{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0042215467747382645,
  "eval_steps": 9,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016886187098953058,
      "grad_norm": 13.738941192626953,
      "learning_rate": 1e-05,
      "loss": 6.6647,
      "step": 1
    },
    {
      "epoch": 0.00016886187098953058,
      "eval_loss": 7.013807773590088,
      "eval_runtime": 547.6222,
      "eval_samples_per_second": 9.107,
      "eval_steps_per_second": 1.139,
      "step": 1
    },
    {
      "epoch": 0.00033772374197906115,
      "grad_norm": 11.927528381347656,
      "learning_rate": 2e-05,
      "loss": 6.6838,
      "step": 2
    },
    {
      "epoch": 0.0005065856129685917,
      "grad_norm": 12.927790641784668,
      "learning_rate": 3e-05,
      "loss": 6.7555,
      "step": 3
    },
    {
      "epoch": 0.0006754474839581223,
      "grad_norm": 16.575254440307617,
      "learning_rate": 4e-05,
      "loss": 6.658,
      "step": 4
    },
    {
      "epoch": 0.0008443093549476528,
      "grad_norm": 16.825057983398438,
      "learning_rate": 5e-05,
      "loss": 6.912,
      "step": 5
    },
    {
      "epoch": 0.0010131712259371835,
      "grad_norm": 19.55130958557129,
      "learning_rate": 6e-05,
      "loss": 7.1032,
      "step": 6
    },
    {
      "epoch": 0.001182033096926714,
      "grad_norm": 18.538299560546875,
      "learning_rate": 7e-05,
      "loss": 5.4669,
      "step": 7
    },
    {
      "epoch": 0.0013508949679162446,
      "grad_norm": 16.627212524414062,
      "learning_rate": 8e-05,
      "loss": 3.6652,
      "step": 8
    },
    {
      "epoch": 0.001519756838905775,
      "grad_norm": 17.426902770996094,
      "learning_rate": 9e-05,
      "loss": 1.4218,
      "step": 9
    },
    {
      "epoch": 0.001519756838905775,
      "eval_loss": 1.1324265003204346,
      "eval_runtime": 547.8033,
      "eval_samples_per_second": 9.104,
      "eval_steps_per_second": 1.139,
      "step": 9
    },
    {
      "epoch": 0.0016886187098953055,
      "grad_norm": 9.461427688598633,
      "learning_rate": 0.0001,
      "loss": 0.8645,
      "step": 10
    },
    {
      "epoch": 0.0018574805808848362,
      "grad_norm": 14.465333938598633,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.5779,
      "step": 11
    },
    {
      "epoch": 0.002026342451874367,
      "grad_norm": 4.43085241317749,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.2061,
      "step": 12
    },
    {
      "epoch": 0.002195204322863897,
      "grad_norm": 3.272099018096924,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.2045,
      "step": 13
    },
    {
      "epoch": 0.002364066193853428,
      "grad_norm": 6.308006763458252,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.151,
      "step": 14
    },
    {
      "epoch": 0.0025329280648429585,
      "grad_norm": 2.1944222450256348,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.0865,
      "step": 15
    },
    {
      "epoch": 0.002701789935832489,
      "grad_norm": 3.657510280609131,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.0805,
      "step": 16
    },
    {
      "epoch": 0.0028706518068220195,
      "grad_norm": 7.360884189605713,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.2637,
      "step": 17
    },
    {
      "epoch": 0.00303951367781155,
      "grad_norm": 7.242488384246826,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.2653,
      "step": 18
    },
    {
      "epoch": 0.00303951367781155,
      "eval_loss": 0.1920052468776703,
      "eval_runtime": 548.1102,
      "eval_samples_per_second": 9.099,
      "eval_steps_per_second": 1.138,
      "step": 18
    },
    {
      "epoch": 0.003208375548801081,
      "grad_norm": 4.502208709716797,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0484,
      "step": 19
    },
    {
      "epoch": 0.003377237419790611,
      "grad_norm": 22.75486946105957,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.4917,
      "step": 20
    },
    {
      "epoch": 0.0035460992907801418,
      "grad_norm": 10.100854873657227,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.3209,
      "step": 21
    },
    {
      "epoch": 0.0037149611617696724,
      "grad_norm": 7.107204437255859,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.1272,
      "step": 22
    },
    {
      "epoch": 0.003883823032759203,
      "grad_norm": 8.472229957580566,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.1549,
      "step": 23
    },
    {
      "epoch": 0.004052684903748734,
      "grad_norm": 7.11989164352417,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.3053,
      "step": 24
    },
    {
      "epoch": 0.0042215467747382645,
      "grad_norm": 8.643906593322754,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.467,
      "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
}