{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0053705692803437165,
  "eval_steps": 3,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010741138560687433,
      "grad_norm": 2.2083053588867188,
      "learning_rate": 2e-05,
      "loss": 1.8117,
      "step": 1
    },
    {
      "epoch": 0.0010741138560687433,
      "eval_loss": 2.334104537963867,
      "eval_runtime": 36.9521,
      "eval_samples_per_second": 10.608,
      "eval_steps_per_second": 5.304,
      "step": 1
    },
    {
      "epoch": 0.0021482277121374865,
      "grad_norm": 2.335937738418579,
      "learning_rate": 4e-05,
      "loss": 1.7871,
      "step": 2
    },
    {
      "epoch": 0.00322234156820623,
      "grad_norm": 3.0078506469726562,
      "learning_rate": 6e-05,
      "loss": 2.0484,
      "step": 3
    },
    {
      "epoch": 0.00322234156820623,
      "eval_loss": 2.260688304901123,
      "eval_runtime": 37.006,
      "eval_samples_per_second": 10.593,
      "eval_steps_per_second": 5.296,
      "step": 3
    },
    {
      "epoch": 0.004296455424274973,
      "grad_norm": 3.236494302749634,
      "learning_rate": 8e-05,
      "loss": 2.4528,
      "step": 4
    },
    {
      "epoch": 0.0053705692803437165,
      "grad_norm": 2.1256258487701416,
      "learning_rate": 0.0001,
      "loss": 1.5065,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2052393617326080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}