{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.984709480122324,
  "eval_steps": 500,
  "global_step": 366,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08154943934760449,
      "grad_norm": 0.6581962704658508,
      "learning_rate": 2.702702702702703e-05,
      "loss": 1.2642,
      "step": 10
    },
    {
      "epoch": 0.16309887869520898,
      "grad_norm": 0.49579960107803345,
      "learning_rate": 5.405405405405406e-05,
      "loss": 1.3625,
      "step": 20
    },
    {
      "epoch": 0.24464831804281345,
      "grad_norm": 0.4957895278930664,
      "learning_rate": 8.108108108108109e-05,
      "loss": 1.232,
      "step": 30
    },
    {
      "epoch": 0.32619775739041795,
      "grad_norm": 0.3685353100299835,
      "learning_rate": 9.997948550797227e-05,
      "loss": 1.11,
      "step": 40
    },
    {
      "epoch": 0.4077471967380224,
      "grad_norm": 0.5396739840507507,
      "learning_rate": 9.961525153583327e-05,
      "loss": 1.0695,
      "step": 50
    },
    {
      "epoch": 0.4892966360856269,
      "grad_norm": 0.7498260140419006,
      "learning_rate": 9.879896064123961e-05,
      "loss": 1.1538,
      "step": 60
    },
    {
      "epoch": 0.5708460754332314,
      "grad_norm": 0.693131685256958,
      "learning_rate": 9.753805025397779e-05,
      "loss": 1.1681,
      "step": 70
    },
    {
      "epoch": 0.6523955147808359,
      "grad_norm": 0.51374751329422,
      "learning_rate": 9.584400884284545e-05,
      "loss": 0.9667,
      "step": 80
    },
    {
      "epoch": 0.7339449541284404,
      "grad_norm": 0.3830406665802002,
      "learning_rate": 9.373227124134888e-05,
      "loss": 1.1852,
      "step": 90
    },
    {
      "epoch": 0.8154943934760448,
      "grad_norm": 0.6004562973976135,
      "learning_rate": 9.122207801708802e-05,
      "loss": 1.0581,
      "step": 100
    },
    {
      "epoch": 0.8970438328236493,
      "grad_norm": 0.4539795219898224,
      "learning_rate": 8.833630016614976e-05,
      "loss": 1.1625,
      "step": 110
    },
    {
      "epoch": 0.9785932721712538,
      "grad_norm": 0.5552476048469543,
      "learning_rate": 8.510123072976239e-05,
      "loss": 1.0709,
      "step": 120
    },
    {
      "epoch": 1.0601427115188584,
      "grad_norm": 0.4887731075286865,
      "learning_rate": 8.154634523184388e-05,
      "loss": 1.1367,
      "step": 130
    },
    {
      "epoch": 1.1416921508664628,
      "grad_norm": 1.0751506090164185,
      "learning_rate": 7.770403312015721e-05,
      "loss": 1.0379,
      "step": 140
    },
    {
      "epoch": 1.2232415902140672,
      "grad_norm": 0.5014678239822388,
      "learning_rate": 7.360930265797935e-05,
      "loss": 1.0853,
      "step": 150
    },
    {
      "epoch": 1.3047910295616718,
      "grad_norm": 0.5106374621391296,
      "learning_rate": 6.929946195508932e-05,
      "loss": 1.0257,
      "step": 160
    },
    {
      "epoch": 1.3863404689092762,
      "grad_norm": 0.7296202182769775,
      "learning_rate": 6.481377904428171e-05,
      "loss": 0.9603,
      "step": 170
    },
    {
      "epoch": 1.4678899082568808,
      "grad_norm": 0.6069113612174988,
      "learning_rate": 6.019312410053286e-05,
      "loss": 1.0353,
      "step": 180
    },
    {
      "epoch": 1.5494393476044852,
      "grad_norm": 0.6981645226478577,
      "learning_rate": 5.547959706265068e-05,
      "loss": 0.9696,
