{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5809731299927379,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014524328249818446,
      "eval_loss": 1.3245296478271484,
      "eval_runtime": 9.9033,
      "eval_samples_per_second": 29.283,
      "eval_steps_per_second": 14.642,
      "step": 1
    },
    {
      "epoch": 0.007262164124909223,
      "grad_norm": 0.3581368923187256,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.0795,
      "step": 5
    },
    {
      "epoch": 0.014524328249818447,
      "grad_norm": 0.4703170359134674,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.1852,
      "step": 10
    },
    {
      "epoch": 0.02178649237472767,
      "grad_norm": 0.4361855089664459,
      "learning_rate": 5e-05,
      "loss": 1.2702,
      "step": 15
    },
    {
      "epoch": 0.029048656499636893,
      "grad_norm": 0.5707547068595886,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.2406,
      "step": 20
    },
    {
      "epoch": 0.03631082062454612,
      "grad_norm": 0.7209172248840332,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.1345,
      "step": 25
    },
    {
      "epoch": 0.04357298474945534,
      "grad_norm": 0.6977463960647583,
      "learning_rate": 0.0001,
      "loss": 0.9385,
      "step": 30
    },
    {
      "epoch": 0.050835148874364564,
      "grad_norm": 0.6791632771492004,
      "learning_rate": 9.995494831023409e-05,
      "loss": 0.7848,
      "step": 35
    },
    {
      "epoch": 0.05809731299927379,
      "grad_norm": 0.543228268623352,
      "learning_rate": 9.981987442712633e-05,
      "loss": 0.6899,
      "step": 40
    },
    {
      "epoch": 0.06535947712418301,
      "grad_norm": 0.5850688815116882,
      "learning_rate": 9.959502176294383e-05,
      "loss": 0.5664,
      "step": 45
    },
    {
      "epoch": 0.07262164124909223,
      "grad_norm": 0.7177279591560364,
      "learning_rate": 9.928079551738543e-05,
      "loss": 0.5359,
      "step": 50
    },
    {
      "epoch": 0.07988380537400146,
      "grad_norm": 0.5556406378746033,
      "learning_rate": 9.887776194738432e-05,
      "loss": 0.4749,
      "step": 55
    },
    {
      "epoch": 0.08714596949891068,
      "grad_norm": 0.5208691954612732,
      "learning_rate": 9.838664734667495e-05,
      "loss": 0.4862,
      "step": 60
    },
    {
      "epoch": 0.0944081336238199,
      "grad_norm": 0.35588008165359497,
      "learning_rate": 9.780833673696254e-05,
      "loss": 0.3491,
      "step": 65
    },
    {
      "epoch": 0.10167029774872913,
      "grad_norm": 0.6063373684883118,
      "learning_rate": 9.714387227305422e-05,
      "loss": 0.5132,
      "step": 70
    },
    {
      "epoch": 0.10893246187363835,
      "grad_norm": 0.4741774797439575,
      "learning_rate": 9.639445136482548e-05,
      "loss": 0.4523,
      "step": 75
    },
    {
      "epoch": 0.11619462599854757,
      "grad_norm": 0.4634912610054016,
      "learning_rate": 9.55614245194068e-05,
      "loss": 0.4385,
      "step": 80
    },
    {
      "epoch": 0.12345679012345678,
      "grad_norm": 0.4749130308628082,
      "learning_rate": 9.464629290747842e-05,
      "loss": 0.4119,
      "step": 85
    },
    {
      "epoch": 0.13071895424836602,
      "grad_norm": 0.5013887286186218,
      "learning_rate": 9.365070565805941e-05,
      "loss": 0.3721,
      "step": 90
    },
    {
      "epoch": 0.13798111837327523,
      "grad_norm": 0.6452203989028931,
      "learning_rate": 9.257645688666556e-05,
      "loss": 0.5071,
      "step": 95
    },
    {
      "epoch": 0.14524328249818447,
      "grad_norm": 0.6926259994506836,
      "learning_rate": 9.142548246219212e-05,
      "loss": 0.3755,
      "step": 100
    },
    {
