{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.999068850303993,
  "eval_steps": 500,
  "global_step": 570,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 3.5087719298245615e-06,
      "loss": 1.2582,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.7543859649122806e-05,
      "loss": 1.2488,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.508771929824561e-05,
      "loss": 1.2359,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.2631578947368424e-05,
      "loss": 1.2016,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.017543859649122e-05,
      "loss": 1.155,
      "step": 20
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.771929824561403e-05,
      "loss": 1.1231,
      "step": 25
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00010526315789473685,
      "loss": 1.1019,
      "step": 30
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00012280701754385965,
      "loss": 1.0873,
      "step": 35
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00014035087719298245,
      "loss": 1.0644,
      "step": 40
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00015789473684210527,
      "loss": 1.0655,
      "step": 45
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00017543859649122806,
      "loss": 1.0574,
      "step": 50
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019298245614035088,
      "loss": 1.0447,
      "step": 55
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019998312416333227,
      "loss": 1.0356,
      "step": 60
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001998800146766861,
      "loss": 1.0223,
      "step": 65
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019968326771610797,
      "loss": 1.031,
      "step": 70
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019939306773179497,
      "loss": 1.0194,
      "step": 75
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019900968678611666,
      "loss": 1.0126,
      "step": 80
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019853348429855672,
      "loss": 1.0082,
      "step": 85
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001979649067087574,
      "loss": 1.0099,
      "step": 90
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019730448705798239,
      "loss": 1.0018,
      "step": 95
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019655284448939094,
      "loss": 1.0068,
      "step": 100
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019571068366759143,
      "loss": 1.0011,
      "step": 105
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019477879411801844,
      "loss": 1.0074,
      "step": 110
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019375804948675306,
      "loss": 0.9902,
      "step": 115
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019264940672148018,
      "loss": 0.996,
      "step": 120
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019145390517435012,
      "loss": 1.0023,
      "step": 125
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019017266562758659,
      "loss": 1.0005,
      "step": 130
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018880688924275378,
      "loss": 0.9882,
      "step": 135
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018735785643466784,
      "loss": 0.9905,
      "step": 140
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018582692567100867,
      "loss": 0.9949,
      "step": 145
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018421553219875658,
      "loss": 0.9976,
      "step": 150
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00018252518669864936,
      "loss": 0.9847,
      "step": 155
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001807574738689193,
      "loss": 0.9881,
      "step": 160
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00017891405093963938,
      "loss": 0.9812,
      "step": 165
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00017699664611907072,
      "loss": 1.0059,
      "step": 170
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001750070569734681,
      "loss": 0.9895,
      "step": 175
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001729471487418621,
      "loss": 0.9902,
      "step": 180
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00017081885258739846,
      "loss": 0.9846,
      "step": 185
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001686241637868734,
      "loss": 0.9848,
      "step": 190
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00016636513986016213,
      "loss": 0.9778,
      "step": 195
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00016404389864129533,
      "loss": 0.9812,
      "step": 200
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00016166261629298995,
      "loss": 1.0017,
      "step": 205
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00015922352526649803,
      "loss": 0.9853,
      "step": 210
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00015672891220868432,
      "loss": 0.9849,
      "step": 215
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00015418111581829574,
      "loss": 0.9827,
      "step": 220
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00015158252465343242,
      "loss": 0.9908,
      "step": 225
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00014893557489227517,
      "loss": 0.9773,
      "step": 230
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00014624274804916958,
      "loss": 0.988,
      "step": 235
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00014350656864820733,
      "loss": 0.9897,
      "step": 240
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00014072960185648577,
      "loss": 0.9757,
      "step": 245
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00013791445107926478,
      "loss": 0.9731,
      "step": 250
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00013506375551927547,
      "loss": 0.9815,
      "step": 255
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00013218018770246858,
      "loss": 0.9755,
      "step": 260
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001292664509725226,
      "loss": 0.9746,
      "step": 265
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00012632527695645993,
      "loss": 0.9744,
      "step": 270
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00012335942300374788,
      "loss": 0.9807,
      "step": 275
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00012037166960128443,
      "loss": 0.9888,
      "step": 280
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00011736481776669306,
      "loss": 0.9848,
      "step": 285
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00011434168642236964,
      "loss": 0.9797,
      "step": 290
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00011130510975274409,
      "loss": 0.9799,
      "step": 295
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00010825793454723325,
