{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9921259842519685,
  "eval_steps": 16,
  "global_step": 63,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.015748031496062992,
      "grad_norm": 0.034481361508369446,
      "learning_rate": 4e-05,
      "loss": 0.1412,
      "step": 1
    },
    {
      "epoch": 0.015748031496062992,
      "eval_loss": 0.1612786203622818,
      "eval_runtime": 64.5157,
      "eval_samples_per_second": 7.812,
      "eval_steps_per_second": 0.977,
      "step": 1
    },
    {
      "epoch": 0.031496062992125984,
      "grad_norm": 0.029317770153284073,
      "learning_rate": 8e-05,
      "loss": 0.1191,
      "step": 2
    },
    {
      "epoch": 0.047244094488188976,
      "grad_norm": 0.036621659994125366,
      "learning_rate": 0.00012,
      "loss": 0.1369,
      "step": 3
    },
    {
      "epoch": 0.06299212598425197,
      "grad_norm": 0.04425783455371857,
      "learning_rate": 0.00016,
      "loss": 0.1321,
      "step": 4
    },
    {
      "epoch": 0.07874015748031496,
      "grad_norm": 0.05247063934803009,
      "learning_rate": 0.0002,
      "loss": 0.1285,
      "step": 5
    },
    {
      "epoch": 0.09448818897637795,
      "grad_norm": 0.03902214765548706,
      "learning_rate": 0.00019996629653035126,
      "loss": 0.1004,
      "step": 6
    },
    {
      "epoch": 0.11023622047244094,
      "grad_norm": 0.03752463683485985,
      "learning_rate": 0.00019986520883988232,
      "loss": 0.0985,
      "step": 7
    },
    {
      "epoch": 0.12598425196850394,
      "grad_norm": 0.03061060793697834,
      "learning_rate": 0.00019969680506871137,
      "loss": 0.0912,
      "step": 8
    },
    {
      "epoch": 0.14173228346456693,
      "grad_norm": 0.034427180886268616,
      "learning_rate": 0.00019946119873266613,
      "loss": 0.0836,
      "step": 9
    },
    {
      "epoch": 0.15748031496062992,
      "grad_norm": 0.03106631338596344,
      "learning_rate": 0.00019915854864676664,
      "loss": 0.0734,
      "step": 10
    },
    {
      "epoch": 0.1732283464566929,
      "grad_norm": 0.02498232200741768,
      "learning_rate": 0.00019878905881817252,
      "loss": 0.0729,
      "step": 11
    },
    {
      "epoch": 0.1889763779527559,
      "grad_norm": 0.03798564895987511,
      "learning_rate": 0.00019835297830866826,
      "loss": 0.0694,
      "step": 12
    },
    {
      "epoch": 0.2047244094488189,
      "grad_norm": 0.046124912798404694,
      "learning_rate": 0.00019785060106677818,
      "loss": 0.0833,
      "step": 13
    },
    {
      "epoch": 0.2204724409448819,
      "grad_norm": 0.02981509082019329,
      "learning_rate": 0.00019728226572962473,
      "loss": 0.0713,
      "step": 14
    },
    {
      "epoch": 0.23622047244094488,
      "grad_norm": 0.02461801841855049,
      "learning_rate": 0.0001966483553946637,
      "loss": 0.0657,
      "step": 15
    },
    {
      "epoch": 0.25196850393700787,
      "grad_norm": 0.04344266653060913,
      "learning_rate": 0.00019594929736144976,
      "loss": 0.0635,
      "step": 16
    },
    {
      "epoch": 0.25196850393700787,
      "eval_loss": 0.06579381227493286,
      "eval_runtime": 64.6166,
      "eval_samples_per_second": 7.8,
      "eval_steps_per_second": 0.975,
      "step": 16
    },
    {
      "epoch": 0.2677165354330709,
      "grad_norm": 0.0320642925798893,
      "learning_rate": 0.00019518556284360696,
      "loss": 0.0656,
      "step": 17
    },
    {
      "epoch": 0.28346456692913385,
      "grad_norm": 0.028899891301989555,
      "learning_rate": 0.0001943576666511982,
      "loss": 0.0462,
      "step": 18
    },
    {
      "epoch": 0.2992125984251969,
      "grad_norm": 0.02383616380393505,
      "learning_rate": 0.0001934661668437073,
      "loss": 0.0649,
      "step": 19
    },
    {
      "epoch": 0.31496062992125984,
      "grad_norm": 0.03346535563468933,
      "learning_rate": 0.0001925116643538684,
      "loss": 0.0546,
      "step": 20
    },
    {
      "epoch": 0.33070866141732286,
      "grad_norm": 0.020454615354537964,
