{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1362281822051937,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00034057045551298427,
      "eval_loss": 1.8361178636550903,
      "eval_runtime": 101.827,
      "eval_samples_per_second": 12.148,
      "eval_steps_per_second": 6.079,
      "step": 1
    },
    {
      "epoch": 0.0017028522775649213,
      "grad_norm": 0.41594547033309937,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.0333,
      "step": 5
    },
    {
      "epoch": 0.0034057045551298426,
      "grad_norm": 0.6465234160423279,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.0047,
      "step": 10
    },
    {
      "epoch": 0.005108556832694764,
      "grad_norm": 0.8802253603935242,
      "learning_rate": 5e-05,
      "loss": 1.1382,
      "step": 15
    },
    {
      "epoch": 0.006811409110259685,
      "grad_norm": 0.41058072447776794,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.1082,
      "step": 20
    },
    {
      "epoch": 0.008514261387824606,
      "grad_norm": 0.5125563144683838,
      "learning_rate": 8.333333333333334e-05,
      "loss": 0.9712,
      "step": 25
    },
    {
      "epoch": 0.010217113665389528,
      "grad_norm": 0.751390278339386,
      "learning_rate": 0.0001,
      "loss": 1.0366,
      "step": 30
    },
    {
      "epoch": 0.011919965942954448,
      "grad_norm": 0.7571478486061096,
      "learning_rate": 9.995494831023409e-05,
      "loss": 1.0073,
      "step": 35
    },
    {
      "epoch": 0.01362281822051937,
      "grad_norm": 0.6469959616661072,
      "learning_rate": 9.981987442712633e-05,
      "loss": 0.9567,
      "step": 40
    },
    {
      "epoch": 0.01532567049808429,
      "grad_norm": 0.8713700771331787,
      "learning_rate": 9.959502176294383e-05,
      "loss": 1.1128,
      "step": 45
    },
    {
      "epoch": 0.017028522775649212,
      "grad_norm": 1.3194971084594727,
      "learning_rate": 9.928079551738543e-05,
      "loss": 1.1412,
      "step": 50
    },
    {
      "epoch": 0.018731375053214133,
      "grad_norm": 0.25489541888237,
      "learning_rate": 9.887776194738432e-05,
      "loss": 0.776,
      "step": 55
    },
    {
      "epoch": 0.020434227330779056,
      "grad_norm": 0.3596874475479126,
      "learning_rate": 9.838664734667495e-05,
      "loss": 0.8018,
      "step": 60
    },
    {
      "epoch": 0.022137079608343976,
      "grad_norm": 0.35467663407325745,
      "learning_rate": 9.780833673696254e-05,
      "loss": 0.8187,
      "step": 65
    },
    {
      "epoch": 0.023839931885908897,
      "grad_norm": 0.36793845891952515,
      "learning_rate": 9.714387227305422e-05,
      "loss": 0.8099,
      "step": 70
    },
    {
      "epoch": 0.02554278416347382,
      "grad_norm": 0.44260016083717346,
      "learning_rate": 9.639445136482548e-05,
      "loss": 0.7714,
      "step": 75
    },
    {
      "epoch": 0.02724563644103874,
      "grad_norm": 0.6863613128662109,
      "learning_rate": 9.55614245194068e-05,
      "loss": 0.8211,
      "step": 80
    },
    {
      "epoch": 0.02894848871860366,
      "grad_norm": 0.6633279323577881,
      "learning_rate": 9.464629290747842e-05,
      "loss": 0.8158,
      "step": 85
    },
    {
      "epoch": 0.03065134099616858,
      "grad_norm": 1.0327296257019043,
      "learning_rate": 9.365070565805941e-05,
      "loss": 0.9717,
      "step": 90
    },
    {
      "epoch": 0.032354193273733504,
      "grad_norm": 0.7854035496711731,
      "learning_rate": 9.257645688666556e-05,
      "loss": 0.9801,
      "step": 95
    },
    {
      "epoch": 0.034057045551298425,
      "grad_norm": 1.9543837308883667,
      "learning_rate": 9.142548246219212e-05,
      "loss": 1.2958,
      "step": 100
    },
    {
