{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9994372537985369,
  "eval_steps": 500,
  "global_step": 444,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022509848058525603,
      "grad_norm": 2.0995140075683594,
      "learning_rate": 2.222222222222222e-06,
      "loss": 7.6372,
      "step": 10
    },
    {
      "epoch": 0.04501969611705121,
      "grad_norm": 1.5694997310638428,
      "learning_rate": 4.444444444444444e-06,
      "loss": 5.9484,
      "step": 20
    },
    {
      "epoch": 0.06752954417557681,
      "grad_norm": 0.6644842028617859,
      "learning_rate": 6.666666666666667e-06,
      "loss": 4.3735,
      "step": 30
    },
    {
      "epoch": 0.09003939223410241,
      "grad_norm": 0.6358130574226379,
      "learning_rate": 8.888888888888888e-06,
      "loss": 4.0886,
      "step": 40
    },
    {
      "epoch": 0.11254924029262803,
      "grad_norm": 0.6227572560310364,
      "learning_rate": 9.87468671679198e-06,
      "loss": 3.9393,
      "step": 50
    },
    {
      "epoch": 0.13505908835115363,
      "grad_norm": 0.7231594920158386,
      "learning_rate": 9.62406015037594e-06,
      "loss": 4.1059,
      "step": 60
    },
    {
      "epoch": 0.15756893640967923,
      "grad_norm": 0.6719961166381836,
      "learning_rate": 9.3734335839599e-06,
      "loss": 3.9435,
      "step": 70
    },
    {
      "epoch": 0.18007878446820483,
      "grad_norm": 0.5704289674758911,
      "learning_rate": 9.12280701754386e-06,
      "loss": 3.9126,
      "step": 80
    },
    {
      "epoch": 0.20258863252673046,
      "grad_norm": 0.6164883971214294,
      "learning_rate": 8.87218045112782e-06,
      "loss": 3.8401,
      "step": 90
    },
    {
      "epoch": 0.22509848058525606,
      "grad_norm": 0.5553519129753113,
      "learning_rate": 8.62155388471178e-06,
      "loss": 3.868,
      "step": 100
    },
    {
      "epoch": 0.24760832864378166,
      "grad_norm": 0.5921124815940857,
      "learning_rate": 8.370927318295739e-06,
      "loss": 3.7648,
      "step": 110
    },
    {
      "epoch": 0.27011817670230726,
      "grad_norm": 0.5414007306098938,
      "learning_rate": 8.1203007518797e-06,
      "loss": 3.7132,
      "step": 120
    },
    {
      "epoch": 0.2926280247608329,
      "grad_norm": 0.5745058655738831,
      "learning_rate": 7.86967418546366e-06,
      "loss": 3.7257,
      "step": 130
    },
    {
      "epoch": 0.31513787281935846,
      "grad_norm": 0.5793574452400208,
      "learning_rate": 7.61904761904762e-06,
      "loss": 3.828,
      "step": 140
    },
    {
      "epoch": 0.3376477208778841,
      "grad_norm": 0.5630424618721008,
      "learning_rate": 7.368421052631579e-06,
      "loss": 3.698,
      "step": 150
    },
    {
      "epoch": 0.36015756893640966,
      "grad_norm": 0.6242647171020508,
      "learning_rate": 7.117794486215539e-06,
      "loss": 3.6934,
      "step": 160
    },
    {
      "epoch": 0.3826674169949353,
      "grad_norm": 0.5970180034637451,
      "learning_rate": 6.867167919799499e-06,
      "loss": 3.6327,
      "step": 170
    },
    {
      "epoch": 0.4051772650534609,
      "grad_norm": 0.4859864413738251,
      "learning_rate": 6.616541353383459e-06,
      "loss": 3.6138,
      "step": 180
    },
    {
      "epoch": 0.4276871131119865,
      "grad_norm": 0.5941168665885925,
      "learning_rate": 6.365914786967419e-06,
      "loss": 3.6695,
      "step": 190
    },
    {
      "epoch": 0.4501969611705121,
      "grad_norm": 0.5945659875869751,
      "learning_rate": 6.115288220551378e-06,
      "loss": 3.6459,
      "step": 200
    },
    {
      "epoch": 0.4727068092290377,
      "grad_norm": 0.5131842494010925,
      "learning_rate": 5.864661654135339e-06,
      "loss": 3.5887,
      "step": 210
    },
    {
      "epoch": 0.4952166572875633,
      "grad_norm": 0.5476564168930054,
      "learning_rate": 5.6140350877192985e-06,
      "loss": 3.5615,
      "step": 220
    },
    {
