{
  "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": 10.0307,
      "eval_samples_per_second": 28.911,
      "eval_steps_per_second": 14.456,
      "step": 1
    },
    {
      "epoch": 0.007262164124909223,
      "grad_norm": 0.3432396650314331,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.0786,
      "step": 5
    },
    {
      "epoch": 0.014524328249818447,
      "grad_norm": 0.4573116898536682,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.1861,
      "step": 10
    },
    {
      "epoch": 0.02178649237472767,
      "grad_norm": 0.42056816816329956,
      "learning_rate": 5e-05,
      "loss": 1.2691,
      "step": 15
    },
    {
      "epoch": 0.029048656499636893,
      "grad_norm": 0.5584819912910461,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.2434,
      "step": 20
    },
    {
      "epoch": 0.03631082062454612,
      "grad_norm": 0.7118600010871887,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.1387,
      "step": 25
    },
    {
      "epoch": 0.04357298474945534,
      "grad_norm": 0.6868016719818115,
      "learning_rate": 0.0001,
      "loss": 0.9437,
      "step": 30
    },
    {
      "epoch": 0.050835148874364564,
      "grad_norm": 0.6688479781150818,
      "learning_rate": 9.995494831023409e-05,
      "loss": 0.7878,
      "step": 35
    },
    {
      "epoch": 0.05809731299927379,
      "grad_norm": 0.5368048548698425,
      "learning_rate": 9.981987442712633e-05,
      "loss": 0.692,
      "step": 40
    },
    {
      "epoch": 0.06535947712418301,
      "grad_norm": 0.574111819267273,
      "learning_rate": 9.959502176294383e-05,
      "loss": 0.5666,
      "step": 45
    },
    {
      "epoch": 0.07262164124909223,
      "grad_norm": 0.7118582725524902,
      "learning_rate": 9.928079551738543e-05,
      "loss": 0.5391,
      "step": 50
    },
    {
      "epoch": 0.07988380537400146,
      "grad_norm": 0.5473505854606628,
      "learning_rate": 9.887776194738432e-05,
      "loss": 0.4748,
      "step": 55
    },
    {
      "epoch": 0.08714596949891068,
      "grad_norm": 0.5047345757484436,
      "learning_rate": 9.838664734667495e-05,
      "loss": 0.4856,
      "step": 60
    },
    {
      "epoch": 0.0944081336238199,
      "grad_norm": 0.35372811555862427,
      "learning_rate": 9.780833673696254e-05,
      "loss": 0.348,
      "step": 65
    },
    {
      "epoch": 0.10167029774872913,
      "grad_norm": 0.5999704003334045,
      "learning_rate": 9.714387227305422e-05,
      "loss": 0.5124,
      "step": 70
    },
    {
      "epoch": 0.10893246187363835,
      "grad_norm": 0.4666677415370941,
      "learning_rate": 9.639445136482548e-05,
      "loss": 0.4533,
      "step": 75
    },
    {
      "epoch": 0.11619462599854757,
      "grad_norm": 0.45984530448913574,
      "learning_rate": 9.55614245194068e-05,
      "loss": 0.4386,
      "step": 80
    },
    {
      "epoch": 0.12345679012345678,
      "grad_norm": 0.4653758704662323,
      "learning_rate": 9.464629290747842e-05,
      "loss": 0.4129,
      "step": 85
    },
    {
      "epoch": 0.13071895424836602,
      "grad_norm": 0.49631646275520325,
      "learning_rate": 9.365070565805941e-05,
      "loss": 0.3732,
      "step": 90
    },
    {
      "epoch": 0.13798111837327523,
      "grad_norm": 0.6299993395805359,
      "learning_rate": 9.257645688666556e-05,
      "loss": 0.5078,
      "step": 95
    },
    {
      "epoch": 0.14524328249818447,
      "grad_norm": 0.6679750680923462,
      "learning_rate": 9.142548246219212e-05,
      "loss": 0.3762,
      "step": 100
    },
    {
      "epoch": 0.14524328249818447,
      "eval_loss": 0.42616939544677734,
      "eval_runtime": 10.0024,
