{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07889546351084813,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007889546351084813,
      "grad_norm": 0.9305204153060913,
      "learning_rate": 2e-05,
      "loss": 2.4609,
      "step": 1
    },
    {
      "epoch": 0.007889546351084813,
      "eval_loss": 2.4809954166412354,
      "eval_runtime": 2.4627,
      "eval_samples_per_second": 86.895,
      "eval_steps_per_second": 10.963,
      "step": 1
    },
    {
      "epoch": 0.015779092702169626,
      "grad_norm": 0.97751384973526,
      "learning_rate": 4e-05,
      "loss": 2.4987,
      "step": 2
    },
    {
      "epoch": 0.023668639053254437,
      "grad_norm": 0.8712426424026489,
      "learning_rate": 6e-05,
      "loss": 2.4658,
      "step": 3
    },
    {
      "epoch": 0.023668639053254437,
      "eval_loss": 2.454739570617676,
      "eval_runtime": 1.8562,
      "eval_samples_per_second": 115.286,
      "eval_steps_per_second": 14.545,
      "step": 3
    },
    {
      "epoch": 0.03155818540433925,
      "grad_norm": 0.8664816617965698,
      "learning_rate": 8e-05,
      "loss": 2.4487,
      "step": 4
    },
    {
      "epoch": 0.03944773175542406,
      "grad_norm": 0.7029237151145935,
      "learning_rate": 0.0001,
      "loss": 2.4527,
      "step": 5
    },
    {
      "epoch": 0.047337278106508875,
      "grad_norm": 0.6516984105110168,
      "learning_rate": 0.00012,
      "loss": 2.4506,
      "step": 6
    },
    {
      "epoch": 0.047337278106508875,
      "eval_loss": 2.3944079875946045,
      "eval_runtime": 1.879,
      "eval_samples_per_second": 113.893,
      "eval_steps_per_second": 14.37,
      "step": 6
    },
    {
      "epoch": 0.055226824457593686,
      "grad_norm": 0.74710613489151,
      "learning_rate": 0.00014,
      "loss": 2.4339,
      "step": 7
    },
    {
      "epoch": 0.0631163708086785,
      "grad_norm": 0.7509329915046692,
      "learning_rate": 0.00016,
      "loss": 2.3672,
      "step": 8
    },
    {
      "epoch": 0.07100591715976332,
      "grad_norm": 0.7366978526115417,
      "learning_rate": 0.00018,
      "loss": 2.3838,
      "step": 9
    },
    {
      "epoch": 0.07100591715976332,
      "eval_loss": 2.343579053878784,
      "eval_runtime": 1.8762,
      "eval_samples_per_second": 114.06,
      "eval_steps_per_second": 14.391,
      "step": 9
    },
    {
      "epoch": 0.07889546351084813,
      "grad_norm": 0.7767159938812256,
      "learning_rate": 0.0002,
      "loss": 2.3549,
      "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": 2883817203302400.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}