{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0007186489399928135,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.186489399928136e-05,
      "grad_norm": 2.0124285221099854,
      "learning_rate": 2e-05,
      "loss": 0.8141,
      "step": 1
    },
    {
      "epoch": 7.186489399928136e-05,
      "eval_loss": 0.900182843208313,
      "eval_runtime": 428.33,
      "eval_samples_per_second": 13.679,
      "eval_steps_per_second": 6.841,
      "step": 1
    },
    {
      "epoch": 0.00014372978799856272,
      "grad_norm": 1.7584153413772583,
      "learning_rate": 4e-05,
      "loss": 0.8269,
      "step": 2
    },
    {
      "epoch": 0.00021559468199784405,
      "grad_norm": 1.7679075002670288,
      "learning_rate": 6e-05,
      "loss": 0.8504,
      "step": 3
    },
    {
      "epoch": 0.00021559468199784405,
      "eval_loss": 0.8821046352386475,
      "eval_runtime": 466.5981,
      "eval_samples_per_second": 12.557,
      "eval_steps_per_second": 6.279,
      "step": 3
    },
    {
      "epoch": 0.00028745957599712543,
      "grad_norm": 2.3857507705688477,
      "learning_rate": 8e-05,
      "loss": 1.0564,
      "step": 4
    },
    {
      "epoch": 0.00035932446999640676,
      "grad_norm": 1.9755971431732178,
      "learning_rate": 0.0001,
      "loss": 0.9299,
      "step": 5
    },
    {
      "epoch": 0.0004311893639956881,
      "grad_norm": 0.9703513383865356,
      "learning_rate": 0.00012,
      "loss": 0.7695,
      "step": 6
    },
    {
      "epoch": 0.0004311893639956881,
      "eval_loss": 0.7238779664039612,
      "eval_runtime": 434.7565,
      "eval_samples_per_second": 13.477,
      "eval_steps_per_second": 6.739,
      "step": 6
    },
    {
      "epoch": 0.0005030542579949694,
      "grad_norm": 0.7655055522918701,
      "learning_rate": 0.00014,
      "loss": 0.6436,
      "step": 7
    },
    {
      "epoch": 0.0005749191519942509,
      "grad_norm": 0.9915606379508972,
      "learning_rate": 0.00016,
      "loss": 0.817,
      "step": 8
    },
    {
      "epoch": 0.0006467840459935322,
      "grad_norm": 0.5387942790985107,
      "learning_rate": 0.00018,
      "loss": 0.3901,
      "step": 9
    },
    {
      "epoch": 0.0006467840459935322,
      "eval_loss": 0.5753056406974792,
      "eval_runtime": 435.0945,
      "eval_samples_per_second": 13.466,
      "eval_steps_per_second": 6.734,
      "step": 9
    },
    {
      "epoch": 0.0007186489399928135,
      "grad_norm": 0.6182520389556885,
      "learning_rate": 0.0002,
      "loss": 0.5491,
      "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": 324298258513920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}