{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9988193624557261,
  "eval_steps": 500,
  "global_step": 423,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0023612750885478157,
      "grad_norm": 1.5131582373299473,
      "learning_rate": 2.3255813953488374e-07,
      "loss": 1.3255,
      "step": 1
    },
    {
      "epoch": 0.011806375442739079,
      "grad_norm": 1.4970470206944162,
      "learning_rate": 1.1627906976744188e-06,
      "loss": 1.3229,
      "step": 5
    },
    {
      "epoch": 0.023612750885478158,
      "grad_norm": 1.4534560068903173,
      "learning_rate": 2.3255813953488376e-06,
      "loss": 1.3249,
      "step": 10
    },
    {
      "epoch": 0.03541912632821724,
      "grad_norm": 1.3529390744329275,
      "learning_rate": 3.4883720930232564e-06,
      "loss": 1.3105,
      "step": 15
    },
    {
      "epoch": 0.047225501770956316,
      "grad_norm": 1.1377914835607748,
      "learning_rate": 4.651162790697675e-06,
      "loss": 1.2795,
      "step": 20
    },
    {
      "epoch": 0.0590318772136954,
      "grad_norm": 0.9300447218970413,
      "learning_rate": 5.8139534883720935e-06,
      "loss": 1.2542,
      "step": 25
    },
    {
      "epoch": 0.07083825265643448,
      "grad_norm": 0.7033484136291787,
      "learning_rate": 6.976744186046513e-06,
      "loss": 1.2254,
      "step": 30
    },
    {
      "epoch": 0.08264462809917356,
      "grad_norm": 0.5519511550883764,
      "learning_rate": 8.139534883720931e-06,
      "loss": 1.1956,
      "step": 35
    },
    {
      "epoch": 0.09445100354191263,
      "grad_norm": 0.530461549075621,
      "learning_rate": 9.30232558139535e-06,
      "loss": 1.1609,
      "step": 40
    },
    {
      "epoch": 0.10625737898465171,
      "grad_norm": 0.4882723618310303,
      "learning_rate": 9.999316524962347e-06,
      "loss": 1.1353,
      "step": 45
    },
    {
      "epoch": 0.1180637544273908,
      "grad_norm": 0.43070884824119315,
      "learning_rate": 9.991629576543164e-06,
      "loss": 1.1108,
      "step": 50
    },
    {
      "epoch": 0.12987012987012986,
      "grad_norm": 0.4326223460490506,
      "learning_rate": 9.975414512725058e-06,
      "loss": 1.0912,
      "step": 55
    },
    {
      "epoch": 0.14167650531286896,
      "grad_norm": 0.3990410735697587,
      "learning_rate": 9.95069903667256e-06,
      "loss": 1.0684,
      "step": 60
    },
    {
      "epoch": 0.15348288075560804,
      "grad_norm": 0.4102324061429566,
      "learning_rate": 9.917525374361913e-06,
      "loss": 1.0513,
      "step": 65
    },
    {
      "epoch": 0.1652892561983471,
      "grad_norm": 0.4553698218636962,
      "learning_rate": 9.8759502024387e-06,
      "loss": 1.0205,
      "step": 70
    },
    {
      "epoch": 0.1770956316410862,
      "grad_norm": 0.4487232032461124,
      "learning_rate": 9.826044551386743e-06,
      "loss": 0.9933,
      "step": 75
    },
    {
      "epoch": 0.18890200708382526,
      "grad_norm": 0.37710863024094676,
      "learning_rate": 9.767893684173722e-06,
      "loss": 0.9569,
      "step": 80
    },
    {
      "epoch": 0.20070838252656434,
      "grad_norm": 0.29780121644785873,
      "learning_rate": 9.701596950580807e-06,
      "loss": 0.944,
      "step": 85
    },
    {
      "epoch": 0.21251475796930341,
      "grad_norm": 0.2779699178964329,
      "learning_rate": 9.627267617465243e-06,
      "loss": 0.9348,
      "step": 90
    },
    {
      "epoch": 0.2243211334120425,
      "grad_norm": 0.25856375372275114,
      "learning_rate": 9.545032675245814e-06,
      "loss": 0.931,
      "step": 95
    },
    {
      "epoch": 0.2361275088547816,
      "grad_norm": 0.2613892946414014,
      "learning_rate": 9.45503262094184e-06,
      "loss": 0.9177,
      "step": 100
    },
    {
      "epoch": 0.24793388429752067,
      "grad_norm": 0.2354999119122035,