      "step": 190
    },
    {
      "epoch": 1.6309887869520896,
      "grad_norm": 0.6552231311798096,
      "learning_rate": 5.0716144050239375e-05,
      "loss": 0.9507,
      "step": 200
    },
    {
      "epoch": 1.7125382262996942,
      "grad_norm": 0.5785824060440063,
      "learning_rate": 4.594616607090028e-05,
      "loss": 1.0278,
      "step": 210
    },
    {
      "epoch": 1.7940876656472988,
      "grad_norm": 0.6869484782218933,
      "learning_rate": 4.121312358283463e-05,
      "loss": 0.97,
      "step": 220
    },
    {
      "epoch": 1.8756371049949032,
      "grad_norm": 0.8592352271080017,
      "learning_rate": 3.656014051577713e-05,
      "loss": 1.02,
      "step": 230
    },
    {
      "epoch": 1.9571865443425076,
      "grad_norm": 0.7686919569969177,
      "learning_rate": 3.202961135812437e-05,
      "loss": 1.0016,
      "step": 240
    },
    {
      "epoch": 2.038735983690112,
      "grad_norm": 0.8709023594856262,
      "learning_rate": 2.7662814890184818e-05,
      "loss": 0.9708,
      "step": 250
    },
    {
      "epoch": 2.120285423037717,
      "grad_norm": 0.7683507204055786,
      "learning_rate": 2.3499538082923606e-05,
      "loss": 0.9663,
      "step": 260
    },
    {
      "epoch": 2.2018348623853212,
      "grad_norm": 0.6658952236175537,
      "learning_rate": 1.9577713588953795e-05,
      "loss": 0.8854,
      "step": 270
    },
    {
      "epoch": 2.2833843017329256,
      "grad_norm": 0.625361979007721,
      "learning_rate": 1.5933074128684332e-05,
      "loss": 0.9291,
      "step": 280
    },
    {
      "epoch": 2.36493374108053,
      "grad_norm": 0.8144427537918091,
      "learning_rate": 1.2598826920598772e-05,
      "loss": 0.9754,
      "step": 290
    },
    {
      "epoch": 2.4464831804281344,
      "grad_norm": 0.8737558722496033,
      "learning_rate": 9.605351122011309e-06,
      "loss": 0.9775,
      "step": 300
    },
    {
      "epoch": 2.528032619775739,
      "grad_norm": 0.6809930801391602,
      "learning_rate": 6.979921036993042e-06,
      "loss": 0.8337,
      "step": 310
    },
    {
      "epoch": 2.6095820591233436,
      "grad_norm": 0.7553091049194336,
      "learning_rate": 4.746457613389904e-06,
      "loss": 0.9127,
      "step": 320
    },
    {
      "epoch": 2.691131498470948,
      "grad_norm": 0.9476282000541687,
      "learning_rate": 2.925310493105099e-06,
      "loss": 0.964,
      "step": 330
    },
    {
      "epoch": 2.7726809378185524,
      "grad_norm": 1.2003215551376343,
      "learning_rate": 1.5330726014397668e-06,
      "loss": 0.9675,
      "step": 340
    },
    {
      "epoch": 2.8542303771661572,
      "grad_norm": 0.8831192255020142,
      "learning_rate": 5.824289648152126e-07,
      "loss": 0.8972,
      "step": 350
    },
    {
      "epoch": 2.9357798165137616,
      "grad_norm": 1.0032685995101929,
      "learning_rate": 8.204113433559201e-08,
      "loss": 0.9376,
      "step": 360
    },
    {
      "epoch": 2.984709480122324,
      "step": 366,
      "total_flos": 8328022270279680.0,
      "train_loss": 1.033826659937374,
      "train_runtime": 686.5365,
      "train_samples_per_second": 4.287,
      "train_steps_per_second": 0.533
    }
  ],
  "logging_steps": 10,
  "max_steps": 366,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 8328022270279680.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}