{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0003989706557082727,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.9897065570827266e-05,
      "grad_norm": 3.5702507495880127,
      "learning_rate": 2e-05,
      "loss": 1.5416,
      "step": 1
    },
    {
      "epoch": 3.9897065570827266e-05,
      "eval_loss": 2.3241939544677734,
      "eval_runtime": 446.3497,
      "eval_samples_per_second": 23.645,
      "eval_steps_per_second": 11.823,
      "step": 1
    },
    {
      "epoch": 7.979413114165453e-05,
      "grad_norm": 5.230420112609863,
      "learning_rate": 4e-05,
      "loss": 2.5934,
      "step": 2
    },
    {
      "epoch": 0.0001196911967124818,
      "grad_norm": 9.121637344360352,
      "learning_rate": 6e-05,
      "loss": 2.594,
      "step": 3
    },
    {
      "epoch": 0.0001196911967124818,
      "eval_loss": 2.318938732147217,
      "eval_runtime": 444.2607,
      "eval_samples_per_second": 23.756,
      "eval_steps_per_second": 11.878,
      "step": 3
    },
    {
      "epoch": 0.00015958826228330906,
      "grad_norm": 3.5380563735961914,
      "learning_rate": 8e-05,
      "loss": 1.0391,
      "step": 4
    },
    {
      "epoch": 0.00019948532785413634,
      "grad_norm": 8.689284324645996,
      "learning_rate": 0.0001,
      "loss": 5.1956,
      "step": 5
    },
    {
      "epoch": 0.0002393823934249636,
      "grad_norm": 10.165144920349121,
      "learning_rate": 0.00012,
      "loss": 1.8167,
      "step": 6
    },
    {
      "epoch": 0.0002393823934249636,
      "eval_loss": 2.206679344177246,
      "eval_runtime": 444.3033,
      "eval_samples_per_second": 23.754,
      "eval_steps_per_second": 11.877,
      "step": 6
    },
    {
      "epoch": 0.00027927945899579087,
      "grad_norm": 5.661115646362305,
      "learning_rate": 0.00014,
      "loss": 1.604,
      "step": 7
    },
    {
      "epoch": 0.0003191765245666181,
      "grad_norm": 11.387893676757812,
      "learning_rate": 0.00016,
      "loss": 2.5723,
      "step": 8
    },
    {
      "epoch": 0.0003590735901374454,
      "grad_norm": 10.127872467041016,
      "learning_rate": 0.00018,
      "loss": 1.1432,
      "step": 9
    },
    {
      "epoch": 0.0003590735901374454,
      "eval_loss": 1.4466105699539185,
      "eval_runtime": 444.4069,
      "eval_samples_per_second": 23.749,
      "eval_steps_per_second": 11.874,
      "step": 9
    },
    {
      "epoch": 0.0003989706557082727,
      "grad_norm": 8.625518798828125,
      "learning_rate": 0.0002,
      "loss": 1.8661,
      "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": 2774346372218880.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}