{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3937007874015748,
  "eval_steps": 40,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001968503937007874,
      "eval_loss": 11.930732727050781,
      "eval_runtime": 5.6606,
      "eval_samples_per_second": 151.222,
      "eval_steps_per_second": 75.611,
      "step": 1
    },
    {
      "epoch": 0.07874015748031496,
      "grad_norm": 0.010532720014452934,
      "learning_rate": 1e-05,
      "loss": 11.9308,
      "step": 40
    },
    {
      "epoch": 0.07874015748031496,
      "eval_loss": 11.93071174621582,
      "eval_runtime": 5.6922,
      "eval_samples_per_second": 150.381,
      "eval_steps_per_second": 75.19,
      "step": 40
    },
    {
      "epoch": 0.15748031496062992,
      "grad_norm": 0.008365984074771404,
      "learning_rate": 2e-05,
      "loss": 11.9306,
      "step": 80
    },
    {
      "epoch": 0.15748031496062992,
      "eval_loss": 11.930635452270508,
      "eval_runtime": 5.7389,
      "eval_samples_per_second": 149.158,
      "eval_steps_per_second": 74.579,
      "step": 80
    },
    {
      "epoch": 0.23622047244094488,
      "grad_norm": 0.010611936450004578,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 11.9305,
      "step": 120
    },
    {
      "epoch": 0.23622047244094488,
      "eval_loss": 11.930538177490234,
      "eval_runtime": 5.7383,
      "eval_samples_per_second": 149.172,
      "eval_steps_per_second": 74.586,
      "step": 120
    },
    {
      "epoch": 0.31496062992125984,
      "grad_norm": 0.008034692145884037,
      "learning_rate": 5.000000000000003e-06,
      "loss": 11.9303,
      "step": 160
    },
    {
      "epoch": 0.31496062992125984,
      "eval_loss": 11.930480003356934,
      "eval_runtime": 5.7325,
      "eval_samples_per_second": 149.325,
      "eval_steps_per_second": 74.662,
      "step": 160
    },
    {
      "epoch": 0.3937007874015748,
      "grad_norm": 0.015014749951660633,
      "learning_rate": 0.0,
      "loss": 11.9303,
      "step": 200
    },
    {
      "epoch": 0.3937007874015748,
      "eval_loss": 11.930471420288086,
      "eval_runtime": 5.7288,
      "eval_samples_per_second": 149.42,
      "eval_steps_per_second": 74.71,
      "step": 200
    }
  ],
  "logging_steps": 40,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 40,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 156977430528.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}