{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.048856453632171976,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00012214113408042993,
      "eval_loss": 11.5,
      "eval_runtime": 22.3392,
      "eval_samples_per_second": 154.348,
      "eval_steps_per_second": 77.174,
      "step": 1
    },
    {
      "epoch": 0.0006107056704021497,
      "grad_norm": 5.640897143166512e-05,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.0012214113408042994,
      "grad_norm": 7.911106513347477e-05,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 46.0,
      "step": 10
    },
    {
      "epoch": 0.001832117011206449,
      "grad_norm": 7.98892870079726e-05,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 15
    },
    {
      "epoch": 0.002442822681608599,
      "grad_norm": 9.459878492634743e-05,
      "learning_rate": 6.666666666666667e-05,
      "loss": 46.0,
      "step": 20
    },
    {
      "epoch": 0.0030535283520107485,
      "grad_norm": 7.22497861715965e-05,
      "learning_rate": 8.333333333333334e-05,
      "loss": 46.0,
      "step": 25
    },
    {
      "epoch": 0.003664234022412898,
      "grad_norm": 7.780244777677581e-05,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 30
    },
    {
      "epoch": 0.004274939692815048,
      "grad_norm": 8.012832404347137e-05,
      "learning_rate": 9.995494831023409e-05,
      "loss": 46.0,
      "step": 35
    },
    {
      "epoch": 0.004885645363217198,
      "grad_norm": 8.905514550860971e-05,
      "learning_rate": 9.981987442712633e-05,
      "loss": 46.0,
      "step": 40
    },
    {
      "epoch": 0.005496351033619347,
      "grad_norm": 8.750787674216554e-05,
      "learning_rate": 9.959502176294383e-05,
      "loss": 46.0,
      "step": 45
    },
    {
      "epoch": 0.006107056704021497,
      "grad_norm": 9.322659025201574e-05,
      "learning_rate": 9.928079551738543e-05,
      "loss": 46.0,
      "step": 50
    },
    {
      "epoch": 0.006717762374423646,
      "grad_norm": 7.013502181507647e-05,
      "learning_rate": 9.887776194738432e-05,
      "loss": 46.0,
      "step": 55
    },
    {
      "epoch": 0.007328468044825796,
      "grad_norm": 7.971763261593878e-05,
      "learning_rate": 9.838664734667495e-05,
      "loss": 46.0,
      "step": 60
    },
    {
      "epoch": 0.007939173715227945,
      "grad_norm": 8.508894825354218e-05,
      "learning_rate": 9.780833673696254e-05,
      "loss": 46.0,
      "step": 65
    },
    {
      "epoch": 0.008549879385630095,
      "grad_norm": 9.751072502695024e-05,
      "learning_rate": 9.714387227305422e-05,
      "loss": 46.0,
      "step": 70
    },
    {
      "epoch": 0.009160585056032245,
      "grad_norm": 0.00010631086479406804,
      "learning_rate": 9.639445136482548e-05,
      "loss": 46.0,
      "step": 75
    },
    {
      "epoch": 0.009771290726434395,
      "grad_norm": 0.00012184488878119737,
      "learning_rate": 9.55614245194068e-05,
      "loss": 46.0,
      "step": 80
    },
    {
      "epoch": 0.010381996396836544,
      "grad_norm": 9.975822467822582e-05,
      "learning_rate": 9.464629290747842e-05,
      "loss": 46.0,
      "step": 85
    },
    {
      "epoch": 0.010992702067238694,
      "grad_norm": 0.00011803951201727614,
      "learning_rate": 9.365070565805941e-05,
      "loss": 46.0,
      "step": 90
    },
    {
      "epoch": 0.011603407737640844,
      "grad_norm": 0.00013076045433990657,
      "learning_rate": 9.257645688666556e-05,
      "loss": 46.0,
      "step": 95
    },
    {
      "epoch": 0.012214113408042994,
      "grad_norm": 0.00011885855928994715,
      "learning_rate": 9.142548246219212e-05,
      "loss": 46.0,
      "step": 100
    },
    {
      "epoch": 0.012214113408042994,
      "eval_loss": 11.5,
