{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.011368480886741509,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002273696177348302,
      "grad_norm": Infinity,
      "learning_rate": 1e-05,
      "loss": 37.7188,
      "step": 1
    },
    {
      "epoch": 0.002273696177348302,
      "eval_loss": 2.162433624267578,
      "eval_runtime": 82.7908,
      "eval_samples_per_second": 8.95,
      "eval_steps_per_second": 4.481,
      "step": 1
    },
    {
      "epoch": 0.004547392354696604,
      "grad_norm": 17.4912052154541,
      "learning_rate": 2e-05,
      "loss": 36.5469,
      "step": 2
    },
    {
      "epoch": 0.004547392354696604,
      "eval_loss": 2.1552114486694336,
      "eval_runtime": 9.2598,
      "eval_samples_per_second": 80.024,
      "eval_steps_per_second": 40.066,
      "step": 2
    },
    {
      "epoch": 0.006821088532044906,
      "grad_norm": 13.584527015686035,
      "learning_rate": 3e-05,
      "loss": 34.4414,
      "step": 3
    },
    {
      "epoch": 0.009094784709393207,
      "grad_norm": 14.076813697814941,
      "learning_rate": 4e-05,
      "loss": 34.2227,
      "step": 4
    },
    {
      "epoch": 0.009094784709393207,
      "eval_loss": 2.136265277862549,
      "eval_runtime": 9.2492,
      "eval_samples_per_second": 80.115,
      "eval_steps_per_second": 40.111,
      "step": 4
    },
    {
      "epoch": 0.011368480886741509,
      "grad_norm": 14.873819351196289,
      "learning_rate": 5e-05,
      "loss": 35.3398,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 178290425856000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}