      "eval_samples_per_second": 28.993,
      "eval_steps_per_second": 14.496,
      "step": 100
    },
    {
      "epoch": 0.15250544662309368,
      "grad_norm": 0.48117795586586,
      "learning_rate": 9.019985651834703e-05,
      "loss": 0.4826,
      "step": 105
    },
    {
      "epoch": 0.15976761074800291,
      "grad_norm": 0.4899686872959137,
      "learning_rate": 8.890178771592199e-05,
      "loss": 0.4264,
      "step": 110
    },
    {
      "epoch": 0.16702977487291212,
      "grad_norm": 0.3432672917842865,
      "learning_rate": 8.753361526263621e-05,
      "loss": 0.4706,
      "step": 115
    },
    {
      "epoch": 0.17429193899782136,
      "grad_norm": 0.4990599453449249,
      "learning_rate": 8.609780469772623e-05,
      "loss": 0.3511,
      "step": 120
    },
    {
      "epoch": 0.18155410312273057,
      "grad_norm": 0.5495415329933167,
      "learning_rate": 8.459694344887732e-05,
      "loss": 0.4569,
      "step": 125
    },
    {
      "epoch": 0.1888162672476398,
      "grad_norm": 0.5961700081825256,
      "learning_rate": 8.303373616950408e-05,
      "loss": 0.4265,
      "step": 130
    },
    {
      "epoch": 0.19607843137254902,
      "grad_norm": 0.5166049003601074,
      "learning_rate": 8.141099986478212e-05,
      "loss": 0.3067,
      "step": 135
    },
    {
      "epoch": 0.20334059549745825,
      "grad_norm": 0.4597107768058777,
      "learning_rate": 7.973165881521434e-05,
      "loss": 0.2833,
      "step": 140
    },
    {
      "epoch": 0.21060275962236746,
      "grad_norm": 0.9159771800041199,
      "learning_rate": 7.799873930687978e-05,
      "loss": 0.3958,
      "step": 145
    },
    {
      "epoch": 0.2178649237472767,
      "grad_norm": 0.5312595367431641,
      "learning_rate": 7.621536417786159e-05,
      "loss": 0.3202,
      "step": 150
    },
    {
      "epoch": 0.2251270878721859,
      "grad_norm": 0.5271121263504028,
      "learning_rate": 7.438474719068173e-05,
      "loss": 0.5322,
      "step": 155
    },
    {
      "epoch": 0.23238925199709515,
      "grad_norm": 0.4663078784942627,
      "learning_rate": 7.251018724088367e-05,
      "loss": 0.3921,
      "step": 160
    },
    {
      "epoch": 0.23965141612200436,
      "grad_norm": 0.5724524259567261,
      "learning_rate": 7.059506241219965e-05,
      "loss": 0.3765,
      "step": 165
    },
    {
      "epoch": 0.24691358024691357,
      "grad_norm": 0.3281378448009491,
      "learning_rate": 6.864282388901544e-05,
      "loss": 0.3337,
      "step": 170
    },
    {
      "epoch": 0.2541757443718228,
      "grad_norm": 0.6712502241134644,
      "learning_rate": 6.665698973710288e-05,
      "loss": 0.3547,
      "step": 175
    },
    {
      "epoch": 0.26143790849673204,
      "grad_norm": 0.4867268204689026,
      "learning_rate": 6.464113856382752e-05,
      "loss": 0.328,
      "step": 180
    },
    {
      "epoch": 0.26870007262164125,
      "grad_norm": 0.43125975131988525,
      "learning_rate": 6.259890306925627e-05,
      "loss": 0.3375,
      "step": 185
    },
    {
      "epoch": 0.27596223674655046,
      "grad_norm": 0.6453309059143066,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 0.41,
      "step": 190
    },
    {
      "epoch": 0.28322440087145967,
      "grad_norm": 0.5164971351623535,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 0.4044,
      "step": 195
    },
    {
      "epoch": 0.29048656499636893,
      "grad_norm": 0.9465965032577515,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 0.4252,
      "step": 200
    },
    {
      "epoch": 0.29048656499636893,
      "eval_loss": 0.3883720934391022,
      "eval_runtime": 10.0049,