      "learning_rate": 9.357421218136387e-06,
      "loss": 0.9148,
      "step": 105
    },
    {
      "epoch": 0.2597402597402597,
      "grad_norm": 0.2162870999711504,
      "learning_rate": 9.252365234273754e-06,
      "loss": 0.9164,
      "step": 110
    },
    {
      "epoch": 0.2715466351829988,
      "grad_norm": 0.22180996969883549,
      "learning_rate": 9.140044155740102e-06,
      "loss": 0.9011,
      "step": 115
    },
    {
      "epoch": 0.2833530106257379,
      "grad_norm": 0.22437103522632068,
      "learning_rate": 9.02064988121396e-06,
      "loss": 0.9006,
      "step": 120
    },
    {
      "epoch": 0.29515938606847697,
      "grad_norm": 0.21463636431913852,
      "learning_rate": 8.894386393810563e-06,
      "loss": 0.8936,
      "step": 125
    },
    {
      "epoch": 0.3069657615112161,
      "grad_norm": 0.21659671484135407,
      "learning_rate": 8.761469412580126e-06,
      "loss": 0.892,
      "step": 130
    },
    {
      "epoch": 0.3187721369539551,
      "grad_norm": 0.22355054167698388,
      "learning_rate": 8.622126023955446e-06,
      "loss": 0.892,
      "step": 135
    },
    {
      "epoch": 0.3305785123966942,
      "grad_norm": 0.21653458201632308,
      "learning_rate": 8.476594293778561e-06,
      "loss": 0.8925,
      "step": 140
    },
    {
      "epoch": 0.34238488783943327,
      "grad_norm": 0.222501084583819,
      "learning_rate": 8.325122860569241e-06,
      "loss": 0.8864,
      "step": 145
    },
    {
      "epoch": 0.3541912632821724,
      "grad_norm": 0.21898064700237985,
      "learning_rate": 8.167970510730254e-06,
      "loss": 0.8849,
      "step": 150
    },
    {
      "epoch": 0.3659976387249115,
      "grad_norm": 0.22115057529251225,
      "learning_rate": 8.005405736415127e-06,
      "loss": 0.8815,
      "step": 155
    },
    {
      "epoch": 0.3778040141676505,
      "grad_norm": 0.21778385690198585,
      "learning_rate": 7.837706276813819e-06,
      "loss": 0.8806,
      "step": 160
    },
    {
      "epoch": 0.38961038961038963,
      "grad_norm": 0.2293476838871522,
      "learning_rate": 7.66515864363997e-06,
      "loss": 0.8781,
      "step": 165
    },
    {
      "epoch": 0.4014167650531287,
      "grad_norm": 0.23331956197796366,
      "learning_rate": 7.488057631630438e-06,
      "loss": 0.8742,
      "step": 170
    },
    {
      "epoch": 0.4132231404958678,
      "grad_norm": 0.21721254042866397,
      "learning_rate": 7.30670581489344e-06,
      "loss": 0.8805,
      "step": 175
    },
    {
      "epoch": 0.42502951593860683,
      "grad_norm": 0.23010261349577163,
      "learning_rate": 7.121413029965769e-06,
      "loss": 0.8742,
      "step": 180
    },
    {
      "epoch": 0.43683589138134593,
      "grad_norm": 0.2206787567833532,
      "learning_rate": 6.932495846462262e-06,
      "loss": 0.876,
      "step": 185
    },
    {
      "epoch": 0.448642266824085,
      "grad_norm": 0.2398992468500764,
      "learning_rate": 6.7402770262219234e-06,
      "loss": 0.8703,
      "step": 190
    },
    {
      "epoch": 0.4604486422668241,
      "grad_norm": 0.2448460311968614,
      "learning_rate": 6.545084971874738e-06,
      "loss": 0.873,
      "step": 195
    },
    {
      "epoch": 0.4722550177095632,
      "grad_norm": 0.2612008536174653,
      "learning_rate": 6.34725316577129e-06,
      "loss": 0.8746,
      "step": 200
    },
    {
      "epoch": 0.48406139315230223,
      "grad_norm": 0.24693316413096483,
      "learning_rate": 6.147119600233758e-06,
      "loss": 0.8736,
      "step": 205
    },
    {
      "epoch": 0.49586776859504134,
      "grad_norm": 0.24534026805051296,
      "learning_rate": 5.945026200101702e-06,
      "loss": 0.8652,
      "step": 210
    },
    {
      "epoch": 0.5076741440377804,
      "grad_norm": 0.23005356270231522,
      "learning_rate": 5.74131823855921e-06,
      "loss": 0.8624,
