{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 625,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016,
      "grad_norm": 14.25,
      "learning_rate": 3.1746031746031746e-06,
      "loss": 2.4132,
      "step": 10
    },
    {
      "epoch": 0.032,
      "grad_norm": 11.4375,
      "learning_rate": 6.349206349206349e-06,
      "loss": 2.462,
      "step": 20
    },
    {
      "epoch": 0.048,
      "grad_norm": 11.0,
      "learning_rate": 9.523809523809525e-06,
      "loss": 2.3388,
      "step": 30
    },
    {
      "epoch": 0.064,
      "grad_norm": 8.5625,
      "learning_rate": 1.2698412698412699e-05,
      "loss": 2.1813,
      "step": 40
    },
    {
      "epoch": 0.08,
      "grad_norm": 8.0625,
      "learning_rate": 1.5873015873015872e-05,
      "loss": 1.9853,
      "step": 50
    },
    {
      "epoch": 0.096,
      "grad_norm": 9.75,
      "learning_rate": 1.904761904761905e-05,
      "loss": 1.9632,
      "step": 60
    },
    {
      "epoch": 0.112,
      "grad_norm": 8.3125,
      "learning_rate": 1.9750889679715305e-05,
      "loss": 1.7842,
      "step": 70
    },
    {
      "epoch": 0.128,
      "grad_norm": 7.75,
      "learning_rate": 1.939501779359431e-05,
      "loss": 1.7123,
      "step": 80
    },
    {
      "epoch": 0.144,
      "grad_norm": 7.5625,
      "learning_rate": 1.903914590747331e-05,
      "loss": 1.6547,
      "step": 90
    },
    {
      "epoch": 0.16,
      "grad_norm": 6.3125,
      "learning_rate": 1.8683274021352315e-05,
      "loss": 1.5779,
      "step": 100
    },
    {
      "epoch": 0.176,
      "grad_norm": 6.46875,
      "learning_rate": 1.832740213523132e-05,
      "loss": 1.5657,
      "step": 110
    },
    {
      "epoch": 0.192,
      "grad_norm": 5.9375,
      "learning_rate": 1.7971530249110324e-05,
      "loss": 1.55,
      "step": 120
    },
    {
      "epoch": 0.208,
      "grad_norm": 6.28125,
      "learning_rate": 1.7615658362989325e-05,
      "loss": 1.504,
      "step": 130
    },
    {
      "epoch": 0.224,
      "grad_norm": 6.65625,
      "learning_rate": 1.725978647686833e-05,
      "loss": 1.5066,
      "step": 140
    },
    {
      "epoch": 0.24,
      "grad_norm": 6.09375,
      "learning_rate": 1.690391459074733e-05,
      "loss": 1.5028,
      "step": 150
    },
    {
      "epoch": 0.256,
      "grad_norm": 6.59375,
      "learning_rate": 1.6548042704626336e-05,
      "loss": 1.4306,
      "step": 160
    },
    {
      "epoch": 0.272,
      "grad_norm": 7.875,
      "learning_rate": 1.619217081850534e-05,
      "loss": 1.4841,
      "step": 170
    },
    {
      "epoch": 0.288,
      "grad_norm": 6.8125,
      "learning_rate": 1.583629893238434e-05,
      "loss": 1.4241,
      "step": 180
    },
    {
      "epoch": 0.304,
      "grad_norm": 6.4375,
      "learning_rate": 1.5480427046263346e-05,
      "loss": 1.4209,
      "step": 190
    },
    {
      "epoch": 0.32,
      "grad_norm": 7.0625,
      "learning_rate": 1.5124555160142349e-05,
      "loss": 1.4404,
      "step": 200
    },
    {
      "epoch": 0.336,
      "grad_norm": 6.0625,
      "learning_rate": 1.4768683274021354e-05,
      "loss": 1.382,
      "step": 210
    },
    {
      "epoch": 0.352,
      "grad_norm": 6.09375,
