{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06109979633401222,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002036659877800407,
      "eval_loss": 9.511523246765137,
      "eval_runtime": 27.2295,
      "eval_samples_per_second": 7.602,
      "eval_steps_per_second": 3.819,
      "step": 1
    },
    {
      "epoch": 0.006109979633401222,
      "grad_norm": 11.899316787719727,
      "learning_rate": 6e-05,
      "loss": 9.82,
      "step": 3
    },
    {
      "epoch": 0.012219959266802444,
      "grad_norm": 7.663187503814697,
      "learning_rate": 0.00012,
      "loss": 8.8575,
      "step": 6
    },
    {
      "epoch": 0.016293279022403257,
      "eval_loss": 5.380807399749756,
      "eval_runtime": 26.8628,
      "eval_samples_per_second": 7.706,
      "eval_steps_per_second": 3.872,
      "step": 8
    },
    {
      "epoch": 0.018329938900203666,
      "grad_norm": 11.463760375976562,
      "learning_rate": 0.00018,
      "loss": 6.5596,
      "step": 9
    },
    {
      "epoch": 0.024439918533604887,
      "grad_norm": 7.058080196380615,
      "learning_rate": 0.00019510565162951537,
      "loss": 2.3358,
      "step": 12
    },
    {
      "epoch": 0.03054989816700611,
      "grad_norm": 7.287899971008301,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.455,
      "step": 15
    },
    {
      "epoch": 0.032586558044806514,
      "eval_loss": 0.3699367344379425,
      "eval_runtime": 27.0208,
      "eval_samples_per_second": 7.661,
      "eval_steps_per_second": 3.849,
      "step": 16
    },
    {
      "epoch": 0.03665987780040733,
      "grad_norm": 4.653202533721924,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.2774,
      "step": 18
    },
    {
      "epoch": 0.04276985743380855,
      "grad_norm": 1.0046573877334595,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.2072,
      "step": 21
    },
    {
      "epoch": 0.048879837067209775,
      "grad_norm": 5.679718494415283,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.3171,
      "step": 24
    },
    {
      "epoch": 0.048879837067209775,
      "eval_loss": 0.22674037516117096,
      "eval_runtime": 27.0728,
      "eval_samples_per_second": 7.646,
      "eval_steps_per_second": 3.841,
      "step": 24
    },
    {
      "epoch": 0.054989816700611,
      "grad_norm": 2.2360281944274902,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.2582,
      "step": 27
    },
    {
      "epoch": 0.06109979633401222,
      "grad_norm": 2.5707244873046875,
      "learning_rate": 0.0,
      "loss": 0.2164,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 70,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.109738548887552e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}