{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03375171395422424,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.437928488556059e-05,
      "eval_loss": 1.4796180725097656,
      "eval_runtime": 658.6961,
      "eval_samples_per_second": 7.576,
      "eval_steps_per_second": 3.788,
      "step": 1
    },
    {
      "epoch": 0.00042189642442780296,
      "grad_norm": 0.4631634056568146,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 4.7387,
      "step": 5
    },
    {
      "epoch": 0.0008437928488556059,
      "grad_norm": 0.7140416502952576,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 5.3567,
      "step": 10
    },
    {
      "epoch": 0.0012656892732834089,
      "grad_norm": 1.127893090248108,
      "learning_rate": 5e-05,
      "loss": 5.244,
      "step": 15
    },
    {
      "epoch": 0.0016875856977112118,
      "grad_norm": 1.7558420896530151,
      "learning_rate": 6.666666666666667e-05,
      "loss": 5.0035,
      "step": 20
    },
    {
      "epoch": 0.002109482122139015,
      "grad_norm": 1.5938293933868408,
      "learning_rate": 8.333333333333334e-05,
      "loss": 4.5958,
      "step": 25
    },
    {
      "epoch": 0.0025313785465668178,
      "grad_norm": 1.6330130100250244,
      "learning_rate": 0.0001,
      "loss": 4.2993,
      "step": 30
    },
    {
      "epoch": 0.0029532749709946207,
      "grad_norm": 1.7025134563446045,
      "learning_rate": 9.995494831023409e-05,
      "loss": 4.1482,
      "step": 35
    },
    {
      "epoch": 0.0033751713954224237,
      "grad_norm": 1.460693359375,
      "learning_rate": 9.981987442712633e-05,
      "loss": 3.8792,
      "step": 40
    },
    {
      "epoch": 0.0037970678198502267,
      "grad_norm": 1.8393712043762207,
      "learning_rate": 9.959502176294383e-05,
      "loss": 3.7861,
      "step": 45
    },
    {
      "epoch": 0.00421896424427803,
      "grad_norm": 2.969388246536255,
      "learning_rate": 9.928079551738543e-05,
      "loss": 3.6155,
      "step": 50
    },
    {
      "epoch": 0.004640860668705833,
      "grad_norm": 1.291517734527588,
      "learning_rate": 9.887776194738432e-05,
      "loss": 3.3926,
      "step": 55
    },
    {
      "epoch": 0.0050627570931336355,
      "grad_norm": 1.0775760412216187,
      "learning_rate": 9.838664734667495e-05,
      "loss": 3.2625,
      "step": 60
    },
    {
      "epoch": 0.005484653517561439,
      "grad_norm": 1.4835420846939087,
      "learning_rate": 9.780833673696254e-05,
      "loss": 3.1183,
      "step": 65
    },
    {
      "epoch": 0.0059065499419892415,
      "grad_norm": 1.3978452682495117,
      "learning_rate": 9.714387227305422e-05,
      "loss": 3.0114,
      "step": 70
    },
    {
      "epoch": 0.006328446366417045,
      "grad_norm": 1.770120620727539,
      "learning_rate": 9.639445136482548e-05,
      "loss": 3.0342,
      "step": 75
    },
    {
      "epoch": 0.006750342790844847,
      "grad_norm": 2.0573582649230957,
      "learning_rate": 9.55614245194068e-05,
      "loss": 2.9655,
      "step": 80
    },
    {
      "epoch": 0.007172239215272651,
      "grad_norm": 2.2362797260284424,
      "learning_rate": 9.464629290747842e-05,
      "loss": 3.0051,
      "step": 85
    },
    {
      "epoch": 0.007594135639700453,
      "grad_norm": 2.4911794662475586,
      "learning_rate": 9.365070565805941e-05,
      "loss": 2.8141,
      "step": 90
    },
    {
      "epoch": 0.008016032064128256,
      "grad_norm": 2.7591800689697266,
      "learning_rate": 9.257645688666556e-05,
      "loss": 2.422,
      "step": 95
    },
    {
      "epoch": 0.00843792848855606,
      "grad_norm": 4.135620594024658,
      "learning_rate": 9.142548246219212e-05,
      "loss": 2.7617,
      "step": 100
    },