      "epoch": 0.034057045551298425,
      "eval_loss": 0.8909078240394592,
      "eval_runtime": 103.3047,
      "eval_samples_per_second": 11.974,
      "eval_steps_per_second": 5.992,
      "step": 100
    },
    {
      "epoch": 0.035759897828863345,
      "grad_norm": 0.23156222701072693,
      "learning_rate": 9.019985651834703e-05,
      "loss": 0.6506,
      "step": 105
    },
    {
      "epoch": 0.037462750106428265,
      "grad_norm": 0.3277677297592163,
      "learning_rate": 8.890178771592199e-05,
      "loss": 0.8633,
      "step": 110
    },
    {
      "epoch": 0.039165602383993185,
      "grad_norm": 0.33476242423057556,
      "learning_rate": 8.753361526263621e-05,
      "loss": 0.8823,
      "step": 115
    },
    {
      "epoch": 0.04086845466155811,
      "grad_norm": 0.36144304275512695,
      "learning_rate": 8.609780469772623e-05,
      "loss": 0.7879,
      "step": 120
    },
    {
      "epoch": 0.04257130693912303,
      "grad_norm": 0.3987506926059723,
      "learning_rate": 8.459694344887732e-05,
      "loss": 0.7091,
      "step": 125
    },
    {
      "epoch": 0.04427415921668795,
      "grad_norm": 0.5698655843734741,
      "learning_rate": 8.303373616950408e-05,
      "loss": 0.82,
      "step": 130
    },
    {
      "epoch": 0.04597701149425287,
      "grad_norm": 0.805975615978241,
      "learning_rate": 8.141099986478212e-05,
      "loss": 0.8761,
      "step": 135
    },
    {
      "epoch": 0.04767986377181779,
      "grad_norm": 1.0833746194839478,
      "learning_rate": 7.973165881521434e-05,
      "loss": 1.0889,
      "step": 140
    },
    {
      "epoch": 0.04938271604938271,
      "grad_norm": 0.7163301110267639,
      "learning_rate": 7.799873930687978e-05,
      "loss": 0.94,
      "step": 145
    },
    {
      "epoch": 0.05108556832694764,
      "grad_norm": 2.4993340969085693,
      "learning_rate": 7.621536417786159e-05,
      "loss": 1.1311,
      "step": 150
    },
    {
      "epoch": 0.05278842060451256,
      "grad_norm": 0.2643802762031555,
      "learning_rate": 7.438474719068173e-05,
      "loss": 0.7175,
      "step": 155
    },
    {
      "epoch": 0.05449127288207748,
      "grad_norm": 0.3255314826965332,
      "learning_rate": 7.251018724088367e-05,
      "loss": 0.7516,
      "step": 160
    },
    {
      "epoch": 0.0561941251596424,
      "grad_norm": 0.5198604464530945,
      "learning_rate": 7.059506241219965e-05,
      "loss": 0.767,
      "step": 165
    },
    {
      "epoch": 0.05789697743720732,
      "grad_norm": 0.477650910615921,
      "learning_rate": 6.864282388901544e-05,
      "loss": 0.7519,
      "step": 170
    },
    {
      "epoch": 0.05959982971477224,
      "grad_norm": 0.48475128412246704,
      "learning_rate": 6.665698973710288e-05,
      "loss": 0.7067,
      "step": 175
    },
    {
      "epoch": 0.06130268199233716,
      "grad_norm": 0.7966631650924683,
      "learning_rate": 6.464113856382752e-05,
      "loss": 0.8934,
      "step": 180
    },
    {
      "epoch": 0.06300553426990209,
      "grad_norm": 0.8111737966537476,
      "learning_rate": 6.259890306925627e-05,
      "loss": 0.7036,
      "step": 185
    },
    {
      "epoch": 0.06470838654746701,
      "grad_norm": 0.6757014393806458,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 0.7597,
      "step": 190
    },
    {
      "epoch": 0.06641123882503193,
      "grad_norm": 0.7240155935287476,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 0.7963,
      "step": 195
    },
    {
      "epoch": 0.06811409110259685,
      "grad_norm": 2.1751976013183594,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 1.195,
      "step": 200
    },
    {
      "epoch": 0.06811409110259685,
      "eval_loss": 0.832435131072998,
