{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03364030108069467,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.410075270173668e-05,
      "eval_loss": 2.455552101135254,
      "eval_runtime": 138.2596,
      "eval_samples_per_second": 36.214,
      "eval_steps_per_second": 18.111,
      "step": 1
    },
    {
      "epoch": 0.0004205037635086834,
      "grad_norm": 0.06288853287696838,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 2.566,
      "step": 5
    },
    {
      "epoch": 0.0008410075270173668,
      "grad_norm": 0.0672573670744896,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.4565,
      "step": 10
    },
    {
      "epoch": 0.0012615112905260501,
      "grad_norm": 0.07510022819042206,
      "learning_rate": 5e-05,
      "loss": 2.3643,
      "step": 15
    },
    {
      "epoch": 0.0016820150540347335,
      "grad_norm": 0.0756649598479271,
      "learning_rate": 6.666666666666667e-05,
      "loss": 2.5781,
      "step": 20
    },
    {
      "epoch": 0.002102518817543417,
      "grad_norm": 0.09395594894886017,
      "learning_rate": 8.333333333333334e-05,
      "loss": 2.4296,
      "step": 25
    },
    {
      "epoch": 0.0025230225810521003,
      "grad_norm": 0.10693749040365219,
      "learning_rate": 0.0001,
      "loss": 2.3956,
      "step": 30
    },
    {
      "epoch": 0.0029435263445607837,
      "grad_norm": 0.1340353637933731,
      "learning_rate": 9.995494831023409e-05,
      "loss": 2.3548,
      "step": 35
    },
    {
      "epoch": 0.003364030108069467,
      "grad_norm": 0.16637980937957764,
      "learning_rate": 9.981987442712633e-05,
      "loss": 2.3691,
      "step": 40
    },
    {
      "epoch": 0.0037845338715781504,
      "grad_norm": 0.17769795656204224,
      "learning_rate": 9.959502176294383e-05,
      "loss": 2.392,
      "step": 45
    },
    {
      "epoch": 0.004205037635086834,
      "grad_norm": 0.4028211534023285,
      "learning_rate": 9.928079551738543e-05,
      "loss": 2.4662,
      "step": 50
    },
    {
      "epoch": 0.004625541398595517,
      "grad_norm": 0.09516683220863342,
      "learning_rate": 9.887776194738432e-05,
      "loss": 2.498,
      "step": 55
    },
    {
      "epoch": 0.005046045162104201,
      "grad_norm": 0.11103392392396927,
      "learning_rate": 9.838664734667495e-05,
      "loss": 2.2964,
      "step": 60
    },
    {
      "epoch": 0.005466548925612884,
      "grad_norm": 0.13888299465179443,
      "learning_rate": 9.780833673696254e-05,
      "loss": 2.421,
      "step": 65
    },
    {
      "epoch": 0.005887052689121567,
      "grad_norm": 0.1731582134962082,
      "learning_rate": 9.714387227305422e-05,
      "loss": 2.1062,
      "step": 70
    },
    {
      "epoch": 0.006307556452630251,
      "grad_norm": 0.16878341138362885,
      "learning_rate": 9.639445136482548e-05,
      "loss": 2.2202,
      "step": 75
    },
    {
      "epoch": 0.006728060216138934,
      "grad_norm": 0.15920491516590118,
      "learning_rate": 9.55614245194068e-05,
      "loss": 2.2138,
      "step": 80
    },
    {
      "epoch": 0.0071485639796476175,
      "grad_norm": 0.1858222931623459,
      "learning_rate": 9.464629290747842e-05,
      "loss": 2.2224,
      "step": 85
    },
    {
      "epoch": 0.007569067743156301,
      "grad_norm": 0.27493521571159363,
      "learning_rate": 9.365070565805941e-05,
      "loss": 2.1246,
      "step": 90
    },
    {
      "epoch": 0.007989571506664985,
      "grad_norm": 0.26363685727119446,
      "learning_rate": 9.257645688666556e-05,
      "loss": 2.1235,
      "step": 95
    },
    {
      "epoch": 0.008410075270173668,
      "grad_norm": 0.5503014922142029,
      "learning_rate": 9.142548246219212e-05,
      "loss": 2.221,
      "step": 100
    },
    {