      "eval_runtime": 22.3431,
      "eval_samples_per_second": 154.32,
      "eval_steps_per_second": 77.16,
      "step": 100
    },
    {
      "epoch": 0.012824819078445144,
      "grad_norm": 8.25794049887918e-05,
      "learning_rate": 9.019985651834703e-05,
      "loss": 46.0,
      "step": 105
    },
    {
      "epoch": 0.013435524748847292,
      "grad_norm": 0.0001379641325911507,
      "learning_rate": 8.890178771592199e-05,
      "loss": 46.0,
      "step": 110
    },
    {
      "epoch": 0.014046230419249442,
      "grad_norm": 0.00014777411706745625,
      "learning_rate": 8.753361526263621e-05,
      "loss": 46.0,
      "step": 115
    },
    {
      "epoch": 0.014656936089651592,
      "grad_norm": 0.00013291859067976475,
      "learning_rate": 8.609780469772623e-05,
      "loss": 46.0,
      "step": 120
    },
    {
      "epoch": 0.015267641760053742,
      "grad_norm": 0.0001347983634332195,
      "learning_rate": 8.459694344887732e-05,
      "loss": 46.0,
      "step": 125
    },
    {
      "epoch": 0.01587834743045589,
      "grad_norm": 0.000160489886184223,
      "learning_rate": 8.303373616950408e-05,
      "loss": 46.0,
      "step": 130
    },
    {
      "epoch": 0.01648905310085804,
      "grad_norm": 0.00014025198470335454,
      "learning_rate": 8.141099986478212e-05,
      "loss": 46.0,
      "step": 135
    },
    {
      "epoch": 0.01709975877126019,
      "grad_norm": 0.0001880452618934214,
      "learning_rate": 7.973165881521434e-05,
      "loss": 46.0,
      "step": 140
    },
    {
      "epoch": 0.01771046444166234,
      "grad_norm": 0.00018401446868665516,
      "learning_rate": 7.799873930687978e-05,
      "loss": 46.0,
      "step": 145
    },
    {
      "epoch": 0.01832117011206449,
      "grad_norm": 0.00023051275638863444,
      "learning_rate": 7.621536417786159e-05,
      "loss": 46.0,
      "step": 150
    },
    {
      "epoch": 0.01893187578246664,
      "grad_norm": 0.0001433873549103737,
      "learning_rate": 7.438474719068173e-05,
      "loss": 46.0,
      "step": 155
    },
    {
      "epoch": 0.01954258145286879,
      "grad_norm": 0.00019341360894031823,
      "learning_rate": 7.251018724088367e-05,
      "loss": 46.0,
      "step": 160
    },
    {
      "epoch": 0.02015328712327094,
      "grad_norm": 0.00021299674699548632,
      "learning_rate": 7.059506241219965e-05,
      "loss": 46.0,
      "step": 165
    },
    {
      "epoch": 0.020763992793673088,
      "grad_norm": 0.00024367104924749583,
      "learning_rate": 6.864282388901544e-05,
      "loss": 46.0,
      "step": 170
    },
    {
      "epoch": 0.021374698464075238,
      "grad_norm": 0.00023080628307070583,
      "learning_rate": 6.665698973710288e-05,
      "loss": 46.0,
      "step": 175
    },
    {
      "epoch": 0.021985404134477388,
      "grad_norm": 0.00023835583124309778,
      "learning_rate": 6.464113856382752e-05,
      "loss": 46.0,
      "step": 180
    },
    {
      "epoch": 0.022596109804879538,
      "grad_norm": 0.00025805115001276135,
      "learning_rate": 6.259890306925627e-05,
      "loss": 46.0,
      "step": 185
    },
    {
      "epoch": 0.023206815475281688,
      "grad_norm": 0.0002209192607551813,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 46.0,
      "step": 190
    },
    {
      "epoch": 0.023817521145683838,
      "grad_norm": 0.00032963225385174155,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 46.0,
      "step": 195
    },
    {
      "epoch": 0.024428226816085988,
      "grad_norm": 0.0002963414299301803,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 46.0,
      "step": 200
    },
    {
      "epoch": 0.024428226816085988,
      "eval_loss": 11.5,
      "eval_runtime": 22.3211,
