_norm": 6.1038055419921875,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 0.8728,
      "step": 250
    },
    {
      "epoch": 0.20074788427474907,
      "grad_norm": 2.3163340091705322,
      "learning_rate": 3.334301026289712e-05,
      "loss": 0.5208,
      "step": 255
    },
    {
      "epoch": 0.20468411729974414,
      "grad_norm": 2.6426377296447754,
      "learning_rate": 3.135717611098458e-05,
      "loss": 0.5808,
      "step": 260
    },
    {
      "epoch": 0.20862035032473922,
      "grad_norm": 1.9240648746490479,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 0.4606,
      "step": 265
    },
    {
      "epoch": 0.2125565833497343,
      "grad_norm": 2.9262654781341553,
      "learning_rate": 2.748981275911633e-05,
      "loss": 0.6141,
      "step": 270
    },
    {
      "epoch": 0.2164928163747294,
      "grad_norm": 1.9150549173355103,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 0.5032,
      "step": 275
    },
    {
      "epoch": 0.22042904939972446,
      "grad_norm": 2.690410614013672,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 0.4777,
      "step": 280
    },
    {
      "epoch": 0.22436528242471954,
      "grad_norm": 9.347960472106934,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 0.5886,
      "step": 285
    },
    {
      "epoch": 0.2283015154497146,
      "grad_norm": 7.149267196655273,
      "learning_rate": 2.026834118478567e-05,
      "loss": 0.491,
      "step": 290
    },
    {
      "epoch": 0.2322377484747097,
      "grad_norm": 3.001629114151001,
      "learning_rate": 1.858900013521788e-05,
      "loss": 0.5241,
      "step": 295
    },
    {
      "epoch": 0.23617398149970478,
      "grad_norm": 5.5716776847839355,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 0.5923,
      "step": 300
    },
    {
      "epoch": 0.23617398149970478,
      "eval_loss": 0.6164750456809998,
      "eval_runtime": 40.0458,
      "eval_samples_per_second": 13.36,
      "eval_steps_per_second": 6.692,
      "step": 300
    },
    {
      "epoch": 0.24011021452469986,
      "grad_norm": 1.9683716297149658,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 0.5396,
      "step": 305
    },
    {
      "epoch": 0.24404644754969493,
      "grad_norm": 2.5637612342834473,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 0.6067,
      "step": 310
    },
    {
      "epoch": 0.24798268057469003,
      "grad_norm": 3.7359297275543213,
      "learning_rate": 1.246638473736378e-05,
      "loss": 0.697,
      "step": 315
    },
    {
      "epoch": 0.2519189135996851,
      "grad_norm": 1.4351948499679565,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 0.4843,
      "step": 320
    },
    {
      "epoch": 0.2558551466246802,
      "grad_norm": 3.02543306350708,
      "learning_rate": 9.800143481652979e-06,
      "loss": 0.5738,
      "step": 325
    },
    {
      "epoch": 0.25979137964967525,
      "grad_norm": 2.9249134063720703,
      "learning_rate": 8.574517537807897e-06,
      "loss": 0.4891,
      "step": 330
    },
    {
      "epoch": 0.2637276126746703,
      "grad_norm": 2.3675098419189453,
      "learning_rate": 7.423543113334436e-06,
      "loss": 0.6064,
      "step": 335
    },
    {
      "epoch": 0.2676638456996654,
      "grad_norm": 2.7012715339660645,
      "learning_rate": 6.349294341940593e-06,
      "loss": 0.5317,
      "step": 340
    },
    {
      "epoch": 0.2716000787246605,
      "grad_norm": 3.8618979454040527,
      "learning_rate": 5.353707092521582e-06,
      "loss": 0.7395,
      "step": 345
    },
    {
      "epoch": 0.2755363117496556,
      "grad_norm": 9.676193237304688,
      "learning_rate": 4.43857548059321e-06,
      "loss": 0.8015,
      "step": 350
    },
    {
      "epoch": 0.27947254477465067,
      "grad_norm": 2.359666347503662,
      "learning_rate": 3.605548635174533e-06,
      "loss": 0.601,
      "step": 355
    },
    {
      "epoch": 0.28340877779964574,
      "grad_norm": 2.5223586559295654,
      "learning_rate": 2.85612772694579e-06,
      "loss": 0.6174,
      "step": 360
    },
    {
      "epoch": 0.2873450108246408,
      "grad_norm": 2.070843458175659,
      "learning_rate": 2.191663263037458e-06,
      "loss": 0.493,
      "step": 365
    },
    {
      "epoch": 0.2912812438496359,
      "grad_norm": 2.620171546936035,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 0.6141,
      "step": 370
    },
    {
      "epoch": 0.29521747687463096,
      "grad_norm": 11.396443367004395,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 0.5561,
      "step": 375
    },
    {
      "epoch": 0.29915370989962603,
      "grad_norm": 4.162880897521973,
      "learning_rate": 7.192044826145771e-07,
      "loss": 0.4605,
      "step": 380
    },
    {
      "epoch": 0.30308994292462116,
      "grad_norm": 1.9833643436431885,
      "learning_rate": 4.049782370561583e-07,
      "loss": 0.4564,
      "step": 385
    },
    {
      "epoch": 0.30702617594961623,
      "grad_norm": 3.277276039123535,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 0.5269,
      "step": 390
    },
    {
      "epoch": 0.3109624089746113,
      "grad_norm": 4.305200099945068,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 0.5661,
      "step": 395
    },
    {
      "epoch": 0.3148986419996064,
      "grad_norm": 11.541528701782227,
      "learning_rate": 0.0,
      "loss": 0.8866,
      "step": 400
    },
    {
      "epoch": 0.3148986419996064,
      "eval_loss": 0.6033578515052795,
      "eval_runtime": 40.0472,
      "eval_samples_per_second": 13.359,
      "eval_steps_per_second": 6.692,
      "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": 1.394108836872192e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}