{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8919350295746878,
  "eval_steps": 5000,
  "global_step": 9500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009388789784996713,
      "grad_norm": 87.77811431884766,
      "learning_rate": 9.009854528390429e-07,
      "loss": 16.2337,
      "step": 100
    },
    {
      "epoch": 0.018777579569993427,
      "grad_norm": 85.86430358886719,
      "learning_rate": 1.8395119662130456e-06,
      "loss": 13.5901,
      "step": 200
    },
    {
      "epoch": 0.02816636935499014,
      "grad_norm": 14.885255813598633,
      "learning_rate": 2.7592679493195683e-06,
      "loss": 9.8565,
      "step": 300
    },
    {
      "epoch": 0.03755515913998685,
      "grad_norm": 6.9691972732543945,
      "learning_rate": 3.6977944626935713e-06,
      "loss": 8.3332,
      "step": 400
    },
    {
      "epoch": 0.04694394892498357,
      "grad_norm": 5.612818241119385,
      "learning_rate": 4.6363209760675744e-06,
      "loss": 8.1261,
      "step": 500
    },
    {
      "epoch": 0.05633273870998028,
      "grad_norm": 4.705409526824951,
      "learning_rate": 5.574847489441577e-06,
      "loss": 8.0697,
      "step": 600
    },
    {
      "epoch": 0.06572152849497699,
      "grad_norm": 4.337332725524902,
      "learning_rate": 6.51337400281558e-06,
      "loss": 8.0298,
      "step": 700
    },
    {
      "epoch": 0.0751103182799737,
      "grad_norm": 3.6314213275909424,
      "learning_rate": 7.451900516189583e-06,
      "loss": 8.033,
      "step": 800
    },
    {
      "epoch": 0.08449910806497042,
      "grad_norm": 3.4845075607299805,
      "learning_rate": 8.390427029563585e-06,
      "loss": 7.9858,
      "step": 900
    },
    {
      "epoch": 0.09388789784996714,
      "grad_norm": 5.188210487365723,
      "learning_rate": 9.328953542937589e-06,
      "loss": 8.012,
      "step": 1000
    },
    {
      "epoch": 0.10327668763496385,
      "grad_norm": 3.0830442905426025,
      "learning_rate": 1.0267480056311592e-05,
      "loss": 7.9745,
      "step": 1100
    },
    {
      "epoch": 0.11266547741996057,
      "grad_norm": 3.4729278087615967,
      "learning_rate": 1.1206006569685594e-05,
      "loss": 8.0091,
      "step": 1200
    },
    {
      "epoch": 0.12205426720495728,
      "grad_norm": 2.329235076904297,
      "learning_rate": 1.2144533083059597e-05,
      "loss": 8.0221,
      "step": 1300
    },
    {
      "epoch": 0.13144305698995398,
      "grad_norm": 2.7225279808044434,
      "learning_rate": 1.3083059596433601e-05,
      "loss": 7.9583,
      "step": 1400
    },
    {
      "epoch": 0.1408318467749507,
      "grad_norm": 2.012805938720703,
      "learning_rate": 1.4021586109807603e-05,
      "loss": 8.0031,
      "step": 1500
    },
    {
      "epoch": 0.1502206365599474,
      "grad_norm": 2.9397523403167725,
      "learning_rate": 1.4960112623181606e-05,
      "loss": 7.9985,
      "step": 1600
    },
    {
      "epoch": 0.15960942634494413,
      "grad_norm": 2.356337308883667,
      "learning_rate": 1.589863913655561e-05,
      "loss": 7.9647,
      "step": 1700
    },
    {
      "epoch": 0.16899821612994084,
      "grad_norm": 2.6846818923950195,
      "learning_rate": 1.6837165649929613e-05,
      "loss": 7.9857,
      "step": 1800
    },
    {
      "epoch": 0.17838700591493756,
      "grad_norm": 2.0188565254211426,
      "learning_rate": 1.7775692163303613e-05,