      "epoch": 0.14524328249818447,
      "eval_loss": 0.4264805316925049,
      "eval_runtime": 9.893,
      "eval_samples_per_second": 29.314,
      "eval_steps_per_second": 14.657,
      "step": 100
    },
    {
      "epoch": 0.15250544662309368,
      "grad_norm": 0.4893040060997009,
      "learning_rate": 9.019985651834703e-05,
      "loss": 0.4813,
      "step": 105
    },
    {
      "epoch": 0.15976761074800291,
      "grad_norm": 0.4910524785518646,
      "learning_rate": 8.890178771592199e-05,
      "loss": 0.4276,
      "step": 110
    },
    {
      "epoch": 0.16702977487291212,
      "grad_norm": 0.35125866532325745,
      "learning_rate": 8.753361526263621e-05,
      "loss": 0.4712,
      "step": 115
    },
    {
      "epoch": 0.17429193899782136,
      "grad_norm": 0.5084987878799438,
      "learning_rate": 8.609780469772623e-05,
      "loss": 0.351,
      "step": 120
    },
    {
      "epoch": 0.18155410312273057,
      "grad_norm": 0.5584767460823059,
      "learning_rate": 8.459694344887732e-05,
      "loss": 0.4581,
      "step": 125
    },
    {
      "epoch": 0.1888162672476398,
      "grad_norm": 0.6026501059532166,
      "learning_rate": 8.303373616950408e-05,
      "loss": 0.4256,
      "step": 130
    },
    {
      "epoch": 0.19607843137254902,
      "grad_norm": 0.5166791081428528,
      "learning_rate": 8.141099986478212e-05,
      "loss": 0.3086,
      "step": 135
    },
    {
      "epoch": 0.20334059549745825,
      "grad_norm": 0.47290974855422974,
      "learning_rate": 7.973165881521434e-05,
      "loss": 0.2829,
      "step": 140
    },
    {
      "epoch": 0.21060275962236746,
      "grad_norm": 0.8857648968696594,
      "learning_rate": 7.799873930687978e-05,
      "loss": 0.3925,
      "step": 145
    },
    {
      "epoch": 0.2178649237472767,
      "grad_norm": 0.556354820728302,
      "learning_rate": 7.621536417786159e-05,
      "loss": 0.3179,
      "step": 150
    },
    {
      "epoch": 0.2251270878721859,
      "grad_norm": 0.5451553463935852,
      "learning_rate": 7.438474719068173e-05,
      "loss": 0.533,
      "step": 155
    },
    {
      "epoch": 0.23238925199709515,
      "grad_norm": 0.4838148355484009,
      "learning_rate": 7.251018724088367e-05,
      "loss": 0.3915,
      "step": 160
    },
    {
      "epoch": 0.23965141612200436,
      "grad_norm": 0.5822657346725464,
      "learning_rate": 7.059506241219965e-05,
      "loss": 0.3773,
      "step": 165
    },
    {
      "epoch": 0.24691358024691357,
      "grad_norm": 0.3328821063041687,
      "learning_rate": 6.864282388901544e-05,
      "loss": 0.3349,
      "step": 170
    },
    {
      "epoch": 0.2541757443718228,
      "grad_norm": 0.6934670805931091,
      "learning_rate": 6.665698973710288e-05,
      "loss": 0.3541,
      "step": 175
    },
    {
      "epoch": 0.26143790849673204,
      "grad_norm": 0.510351836681366,
      "learning_rate": 6.464113856382752e-05,
      "loss": 0.3289,
      "step": 180
    },
    {
      "epoch": 0.26870007262164125,
      "grad_norm": 0.44297555088996887,
      "learning_rate": 6.259890306925627e-05,
      "loss": 0.3353,
      "step": 185
    },
    {
      "epoch": 0.27596223674655046,
      "grad_norm": 0.676437497138977,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 0.4069,
      "step": 190
    },
    {
      "epoch": 0.28322440087145967,
      "grad_norm": 0.5199609398841858,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 0.4057,
      "step": 195
    },
    {
      "epoch": 0.29048656499636893,
      "grad_norm": 1.008725643157959,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 0.4285,
      "step": 200
    },
    {
      "epoch": 0.29048656499636893,
      "eval_loss": 0.3880468010902405,
