{
  "best_global_step": 5780,
  "best_metric": 3.4774351119995117,
  "best_model_checkpoint": "sindhibert_session6/checkpoint-5780",
  "epoch": 2.0,
  "eval_steps": 2890,
  "global_step": 5780,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03460207612456748,
      "grad_norm": 5.271186828613281,
      "learning_rate": 8.583815028901734e-07,
      "loss": 14.7112890625,
      "step": 100
    },
    {
      "epoch": 0.06920415224913495,
      "grad_norm": 5.328507900238037,
      "learning_rate": 1.7254335260115608e-06,
      "loss": 14.65601806640625,
      "step": 200
    },
    {
      "epoch": 0.10380622837370242,
      "grad_norm": 5.2988433837890625,
      "learning_rate": 2.592485549132948e-06,
      "loss": 14.6437841796875,
      "step": 300
    },
    {
      "epoch": 0.1384083044982699,
      "grad_norm": 5.144472122192383,
      "learning_rate": 2.9992958916410005e-06,
      "loss": 14.644112548828126,
      "step": 400
    },
    {
      "epoch": 0.17301038062283736,
      "grad_norm": 5.255625247955322,
      "learning_rate": 2.994135629312096e-06,
      "loss": 14.592845458984375,
      "step": 500
    },
    {
      "epoch": 0.20761245674740483,
      "grad_norm": 5.365286827087402,
      "learning_rate": 2.9839827352831524e-06,
      "loss": 14.59123779296875,
      "step": 600
    },
    {
      "epoch": 0.2422145328719723,
      "grad_norm": 5.114892959594727,
      "learning_rate": 2.96887113529664e-06,
      "loss": 14.588660888671875,
      "step": 700
    },
    {
      "epoch": 0.2768166089965398,
      "grad_norm": 5.162683486938477,
      "learning_rate": 2.948851324536296e-06,
      "loss": 14.5647998046875,
      "step": 800
    },
    {
      "epoch": 0.31141868512110726,
      "grad_norm": 5.2245635986328125,
      "learning_rate": 2.9239901988982294e-06,
      "loss": 14.566002197265625,
      "step": 900
    },
    {
      "epoch": 0.3460207612456747,
      "grad_norm": 5.22702169418335,
      "learning_rate": 2.8943708314592917e-06,
      "loss": 14.56361328125,
      "step": 1000
    },
    {
      "epoch": 0.3806228373702422,
      "grad_norm": 5.353369235992432,
      "learning_rate": 2.8600921948896393e-06,
      "loss": 14.56337890625,
      "step": 1100
    },
    {
      "epoch": 0.41522491349480967,
      "grad_norm": 5.189014911651611,
      "learning_rate": 2.821268830737051e-06,
      "loss": 14.566427001953125,
      "step": 1200
    },
    {
      "epoch": 0.44982698961937717,
      "grad_norm": 5.108746528625488,
      "learning_rate": 2.7780304666880683e-06,
      "loss": 14.5394287109375,
      "step": 1300
    },
    {
      "epoch": 0.4844290657439446,
      "grad_norm": 5.1513895988464355,
      "learning_rate": 2.7305215830848867e-06,
      "loss": 14.531617431640624,
      "step": 1400
    },
    {
      "epoch": 0.5190311418685121,
      "grad_norm": 5.2011942863464355,
      "learning_rate": 2.678900930146467e-06,
      "loss": 14.5282666015625,
      "step": 1500
    },
    {
      "epoch": 0.5536332179930796,
      "grad_norm": 5.219590663909912,
      "learning_rate": 2.6233409975070707e-06,
      "loss": 14.489625244140624,
      "step": 1600
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 5.411579132080078,
      "learning_rate": 2.5640274378447445e-06,
      "loss": 14.49999755859375,
      "step": 1700
    },
    {
      "epoch": 0.6228373702422145,
      "grad_norm": 5.120180606842041,
      "learning_rate": 2.5011584465256946e-06,
      "loss": 14.515745849609376,
      "step": 1800
    },
    {
      "epoch": 0.657439446366782,
      "grad_norm": 5.3347883224487305,
      "learning_rate": 2.434944099337454e-06,
      "loss": 14.52021728515625,
      "step": 1900
    },
    {
      "epoch": 0.6920415224913494,