      "epoch": 0.008410075270173668,
      "eval_loss": 2.2321887016296387,
      "eval_runtime": 137.1448,
      "eval_samples_per_second": 36.509,
      "eval_steps_per_second": 18.258,
      "step": 100
    },
    {
      "epoch": 0.008830579033682352,
      "grad_norm": 0.16289430856704712,
      "learning_rate": 9.019985651834703e-05,
      "loss": 2.5116,
      "step": 105
    },
    {
      "epoch": 0.009251082797191034,
      "grad_norm": 0.1564548909664154,
      "learning_rate": 8.890178771592199e-05,
      "loss": 2.2799,
      "step": 110
    },
    {
      "epoch": 0.009671586560699719,
      "grad_norm": 0.16099359095096588,
      "learning_rate": 8.753361526263621e-05,
      "loss": 2.1965,
      "step": 115
    },
    {
      "epoch": 0.010092090324208401,
      "grad_norm": 0.14875778555870056,
      "learning_rate": 8.609780469772623e-05,
      "loss": 2.2595,
      "step": 120
    },
    {
      "epoch": 0.010512594087717085,
      "grad_norm": 0.1486121267080307,
      "learning_rate": 8.459694344887732e-05,
      "loss": 2.2693,
      "step": 125
    },
    {
      "epoch": 0.010933097851225768,
      "grad_norm": 0.1574985682964325,
      "learning_rate": 8.303373616950408e-05,
      "loss": 2.1078,
      "step": 130
    },
    {
      "epoch": 0.011353601614734452,
      "grad_norm": 0.17520491778850555,
      "learning_rate": 8.141099986478212e-05,
      "loss": 1.9398,
      "step": 135
    },
    {
      "epoch": 0.011774105378243135,
      "grad_norm": 0.27182435989379883,
      "learning_rate": 7.973165881521434e-05,
      "loss": 2.2749,
      "step": 140
    },
    {
      "epoch": 0.012194609141751819,
      "grad_norm": 0.3976014256477356,
      "learning_rate": 7.799873930687978e-05,
      "loss": 2.21,
      "step": 145
    },
    {
      "epoch": 0.012615112905260501,
      "grad_norm": 0.5776176452636719,
      "learning_rate": 7.621536417786159e-05,
      "loss": 2.3219,
      "step": 150
    },
    {
      "epoch": 0.013035616668769186,
      "grad_norm": 0.15068869292736053,
      "learning_rate": 7.438474719068173e-05,
      "loss": 2.5078,
      "step": 155
    },
    {
      "epoch": 0.013456120432277868,
      "grad_norm": 0.1611473262310028,
      "learning_rate": 7.251018724088367e-05,
      "loss": 2.4107,
      "step": 160
    },
    {
      "epoch": 0.013876624195786552,
      "grad_norm": 0.17580749094486237,
      "learning_rate": 7.059506241219965e-05,
      "loss": 2.2559,
      "step": 165
    },
    {
      "epoch": 0.014297127959295235,
      "grad_norm": 0.16627754271030426,
      "learning_rate": 6.864282388901544e-05,
      "loss": 2.2975,
      "step": 170
    },
    {
      "epoch": 0.01471763172280392,
      "grad_norm": 0.18935278058052063,
      "learning_rate": 6.665698973710288e-05,
      "loss": 2.3638,
      "step": 175
    },
    {
      "epoch": 0.015138135486312602,
      "grad_norm": 0.16785839200019836,
      "learning_rate": 6.464113856382752e-05,
      "loss": 2.0706,
      "step": 180
    },
    {
      "epoch": 0.015558639249821286,
      "grad_norm": 0.19793659448623657,
      "learning_rate": 6.259890306925627e-05,
      "loss": 2.2069,
      "step": 185
    },
    {
      "epoch": 0.01597914301332997,
      "grad_norm": 0.20442405343055725,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 2.0747,
      "step": 190
    },
    {
      "epoch": 0.016399646776838653,
      "grad_norm": 0.291321337223053,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 2.0967,
      "step": 195
    },
    {
      "epoch": 0.016820150540347335,
      "grad_norm": 0.5253951549530029,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 2.2031,
      "step": 200
    },
    {
      "epoch": 0.016820150540347335,
      "eval_loss": 2.1990108489990234,
