{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.026917900403768506,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0026917900403768506,
      "grad_norm": 0.99693363904953,
      "learning_rate": 2e-05,
      "loss": 5.7445,
      "step": 1
    },
    {
      "epoch": 0.0026917900403768506,
      "eval_loss": 5.104186058044434,
      "eval_runtime": 4.5898,
      "eval_samples_per_second": 34.207,
      "eval_steps_per_second": 17.212,
      "step": 1
    },
    {
      "epoch": 0.005383580080753701,
      "grad_norm": 0.8731223940849304,
      "learning_rate": 4e-05,
      "loss": 5.0576,
      "step": 2
    },
    {
      "epoch": 0.008075370121130552,
      "grad_norm": 0.9182137250900269,
      "learning_rate": 6e-05,
      "loss": 5.674,
      "step": 3
    },
    {
      "epoch": 0.008075370121130552,
      "eval_loss": 5.100185394287109,
      "eval_runtime": 3.7416,
      "eval_samples_per_second": 41.96,
      "eval_steps_per_second": 21.114,
      "step": 3
    },
    {
      "epoch": 0.010767160161507403,
      "grad_norm": 0.973735511302948,
      "learning_rate": 8e-05,
      "loss": 5.7622,
      "step": 4
    },
    {
      "epoch": 0.013458950201884253,
      "grad_norm": 0.9886600971221924,
      "learning_rate": 0.0001,
      "loss": 4.9199,
      "step": 5
    },
    {
      "epoch": 0.016150740242261104,
      "grad_norm": 1.0862919092178345,
      "learning_rate": 0.00012,
      "loss": 5.0962,
      "step": 6
    },
    {
      "epoch": 0.016150740242261104,
      "eval_loss": 5.014194965362549,
      "eval_runtime": 3.7876,
      "eval_samples_per_second": 41.451,
      "eval_steps_per_second": 20.858,
      "step": 6
    },
    {
      "epoch": 0.018842530282637954,
      "grad_norm": 1.120705485343933,
      "learning_rate": 0.00014,
      "loss": 4.692,
      "step": 7
    },
    {
      "epoch": 0.021534320323014805,
      "grad_norm": 1.426712155342102,
      "learning_rate": 0.00016,
      "loss": 4.9349,
      "step": 8
    },
    {
      "epoch": 0.024226110363391656,
      "grad_norm": 1.7518353462219238,
      "learning_rate": 0.00018,
      "loss": 4.4496,
      "step": 9
    },
    {
      "epoch": 0.024226110363391656,
      "eval_loss": 4.5209760665893555,
      "eval_runtime": 3.7818,
      "eval_samples_per_second": 41.515,
      "eval_steps_per_second": 20.889,
      "step": 9
    },
    {
      "epoch": 0.026917900403768506,
      "grad_norm": 1.6788541078567505,
      "learning_rate": 0.0002,
      "loss": 4.1978,
      "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": 649047740252160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}