{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06337938902268982,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006337938902268982,
      "grad_norm": 19.0,
      "learning_rate": 3.4285714285714284e-05,
      "loss": 2.3561,
      "step": 5
    },
    {
      "epoch": 0.0012675877804537963,
      "grad_norm": 12.3125,
      "learning_rate": 7.714285714285713e-05,
      "loss": 2.0686,
      "step": 10
    },
    {
      "epoch": 0.0019013816706806947,
      "grad_norm": 6.78125,
      "learning_rate": 0.00011999999999999999,
      "loss": 1.412,
      "step": 15
    },
    {
      "epoch": 0.0025351755609075927,
      "grad_norm": 2.296875,
      "learning_rate": 0.00016285714285714284,
      "loss": 0.8966,
      "step": 20
    },
    {
      "epoch": 0.003168969451134491,
      "grad_norm": 1.8671875,
      "learning_rate": 0.0002057142857142857,
      "loss": 0.7659,
      "step": 25
    },
    {
      "epoch": 0.0038027633413613895,
      "grad_norm": 2.046875,
      "learning_rate": 0.00024857142857142857,
      "loss": 0.7462,
      "step": 30
    },
    {
      "epoch": 0.0044365572315882874,
      "grad_norm": 1.640625,
      "learning_rate": 0.0002914285714285714,
      "loss": 0.7137,
      "step": 35
    },
    {
      "epoch": 0.005070351121815185,
      "grad_norm": 1.4765625,
      "learning_rate": 0.0002999999985714883,
      "loss": 0.7019,
      "step": 40
    },
    {
      "epoch": 0.005704145012042084,
      "grad_norm": 2.234375,
      "learning_rate": 0.0002999999927681599,
      "loss": 0.682,
      "step": 45
    },
    {
      "epoch": 0.006337938902268982,
      "grad_norm": 1.8984375,
      "learning_rate": 0.00029999998250073286,
      "loss": 0.6785,
      "step": 50
    },
    {
      "epoch": 0.00697173279249588,
      "grad_norm": 1.84375,
      "learning_rate": 0.00029999996776920767,
      "loss": 0.6718,
      "step": 55
    },
    {
      "epoch": 0.007605526682722779,
      "grad_norm": 2.640625,
      "learning_rate": 0.0002999999485735849,
      "loss": 0.6704,
      "step": 60
    },
    {
      "epoch": 0.008239320572949677,
      "grad_norm": 1.4765625,
      "learning_rate": 0.0002999999249138654,
      "loss": 0.6495,
      "step": 65
    },
    {
      "epoch": 0.008873114463176575,
      "grad_norm": 1.6328125,
      "learning_rate": 0.00029999989679004995,
      "loss": 0.652,
      "step": 70
    },
    {
      "epoch": 0.009506908353403473,
      "grad_norm": 1.6171875,
      "learning_rate": 0.00029999986420213977,
      "loss": 0.6583,
      "step": 75
    },
    {
      "epoch": 0.01014070224363037,
      "grad_norm": 1.671875,
      "learning_rate": 0.0002999998271501361,
      "loss": 0.6612,
      "step": 80
    },
    {
      "epoch": 0.01077449613385727,
      "grad_norm": 1.625,
      "learning_rate": 0.0002999997856340405,
      "loss": 0.6436,
      "step": 85
    },
    {
      "epoch": 0.011408290024084168,
      "grad_norm": 1.390625,
      "learning_rate": 0.00029999973965385445,
      "loss": 0.6532,
      "step": 90
    },
    {
      "epoch": 0.012042083914311066,
      "grad_norm": 1.4609375,
      "learning_rate": 0.00029999968920958,
      "loss": 0.6426,
      "step": 95
    },
    {
      "epoch": 0.012675877804537964,
      "grad_norm": 1.921875,
      "learning_rate": 0.000299999634301219,
      "loss": 0.6507,
      "step": 100
    },
    {
