{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005198180636777128,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005198180636777127,
      "grad_norm": 23.659555435180664,
      "learning_rate": 2e-05,
      "loss": 6.7677,
      "step": 1
    },
    {
      "epoch": 0.0005198180636777127,
      "eval_loss": 1.7232974767684937,
      "eval_runtime": 11.2314,
      "eval_samples_per_second": 72.208,
      "eval_steps_per_second": 36.149,
      "step": 1
    },
    {
      "epoch": 0.0010396361273554255,
      "grad_norm": 24.192602157592773,
      "learning_rate": 4e-05,
      "loss": 6.6812,
      "step": 2
    },
    {
      "epoch": 0.0015594541910331384,
      "grad_norm": 17.6358699798584,
      "learning_rate": 6e-05,
      "loss": 6.2984,
      "step": 3
    },
    {
      "epoch": 0.0015594541910331384,
      "eval_loss": 1.7251933813095093,
      "eval_runtime": 10.932,
      "eval_samples_per_second": 74.186,
      "eval_steps_per_second": 37.139,
      "step": 3
    },
    {
      "epoch": 0.002079272254710851,
      "grad_norm": 23.270580291748047,
      "learning_rate": 8e-05,
      "loss": 6.3308,
      "step": 4
    },
    {
      "epoch": 0.002599090318388564,
      "grad_norm": 20.584447860717773,
      "learning_rate": 0.0001,
      "loss": 6.5874,
      "step": 5
    },
    {
      "epoch": 0.0031189083820662767,
      "grad_norm": 17.223291397094727,
      "learning_rate": 0.00012,
      "loss": 7.0388,
      "step": 6
    },
    {
      "epoch": 0.0031189083820662767,
      "eval_loss": 1.7166107892990112,
      "eval_runtime": 10.5576,
      "eval_samples_per_second": 76.816,
      "eval_steps_per_second": 38.456,
      "step": 6
    },
    {
      "epoch": 0.0036387264457439896,
      "grad_norm": 19.44442367553711,
      "learning_rate": 0.00014,
      "loss": 7.4614,
      "step": 7
    },
    {
      "epoch": 0.004158544509421702,
      "grad_norm": 23.95518684387207,
      "learning_rate": 0.00016,
      "loss": 6.9581,
      "step": 8
    },
    {
      "epoch": 0.004678362573099415,
      "grad_norm": 21.72780990600586,
      "learning_rate": 0.00018,
      "loss": 6.5957,
      "step": 9
    },
    {
      "epoch": 0.004678362573099415,
      "eval_loss": 1.6892961263656616,
      "eval_runtime": 10.5882,
      "eval_samples_per_second": 76.595,
      "eval_steps_per_second": 38.345,
      "step": 9
    },
    {
      "epoch": 0.005198180636777128,
      "grad_norm": 20.988662719726562,
      "learning_rate": 0.0002,
      "loss": 6.5359,
      "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": 175457131560960.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}