{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04709622347158037,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00011774055867895093,
      "eval_loss": 11.5,
      "eval_runtime": 23.2626,
      "eval_samples_per_second": 153.766,
      "eval_steps_per_second": 76.904,
      "step": 1
    },
    {
      "epoch": 0.0005887027933947547,
      "grad_norm": 0.0001290775981033221,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.0011774055867895094,
      "grad_norm": 0.00010477239993633702,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 46.0,
      "step": 10
    },
    {
      "epoch": 0.001766108380184264,
      "grad_norm": 8.767608960624784e-05,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 15
    },
    {
      "epoch": 0.002354811173579019,
      "grad_norm": 8.796458860160783e-05,
      "learning_rate": 6.666666666666667e-05,
      "loss": 46.0,
      "step": 20
    },
    {
      "epoch": 0.0029435139669737732,
      "grad_norm": 0.00010454504081280902,
      "learning_rate": 8.333333333333334e-05,
      "loss": 46.0,
      "step": 25
    },
    {
      "epoch": 0.003532216760368528,
      "grad_norm": 7.229079346871004e-05,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 30
    },
    {
      "epoch": 0.004120919553763282,
      "grad_norm": 0.00011278772581135854,
      "learning_rate": 9.995494831023409e-05,
      "loss": 46.0,
      "step": 35
    },
    {
      "epoch": 0.004709622347158038,
      "grad_norm": 7.370460662059486e-05,
      "learning_rate": 9.981987442712633e-05,
      "loss": 46.0,
      "step": 40
    },
    {
      "epoch": 0.005298325140552792,
      "grad_norm": 5.859605880687013e-05,
      "learning_rate": 9.959502176294383e-05,
      "loss": 46.0,
      "step": 45
    },
    {
      "epoch": 0.0058870279339475464,
      "grad_norm": 0.00011565225577214733,
      "learning_rate": 9.928079551738543e-05,
      "loss": 46.0,
      "step": 50
    },
    {
      "epoch": 0.006475730727342301,
      "grad_norm": 0.00018157740123569965,
      "learning_rate": 9.887776194738432e-05,
      "loss": 46.0,
      "step": 55
    },
    {
      "epoch": 0.007064433520737056,
      "grad_norm": 0.00012944494665134698,
      "learning_rate": 9.838664734667495e-05,
      "loss": 46.0,
      "step": 60
    },
    {
      "epoch": 0.0076531363141318105,
      "grad_norm": 0.0001439522166037932,
      "learning_rate": 9.780833673696254e-05,
      "loss": 46.0,
      "step": 65
    },
    {
      "epoch": 0.008241839107526565,
      "grad_norm": 0.00012116672587580979,
      "learning_rate": 9.714387227305422e-05,
      "loss": 46.0,
      "step": 70
    },
    {
      "epoch": 0.00883054190092132,
      "grad_norm": 0.0001838503812905401,
      "learning_rate": 9.639445136482548e-05,
      "loss": 46.0,
      "step": 75
    },
    {
      "epoch": 0.009419244694316075,
      "grad_norm": 0.00015107652870938182,
      "learning_rate": 9.55614245194068e-05,
      "loss": 46.0,
      "step": 80
    },
    {
      "epoch": 0.01000794748771083,
      "grad_norm": 0.000147761165862903,
      "learning_rate": 9.464629290747842e-05,
      "loss": 46.0,
      "step": 85
    },
    {
      "epoch": 0.010596650281105584,
      "grad_norm": 0.00018192124844063073,
      "learning_rate": 9.365070565805941e-05,
      "loss": 46.0,
      "step": 90
    },
    {
      "epoch": 0.011185353074500338,
      "grad_norm": 0.00010093303717439994,
      "learning_rate": 9.257645688666556e-05,
      "loss": 46.0,
      "step": 95
    },
    {
      "epoch": 0.011774055867895093,
      "grad_norm": 5.6614928325871006e-05,
      "learning_rate": 9.142548246219212e-05,
      "loss": 46.0,
      "step": 100
    },
    {
      "epoch": 0.011774055867895093,