      "eval_runtime": 137.8422,
      "eval_samples_per_second": 36.324,
      "eval_steps_per_second": 18.166,
      "step": 200
    },
    {
      "epoch": 0.017240654303856018,
      "grad_norm": 0.1373487263917923,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 2.4321,
      "step": 205
    },
    {
      "epoch": 0.017661158067364704,
      "grad_norm": 0.13446733355522156,
      "learning_rate": 5.212206015980742e-05,
      "loss": 2.3212,
      "step": 210
    },
    {
      "epoch": 0.018081661830873386,
      "grad_norm": 0.15374958515167236,
      "learning_rate": 5e-05,
      "loss": 2.1707,
      "step": 215
    },
    {
      "epoch": 0.01850216559438207,
      "grad_norm": 0.17386586964130402,
      "learning_rate": 4.78779398401926e-05,
      "loss": 2.2506,
      "step": 220
    },
    {
      "epoch": 0.018922669357890755,
      "grad_norm": 0.16173112392425537,
      "learning_rate": 4.575970377622456e-05,
      "loss": 2.1609,
      "step": 225
    },
    {
      "epoch": 0.019343173121399437,
      "grad_norm": 0.2234823852777481,
      "learning_rate": 4.364910901265606e-05,
      "loss": 2.2917,
      "step": 230
    },
    {
      "epoch": 0.01976367688490812,
      "grad_norm": 0.18885092437267303,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 2.2025,
      "step": 235
    },
    {
      "epoch": 0.020184180648416802,
      "grad_norm": 0.2342340499162674,
      "learning_rate": 3.94660365002137e-05,
      "loss": 2.2165,
      "step": 240
    },
    {
      "epoch": 0.02060468441192549,
      "grad_norm": 0.2419833242893219,
      "learning_rate": 3.740109693074375e-05,
      "loss": 2.0213,
      "step": 245
    },
    {
      "epoch": 0.02102518817543417,
      "grad_norm": 0.5271613597869873,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 2.4064,
      "step": 250
    },
    {
      "epoch": 0.021445691938942853,
      "grad_norm": 0.1288193166255951,
      "learning_rate": 3.334301026289712e-05,
      "loss": 2.3969,
      "step": 255
    },
    {
      "epoch": 0.021866195702451536,
      "grad_norm": 0.13628017902374268,
      "learning_rate": 3.135717611098458e-05,
      "loss": 2.4522,
      "step": 260
    },
    {
      "epoch": 0.022286699465960222,
      "grad_norm": 0.18752817809581757,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 2.2498,
      "step": 265
    },
    {
      "epoch": 0.022707203229468904,
      "grad_norm": 0.15107370913028717,
      "learning_rate": 2.748981275911633e-05,
      "loss": 2.2232,
      "step": 270
    },
    {
      "epoch": 0.023127706992977587,
      "grad_norm": 0.16715684533119202,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 2.3243,
      "step": 275
    },
    {
      "epoch": 0.02354821075648627,
      "grad_norm": 0.1846175491809845,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 2.0287,
      "step": 280
    },
    {
      "epoch": 0.023968714519994955,
      "grad_norm": 0.2120099663734436,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 2.172,
      "step": 285
    },
    {
      "epoch": 0.024389218283503638,
      "grad_norm": 0.2088957130908966,
      "learning_rate": 2.026834118478567e-05,
      "loss": 2.1586,
      "step": 290
    },
    {
      "epoch": 0.02480972204701232,
      "grad_norm": 0.314209520816803,
      "learning_rate": 1.858900013521788e-05,
      "loss": 2.0427,
      "step": 295
    },
    {
      "epoch": 0.025230225810521003,
      "grad_norm": 0.5395681858062744,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 2.0398,
      "step": 300
    },
    {
      "epoch": 0.025230225810521003,
      "eval_loss": 2.1906521320343018,
      "eval_runtime": 138.2662,
      "eval_samples_per_second": 36.213,
      "eval_steps_per_second": 18.11,
