{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 100,
  "global_step": 486,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06172839506172839,
      "grad_norm": 10.125808206289982,
      "learning_rate": 2.0408163265306125e-06,
      "loss": 1.0772,
      "step": 10
    },
    {
      "epoch": 0.12345679012345678,
      "grad_norm": 2.5386203860784136,
      "learning_rate": 4.081632653061225e-06,
      "loss": 0.5972,
      "step": 20
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 2.0806228443763923,
      "learning_rate": 6.122448979591837e-06,
      "loss": 0.3747,
      "step": 30
    },
    {
      "epoch": 0.24691358024691357,
      "grad_norm": 1.5238040517024116,
      "learning_rate": 8.16326530612245e-06,
      "loss": 0.3125,
      "step": 40
    },
    {
      "epoch": 0.30864197530864196,
      "grad_norm": 1.0455816905588915,
      "learning_rate": 9.999870796282452e-06,
      "loss": 0.3415,
      "step": 50
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 1.4397690389950966,
      "learning_rate": 9.984374428250894e-06,
      "loss": 0.3261,
      "step": 60
    },
    {
      "epoch": 0.43209876543209874,
      "grad_norm": 1.4784124049840264,
      "learning_rate": 9.943129053516176e-06,
      "loss": 0.2905,
      "step": 70
    },
    {
      "epoch": 0.49382716049382713,
      "grad_norm": 1.4073358258964512,
      "learning_rate": 9.876347743436758e-06,
      "loss": 0.3551,
      "step": 80
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 1.3358444097895485,
      "learning_rate": 9.78437548662167e-06,
      "loss": 0.3212,
      "step": 90
    },
    {
      "epoch": 0.6172839506172839,
      "grad_norm": 1.196559054025763,
      "learning_rate": 9.66768740673815e-06,
      "loss": 0.3022,
      "step": 100
    },
    {
      "epoch": 0.6172839506172839,
      "eval_loss": 0.28118011355400085,
      "eval_runtime": 33.8848,
      "eval_samples_per_second": 16.999,
      "eval_steps_per_second": 8.499,
      "step": 100
    },
    {
      "epoch": 0.6790123456790124,
      "grad_norm": 1.4169927804373623,
      "learning_rate": 9.52688630804867e-06,
      "loss": 0.3117,
      "step": 110
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 1.2415828541125944,
      "learning_rate": 9.362699561356957e-06,
      "loss": 0.3195,
      "step": 120
    },
    {
      "epoch": 0.8024691358024691,
      "grad_norm": 1.2836969169427264,
      "learning_rate": 9.175975346450063e-06,
      "loss": 0.333,
      "step": 130
    },
    {
      "epoch": 0.8641975308641975,
      "grad_norm": 1.2566606887109202,
      "learning_rate": 8.9676782704478e-06,
      "loss": 0.2938,
      "step": 140
    },
    {
      "epoch": 0.9259259259259259,
      "grad_norm": 1.3623865418664496,
      "learning_rate": 8.738884384694905e-06,
      "loss": 0.2986,
      "step": 150
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 1.4233923905829797,
      "learning_rate": 8.490775625938452e-06,
      "loss": 0.2574,
      "step": 160
    },
    {
      "epoch": 1.0493827160493827,
      "grad_norm": 1.190370194761653,
      "learning_rate": 8.224633710506997e-06,
      "loss": 0.1849,
      "step": 170
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 1.099933924299963,
      "learning_rate": 7.941833513033873e-06,
      "loss": 0.2084,
      "step": 180
    },
    {
      "epoch": 1.1728395061728394,
      "grad_norm": 1.3411794107712403,
      "learning_rate": 7.643835963929747e-06,
      "loss": 0.239,
      "step": 190
    },
    {
      "epoch": 1.2345679012345678,
      "grad_norm": 1.006333035037764,
      "learning_rate": 7.332180502295729e-06,
      "loss": 0.2176,
      "step": 200
    },
    {
      "epoch": 1.2345679012345678,
      "eval_loss": 0.28219473361968994,
      "eval_runtime": 33.6239,
      "eval_samples_per_second": 17.131,
      "eval_steps_per_second": 8.565,
      "step": 200
    },
    {
      "epoch": 1.2962962962962963,
      "grad_norm": 1.139264768106286,
      "learning_rate": 7.008477123264849e-06,
      "loss": 0.2283,
      "step": 210
    },
    {
      "epoch": 1.3580246913580247,
      "grad_norm": 1.1371107931484845,
      "learning_rate": 6.674398060854931e-06,
      "loss": 0.1902,
      "step": 220
    },
    {
      "epoch": 1.4197530864197532,
      "grad_norm": 1.3730452135228395,
      "learning_rate": 6.331669149298781e-06,
      "loss": 0.2333,
      "step": 230
    },
    {
      "epoch": 1.4814814814814814,
      "grad_norm": 1.1201678992731283,
      "learning_rate": 5.982060907478568e-06,
      "loss": 0.2069,
      "step": 240
    },
    {
      "epoch": 1.5432098765432098,
      "grad_norm": 1.3356992773689496,
      "learning_rate": 5.627379392521758e-06,
      "loss": 0.2263,
      "step": 250
    },
