{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.015181129855589502,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.795282463897376e-05,
      "eval_loss": 2.1576380729675293,
      "eval_runtime": 850.7278,
      "eval_samples_per_second": 13.042,
      "eval_steps_per_second": 6.521,
      "step": 1
    },
    {
      "epoch": 0.00018976412319486878,
      "grad_norm": 0.5731865763664246,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.654,
      "step": 5
    },
    {
      "epoch": 0.00037952824638973757,
      "grad_norm": 0.7176395058631897,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.8183,
      "step": 10
    },
    {
      "epoch": 0.0005692923695846063,
      "grad_norm": 1.1065971851348877,
      "learning_rate": 5e-05,
      "loss": 1.8083,
      "step": 15
    },
    {
      "epoch": 0.0007590564927794751,
      "grad_norm": 1.0144658088684082,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.6738,
      "step": 20
    },
    {
      "epoch": 0.0009488206159743439,
      "grad_norm": 0.9351977109909058,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.6931,
      "step": 25
    },
    {
      "epoch": 0.0011385847391692126,
      "grad_norm": 1.1281682252883911,
      "learning_rate": 0.0001,
      "loss": 1.4287,
      "step": 30
    },
    {
      "epoch": 0.0013283488623640814,
      "grad_norm": 1.6895772218704224,
      "learning_rate": 9.995494831023409e-05,
      "loss": 1.3096,
      "step": 35
    },
    {
      "epoch": 0.0015181129855589503,
      "grad_norm": 1.4577206373214722,
      "learning_rate": 9.981987442712633e-05,
      "loss": 1.3396,
      "step": 40
    },
    {
      "epoch": 0.001707877108753819,
      "grad_norm": 1.237876057624817,
      "learning_rate": 9.959502176294383e-05,
      "loss": 1.3612,
      "step": 45
    },
    {
      "epoch": 0.0018976412319486877,
      "grad_norm": 2.0654523372650146,
      "learning_rate": 9.928079551738543e-05,
      "loss": 1.4159,
      "step": 50
    },
    {
      "epoch": 0.0020874053551435566,
      "grad_norm": 0.9482754468917847,
      "learning_rate": 9.887776194738432e-05,
      "loss": 1.1775,
      "step": 55
    },
    {
      "epoch": 0.002277169478338425,
      "grad_norm": 0.6003905534744263,
      "learning_rate": 9.838664734667495e-05,
      "loss": 1.0262,
      "step": 60
    },
    {
      "epoch": 0.0024669336015332942,
      "grad_norm": 0.7832050919532776,
      "learning_rate": 9.780833673696254e-05,
      "loss": 0.9915,
      "step": 65
    },
    {
      "epoch": 0.002656697724728163,
      "grad_norm": 0.7753303050994873,
      "learning_rate": 9.714387227305422e-05,
      "loss": 1.1298,
      "step": 70
    },
    {
      "epoch": 0.0028464618479230315,
      "grad_norm": 0.8821681141853333,
      "learning_rate": 9.639445136482548e-05,
      "loss": 0.9965,
      "step": 75
    },
    {
      "epoch": 0.0030362259711179005,
      "grad_norm": 0.8993760347366333,
      "learning_rate": 9.55614245194068e-05,
      "loss": 0.9885,
      "step": 80
    },
    {
      "epoch": 0.003225990094312769,
      "grad_norm": 1.0164976119995117,
      "learning_rate": 9.464629290747842e-05,
      "loss": 1.0723,
      "step": 85
    },
    {
      "epoch": 0.003415754217507638,
      "grad_norm": 0.9889712929725647,
      "learning_rate": 9.365070565805941e-05,
      "loss": 1.1378,
      "step": 90
    },
    {
      "epoch": 0.003605518340702507,
      "grad_norm": 1.3623729944229126,
      "learning_rate": 9.257645688666556e-05,
      "loss": 1.2697,
      "step": 95
    },
    {
      "epoch": 0.0037952824638973755,
      "grad_norm": 1.5822207927703857,
      "learning_rate": 9.142548246219212e-05,
      "loss": 1.2019,
      "step": 100
    },
    {
