{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.012007144250829244,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.0017860627073107e-05,
      "eval_loss": 1.443517804145813,
      "eval_runtime": 510.9532,
      "eval_samples_per_second": 27.453,
      "eval_steps_per_second": 13.727,
      "step": 1
    },
    {
      "epoch": 0.00015008930313536553,
      "grad_norm": 0.3933664560317993,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.2961,
      "step": 5
    },
    {
      "epoch": 0.00030017860627073106,
      "grad_norm": 0.7418891191482544,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.4393,
      "step": 10
    },
    {
      "epoch": 0.0004502679094060966,
      "grad_norm": 0.9560197591781616,
      "learning_rate": 5e-05,
      "loss": 0.5289,
      "step": 15
    },
    {
      "epoch": 0.0006003572125414621,
      "grad_norm": 0.680629551410675,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.5328,
      "step": 20
    },
    {
      "epoch": 0.0007504465156768277,
      "grad_norm": 1.0983694791793823,
      "learning_rate": 8.333333333333334e-05,
      "loss": 0.4416,
      "step": 25
    },
    {
      "epoch": 0.0009005358188121932,
      "grad_norm": 1.356644630432129,
      "learning_rate": 0.0001,
      "loss": 0.2916,
      "step": 30
    },
    {
      "epoch": 0.0010506251219475587,
      "grad_norm": 1.1323988437652588,
      "learning_rate": 9.995494831023409e-05,
      "loss": 0.1692,
      "step": 35
    },
    {
      "epoch": 0.0012007144250829242,
      "grad_norm": 0.3086409866809845,
      "learning_rate": 9.981987442712633e-05,
      "loss": 0.0314,
      "step": 40
    },
    {
      "epoch": 0.00135080372821829,
      "grad_norm": 0.08165588974952698,
      "learning_rate": 9.959502176294383e-05,
      "loss": 0.0181,
      "step": 45
    },
    {
      "epoch": 0.0015008930313536555,
      "grad_norm": 0.1854889690876007,
      "learning_rate": 9.928079551738543e-05,
      "loss": 0.0083,
      "step": 50
    },
    {
      "epoch": 0.001650982334489021,
      "grad_norm": 0.049650534987449646,
      "learning_rate": 9.887776194738432e-05,
      "loss": 0.037,
      "step": 55
    },
    {
      "epoch": 0.0018010716376243865,
      "grad_norm": 0.35255470871925354,
      "learning_rate": 9.838664734667495e-05,
      "loss": 0.0096,
      "step": 60
    },
    {
      "epoch": 0.001951160940759752,
      "grad_norm": 0.16714519262313843,
      "learning_rate": 9.780833673696254e-05,
      "loss": 0.0045,
      "step": 65
    },
    {
      "epoch": 0.0021012502438951175,
      "grad_norm": 0.05677841603755951,
      "learning_rate": 9.714387227305422e-05,
      "loss": 0.0107,
      "step": 70
    },
    {
      "epoch": 0.002251339547030483,
      "grad_norm": 0.37986552715301514,
      "learning_rate": 9.639445136482548e-05,
      "loss": 0.0242,
      "step": 75
    },
    {
      "epoch": 0.0024014288501658485,
      "grad_norm": 0.16469906270503998,
      "learning_rate": 9.55614245194068e-05,
      "loss": 0.0026,
      "step": 80
    },
    {
      "epoch": 0.002551518153301214,
      "grad_norm": 0.03446728736162186,
      "learning_rate": 9.464629290747842e-05,
      "loss": 0.0125,
      "step": 85
    },
    {
      "epoch": 0.00270160745643658,
      "grad_norm": 0.08204316347837448,
      "learning_rate": 9.365070565805941e-05,
      "loss": 0.0101,
      "step": 90
    },
    {
      "epoch": 0.002851696759571945,
      "grad_norm": 0.133678138256073,
      "learning_rate": 9.257645688666556e-05,
      "loss": 0.0039,
      "step": 95
    },
    {
      "epoch": 0.003001786062707311,
      "grad_norm": 0.03044506348669529,
      "learning_rate": 9.142548246219212e-05,
      "loss": 0.0094,
      "step": 100
    },
    {
      "epoch": 0.003001786062707311,