      "epoch": 0.013309671694764862,
      "grad_norm": 1.265625,
      "learning_rate": 0.0002999995749287736,
      "loss": 0.6404,
      "step": 105
    },
    {
      "epoch": 0.01394346558499176,
      "grad_norm": 1.390625,
      "learning_rate": 0.00029999951109224623,
      "loss": 0.6312,
      "step": 110
    },
    {
      "epoch": 0.014577259475218658,
      "grad_norm": 1.453125,
      "learning_rate": 0.0002999994427916394,
      "loss": 0.6227,
      "step": 115
    },
    {
      "epoch": 0.015211053365445558,
      "grad_norm": 1.6015625,
      "learning_rate": 0.0002999993700269559,
      "loss": 0.6377,
      "step": 120
    },
    {
      "epoch": 0.015844847255672454,
      "grad_norm": 1.4296875,
      "learning_rate": 0.0002999992927981985,
      "loss": 0.6294,
      "step": 125
    },
    {
      "epoch": 0.016478641145899354,
      "grad_norm": 1.484375,
      "learning_rate": 0.0002999992111053703,
      "loss": 0.6333,
      "step": 130
    },
    {
      "epoch": 0.01711243503612625,
      "grad_norm": 1.484375,
      "learning_rate": 0.0002999991249484746,
      "loss": 0.6157,
      "step": 135
    },
    {
      "epoch": 0.01774622892635315,
      "grad_norm": 2.203125,
      "learning_rate": 0.0002999990343275147,
      "loss": 0.6145,
      "step": 140
    },
    {
      "epoch": 0.01838002281658005,
      "grad_norm": 1.2734375,
      "learning_rate": 0.00029999893924249427,
      "loss": 0.6091,
      "step": 145
    },
    {
      "epoch": 0.019013816706806946,
      "grad_norm": 1.296875,
      "learning_rate": 0.00029999883969341717,
      "loss": 0.6149,
      "step": 150
    },
    {
      "epoch": 0.019647610597033845,
      "grad_norm": 1.6328125,
      "learning_rate": 0.0002999987356802872,
      "loss": 0.6171,
      "step": 155
    },
    {
      "epoch": 0.02028140448726074,
      "grad_norm": 1.3984375,
      "learning_rate": 0.00029999862720310857,
      "loss": 0.6021,
      "step": 160
    },
    {
      "epoch": 0.02091519837748764,
      "grad_norm": 1.546875,
      "learning_rate": 0.0002999985142618855,
      "loss": 0.6303,
      "step": 165
    },
    {
      "epoch": 0.02154899226771454,
      "grad_norm": 1.6953125,
      "learning_rate": 0.0002999983968566226,
      "loss": 0.6139,
      "step": 170
    },
    {
      "epoch": 0.022182786157941437,
      "grad_norm": 1.9765625,
      "learning_rate": 0.0002999982749873244,
      "loss": 0.6173,
      "step": 175
    },
    {
      "epoch": 0.022816580048168337,
      "grad_norm": 1.3515625,
      "learning_rate": 0.00029999814865399585,
      "loss": 0.6074,
      "step": 180
    },
    {
      "epoch": 0.023450373938395233,
      "grad_norm": 1.3828125,
      "learning_rate": 0.00029999801785664194,
      "loss": 0.6046,
      "step": 185
    },
    {
      "epoch": 0.024084167828622133,
      "grad_norm": 1.28125,
      "learning_rate": 0.00029999788259526774,
      "loss": 0.5923,
      "step": 190
    },
    {
      "epoch": 0.02471796171884903,
      "grad_norm": 1.265625,
      "learning_rate": 0.00029999774286987876,
      "loss": 0.6149,
      "step": 195
    },
    {
      "epoch": 0.02535175560907593,
      "grad_norm": 1.8984375,
      "learning_rate": 0.0002999975986804805,
      "loss": 0.5969,
      "step": 200
    },
    {
      "epoch": 0.02598554949930283,
      "grad_norm": 1.4609375,