      "epoch": 0.0037952824638973755,
      "eval_loss": 1.101567029953003,
      "eval_runtime": 857.1834,
      "eval_samples_per_second": 12.944,
      "eval_steps_per_second": 6.472,
      "step": 100
    },
    {
      "epoch": 0.0039850465870922445,
      "grad_norm": 0.7287427186965942,
      "learning_rate": 9.019985651834703e-05,
      "loss": 1.1496,
      "step": 105
    },
    {
      "epoch": 0.004174810710287113,
      "grad_norm": 0.6560399532318115,
      "learning_rate": 8.890178771592199e-05,
      "loss": 1.2194,
      "step": 110
    },
    {
      "epoch": 0.004364574833481982,
      "grad_norm": 0.6463301777839661,
      "learning_rate": 8.753361526263621e-05,
      "loss": 1.1142,
      "step": 115
    },
    {
      "epoch": 0.00455433895667685,
      "grad_norm": 0.6335498094558716,
      "learning_rate": 8.609780469772623e-05,
      "loss": 0.9229,
      "step": 120
    },
    {
      "epoch": 0.00474410307987172,
      "grad_norm": 0.7402055263519287,
      "learning_rate": 8.459694344887732e-05,
      "loss": 0.9781,
      "step": 125
    },
    {
      "epoch": 0.0049338672030665885,
      "grad_norm": 0.7810035943984985,
      "learning_rate": 8.303373616950408e-05,
      "loss": 1.0616,
      "step": 130
    },
    {
      "epoch": 0.005123631326261457,
      "grad_norm": 0.8350050449371338,
      "learning_rate": 8.141099986478212e-05,
      "loss": 0.9902,
      "step": 135
    },
    {
      "epoch": 0.005313395449456326,
      "grad_norm": 0.8246821761131287,
      "learning_rate": 7.973165881521434e-05,
      "loss": 1.1825,
      "step": 140
    },
    {
      "epoch": 0.005503159572651194,
      "grad_norm": 1.0053590536117554,
      "learning_rate": 7.799873930687978e-05,
      "loss": 1.1309,
      "step": 145
    },
    {
      "epoch": 0.005692923695846063,
      "grad_norm": 2.70648193359375,
      "learning_rate": 7.621536417786159e-05,
      "loss": 1.4593,
      "step": 150
    },
    {
      "epoch": 0.0058826878190409325,
      "grad_norm": 0.7757177948951721,
      "learning_rate": 7.438474719068173e-05,
      "loss": 0.9812,
      "step": 155
    },
    {
      "epoch": 0.006072451942235801,
      "grad_norm": 0.5764933228492737,
      "learning_rate": 7.251018724088367e-05,
      "loss": 0.9636,
      "step": 160
    },
    {
      "epoch": 0.00626221606543067,
      "grad_norm": 0.7440540790557861,
      "learning_rate": 7.059506241219965e-05,
      "loss": 0.9517,
      "step": 165
    },
    {
      "epoch": 0.006451980188625538,
      "grad_norm": 0.9800004959106445,
      "learning_rate": 6.864282388901544e-05,
      "loss": 1.108,
      "step": 170
    },
    {
      "epoch": 0.006641744311820407,
      "grad_norm": 0.8193339109420776,
      "learning_rate": 6.665698973710288e-05,
      "loss": 0.9969,
      "step": 175
    },
    {
      "epoch": 0.006831508435015276,
      "grad_norm": 0.813203752040863,
      "learning_rate": 6.464113856382752e-05,
      "loss": 0.8408,
      "step": 180
    },
    {
      "epoch": 0.007021272558210145,
      "grad_norm": 0.991565465927124,
      "learning_rate": 6.259890306925627e-05,
      "loss": 1.0614,
      "step": 185
    },
    {
      "epoch": 0.007211036681405014,
      "grad_norm": 0.8006114959716797,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 1.1613,
      "step": 190
    },
    {
      "epoch": 0.007400800804599882,
      "grad_norm": 1.1749229431152344,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 1.0541,
      "step": 195
    },
    {
      "epoch": 0.007590564927794751,
      "grad_norm": 2.0654520988464355,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 1.1676,
      "step": 200
    },
    {
      "epoch": 0.007590564927794751,
      "eval_loss": 1.0440938472747803,
      "eval_runtime": 854.169,