      "eval_loss": 11.5,
      "eval_runtime": 23.2789,
      "eval_samples_per_second": 153.659,
      "eval_steps_per_second": 76.851,
      "step": 100
    },
    {
      "epoch": 0.012362758661289847,
      "grad_norm": 0.00043836390250362456,
      "learning_rate": 9.019985651834703e-05,
      "loss": 46.0,
      "step": 105
    },
    {
      "epoch": 0.012951461454684602,
      "grad_norm": 0.00036111564259044826,
      "learning_rate": 8.890178771592199e-05,
      "loss": 46.0,
      "step": 110
    },
    {
      "epoch": 0.013540164248079358,
      "grad_norm": 0.00022299740521702915,
      "learning_rate": 8.753361526263621e-05,
      "loss": 46.0,
      "step": 115
    },
    {
      "epoch": 0.014128867041474112,
      "grad_norm": 0.0001942400267580524,
      "learning_rate": 8.609780469772623e-05,
      "loss": 46.0,
      "step": 120
    },
    {
      "epoch": 0.014717569834868867,
      "grad_norm": 0.00024326215498149395,
      "learning_rate": 8.459694344887732e-05,
      "loss": 46.0,
      "step": 125
    },
    {
      "epoch": 0.015306272628263621,
      "grad_norm": 0.0003793689247686416,
      "learning_rate": 8.303373616950408e-05,
      "loss": 46.0,
      "step": 130
    },
    {
      "epoch": 0.015894975421658377,
      "grad_norm": 0.000218657121877186,
      "learning_rate": 8.141099986478212e-05,
      "loss": 46.0,
      "step": 135
    },
    {
      "epoch": 0.01648367821505313,
      "grad_norm": 0.00033277113107033074,
      "learning_rate": 7.973165881521434e-05,
      "loss": 46.0,
      "step": 140
    },
    {
      "epoch": 0.017072381008447886,
      "grad_norm": 0.00014911754988133907,
      "learning_rate": 7.799873930687978e-05,
      "loss": 46.0,
      "step": 145
    },
    {
      "epoch": 0.01766108380184264,
      "grad_norm": 0.0002728045510593802,
      "learning_rate": 7.621536417786159e-05,
      "loss": 46.0,
      "step": 150
    },
    {
      "epoch": 0.018249786595237395,
      "grad_norm": 0.0006224053213372827,
      "learning_rate": 7.438474719068173e-05,
      "loss": 46.0,
      "step": 155
    },
    {
      "epoch": 0.01883848938863215,
      "grad_norm": 0.0005212260293774307,
      "learning_rate": 7.251018724088367e-05,
      "loss": 46.0,
      "step": 160
    },
    {
      "epoch": 0.019427192182026903,
      "grad_norm": 0.0005189418443478644,
      "learning_rate": 7.059506241219965e-05,
      "loss": 46.0,
      "step": 165
    },
    {
      "epoch": 0.02001589497542166,
      "grad_norm": 0.0004071235889568925,
      "learning_rate": 6.864282388901544e-05,
      "loss": 46.0,
      "step": 170
    },
    {
      "epoch": 0.020604597768816412,
      "grad_norm": 0.0005512144998647273,
      "learning_rate": 6.665698973710288e-05,
      "loss": 46.0,
      "step": 175
    },
    {
      "epoch": 0.021193300562211168,
      "grad_norm": 0.0005048111779615283,
      "learning_rate": 6.464113856382752e-05,
      "loss": 46.0,
      "step": 180
    },
    {
      "epoch": 0.02178200335560592,
      "grad_norm": 0.00035031110746786,
      "learning_rate": 6.259890306925627e-05,
      "loss": 46.0,
      "step": 185
    },
    {
      "epoch": 0.022370706149000677,
      "grad_norm": 0.00039796109194867313,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 46.0,
      "step": 190
    },
    {
      "epoch": 0.022959408942395433,
      "grad_norm": 0.0004980563535355031,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 46.0,
      "step": 195
    },
    {
      "epoch": 0.023548111735790186,
      "grad_norm": 0.0002501264098100364,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 46.0,
      "step": 200
    },
    {
      "epoch": 0.023548111735790186,
      "eval_loss": 11.5,
      "eval_runtime": 23.307,
