{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.030482577301910875,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.62064432547772e-05,
      "eval_loss": 2.8183770179748535,
      "eval_runtime": 462.6503,
      "eval_samples_per_second": 11.944,
      "eval_steps_per_second": 5.972,
      "step": 1
    },
    {
      "epoch": 0.00038103221627388596,
      "grad_norm": 2.621533155441284,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.7898,
      "step": 5
    },
    {
      "epoch": 0.0007620644325477719,
      "grad_norm": 2.2636330127716064,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.8006,
      "step": 10
    },
    {
      "epoch": 0.0011430966488216578,
      "grad_norm": 1.7934571504592896,
      "learning_rate": 5e-05,
      "loss": 2.2339,
      "step": 15
    },
    {
      "epoch": 0.0015241288650955438,
      "grad_norm": 3.306905746459961,
      "learning_rate": 6.666666666666667e-05,
      "loss": 2.6341,
      "step": 20
    },
    {
      "epoch": 0.0019051610813694297,
      "grad_norm": 2.1604180335998535,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.9358,
      "step": 25
    },
    {
      "epoch": 0.0022861932976433155,
      "grad_norm": 2.6654839515686035,
      "learning_rate": 0.0001,
      "loss": 1.6717,
      "step": 30
    },
    {
      "epoch": 0.002667225513917202,
      "grad_norm": 3.1767466068267822,
      "learning_rate": 9.995494831023409e-05,
      "loss": 1.6985,
      "step": 35
    },
    {
      "epoch": 0.0030482577301910877,
      "grad_norm": 2.4633893966674805,
      "learning_rate": 9.981987442712633e-05,
      "loss": 1.595,
      "step": 40
    },
    {
      "epoch": 0.0034292899464649735,
      "grad_norm": 2.9776158332824707,
      "learning_rate": 9.959502176294383e-05,
      "loss": 1.4452,
      "step": 45
    },
    {
      "epoch": 0.0038103221627388594,
      "grad_norm": 7.1352105140686035,
      "learning_rate": 9.928079551738543e-05,
      "loss": 1.9279,
      "step": 50
    },
    {
      "epoch": 0.004191354379012745,
      "grad_norm": 2.550354242324829,
      "learning_rate": 9.887776194738432e-05,
      "loss": 2.1826,
      "step": 55
    },
    {
      "epoch": 0.004572386595286631,
      "grad_norm": 1.5781782865524292,
      "learning_rate": 9.838664734667495e-05,
      "loss": 1.8981,
      "step": 60
    },
    {
      "epoch": 0.004953418811560518,
      "grad_norm": 1.6646926403045654,
      "learning_rate": 9.780833673696254e-05,
      "loss": 1.8603,
      "step": 65
    },
    {
      "epoch": 0.005334451027834404,
      "grad_norm": 2.160353422164917,
      "learning_rate": 9.714387227305422e-05,
      "loss": 1.9706,
      "step": 70
    },
    {
      "epoch": 0.0057154832441082895,
      "grad_norm": 1.6091870069503784,
      "learning_rate": 9.639445136482548e-05,
      "loss": 1.6622,
      "step": 75
    },
    {
      "epoch": 0.006096515460382175,
      "grad_norm": 1.821466088294983,
      "learning_rate": 9.55614245194068e-05,
      "loss": 1.8387,
      "step": 80
    },
    {
      "epoch": 0.006477547676656061,
      "grad_norm": 1.8064284324645996,
      "learning_rate": 9.464629290747842e-05,
      "loss": 1.5764,
      "step": 85
    },
    {
      "epoch": 0.006858579892929947,
      "grad_norm": 3.3229191303253174,
      "learning_rate": 9.365070565805941e-05,
      "loss": 1.5239,
      "step": 90
    },
    {
      "epoch": 0.007239612109203833,
      "grad_norm": 3.05495548248291,
      "learning_rate": 9.257645688666556e-05,
      "loss": 1.3448,
      "step": 95
    },
    {
      "epoch": 0.007620644325477719,
      "grad_norm": 3.9356956481933594,
      "learning_rate": 9.142548246219212e-05,
      "loss": 1.4656,
      "step": 100
    },
    {
