{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2886783942264321,
  "eval_steps": 40,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014433919711321606,
      "eval_loss": 2.8301005363464355,
      "eval_runtime": 79.3064,
      "eval_samples_per_second": 14.715,
      "eval_steps_per_second": 7.364,
      "step": 1
    },
    {
      "epoch": 0.05773567884528642,
      "grad_norm": 0.978273868560791,
      "learning_rate": 1e-05,
      "loss": 2.7001,
      "step": 40
    },
    {
      "epoch": 0.05773567884528642,
      "eval_loss": 2.704793691635132,
      "eval_runtime": 77.827,
      "eval_samples_per_second": 14.995,
      "eval_steps_per_second": 7.504,
      "step": 40
    },
    {
      "epoch": 0.11547135769057285,
      "grad_norm": 0.7296150922775269,
      "learning_rate": 2e-05,
      "loss": 2.4352,
      "step": 80
    },
    {
      "epoch": 0.11547135769057285,
      "eval_loss": 2.3030242919921875,
      "eval_runtime": 77.8746,
      "eval_samples_per_second": 14.986,
      "eval_steps_per_second": 7.499,
      "step": 80
    },
    {
      "epoch": 0.17320703653585928,
      "grad_norm": 0.6077208518981934,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 2.2109,
      "step": 120
    },
    {
      "epoch": 0.17320703653585928,
      "eval_loss": 2.2112300395965576,
      "eval_runtime": 77.9093,
      "eval_samples_per_second": 14.979,
      "eval_steps_per_second": 7.496,
      "step": 120
    },
    {
      "epoch": 0.2309427153811457,
      "grad_norm": 0.6882339715957642,
      "learning_rate": 5.000000000000003e-06,
      "loss": 2.1861,
      "step": 160
    },
    {
      "epoch": 0.2309427153811457,
      "eval_loss": 2.1889638900756836,
      "eval_runtime": 78.1035,
      "eval_samples_per_second": 14.942,
      "eval_steps_per_second": 7.477,
      "step": 160
    },
    {
      "epoch": 0.2886783942264321,
      "grad_norm": 0.6551962494850159,
      "learning_rate": 0.0,
      "loss": 2.1619,
      "step": 200
    },
    {
      "epoch": 0.2886783942264321,
      "eval_loss": 2.185681104660034,
      "eval_runtime": 77.8978,
      "eval_samples_per_second": 14.981,
      "eval_steps_per_second": 7.497,
      "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": 1.547160493574062e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}