{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008680781617576847,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.7361563235153692e-05,
      "eval_loss": 3.2406625747680664,
      "eval_runtime": 1579.9553,
      "eval_samples_per_second": 15.35,
      "eval_steps_per_second": 7.675,
      "step": 1
    },
    {
      "epoch": 8.680781617576846e-05,
      "grad_norm": 56.969181060791016,
      "learning_rate": 5e-05,
      "loss": 12.0664,
      "step": 5
    },
    {
      "epoch": 0.00017361563235153692,
      "grad_norm": 48.02027130126953,
      "learning_rate": 0.0001,
      "loss": 8.5399,
      "step": 10
    },
    {
      "epoch": 0.00017361563235153692,
      "eval_loss": 1.7465617656707764,
      "eval_runtime": 1583.1765,
      "eval_samples_per_second": 15.319,
      "eval_steps_per_second": 7.659,
      "step": 10
    },
    {
      "epoch": 0.0002604234485273054,
      "grad_norm": 24.002090454101562,
      "learning_rate": 9.619397662556435e-05,
      "loss": 6.8368,
      "step": 15
    },
    {
      "epoch": 0.00034723126470307384,
      "grad_norm": 22.417949676513672,
      "learning_rate": 8.535533905932738e-05,
      "loss": 6.5063,
      "step": 20
    },
    {
      "epoch": 0.00034723126470307384,
      "eval_loss": 1.3497487306594849,
      "eval_runtime": 1582.5355,
      "eval_samples_per_second": 15.325,
      "eval_steps_per_second": 7.662,
      "step": 20
    },
    {
      "epoch": 0.00043403908087884236,
      "grad_norm": 26.679052352905273,
      "learning_rate": 6.91341716182545e-05,
      "loss": 5.296,
      "step": 25
    },
    {
      "epoch": 0.0005208468970546108,
      "grad_norm": 23.542726516723633,
      "learning_rate": 5e-05,
      "loss": 5.1197,
      "step": 30
    },
    {
      "epoch": 0.0005208468970546108,
      "eval_loss": 1.267897367477417,
      "eval_runtime": 1579.6304,
      "eval_samples_per_second": 15.353,
      "eval_steps_per_second": 7.676,
      "step": 30
    },
    {
      "epoch": 0.0006076547132303793,
      "grad_norm": 19.179880142211914,
      "learning_rate": 3.086582838174551e-05,
      "loss": 4.7048,
      "step": 35
    },
    {
      "epoch": 0.0006944625294061477,
      "grad_norm": 19.000234603881836,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 5.4107,
      "step": 40
    },
    {
      "epoch": 0.0006944625294061477,
      "eval_loss": 1.2511236667633057,
      "eval_runtime": 1584.0605,
      "eval_samples_per_second": 15.31,
      "eval_steps_per_second": 7.655,
      "step": 40
    },
    {
      "epoch": 0.0007812703455819162,
      "grad_norm": 22.011131286621094,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 5.3537,
      "step": 45
    },
    {
      "epoch": 0.0008680781617576847,
      "grad_norm": 17.464994430541992,
      "learning_rate": 0.0,
      "loss": 4.3659,
      "step": 50
    },
    {
      "epoch": 0.0008680781617576847,
      "eval_loss": 1.2439897060394287,
      "eval_runtime": 1587.0763,
      "eval_samples_per_second": 15.281,
      "eval_steps_per_second": 7.64,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8763509991014400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}