{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04595236271731638,
  "eval_steps": 25,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006126981695642184,
      "grad_norm": 16.523408889770508,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 6.7324,
      "step": 1
    },
    {
      "epoch": 0.0006126981695642184,
      "eval_loss": 7.338907718658447,
      "eval_runtime": 69.8065,
      "eval_samples_per_second": 19.697,
      "eval_steps_per_second": 9.856,
      "step": 1
    },
    {
      "epoch": 0.0012253963391284368,
      "grad_norm": 18.644798278808594,
      "learning_rate": 6.666666666666667e-05,
      "loss": 6.6114,
      "step": 2
    },
    {
      "epoch": 0.0018380945086926552,
      "grad_norm": 15.051867485046387,
      "learning_rate": 0.0001,
      "loss": 5.7936,
      "step": 3
    },
    {
      "epoch": 0.0024507926782568737,
      "grad_norm": 15.758862495422363,
      "learning_rate": 9.99524110790929e-05,
      "loss": 5.8646,
      "step": 4
    },
    {
      "epoch": 0.0030634908478210923,
      "grad_norm": 12.907825469970703,
      "learning_rate": 9.980973490458728e-05,
      "loss": 4.3165,
      "step": 5
    },
    {
      "epoch": 0.0036761890173853105,
      "grad_norm": 13.11896800994873,
      "learning_rate": 9.957224306869053e-05,
      "loss": 3.7056,
      "step": 6
    },
    {
      "epoch": 0.004288887186949529,
      "grad_norm": 11.859108924865723,
      "learning_rate": 9.924038765061042e-05,
      "loss": 3.0861,
      "step": 7
    },
    {
      "epoch": 0.004901585356513747,
      "grad_norm": 11.189018249511719,
      "learning_rate": 9.881480035599667e-05,
      "loss": 3.0677,
      "step": 8
    },
    {
      "epoch": 0.005514283526077966,
      "grad_norm": 8.765135765075684,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.8499,
      "step": 9
    },
    {
      "epoch": 0.006126981695642185,
      "grad_norm": 7.158143520355225,
      "learning_rate": 9.768584753741134e-05,
      "loss": 2.1377,
      "step": 10
    },
    {
      "epoch": 0.006739679865206402,
      "grad_norm": 7.217545509338379,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.4496,
      "step": 11
    },
    {
      "epoch": 0.007352378034770621,
      "grad_norm": 7.291643142700195,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.249,
      "step": 12
    },
    {
      "epoch": 0.007965076204334839,
      "grad_norm": 8.006402015686035,
      "learning_rate": 9.53153893518325e-05,
      "loss": 2.7193,
      "step": 13
    },
    {
      "epoch": 0.008577774373899057,
      "grad_norm": 6.830563545227051,
      "learning_rate": 9.435054165891109e-05,
      "loss": 2.7104,
      "step": 14
    },
    {
      "epoch": 0.009190472543463276,
      "grad_norm": 5.633250713348389,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.0096,
      "step": 15
    },
    {
      "epoch": 0.009803170713027495,
      "grad_norm": 4.747769832611084,
      "learning_rate": 9.21695722906443e-05,
      "loss": 1.9659,
      "step": 16
    },
    {
      "epoch": 0.010415868882591713,
      "grad_norm": 4.103663921356201,
      "learning_rate": 9.09576022144496e-05,
      "loss": 1.8876,
      "step": 17
    },
    {
      "epoch": 0.011028567052155932,
      "grad_norm": 5.507636547088623,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.6484,
      "step": 18
    },
    {
      "epoch": 0.01164126522172015,
      "grad_norm": 4.795409679412842,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.8157,
      "step": 19
    },
    {
      "epoch": 0.01225396339128437,
      "grad_norm": 4.361155033111572,
      "learning_rate": 8.68638668405062e-05,
      "loss": 1.8387,
      "step": 20
    },
    {
      "epoch": 0.012866661560848588,
      "grad_norm": 4.868300914764404,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.2786,
      "step": 21
    },
    {
      "epoch": 0.013479359730412805,
      "grad_norm": 6.176185131072998,
      "learning_rate": 8.377951038078302e-05,
      "loss": 2.3026,
      "step": 22
    },
    {
      "epoch": 0.014092057899977023,
      "grad_norm": 4.714465141296387,
      "learning_rate": 8.213938048432697e-05,
      "loss": 2.1449,
      "step": 23
    },
    {
      "epoch": 0.014704756069541242,
      "grad_norm": 4.232319355010986,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.418,
      "step": 24
    },
    {
      "epoch": 0.01531745423910546,
      "grad_norm": 4.79272985458374,
      "learning_rate": 7.86788218175523e-05,
      "loss": 2.043,
      "step": 25
    },
    {