      "eval_samples_per_second": 12.989,
      "eval_steps_per_second": 6.495,
      "step": 200
    },
    {
      "epoch": 0.0077803290509896195,
      "grad_norm": 0.6320887804031372,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 1.2171,
      "step": 205
    },
    {
      "epoch": 0.007970093174184489,
      "grad_norm": 0.6037514209747314,
      "learning_rate": 5.212206015980742e-05,
      "loss": 0.9721,
      "step": 210
    },
    {
      "epoch": 0.008159857297379357,
      "grad_norm": 0.7819492816925049,
      "learning_rate": 5e-05,
      "loss": 1.1028,
      "step": 215
    },
    {
      "epoch": 0.008349621420574226,
      "grad_norm": 0.6581225991249084,
      "learning_rate": 4.78779398401926e-05,
      "loss": 0.9646,
      "step": 220
    },
    {
      "epoch": 0.008539385543769096,
      "grad_norm": 0.7874705195426941,
      "learning_rate": 4.575970377622456e-05,
      "loss": 0.9913,
      "step": 225
    },
    {
      "epoch": 0.008729149666963964,
      "grad_norm": 0.7567994594573975,
      "learning_rate": 4.364910901265606e-05,
      "loss": 0.873,
      "step": 230
    },
    {
      "epoch": 0.008918913790158833,
      "grad_norm": 0.7803477048873901,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 0.964,
      "step": 235
    },
    {
      "epoch": 0.0091086779133537,
      "grad_norm": 1.0606672763824463,
      "learning_rate": 3.94660365002137e-05,
      "loss": 1.0612,
      "step": 240
    },
    {
      "epoch": 0.00929844203654857,
      "grad_norm": 1.069953203201294,
      "learning_rate": 3.740109693074375e-05,
      "loss": 1.1362,
      "step": 245
    },
    {
      "epoch": 0.00948820615974344,
      "grad_norm": 1.8780826330184937,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 1.2513,
      "step": 250
    },
    {
      "epoch": 0.009677970282938307,
      "grad_norm": 0.6101130843162537,
      "learning_rate": 3.334301026289712e-05,
      "loss": 1.0985,
      "step": 255
    },
    {
      "epoch": 0.009867734406133177,
      "grad_norm": 0.8326043486595154,
      "learning_rate": 3.135717611098458e-05,
      "loss": 1.0019,
      "step": 260
    },
    {
      "epoch": 0.010057498529328045,
      "grad_norm": 0.6600733399391174,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 0.9358,
      "step": 265
    },
    {
      "epoch": 0.010247262652522914,
      "grad_norm": 0.6974927186965942,
      "learning_rate": 2.748981275911633e-05,
      "loss": 1.0073,
      "step": 270
    },
    {
      "epoch": 0.010437026775717782,
      "grad_norm": 0.7026144862174988,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 0.9925,
      "step": 275
    },
    {
      "epoch": 0.010626790898912651,
      "grad_norm": 0.8885721564292908,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 1.0314,
      "step": 280
    },
    {
      "epoch": 0.010816555022107521,
      "grad_norm": 0.6575035452842712,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 0.7637,
      "step": 285
    },
    {
      "epoch": 0.011006319145302389,
      "grad_norm": 1.0016722679138184,
      "learning_rate": 2.026834118478567e-05,
      "loss": 1.1063,
      "step": 290
    },
    {
      "epoch": 0.011196083268497258,
      "grad_norm": 1.0121612548828125,
      "learning_rate": 1.858900013521788e-05,
      "loss": 1.0149,
      "step": 295
    },
    {
      "epoch": 0.011385847391692126,
      "grad_norm": 1.9054632186889648,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 1.3082,
      "step": 300
    },
    {
      "epoch": 0.011385847391692126,
      "eval_loss": 1.0266152620315552,
      "eval_runtime": 855.0452,
      "eval_samples_per_second": 12.976,
      "eval_steps_per_second": 6.489,
      "step": 300
    },
    {
