{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0005714612263557917,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.714612263557917e-05,
      "grad_norm": 8.440564155578613,
      "learning_rate": 2e-05,
      "loss": 4.652,
      "step": 1
    },
    {
      "epoch": 5.714612263557917e-05,
      "eval_loss": 8.63033676147461,
      "eval_runtime": 635.9808,
      "eval_samples_per_second": 11.585,
      "eval_steps_per_second": 5.793,
      "step": 1
    },
    {
      "epoch": 0.00011429224527115835,
      "grad_norm": 3.354069232940674,
      "learning_rate": 4e-05,
      "loss": 2.992,
      "step": 2
    },
    {
      "epoch": 0.00017143836790673754,
      "grad_norm": 8.306694030761719,
      "learning_rate": 6e-05,
      "loss": 5.9776,
      "step": 3
    },
    {
      "epoch": 0.00017143836790673754,
      "eval_loss": 8.384699821472168,
      "eval_runtime": 636.1494,
      "eval_samples_per_second": 11.582,
      "eval_steps_per_second": 5.791,
      "step": 3
    },
    {
      "epoch": 0.0002285844905423167,
      "grad_norm": 3.1300694942474365,
      "learning_rate": 8e-05,
      "loss": 2.4436,
      "step": 4
    },
    {
      "epoch": 0.00028573061317789587,
      "grad_norm": 6.622464179992676,
      "learning_rate": 0.0001,
      "loss": 2.725,
      "step": 5
    },
    {
      "epoch": 0.0003428767358134751,
      "grad_norm": 9.001588821411133,
      "learning_rate": 0.00012,
      "loss": 5.2611,
      "step": 6
    },
    {
      "epoch": 0.0003428767358134751,
      "eval_loss": 6.090610980987549,
      "eval_runtime": 636.4144,
      "eval_samples_per_second": 11.577,
      "eval_steps_per_second": 5.789,
      "step": 6
    },
    {
      "epoch": 0.00040002285844905423,
      "grad_norm": 3.785672664642334,
      "learning_rate": 0.00014,
      "loss": 2.5692,
      "step": 7
    },
    {
      "epoch": 0.0004571689810846334,
      "grad_norm": 5.170735836029053,
      "learning_rate": 0.00016,
      "loss": 3.3098,
      "step": 8
    },
    {
      "epoch": 0.0005143151037202125,
      "grad_norm": 3.0438833236694336,
      "learning_rate": 0.00018,
      "loss": 2.1233,
      "step": 9
    },
    {
      "epoch": 0.0005143151037202125,
      "eval_loss": 3.933885097503662,
      "eval_runtime": 636.4373,
      "eval_samples_per_second": 11.577,
      "eval_steps_per_second": 5.788,
      "step": 9
    },
    {
      "epoch": 0.0005714612263557917,
      "grad_norm": 38.98322677612305,
      "learning_rate": 0.0002,
      "loss": 5.961,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4053477394219008.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}