      "learning_rate": 1.4412811387900356e-05,
      "loss": 1.4079,
      "step": 220
    },
    {
      "epoch": 0.368,
      "grad_norm": 6.0,
      "learning_rate": 1.4056939501779361e-05,
      "loss": 1.3182,
      "step": 230
    },
    {
      "epoch": 0.384,
      "grad_norm": 6.0,
      "learning_rate": 1.3701067615658364e-05,
      "loss": 1.3337,
      "step": 240
    },
    {
      "epoch": 0.4,
      "grad_norm": 6.0,
      "learning_rate": 1.3345195729537369e-05,
      "loss": 1.3165,
      "step": 250
    },
    {
      "epoch": 0.416,
      "grad_norm": 7.8125,
      "learning_rate": 1.298932384341637e-05,
      "loss": 1.2977,
      "step": 260
    },
    {
      "epoch": 0.432,
      "grad_norm": 6.5625,
      "learning_rate": 1.2633451957295374e-05,
      "loss": 1.3135,
      "step": 270
    },
    {
      "epoch": 0.448,
      "grad_norm": 7.65625,
      "learning_rate": 1.2277580071174377e-05,
      "loss": 1.281,
      "step": 280
    },
    {
      "epoch": 0.464,
      "grad_norm": 6.125,
      "learning_rate": 1.1921708185053382e-05,
      "loss": 1.3239,
      "step": 290
    },
    {
      "epoch": 0.48,
      "grad_norm": 6.71875,
      "learning_rate": 1.1565836298932385e-05,
      "loss": 1.287,
      "step": 300
    },
    {
      "epoch": 0.496,
      "grad_norm": 6.0,
      "learning_rate": 1.120996441281139e-05,
      "loss": 1.3248,
      "step": 310
    },
    {
      "epoch": 0.512,
      "grad_norm": 6.71875,
      "learning_rate": 1.0854092526690392e-05,
      "loss": 1.3225,
      "step": 320
    },
    {
      "epoch": 0.528,
      "grad_norm": 6.375,
      "learning_rate": 1.0498220640569397e-05,
      "loss": 1.3121,
      "step": 330
    },
    {
      "epoch": 0.544,
      "grad_norm": 6.0625,
      "learning_rate": 1.01423487544484e-05,
      "loss": 1.2764,
      "step": 340
    },
    {
      "epoch": 0.56,
      "grad_norm": 6.96875,
      "learning_rate": 9.786476868327403e-06,
      "loss": 1.2815,
      "step": 350
    },
    {
      "epoch": 0.576,
      "grad_norm": 6.28125,
      "learning_rate": 9.430604982206405e-06,
      "loss": 1.2981,
      "step": 360
    },
    {
      "epoch": 0.592,
      "grad_norm": 6.09375,
      "learning_rate": 9.07473309608541e-06,
      "loss": 1.2226,
      "step": 370
    },
    {
      "epoch": 0.608,
      "grad_norm": 7.125,
      "learning_rate": 8.718861209964413e-06,
      "loss": 1.2702,
      "step": 380
    },
    {
      "epoch": 0.624,
      "grad_norm": 6.09375,
      "learning_rate": 8.362989323843418e-06,
      "loss": 1.1996,
      "step": 390
    },
    {
      "epoch": 0.64,
      "grad_norm": 6.21875,
      "learning_rate": 8.00711743772242e-06,
      "loss": 1.2685,
      "step": 400
    },
    {
      "epoch": 0.656,
      "grad_norm": 6.84375,
      "learning_rate": 7.651245551601423e-06,
      "loss": 1.3484,
      "step": 410
    },
    {
      "epoch": 0.672,
      "grad_norm": 6.84375,
      "learning_rate": 7.295373665480427e-06,
      "loss": 1.2453,
      "step": 420
    },
    {
      "epoch": 0.688,
      "grad_norm": 5.875,
      "learning_rate": 6.939501779359431e-06,
      "loss": 1.2525,
      "step": 430
    },
    {
      "epoch": 0.704,
      "grad_norm": 6.65625,