      "eval_samples_per_second": 28.986,
      "eval_steps_per_second": 14.493,
      "step": 200
    },
    {
      "epoch": 0.29774872912127814,
      "grad_norm": 0.4956851899623871,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 0.4018,
      "step": 205
    },
    {
      "epoch": 0.30501089324618735,
      "grad_norm": 0.563204824924469,
      "learning_rate": 5.212206015980742e-05,
      "loss": 0.4463,
      "step": 210
    },
    {
      "epoch": 0.31227305737109656,
      "grad_norm": 0.4029311537742615,
      "learning_rate": 5e-05,
      "loss": 0.3743,
      "step": 215
    },
    {
      "epoch": 0.31953522149600583,
      "grad_norm": 0.5268800854682922,
      "learning_rate": 4.78779398401926e-05,
      "loss": 0.4264,
      "step": 220
    },
    {
      "epoch": 0.32679738562091504,
      "grad_norm": 0.5092837810516357,
      "learning_rate": 4.575970377622456e-05,
      "loss": 0.332,
      "step": 225
    },
    {
      "epoch": 0.33405954974582425,
      "grad_norm": 0.35977280139923096,
      "learning_rate": 4.364910901265606e-05,
      "loss": 0.2865,
      "step": 230
    },
    {
      "epoch": 0.34132171387073346,
      "grad_norm": 0.5845527648925781,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 0.4329,
      "step": 235
    },
    {
      "epoch": 0.3485838779956427,
      "grad_norm": 0.6270412802696228,
      "learning_rate": 3.94660365002137e-05,
      "loss": 0.4709,
      "step": 240
    },
    {
      "epoch": 0.35584604212055193,
      "grad_norm": 0.36093130707740784,
      "learning_rate": 3.740109693074375e-05,
      "loss": 0.2607,
      "step": 245
    },
    {
      "epoch": 0.36310820624546114,
      "grad_norm": 0.6142938137054443,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 0.3285,
      "step": 250
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 0.48650553822517395,
      "learning_rate": 3.334301026289712e-05,
      "loss": 0.3845,
      "step": 255
    },
    {
      "epoch": 0.3776325344952796,
      "grad_norm": 0.40756455063819885,
      "learning_rate": 3.135717611098458e-05,
      "loss": 0.3649,
      "step": 260
    },
    {
      "epoch": 0.3848946986201888,
      "grad_norm": 0.5091582536697388,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 0.3867,
      "step": 265
    },
    {
      "epoch": 0.39215686274509803,
      "grad_norm": 0.6553879976272583,
      "learning_rate": 2.748981275911633e-05,
      "loss": 0.4012,
      "step": 270
    },
    {
      "epoch": 0.39941902687000724,
      "grad_norm": 0.5700201988220215,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 0.405,
      "step": 275
    },
    {
      "epoch": 0.4066811909949165,
      "grad_norm": 0.4261768162250519,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 0.4248,
      "step": 280
    },
    {
      "epoch": 0.4139433551198257,
      "grad_norm": 0.5792927145957947,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 0.3977,
      "step": 285
    },
    {
      "epoch": 0.4212055192447349,
      "grad_norm": 0.4655124545097351,
      "learning_rate": 2.026834118478567e-05,
      "loss": 0.4036,
      "step": 290
    },
    {
      "epoch": 0.42846768336964414,
      "grad_norm": 0.57184237241745,
      "learning_rate": 1.858900013521788e-05,
      "loss": 0.2864,
      "step": 295
    },
    {
      "epoch": 0.4357298474945534,
      "grad_norm": 0.66450035572052,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 0.3224,
      "step": 300
    },
    {
      "epoch": 0.4357298474945534,
      "eval_loss": 0.37213850021362305,
      "eval_runtime": 10.008,
      "eval_samples_per_second": 28.977,
      "eval_steps_per_second": 14.488,
