{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0005850775959161584,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.9502586530538612e-05,
      "eval_loss": 3.453108072280884,
      "eval_runtime": 1466.7785,
      "eval_samples_per_second": 14.719,
      "eval_steps_per_second": 7.36,
      "step": 1
    },
    {
      "epoch": 5.850775959161584e-05,
      "grad_norm": 29.78322982788086,
      "learning_rate": 6e-05,
      "loss": 15.4558,
      "step": 3
    },
    {
      "epoch": 0.00011701551918323167,
      "grad_norm": 16.993513107299805,
      "learning_rate": 0.00012,
      "loss": 12.5761,
      "step": 6
    },
    {
      "epoch": 0.0001560206922443089,
      "eval_loss": 2.9539127349853516,
      "eval_runtime": 1467.4803,
      "eval_samples_per_second": 14.712,
      "eval_steps_per_second": 7.356,
      "step": 8
    },
    {
      "epoch": 0.00017552327877484752,
      "grad_norm": 12.85067081451416,
      "learning_rate": 0.00018,
      "loss": 11.6503,
      "step": 9
    },
    {
      "epoch": 0.00023403103836646335,
      "grad_norm": 17.868330001831055,
      "learning_rate": 0.00019510565162951537,
      "loss": 11.7207,
      "step": 12
    },
    {
      "epoch": 0.0002925387979580792,
      "grad_norm": 13.60641098022461,
      "learning_rate": 0.00017071067811865476,
      "loss": 11.5884,
      "step": 15
    },
    {
      "epoch": 0.0003120413844886178,
      "eval_loss": 2.744744300842285,
      "eval_runtime": 1468.1313,
      "eval_samples_per_second": 14.706,
      "eval_steps_per_second": 7.353,
      "step": 16
    },
    {
      "epoch": 0.00035104655754969504,
      "grad_norm": 13.693025588989258,
      "learning_rate": 0.00013090169943749476,
      "loss": 10.7769,
      "step": 18
    },
    {
      "epoch": 0.00040955431714131084,
      "grad_norm": 16.416988372802734,
      "learning_rate": 8.435655349597689e-05,
      "loss": 10.6507,
      "step": 21
    },
    {
      "epoch": 0.0004680620767329267,
      "grad_norm": 13.546721458435059,
      "learning_rate": 4.12214747707527e-05,
      "loss": 11.2692,
      "step": 24
    },
    {
      "epoch": 0.0004680620767329267,
      "eval_loss": 2.682469129562378,
      "eval_runtime": 1467.7144,
      "eval_samples_per_second": 14.71,
      "eval_steps_per_second": 7.355,
      "step": 24
    },
    {
      "epoch": 0.0005265698363245426,
      "grad_norm": 16.323583602905273,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 10.9527,
      "step": 27
    },
    {
      "epoch": 0.0005850775959161584,
      "grad_norm": 13.710123062133789,
      "learning_rate": 0.0,
      "loss": 11.1326,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.054694248022016e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}