      "eval_samples_per_second": 153.473,
      "eval_steps_per_second": 76.758,
      "step": 200
    },
    {
      "epoch": 0.024136814529184942,
      "grad_norm": 0.0008755507878959179,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 46.0,
      "step": 205
    },
    {
      "epoch": 0.024725517322579695,
      "grad_norm": 0.0006989152752794325,
      "learning_rate": 5.212206015980742e-05,
      "loss": 46.0,
      "step": 210
    },
    {
      "epoch": 0.02531422011597445,
      "grad_norm": 0.0007511722506023943,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 215
    },
    {
      "epoch": 0.025902922909369203,
      "grad_norm": 0.0005252875271253288,
      "learning_rate": 4.78779398401926e-05,
      "loss": 46.0,
      "step": 220
    },
    {
      "epoch": 0.02649162570276396,
      "grad_norm": 0.000517240259796381,
      "learning_rate": 4.575970377622456e-05,
      "loss": 46.0,
      "step": 225
    },
    {
      "epoch": 0.027080328496158716,
      "grad_norm": 0.0004974912153556943,
      "learning_rate": 4.364910901265606e-05,
      "loss": 46.0,
      "step": 230
    },
    {
      "epoch": 0.027669031289553468,
      "grad_norm": 0.0008188697975128889,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 46.0,
      "step": 235
    },
    {
      "epoch": 0.028257734082948224,
      "grad_norm": 0.0003775698714889586,
      "learning_rate": 3.94660365002137e-05,
      "loss": 46.0,
      "step": 240
    },
    {
      "epoch": 0.028846436876342977,
      "grad_norm": 0.0006426152540370822,
      "learning_rate": 3.740109693074375e-05,
      "loss": 46.0,
      "step": 245
    },
    {
      "epoch": 0.029435139669737733,
      "grad_norm": 0.0005528911715373397,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 46.0,
      "step": 250
    },
    {
      "epoch": 0.03002384246313249,
      "grad_norm": 0.0013645205181092024,
      "learning_rate": 3.334301026289712e-05,
      "loss": 46.0,
      "step": 255
    },
    {
      "epoch": 0.030612545256527242,
      "grad_norm": 0.000937989039812237,
      "learning_rate": 3.135717611098458e-05,
      "loss": 46.0,
      "step": 260
    },
    {
      "epoch": 0.031201248049921998,
      "grad_norm": 0.001120740664191544,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 46.0,
      "step": 265
    },
    {
      "epoch": 0.031789950843316754,
      "grad_norm": 0.0008530758204869926,
      "learning_rate": 2.748981275911633e-05,
      "loss": 46.0,
      "step": 270
    },
    {
      "epoch": 0.0323786536367115,
      "grad_norm": 0.0007581591489724815,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 46.0,
      "step": 275
    },
    {
      "epoch": 0.03296735643010626,
      "grad_norm": 0.0007406318909488618,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 46.0,
      "step": 280
    },
    {
      "epoch": 0.033556059223501015,
      "grad_norm": 0.0007063026423566043,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 46.0,
      "step": 285
    },
    {
      "epoch": 0.03414476201689577,
      "grad_norm": 0.0007229686598293483,
      "learning_rate": 2.026834118478567e-05,
      "loss": 46.0,
      "step": 290
    },
    {
      "epoch": 0.03473346481029053,
      "grad_norm": 0.0005272207199595869,
      "learning_rate": 1.858900013521788e-05,
      "loss": 46.0,
      "step": 295
    },
    {
      "epoch": 0.03532216760368528,
      "grad_norm": 0.0005446030991151929,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 46.0,
      "step": 300
    },
    {
      "epoch": 0.03532216760368528,
      "eval_loss": 11.5,
      "eval_runtime": 23.1896,
      "eval_samples_per_second": 154.25,
      "eval_steps_per_second": 77.147,
      "step": 300
    },