      "epoch": 0.01531745423910546,
      "eval_loss": 1.8542509078979492,
      "eval_runtime": 69.8889,
      "eval_samples_per_second": 19.674,
      "eval_steps_per_second": 9.844,
      "step": 25
    },
    {
      "epoch": 0.015930152408669677,
      "grad_norm": 4.93162202835083,
      "learning_rate": 7.68649804173412e-05,
      "loss": 1.8622,
      "step": 26
    },
    {
      "epoch": 0.016542850578233896,
      "grad_norm": 4.746114730834961,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.6622,
      "step": 27
    },
    {
      "epoch": 0.017155548747798115,
      "grad_norm": 4.882776260375977,
      "learning_rate": 7.308743066175172e-05,
      "loss": 1.8984,
      "step": 28
    },
    {
      "epoch": 0.017768246917362333,
      "grad_norm": 3.9814393520355225,
      "learning_rate": 7.113091308703498e-05,
      "loss": 1.3697,
      "step": 29
    },
    {
      "epoch": 0.018380945086926552,
      "grad_norm": 7.2121992111206055,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.1676,
      "step": 30
    },
    {
      "epoch": 0.01899364325649077,
      "grad_norm": 5.58474588394165,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.6876,
      "step": 31
    },
    {
      "epoch": 0.01960634142605499,
      "grad_norm": 4.772983551025391,
      "learning_rate": 6.503528997521366e-05,
      "loss": 1.7231,
      "step": 32
    },
    {
      "epoch": 0.020219039595619208,
      "grad_norm": 3.946286678314209,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.2223,
      "step": 33
    },
    {
      "epoch": 0.020831737765183427,
      "grad_norm": 4.936631679534912,
      "learning_rate": 6.0821980696905146e-05,
      "loss": 1.6819,
      "step": 34
    },
    {
      "epoch": 0.021444435934747645,
      "grad_norm": 4.5297956466674805,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.824,
      "step": 35
    },
    {
      "epoch": 0.022057134104311864,
      "grad_norm": 5.4143524169921875,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 2.5458,
      "step": 36
    },
    {
      "epoch": 0.022669832273876082,
      "grad_norm": 4.592708110809326,
      "learning_rate": 5.435778713738292e-05,
      "loss": 1.6016,
      "step": 37
    },
    {
      "epoch": 0.0232825304434403,
      "grad_norm": 5.789618492126465,
      "learning_rate": 5.218096936826681e-05,
      "loss": 2.0341,
      "step": 38
    },
    {
      "epoch": 0.02389522861300452,
      "grad_norm": 6.866486549377441,
      "learning_rate": 5e-05,
      "loss": 1.9014,
      "step": 39
    },
    {
      "epoch": 0.02450792678256874,
      "grad_norm": 3.9232795238494873,
      "learning_rate": 4.781903063173321e-05,
      "loss": 1.5297,
      "step": 40
    },
    {
      "epoch": 0.025120624952132957,
      "grad_norm": 5.109820365905762,
      "learning_rate": 4.564221286261709e-05,
      "loss": 1.4501,
      "step": 41
    },
    {
      "epoch": 0.025733323121697176,
      "grad_norm": 4.550601959228516,
      "learning_rate": 4.347369038899744e-05,
      "loss": 1.8131,
      "step": 42
    },
    {
      "epoch": 0.02634602129126139,
      "grad_norm": 4.237565994262695,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.4321,
      "step": 43
    },
    {
      "epoch": 0.02695871946082561,
      "grad_norm": 4.74612283706665,
      "learning_rate": 3.917801930309486e-05,
      "loss": 1.7617,
      "step": 44
    },
    {
      "epoch": 0.027571417630389828,
      "grad_norm": 4.633487224578857,
      "learning_rate": 3.705904774487396e-05,
      "loss": 1.5634,
      "step": 45
    },
    {
      "epoch": 0.028184115799954047,
      "grad_norm": 5.383734703063965,
      "learning_rate": 3.4964710024786354e-05,
      "loss": 1.2762,
      "step": 46
    },
    {
      "epoch": 0.028796813969518265,
      "grad_norm": 4.597635746002197,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.6126,
      "step": 47
    },
    {
      "epoch": 0.029409512139082484,
      "grad_norm": 5.0467939376831055,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.8275,
      "step": 48
    },
    {
      "epoch": 0.030022210308646703,
      "grad_norm": 4.837862968444824,
      "learning_rate": 2.886908691296504e-05,
      "loss": 1.354,
      "step": 49
    },
    {
      "epoch": 0.03063490847821092,
      "grad_norm": 5.544301509857178,
      "learning_rate": 2.6912569338248315e-05,
      "loss": 2.0362,
      "step": 50
    },
    {
      "epoch": 0.03063490847821092,
      "eval_loss": 1.6958106756210327,
      "eval_runtime": 69.8654,
      "eval_samples_per_second": 19.681,
