{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07399459839431721,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014798919678863443,
      "grad_norm": 3.318990468978882,
      "learning_rate": 3.6e-05,
      "loss": 0.8225,
      "step": 10
    },
    {
      "epoch": 0.0029597839357726886,
      "grad_norm": 1.644492745399475,
      "learning_rate": 7.6e-05,
      "loss": 0.2495,
      "step": 20
    },
    {
      "epoch": 0.004439675903659033,
      "grad_norm": 2.137453556060791,
      "learning_rate": 9.998250366089848e-05,
      "loss": 0.2076,
      "step": 30
    },
    {
      "epoch": 0.005919567871545377,
      "grad_norm": 1.6013213396072388,
      "learning_rate": 9.97858104436822e-05,
      "loss": 0.1753,
      "step": 40
    },
    {
      "epoch": 0.007399459839431722,
      "grad_norm": 2.4884767532348633,
      "learning_rate": 9.937141654477528e-05,
      "loss": 0.1661,
      "step": 50
    },
    {
      "epoch": 0.008879351807318065,
      "grad_norm": 1.5080770254135132,
      "learning_rate": 9.87411340032603e-05,
      "loss": 0.1414,
      "step": 60
    },
    {
      "epoch": 0.01035924377520441,
      "grad_norm": 1.3873870372772217,
      "learning_rate": 9.789771888432375e-05,
      "loss": 0.1409,
      "step": 70
    },
    {
      "epoch": 0.011839135743090754,
      "grad_norm": 1.1532950401306152,
      "learning_rate": 9.684485922768422e-05,
      "loss": 0.1169,
      "step": 80
    },
    {
      "epoch": 0.013319027710977099,
      "grad_norm": 1.088762640953064,
      "learning_rate": 9.558715892073323e-05,
      "loss": 0.1043,
      "step": 90
    },
    {
      "epoch": 0.014798919678863444,
      "grad_norm": 2.323737621307373,
      "learning_rate": 9.413011756690685e-05,
      "loss": 0.116,
      "step": 100
    },
    {
      "epoch": 0.016278811646749786,
      "grad_norm": 1.2114522457122803,
      "learning_rate": 9.248010643731935e-05,
      "loss": 0.1146,
      "step": 110
    },
    {
      "epoch": 0.01775870361463613,
      "grad_norm": 1.2140398025512695,
      "learning_rate": 9.064434061081562e-05,
      "loss": 0.1248,
      "step": 120
    },
    {
      "epoch": 0.019238595582522475,
      "grad_norm": 1.2787519693374634,
      "learning_rate": 8.863084742426719e-05,
      "loss": 0.0848,
      "step": 130
    },
    {
      "epoch": 0.02071848755040882,
      "grad_norm": 0.8212881684303284,
      "learning_rate": 8.644843137107059e-05,
      "loss": 0.0965,
      "step": 140
    },
    {
      "epoch": 0.022198379518295164,
      "grad_norm": 1.0979036092758179,
      "learning_rate": 8.410663560133784e-05,
      "loss": 0.0922,
      "step": 150
    },
    {
      "epoch": 0.02367827148618151,
      "grad_norm": 0.9978598356246948,
      "learning_rate": 8.161570019212921e-05,
      "loss": 0.0916,
      "step": 160
    },
    {
      "epoch": 0.025158163454067854,
      "grad_norm": 0.8716151714324951,
      "learning_rate": 7.898651737020166e-05,
      "loss": 0.067,
      "step": 170
    },
    {
      "epoch": 0.026638055421954198,
      "grad_norm": 1.0746519565582275,
      "learning_rate": 7.623058388307269e-05,
      "loss": 0.0802,
      "step": 180
    },
    {
      "epoch": 0.028117947389840543,
      "grad_norm": 1.3861006498336792,
      "learning_rate": 7.335995072666848e-05,
      "loss": 0.0907,
      "step": 190
    },
    {
      "epoch": 0.029597839357726887,
      "grad_norm": 1.093328833580017,
      "learning_rate": 7.038717044938519e-05,
      "loss": 0.0657,
      "step": 200
    },
    {
      "epoch": 0.03107773132561323,
      "grad_norm": 0.8141024708747864,
      "learning_rate": 6.732524226298841e-05,
      "loss": 0.0613,
      "step": 210
    },
    {
      "epoch": 0.03255762329349957,
      "grad_norm": 0.9468361139297485,
      "learning_rate": 6.418755520036775e-05,
      "loss": 0.0829,
      "step": 220
    },
    {
      "epoch": 0.03403751526138592,
      "grad_norm": 0.6965128183364868,
      "learning_rate": 6.0987829568702656e-05,
      "loss": 0.0796,
      "step": 230
    },
    {
      "epoch": 0.03551740722927226,
      "grad_norm": 1.127314567565918,
      "learning_rate": 5.7740056954050084e-05,
      "loss": 0.0798,
      "step": 240
    },
    {
      "epoch": 0.036997299197158606,
      "grad_norm": 1.4155848026275635,
      "learning_rate": 5.445843903969854e-05,
      "loss": 0.06,
      "step": 250
    },
    {
      "epoch": 0.03847719116504495,
      "grad_norm": 0.7054800987243652,
      "learning_rate": 5.1157325505820694e-05,