      "step": 300
    },
    {
      "epoch": 0.02565072957402969,
      "grad_norm": 0.12976689636707306,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 2.325,
      "step": 305
    },
    {
      "epoch": 0.02607123333753837,
      "grad_norm": 0.3184930682182312,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 2.2399,
      "step": 310
    },
    {
      "epoch": 0.026491737101047054,
      "grad_norm": 0.16288700699806213,
      "learning_rate": 1.246638473736378e-05,
      "loss": 2.292,
      "step": 315
    },
    {
      "epoch": 0.026912240864555736,
      "grad_norm": 0.14881478250026703,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 2.1848,
      "step": 320
    },
    {
      "epoch": 0.027332744628064422,
      "grad_norm": 0.19080372154712677,
      "learning_rate": 9.800143481652979e-06,
      "loss": 2.262,
      "step": 325
    },
    {
      "epoch": 0.027753248391573105,
      "grad_norm": 0.1788197010755539,
      "learning_rate": 8.574517537807897e-06,
      "loss": 2.0933,
      "step": 330
    },
    {
      "epoch": 0.028173752155081788,
      "grad_norm": 0.22491934895515442,
      "learning_rate": 7.423543113334436e-06,
      "loss": 2.0307,
      "step": 335
    },
    {
      "epoch": 0.02859425591859047,
      "grad_norm": 0.24803785979747772,
      "learning_rate": 6.349294341940593e-06,
      "loss": 2.1817,
      "step": 340
    },
    {
      "epoch": 0.029014759682099156,
      "grad_norm": 0.2737451195716858,
      "learning_rate": 5.353707092521582e-06,
      "loss": 2.0864,
      "step": 345
    },
    {
      "epoch": 0.02943526344560784,
      "grad_norm": 0.5372247099876404,
      "learning_rate": 4.43857548059321e-06,
      "loss": 2.0402,
      "step": 350
    },
    {
      "epoch": 0.02985576720911652,
      "grad_norm": 0.12413191050291061,
      "learning_rate": 3.605548635174533e-06,
      "loss": 2.4881,
      "step": 355
    },
    {
      "epoch": 0.030276270972625204,
      "grad_norm": 0.14699317514896393,
      "learning_rate": 2.85612772694579e-06,
      "loss": 2.3984,
      "step": 360
    },
    {
      "epoch": 0.03069677473613389,
      "grad_norm": 0.16684670746326447,
      "learning_rate": 2.191663263037458e-06,
      "loss": 2.1938,
      "step": 365
    },
    {
      "epoch": 0.031117278499642572,
      "grad_norm": 0.14887583255767822,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 2.1288,
      "step": 370
    },
    {
      "epoch": 0.03153778226315126,
      "grad_norm": 0.17945723235607147,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 2.3047,
      "step": 375
    },
    {
      "epoch": 0.03195828602665994,
      "grad_norm": 0.19046396017074585,
      "learning_rate": 7.192044826145771e-07,
      "loss": 2.1788,
      "step": 380
    },
    {
      "epoch": 0.03237878979016862,
      "grad_norm": 0.19645310938358307,
      "learning_rate": 4.049782370561583e-07,
      "loss": 2.2291,
      "step": 385
    },
    {
      "epoch": 0.032799293553677306,
      "grad_norm": 0.2140706181526184,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 2.0335,
      "step": 390
    },
    {
      "epoch": 0.03321979731718599,
      "grad_norm": 0.31230586767196655,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 2.0961,
      "step": 395
    },
    {
      "epoch": 0.03364030108069467,
      "grad_norm": 0.5311707854270935,
      "learning_rate": 0.0,
      "loss": 2.0589,
      "step": 400
    },
    {
      "epoch": 0.03364030108069467,
      "eval_loss": 2.189105987548828,
      "eval_runtime": 138.0331,
      "eval_samples_per_second": 36.274,
      "eval_steps_per_second": 18.141,
      "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": 6279181392936960.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}