      "learning_rate": 0.00019149480258259533,
      "loss": 0.0538,
      "step": 21
    },
    {
      "epoch": 0.3464566929133858,
      "grad_norm": 0.02081696316599846,
      "learning_rate": 0.00019041626696528503,
      "loss": 0.0526,
      "step": 22
    },
    {
      "epoch": 0.36220472440944884,
      "grad_norm": 0.028128350153565407,
      "learning_rate": 0.0001892767845097864,
      "loss": 0.0593,
      "step": 23
    },
    {
      "epoch": 0.3779527559055118,
      "grad_norm": 0.015519126318395138,
      "learning_rate": 0.00018807712330634642,
      "loss": 0.0528,
      "step": 24
    },
    {
      "epoch": 0.3937007874015748,
      "grad_norm": 0.03593792766332626,
      "learning_rate": 0.0001868180920098644,
      "loss": 0.0481,
      "step": 25
    },
    {
      "epoch": 0.4094488188976378,
      "grad_norm": 0.015408644452691078,
      "learning_rate": 0.00018550053929480202,
      "loss": 0.0479,
      "step": 26
    },
    {
      "epoch": 0.4251968503937008,
      "grad_norm": 0.021226301789283752,
      "learning_rate": 0.00018412535328311814,
      "loss": 0.054,
      "step": 27
    },
    {
      "epoch": 0.4409448818897638,
      "grad_norm": 0.01717953570187092,
      "learning_rate": 0.0001826934609456129,
      "loss": 0.0523,
      "step": 28
    },
    {
      "epoch": 0.4566929133858268,
      "grad_norm": 0.019626960158348083,
      "learning_rate": 0.00018120582747708502,
      "loss": 0.0512,
      "step": 29
    },
    {
      "epoch": 0.47244094488188976,
      "grad_norm": 0.019186396151781082,
      "learning_rate": 0.0001796634556457236,
      "loss": 0.05,
      "step": 30
    },
    {
      "epoch": 0.4881889763779528,
      "grad_norm": 0.014989328570663929,
      "learning_rate": 0.0001780673851171728,
      "loss": 0.0441,
      "step": 31
    },
    {
      "epoch": 0.5039370078740157,
      "grad_norm": 0.012519012205302715,
      "learning_rate": 0.00017641869175372493,
      "loss": 0.0459,
      "step": 32
    },
    {
      "epoch": 0.5039370078740157,
      "eval_loss": 0.056131936609745026,
      "eval_runtime": 64.4985,
      "eval_samples_per_second": 7.814,
      "eval_steps_per_second": 0.977,
      "step": 32
    },
    {
      "epoch": 0.5196850393700787,
      "grad_norm": 0.01598576456308365,
      "learning_rate": 0.00017471848688911464,
      "loss": 0.0496,
      "step": 33
    },
    {
      "epoch": 0.5354330708661418,
      "grad_norm": 0.017361309379339218,
      "learning_rate": 0.000172967916579403,
      "loss": 0.0534,
      "step": 34
    },
    {
      "epoch": 0.5511811023622047,
      "grad_norm": 0.021230200305581093,
      "learning_rate": 0.00017116816083045602,
      "loss": 0.0505,
      "step": 35
    },
    {
      "epoch": 0.5669291338582677,
      "grad_norm": 0.01624094881117344,
      "learning_rate": 0.0001693204328025389,
      "loss": 0.0568,
      "step": 36
    },
    {
      "epoch": 0.5826771653543307,
      "grad_norm": 0.014916475862264633,
      "learning_rate": 0.00016742597799256182,
      "loss": 0.0542,
      "step": 37
    },
    {
      "epoch": 0.5984251968503937,
      "grad_norm": 0.013211382552981377,
      "learning_rate": 0.00016548607339452853,
      "loss": 0.0507,
      "step": 38
    },
    {
      "epoch": 0.6141732283464567,
      "grad_norm": 0.01305565144866705,
      "learning_rate": 0.00016350202663875386,
      "loss": 0.0387,
      "step": 39
    },
    {
      "epoch": 0.6299212598425197,
      "grad_norm": 0.011459614150226116,
      "learning_rate": 0.0001614751751104301,
      "loss": 0.0433,
      "step": 40
    },
    {
      "epoch": 0.6456692913385826,
      "grad_norm": 0.014712609350681305,
      "learning_rate": 0.00015940688504813662,
      "loss": 0.0571,
      "step": 41
    },
    {
      "epoch": 0.6614173228346457,
      "grad_norm": 0.015662657096982002,
      "learning_rate": 0.00015729855062290022,
      "loss": 0.0504,
      "step": 42
    },
    {
      "epoch": 0.6771653543307087,
