{
  "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": 35.47718811035156,
      "learning_rate": 2e-05,
      "loss": 13.3251,
      "step": 1
    },
    {
      "epoch": 3.9897065570827266e-05,
      "eval_loss": 13.681809425354004,
      "eval_runtime": 457.0873,
      "eval_samples_per_second": 23.09,
      "eval_steps_per_second": 11.545,
      "step": 1
    },
    {
      "epoch": 7.979413114165453e-05,
      "grad_norm": 30.661855697631836,
      "learning_rate": 4e-05,
      "loss": 13.4017,
      "step": 2
    },
    {
      "epoch": 0.0001196911967124818,
      "grad_norm": 32.9249267578125,
      "learning_rate": 6e-05,
      "loss": 13.9967,
      "step": 3
    },
    {
      "epoch": 0.0001196911967124818,
      "eval_loss": 13.185033798217773,
      "eval_runtime": 456.4316,
      "eval_samples_per_second": 23.123,
      "eval_steps_per_second": 11.561,
      "step": 3
    },
    {
      "epoch": 0.00015958826228330906,
      "grad_norm": 33.04832077026367,
      "learning_rate": 8e-05,
      "loss": 12.1595,
      "step": 4
    },
    {
      "epoch": 0.00019948532785413634,
      "grad_norm": 26.91349220275879,
      "learning_rate": 0.0001,
      "loss": 13.6996,
      "step": 5
    },
    {
      "epoch": 0.0002393823934249636,
      "grad_norm": 29.799123764038086,
      "learning_rate": 0.00012,
      "loss": 9.4308,
      "step": 6
    },
    {
      "epoch": 0.0002393823934249636,
      "eval_loss": 6.898678779602051,
      "eval_runtime": 456.3521,
      "eval_samples_per_second": 23.127,
      "eval_steps_per_second": 11.563,
      "step": 6
    },
    {
      "epoch": 0.00027927945899579087,
      "grad_norm": 41.86083221435547,
      "learning_rate": 0.00014,
      "loss": 5.7658,
      "step": 7
    },
    {
      "epoch": 0.0003191765245666181,
      "grad_norm": 15.647209167480469,
      "learning_rate": 0.00016,
      "loss": 6.5206,
      "step": 8
    },
    {
      "epoch": 0.0003590735901374454,
      "grad_norm": 8.862835884094238,
      "learning_rate": 0.00018,
      "loss": 3.0896,
      "step": 9
    },
    {
      "epoch": 0.0003590735901374454,
      "eval_loss": 3.4959287643432617,
      "eval_runtime": 456.078,
      "eval_samples_per_second": 23.141,
      "eval_steps_per_second": 11.57,
      "step": 9
    },
    {
      "epoch": 0.0003989706557082727,
      "grad_norm": 11.718125343322754,
      "learning_rate": 0.0002,
      "loss": 4.0113,
      "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
}