      "eval_samples_per_second": 154.472,
      "eval_steps_per_second": 77.236,
      "step": 200
    },
    {
      "epoch": 0.025038932486488138,
      "grad_norm": 0.00021887882030569017,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 46.0,
      "step": 205
    },
    {
      "epoch": 0.025649638156890288,
      "grad_norm": 0.00023999107361305505,
      "learning_rate": 5.212206015980742e-05,
      "loss": 46.0,
      "step": 210
    },
    {
      "epoch": 0.026260343827292438,
      "grad_norm": 0.00023386770044453442,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 215
    },
    {
      "epoch": 0.026871049497694584,
      "grad_norm": 0.0002699745527934283,
      "learning_rate": 4.78779398401926e-05,
      "loss": 46.0,
      "step": 220
    },
    {
      "epoch": 0.027481755168096735,
      "grad_norm": 0.00032450436265207827,
      "learning_rate": 4.575970377622456e-05,
      "loss": 46.0,
      "step": 225
    },
    {
      "epoch": 0.028092460838498885,
      "grad_norm": 0.0002890110481530428,
      "learning_rate": 4.364910901265606e-05,
      "loss": 46.0,
      "step": 230
    },
    {
      "epoch": 0.028703166508901035,
      "grad_norm": 0.0002972777874674648,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 46.0,
      "step": 235
    },
    {
      "epoch": 0.029313872179303185,
      "grad_norm": 0.0003348960308358073,
      "learning_rate": 3.94660365002137e-05,
      "loss": 46.0,
      "step": 240
    },
    {
      "epoch": 0.029924577849705335,
      "grad_norm": 0.0003595406888052821,
      "learning_rate": 3.740109693074375e-05,
      "loss": 46.0,
      "step": 245
    },
    {
      "epoch": 0.030535283520107485,
      "grad_norm": 0.00034705991856753826,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 46.0,
      "step": 250
    },
    {
      "epoch": 0.031145989190509635,
      "grad_norm": 0.00019824641640298069,
      "learning_rate": 3.334301026289712e-05,
      "loss": 46.0,
      "step": 255
    },
    {
      "epoch": 0.03175669486091178,
      "grad_norm": 0.0003378826950211078,
      "learning_rate": 3.135717611098458e-05,
      "loss": 46.0,
      "step": 260
    },
    {
      "epoch": 0.032367400531313935,
      "grad_norm": 0.00028211367316544056,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 46.0,
      "step": 265
    },
    {
      "epoch": 0.03297810620171608,
      "grad_norm": 0.00028978593763895333,
      "learning_rate": 2.748981275911633e-05,
      "loss": 46.0,
      "step": 270
    },
    {
      "epoch": 0.033588811872118235,
      "grad_norm": 0.00031383702298626304,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 46.0,
      "step": 275
    },
    {
      "epoch": 0.03419951754252038,
      "grad_norm": 0.0003121411718893796,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 46.0,
      "step": 280
    },
    {
      "epoch": 0.034810223212922535,
      "grad_norm": 0.000346492714015767,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 46.0,
      "step": 285
    },
    {
      "epoch": 0.03542092888332468,
      "grad_norm": 0.00036268169060349464,
      "learning_rate": 2.026834118478567e-05,
      "loss": 46.0,
      "step": 290
    },
    {
      "epoch": 0.03603163455372683,
      "grad_norm": 0.00044341495959088206,
      "learning_rate": 1.858900013521788e-05,
      "loss": 46.0,
      "step": 295
    },
    {
      "epoch": 0.03664234022412898,
      "grad_norm": 0.0003739699022844434,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 46.0,
      "step": 300
    },
    {
      "epoch": 0.03664234022412898,
      "eval_loss": 11.5,
      "eval_runtime": 22.4161,
      "eval_samples_per_second": 153.818,
      "eval_steps_per_second": 76.909,
      "step": 300
    },
    {