      "eval_loss": 0.012762267142534256,
      "eval_runtime": 510.9883,
      "eval_samples_per_second": 27.451,
      "eval_steps_per_second": 13.726,
      "step": 100
    },
    {
      "epoch": 0.003151875365842676,
      "grad_norm": 0.28025349974632263,
      "learning_rate": 9.019985651834703e-05,
      "loss": 0.0103,
      "step": 105
    },
    {
      "epoch": 0.003301964668978042,
      "grad_norm": 0.2238554209470749,
      "learning_rate": 8.890178771592199e-05,
      "loss": 0.0382,
      "step": 110
    },
    {
      "epoch": 0.0034520539721134076,
      "grad_norm": 0.016901832073926926,
      "learning_rate": 8.753361526263621e-05,
      "loss": 0.0138,
      "step": 115
    },
    {
      "epoch": 0.003602143275248773,
      "grad_norm": 0.008931729942560196,
      "learning_rate": 8.609780469772623e-05,
      "loss": 0.0128,
      "step": 120
    },
    {
      "epoch": 0.0037522325783841386,
      "grad_norm": 0.07771596312522888,
      "learning_rate": 8.459694344887732e-05,
      "loss": 0.0017,
      "step": 125
    },
    {
      "epoch": 0.003902321881519504,
      "grad_norm": 0.09958741813898087,
      "learning_rate": 8.303373616950408e-05,
      "loss": 0.0028,
      "step": 130
    },
    {
      "epoch": 0.00405241118465487,
      "grad_norm": 0.3993448317050934,
      "learning_rate": 8.141099986478212e-05,
      "loss": 0.0142,
      "step": 135
    },
    {
      "epoch": 0.004202500487790235,
      "grad_norm": 0.0050088949501514435,
      "learning_rate": 7.973165881521434e-05,
      "loss": 0.0008,
      "step": 140
    },
    {
      "epoch": 0.004352589790925601,
      "grad_norm": 0.027677390724420547,
      "learning_rate": 7.799873930687978e-05,
      "loss": 0.0007,
      "step": 145
    },
    {
      "epoch": 0.004502679094060966,
      "grad_norm": 1.8557262420654297,
      "learning_rate": 7.621536417786159e-05,
      "loss": 0.0486,
      "step": 150
    },
    {
      "epoch": 0.004652768397196332,
      "grad_norm": 0.013031048700213432,
      "learning_rate": 7.438474719068173e-05,
      "loss": 0.0049,
      "step": 155
    },
    {
      "epoch": 0.004802857700331697,
      "grad_norm": 0.013981903903186321,
      "learning_rate": 7.251018724088367e-05,
      "loss": 0.0006,
      "step": 160
    },
    {
      "epoch": 0.004952947003467063,
      "grad_norm": 0.05604551360011101,
      "learning_rate": 7.059506241219965e-05,
      "loss": 0.0151,
      "step": 165
    },
    {
      "epoch": 0.005103036306602428,
      "grad_norm": 0.00818183645606041,
      "learning_rate": 6.864282388901544e-05,
      "loss": 0.0046,
      "step": 170
    },
    {
      "epoch": 0.005253125609737794,
      "grad_norm": 0.005792565643787384,
      "learning_rate": 6.665698973710288e-05,
      "loss": 0.0058,
      "step": 175
    },
    {
      "epoch": 0.00540321491287316,
      "grad_norm": 0.008401204831898212,
      "learning_rate": 6.464113856382752e-05,
      "loss": 0.0006,
      "step": 180
    },
    {
      "epoch": 0.005553304216008525,
      "grad_norm": 0.004655248951166868,
      "learning_rate": 6.259890306925627e-05,
      "loss": 0.0005,
      "step": 185
    },
    {
      "epoch": 0.00570339351914389,
      "grad_norm": 0.40482771396636963,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 0.0027,
      "step": 190
    },
    {
      "epoch": 0.005853482822279256,
      "grad_norm": 0.005078907124698162,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 0.0014,
      "step": 195
    },
    {
      "epoch": 0.006003572125414622,
      "grad_norm": 4.6471452713012695,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 0.078,
      "step": 200
    },
    {
      "epoch": 0.006003572125414622,
      "eval_loss": 0.006731819361448288,
      "eval_runtime": 510.7459,
