{
  "best_global_step": 2000,
  "best_metric": 3.409285306930542,
  "best_model_checkpoint": "/tmp/colab_artifacts_v2/pretrain_checkpoints/checkpoint-2000",
  "epoch": 0.42007981516488135,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010501995379122032,
      "grad_norm": 16.108776092529297,
      "learning_rate": 4.716981132075472e-06,
      "loss": 7.048248901367187,
      "step": 50
    },
    {
      "epoch": 0.021003990758244065,
      "grad_norm": 7.494509220123291,
      "learning_rate": 9.958071278825997e-06,
      "loss": 5.635718994140625,
      "step": 100
    },
    {
      "epoch": 0.0315059861373661,
      "grad_norm": 3.1452040672302246,
      "learning_rate": 1.5199161425576522e-05,
      "loss": 4.769013366699219,
      "step": 150
    },
    {
      "epoch": 0.04200798151648813,
      "grad_norm": 6.104097843170166,
      "learning_rate": 2.0440251572327044e-05,
      "loss": 4.167159423828125,
      "step": 200
    },
    {
      "epoch": 0.05250997689561017,
      "grad_norm": 2.9789626598358154,
      "learning_rate": 2.5681341719077568e-05,
      "loss": 4.021661987304688,
      "step": 250
    },
    {
      "epoch": 0.0630119722747322,
      "grad_norm": 3.7343900203704834,
      "learning_rate": 3.092243186582809e-05,
      "loss": 3.8835012817382815,
      "step": 300
    },
    {
      "epoch": 0.07351396765385423,
      "grad_norm": 3.598313808441162,
      "learning_rate": 3.6163522012578616e-05,
      "loss": 3.719826354980469,
      "step": 350
    },
    {
      "epoch": 0.08401596303297626,
      "grad_norm": 2.9602694511413574,
      "learning_rate": 4.140461215932914e-05,
      "loss": 3.6351690673828125,
      "step": 400
    },
    {
      "epoch": 0.0945179584120983,
      "grad_norm": 2.4005064964294434,
      "learning_rate": 4.664570230607967e-05,
      "loss": 3.552754211425781,
      "step": 450
    },
    {
      "epoch": 0.10501995379122034,
      "grad_norm": 3.6799378395080566,
      "learning_rate": 4.978991596638656e-05,
      "loss": 3.5413519287109376,
      "step": 500
    },
    {
      "epoch": 0.10501995379122034,
      "eval_loss": 4.811308860778809,
      "eval_runtime": 24.7312,
      "eval_samples_per_second": 10.958,
      "eval_steps_per_second": 2.75,
      "step": 500
    },
    {
      "epoch": 0.11552194917034236,
      "grad_norm": 2.4428603649139404,
      "learning_rate": 4.9206349206349204e-05,
      "loss": 3.434654541015625,
      "step": 550
    },
    {
      "epoch": 0.1260239445494644,
      "grad_norm": 2.2486448287963867,
      "learning_rate": 4.862278244631186e-05,
      "loss": 3.5255862426757814,
      "step": 600
    },
    {
      "epoch": 0.13652593992858644,
      "grad_norm": 2.5440492630004883,
      "learning_rate": 4.803921568627452e-05,
      "loss": 3.265621337890625,
      "step": 650
    },
    {
      "epoch": 0.14702793530770847,
      "grad_norm": 5.0713605880737305,
      "learning_rate": 4.745564892623716e-05,
      "loss": 3.3151104736328123,
      "step": 700
    },
    {
      "epoch": 0.1575299306868305,
      "grad_norm": 3.032827615737915,
      "learning_rate": 4.6872082166199816e-05,
      "loss": 3.3802804565429687,
      "step": 750
    },
    {
      "epoch": 0.16803192606595252,
      "grad_norm": 2.8556971549987793,
      "learning_rate": 4.6288515406162466e-05,
      "loss": 3.175123596191406,
      "step": 800
    },
    {
      "epoch": 0.17853392144507457,
      "grad_norm": 2.813127279281616,
      "learning_rate": 4.5704948646125116e-05,
      "loss": 3.1402743530273436,
      "step": 850
    },
    {
      "epoch": 0.1890359168241966,
      "grad_norm": 3.5564844608306885,
      "learning_rate": 4.512138188608777e-05,
      "loss": 3.1378076171875,
      "step": 900
    },
    {
      "epoch": 0.19953791220331862,
      "grad_norm": 4.420061111450195,
      "learning_rate": 4.453781512605042e-05,
      "loss": 3.09103271484375,
      "step": 950
    },
    {
      "epoch": 0.21003990758244068,
      "grad_norm": 3.6192879676818848,
      "learning_rate": 4.395424836601307e-05,
      "loss": 3.145036315917969,
      "step": 1000
    },
    {
      "epoch": 0.21003990758244068,
      "eval_loss": 3.8735694885253906,
      "eval_runtime": 24.3553,
      "eval_samples_per_second": 11.127,
      "eval_steps_per_second": 2.792,
      "step": 1000
    },
    {
