{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.035555555555555556,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0035555555555555557,
      "grad_norm": 4.945465564727783,
      "learning_rate": 2e-05,
      "loss": 14.6078,
      "step": 1
    },
    {
      "epoch": 0.0035555555555555557,
      "eval_loss": 3.930302381515503,
      "eval_runtime": 9.0247,
      "eval_samples_per_second": 13.186,
      "eval_steps_per_second": 6.648,
      "step": 1
    },
    {
      "epoch": 0.0071111111111111115,
      "grad_norm": 5.646092891693115,
      "learning_rate": 4e-05,
      "loss": 16.1794,
      "step": 2
    },
    {
      "epoch": 0.010666666666666666,
      "grad_norm": 6.364597320556641,
      "learning_rate": 6e-05,
      "loss": 16.1729,
      "step": 3
    },
    {
      "epoch": 0.010666666666666666,
      "eval_loss": 3.9216103553771973,
      "eval_runtime": 8.9924,
      "eval_samples_per_second": 13.233,
      "eval_steps_per_second": 6.672,
      "step": 3
    },
    {
      "epoch": 0.014222222222222223,
      "grad_norm": 5.770050048828125,
      "learning_rate": 8e-05,
      "loss": 15.8349,
      "step": 4
    },
    {
      "epoch": 0.017777777777777778,
      "grad_norm": 6.2088422775268555,
      "learning_rate": 0.0001,
      "loss": 15.4761,
      "step": 5
    },
    {
      "epoch": 0.021333333333333333,
      "grad_norm": 5.62159538269043,
      "learning_rate": 0.00012,
      "loss": 14.1777,
      "step": 6
    },
    {
      "epoch": 0.021333333333333333,
      "eval_loss": 3.837775945663452,
      "eval_runtime": 9.1786,
      "eval_samples_per_second": 12.965,
      "eval_steps_per_second": 6.537,
      "step": 6
    },
    {
      "epoch": 0.024888888888888887,
      "grad_norm": 6.10140323638916,
      "learning_rate": 0.00014,
      "loss": 15.1797,
      "step": 7
    },
    {
      "epoch": 0.028444444444444446,
      "grad_norm": 6.238091468811035,
      "learning_rate": 0.00016,
      "loss": 15.0549,
      "step": 8
    },
    {
      "epoch": 0.032,
      "grad_norm": 8.15093994140625,
      "learning_rate": 0.00018,
      "loss": 14.9351,
      "step": 9
    },
    {
      "epoch": 0.032,
      "eval_loss": 3.5960772037506104,
      "eval_runtime": 9.1722,
      "eval_samples_per_second": 12.974,
      "eval_steps_per_second": 6.541,
      "step": 9
    },
    {
      "epoch": 0.035555555555555556,
      "grad_norm": 7.295120716094971,
      "learning_rate": 0.0002,
      "loss": 14.3428,
      "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": 1628733135912960.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}