      "eval_samples_per_second": 27.464,
      "eval_steps_per_second": 13.733,
      "step": 200
    },
    {
      "epoch": 0.0061536614285499875,
      "grad_norm": 0.18328024446964264,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 0.0073,
      "step": 205
    },
    {
      "epoch": 0.006303750731685352,
      "grad_norm": 0.008907951414585114,
      "learning_rate": 5.212206015980742e-05,
      "loss": 0.0005,
      "step": 210
    },
    {
      "epoch": 0.006453840034820718,
      "grad_norm": 0.18641109764575958,
      "learning_rate": 5e-05,
      "loss": 0.0078,
      "step": 215
    },
    {
      "epoch": 0.006603929337956084,
      "grad_norm": 0.05424876883625984,
      "learning_rate": 4.78779398401926e-05,
      "loss": 0.0013,
      "step": 220
    },
    {
      "epoch": 0.0067540186410914495,
      "grad_norm": 0.7451849579811096,
      "learning_rate": 4.575970377622456e-05,
      "loss": 0.0033,
      "step": 225
    },
    {
      "epoch": 0.006904107944226815,
      "grad_norm": 0.0506892055273056,
      "learning_rate": 4.364910901265606e-05,
      "loss": 0.0056,
      "step": 230
    },
    {
      "epoch": 0.00705419724736218,
      "grad_norm": 0.010004466399550438,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 0.0009,
      "step": 235
    },
    {
      "epoch": 0.007204286550497546,
      "grad_norm": 0.005493512377142906,
      "learning_rate": 3.94660365002137e-05,
      "loss": 0.0052,
      "step": 240
    },
    {
      "epoch": 0.0073543758536329116,
      "grad_norm": 0.014798315241932869,
      "learning_rate": 3.740109693074375e-05,
      "loss": 0.0011,
      "step": 245
    },
    {
      "epoch": 0.007504465156768277,
      "grad_norm": 0.019689688459038734,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 0.0081,
      "step": 250
    },
    {
      "epoch": 0.007654554459903643,
      "grad_norm": 0.0050315759144723415,
      "learning_rate": 3.334301026289712e-05,
      "loss": 0.0026,
      "step": 255
    },
    {
      "epoch": 0.007804643763039008,
      "grad_norm": 0.20544902980327606,
      "learning_rate": 3.135717611098458e-05,
      "loss": 0.0047,
      "step": 260
    },
    {
      "epoch": 0.007954733066174374,
      "grad_norm": 0.010924947448074818,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 0.0011,
      "step": 265
    },
    {
      "epoch": 0.00810482236930974,
      "grad_norm": 0.0026773347053676844,
      "learning_rate": 2.748981275911633e-05,
      "loss": 0.0024,
      "step": 270
    },
    {
      "epoch": 0.008254911672445105,
      "grad_norm": 0.010959619656205177,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 0.001,
      "step": 275
    },
    {
      "epoch": 0.00840500097558047,
      "grad_norm": 0.005525967571884394,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 0.0108,
      "step": 280
    },
    {
      "epoch": 0.008555090278715836,
      "grad_norm": 0.0066901505924761295,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 0.029,
      "step": 285
    },
    {
      "epoch": 0.008705179581851201,
      "grad_norm": 0.006530699320137501,
      "learning_rate": 2.026834118478567e-05,
      "loss": 0.0013,
      "step": 290
    },
    {
      "epoch": 0.008855268884986566,
      "grad_norm": 0.024501588195562363,
      "learning_rate": 1.858900013521788e-05,
      "loss": 0.0006,
      "step": 295
    },
    {
      "epoch": 0.009005358188121933,
      "grad_norm": 0.005288040731102228,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 0.0015,
      "step": 300
    },
    {
      "epoch": 0.009005358188121933,
      "eval_loss": 0.005631438456475735,
      "eval_runtime": 511.2808,
      "eval_samples_per_second": 27.435,
      "eval_steps_per_second": 13.718,
      "step": 300
    },