      "epoch": 0.2205419029615627,
      "grad_norm": 6.488380432128906,
      "learning_rate": 4.337068160597573e-05,
      "loss": 3.167205810546875,
      "step": 1050
    },
    {
      "epoch": 0.23104389834068473,
      "grad_norm": 3.438765525817871,
      "learning_rate": 4.278711484593838e-05,
      "loss": 3.0527557373046874,
      "step": 1100
    },
    {
      "epoch": 0.24154589371980675,
      "grad_norm": 3.3744046688079834,
      "learning_rate": 4.220354808590103e-05,
      "loss": 3.056681823730469,
      "step": 1150
    },
    {
      "epoch": 0.2520478890989288,
      "grad_norm": 2.0418734550476074,
      "learning_rate": 4.1619981325863684e-05,
      "loss": 3.0335903930664063,
      "step": 1200
    },
    {
      "epoch": 0.26254988447805083,
      "grad_norm": 3.0685362815856934,
      "learning_rate": 4.1036414565826334e-05,
      "loss": 2.931863098144531,
      "step": 1250
    },
    {
      "epoch": 0.2730518798571729,
      "grad_norm": 2.3799123764038086,
      "learning_rate": 4.0452847805788984e-05,
      "loss": 3.0471902465820313,
      "step": 1300
    },
    {
      "epoch": 0.2835538752362949,
      "grad_norm": 2.9344570636749268,
      "learning_rate": 3.986928104575164e-05,
      "loss": 2.888125,
      "step": 1350
    },
    {
      "epoch": 0.29405587061541694,
      "grad_norm": 2.8988893032073975,
      "learning_rate": 3.928571428571429e-05,
      "loss": 2.940912170410156,
      "step": 1400
    },
    {
      "epoch": 0.304557865994539,
      "grad_norm": 8.145448684692383,
      "learning_rate": 3.870214752567694e-05,
      "loss": 2.9622201538085937,
      "step": 1450
    },
    {
      "epoch": 0.315059861373661,
      "grad_norm": 3.801460027694702,
      "learning_rate": 3.811858076563959e-05,
      "loss": 2.9859747314453124,
      "step": 1500
    },
    {
      "epoch": 0.315059861373661,
      "eval_loss": 3.5815439224243164,
      "eval_runtime": 24.3722,
      "eval_samples_per_second": 11.119,
      "eval_steps_per_second": 2.79,
      "step": 1500
    },
    {
      "epoch": 0.32556185675278304,
      "grad_norm": 2.2608940601348877,
      "learning_rate": 3.753501400560224e-05,
      "loss": 2.870184326171875,
      "step": 1550
    },
    {
      "epoch": 0.33606385213190504,
      "grad_norm": 3.5865588188171387,
      "learning_rate": 3.6951447245564896e-05,
      "loss": 2.9996963500976563,
      "step": 1600
    },
    {
      "epoch": 0.3465658475110271,
      "grad_norm": 3.1756653785705566,
      "learning_rate": 3.6367880485527545e-05,
      "loss": 2.9004736328125,
      "step": 1650
    },
    {
      "epoch": 0.35706784289014915,
      "grad_norm": 3.698146104812622,
      "learning_rate": 3.5784313725490195e-05,
      "loss": 2.9160443115234376,
      "step": 1700
    },
    {
      "epoch": 0.36756983826927114,
      "grad_norm": 2.639841079711914,
      "learning_rate": 3.520074696545285e-05,
      "loss": 2.928147888183594,
      "step": 1750
    },
    {
      "epoch": 0.3780718336483932,
      "grad_norm": 3.2465906143188477,
      "learning_rate": 3.46171802054155e-05,
      "loss": 2.837327575683594,
      "step": 1800
    },
    {
      "epoch": 0.38857382902751525,
      "grad_norm": 3.475036859512329,
      "learning_rate": 3.403361344537815e-05,
      "loss": 2.87112548828125,
      "step": 1850
    },
    {
      "epoch": 0.39907582440663725,
      "grad_norm": 2.9756319522857666,
      "learning_rate": 3.34500466853408e-05,
      "loss": 2.870127868652344,
      "step": 1900
    },
    {
      "epoch": 0.4095778197857593,
      "grad_norm": 2.9511425495147705,
      "learning_rate": 3.286647992530346e-05,
      "loss": 2.887370910644531,
      "step": 1950
    },
    {
      "epoch": 0.42007981516488135,
      "grad_norm": 2.802246332168579,
      "learning_rate": 3.228291316526611e-05,
      "loss": 2.8228793334960938,
      "step": 2000
    },
    {
      "epoch": 0.42007981516488135,
      "eval_loss": 3.409285306930542,
      "eval_runtime": 24.4492,
      "eval_samples_per_second": 11.084,
      "eval_steps_per_second": 2.781,
      "step": 2000
    }
  ],
  "logging_steps": 50,
  "max_steps": 4761,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.01
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.8553127709753344e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}