      "loss": 7.9806,
      "step": 1900
    },
    {
      "epoch": 0.18777579569993427,
      "grad_norm": 4.030488014221191,
      "learning_rate": 1.8714218676677617e-05,
      "loss": 7.9761,
      "step": 2000
    },
    {
      "epoch": 0.197164585484931,
      "grad_norm": 4.183101654052734,
      "learning_rate": 1.965274519005162e-05,
      "loss": 7.9696,
      "step": 2100
    },
    {
      "epoch": 0.2065533752699277,
      "grad_norm": 1.4769889116287231,
      "learning_rate": 1.9934275728965626e-05,
      "loss": 8.0014,
      "step": 2200
    },
    {
      "epoch": 0.21594216505492442,
      "grad_norm": 2.1914358139038086,
      "learning_rate": 1.9829951489228525e-05,
      "loss": 7.9546,
      "step": 2300
    },
    {
      "epoch": 0.22533095483992113,
      "grad_norm": 22.55516815185547,
      "learning_rate": 1.972562724949142e-05,
      "loss": 7.9874,
      "step": 2400
    },
    {
      "epoch": 0.23471974462491785,
      "grad_norm": 1.635116457939148,
      "learning_rate": 1.962130300975432e-05,
      "loss": 7.9846,
      "step": 2500
    },
    {
      "epoch": 0.24410853440991456,
      "grad_norm": 5.707275390625,
      "learning_rate": 1.9516978770017215e-05,
      "loss": 7.9664,
      "step": 2600
    },
    {
      "epoch": 0.2534973241949113,
      "grad_norm": 4.194604396820068,
      "learning_rate": 1.9412654530280113e-05,
      "loss": 7.9725,
      "step": 2700
    },
    {
      "epoch": 0.26288611397990796,
      "grad_norm": 2.0074055194854736,
      "learning_rate": 1.930833029054301e-05,
      "loss": 7.9419,
      "step": 2800
    },
    {
      "epoch": 0.2722749037649047,
      "grad_norm": 26.4300479888916,
      "learning_rate": 1.9204006050805904e-05,
      "loss": 7.9786,
      "step": 2900
    },
    {
      "epoch": 0.2816636935499014,
      "grad_norm": 2.5870931148529053,
      "learning_rate": 1.9099681811068803e-05,
      "loss": 7.9479,
      "step": 3000
    },
    {
      "epoch": 0.29105248333489814,
      "grad_norm": 1.6209933757781982,
      "learning_rate": 1.8995357571331702e-05,
      "loss": 7.9526,
      "step": 3100
    },
    {
      "epoch": 0.3004412731198948,
      "grad_norm": 19.398080825805664,
      "learning_rate": 1.8891033331594598e-05,
      "loss": 7.9613,
      "step": 3200
    },
    {
      "epoch": 0.30983006290489157,
      "grad_norm": 2.124729871749878,
      "learning_rate": 1.8786709091857496e-05,
      "loss": 7.9994,
      "step": 3300
    },
    {
      "epoch": 0.31921885268988826,
      "grad_norm": 2.701019763946533,
      "learning_rate": 1.8682384852120392e-05,
      "loss": 7.9464,
      "step": 3400
    },
    {
      "epoch": 0.328607642474885,
      "grad_norm": 1.944600224494934,
      "learning_rate": 1.8578060612383287e-05,
      "loss": 7.9429,
      "step": 3500
    },
    {
      "epoch": 0.3379964322598817,
      "grad_norm": 41.85493087768555,
      "learning_rate": 1.8473736372646186e-05,
      "loss": 7.9539,
      "step": 3600
    },
    {
      "epoch": 0.34738522204487843,
      "grad_norm": 2.024019479751587,
      "learning_rate": 1.8369412132909085e-05,
      "loss": 7.9699,
      "step": 3700
    },
    {
      "epoch": 0.3567740118298751,
      "grad_norm": 2.2833781242370605,
      "learning_rate": 1.826508789317198e-05,
      "loss": 7.9144,
      "step": 3800
    },
    {
      "epoch": 0.36616280161487186,