      "epoch": 0.007620644325477719,
      "eval_loss": 1.635000467300415,
      "eval_runtime": 464.3134,
      "eval_samples_per_second": 11.901,
      "eval_steps_per_second": 5.951,
      "step": 100
    },
    {
      "epoch": 0.008001676541751605,
      "grad_norm": 1.8800768852233887,
      "learning_rate": 9.019985651834703e-05,
      "loss": 1.7591,
      "step": 105
    },
    {
      "epoch": 0.00838270875802549,
      "grad_norm": 1.5923824310302734,
      "learning_rate": 8.890178771592199e-05,
      "loss": 2.0742,
      "step": 110
    },
    {
      "epoch": 0.008763740974299376,
      "grad_norm": 1.8231480121612549,
      "learning_rate": 8.753361526263621e-05,
      "loss": 1.6191,
      "step": 115
    },
    {
      "epoch": 0.009144773190573262,
      "grad_norm": 2.527218818664551,
      "learning_rate": 8.609780469772623e-05,
      "loss": 1.5712,
      "step": 120
    },
    {
      "epoch": 0.00952580540684715,
      "grad_norm": 1.8077352046966553,
      "learning_rate": 8.459694344887732e-05,
      "loss": 1.4715,
      "step": 125
    },
    {
      "epoch": 0.009906837623121036,
      "grad_norm": 2.0713860988616943,
      "learning_rate": 8.303373616950408e-05,
      "loss": 1.3179,
      "step": 130
    },
    {
      "epoch": 0.010287869839394921,
      "grad_norm": 2.0263924598693848,
      "learning_rate": 8.141099986478212e-05,
      "loss": 1.5481,
      "step": 135
    },
    {
      "epoch": 0.010668902055668807,
      "grad_norm": 1.9154996871948242,
      "learning_rate": 7.973165881521434e-05,
      "loss": 1.2512,
      "step": 140
    },
    {
      "epoch": 0.011049934271942693,
      "grad_norm": 2.2789220809936523,
      "learning_rate": 7.799873930687978e-05,
      "loss": 1.3806,
      "step": 145
    },
    {
      "epoch": 0.011430966488216579,
      "grad_norm": 3.3408801555633545,
      "learning_rate": 7.621536417786159e-05,
      "loss": 1.4478,
      "step": 150
    },
    {
      "epoch": 0.011811998704490465,
      "grad_norm": 2.8096556663513184,
      "learning_rate": 7.438474719068173e-05,
      "loss": 1.6848,
      "step": 155
    },
    {
      "epoch": 0.01219303092076435,
      "grad_norm": 1.6324262619018555,
      "learning_rate": 7.251018724088367e-05,
      "loss": 1.6888,
      "step": 160
    },
    {
      "epoch": 0.012574063137038237,
      "grad_norm": 1.4184777736663818,
      "learning_rate": 7.059506241219965e-05,
      "loss": 1.7714,
      "step": 165
    },
    {
      "epoch": 0.012955095353312122,
      "grad_norm": 1.8253209590911865,
      "learning_rate": 6.864282388901544e-05,
      "loss": 1.7426,
      "step": 170
    },
    {
      "epoch": 0.013336127569586008,
      "grad_norm": 1.6970152854919434,
      "learning_rate": 6.665698973710288e-05,
      "loss": 1.2758,
      "step": 175
    },
    {
      "epoch": 0.013717159785859894,
      "grad_norm": 1.6781067848205566,
      "learning_rate": 6.464113856382752e-05,
      "loss": 1.3957,
      "step": 180
    },
    {
      "epoch": 0.01409819200213378,
      "grad_norm": 1.9891561269760132,
      "learning_rate": 6.259890306925627e-05,
      "loss": 1.2277,
      "step": 185
    },
    {
      "epoch": 0.014479224218407666,
      "grad_norm": 2.0728087425231934,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 1.2154,
      "step": 190
    },
    {
      "epoch": 0.014860256434681552,
      "grad_norm": 2.113464117050171,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 1.3138,
      "step": 195
    },
    {
      "epoch": 0.015241288650955438,
      "grad_norm": 4.222987651824951,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 1.4503,
      "step": 200
    },
    {
      "epoch": 0.015241288650955438,
      "eval_loss": 1.523425817489624,