      "grad_norm": 0.011235736310482025,
      "learning_rate": 0.00015515159299842707,
      "loss": 0.0453,
      "step": 43
    },
    {
      "epoch": 0.6929133858267716,
      "grad_norm": 0.011984420008957386,
      "learning_rate": 0.00015296745937313987,
      "loss": 0.0402,
      "step": 44
    },
    {
      "epoch": 0.7086614173228346,
      "grad_norm": 0.010523953475058079,
      "learning_rate": 0.00015074762200466556,
      "loss": 0.036,
      "step": 45
    },
    {
      "epoch": 0.7244094488188977,
      "grad_norm": 0.013540665619075298,
      "learning_rate": 0.00014849357721743168,
      "loss": 0.0346,
      "step": 46
    },
    {
      "epoch": 0.7401574803149606,
      "grad_norm": 0.012998640537261963,
      "learning_rate": 0.00014620684439403962,
      "loss": 0.0468,
      "step": 47
    },
    {
      "epoch": 0.7559055118110236,
      "grad_norm": 0.01443515345454216,
      "learning_rate": 0.0001438889649510956,
      "loss": 0.0453,
      "step": 48
    },
    {
      "epoch": 0.7559055118110236,
      "eval_loss": 0.05216333642601967,
      "eval_runtime": 64.5137,
      "eval_samples_per_second": 7.812,
      "eval_steps_per_second": 0.977,
      "step": 48
    },
    {
      "epoch": 0.7716535433070866,
      "grad_norm": 0.01463907677680254,
      "learning_rate": 0.00014154150130018866,
      "loss": 0.0526,
      "step": 49
    },
    {
      "epoch": 0.7874015748031497,
      "grad_norm": 0.01614455319941044,
      "learning_rate": 0.00013916603579471705,
      "loss": 0.0484,
      "step": 50
    },
    {
      "epoch": 0.8031496062992126,
      "grad_norm": 0.014042153023183346,
      "learning_rate": 0.000136764169663272,
      "loss": 0.0419,
      "step": 51
    },
    {
      "epoch": 0.8188976377952756,
      "grad_norm": 0.015309924259781837,
      "learning_rate": 0.00013433752193029886,
      "loss": 0.0425,
      "step": 52
    },
    {
      "epoch": 0.8346456692913385,
      "grad_norm": 0.018054217100143433,
      "learning_rate": 0.00013188772832476188,
      "loss": 0.0426,
      "step": 53
    },
    {
      "epoch": 0.8503937007874016,
      "grad_norm": 0.012343033216893673,
      "learning_rate": 0.00012941644017754964,
      "loss": 0.0448,
      "step": 54
    },
    {
      "epoch": 0.8661417322834646,
      "grad_norm": 0.012457596138119698,
      "learning_rate": 0.00012692532330836346,
      "loss": 0.0451,
      "step": 55
    },
    {
      "epoch": 0.8818897637795275,
      "grad_norm": 0.013512413017451763,
      "learning_rate": 0.00012441605690283915,
      "loss": 0.0413,
      "step": 56
    },
    {
      "epoch": 0.8976377952755905,
      "grad_norm": 0.013424846343696117,
      "learning_rate": 0.0001218903323806595,
      "loss": 0.0441,
      "step": 57
    },
    {
      "epoch": 0.9133858267716536,
      "grad_norm": 0.014157367870211601,
      "learning_rate": 0.00011934985225541998,
      "loss": 0.0443,
      "step": 58
    },
    {
      "epoch": 0.9291338582677166,
      "grad_norm": 0.0130110839381814,
      "learning_rate": 0.00011679632898701649,
      "loss": 0.0478,
      "step": 59
    },
    {
      "epoch": 0.9448818897637795,
      "grad_norm": 0.012677576392889023,
      "learning_rate": 0.00011423148382732853,
      "loss": 0.0399,
      "step": 60
    },
    {
      "epoch": 0.9606299212598425,
      "grad_norm": 0.01409006118774414,
      "learning_rate": 0.00011165704565997593,
      "loss": 0.0481,
      "step": 61
    },
    {
      "epoch": 0.9763779527559056,
      "grad_norm": 0.013535700738430023,
      "learning_rate": 0.00010907474983493144,
      "loss": 0.0406,
      "step": 62
    },
    {
      "epoch": 0.9921259842519685,
      "grad_norm": 0.014210895635187626,
      "learning_rate": 0.0001064863369987743,
      "loss": 0.0425,
      "step": 63
    }
  ],
  "logging_steps": 1,
  "max_steps": 126,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 63,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.3132684787266355e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}