    {
      "epoch": 0.00843792848855606,
      "eval_loss": 0.6811572313308716,
      "eval_runtime": 665.0311,
      "eval_samples_per_second": 7.503,
      "eval_steps_per_second": 3.752,
      "step": 100
    },
    {
      "epoch": 0.008859824912983863,
      "grad_norm": 1.2018241882324219,
      "learning_rate": 9.019985651834703e-05,
      "loss": 2.6433,
      "step": 105
    },
    {
      "epoch": 0.009281721337411666,
      "grad_norm": 1.3547725677490234,
      "learning_rate": 8.890178771592199e-05,
      "loss": 2.6363,
      "step": 110
    },
    {
      "epoch": 0.009703617761839468,
      "grad_norm": 1.348791480064392,
      "learning_rate": 8.753361526263621e-05,
      "loss": 2.4425,
      "step": 115
    },
    {
      "epoch": 0.010125514186267271,
      "grad_norm": 1.5152088403701782,
      "learning_rate": 8.609780469772623e-05,
      "loss": 2.423,
      "step": 120
    },
    {
      "epoch": 0.010547410610695074,
      "grad_norm": 2.1645255088806152,
      "learning_rate": 8.459694344887732e-05,
      "loss": 2.6017,
      "step": 125
    },
    {
      "epoch": 0.010969307035122878,
      "grad_norm": 2.4885878562927246,
      "learning_rate": 8.303373616950408e-05,
      "loss": 2.5553,
      "step": 130
    },
    {
      "epoch": 0.01139120345955068,
      "grad_norm": 2.2648885250091553,
      "learning_rate": 8.141099986478212e-05,
      "loss": 2.578,
      "step": 135
    },
    {
      "epoch": 0.011813099883978483,
      "grad_norm": 2.8952243328094482,
      "learning_rate": 7.973165881521434e-05,
      "loss": 2.3747,
      "step": 140
    },
    {
      "epoch": 0.012234996308406286,
      "grad_norm": 3.0320076942443848,
      "learning_rate": 7.799873930687978e-05,
      "loss": 2.2956,
      "step": 145
    },
    {
      "epoch": 0.01265689273283409,
      "grad_norm": 4.181705951690674,
      "learning_rate": 7.621536417786159e-05,
      "loss": 2.2686,
      "step": 150
    },
    {
      "epoch": 0.013078789157261891,
      "grad_norm": 1.7516874074935913,
      "learning_rate": 7.438474719068173e-05,
      "loss": 2.6782,
      "step": 155
    },
    {
      "epoch": 0.013500685581689695,
      "grad_norm": 1.6716452836990356,
      "learning_rate": 7.251018724088367e-05,
      "loss": 2.4836,
      "step": 160
    },
    {
      "epoch": 0.013922582006117498,
      "grad_norm": 1.7507989406585693,
      "learning_rate": 7.059506241219965e-05,
      "loss": 2.6105,
      "step": 165
    },
    {
      "epoch": 0.014344478430545302,
      "grad_norm": 1.893986701965332,
      "learning_rate": 6.864282388901544e-05,
      "loss": 2.5252,
      "step": 170
    },
    {
      "epoch": 0.014766374854973103,
      "grad_norm": 2.1046249866485596,
      "learning_rate": 6.665698973710288e-05,
      "loss": 2.4737,
      "step": 175
    },
    {
      "epoch": 0.015188271279400907,
      "grad_norm": 2.3457796573638916,
      "learning_rate": 6.464113856382752e-05,
      "loss": 2.4018,
      "step": 180
    },
    {
      "epoch": 0.01561016770382871,
      "grad_norm": 2.703225612640381,
      "learning_rate": 6.259890306925627e-05,
      "loss": 2.3142,
      "step": 185
    },
    {
      "epoch": 0.01603206412825651,
      "grad_norm": 2.770165205001831,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 2.2951,
      "step": 190
    },
    {
      "epoch": 0.016453960552684315,
      "grad_norm": 3.2324838638305664,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 2.2542,
      "step": 195
    },
    {
      "epoch": 0.01687585697711212,
      "grad_norm": 4.079437732696533,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 2.3806,
      "step": 200
    },
    {
      "epoch": 0.01687585697711212,
      "eval_loss": 0.6063917875289917,