      "eval_runtime": 9.8865,
      "eval_samples_per_second": 29.333,
      "eval_steps_per_second": 14.667,
      "step": 200
    },
    {
      "epoch": 0.29774872912127814,
      "grad_norm": 0.51472407579422,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 0.4026,
      "step": 205
    },
    {
      "epoch": 0.30501089324618735,
      "grad_norm": 0.5710492134094238,
      "learning_rate": 5.212206015980742e-05,
      "loss": 0.4438,
      "step": 210
    },
    {
      "epoch": 0.31227305737109656,
      "grad_norm": 0.42128708958625793,
      "learning_rate": 5e-05,
      "loss": 0.3745,
      "step": 215
    },
    {
      "epoch": 0.31953522149600583,
      "grad_norm": 0.537081778049469,
      "learning_rate": 4.78779398401926e-05,
      "loss": 0.4259,
      "step": 220
    },
    {
      "epoch": 0.32679738562091504,
      "grad_norm": 0.5179123878479004,
      "learning_rate": 4.575970377622456e-05,
      "loss": 0.331,
      "step": 225
    },
    {
      "epoch": 0.33405954974582425,
      "grad_norm": 0.35773134231567383,
      "learning_rate": 4.364910901265606e-05,
      "loss": 0.286,
      "step": 230
    },
    {
      "epoch": 0.34132171387073346,
      "grad_norm": 0.6046307682991028,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 0.4355,
      "step": 235
    },
    {
      "epoch": 0.3485838779956427,
      "grad_norm": 0.6580352783203125,
      "learning_rate": 3.94660365002137e-05,
      "loss": 0.4705,
      "step": 240
    },
    {
      "epoch": 0.35584604212055193,
      "grad_norm": 0.3669753968715668,
      "learning_rate": 3.740109693074375e-05,
      "loss": 0.2579,
      "step": 245
    },
    {
      "epoch": 0.36310820624546114,
      "grad_norm": 0.6125357747077942,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 0.3295,
      "step": 250
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 0.5149029493331909,
      "learning_rate": 3.334301026289712e-05,
      "loss": 0.3844,
      "step": 255
    },
    {
      "epoch": 0.3776325344952796,
      "grad_norm": 0.4156867563724518,
      "learning_rate": 3.135717611098458e-05,
      "loss": 0.3641,
      "step": 260
    },
    {
      "epoch": 0.3848946986201888,
      "grad_norm": 0.5225069522857666,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 0.3841,
      "step": 265
    },
    {
      "epoch": 0.39215686274509803,
      "grad_norm": 0.6833149194717407,
      "learning_rate": 2.748981275911633e-05,
      "loss": 0.4008,
      "step": 270
    },
    {
      "epoch": 0.39941902687000724,
      "grad_norm": 0.5781005620956421,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 0.4053,
      "step": 275
    },
    {
      "epoch": 0.4066811909949165,
      "grad_norm": 0.4401971101760864,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 0.422,
      "step": 280
    },
    {
      "epoch": 0.4139433551198257,
      "grad_norm": 0.5976965427398682,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 0.4001,
      "step": 285
    },
    {
      "epoch": 0.4212055192447349,
      "grad_norm": 0.48907601833343506,
      "learning_rate": 2.026834118478567e-05,
      "loss": 0.4062,
      "step": 290
    },
    {
      "epoch": 0.42846768336964414,
      "grad_norm": 0.5775054097175598,
      "learning_rate": 1.858900013521788e-05,
      "loss": 0.287,
      "step": 295
    },
    {
      "epoch": 0.4357298474945534,
      "grad_norm": 0.6676799058914185,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 0.3198,
      "step": 300
    },
    {
      "epoch": 0.4357298474945534,
      "eval_loss": 0.3715769946575165,
      "eval_runtime": 9.8837,
      "eval_samples_per_second": 29.341,
      "eval_steps_per_second": 14.671,
