{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0017498291182501708,
  "eval_steps": 2,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004374572795625427,
      "grad_norm": 0.5104346871376038,
      "learning_rate": 1e-05,
      "loss": 1.9641,
      "step": 1
    },
    {
      "epoch": 0.0004374572795625427,
      "eval_loss": 3.3701279163360596,
      "eval_runtime": 348.7851,
      "eval_samples_per_second": 11.038,
      "eval_steps_per_second": 5.519,
      "step": 1
    },
    {
      "epoch": 0.0008749145591250854,
      "grad_norm": 0.6189126968383789,
      "learning_rate": 2e-05,
      "loss": 2.2266,
      "step": 2
    },
    {
      "epoch": 0.0008749145591250854,
      "eval_loss": 3.3415215015411377,
      "eval_runtime": 274.714,
      "eval_samples_per_second": 14.015,
      "eval_steps_per_second": 7.007,
      "step": 2
    },
    {
      "epoch": 0.0013123718386876281,
      "grad_norm": 0.5454967021942139,
      "learning_rate": 3e-05,
      "loss": 1.9636,
      "step": 3
    },
    {
      "epoch": 0.0017498291182501708,
      "grad_norm": 0.7716733813285828,
      "learning_rate": 4e-05,
      "loss": 2.9186,
      "step": 4
    },
    {
      "epoch": 0.0017498291182501708,
      "eval_loss": 3.322148323059082,
      "eval_runtime": 275.0609,
      "eval_samples_per_second": 13.997,
      "eval_steps_per_second": 6.998,
      "step": 4
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2173128962211840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}