      "eval_runtime": 664.3901,
      "eval_samples_per_second": 7.511,
      "eval_steps_per_second": 3.755,
      "step": 200
    },
    {
      "epoch": 0.017297753401539922,
      "grad_norm": 1.573366403579712,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 2.5323,
      "step": 205
    },
    {
      "epoch": 0.017719649825967725,
      "grad_norm": 1.5846542119979858,
      "learning_rate": 5.212206015980742e-05,
      "loss": 2.5898,
      "step": 210
    },
    {
      "epoch": 0.01814154625039553,
      "grad_norm": 1.6904710531234741,
      "learning_rate": 5e-05,
      "loss": 2.4887,
      "step": 215
    },
    {
      "epoch": 0.018563442674823332,
      "grad_norm": 2.0252418518066406,
      "learning_rate": 4.78779398401926e-05,
      "loss": 2.466,
      "step": 220
    },
    {
      "epoch": 0.018985339099251135,
      "grad_norm": 2.1600403785705566,
      "learning_rate": 4.575970377622456e-05,
      "loss": 2.3847,
      "step": 225
    },
    {
      "epoch": 0.019407235523678935,
      "grad_norm": 2.7030434608459473,
      "learning_rate": 4.364910901265606e-05,
      "loss": 2.4336,
      "step": 230
    },
    {
      "epoch": 0.01982913194810674,
      "grad_norm": 2.669236660003662,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 2.404,
      "step": 235
    },
    {
      "epoch": 0.020251028372534542,
      "grad_norm": 3.328792095184326,
      "learning_rate": 3.94660365002137e-05,
      "loss": 2.2906,
      "step": 240
    },
    {
      "epoch": 0.020672924796962346,
      "grad_norm": 3.6538376808166504,
      "learning_rate": 3.740109693074375e-05,
      "loss": 2.1915,
      "step": 245
    },
    {
      "epoch": 0.02109482122139015,
      "grad_norm": 5.356569290161133,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 2.2162,
      "step": 250
    },
    {
      "epoch": 0.021516717645817952,
      "grad_norm": 1.7316887378692627,
      "learning_rate": 3.334301026289712e-05,
      "loss": 2.3502,
      "step": 255
    },
    {
      "epoch": 0.021938614070245756,
      "grad_norm": 1.6922351121902466,
      "learning_rate": 3.135717611098458e-05,
      "loss": 2.5703,
      "step": 260
    },
    {
      "epoch": 0.02236051049467356,
      "grad_norm": 1.7247025966644287,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 2.3065,
      "step": 265
    },
    {
      "epoch": 0.02278240691910136,
      "grad_norm": 2.0513594150543213,
      "learning_rate": 2.748981275911633e-05,
      "loss": 2.4317,
      "step": 270
    },
    {
      "epoch": 0.023204303343529162,
      "grad_norm": 2.1472418308258057,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 2.5487,
      "step": 275
    },
    {
      "epoch": 0.023626199767956966,
      "grad_norm": 2.583995819091797,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 2.2386,
      "step": 280
    },
    {
      "epoch": 0.02404809619238477,
      "grad_norm": 2.790865182876587,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 2.4509,
      "step": 285
    },
    {
      "epoch": 0.024469992616812573,
      "grad_norm": 3.544792890548706,
      "learning_rate": 2.026834118478567e-05,
      "loss": 2.2631,
      "step": 290
    },
    {
      "epoch": 0.024891889041240376,
      "grad_norm": 3.6801047325134277,
      "learning_rate": 1.858900013521788e-05,
      "loss": 2.3196,
      "step": 295
    },
    {
      "epoch": 0.02531378546566818,
      "grad_norm": 4.780126571655273,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 2.2988,
      "step": 300
    },
    {
      "epoch": 0.02531378546566818,
      "eval_loss": 0.5806547403335571,
      "eval_runtime": 664.2863,
      "eval_samples_per_second": 7.512,
      "eval_steps_per_second": 3.756,