      "grad_norm": 4.978041172027588,
      "learning_rate": 2.365605650523803e-06,
      "loss": 14.50703857421875,
      "step": 2000
    },
    {
      "epoch": 0.726643598615917,
      "grad_norm": 5.3864898681640625,
      "learning_rate": 2.293374793467048e-06,
      "loss": 14.493427734375,
      "step": 2100
    },
    {
      "epoch": 0.7612456747404844,
      "grad_norm": 5.149505138397217,
      "learning_rate": 2.2184928864880712e-06,
      "loss": 14.453104248046875,
      "step": 2200
    },
    {
      "epoch": 0.7958477508650519,
      "grad_norm": 5.451559066772461,
      "learning_rate": 2.1412101463511406e-06,
      "loss": 14.48880126953125,
      "step": 2300
    },
    {
      "epoch": 0.8304498269896193,
      "grad_norm": 5.231166839599609,
      "learning_rate": 2.0617848121683582e-06,
      "loss": 14.46824951171875,
      "step": 2400
    },
    {
      "epoch": 0.8650519031141869,
      "grad_norm": 5.132116794586182,
      "learning_rate": 1.9804822824975567e-06,
      "loss": 14.45693603515625,
      "step": 2500
    },
    {
      "epoch": 0.8996539792387543,
      "grad_norm": 5.454078197479248,
      "learning_rate": 1.8975742285170185e-06,
      "loss": 14.468741455078124,
      "step": 2600
    },
    {
      "epoch": 0.9342560553633218,
      "grad_norm": 5.184955596923828,
      "learning_rate": 1.8133376862403233e-06,
      "loss": 14.482393798828125,
      "step": 2700
    },
    {
      "epoch": 0.9688581314878892,
      "grad_norm": 5.030216693878174,
      "learning_rate": 1.7280541308046812e-06,
      "loss": 14.4536962890625,
      "step": 2800
    },
    {
      "epoch": 1.0,
      "eval_loss": 3.484435558319092,
      "eval_runtime": 11.6834,
      "eval_samples_per_second": 639.538,
      "eval_steps_per_second": 10.014,
      "step": 2890
    },
    {
      "epoch": 1.0034602076124568,
      "grad_norm": 5.57059383392334,
      "learning_rate": 1.642008535926004e-06,
      "loss": 14.452493896484375,
      "step": 2900
    },
    {
      "epoch": 1.0380622837370241,
      "grad_norm": 5.143775939941406,
      "learning_rate": 1.555488421663523e-06,
      "loss": 14.467264404296875,
      "step": 3000
    },
    {
      "epoch": 1.0726643598615917,
      "grad_norm": 5.192799091339111,
      "learning_rate": 1.4687828936758435e-06,
      "loss": 14.464970703125,
      "step": 3100
    },
    {
      "epoch": 1.1072664359861593,
      "grad_norm": 5.265404224395752,
      "learning_rate": 1.3821816771787413e-06,
      "loss": 14.4964404296875,
      "step": 3200
    },
    {
      "epoch": 1.1418685121107266,
      "grad_norm": 5.28303337097168,
      "learning_rate": 1.295974148832716e-06,
      "loss": 14.460384521484375,
      "step": 3300
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 5.456825256347656,
      "learning_rate": 1.2104483697952423e-06,
      "loss": 14.472330322265625,
      "step": 3400
    },
    {
      "epoch": 1.2110726643598615,
      "grad_norm": 5.192461013793945,
      "learning_rate": 1.1258901231687475e-06,
      "loss": 14.4242919921875,
      "step": 3500
    },
    {
      "epoch": 1.245674740484429,
      "grad_norm": 5.02662992477417,
      "learning_rate": 1.0425819590606824e-06,
      "loss": 14.4378662109375,
      "step": 3600
    },
    {
      "epoch": 1.2802768166089966,
      "grad_norm": 5.156518459320068,
      "learning_rate": 9.608022504465906e-07,
      "loss": 14.4332080078125,
      "step": 3700
    },
    {
      "epoch": 1.314878892733564,
      "grad_norm": 5.137354850769043,
      "learning_rate": 8.808242629910054e-07,
      "loss": 14.42055419921875,
      "step": 3800
    },
    {
      "epoch": 1.3494809688581315,
      "grad_norm": 4.931822299957275,
      "learning_rate": 8.029152419343472e-07,