      "eval_runtime": 103.3366,
      "eval_samples_per_second": 11.971,
      "eval_steps_per_second": 5.99,
      "step": 200
    },
    {
      "epoch": 0.06981694338016177,
      "grad_norm": 0.2670830488204956,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 0.8186,
      "step": 205
    },
    {
      "epoch": 0.07151979565772669,
      "grad_norm": 0.37276825308799744,
      "learning_rate": 5.212206015980742e-05,
      "loss": 0.6461,
      "step": 210
    },
    {
      "epoch": 0.07322264793529161,
      "grad_norm": 0.4148285686969757,
      "learning_rate": 5e-05,
      "loss": 0.6849,
      "step": 215
    },
    {
      "epoch": 0.07492550021285653,
      "grad_norm": 0.467510849237442,
      "learning_rate": 4.78779398401926e-05,
      "loss": 0.7479,
      "step": 220
    },
    {
      "epoch": 0.07662835249042145,
      "grad_norm": 0.4516083002090454,
      "learning_rate": 4.575970377622456e-05,
      "loss": 0.7046,
      "step": 225
    },
    {
      "epoch": 0.07833120476798637,
      "grad_norm": 0.6386833786964417,
      "learning_rate": 4.364910901265606e-05,
      "loss": 0.8149,
      "step": 230
    },
    {
      "epoch": 0.0800340570455513,
      "grad_norm": 0.7090473771095276,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 0.7141,
      "step": 235
    },
    {
      "epoch": 0.08173690932311622,
      "grad_norm": 0.8289636969566345,
      "learning_rate": 3.94660365002137e-05,
      "loss": 0.7959,
      "step": 240
    },
    {
      "epoch": 0.08343976160068114,
      "grad_norm": 0.7692727446556091,
      "learning_rate": 3.740109693074375e-05,
      "loss": 0.8913,
      "step": 245
    },
    {
      "epoch": 0.08514261387824607,
      "grad_norm": 2.1364786624908447,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 1.1669,
      "step": 250
    },
    {
      "epoch": 0.08684546615581099,
      "grad_norm": 0.2958797812461853,
      "learning_rate": 3.334301026289712e-05,
      "loss": 0.5825,
      "step": 255
    },
    {
      "epoch": 0.0885483184333759,
      "grad_norm": 0.3214460611343384,
      "learning_rate": 3.135717611098458e-05,
      "loss": 0.6469,
      "step": 260
    },
    {
      "epoch": 0.09025117071094083,
      "grad_norm": 0.35879385471343994,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 0.6802,
      "step": 265
    },
    {
      "epoch": 0.09195402298850575,
      "grad_norm": 0.4895831048488617,
      "learning_rate": 2.748981275911633e-05,
      "loss": 0.6844,
      "step": 270
    },
    {
      "epoch": 0.09365687526607067,
      "grad_norm": 0.5248720645904541,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 0.816,
      "step": 275
    },
    {
      "epoch": 0.09535972754363559,
      "grad_norm": 0.9332192540168762,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 0.7685,
      "step": 280
    },
    {
      "epoch": 0.0970625798212005,
      "grad_norm": 1.0168631076812744,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 0.8865,
      "step": 285
    },
    {
      "epoch": 0.09876543209876543,
      "grad_norm": 0.9966294169425964,
      "learning_rate": 2.026834118478567e-05,
      "loss": 0.7829,
      "step": 290
    },
    {
      "epoch": 0.10046828437633035,
      "grad_norm": 0.7733042240142822,
      "learning_rate": 1.858900013521788e-05,
      "loss": 0.8039,
      "step": 295
    },
    {
      "epoch": 0.10217113665389528,
      "grad_norm": 1.4958066940307617,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 1.0362,
      "step": 300
    },
    {
      "epoch": 0.10217113665389528,
      "eval_loss": 0.8057827949523926,
      "eval_runtime": 103.3191,
      "eval_samples_per_second": 11.973,
      "eval_steps_per_second": 5.991,
      "step": 300
