{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05119672340970178,
  "eval_steps": 1000,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012799180852425445,
      "grad_norm": 1.2002202272415161,
      "learning_rate": 1.4404609475032012e-07,
      "loss": 0.714,
      "step": 10
    },
    {
      "epoch": 0.002559836170485089,
      "grad_norm": 1.0710716247558594,
      "learning_rate": 3.040973111395647e-07,
      "loss": 0.7181,
      "step": 20
    },
    {
      "epoch": 0.0038397542557276334,
      "grad_norm": 1.0631524324417114,
      "learning_rate": 4.641485275288093e-07,
      "loss": 0.7114,
      "step": 30
    },
    {
      "epoch": 0.005119672340970178,
      "grad_norm": 1.1470946073532104,
      "learning_rate": 6.241997439180538e-07,
      "loss": 0.7083,
      "step": 40
    },
    {
      "epoch": 0.006399590426212722,
      "grad_norm": 1.1680080890655518,
      "learning_rate": 7.842509603072984e-07,
      "loss": 0.7109,
      "step": 50
    },
    {
      "epoch": 0.007679508511455267,
      "grad_norm": 0.6832358241081238,
      "learning_rate": 9.44302176696543e-07,
      "loss": 0.7131,
      "step": 60
    },
    {
      "epoch": 0.008959426596697812,
      "grad_norm": 1.8029249906539917,
      "learning_rate": 1.1043533930857875e-06,
      "loss": 0.7092,
      "step": 70
    },
    {
      "epoch": 0.010239344681940356,
      "grad_norm": 1.795204758644104,
      "learning_rate": 1.264404609475032e-06,
      "loss": 0.7063,
      "step": 80
    },
    {
      "epoch": 0.011519262767182901,
      "grad_norm": 1.2713547945022583,
      "learning_rate": 1.4244558258642767e-06,
      "loss": 0.7126,
      "step": 90
    },
    {
      "epoch": 0.012799180852425445,
      "grad_norm": 1.2709708213806152,
      "learning_rate": 1.5845070422535212e-06,
      "loss": 0.7069,
      "step": 100
    },
    {
      "epoch": 0.01407909893766799,
      "grad_norm": 0.8230543732643127,
      "learning_rate": 1.7445582586427658e-06,
      "loss": 0.7036,
      "step": 110
    },
    {
      "epoch": 0.015359017022910534,
      "grad_norm": 0.7209059596061707,
      "learning_rate": 1.9046094750320101e-06,
      "loss": 0.7058,
      "step": 120
    },
    {
      "epoch": 0.016638935108153077,
      "grad_norm": 0.7314836978912354,
      "learning_rate": 2.064660691421255e-06,
      "loss": 0.7046,
      "step": 130
    },
    {
      "epoch": 0.017918853193395624,
      "grad_norm": 0.7659752368927002,
      "learning_rate": 2.2247119078104993e-06,
      "loss": 0.6989,
      "step": 140
    },
    {
      "epoch": 0.019198771278638168,
      "grad_norm": 0.9008486866950989,
      "learning_rate": 2.384763124199744e-06,
      "loss": 0.6998,
      "step": 150
    },
    {
      "epoch": 0.02047868936388071,
      "grad_norm": 1.0409601926803589,
      "learning_rate": 2.5448143405889883e-06,
      "loss": 0.7016,
      "step": 160
    },
    {
      "epoch": 0.021758607449123255,
      "grad_norm": 0.8855634927749634,
      "learning_rate": 2.704865556978233e-06,
      "loss": 0.6947,
      "step": 170
    },
    {
      "epoch": 0.023038525534365802,
      "grad_norm": 0.798701286315918,
      "learning_rate": 2.8649167733674777e-06,
      "loss": 0.6935,
      "step": 180
    },
    {
      "epoch": 0.024318443619608346,
      "grad_norm": 1.1289243698120117,
      "learning_rate": 3.024967989756722e-06,
      "loss": 0.6937,
      "step": 190
    },
    {
      "epoch": 0.02559836170485089,
      "grad_norm": 1.4480715990066528,
      "learning_rate": 3.185019206145967e-06,
      "loss": 0.6948,
      "step": 200
    },
    {