      "eval_runtime": 464.2054,
      "eval_samples_per_second": 11.904,
      "eval_steps_per_second": 5.952,
      "step": 200
    },
    {
      "epoch": 0.015622320867229323,
      "grad_norm": 3.6519534587860107,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 1.7968,
      "step": 205
    },
    {
      "epoch": 0.01600335308350321,
      "grad_norm": 2.212120771408081,
      "learning_rate": 5.212206015980742e-05,
      "loss": 1.7399,
      "step": 210
    },
    {
      "epoch": 0.016384385299777097,
      "grad_norm": 1.745534896850586,
      "learning_rate": 5e-05,
      "loss": 1.702,
      "step": 215
    },
    {
      "epoch": 0.01676541751605098,
      "grad_norm": 2.3732457160949707,
      "learning_rate": 4.78779398401926e-05,
      "loss": 1.4814,
      "step": 220
    },
    {
      "epoch": 0.01714644973232487,
      "grad_norm": 2.359468460083008,
      "learning_rate": 4.575970377622456e-05,
      "loss": 1.3712,
      "step": 225
    },
    {
      "epoch": 0.017527481948598753,
      "grad_norm": 1.7999073266983032,
      "learning_rate": 4.364910901265606e-05,
      "loss": 1.3606,
      "step": 230
    },
    {
      "epoch": 0.01790851416487264,
      "grad_norm": 1.6490678787231445,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 1.3691,
      "step": 235
    },
    {
      "epoch": 0.018289546381146524,
      "grad_norm": 3.9256560802459717,
      "learning_rate": 3.94660365002137e-05,
      "loss": 1.1184,
      "step": 240
    },
    {
      "epoch": 0.018670578597420412,
      "grad_norm": 1.9621838331222534,
      "learning_rate": 3.740109693074375e-05,
      "loss": 1.0813,
      "step": 245
    },
    {
      "epoch": 0.0190516108136943,
      "grad_norm": 3.3996524810791016,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 1.5535,
      "step": 250
    },
    {
      "epoch": 0.019432643029968184,
      "grad_norm": 2.404664993286133,
      "learning_rate": 3.334301026289712e-05,
      "loss": 1.6254,
      "step": 255
    },
    {
      "epoch": 0.01981367524624207,
      "grad_norm": 2.262866258621216,
      "learning_rate": 3.135717611098458e-05,
      "loss": 1.8334,
      "step": 260
    },
    {
      "epoch": 0.020194707462515955,
      "grad_norm": 1.7600617408752441,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 1.446,
      "step": 265
    },
    {
      "epoch": 0.020575739678789843,
      "grad_norm": 2.7334885597229004,
      "learning_rate": 2.748981275911633e-05,
      "loss": 1.6289,
      "step": 270
    },
    {
      "epoch": 0.020956771895063727,
      "grad_norm": 1.8681226968765259,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 1.1666,
      "step": 275
    },
    {
      "epoch": 0.021337804111337615,
      "grad_norm": 1.8139694929122925,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 1.2283,
      "step": 280
    },
    {
      "epoch": 0.0217188363276115,
      "grad_norm": 2.352893829345703,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 1.3424,
      "step": 285
    },
    {
      "epoch": 0.022099868543885386,
      "grad_norm": 2.148400068283081,
      "learning_rate": 2.026834118478567e-05,
      "loss": 1.2934,
      "step": 290
    },
    {
      "epoch": 0.02248090076015927,
      "grad_norm": 2.535423994064331,
      "learning_rate": 1.858900013521788e-05,
      "loss": 1.0938,
      "step": 295
    },
    {
      "epoch": 0.022861932976433158,
      "grad_norm": 3.548401117324829,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 1.4465,
      "step": 300
    },
    {
      "epoch": 0.022861932976433158,
      "eval_loss": 1.4267401695251465,
      "eval_runtime": 465.0865,
      "eval_samples_per_second": 11.882,
      "eval_steps_per_second": 5.941,
      "step": 300
