{
  "best_global_step": 3924,
  "best_metric": 3.390385389328003,
  "best_model_checkpoint": "sindhibert_session5/checkpoint-3924",
  "epoch": 2.0,
  "eval_steps": 1962,
  "global_step": 3924,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05098139179199592,
      "grad_norm": 5.245308876037598,
      "learning_rate": 2.1063829787234044e-06,
      "loss": 14.123677978515625,
      "step": 100
    },
    {
      "epoch": 0.10196278358399184,
      "grad_norm": 5.646098613739014,
      "learning_rate": 4.23404255319149e-06,
      "loss": 14.066470947265625,
      "step": 200
    },
    {
      "epoch": 0.15294417537598776,
      "grad_norm": 5.477426528930664,
      "learning_rate": 4.99628768445363e-06,
      "loss": 14.01585693359375,
      "step": 300
    },
    {
      "epoch": 0.20392556716798368,
      "grad_norm": 5.2961344718933105,
      "learning_rate": 4.975657001043815e-06,
      "loss": 13.965966796875,
      "step": 400
    },
    {
      "epoch": 0.2549069589599796,
      "grad_norm": 5.533503532409668,
      "learning_rate": 4.937082682936824e-06,
      "loss": 13.97388671875,
      "step": 500
    },
    {
      "epoch": 0.3058883507519755,
      "grad_norm": 5.314619064331055,
      "learning_rate": 4.8808443179239025e-06,
      "loss": 13.95988525390625,
      "step": 600
    },
    {
      "epoch": 0.35686974254397147,
      "grad_norm": 5.3324384689331055,
      "learning_rate": 4.807349523327375e-06,
      "loss": 13.953388671875,
      "step": 700
    },
    {
      "epoch": 0.40785113433596737,
      "grad_norm": 5.467737674713135,
      "learning_rate": 4.717130991578312e-06,
      "loss": 13.9411962890625,
      "step": 800
    },
    {
      "epoch": 0.45883252612796327,
      "grad_norm": 5.45510721206665,
      "learning_rate": 4.610842629246138e-06,
      "loss": 13.934332275390625,
      "step": 900
    },
    {
      "epoch": 0.5098139179199592,
      "grad_norm": 5.6341962814331055,
      "learning_rate": 4.489254817504595e-06,
      "loss": 13.926766357421876,
      "step": 1000
    },
    {
      "epoch": 0.5607953097119551,
      "grad_norm": 5.584266662597656,
      "learning_rate": 4.353248828386359e-06,
      "loss": 13.91165283203125,
      "step": 1100
    },
    {
      "epoch": 0.611776701503951,
      "grad_norm": 5.35775899887085,
      "learning_rate": 4.203810437297447e-06,
      "loss": 13.915504150390625,
      "step": 1200
    },
    {
      "epoch": 0.6627580932959469,
      "grad_norm": 5.549437999725342,
      "learning_rate": 4.042022778088111e-06,
      "loss": 13.945462646484375,
      "step": 1300
    },
    {
      "epoch": 0.7137394850879429,
      "grad_norm": 5.455720901489258,
      "learning_rate": 3.869058492466847e-06,
      "loss": 13.89906494140625,
      "step": 1400
    },
    {
      "epoch": 0.7647208768799388,
      "grad_norm": 5.856232166290283,
      "learning_rate": 3.6861712306588434e-06,
      "loss": 13.905211181640626,
      "step": 1500
    },
    {
      "epoch": 0.8157022686719347,
      "grad_norm": 5.481319904327393,
      "learning_rate": 3.4946865649123025e-06,
      "loss": 13.896219482421875,
      "step": 1600
    },
    {
      "epoch": 0.8666836604639306,
      "grad_norm": 5.278250217437744,
      "learning_rate": 3.2959923817118296e-06,
      "loss": 13.906019287109375,
      "step": 1700
    },
    {
      "epoch": 0.9176650522559265,
      "grad_norm": 5.768893718719482,
      "learning_rate": 3.091528822336405e-06,
      "loss": 13.93161376953125,
      "step": 1800
    },
    {
      "epoch": 0.9686464440479226,
      "grad_norm": 5.366046905517578,
      "learning_rate": 2.8827778446730764e-06,
      "loss": 13.906478271484374,
      "step": 1900
    },
    {
      "epoch": 1.0,
      "eval_loss": 3.396049737930298,
      "eval_runtime": 7.952,
      "eval_samples_per_second": 637.827,
      "eval_steps_per_second": 10.06,
      "step": 1962
    },
    {
      "epoch": 1.0193729288809585,
      "grad_norm": 5.584351062774658,