      "epoch": 0.03725304589453113,
      "grad_norm": 0.0001925858814502135,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 46.0,
      "step": 305
    },
    {
      "epoch": 0.03786375156493328,
      "grad_norm": 0.00032552919583395123,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 46.0,
      "step": 310
    },
    {
      "epoch": 0.03847445723533543,
      "grad_norm": 0.00047274224925786257,
      "learning_rate": 1.246638473736378e-05,
      "loss": 46.0,
      "step": 315
    },
    {
      "epoch": 0.03908516290573758,
      "grad_norm": 0.00031744991429150105,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 46.0,
      "step": 320
    },
    {
      "epoch": 0.03969586857613973,
      "grad_norm": 0.0003673922037705779,
      "learning_rate": 9.800143481652979e-06,
      "loss": 46.0,
      "step": 325
    },
    {
      "epoch": 0.04030657424654188,
      "grad_norm": 0.00039610432577319443,
      "learning_rate": 8.574517537807897e-06,
      "loss": 46.0,
      "step": 330
    },
    {
      "epoch": 0.04091727991694403,
      "grad_norm": 0.0004075795004609972,
      "learning_rate": 7.423543113334436e-06,
      "loss": 46.0,
      "step": 335
    },
    {
      "epoch": 0.041527985587346175,
      "grad_norm": 0.00036381828249432147,
      "learning_rate": 6.349294341940593e-06,
      "loss": 46.0,
      "step": 340
    },
    {
      "epoch": 0.04213869125774833,
      "grad_norm": 0.0003588273248169571,
      "learning_rate": 5.353707092521582e-06,
      "loss": 46.0,
      "step": 345
    },
    {
      "epoch": 0.042749396928150475,
      "grad_norm": 0.00041598634561523795,
      "learning_rate": 4.43857548059321e-06,
      "loss": 46.0,
      "step": 350
    },
    {
      "epoch": 0.04336010259855263,
      "grad_norm": 0.00031224085250869393,
      "learning_rate": 3.605548635174533e-06,
      "loss": 46.0,
      "step": 355
    },
    {
      "epoch": 0.043970808268954775,
      "grad_norm": 0.00037712001358158886,
      "learning_rate": 2.85612772694579e-06,
      "loss": 46.0,
      "step": 360
    },
    {
      "epoch": 0.04458151393935693,
      "grad_norm": 0.0003957616863772273,
      "learning_rate": 2.191663263037458e-06,
      "loss": 46.0,
      "step": 365
    },
    {
      "epoch": 0.045192219609759075,
      "grad_norm": 0.00037767720641568303,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 46.0,
      "step": 370
    },
    {
      "epoch": 0.04580292528016123,
      "grad_norm": 0.00033137385617010295,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 46.0,
      "step": 375
    },
    {
      "epoch": 0.046413630950563375,
      "grad_norm": 0.00036192245897836983,
      "learning_rate": 7.192044826145771e-07,
      "loss": 46.0,
      "step": 380
    },
    {
      "epoch": 0.04702433662096553,
      "grad_norm": 0.0004093432507943362,
      "learning_rate": 4.049782370561583e-07,
      "loss": 46.0,
      "step": 385
    },
    {
      "epoch": 0.047635042291367675,
      "grad_norm": 0.000310163595713675,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 46.0,
      "step": 390
    },
    {
      "epoch": 0.04824574796176982,
      "grad_norm": 0.0002933391951955855,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 46.0,
      "step": 395
    },
    {
      "epoch": 0.048856453632171976,
      "grad_norm": 0.00036240380723029375,
      "learning_rate": 0.0,
      "loss": 46.0,
      "step": 400
    },
    {
      "epoch": 0.048856453632171976,
      "eval_loss": 11.5,
      "eval_runtime": 22.3644,
      "eval_samples_per_second": 154.174,
      "eval_steps_per_second": 77.087,
      "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": 16197300191232.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}