    {
      "epoch": 0.03591087039708003,
      "grad_norm": 0.0013344062026590109,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 46.0,
      "step": 305
    },
    {
      "epoch": 0.03649957319047479,
      "grad_norm": 0.0009276200435124338,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 46.0,
      "step": 310
    },
    {
      "epoch": 0.037088275983869545,
      "grad_norm": 0.0009761730907484889,
      "learning_rate": 1.246638473736378e-05,
      "loss": 46.0,
      "step": 315
    },
    {
      "epoch": 0.0376769787772643,
      "grad_norm": 0.0008747640531510115,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 46.0,
      "step": 320
    },
    {
      "epoch": 0.03826568157065905,
      "grad_norm": 0.0008400992956012487,
      "learning_rate": 9.800143481652979e-06,
      "loss": 46.0,
      "step": 325
    },
    {
      "epoch": 0.03885438436405381,
      "grad_norm": 0.0005525358719751239,
      "learning_rate": 8.574517537807897e-06,
      "loss": 46.0,
      "step": 330
    },
    {
      "epoch": 0.03944308715744856,
      "grad_norm": 0.0007394708809442818,
      "learning_rate": 7.423543113334436e-06,
      "loss": 46.0,
      "step": 335
    },
    {
      "epoch": 0.04003178995084332,
      "grad_norm": 0.0005816684570163488,
      "learning_rate": 6.349294341940593e-06,
      "loss": 46.0,
      "step": 340
    },
    {
      "epoch": 0.04062049274423807,
      "grad_norm": 0.00047969381557777524,
      "learning_rate": 5.353707092521582e-06,
      "loss": 46.0,
      "step": 345
    },
    {
      "epoch": 0.041209195537632824,
      "grad_norm": 0.0008183843456208706,
      "learning_rate": 4.43857548059321e-06,
      "loss": 46.0,
      "step": 350
    },
    {
      "epoch": 0.04179789833102758,
      "grad_norm": 0.0014757461613044143,
      "learning_rate": 3.605548635174533e-06,
      "loss": 46.0,
      "step": 355
    },
    {
      "epoch": 0.042386601124422336,
      "grad_norm": 0.0009852014482021332,
      "learning_rate": 2.85612772694579e-06,
      "loss": 46.0,
      "step": 360
    },
    {
      "epoch": 0.04297530391781709,
      "grad_norm": 0.0010490691056475043,
      "learning_rate": 2.191663263037458e-06,
      "loss": 46.0,
      "step": 365
    },
    {
      "epoch": 0.04356400671121184,
      "grad_norm": 0.0008946338202804327,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 46.0,
      "step": 370
    },
    {
      "epoch": 0.0441527095046066,
      "grad_norm": 0.000940500816795975,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 46.0,
      "step": 375
    },
    {
      "epoch": 0.044741412298001354,
      "grad_norm": 0.0006795782246626914,
      "learning_rate": 7.192044826145771e-07,
      "loss": 46.0,
      "step": 380
    },
    {
      "epoch": 0.04533011509139611,
      "grad_norm": 0.0006636727484874427,
      "learning_rate": 4.049782370561583e-07,
      "loss": 46.0,
      "step": 385
    },
    {
      "epoch": 0.045918817884790866,
      "grad_norm": 0.0007163998088799417,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 46.0,
      "step": 390
    },
    {
      "epoch": 0.046507520678185615,
      "grad_norm": 0.0005471633048728108,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 46.0,
      "step": 395
    },
    {
      "epoch": 0.04709622347158037,
      "grad_norm": 0.00041076645720750093,
      "learning_rate": 0.0,
      "loss": 46.0,
      "step": 400
    },
    {
      "epoch": 0.04709622347158037,
      "eval_loss": 11.5,
      "eval_runtime": 23.1389,
      "eval_samples_per_second": 154.588,
      "eval_steps_per_second": 77.316,
      "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": 15938302771200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}