      "loss": 14.446268310546875,
      "step": 3900
    },
    {
      "epoch": 1.3840830449826989,
      "grad_norm": 5.438608169555664,
      "learning_rate": 7.273355190969783e-07,
      "loss": 14.436180419921875,
      "step": 4000
    },
    {
      "epoch": 1.4186851211072664,
      "grad_norm": 5.530498027801514,
      "learning_rate": 6.54337642984345e-07,
      "loss": 14.427529296875,
      "step": 4100
    },
    {
      "epoch": 1.453287197231834,
      "grad_norm": 5.223482608795166,
      "learning_rate": 5.841655348999535e-07,
      "loss": 14.415745849609374,
      "step": 4200
    },
    {
      "epoch": 1.4878892733564013,
      "grad_norm": 5.245316982269287,
      "learning_rate": 5.170536738860046e-07,
      "loss": 14.42922119140625,
      "step": 4300
    },
    {
      "epoch": 1.5224913494809689,
      "grad_norm": 5.100404739379883,
      "learning_rate": 4.532263132152101e-07,
      "loss": 14.461243896484374,
      "step": 4400
    },
    {
      "epoch": 1.5570934256055362,
      "grad_norm": 5.252062797546387,
      "learning_rate": 3.928967310518557e-07,
      "loss": 14.419617919921874,
      "step": 4500
    },
    {
      "epoch": 1.5916955017301038,
      "grad_norm": 5.039636611938477,
      "learning_rate": 3.362665177860309e-07,
      "loss": 14.477161865234375,
      "step": 4600
    },
    {
      "epoch": 1.6262975778546713,
      "grad_norm": 5.289979457855225,
      "learning_rate": 2.8352490242237476e-07,
      "loss": 14.38912109375,
      "step": 4700
    },
    {
      "epoch": 1.6608996539792389,
      "grad_norm": 5.163676738739014,
      "learning_rate": 2.348481202742086e-07,
      "loss": 14.403753662109375,
      "step": 4800
    },
    {
      "epoch": 1.6955017301038062,
      "grad_norm": 5.600104331970215,
      "learning_rate": 1.9039882407588976e-07,
      "loss": 14.447159423828126,
      "step": 4900
    },
    {
      "epoch": 1.7301038062283736,
      "grad_norm": 5.240525722503662,
      "learning_rate": 1.503255404811511e-07,
      "loss": 14.401494140625,
      "step": 5000
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 5.186587810516357,
      "learning_rate": 1.1476217376352293e-07,
      "loss": 14.4153125,
      "step": 5100
    },
    {
      "epoch": 1.7993079584775087,
      "grad_norm": 5.226868152618408,
      "learning_rate": 8.382755837722234e-08,
      "loss": 14.4057421875,
      "step": 5200
    },
    {
      "epoch": 1.8339100346020762,
      "grad_norm": 5.335669994354248,
      "learning_rate": 5.762506187361205e-08,
      "loss": 14.435169677734375,
      "step": 5300
    },
    {
      "epoch": 1.8685121107266436,
      "grad_norm": 5.08687686920166,
      "learning_rate": 3.624223950008548e-08,
      "loss": 14.43446533203125,
      "step": 5400
    },
    {
      "epoch": 1.903114186851211,
      "grad_norm": 5.379976272583008,
      "learning_rate": 1.975054163552692e-08,
      "loss": 14.415914306640625,
      "step": 5500
    },
    {
      "epoch": 1.9377162629757785,
      "grad_norm": 5.047989845275879,
      "learning_rate": 8.205075039945553e-09,
      "loss": 14.41682861328125,
      "step": 5600
    },
    {
      "epoch": 1.972318339100346,
      "grad_norm": 5.379687786102295,
      "learning_rate": 1.6444187160679635e-09,
      "loss": 14.4242138671875,
      "step": 5700
    },
    {
      "epoch": 2.0,
      "eval_loss": 3.4774351119995117,
      "eval_runtime": 11.6654,
      "eval_samples_per_second": 640.524,
      "eval_steps_per_second": 10.03,
      "step": 5780
    }
  ],
  "logging_steps": 100,
  "max_steps": 5780,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 2890,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.8943456160818586e+17,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}