      "learning_rate": 2.6712524819426355e-06,
      "loss": 13.823892822265625,
      "step": 2000
    },
    {
      "epoch": 1.0703543206729544,
      "grad_norm": 5.338160037994385,
      "learning_rate": 2.458485876190375e-06,
      "loss": 13.90267333984375,
      "step": 2100
    },
    {
      "epoch": 1.1213357124649503,
      "grad_norm": 5.378915309906006,
      "learning_rate": 2.246020166027488e-06,
      "loss": 13.9045458984375,
      "step": 2200
    },
    {
      "epoch": 1.1723171042569462,
      "grad_norm": 5.420534133911133,
      "learning_rate": 2.0353953091650912e-06,
      "loss": 13.91886474609375,
      "step": 2300
    },
    {
      "epoch": 1.2232984960489421,
      "grad_norm": 5.299575328826904,
      "learning_rate": 1.82813792075548e-06,
      "loss": 13.879603271484376,
      "step": 2400
    },
    {
      "epoch": 1.274279887840938,
      "grad_norm": 5.256579875946045,
      "learning_rate": 1.6257502084406458e-06,
      "loss": 13.92048828125,
      "step": 2500
    },
    {
      "epoch": 1.325261279632934,
      "grad_norm": 5.846710205078125,
      "learning_rate": 1.4296990843071351e-06,
      "loss": 13.912366943359375,
      "step": 2600
    },
    {
      "epoch": 1.3762426714249298,
      "grad_norm": 5.547558307647705,
      "learning_rate": 1.2414055326641378e-06,
      "loss": 13.929051513671874,
      "step": 2700
    },
    {
      "epoch": 1.4272240632169257,
      "grad_norm": 5.693734169006348,
      "learning_rate": 1.062234310707458e-06,
      "loss": 13.929571533203125,
      "step": 2800
    },
    {
      "epoch": 1.4782054550089216,
      "grad_norm": 5.414492607116699,
      "learning_rate": 8.934840567192496e-07,
      "loss": 13.91981201171875,
      "step": 2900
    },
    {
      "epoch": 1.5291868468009175,
      "grad_norm": 5.501009941101074,
      "learning_rate": 7.363778774995834e-07,
      "loss": 13.91615478515625,
      "step": 3000
    },
    {
      "epoch": 1.5801682385929134,
      "grad_norm": 5.355737686157227,
      "learning_rate": 5.920544832524166e-07,
      "loss": 13.9007421875,
      "step": 3100
    },
    {
      "epoch": 1.6311496303849093,
      "grad_norm": 5.376833915710449,
      "learning_rate": 4.61559934180571e-07,
      "loss": 13.915396728515624,
      "step": 3200
    },
    {
      "epoch": 1.6821310221769055,
      "grad_norm": 5.302165985107422,
      "learning_rate": 3.4584005861063974e-07,
      "loss": 13.94998046875,
      "step": 3300
    },
    {
      "epoch": 1.7331124139689014,
      "grad_norm": 5.571377277374268,
      "learning_rate": 2.4573359760148354e-07,
      "loss": 13.98015380859375,
      "step": 3400
    },
    {
      "epoch": 1.7840938057608973,
      "grad_norm": 5.618070125579834,
      "learning_rate": 1.619661257243843e-07,
      "loss": 13.96041015625,
      "step": 3500
    },
    {
      "epoch": 1.8350751975528932,
      "grad_norm": 5.216390132904053,
      "learning_rate": 9.514479207723276e-08,
      "loss": 13.9774560546875,
      "step": 3600
    },
    {
      "epoch": 1.886056589344889,
      "grad_norm": 5.458727836608887,
      "learning_rate": 4.575391965002174e-08,
      "loss": 14.00027587890625,
      "step": 3700
    },
    {
      "epoch": 1.9370379811368852,
      "grad_norm": 5.513509273529053,
      "learning_rate": 1.4151494937582056e-08,
      "loss": 14.0021728515625,
      "step": 3800
    },
    {
      "epoch": 1.988019372928881,
      "grad_norm": 5.200069904327393,
      "learning_rate": 5.665732429496751e-10,
      "loss": 13.960343017578126,
      "step": 3900
    },
    {
      "epoch": 2.0,
      "eval_loss": 3.390385389328003,
      "eval_runtime": 7.9843,
      "eval_samples_per_second": 635.249,
      "eval_steps_per_second": 10.02,
      "step": 3924
    }
  ],
  "logging_steps": 100,
  "max_steps": 3924,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 1962,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.643322074019246e+17,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}