      "loss": 0.9939,
      "step": 300
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00010520301753137724,
      "loss": 0.9693,
      "step": 305
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00010214322268866032,
      "loss": 0.9846,
      "step": 310
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.908141857552737e-05,
      "loss": 0.9754,
      "step": 315
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.602047563211359e-05,
      "loss": 0.9912,
      "step": 320
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.296326349120785e-05,
      "loss": 0.9778,
      "step": 325
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.991264828797319e-05,
      "loss": 0.9828,
      "step": 330
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.687148997294621e-05,
      "loss": 0.9717,
      "step": 335
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.384263963083453e-05,
      "loss": 0.9907,
      "step": 340
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.082893680762619e-05,
      "loss": 0.9787,
      "step": 345
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.783320684851614e-05,
      "loss": 0.9793,
      "step": 350
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.485825824914659e-05,
      "loss": 0.9698,
      "step": 355
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.190688002264308e-05,
      "loss": 0.9792,
      "step": 360
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.898183908491617e-05,
      "loss": 0.9821,
      "step": 365
    },
    {
      "epoch": 0.65,
      "learning_rate": 6.608587766067852e-05,
      "loss": 0.9796,
      "step": 370
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.322171071261071e-05,
      "loss": 0.9832,
      "step": 375
    },
    {
      "epoch": 0.67,
      "learning_rate": 6.039202339608432e-05,
      "loss": 0.9853,
      "step": 380
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.7599468541830356e-05,
      "loss": 0.9659,
      "step": 385
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.484666416891109e-05,
      "loss": 0.971,
      "step": 390
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.2136191030328455e-05,
      "loss": 0.9705,
      "step": 395
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.9470590193569044e-05,
      "loss": 0.9829,
      "step": 400
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.685236065835443e-05,
      "loss": 0.9638,
      "step": 405
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.4283957013829846e-05,
      "loss": 0.9592,
      "step": 410
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.176778713738787e-05,
      "loss": 0.9758,
      "step": 415
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.9306209937284346e-05,
      "loss": 0.9843,
      "step": 420
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.69015331411628e-05,
      "loss": 0.979,
      "step": 425
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.455601113256073e-05,
      "loss": 0.9816,
      "step": 430
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.227184283742591e-05,
      "loss": 0.9885,
      "step": 435
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.0051169662624225e-05,
      "loss": 0.9757,
      "step": 440
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.789607348837153e-05,
      "loss": 0.9678,
      "step": 445
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.5808574716471856e-05,
      "loss": 0.9757,
      "step": 450
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.379063037619146e-05,
      "loss": 0.979,
      "step": 455
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.184413228954468e-05,
      "loss": 0.9789,
      "step": 460
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.9970905297711606e-05,
      "loss": 0.9728,
      "step": 465
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.8172705550250092e-05,
      "loss": 0.9863,
      "step": 470
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.6451218858706374e-05,
      "loss": 0.9887,
      "step": 475
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.4808059116167305e-05,
      "loss": 0.9824,
      "step": 480
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.3244766784236307e-05,
      "loss": 0.9743,
      "step": 485
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.176280744885121e-05,
      "loss": 0.9859,
      "step": 490
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.0363570446297999e-05,
      "loss": 0.9732,
      "step": 495
    },
    {
      "epoch": 0.88,
      "learning_rate": 9.048367560708604e-06,
      "loss": 0.9768,
      "step": 500
    },
    {
      "epoch": 0.89,
      "learning_rate": 7.818431794263836e-06,
      "loss": 0.9708,
      "step": 505
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.674916211254289e-06,
      "loss": 0.9679,
      "step": 510
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.618892857083069e-06,
      "loss": 0.9739,
      "step": 515
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.65135175322361e-06,
      "loss": 0.9795,
      "step": 520
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.7731999690749585e-06,
      "loss": 0.9785,
      "step": 525
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.9852607715846193e-06,
      "loss": 0.9904,
      "step": 530
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.288272853436013e-06,
      "loss": 0.9778,
      "step": 535
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.6828896405244988e-06,
      "loss": 0.972,
      "step": 540
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.1696786793707781e-06,
      "loss": 0.9647,
      "step": 545
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.491211050462798e-07,
      "loss": 0.9865,
      "step": 550
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.216111901092501e-07,
      "loss": 0.9742,
      "step": 555
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.8745597497433765e-07,
      "loss": 0.9649,
      "step": 560
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.687498006236135e-08,
      "loss": 0.9745,
      "step": 565
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 0.9771,
      "step": 570
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.981906533241272,
      "eval_runtime": 2107.2433,
      "eval_samples_per_second": 7.672,
      "eval_steps_per_second": 0.24,
      "step": 570
    },
    {
      "epoch": 1.0,
      "step": 570,
      "total_flos": 1.1919078088043921e+19,
      "train_loss": 0.9983171429550438,
      "train_runtime": 52319.2765,
      "train_samples_per_second": 2.792,
      "train_steps_per_second": 0.011
    }
  ],
  "logging_steps": 5,
  "max_steps": 570,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 1.1919078088043921e+19,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}