    },
    {
      "epoch": 0.023242965192707042,
      "grad_norm": 1.9533120393753052,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 1.6214,
      "step": 305
    },
    {
      "epoch": 0.02362399740898093,
      "grad_norm": 1.8162742853164673,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 1.7682,
      "step": 310
    },
    {
      "epoch": 0.024005029625254814,
      "grad_norm": 1.6404738426208496,
      "learning_rate": 1.246638473736378e-05,
      "loss": 1.5273,
      "step": 315
    },
    {
      "epoch": 0.0243860618415287,
      "grad_norm": 2.012794017791748,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 1.5279,
      "step": 320
    },
    {
      "epoch": 0.024767094057802586,
      "grad_norm": 2.579059600830078,
      "learning_rate": 9.800143481652979e-06,
      "loss": 1.387,
      "step": 325
    },
    {
      "epoch": 0.025148126274076473,
      "grad_norm": 1.9421414136886597,
      "learning_rate": 8.574517537807897e-06,
      "loss": 1.2756,
      "step": 330
    },
    {
      "epoch": 0.02552915849035036,
      "grad_norm": 1.9849478006362915,
      "learning_rate": 7.423543113334436e-06,
      "loss": 1.1314,
      "step": 335
    },
    {
      "epoch": 0.025910190706624245,
      "grad_norm": 2.5098581314086914,
      "learning_rate": 6.349294341940593e-06,
      "loss": 1.2295,
      "step": 340
    },
    {
      "epoch": 0.026291222922898132,
      "grad_norm": 2.8621582984924316,
      "learning_rate": 5.353707092521582e-06,
      "loss": 1.0212,
      "step": 345
    },
    {
      "epoch": 0.026672255139172017,
      "grad_norm": 4.128223419189453,
      "learning_rate": 4.43857548059321e-06,
      "loss": 1.4369,
      "step": 350
    },
    {
      "epoch": 0.027053287355445904,
      "grad_norm": 1.5159494876861572,
      "learning_rate": 3.605548635174533e-06,
      "loss": 1.599,
      "step": 355
    },
    {
      "epoch": 0.027434319571719788,
      "grad_norm": 1.6853203773498535,
      "learning_rate": 2.85612772694579e-06,
      "loss": 1.6639,
      "step": 360
    },
    {
      "epoch": 0.027815351787993676,
      "grad_norm": 1.6744269132614136,
      "learning_rate": 2.191663263037458e-06,
      "loss": 1.4604,
      "step": 365
    },
    {
      "epoch": 0.02819638400426756,
      "grad_norm": 2.027444362640381,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 1.5011,
      "step": 370
    },
    {
      "epoch": 0.028577416220541448,
      "grad_norm": 1.8970798254013062,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 1.1266,
      "step": 375
    },
    {
      "epoch": 0.02895844843681533,
      "grad_norm": 2.5559067726135254,
      "learning_rate": 7.192044826145771e-07,
      "loss": 1.4254,
      "step": 380
    },
    {
      "epoch": 0.02933948065308922,
      "grad_norm": 1.8470799922943115,
      "learning_rate": 4.049782370561583e-07,
      "loss": 1.2642,
      "step": 385
    },
    {
      "epoch": 0.029720512869363103,
      "grad_norm": 2.398313045501709,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 1.1736,
      "step": 390
    },
    {
      "epoch": 0.03010154508563699,
      "grad_norm": 2.755197286605835,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 1.241,
      "step": 395
    },
    {
      "epoch": 0.030482577301910875,
      "grad_norm": 3.3371331691741943,
      "learning_rate": 0.0,
      "loss": 1.1579,
      "step": 400
    },
    {
      "epoch": 0.030482577301910875,
      "eval_loss": 1.4240096807479858,
      "eval_runtime": 464.3789,
      "eval_samples_per_second": 11.9,
      "eval_steps_per_second": 5.95,
      "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": 1.5194170298518733e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}