      "step": 215
    },
    {
      "epoch": 0.5194805194805194,
      "grad_norm": 0.24466967197626655,
      "learning_rate": 5.53634374724146e-06,
      "loss": 0.8639,
      "step": 220
    },
    {
      "epoch": 0.5312868949232585,
      "grad_norm": 0.24160067474761546,
      "learning_rate": 5.3304529216284974e-06,
      "loss": 0.8632,
      "step": 225
    },
    {
      "epoch": 0.5430932703659976,
      "grad_norm": 0.26220069503373417,
      "learning_rate": 5.123997522742151e-06,
      "loss": 0.8639,
      "step": 230
    },
    {
      "epoch": 0.5548996458087367,
      "grad_norm": 0.264066001522196,
      "learning_rate": 4.917330276168208e-06,
      "loss": 0.8623,
      "step": 235
    },
    {
      "epoch": 0.5667060212514758,
      "grad_norm": 0.24428345928123874,
      "learning_rate": 4.710804269430681e-06,
      "loss": 0.8692,
      "step": 240
    },
    {
      "epoch": 0.5785123966942148,
      "grad_norm": 0.24362157236851636,
      "learning_rate": 4.504772348747687e-06,
      "loss": 0.8617,
      "step": 245
    },
    {
      "epoch": 0.5903187721369539,
      "grad_norm": 0.2605786039459921,
      "learning_rate": 4.299586516199611e-06,
      "loss": 0.8631,
      "step": 250
    },
    {
      "epoch": 0.602125147579693,
      "grad_norm": 0.24469411057849033,
      "learning_rate": 4.0955973283394525e-06,
      "loss": 0.8519,
      "step": 255
    },
    {
      "epoch": 0.6139315230224321,
      "grad_norm": 0.24265909990188317,
      "learning_rate": 3.893153297272829e-06,
      "loss": 0.858,
      "step": 260
    },
    {
      "epoch": 0.6257378984651711,
      "grad_norm": 0.2431981393362141,
      "learning_rate": 3.6926002952309015e-06,
      "loss": 0.8574,
      "step": 265
    },
    {
      "epoch": 0.6375442739079102,
      "grad_norm": 0.25137244252341084,
      "learning_rate": 3.4942809636534637e-06,
      "loss": 0.8584,
      "step": 270
    },
    {
      "epoch": 0.6493506493506493,
      "grad_norm": 0.2520911165703089,
      "learning_rate": 3.298534127791785e-06,
      "loss": 0.8578,
      "step": 275
    },
    {
      "epoch": 0.6611570247933884,
      "grad_norm": 0.2651721936087408,
      "learning_rate": 3.105694217831361e-06,
      "loss": 0.8589,
      "step": 280
    },
    {
      "epoch": 0.6729634002361276,
      "grad_norm": 0.2546800394311146,
      "learning_rate": 2.9160906975235493e-06,
      "loss": 0.8523,
      "step": 285
    },
    {
      "epoch": 0.6847697756788665,
      "grad_norm": 0.25316819030742643,
      "learning_rate": 2.7300475013022666e-06,
      "loss": 0.8552,
      "step": 290
    },
    {
      "epoch": 0.6965761511216056,
      "grad_norm": 0.2509477836308168,
      "learning_rate": 2.5478824808474613e-06,
      "loss": 0.8574,
      "step": 295
    },
    {
      "epoch": 0.7083825265643447,
      "grad_norm": 0.22985580266469613,
      "learning_rate": 2.3699068620408305e-06,
      "loss": 0.8525,
      "step": 300
    },
    {
      "epoch": 0.7201889020070839,
      "grad_norm": 0.24633435787531885,
      "learning_rate": 2.1964247132416373e-06,
      "loss": 0.8541,
      "step": 305
    },
    {
      "epoch": 0.731995277449823,
      "grad_norm": 0.2550223994617769,
      "learning_rate": 2.027732425791011e-06,
      "loss": 0.8575,
      "step": 310
    },
    {
      "epoch": 0.743801652892562,
      "grad_norm": 0.250598594634277,
      "learning_rate": 1.864118207632315e-06,
      "loss": 0.8584,
      "step": 315
    },
    {
      "epoch": 0.755608028335301,
      "grad_norm": 0.2547611444118788,
      "learning_rate": 1.7058615909127102e-06,
      "loss": 0.8578,
      "step": 320
    },
    {
      "epoch": 0.7674144037780402,
      "grad_norm": 0.2551344265566289,
      "learning_rate": 1.5532329544071712e-06,
      "loss": 0.8568,
      "step": 325
    },
    {
      "epoch": 0.7792207792207793,