      "learning_rate": 0.0002999974500270787,
      "loss": 0.6083,
      "step": 205
    },
    {
      "epoch": 0.026619343389529725,
      "grad_norm": 1.4609375,
      "learning_rate": 0.00029999729690967917,
      "loss": 0.6029,
      "step": 210
    },
    {
      "epoch": 0.027253137279756624,
      "grad_norm": 1.515625,
      "learning_rate": 0.0002999971393282881,
      "loss": 0.6064,
      "step": 215
    },
    {
      "epoch": 0.02788693116998352,
      "grad_norm": 1.2734375,
      "learning_rate": 0.0002999969772829116,
      "loss": 0.6102,
      "step": 220
    },
    {
      "epoch": 0.02852072506021042,
      "grad_norm": 1.3984375,
      "learning_rate": 0.00029999681077355633,
      "loss": 0.5899,
      "step": 225
    },
    {
      "epoch": 0.029154518950437316,
      "grad_norm": 1.4765625,
      "learning_rate": 0.00029999663980022866,
      "loss": 0.595,
      "step": 230
    },
    {
      "epoch": 0.029788312840664216,
      "grad_norm": 1.5078125,
      "learning_rate": 0.00029999646436293555,
      "loss": 0.5848,
      "step": 235
    },
    {
      "epoch": 0.030422106730891116,
      "grad_norm": 1.46875,
      "learning_rate": 0.00029999628446168383,
      "loss": 0.6003,
      "step": 240
    },
    {
      "epoch": 0.031055900621118012,
      "grad_norm": 1.34375,
      "learning_rate": 0.0002999961000964807,
      "loss": 0.5875,
      "step": 245
    },
    {
      "epoch": 0.03168969451134491,
      "grad_norm": 1.5078125,
      "learning_rate": 0.00029999591126733346,
      "loss": 0.5769,
      "step": 250
    },
    {
      "epoch": 0.03232348840157181,
      "grad_norm": 1.328125,
      "learning_rate": 0.00029999571797424966,
      "loss": 0.5928,
      "step": 255
    },
    {
      "epoch": 0.03295728229179871,
      "grad_norm": 1.578125,
      "learning_rate": 0.0002999955202172369,
      "loss": 0.5767,
      "step": 260
    },
    {
      "epoch": 0.03359107618202561,
      "grad_norm": 1.515625,
      "learning_rate": 0.000299995317996303,
      "loss": 0.5763,
      "step": 265
    },
    {
      "epoch": 0.0342248700722525,
      "grad_norm": 1.5078125,
      "learning_rate": 0.0002999951113114561,
      "loss": 0.5852,
      "step": 270
    },
    {
      "epoch": 0.0348586639624794,
      "grad_norm": 1.8125,
      "learning_rate": 0.0002999949001627043,
      "loss": 0.5965,
      "step": 275
    },
    {
      "epoch": 0.0354924578527063,
      "grad_norm": 1.5703125,
      "learning_rate": 0.00029999468455005606,
      "loss": 0.5828,
      "step": 280
    },
    {
      "epoch": 0.0361262517429332,
      "grad_norm": 1.5,
      "learning_rate": 0.00029999446447351985,
      "loss": 0.5918,
      "step": 285
    },
    {
      "epoch": 0.0367600456331601,
      "grad_norm": 1.3828125,
      "learning_rate": 0.00029999423993310446,
      "loss": 0.5853,
      "step": 290
    },
    {
      "epoch": 0.03739383952338699,
      "grad_norm": 1.703125,
      "learning_rate": 0.00029999401092881876,
      "loss": 0.5706,
      "step": 295
    },
    {
      "epoch": 0.03802763341361389,
      "grad_norm": 1.5859375,
      "learning_rate": 0.0002999937774606719,
      "loss": 0.571,
      "step": 300
    },
    {
      "epoch": 0.03866142730384079,
      "grad_norm": 1.578125,
      "learning_rate": 0.00029999353952867307,
      "loss": 0.5731,
      "step": 305
    },
    {
      "epoch": 0.03929522119406769,