    {
      "epoch": 0.009155447491257298,
      "grad_norm": 0.0063221510499715805,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 0.005,
      "step": 305
    },
    {
      "epoch": 0.009305536794392664,
      "grad_norm": 0.006659193895757198,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 0.0024,
      "step": 310
    },
    {
      "epoch": 0.009455626097528029,
      "grad_norm": 0.01631927862763405,
      "learning_rate": 1.246638473736378e-05,
      "loss": 0.0124,
      "step": 315
    },
    {
      "epoch": 0.009605715400663394,
      "grad_norm": 0.007320760283619165,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 0.0018,
      "step": 320
    },
    {
      "epoch": 0.00975580470379876,
      "grad_norm": 0.007207963615655899,
      "learning_rate": 9.800143481652979e-06,
      "loss": 0.0005,
      "step": 325
    },
    {
      "epoch": 0.009905894006934125,
      "grad_norm": 0.01264453399926424,
      "learning_rate": 8.574517537807897e-06,
      "loss": 0.0178,
      "step": 330
    },
    {
      "epoch": 0.010055983310069492,
      "grad_norm": 0.010427780449390411,
      "learning_rate": 7.423543113334436e-06,
      "loss": 0.0009,
      "step": 335
    },
    {
      "epoch": 0.010206072613204857,
      "grad_norm": 0.019130609929561615,
      "learning_rate": 6.349294341940593e-06,
      "loss": 0.015,
      "step": 340
    },
    {
      "epoch": 0.010356161916340222,
      "grad_norm": 0.004735421389341354,
      "learning_rate": 5.353707092521582e-06,
      "loss": 0.0004,
      "step": 345
    },
    {
      "epoch": 0.010506251219475588,
      "grad_norm": 0.004065056797116995,
      "learning_rate": 4.43857548059321e-06,
      "loss": 0.032,
      "step": 350
    },
    {
      "epoch": 0.010656340522610953,
      "grad_norm": 0.01809353567659855,
      "learning_rate": 3.605548635174533e-06,
      "loss": 0.0105,
      "step": 355
    },
    {
      "epoch": 0.01080642982574632,
      "grad_norm": 0.005520292557775974,
      "learning_rate": 2.85612772694579e-06,
      "loss": 0.002,
      "step": 360
    },
    {
      "epoch": 0.010956519128881684,
      "grad_norm": 0.009921744465827942,
      "learning_rate": 2.191663263037458e-06,
      "loss": 0.0006,
      "step": 365
    },
    {
      "epoch": 0.01110660843201705,
      "grad_norm": 0.015676943585276604,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 0.0007,
      "step": 370
    },
    {
      "epoch": 0.011256697735152416,
      "grad_norm": 0.001278752344660461,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 0.0077,
      "step": 375
    },
    {
      "epoch": 0.01140678703828778,
      "grad_norm": 0.038098469376564026,
      "learning_rate": 7.192044826145771e-07,
      "loss": 0.0006,
      "step": 380
    },
    {
      "epoch": 0.011556876341423147,
      "grad_norm": 0.018751483410596848,
      "learning_rate": 4.049782370561583e-07,
      "loss": 0.0005,
      "step": 385
    },
    {
      "epoch": 0.011706965644558512,
      "grad_norm": 0.012710168026387691,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 0.0109,
      "step": 390
    },
    {
      "epoch": 0.011857054947693877,
      "grad_norm": 0.010042375884950161,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 0.0082,
      "step": 395
    },
    {
      "epoch": 0.012007144250829244,
      "grad_norm": 0.014652569778263569,
      "learning_rate": 0.0,
      "loss": 0.0016,
      "step": 400
    },
    {
      "epoch": 0.012007144250829244,
      "eval_loss": 0.005542390514165163,
      "eval_runtime": 511.1894,
      "eval_samples_per_second": 27.44,
      "eval_steps_per_second": 13.721,
      "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": 2.6365448417181696e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}