      "epoch": 0.5177265053460889,
      "grad_norm": 0.5150834918022156,
      "learning_rate": 5.363408521303258e-06,
      "loss": 3.5065,
      "step": 230
    },
    {
      "epoch": 0.5402363534046145,
      "grad_norm": 0.5556353330612183,
      "learning_rate": 5.112781954887218e-06,
      "loss": 3.4446,
      "step": 240
    },
    {
      "epoch": 0.5627462014631401,
      "grad_norm": 0.5478722453117371,
      "learning_rate": 4.862155388471178e-06,
      "loss": 3.4909,
      "step": 250
    },
    {
      "epoch": 0.5852560495216658,
      "grad_norm": 0.5975968837738037,
      "learning_rate": 4.611528822055138e-06,
      "loss": 3.3949,
      "step": 260
    },
    {
      "epoch": 0.6077658975801913,
      "grad_norm": 0.5002927184104919,
      "learning_rate": 4.360902255639098e-06,
      "loss": 3.4045,
      "step": 270
    },
    {
      "epoch": 0.6302757456387169,
      "grad_norm": 0.5572878122329712,
      "learning_rate": 4.110275689223058e-06,
      "loss": 3.3974,
      "step": 280
    },
    {
      "epoch": 0.6527855936972425,
      "grad_norm": 0.49857544898986816,
      "learning_rate": 3.859649122807018e-06,
      "loss": 3.2611,
      "step": 290
    },
    {
      "epoch": 0.6752954417557682,
      "grad_norm": 0.5412642359733582,
      "learning_rate": 3.6090225563909775e-06,
      "loss": 3.3651,
      "step": 300
    },
    {
      "epoch": 0.6978052898142938,
      "grad_norm": 0.5446689128875732,
      "learning_rate": 3.3583959899749375e-06,
      "loss": 3.3926,
      "step": 310
    },
    {
      "epoch": 0.7203151378728193,
      "grad_norm": 0.5008708238601685,
      "learning_rate": 3.107769423558897e-06,
      "loss": 3.3208,
      "step": 320
    },
    {
      "epoch": 0.7428249859313449,
      "grad_norm": 0.50593101978302,
      "learning_rate": 2.8571428571428573e-06,
      "loss": 3.2888,
      "step": 330
    },
    {
      "epoch": 0.7653348339898706,
      "grad_norm": 0.5109095573425293,
      "learning_rate": 2.606516290726817e-06,
      "loss": 3.3388,
      "step": 340
    },
    {
      "epoch": 0.7878446820483962,
      "grad_norm": 0.5837152600288391,
      "learning_rate": 2.355889724310777e-06,
      "loss": 3.3427,
      "step": 350
    },
    {
      "epoch": 0.8103545301069218,
      "grad_norm": 0.4692504107952118,
      "learning_rate": 2.105263157894737e-06,
      "loss": 3.3756,
      "step": 360
    },
    {
      "epoch": 0.8328643781654473,
      "grad_norm": 0.5203748941421509,
      "learning_rate": 1.8546365914786967e-06,
      "loss": 3.3402,
      "step": 370
    },
    {
      "epoch": 0.855374226223973,
      "grad_norm": 0.5327721834182739,
      "learning_rate": 1.6040100250626568e-06,
      "loss": 3.296,
      "step": 380
    },
    {
      "epoch": 0.8778840742824986,
      "grad_norm": 0.5080034136772156,
      "learning_rate": 1.3533834586466167e-06,
      "loss": 3.2394,
      "step": 390
    },
    {
      "epoch": 0.9003939223410242,
      "grad_norm": 0.47599706053733826,
      "learning_rate": 1.1027568922305765e-06,
      "loss": 3.2577,
      "step": 400
    },
    {
      "epoch": 0.9229037703995498,
      "grad_norm": 0.5053209066390991,
      "learning_rate": 8.521303258145364e-07,
      "loss": 3.1879,
      "step": 410
    },
    {
      "epoch": 0.9454136184580754,
      "grad_norm": 0.4937838912010193,
      "learning_rate": 6.015037593984962e-07,
      "loss": 3.2803,
      "step": 420
    },
    {
      "epoch": 0.967923466516601,
      "grad_norm": 0.5207067728042603,
      "learning_rate": 3.5087719298245616e-07,
      "loss": 3.1842,
      "step": 430
    },
    {
      "epoch": 0.9904333145751266,
      "grad_norm": 0.4591236412525177,
      "learning_rate": 1.0025062656641605e-07,
      "loss": 3.3321,
      "step": 440
    }
  ],
  "logging_steps": 10,
  "max_steps": 444,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.6197148726984704e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}