      "eval_steps_per_second": 9.848,
      "step": 50
    },
    {
      "epoch": 0.03124760664777514,
      "grad_norm": 5.290032863616943,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.7652,
      "step": 51
    },
    {
      "epoch": 0.031860304817339355,
      "grad_norm": 4.4247918128967285,
      "learning_rate": 2.3135019582658802e-05,
      "loss": 1.3013,
      "step": 52
    },
    {
      "epoch": 0.032473002986903574,
      "grad_norm": 5.015321731567383,
      "learning_rate": 2.132117818244771e-05,
      "loss": 1.7464,
      "step": 53
    },
    {
      "epoch": 0.03308570115646779,
      "grad_norm": 4.878988742828369,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 1.8481,
      "step": 54
    },
    {
      "epoch": 0.03369839932603201,
      "grad_norm": 5.039571762084961,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.8381,
      "step": 55
    },
    {
      "epoch": 0.03431109749559623,
      "grad_norm": 4.236940860748291,
      "learning_rate": 1.622048961921699e-05,
      "loss": 1.6581,
      "step": 56
    },
    {
      "epoch": 0.03492379566516045,
      "grad_norm": 4.249587059020996,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.8034,
      "step": 57
    },
    {
      "epoch": 0.03553649383472467,
      "grad_norm": 4.9123101234436035,
      "learning_rate": 1.3136133159493802e-05,
      "loss": 1.9322,
      "step": 58
    },
    {
      "epoch": 0.036149192004288885,
      "grad_norm": 4.07620906829834,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.7094,
      "step": 59
    },
    {
      "epoch": 0.036761890173853104,
      "grad_norm": 5.378344535827637,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 2.0213,
      "step": 60
    },
    {
      "epoch": 0.03737458834341732,
      "grad_norm": 5.754098415374756,
      "learning_rate": 9.042397785550405e-06,
      "loss": 1.9983,
      "step": 61
    },
    {
      "epoch": 0.03798728651298154,
      "grad_norm": 4.320245265960693,
      "learning_rate": 7.830427709355725e-06,
      "loss": 1.4495,
      "step": 62
    },
    {
      "epoch": 0.03859998468254576,
      "grad_norm": 4.051548004150391,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.3731,
      "step": 63
    },
    {
      "epoch": 0.03921268285210998,
      "grad_norm": 4.426172733306885,
      "learning_rate": 5.649458341088915e-06,
      "loss": 1.3405,
      "step": 64
    },
    {
      "epoch": 0.0398253810216742,
      "grad_norm": 3.88987398147583,
      "learning_rate": 4.684610648167503e-06,
      "loss": 1.2247,
      "step": 65
    },
    {
      "epoch": 0.040438079191238416,
      "grad_norm": 3.9318177700042725,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.5804,
      "step": 66
    },
    {
      "epoch": 0.041050777360802634,
      "grad_norm": 4.765309810638428,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.894,
      "step": 67
    },
    {
      "epoch": 0.04166347553036685,
      "grad_norm": 4.806102275848389,
      "learning_rate": 2.314152462588659e-06,
      "loss": 1.8357,
      "step": 68
    },
    {
      "epoch": 0.04227617369993107,
      "grad_norm": 3.432342767715454,
      "learning_rate": 1.70370868554659e-06,
      "loss": 1.4435,
      "step": 69
    },
    {
      "epoch": 0.04288887186949529,
      "grad_norm": 4.094058513641357,
      "learning_rate": 1.1851996440033319e-06,
      "loss": 1.7393,
      "step": 70
    },
    {
      "epoch": 0.04350157003905951,
      "grad_norm": 3.67228364944458,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.2483,
      "step": 71
    },
    {
      "epoch": 0.04411426820862373,
      "grad_norm": 4.162522315979004,
      "learning_rate": 4.277569313094809e-07,
      "loss": 1.5257,
      "step": 72
    },
    {
      "epoch": 0.044726966378187946,
      "grad_norm": 4.666938781738281,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 1.442,
      "step": 73
    },
    {
      "epoch": 0.045339664547752165,
      "grad_norm": 4.068970203399658,
      "learning_rate": 4.7588920907110094e-08,
      "loss": 1.3729,
      "step": 74
    },
    {
      "epoch": 0.04595236271731638,
      "grad_norm": 4.049544334411621,
      "learning_rate": 0.0,
      "loss": 1.4979,
      "step": 75
    },
    {
      "epoch": 0.04595236271731638,
      "eval_loss": 1.6688679456710815,
      "eval_runtime": 69.8874,
      "eval_samples_per_second": 19.674,
      "eval_steps_per_second": 9.844,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.95132603613184e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}