{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 4,
  "global_step": 14,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07142857142857142,
      "eval_loss": 1.3440238237380981,
      "eval_runtime": 0.4188,
      "eval_samples_per_second": 4.776,
      "eval_steps_per_second": 2.388,
      "step": 1
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 3.641674518585205,
      "learning_rate": 6e-05,
      "loss": 1.5112,
      "step": 3
    },
    {
      "epoch": 0.2857142857142857,
      "eval_loss": 1.2729363441467285,
      "eval_runtime": 0.4224,
      "eval_samples_per_second": 4.735,
      "eval_steps_per_second": 2.368,
      "step": 4
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 1.652285099029541,
      "learning_rate": 0.00012,
      "loss": 1.4388,
      "step": 6
    },
    {
      "epoch": 0.5714285714285714,
      "eval_loss": 0.9863370656967163,
      "eval_runtime": 0.4225,
      "eval_samples_per_second": 4.733,
      "eval_steps_per_second": 2.367,
      "step": 8
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 1.5673928260803223,
      "learning_rate": 0.00018,
      "loss": 1.2657,
      "step": 9
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 3.1150293350219727,
      "learning_rate": 0.0001,
      "loss": 0.9705,
      "step": 12
    },
    {
      "epoch": 0.8571428571428571,
      "eval_loss": 0.8828628659248352,
      "eval_runtime": 0.43,
      "eval_samples_per_second": 4.651,
      "eval_steps_per_second": 2.326,
      "step": 12
    }
  ],
  "logging_steps": 3,
  "max_steps": 14,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2684130265399296.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}