      "epoch": 0.026878279790093433,
      "grad_norm": 0.6359772682189941,
      "learning_rate": 3.3450704225352113e-06,
      "loss": 0.6904,
      "step": 210
    },
    {
      "epoch": 0.02815819787533598,
      "grad_norm": 1.1023344993591309,
      "learning_rate": 3.5051216389244556e-06,
      "loss": 0.6873,
      "step": 220
    },
    {
      "epoch": 0.029438115960578524,
      "grad_norm": 0.8251340389251709,
      "learning_rate": 3.6651728553137003e-06,
      "loss": 0.6859,
      "step": 230
    },
    {
      "epoch": 0.030718034045821067,
      "grad_norm": 0.7032744288444519,
      "learning_rate": 3.825224071702945e-06,
      "loss": 0.6804,
      "step": 240
    },
    {
      "epoch": 0.031997952131063614,
      "grad_norm": 0.7794032096862793,
      "learning_rate": 3.98527528809219e-06,
      "loss": 0.6831,
      "step": 250
    },
    {
      "epoch": 0.033277870216306155,
      "grad_norm": 0.6654011607170105,
      "learning_rate": 4.145326504481434e-06,
      "loss": 0.6813,
      "step": 260
    },
    {
      "epoch": 0.0345577883015487,
      "grad_norm": 1.7002371549606323,
      "learning_rate": 4.3053777208706795e-06,
      "loss": 0.6793,
      "step": 270
    },
    {
      "epoch": 0.03583770638679125,
      "grad_norm": 1.0438320636749268,
      "learning_rate": 4.465428937259923e-06,
      "loss": 0.6758,
      "step": 280
    },
    {
      "epoch": 0.03711762447203379,
      "grad_norm": 0.6591306924819946,
      "learning_rate": 4.625480153649168e-06,
      "loss": 0.6758,
      "step": 290
    },
    {
      "epoch": 0.038397542557276336,
      "grad_norm": 0.5876058340072632,
      "learning_rate": 4.785531370038412e-06,
      "loss": 0.6742,
      "step": 300
    },
    {
      "epoch": 0.039677460642518876,
      "grad_norm": 0.5839381814002991,
      "learning_rate": 4.9455825864276575e-06,
      "loss": 0.6706,
      "step": 310
    },
    {
      "epoch": 0.04095737872776142,
      "grad_norm": 1.3025041818618774,
      "learning_rate": 5.105633802816902e-06,
      "loss": 0.6658,
      "step": 320
    },
    {
      "epoch": 0.04223729681300397,
      "grad_norm": 0.5543903708457947,
      "learning_rate": 5.265685019206147e-06,
      "loss": 0.6722,
      "step": 330
    },
    {
      "epoch": 0.04351721489824651,
      "grad_norm": 0.5097215175628662,
      "learning_rate": 5.425736235595391e-06,
      "loss": 0.6704,
      "step": 340
    },
    {
      "epoch": 0.04479713298348906,
      "grad_norm": 0.760080873966217,
      "learning_rate": 5.585787451984635e-06,
      "loss": 0.6652,
      "step": 350
    },
    {
      "epoch": 0.046077051068731605,
      "grad_norm": 0.7467712759971619,
      "learning_rate": 5.74583866837388e-06,
      "loss": 0.668,
      "step": 360
    },
    {
      "epoch": 0.047356969153974145,
      "grad_norm": 0.9601678848266602,
      "learning_rate": 5.905889884763125e-06,
      "loss": 0.6619,
      "step": 370
    },
    {
      "epoch": 0.04863688723921669,
      "grad_norm": 0.7230914235115051,
      "learning_rate": 6.065941101152369e-06,
      "loss": 0.6585,
      "step": 380
    },
    {
      "epoch": 0.04991680532445923,
      "grad_norm": 0.8606265783309937,
      "learning_rate": 6.225992317541613e-06,
      "loss": 0.6591,
      "step": 390
    },
    {
      "epoch": 0.05119672340970178,
      "grad_norm": 0.6350621581077576,
      "learning_rate": 6.386043533930858e-06,
      "loss": 0.6575,
      "step": 400
    }
  ],
  "logging_steps": 10,
  "max_steps": 31252,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6735643017216000.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}