      "grad_norm": 0.24284035631227585,
      "learning_rate": 1.406493061580881e-06,
      "loss": 0.854,
      "step": 330
    },
    {
      "epoch": 0.7910271546635183,
      "grad_norm": 0.2454427828284572,
      "learning_rate": 1.2658926150792321e-06,
      "loss": 0.8543,
      "step": 335
    },
    {
      "epoch": 0.8028335301062574,
      "grad_norm": 0.24171894401645216,
      "learning_rate": 1.1316718284065536e-06,
      "loss": 0.8601,
      "step": 340
    },
    {
      "epoch": 0.8146399055489965,
      "grad_norm": 0.24890059165826273,
      "learning_rate": 1.0040600155253766e-06,
      "loss": 0.8588,
      "step": 345
    },
    {
      "epoch": 0.8264462809917356,
      "grad_norm": 0.24128541650834764,
      "learning_rate": 8.832751990773714e-07,
      "loss": 0.8547,
      "step": 350
    },
    {
      "epoch": 0.8382526564344747,
      "grad_norm": 0.25646382446616656,
      "learning_rate": 7.695237378953224e-07,
      "loss": 0.859,
      "step": 355
    },
    {
      "epoch": 0.8500590318772137,
      "grad_norm": 0.2460481416324142,
      "learning_rate": 6.629999744425236e-07,
      "loss": 0.8567,
      "step": 360
    },
    {
      "epoch": 0.8618654073199528,
      "grad_norm": 0.24513983983677975,
      "learning_rate": 5.63885902781941e-07,
      "loss": 0.8596,
      "step": 365
    },
    {
      "epoch": 0.8736717827626919,
      "grad_norm": 0.2343335791217957,
      "learning_rate": 4.723508576424063e-07,
      "loss": 0.8552,
      "step": 370
    },
    {
      "epoch": 0.885478158205431,
      "grad_norm": 0.2519214484705661,
      "learning_rate": 3.885512251130763e-07,
      "loss": 0.8527,
      "step": 375
    },
    {
      "epoch": 0.89728453364817,
      "grad_norm": 0.2440125511079392,
      "learning_rate": 3.126301754604233e-07,
      "loss": 0.8548,
      "step": 380
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.2532464399771227,
      "learning_rate": 2.447174185242324e-07,
      "loss": 0.854,
      "step": 385
    },
    {
      "epoch": 0.9208972845336482,
      "grad_norm": 0.23622376914066623,
      "learning_rate": 1.849289821105199e-07,
      "loss": 0.8521,
      "step": 390
    },
    {
      "epoch": 0.9327036599763873,
      "grad_norm": 0.2444798272238538,
      "learning_rate": 1.333670137599713e-07,
      "loss": 0.8532,
      "step": 395
    },
    {
      "epoch": 0.9445100354191264,
      "grad_norm": 0.23429527809735437,
      "learning_rate": 9.011960623058202e-08,
      "loss": 0.8532,
      "step": 400
    },
    {
      "epoch": 0.9563164108618654,
      "grad_norm": 0.23623057232372727,
      "learning_rate": 5.526064699265754e-08,
      "loss": 0.8506,
      "step": 405
    },
    {
      "epoch": 0.9681227863046045,
      "grad_norm": 0.2482774375940229,
      "learning_rate": 2.884969199331178e-08,
      "loss": 0.8587,
      "step": 410
    },
    {
      "epoch": 0.9799291617473436,
      "grad_norm": 0.23526019800815218,
      "learning_rate": 1.0931863906127327e-08,
      "loss": 0.8558,
      "step": 415
    },
    {
      "epoch": 0.9917355371900827,
      "grad_norm": 0.24074172289610016,
      "learning_rate": 1.53777503982655e-09,
      "loss": 0.853,
      "step": 420
    },
    {
      "epoch": 0.9988193624557261,
      "eval_loss": 0.8673050403594971,
      "eval_runtime": 1.109,
      "eval_samples_per_second": 1.804,
      "eval_steps_per_second": 0.902,
      "step": 423
    },
    {
      "epoch": 0.9988193624557261,
      "step": 423,
      "total_flos": 1701364321222656.0,
      "train_loss": 0.0,
      "train_runtime": 0.0113,
      "train_samples_per_second": 2398604.87,
      "train_steps_per_second": 37460.213
    }
  ],
  "logging_steps": 5,
  "max_steps": 423,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1701364321222656.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}