      "step": 300
    },
    {
      "epoch": 0.4429920116194626,
      "grad_norm": 0.47516536712646484,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 0.3978,
      "step": 305
    },
    {
      "epoch": 0.4502541757443718,
      "grad_norm": 0.625796914100647,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 0.3991,
      "step": 310
    },
    {
      "epoch": 0.45751633986928103,
      "grad_norm": 0.5647926926612854,
      "learning_rate": 1.246638473736378e-05,
      "loss": 0.382,
      "step": 315
    },
    {
      "epoch": 0.4647785039941903,
      "grad_norm": 0.5255870223045349,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 0.4099,
      "step": 320
    },
    {
      "epoch": 0.4720406681190995,
      "grad_norm": 0.4743548631668091,
      "learning_rate": 9.800143481652979e-06,
      "loss": 0.3151,
      "step": 325
    },
    {
      "epoch": 0.4793028322440087,
      "grad_norm": 0.4534391164779663,
      "learning_rate": 8.574517537807897e-06,
      "loss": 0.3049,
      "step": 330
    },
    {
      "epoch": 0.4865649963689179,
      "grad_norm": 0.47613316774368286,
      "learning_rate": 7.423543113334436e-06,
      "loss": 0.3303,
      "step": 335
    },
    {
      "epoch": 0.49382716049382713,
      "grad_norm": 0.8216122984886169,
      "learning_rate": 6.349294341940593e-06,
      "loss": 0.4105,
      "step": 340
    },
    {
      "epoch": 0.5010893246187363,
      "grad_norm": 0.8250996470451355,
      "learning_rate": 5.353707092521582e-06,
      "loss": 0.3641,
      "step": 345
    },
    {
      "epoch": 0.5083514887436456,
      "grad_norm": 0.89671391248703,
      "learning_rate": 4.43857548059321e-06,
      "loss": 0.3283,
      "step": 350
    },
    {
      "epoch": 0.5156136528685549,
      "grad_norm": 0.58024662733078,
      "learning_rate": 3.605548635174533e-06,
      "loss": 0.2993,
      "step": 355
    },
    {
      "epoch": 0.5228758169934641,
      "grad_norm": 0.5099973678588867,
      "learning_rate": 2.85612772694579e-06,
      "loss": 0.4482,
      "step": 360
    },
    {
      "epoch": 0.5301379811183733,
      "grad_norm": 0.4654390215873718,
      "learning_rate": 2.191663263037458e-06,
      "loss": 0.39,
      "step": 365
    },
    {
      "epoch": 0.5374001452432825,
      "grad_norm": 0.53952556848526,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 0.3133,
      "step": 370
    },
    {
      "epoch": 0.5446623093681917,
      "grad_norm": 0.6697345972061157,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 0.3592,
      "step": 375
    },
    {
      "epoch": 0.5519244734931009,
      "grad_norm": 0.4165039658546448,
      "learning_rate": 7.192044826145771e-07,
      "loss": 0.3901,
      "step": 380
    },
    {
      "epoch": 0.5591866376180101,
      "grad_norm": 0.5658162236213684,
      "learning_rate": 4.049782370561583e-07,
      "loss": 0.3592,
      "step": 385
    },
    {
      "epoch": 0.5664488017429193,
      "grad_norm": 0.6180537343025208,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 0.4346,
      "step": 390
    },
    {
      "epoch": 0.5737109658678287,
      "grad_norm": 0.6906850934028625,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 0.3313,
      "step": 395
    },
    {
      "epoch": 0.5809731299927379,
      "grad_norm": 0.798138439655304,
      "learning_rate": 0.0,
      "loss": 0.455,
      "step": 400
    },
    {
      "epoch": 0.5809731299927379,
      "eval_loss": 0.36389341950416565,
      "eval_runtime": 9.8878,
      "eval_samples_per_second": 29.329,
      "eval_steps_per_second": 14.664,
      "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": 3.18457195266048e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}