{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008361064196250899,
  "eval_steps": 9,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.3444256785003593e-05,
      "grad_norm": 4.028215408325195,
      "learning_rate": 1e-05,
      "loss": 3.5489,
      "step": 1
    },
    {
      "epoch": 3.3444256785003593e-05,
      "eval_loss": 3.722480297088623,
      "eval_runtime": 2739.1214,
      "eval_samples_per_second": 9.193,
      "eval_steps_per_second": 1.149,
      "step": 1
    },
    {
      "epoch": 6.688851357000719e-05,
      "grad_norm": 4.290927886962891,
      "learning_rate": 2e-05,
      "loss": 3.6949,
      "step": 2
    },
    {
      "epoch": 0.00010033277035501078,
      "grad_norm": 4.205336570739746,
      "learning_rate": 3e-05,
      "loss": 3.5552,
      "step": 3
    },
    {
      "epoch": 0.00013377702714001437,
      "grad_norm": 4.705852508544922,
      "learning_rate": 4e-05,
      "loss": 3.9999,
      "step": 4
    },
    {
      "epoch": 0.00016722128392501797,
      "grad_norm": 4.193447589874268,
      "learning_rate": 5e-05,
      "loss": 3.3292,
      "step": 5
    },
    {
      "epoch": 0.00020066554071002156,
      "grad_norm": 4.9734721183776855,
      "learning_rate": 6e-05,
      "loss": 3.9245,
      "step": 6
    },
    {
      "epoch": 0.00023410979749502515,
      "grad_norm": 5.040078163146973,
      "learning_rate": 7e-05,
      "loss": 3.5262,
      "step": 7
    },
    {
      "epoch": 0.00026755405428002875,
      "grad_norm": 3.55013370513916,
      "learning_rate": 8e-05,
      "loss": 3.2288,
      "step": 8
    },
    {
      "epoch": 0.00030099831106503237,
      "grad_norm": 3.3910467624664307,
      "learning_rate": 9e-05,
      "loss": 3.0514,
      "step": 9
    },
    {
      "epoch": 0.00030099831106503237,
      "eval_loss": 2.8550124168395996,
      "eval_runtime": 2745.5024,
      "eval_samples_per_second": 9.171,
      "eval_steps_per_second": 1.147,
      "step": 9
    },
    {
      "epoch": 0.00033444256785003593,
      "grad_norm": 3.46765398979187,
      "learning_rate": 0.0001,
      "loss": 2.8576,
      "step": 10
    },
    {
      "epoch": 0.00036788682463503956,
      "grad_norm": 3.2942867279052734,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.7446,
      "step": 11
    },
    {
      "epoch": 0.0004013310814200431,
      "grad_norm": 3.2802114486694336,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.4887,
      "step": 12
    },
    {
      "epoch": 0.00043477533820504674,
      "grad_norm": 3.1480672359466553,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.4346,
      "step": 13
    },
    {
      "epoch": 0.0004682195949900503,
      "grad_norm": 3.0352845191955566,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.1358,
      "step": 14
    },
    {
      "epoch": 0.0005016638517750539,
      "grad_norm": 2.5337398052215576,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.797,
      "step": 15
    },
    {
      "epoch": 0.0005351081085600575,
      "grad_norm": 2.5257315635681152,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.66,
      "step": 16
    },
    {
      "epoch": 0.0005685523653450611,
      "grad_norm": 2.703648567199707,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.5367,
      "step": 17
    },
    {
      "epoch": 0.0006019966221300647,
      "grad_norm": 3.4314801692962646,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.6421,
      "step": 18
    },
    {
      "epoch": 0.0006019966221300647,
      "eval_loss": 1.629733681678772,
      "eval_runtime": 2742.8537,
      "eval_samples_per_second": 9.18,
      "eval_steps_per_second": 1.148,
      "step": 18
    },
    {
      "epoch": 0.0006354408789150684,
      "grad_norm": 3.213797092437744,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.591,
      "step": 19
    },
    {
      "epoch": 0.0006688851357000719,
      "grad_norm": 2.8766260147094727,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.5007,
      "step": 20
    },
    {
      "epoch": 0.0007023293924850755,
      "grad_norm": 3.298490285873413,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.6326,
      "step": 21
    },
    {
      "epoch": 0.0007357736492700791,
      "grad_norm": 3.046107530593872,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.6194,
      "step": 22
    },
    {
      "epoch": 0.0007692179060550827,
      "grad_norm": 3.1948232650756836,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.466,
      "step": 23
    },
    {
      "epoch": 0.0008026621628400862,
      "grad_norm": 3.6307601928710938,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.5915,
      "step": 24
    },
    {
      "epoch": 0.0008361064196250899,
      "grad_norm": 3.745431423187256,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.6644,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.85471820890112e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}