      "grad_norm": 3.1666574478149414,
      "learning_rate": 1.8160763653434876e-05,
      "loss": 7.9424,
      "step": 3900
    },
    {
      "epoch": 0.37555159139986855,
      "grad_norm": 1.7259443998336792,
      "learning_rate": 1.8056439413697775e-05,
      "loss": 7.9361,
      "step": 4000
    },
    {
      "epoch": 0.3849403811848653,
      "grad_norm": 2.5588905811309814,
      "learning_rate": 1.795211517396067e-05,
      "loss": 7.9144,
      "step": 4100
    },
    {
      "epoch": 0.394329170969862,
      "grad_norm": 2.542963743209839,
      "learning_rate": 1.784779093422357e-05,
      "loss": 7.907,
      "step": 4200
    },
    {
      "epoch": 0.4037179607548587,
      "grad_norm": 2.755725622177124,
      "learning_rate": 1.7743466694486468e-05,
      "loss": 7.9049,
      "step": 4300
    },
    {
      "epoch": 0.4131067505398554,
      "grad_norm": 2.6067683696746826,
      "learning_rate": 1.7639142454749364e-05,
      "loss": 7.939,
      "step": 4400
    },
    {
      "epoch": 0.42249554032485215,
      "grad_norm": 2.614475965499878,
      "learning_rate": 1.753481821501226e-05,
      "loss": 7.9067,
      "step": 4500
    },
    {
      "epoch": 0.43188433010984884,
      "grad_norm": 2.172943353652954,
      "learning_rate": 1.7430493975275155e-05,
      "loss": 7.9149,
      "step": 4600
    },
    {
      "epoch": 0.4412731198948456,
      "grad_norm": 6.292716979980469,
      "learning_rate": 1.7326169735538053e-05,
      "loss": 7.9705,
      "step": 4700
    },
    {
      "epoch": 0.45066190967984227,
      "grad_norm": 2.595337152481079,
      "learning_rate": 1.7221845495800952e-05,
      "loss": 7.8992,
      "step": 4800
    },
    {
      "epoch": 0.460050699464839,
      "grad_norm": 5.529814720153809,
      "learning_rate": 1.7117521256063848e-05,
      "loss": 7.9077,
      "step": 4900
    },
    {
      "epoch": 0.4694394892498357,
      "grad_norm": 6.696155548095703,
      "learning_rate": 1.7013197016326747e-05,
      "loss": 7.8992,
      "step": 5000
    },
    {
      "epoch": 0.4694394892498357,
      "eval_loss": 7.916718006134033,
      "eval_runtime": 334.3618,
      "eval_samples_per_second": 1019.336,
      "eval_steps_per_second": 7.964,
      "step": 5000
    },
    {
      "epoch": 0.4788282790348324,
      "grad_norm": 26.500988006591797,
      "learning_rate": 1.6908872776589642e-05,
      "loss": 7.914,
      "step": 5100
    },
    {
      "epoch": 0.4882170688198291,
      "grad_norm": 2.454939126968384,
      "learning_rate": 1.6804548536852537e-05,
      "loss": 7.8913,
      "step": 5200
    },
    {
      "epoch": 0.4976058586048258,
      "grad_norm": 1.8935959339141846,
      "learning_rate": 1.6700224297115436e-05,
      "loss": 7.8999,
      "step": 5300
    },
    {
      "epoch": 0.5069946483898226,
      "grad_norm": 2.2066667079925537,
      "learning_rate": 1.6595900057378335e-05,
      "loss": 7.8818,
      "step": 5400
    },
    {
      "epoch": 0.5163834381748192,
      "grad_norm": 2.7672908306121826,
      "learning_rate": 1.649157581764123e-05,
      "loss": 7.9383,
      "step": 5500
    },
    {
      "epoch": 0.5257722279598159,
      "grad_norm": 4.411477088928223,
      "learning_rate": 1.6387251577904126e-05,
      "loss": 7.9094,
      "step": 5600
    },
    {
      "epoch": 0.5351610177448127,
      "grad_norm": 50.536991119384766,