    },
    {
      "epoch": 0.1038739889314602,
      "grad_norm": 0.2826021909713745,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 0.6531,
      "step": 305
    },
    {
      "epoch": 0.10557684120902512,
      "grad_norm": 0.3743998110294342,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 0.6584,
      "step": 310
    },
    {
      "epoch": 0.10727969348659004,
      "grad_norm": 0.3901960849761963,
      "learning_rate": 1.246638473736378e-05,
      "loss": 0.6357,
      "step": 315
    },
    {
      "epoch": 0.10898254576415496,
      "grad_norm": 0.45998629927635193,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 0.7242,
      "step": 320
    },
    {
      "epoch": 0.11068539804171988,
      "grad_norm": 0.5637640357017517,
      "learning_rate": 9.800143481652979e-06,
      "loss": 0.7037,
      "step": 325
    },
    {
      "epoch": 0.1123882503192848,
      "grad_norm": 0.8985954523086548,
      "learning_rate": 8.574517537807897e-06,
      "loss": 0.6539,
      "step": 330
    },
    {
      "epoch": 0.11409110259684972,
      "grad_norm": 0.580285370349884,
      "learning_rate": 7.423543113334436e-06,
      "loss": 0.6758,
      "step": 335
    },
    {
      "epoch": 0.11579395487441464,
      "grad_norm": 0.9392384886741638,
      "learning_rate": 6.349294341940593e-06,
      "loss": 0.6773,
      "step": 340
    },
    {
      "epoch": 0.11749680715197956,
      "grad_norm": 0.8998203873634338,
      "learning_rate": 5.353707092521582e-06,
      "loss": 0.7652,
      "step": 345
    },
    {
      "epoch": 0.11919965942954448,
      "grad_norm": 1.7155072689056396,
      "learning_rate": 4.43857548059321e-06,
      "loss": 0.9315,
      "step": 350
    },
    {
      "epoch": 0.1209025117071094,
      "grad_norm": 0.24951836466789246,
      "learning_rate": 3.605548635174533e-06,
      "loss": 0.6951,
      "step": 355
    },
    {
      "epoch": 0.12260536398467432,
      "grad_norm": 0.3586573600769043,
      "learning_rate": 2.85612772694579e-06,
      "loss": 0.6712,
      "step": 360
    },
    {
      "epoch": 0.12430821626223926,
      "grad_norm": 0.39840635657310486,
      "learning_rate": 2.191663263037458e-06,
      "loss": 0.7289,
      "step": 365
    },
    {
      "epoch": 0.12601106853980418,
      "grad_norm": 0.4486914277076721,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 0.6964,
      "step": 370
    },
    {
      "epoch": 0.1277139208173691,
      "grad_norm": 0.60421222448349,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 0.6867,
      "step": 375
    },
    {
      "epoch": 0.12941677309493402,
      "grad_norm": 0.6045652031898499,
      "learning_rate": 7.192044826145771e-07,
      "loss": 0.8006,
      "step": 380
    },
    {
      "epoch": 0.13111962537249894,
      "grad_norm": 0.9322503209114075,
      "learning_rate": 4.049782370561583e-07,
      "loss": 0.8982,
      "step": 385
    },
    {
      "epoch": 0.13282247765006386,
      "grad_norm": 0.9230653643608093,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 0.726,
      "step": 390
    },
    {
      "epoch": 0.13452532992762878,
      "grad_norm": 0.8531010150909424,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 0.7812,
      "step": 395
    },
    {
      "epoch": 0.1362281822051937,
      "grad_norm": 2.1816444396972656,
      "learning_rate": 0.0,
      "loss": 1.0379,
      "step": 400
    },
    {
      "epoch": 0.1362281822051937,
      "eval_loss": 0.7936921119689941,
      "eval_runtime": 103.1818,
      "eval_samples_per_second": 11.989,
      "eval_steps_per_second": 5.999,
      "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": 1.3767560524726272e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}