      "epoch": 0.011575611514886995,
      "grad_norm": 0.6057090759277344,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 1.2215,
      "step": 305
    },
    {
      "epoch": 0.011765375638081865,
      "grad_norm": 0.58408123254776,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 1.1013,
      "step": 310
    },
    {
      "epoch": 0.011955139761276733,
      "grad_norm": 0.6465745568275452,
      "learning_rate": 1.246638473736378e-05,
      "loss": 0.9197,
      "step": 315
    },
    {
      "epoch": 0.012144903884471602,
      "grad_norm": 0.5927044749259949,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 0.9358,
      "step": 320
    },
    {
      "epoch": 0.01233466800766647,
      "grad_norm": 0.6737649440765381,
      "learning_rate": 9.800143481652979e-06,
      "loss": 1.0297,
      "step": 325
    },
    {
      "epoch": 0.01252443213086134,
      "grad_norm": 0.8347842693328857,
      "learning_rate": 8.574517537807897e-06,
      "loss": 0.9338,
      "step": 330
    },
    {
      "epoch": 0.012714196254056209,
      "grad_norm": 0.8311460018157959,
      "learning_rate": 7.423543113334436e-06,
      "loss": 1.0809,
      "step": 335
    },
    {
      "epoch": 0.012903960377251077,
      "grad_norm": 0.7732884287834167,
      "learning_rate": 6.349294341940593e-06,
      "loss": 0.9445,
      "step": 340
    },
    {
      "epoch": 0.013093724500445946,
      "grad_norm": 0.8245271444320679,
      "learning_rate": 5.353707092521582e-06,
      "loss": 1.1543,
      "step": 345
    },
    {
      "epoch": 0.013283488623640814,
      "grad_norm": 2.3973090648651123,
      "learning_rate": 4.43857548059321e-06,
      "loss": 1.4494,
      "step": 350
    },
    {
      "epoch": 0.013473252746835683,
      "grad_norm": 0.7564066052436829,
      "learning_rate": 3.605548635174533e-06,
      "loss": 1.0761,
      "step": 355
    },
    {
      "epoch": 0.013663016870030553,
      "grad_norm": 0.7391504049301147,
      "learning_rate": 2.85612772694579e-06,
      "loss": 0.8724,
      "step": 360
    },
    {
      "epoch": 0.01385278099322542,
      "grad_norm": 0.6857224106788635,
      "learning_rate": 2.191663263037458e-06,
      "loss": 1.1109,
      "step": 365
    },
    {
      "epoch": 0.01404254511642029,
      "grad_norm": 0.7058850526809692,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 0.9582,
      "step": 370
    },
    {
      "epoch": 0.014232309239615158,
      "grad_norm": 0.6980537176132202,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 0.8472,
      "step": 375
    },
    {
      "epoch": 0.014422073362810027,
      "grad_norm": 0.6182519197463989,
      "learning_rate": 7.192044826145771e-07,
      "loss": 1.0134,
      "step": 380
    },
    {
      "epoch": 0.014611837486004895,
      "grad_norm": 0.7132819294929504,
      "learning_rate": 4.049782370561583e-07,
      "loss": 0.8478,
      "step": 385
    },
    {
      "epoch": 0.014801601609199765,
      "grad_norm": 1.1005048751831055,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 1.1334,
      "step": 390
    },
    {
      "epoch": 0.014991365732394634,
      "grad_norm": 1.1212615966796875,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 1.0598,
      "step": 395
    },
    {
      "epoch": 0.015181129855589502,
      "grad_norm": 1.638376235961914,
      "learning_rate": 0.0,
      "loss": 1.2034,
      "step": 400
    },
    {
      "epoch": 0.015181129855589502,
      "eval_loss": 1.020525574684143,
      "eval_runtime": 855.3462,
      "eval_samples_per_second": 12.971,
      "eval_steps_per_second": 6.486,
      "step": 400
    }
  ],
  "logging_steps": 5,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3038008752983245e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}