      "step": 300
    },
    {
      "epoch": 0.4429920116194626,
      "grad_norm": 0.4642642140388489,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 0.3969,
      "step": 305
    },
    {
      "epoch": 0.4502541757443718,
      "grad_norm": 0.6916685104370117,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 0.3989,
      "step": 310
    },
    {
      "epoch": 0.45751633986928103,
      "grad_norm": 0.5440875887870789,
      "learning_rate": 1.246638473736378e-05,
      "loss": 0.382,
      "step": 315
    },
    {
      "epoch": 0.4647785039941903,
      "grad_norm": 0.52048659324646,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 0.4083,
      "step": 320
    },
    {
      "epoch": 0.4720406681190995,
      "grad_norm": 0.47202691435813904,
      "learning_rate": 9.800143481652979e-06,
      "loss": 0.3139,
      "step": 325
    },
    {
      "epoch": 0.4793028322440087,
      "grad_norm": 0.4411323368549347,
      "learning_rate": 8.574517537807897e-06,
      "loss": 0.3069,
      "step": 330
    },
    {
      "epoch": 0.4865649963689179,
      "grad_norm": 0.45705756545066833,
      "learning_rate": 7.423543113334436e-06,
      "loss": 0.3321,
      "step": 335
    },
    {
      "epoch": 0.49382716049382713,
      "grad_norm": 0.8066140413284302,
      "learning_rate": 6.349294341940593e-06,
      "loss": 0.4101,
      "step": 340
    },
    {
      "epoch": 0.5010893246187363,
      "grad_norm": 0.7938007712364197,
      "learning_rate": 5.353707092521582e-06,
      "loss": 0.3627,
      "step": 345
    },
    {
      "epoch": 0.5083514887436456,
      "grad_norm": 0.8610228300094604,
      "learning_rate": 4.43857548059321e-06,
      "loss": 0.3294,
      "step": 350
    },
    {
      "epoch": 0.5156136528685549,
      "grad_norm": 0.5776790976524353,
      "learning_rate": 3.605548635174533e-06,
      "loss": 0.2979,
      "step": 355
    },
    {
      "epoch": 0.5228758169934641,
      "grad_norm": 0.5070780515670776,
      "learning_rate": 2.85612772694579e-06,
      "loss": 0.4468,
      "step": 360
    },
    {
      "epoch": 0.5301379811183733,
      "grad_norm": 0.4442654848098755,
      "learning_rate": 2.191663263037458e-06,
      "loss": 0.3897,
      "step": 365
    },
    {
      "epoch": 0.5374001452432825,
      "grad_norm": 0.5217670798301697,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 0.3134,
      "step": 370
    },
    {
      "epoch": 0.5446623093681917,
      "grad_norm": 0.6290925741195679,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 0.3586,
      "step": 375
    },
    {
      "epoch": 0.5519244734931009,
      "grad_norm": 0.41745525598526,
      "learning_rate": 7.192044826145771e-07,
      "loss": 0.3897,
      "step": 380
    },
    {
      "epoch": 0.5591866376180101,
      "grad_norm": 0.5495943427085876,
      "learning_rate": 4.049782370561583e-07,
      "loss": 0.3575,
      "step": 385
    },
    {
      "epoch": 0.5664488017429193,
      "grad_norm": 0.6034603118896484,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 0.434,
      "step": 390
    },
    {
      "epoch": 0.5737109658678287,
      "grad_norm": 0.6801570653915405,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 0.3303,
      "step": 395
    },
    {
      "epoch": 0.5809731299927379,
      "grad_norm": 0.7904310822486877,
      "learning_rate": 0.0,
      "loss": 0.4547,
      "step": 400
    },
    {
      "epoch": 0.5809731299927379,
      "eval_loss": 0.36456015706062317,
      "eval_runtime": 10.0139,
      "eval_samples_per_second": 28.96,
      "eval_steps_per_second": 14.48,
      "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
}