{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008667701975513742,
  "eval_steps": 2,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001444616995918957,
      "grad_norm": 29.741775512695312,
      "learning_rate": 1e-05,
      "loss": 21.916,
      "step": 1
    },
    {
      "epoch": 0.0001444616995918957,
      "eval_loss": 4.278669834136963,
      "eval_runtime": 411.0727,
      "eval_samples_per_second": 7.091,
      "eval_steps_per_second": 3.547,
      "step": 1
    },
    {
      "epoch": 0.0002889233991837914,
      "grad_norm": 28.80156707763672,
      "learning_rate": 2e-05,
      "loss": 18.1093,
      "step": 2
    },
    {
      "epoch": 0.0002889233991837914,
      "eval_loss": 4.272582054138184,
      "eval_runtime": 412.4395,
      "eval_samples_per_second": 7.068,
      "eval_steps_per_second": 3.535,
      "step": 2
    },
    {
      "epoch": 0.0004333850987756871,
      "grad_norm": 27.65138816833496,
      "learning_rate": 3e-05,
      "loss": 11.7399,
      "step": 3
    },
    {
      "epoch": 0.0005778467983675828,
      "grad_norm": 33.123443603515625,
      "learning_rate": 4e-05,
      "loss": 15.397,
      "step": 4
    },
    {
      "epoch": 0.0005778467983675828,
      "eval_loss": 4.1736063957214355,
      "eval_runtime": 412.3727,
      "eval_samples_per_second": 7.069,
      "eval_steps_per_second": 3.536,
      "step": 4
    },
    {
      "epoch": 0.0007223084979594785,
      "grad_norm": 48.433624267578125,
      "learning_rate": 5e-05,
      "loss": 16.1812,
      "step": 5
    },
    {
      "epoch": 0.0008667701975513742,
      "grad_norm": 30.907163619995117,
      "learning_rate": 6e-05,
      "loss": 13.8531,
      "step": 6
    },
    {
      "epoch": 0.0008667701975513742,
      "eval_loss": 3.9675278663635254,
      "eval_runtime": 412.3112,
      "eval_samples_per_second": 7.07,
      "eval_steps_per_second": 3.536,
      "step": 6
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "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": 1960393933062144.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}