      "learning_rate": 1.6282927338167025e-05,
      "loss": 7.8986,
      "step": 5700
    },
    {
      "epoch": 0.5445498075298094,
      "grad_norm": 2.9657583236694336,
      "learning_rate": 1.617860309842992e-05,
      "loss": 7.9015,
      "step": 5800
    },
    {
      "epoch": 0.5539385973148061,
      "grad_norm": 1.910575270652771,
      "learning_rate": 1.607427885869282e-05,
      "loss": 7.9059,
      "step": 5900
    },
    {
      "epoch": 0.5633273870998028,
      "grad_norm": 3.9665298461914062,
      "learning_rate": 1.5969954618955715e-05,
      "loss": 7.8524,
      "step": 6000
    },
    {
      "epoch": 0.5727161768847996,
      "grad_norm": 2.0286688804626465,
      "learning_rate": 1.5865630379218614e-05,
      "loss": 7.8788,
      "step": 6100
    },
    {
      "epoch": 0.5821049666697963,
      "grad_norm": 3.200676202774048,
      "learning_rate": 1.576130613948151e-05,
      "loss": 7.8712,
      "step": 6200
    },
    {
      "epoch": 0.591493756454793,
      "grad_norm": 2.0278351306915283,
      "learning_rate": 1.5656981899744408e-05,
      "loss": 7.8967,
      "step": 6300
    },
    {
      "epoch": 0.6008825462397896,
      "grad_norm": 3.4500420093536377,
      "learning_rate": 1.5553700902404677e-05,
      "loss": 7.8677,
      "step": 6400
    },
    {
      "epoch": 0.6102713360247864,
      "grad_norm": 2.8257575035095215,
      "learning_rate": 1.5450419905064945e-05,
      "loss": 7.9132,
      "step": 6500
    },
    {
      "epoch": 0.6196601258097831,
      "grad_norm": 2.537797212600708,
      "learning_rate": 1.534609566532784e-05,
      "loss": 7.853,
      "step": 6600
    },
    {
      "epoch": 0.6290489155947798,
      "grad_norm": 3.010673999786377,
      "learning_rate": 1.5241771425590736e-05,
      "loss": 7.8968,
      "step": 6700
    },
    {
      "epoch": 0.6384377053797765,
      "grad_norm": 2.7398829460144043,
      "learning_rate": 1.5137447185853635e-05,
      "loss": 7.8656,
      "step": 6800
    },
    {
      "epoch": 0.6478264951647733,
      "grad_norm": 4.402348518371582,
      "learning_rate": 1.5033122946116532e-05,
      "loss": 7.8801,
      "step": 6900
    },
    {
      "epoch": 0.65721528494977,
      "grad_norm": 2.982344388961792,
      "learning_rate": 1.4928798706379428e-05,
      "loss": 7.8378,
      "step": 7000
    },
    {
      "epoch": 0.6666040747347667,
      "grad_norm": 12.262134552001953,
      "learning_rate": 1.4824474466642325e-05,
      "loss": 7.8554,
      "step": 7100
    },
    {
      "epoch": 0.6759928645197634,
      "grad_norm": 3.8007514476776123,
      "learning_rate": 1.4720150226905224e-05,
      "loss": 7.8305,
      "step": 7200
    },
    {
      "epoch": 0.6853816543047602,
      "grad_norm": 3.8391048908233643,
      "learning_rate": 1.461582598716812e-05,
      "loss": 7.8613,
      "step": 7300
    },
    {
      "epoch": 0.6947704440897569,
      "grad_norm": 3.107123374938965,
      "learning_rate": 1.4511501747431017e-05,
      "loss": 7.8554,
      "step": 7400
    },
    {
      "epoch": 0.7041592338747535,
      "grad_norm": 2.5167956352233887,
      "learning_rate": 1.4407177507693915e-05,
      "loss": 7.8653,
      "step": 7500
    },
    {
      "epoch": 0.7135480236597502,
      "grad_norm": 5.4338765144348145,
      "learning_rate": 1.430285326795681e-05,
      "loss": 7.8387,
      "step": 7600
    },