      "step": 300
    },
    {
      "epoch": 0.025735681890095983,
      "grad_norm": 1.7426536083221436,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 2.4235,
      "step": 305
    },
    {
      "epoch": 0.026157578314523783,
      "grad_norm": 1.7099363803863525,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 2.4581,
      "step": 310
    },
    {
      "epoch": 0.026579474738951586,
      "grad_norm": 1.8494468927383423,
      "learning_rate": 1.246638473736378e-05,
      "loss": 2.4114,
      "step": 315
    },
    {
      "epoch": 0.02700137116337939,
      "grad_norm": 2.0955967903137207,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 2.1463,
      "step": 320
    },
    {
      "epoch": 0.027423267587807193,
      "grad_norm": 2.267841339111328,
      "learning_rate": 9.800143481652979e-06,
      "loss": 2.4545,
      "step": 325
    },
    {
      "epoch": 0.027845164012234996,
      "grad_norm": 2.894498825073242,
      "learning_rate": 8.574517537807897e-06,
      "loss": 2.1647,
      "step": 330
    },
    {
      "epoch": 0.0282670604366628,
      "grad_norm": 2.9159038066864014,
      "learning_rate": 7.423543113334436e-06,
      "loss": 2.2689,
      "step": 335
    },
    {
      "epoch": 0.028688956861090603,
      "grad_norm": 2.7776429653167725,
      "learning_rate": 6.349294341940593e-06,
      "loss": 2.1054,
      "step": 340
    },
    {
      "epoch": 0.029110853285518407,
      "grad_norm": 3.911658763885498,
      "learning_rate": 5.353707092521582e-06,
      "loss": 2.2094,
      "step": 345
    },
    {
      "epoch": 0.029532749709946206,
      "grad_norm": 5.785114765167236,
      "learning_rate": 4.43857548059321e-06,
      "loss": 2.155,
      "step": 350
    },
    {
      "epoch": 0.02995464613437401,
      "grad_norm": 1.8787931203842163,
      "learning_rate": 3.605548635174533e-06,
      "loss": 2.3989,
      "step": 355
    },
    {
      "epoch": 0.030376542558801813,
      "grad_norm": 1.836938738822937,
      "learning_rate": 2.85612772694579e-06,
      "loss": 2.4303,
      "step": 360
    },
    {
      "epoch": 0.030798438983229617,
      "grad_norm": 1.9560879468917847,
      "learning_rate": 2.191663263037458e-06,
      "loss": 2.3195,
      "step": 365
    },
    {
      "epoch": 0.03122033540765742,
      "grad_norm": 2.2626380920410156,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 2.3719,
      "step": 370
    },
    {
      "epoch": 0.03164223183208522,
      "grad_norm": 2.454702377319336,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 2.2572,
      "step": 375
    },
    {
      "epoch": 0.03206412825651302,
      "grad_norm": 2.8336808681488037,
      "learning_rate": 7.192044826145771e-07,
      "loss": 2.3476,
      "step": 380
    },
    {
      "epoch": 0.03248602468094083,
      "grad_norm": 3.31632137298584,
      "learning_rate": 4.049782370561583e-07,
      "loss": 2.2668,
      "step": 385
    },
    {
      "epoch": 0.03290792110536863,
      "grad_norm": 3.0663788318634033,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 2.0996,
      "step": 390
    },
    {
      "epoch": 0.033329817529796434,
      "grad_norm": 3.7214670181274414,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 2.2702,
      "step": 395
    },
    {
      "epoch": 0.03375171395422424,
      "grad_norm": 5.355175495147705,
      "learning_rate": 0.0,
      "loss": 1.93,
      "step": 400
    },
    {
      "epoch": 0.03375171395422424,
      "eval_loss": 0.5745403170585632,
      "eval_runtime": 665.1806,
      "eval_samples_per_second": 7.502,
      "eval_steps_per_second": 3.751,
      "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": 2.9930081753235456e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}