      "grad_norm": 1.578125,
      "learning_rate": 0.0002999932971328317,
      "loss": 0.5806,
      "step": 310
    },
    {
      "epoch": 0.03992901508429459,
      "grad_norm": 1.2734375,
      "learning_rate": 0.0002999930502731575,
      "loss": 0.5751,
      "step": 315
    },
    {
      "epoch": 0.04056280897452148,
      "grad_norm": 1.265625,
      "learning_rate": 0.0002999927989496603,
      "loss": 0.5777,
      "step": 320
    },
    {
      "epoch": 0.04119660286474838,
      "grad_norm": 1.5390625,
      "learning_rate": 0.0002999925431623499,
      "loss": 0.5856,
      "step": 325
    },
    {
      "epoch": 0.04183039675497528,
      "grad_norm": 1.46875,
      "learning_rate": 0.00029999228291123655,
      "loss": 0.5754,
      "step": 330
    },
    {
      "epoch": 0.04246419064520218,
      "grad_norm": 1.4921875,
      "learning_rate": 0.0002999920181963306,
      "loss": 0.5684,
      "step": 335
    },
    {
      "epoch": 0.04309798453542908,
      "grad_norm": 1.5703125,
      "learning_rate": 0.0002999917490176425,
      "loss": 0.5665,
      "step": 340
    },
    {
      "epoch": 0.043731778425655975,
      "grad_norm": 1.328125,
      "learning_rate": 0.00029999147537518295,
      "loss": 0.5713,
      "step": 345
    },
    {
      "epoch": 0.044365572315882874,
      "grad_norm": 1.6875,
      "learning_rate": 0.0002999911972689628,
      "loss": 0.5675,
      "step": 350
    },
    {
      "epoch": 0.044999366206109774,
      "grad_norm": 1.59375,
      "learning_rate": 0.0002999909146989931,
      "loss": 0.575,
      "step": 355
    },
    {
      "epoch": 0.045633160096336674,
      "grad_norm": 1.25,
      "learning_rate": 0.0002999906276652851,
      "loss": 0.5721,
      "step": 360
    },
    {
      "epoch": 0.046266953986563567,
      "grad_norm": 1.8828125,
      "learning_rate": 0.00029999033616785015,
      "loss": 0.5653,
      "step": 365
    },
    {
      "epoch": 0.046900747876790466,
      "grad_norm": 1.8125,
      "learning_rate": 0.0002999900402066998,
      "loss": 0.5543,
      "step": 370
    },
    {
      "epoch": 0.047534541767017366,
      "grad_norm": 1.53125,
      "learning_rate": 0.0002999897397818458,
      "loss": 0.5643,
      "step": 375
    },
    {
      "epoch": 0.048168335657244266,
      "grad_norm": 1.78125,
      "learning_rate": 0.0002999894348933001,
      "loss": 0.574,
      "step": 380
    },
    {
      "epoch": 0.048802129547471165,
      "grad_norm": 1.46875,
      "learning_rate": 0.0002999891255410748,
      "loss": 0.5581,
      "step": 385
    },
    {
      "epoch": 0.04943592343769806,
      "grad_norm": 1.4609375,
      "learning_rate": 0.0002999888117251821,
      "loss": 0.558,
      "step": 390
    },
    {
      "epoch": 0.05006971732792496,
      "grad_norm": 1.3671875,
      "learning_rate": 0.00029998849344563456,
      "loss": 0.5614,
      "step": 395
    },
    {
      "epoch": 0.05070351121815186,
      "grad_norm": 1.4609375,
      "learning_rate": 0.00029998817070244475,
      "loss": 0.5692,
      "step": 400
    },
    {
      "epoch": 0.05133730510837876,
      "grad_norm": 1.359375,
      "learning_rate": 0.00029998784349562544,
      "loss": 0.5552,
      "step": 405
    },
    {
      "epoch": 0.05197109899860566,
      "grad_norm": 1.59375,
      "learning_rate": 0.0002999875118251897,
      "loss": 0.5549,