      "learning_rate": 6.5836298932384346e-06,
      "loss": 1.1891,
      "step": 440
    },
    {
      "epoch": 0.72,
      "grad_norm": 6.53125,
      "learning_rate": 6.227758007117438e-06,
      "loss": 1.2031,
      "step": 450
    },
    {
      "epoch": 0.736,
      "grad_norm": 7.03125,
      "learning_rate": 5.871886120996442e-06,
      "loss": 1.2297,
      "step": 460
    },
    {
      "epoch": 0.752,
      "grad_norm": 6.53125,
      "learning_rate": 5.516014234875445e-06,
      "loss": 1.1854,
      "step": 470
    },
    {
      "epoch": 0.768,
      "grad_norm": 6.28125,
      "learning_rate": 5.160142348754449e-06,
      "loss": 1.277,
      "step": 480
    },
    {
      "epoch": 0.784,
      "grad_norm": 5.96875,
      "learning_rate": 4.8042704626334524e-06,
      "loss": 1.1824,
      "step": 490
    },
    {
      "epoch": 0.8,
      "grad_norm": 7.625,
      "learning_rate": 4.448398576512456e-06,
      "loss": 1.2103,
      "step": 500
    },
    {
      "epoch": 0.816,
      "grad_norm": 7.5,
      "learning_rate": 4.09252669039146e-06,
      "loss": 1.1943,
      "step": 510
    },
    {
      "epoch": 0.832,
      "grad_norm": 6.78125,
      "learning_rate": 3.7366548042704632e-06,
      "loss": 1.2306,
      "step": 520
    },
    {
      "epoch": 0.848,
      "grad_norm": 7.0625,
      "learning_rate": 3.3807829181494666e-06,
      "loss": 1.2586,
      "step": 530
    },
    {
      "epoch": 0.864,
      "grad_norm": 6.59375,
      "learning_rate": 3.0249110320284703e-06,
      "loss": 1.2192,
      "step": 540
    },
    {
      "epoch": 0.88,
      "grad_norm": 6.03125,
      "learning_rate": 2.669039145907473e-06,
      "loss": 1.207,
      "step": 550
    },
    {
      "epoch": 0.896,
      "grad_norm": 5.875,
      "learning_rate": 2.313167259786477e-06,
      "loss": 1.2041,
      "step": 560
    },
    {
      "epoch": 0.912,
      "grad_norm": 6.5625,
      "learning_rate": 1.9572953736654807e-06,
      "loss": 1.243,
      "step": 570
    },
    {
      "epoch": 0.928,
      "grad_norm": 5.75,
      "learning_rate": 1.6014234875444842e-06,
      "loss": 1.2168,
      "step": 580
    },
    {
      "epoch": 0.944,
      "grad_norm": 7.65625,
      "learning_rate": 1.2455516014234877e-06,
      "loss": 1.2393,
      "step": 590
    },
    {
      "epoch": 0.96,
      "grad_norm": 6.03125,
      "learning_rate": 8.896797153024913e-07,
      "loss": 1.2151,
      "step": 600
    },
    {
      "epoch": 0.976,
      "grad_norm": 8.125,
      "learning_rate": 5.338078291814947e-07,
      "loss": 1.2361,
      "step": 610
    },
    {
      "epoch": 0.992,
      "grad_norm": 6.96875,
      "learning_rate": 1.7793594306049826e-07,
      "loss": 1.2307,
      "step": 620
    },
    {
      "epoch": 1.0,
      "step": 625,
      "total_flos": 7089149865623552.0,
      "train_loss": 1.4169092582702636,
      "train_runtime": 351.5262,
      "train_samples_per_second": 28.447,
      "train_steps_per_second": 1.778
    }
  ],
  "logging_steps": 10,
  "max_steps": 625,
  "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": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7089149865623552.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}