{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 1250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "grad_norm": 0.19323205947875977,
      "learning_rate": 0.0002,
      "loss": 1.4874,
      "step": 25
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.1678144633769989,
      "learning_rate": 0.0002,
      "loss": 1.4509,
      "step": 50
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.08337455242872238,
      "learning_rate": 0.0002,
      "loss": 1.3405,
      "step": 75
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.09026125818490982,
      "learning_rate": 0.0002,
      "loss": 1.3735,
      "step": 100
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.1073032096028328,
      "learning_rate": 0.0002,
      "loss": 1.4068,
      "step": 125
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.13652268052101135,
      "learning_rate": 0.0002,
      "loss": 1.2271,
      "step": 150
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.12082232534885406,
      "learning_rate": 0.0002,
      "loss": 1.2864,
      "step": 175
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.12123199552297592,
      "learning_rate": 0.0002,
      "loss": 1.254,
      "step": 200
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.11623656004667282,
      "learning_rate": 0.0002,
      "loss": 1.3337,
      "step": 225
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.13121260702610016,
      "learning_rate": 0.0002,
      "loss": 1.2837,
      "step": 250
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.17798519134521484,
      "learning_rate": 0.0002,
      "loss": 1.1528,
      "step": 275
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.16624127328395844,
      "learning_rate": 0.0002,
      "loss": 1.1691,
      "step": 300
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.13809803128242493,
      "learning_rate": 0.0002,
      "loss": 1.1826,
      "step": 325
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.13886697590351105,
      "learning_rate": 0.0002,
      "loss": 1.2243,
      "step": 350
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.20055805146694183,
      "learning_rate": 0.0002,
      "loss": 1.2453,
      "step": 375
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.2664979100227356,
      "learning_rate": 0.0002,
      "loss": 1.068,
      "step": 400
    },
    {
      "epoch": 3.4,
      "grad_norm": 0.19323182106018066,
      "learning_rate": 0.0002,
      "loss": 1.1088,
      "step": 425
    },
    {
      "epoch": 3.6,
      "grad_norm": 0.2079138457775116,
      "learning_rate": 0.0002,
      "loss": 1.0796,
      "step": 450
    },
    {
      "epoch": 3.8,
      "grad_norm": 0.20442678034305573,
      "learning_rate": 0.0002,
      "loss": 1.1325,
      "step": 475
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.25957778096199036,
      "learning_rate": 0.0002,
      "loss": 1.1482,
      "step": 500
    },
    {
      "epoch": 4.2,
      "grad_norm": 0.3366886079311371,
      "learning_rate": 0.0002,
      "loss": 1.0235,
      "step": 525
    },
    {
      "epoch": 4.4,
      "grad_norm": 0.25876155495643616,
      "learning_rate": 0.0002,
      "loss": 0.9673,
      "step": 550
    },
    {
      "epoch": 4.6,
      "grad_norm": 0.239900603890419,
      "learning_rate": 0.0002,
      "loss": 1.0075,
      "step": 575
    },
    {
      "epoch": 4.8,
      "grad_norm": 0.23491528630256653,
      "learning_rate": 0.0002,
      "loss": 1.0195,
      "step": 600
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.27541735768318176,
      "learning_rate": 0.0002,
      "loss": 1.0431,
      "step": 625
    },
    {
      "epoch": 5.2,
      "grad_norm": 0.3689779043197632,
      "learning_rate": 0.0002,
      "loss": 0.9048,
      "step": 650
    },
    {
      "epoch": 5.4,
      "grad_norm": 0.2586508095264435,
      "learning_rate": 0.0002,
      "loss": 0.8714,
      "step": 675
    },
    {
      "epoch": 5.6,
      "grad_norm": 0.2392464578151703,
      "learning_rate": 0.0002,
      "loss": 0.8859,
      "step": 700
    },
    {
      "epoch": 5.8,
      "grad_norm": 0.2529771029949188,
      "learning_rate": 0.0002,
      "loss": 0.9311,
      "step": 725
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.5787801146507263,
      "learning_rate": 0.0002,
      "loss": 0.9657,
      "step": 750
    },
    {
      "epoch": 6.2,
      "grad_norm": 0.5453413128852844,
      "learning_rate": 0.0002,
      "loss": 0.8175,
      "step": 775
    },
    {
      "epoch": 6.4,
      "grad_norm": 0.34291961789131165,
      "learning_rate": 0.0002,
      "loss": 0.8445,
      "step": 800
    },
    {
      "epoch": 6.6,
      "grad_norm": 0.28864824771881104,
      "learning_rate": 0.0002,
      "loss": 0.8116,
      "step": 825
    },
    {
      "epoch": 6.8,
      "grad_norm": 0.22972020506858826,
      "learning_rate": 0.0002,
      "loss": 0.7752,
      "step": 850
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.43756699562072754,
      "learning_rate": 0.0002,
      "loss": 0.8068,
      "step": 875
    },
    {
      "epoch": 7.2,
      "grad_norm": 0.5593159794807434,
      "learning_rate": 0.0002,
      "loss": 0.7582,
      "step": 900
    },
    {
      "epoch": 7.4,
      "grad_norm": 0.3569984436035156,
      "learning_rate": 0.0002,
      "loss": 0.7165,
      "step": 925
    },
    {
      "epoch": 7.6,
      "grad_norm": 0.3286341428756714,
      "learning_rate": 0.0002,
      "loss": 0.706,
      "step": 950
    },
    {
      "epoch": 7.8,
      "grad_norm": 0.27032291889190674,
      "learning_rate": 0.0002,
      "loss": 0.6735,
      "step": 975
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.35773584246635437,
      "learning_rate": 0.0002,
      "loss": 0.7105,
      "step": 1000
    },
    {
      "epoch": 8.2,
      "grad_norm": 0.6158097982406616,
      "learning_rate": 0.0002,
      "loss": 0.6855,
      "step": 1025
    },
    {
      "epoch": 8.4,
      "grad_norm": 0.3763855993747711,
      "learning_rate": 0.0002,
      "loss": 0.6066,
      "step": 1050
    },
    {
      "epoch": 8.6,
      "grad_norm": 0.3213497996330261,
      "learning_rate": 0.0002,
      "loss": 0.623,
      "step": 1075
    },
    {
      "epoch": 8.8,
      "grad_norm": 0.3130660355091095,
      "learning_rate": 0.0002,
      "loss": 0.587,
      "step": 1100
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.49706026911735535,
      "learning_rate": 0.0002,
      "loss": 0.6161,
      "step": 1125
    },
    {
      "epoch": 9.2,
      "grad_norm": 0.606447696685791,
      "learning_rate": 0.0002,
      "loss": 0.5802,
      "step": 1150
    },
    {
      "epoch": 9.4,
      "grad_norm": 0.42242899537086487,
      "learning_rate": 0.0002,
      "loss": 0.5627,
      "step": 1175
    },
    {
      "epoch": 9.6,
      "grad_norm": 0.37915894389152527,
      "learning_rate": 0.0002,
      "loss": 0.5408,
      "step": 1200
    },
    {
      "epoch": 9.8,
      "grad_norm": 0.3458578586578369,
      "learning_rate": 0.0002,
      "loss": 0.524,
      "step": 1225
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.5249849557876587,
      "learning_rate": 0.0002,
      "loss": 0.5091,
      "step": 1250
    }
  ],
  "logging_steps": 25,
  "max_steps": 1250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 25,
  "total_flos": 1.3841243942078054e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}