      "loss": 0.052,
      "step": 260
    },
    {
      "epoch": 0.039957083132931295,
      "grad_norm": 0.7660062909126282,
      "learning_rate": 4.785115128197298e-05,
      "loss": 0.059,
      "step": 270
    },
    {
      "epoch": 0.04143697510081764,
      "grad_norm": 0.7886701822280884,
      "learning_rate": 4.4554373426821374e-05,
      "loss": 0.0536,
      "step": 280
    },
    {
      "epoch": 0.042916867068703984,
      "grad_norm": 1.4434950351715088,
      "learning_rate": 4.1281407911102425e-05,
      "loss": 0.0628,
      "step": 290
    },
    {
      "epoch": 0.04439675903659033,
      "grad_norm": 0.9001641869544983,
      "learning_rate": 3.8046566580251e-05,
      "loss": 0.0536,
      "step": 300
    },
    {
      "epoch": 0.04587665100447667,
      "grad_norm": 0.7539929151535034,
      "learning_rate": 3.4863994572341843e-05,
      "loss": 0.0673,
      "step": 310
    },
    {
      "epoch": 0.04735654297236302,
      "grad_norm": 0.6108214855194092,
      "learning_rate": 3.1747608464999725e-05,
      "loss": 0.0358,
      "step": 320
    },
    {
      "epoch": 0.04883643494024936,
      "grad_norm": 0.4837505519390106,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 0.041,
      "step": 330
    },
    {
      "epoch": 0.05031632690813571,
      "grad_norm": 0.8078829050064087,
      "learning_rate": 2.5767553603881767e-05,
      "loss": 0.0518,
      "step": 340
    },
    {
      "epoch": 0.05179621887602205,
      "grad_norm": 1.5803087949752808,
      "learning_rate": 2.29300341084631e-05,
      "loss": 0.0486,
      "step": 350
    },
    {
      "epoch": 0.053276110843908396,
      "grad_norm": 0.3863455355167389,
      "learning_rate": 2.0210884686272368e-05,
      "loss": 0.039,
      "step": 360
    },
    {
      "epoch": 0.05475600281179474,
      "grad_norm": 0.7085531949996948,
      "learning_rate": 1.7621995485879062e-05,
      "loss": 0.0389,
      "step": 370
    },
    {
      "epoch": 0.056235894779681085,
      "grad_norm": 0.7141103744506836,
      "learning_rate": 1.517468706104589e-05,
      "loss": 0.0425,
      "step": 380
    },
    {
      "epoch": 0.05771578674756743,
      "grad_norm": 0.6287118196487427,
      "learning_rate": 1.2879660868827508e-05,
      "loss": 0.0457,
      "step": 390
    },
    {
      "epoch": 0.059195678715453774,
      "grad_norm": 0.821704089641571,
      "learning_rate": 1.0746952474821614e-05,
      "loss": 0.0436,
      "step": 400
    },
    {
      "epoch": 0.06067557068334012,
      "grad_norm": 0.6595329642295837,
      "learning_rate": 8.785887670194138e-06,
      "loss": 0.0436,
      "step": 410
    },
    {
      "epoch": 0.06215546265122646,
      "grad_norm": 0.5961970090866089,
      "learning_rate": 7.005041692367154e-06,
      "loss": 0.0309,
      "step": 420
    },
    {
      "epoch": 0.06363535461911281,
      "grad_norm": 0.578628659248352,
      "learning_rate": 5.412201727687644e-06,
      "loss": 0.0402,
      "step": 430
    },
    {
      "epoch": 0.06511524658699915,
      "grad_norm": 0.48573747277259827,
      "learning_rate": 4.01433286004283e-06,
      "loss": 0.0338,
      "step": 440
    },
    {
      "epoch": 0.0665951385548855,
      "grad_norm": 0.54139244556427,
      "learning_rate": 2.817547614320615e-06,
      "loss": 0.0269,
      "step": 450
    },
    {
      "epoch": 0.06807503052277183,
      "grad_norm": 0.6104289293289185,
      "learning_rate": 1.8270792278934302e-06,
      "loss": 0.0328,
      "step": 460
    },
    {
      "epoch": 0.06955492249065819,
      "grad_norm": 0.40234851837158203,
      "learning_rate": 1.0472587670027678e-06,
      "loss": 0.0341,
      "step": 470
    },
    {
      "epoch": 0.07103481445854452,
      "grad_norm": 0.3963511288166046,
      "learning_rate": 4.814961881085045e-07,
      "loss": 0.0347,
      "step": 480
    },
    {
      "epoch": 0.07251470642643087,
      "grad_norm": 0.36650583148002625,
      "learning_rate": 1.3226542701689215e-07,
      "loss": 0.0401,
      "step": 490
    },
    {
      "epoch": 0.07399459839431721,
      "grad_norm": 0.48519328236579895,
      "learning_rate": 1.0935809887702154e-09,
      "loss": 0.0292,
      "step": 500
    },
    {
      "epoch": 0.07399459839431721,
      "step": 500,
      "total_flos": 0.0,
      "train_loss": 0.09187581622600556,
      "train_runtime": 831.2312,
      "train_samples_per_second": 4.812,
      "train_steps_per_second": 0.602
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}