    {
      "epoch": 0.7229368134447469,
      "grad_norm": 3.295238733291626,
      "learning_rate": 1.4198529028219708e-05,
      "loss": 7.8513,
      "step": 7700
    },
    {
      "epoch": 0.7323256032297437,
      "grad_norm": 3.02062726020813,
      "learning_rate": 1.4094204788482607e-05,
      "loss": 7.8496,
      "step": 7800
    },
    {
      "epoch": 0.7417143930147404,
      "grad_norm": 2.2482168674468994,
      "learning_rate": 1.3989880548745502e-05,
      "loss": 7.8276,
      "step": 7900
    },
    {
      "epoch": 0.7511031827997371,
      "grad_norm": 3.394895315170288,
      "learning_rate": 1.38855563090084e-05,
      "loss": 7.8353,
      "step": 8000
    },
    {
      "epoch": 0.7604919725847338,
      "grad_norm": 5.990811824798584,
      "learning_rate": 1.3781232069271295e-05,
      "loss": 7.8103,
      "step": 8100
    },
    {
      "epoch": 0.7698807623697306,
      "grad_norm": 6.237292289733887,
      "learning_rate": 1.3676907829534194e-05,
      "loss": 7.8622,
      "step": 8200
    },
    {
      "epoch": 0.7792695521547273,
      "grad_norm": 3.848353147506714,
      "learning_rate": 1.3572583589797091e-05,
      "loss": 7.832,
      "step": 8300
    },
    {
      "epoch": 0.788658341939724,
      "grad_norm": 3.6994402408599854,
      "learning_rate": 1.3468259350059986e-05,
      "loss": 7.8349,
      "step": 8400
    },
    {
      "epoch": 0.7980471317247206,
      "grad_norm": 2.945556163787842,
      "learning_rate": 1.3363935110322885e-05,
      "loss": 7.855,
      "step": 8500
    },
    {
      "epoch": 0.8074359215097174,
      "grad_norm": 3.0218355655670166,
      "learning_rate": 1.3259610870585782e-05,
      "loss": 7.8316,
      "step": 8600
    },
    {
      "epoch": 0.8168247112947141,
      "grad_norm": 3.8162949085235596,
      "learning_rate": 1.3155286630848678e-05,
      "loss": 7.8066,
      "step": 8700
    },
    {
      "epoch": 0.8262135010797108,
      "grad_norm": 4.187964916229248,
      "learning_rate": 1.3050962391111577e-05,
      "loss": 7.8166,
      "step": 8800
    },
    {
      "epoch": 0.8356022908647075,
      "grad_norm": 3.577139139175415,
      "learning_rate": 1.2946638151374474e-05,
      "loss": 7.8588,
      "step": 8900
    },
    {
      "epoch": 0.8449910806497043,
      "grad_norm": 2.923499345779419,
      "learning_rate": 1.284231391163737e-05,
      "loss": 7.8042,
      "step": 9000
    },
    {
      "epoch": 0.854379870434701,
      "grad_norm": 6.15308952331543,
      "learning_rate": 1.2737989671900267e-05,
      "loss": 7.8431,
      "step": 9100
    },
    {
      "epoch": 0.8637686602196977,
      "grad_norm": 5.1844482421875,
      "learning_rate": 1.2633665432163165e-05,
      "loss": 7.7947,
      "step": 9200
    },
    {
      "epoch": 0.8731574500046944,
      "grad_norm": 3.3482980728149414,
      "learning_rate": 1.2530384434823432e-05,
      "loss": 7.8175,
      "step": 9300
    },
    {
      "epoch": 0.8825462397896912,
      "grad_norm": 3.3958215713500977,
      "learning_rate": 1.242606019508633e-05,
      "loss": 7.8299,
      "step": 9400
    },
    {
      "epoch": 0.8919350295746878,
      "grad_norm": 37.65146255493164,
      "learning_rate": 1.2321735955349225e-05,
      "loss": 7.8455,
      "step": 9500
    }
  ],
  "logging_steps": 100,
  "max_steps": 21302,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}