      "step": 410
    },
    {
      "epoch": 0.05260489288883255,
      "grad_norm": 1.484375,
      "learning_rate": 0.00029998717569115063,
      "loss": 0.5574,
      "step": 415
    },
    {
      "epoch": 0.05323868677905945,
      "grad_norm": 1.4765625,
      "learning_rate": 0.0002999868350935216,
      "loss": 0.5587,
      "step": 420
    },
    {
      "epoch": 0.05387248066928635,
      "grad_norm": 1.9765625,
      "learning_rate": 0.00029998649003231613,
      "loss": 0.5611,
      "step": 425
    },
    {
      "epoch": 0.05450627455951325,
      "grad_norm": 1.21875,
      "learning_rate": 0.0002999861405075479,
      "loss": 0.5567,
      "step": 430
    },
    {
      "epoch": 0.05514006844974014,
      "grad_norm": 1.15625,
      "learning_rate": 0.0002999857865192308,
      "loss": 0.5525,
      "step": 435
    },
    {
      "epoch": 0.05577386233996704,
      "grad_norm": 1.8046875,
      "learning_rate": 0.00029998542806737875,
      "loss": 0.5595,
      "step": 440
    },
    {
      "epoch": 0.05640765623019394,
      "grad_norm": 1.4609375,
      "learning_rate": 0.00029998506515200614,
      "loss": 0.5534,
      "step": 445
    },
    {
      "epoch": 0.05704145012042084,
      "grad_norm": 1.453125,
      "learning_rate": 0.0002999846977731273,
      "loss": 0.548,
      "step": 450
    },
    {
      "epoch": 0.05767524401064774,
      "grad_norm": 1.546875,
      "learning_rate": 0.00029998432593075677,
      "loss": 0.5534,
      "step": 455
    },
    {
      "epoch": 0.05830903790087463,
      "grad_norm": 1.390625,
      "learning_rate": 0.00029998394962490945,
      "loss": 0.5593,
      "step": 460
    },
    {
      "epoch": 0.05894283179110153,
      "grad_norm": 1.3359375,
      "learning_rate": 0.0002999835688556001,
      "loss": 0.5591,
      "step": 465
    },
    {
      "epoch": 0.05957662568132843,
      "grad_norm": 1.4609375,
      "learning_rate": 0.0002999831836228439,
      "loss": 0.5674,
      "step": 470
    },
    {
      "epoch": 0.06021041957155533,
      "grad_norm": 1.2734375,
      "learning_rate": 0.00029998279392665615,
      "loss": 0.534,
      "step": 475
    },
    {
      "epoch": 0.06084421346178223,
      "grad_norm": 1.453125,
      "learning_rate": 0.0002999823997670523,
      "loss": 0.5403,
      "step": 480
    },
    {
      "epoch": 0.061478007352009124,
      "grad_norm": 1.3515625,
      "learning_rate": 0.00029998200114404803,
      "loss": 0.542,
      "step": 485
    },
    {
      "epoch": 0.062111801242236024,
      "grad_norm": 1.5,
      "learning_rate": 0.00029998159805765906,
      "loss": 0.5432,
      "step": 490
    },
    {
      "epoch": 0.06274559513246292,
      "grad_norm": 1.4453125,
      "learning_rate": 0.00029998119050790145,
      "loss": 0.5462,
      "step": 495
    },
    {
      "epoch": 0.06337938902268982,
      "grad_norm": 1.4765625,
      "learning_rate": 0.00029998077849479135,
      "loss": 0.5406,
      "step": 500
    },
    {
      "epoch": 0.06337938902268982,
      "eval_loss": 0.5448389053344727,
      "eval_runtime": 2.5375,
      "eval_samples_per_second": 78.818,
      "eval_steps_per_second": 78.818,
      "step": 500
    }
  ],
  "logging_steps": 5,
  "max_steps": 78890,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2537940672512e+16,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": null
}