    {
      "epoch": 1.6049382716049383,
      "grad_norm": 1.4337310673277455,
      "learning_rate": 5.2694568698084085e-06,
      "loss": 0.2573,
      "step": 260
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 1.5488778192587145,
      "learning_rate": 4.910142347588041e-06,
      "loss": 0.2173,
      "step": 270
    },
    {
      "epoch": 1.7283950617283952,
      "grad_norm": 1.0832492592974947,
      "learning_rate": 4.551292025103789e-06,
      "loss": 0.1861,
      "step": 280
    },
    {
      "epoch": 1.7901234567901234,
      "grad_norm": 1.2664457162444653,
      "learning_rate": 4.1947597035682355e-06,
      "loss": 0.2185,
      "step": 290
    },
    {
      "epoch": 1.8518518518518519,
      "grad_norm": 1.5475480527449588,
      "learning_rate": 3.842387209527374e-06,
      "loss": 0.2157,
      "step": 300
    },
    {
      "epoch": 1.8518518518518519,
      "eval_loss": 0.27247950434684753,
      "eval_runtime": 33.6482,
      "eval_samples_per_second": 17.118,
      "eval_steps_per_second": 8.559,
      "step": 300
    },
    {
      "epoch": 1.9135802469135803,
      "grad_norm": 1.1103498380478658,
      "learning_rate": 3.4959948800850253e-06,
      "loss": 0.1885,
      "step": 310
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 1.4161875006518951,
      "learning_rate": 3.1573721591405405e-06,
      "loss": 0.2,
      "step": 320
    },
    {
      "epoch": 2.037037037037037,
      "grad_norm": 1.1185504039182512,
      "learning_rate": 2.8282683532191333e-06,
      "loss": 0.1642,
      "step": 330
    },
    {
      "epoch": 2.0987654320987654,
      "grad_norm": 1.498197806201236,
      "learning_rate": 2.5103835946496846e-06,
      "loss": 0.1336,
      "step": 340
    },
    {
      "epoch": 2.1604938271604937,
      "grad_norm": 1.3374025404689762,
      "learning_rate": 2.205360058773764e-06,
      "loss": 0.103,
      "step": 350
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 1.1254711504767878,
      "learning_rate": 1.914773480557304e-06,
      "loss": 0.1322,
      "step": 360
    },
    {
      "epoch": 2.2839506172839505,
      "grad_norm": 1.556059015124062,
      "learning_rate": 1.6401250144296239e-06,
      "loss": 0.1179,
      "step": 370
    },
    {
      "epoch": 2.3456790123456788,
      "grad_norm": 1.335036517801684,
      "learning_rate": 1.382833479401438e-06,
      "loss": 0.1292,
      "step": 380
    },
    {
      "epoch": 2.4074074074074074,
      "grad_norm": 1.0684099709675043,
      "learning_rate": 1.1442280295231656e-06,
      "loss": 0.1332,
      "step": 390
    },
    {
      "epoch": 2.4691358024691357,
      "grad_norm": 1.0579913108425518,
      "learning_rate": 9.255412875475256e-07,
      "loss": 0.126,
      "step": 400
    },
    {
      "epoch": 2.4691358024691357,
      "eval_loss": 0.30315688252449036,
      "eval_runtime": 33.6087,
      "eval_samples_per_second": 17.138,
      "eval_steps_per_second": 8.569,
      "step": 400
    },
    {
      "epoch": 2.5308641975308643,
      "grad_norm": 1.2810598384548977,
      "learning_rate": 7.279029772675572e-07,
      "loss": 0.1301,
      "step": 410
    },
    {
      "epoch": 2.5925925925925926,
      "grad_norm": 1.0566255697761466,
      "learning_rate": 5.523340874250704e-07,
      "loss": 0.1266,
      "step": 420
    },
    {
      "epoch": 2.6543209876543212,
      "grad_norm": 1.2053538383503994,
      "learning_rate": 3.997415973384311e-07,
      "loss": 0.1176,
      "step": 430
    },
    {
      "epoch": 2.7160493827160495,
      "grad_norm": 1.032781331569874,
      "learning_rate": 2.7091379149682683e-07,
      "loss": 0.1289,
      "step": 440
    },
    {
      "epoch": 2.7777777777777777,
      "grad_norm": 1.1729691522785313,
      "learning_rate": 1.6651618732554774e-07,
      "loss": 0.1032,
      "step": 450
    },
    {
      "epoch": 2.8395061728395063,
      "grad_norm": 1.3896397201247754,
      "learning_rate": 8.708809715922973e-08,
      "loss": 0.118,
      "step": 460
    },
    {
      "epoch": 2.9012345679012346,
      "grad_norm": 1.2233166514446852,
      "learning_rate": 3.303984218372136e-08,
      "loss": 0.1521,
      "step": 470
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 1.3019829879665807,
      "learning_rate": 4.650632739194305e-09,
      "loss": 0.1211,
      "step": 480
    },
    {
      "epoch": 3.0,
      "step": 486,
      "total_flos": 11979215732736.0,
      "train_loss": 0.23958166477120954,
      "train_runtime": 3326.588,
      "train_samples_per_second": 4.672,
      "train_steps_per_second": 0.146
    }
  ],
  "logging_steps": 10,
  "max_steps": 486,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 11979215732736.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}