{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.14184397163120568,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014184397163120567,
      "grad_norm": 0.3054589629173279,
      "learning_rate": 2e-05,
      "loss": 11.9313,
      "step": 1
    },
    {
      "epoch": 0.014184397163120567,
      "eval_loss": 11.930295944213867,
      "eval_runtime": 0.7461,
      "eval_samples_per_second": 144.754,
      "eval_steps_per_second": 48.251,
      "step": 1
    },
    {
      "epoch": 0.028368794326241134,
      "grad_norm": 0.20510129630565643,
      "learning_rate": 4e-05,
      "loss": 11.9315,
      "step": 2
    },
    {
      "epoch": 0.0425531914893617,
      "grad_norm": 0.23965780436992645,
      "learning_rate": 6e-05,
      "loss": 11.9315,
      "step": 3
    },
    {
      "epoch": 0.0425531914893617,
      "eval_loss": 11.929713249206543,
      "eval_runtime": 0.7474,
      "eval_samples_per_second": 144.505,
      "eval_steps_per_second": 48.168,
      "step": 3
    },
    {
      "epoch": 0.05673758865248227,
      "grad_norm": 0.2697097957134247,
      "learning_rate": 8e-05,
      "loss": 11.926,
      "step": 4
    },
    {
      "epoch": 0.07092198581560284,
      "grad_norm": 0.26272961497306824,
      "learning_rate": 0.0001,
      "loss": 11.9299,
      "step": 5
    },
    {
      "epoch": 0.0851063829787234,
      "grad_norm": 0.2433949112892151,
      "learning_rate": 0.00012,
      "loss": 11.9302,
      "step": 6
    },
    {
      "epoch": 0.0851063829787234,
      "eval_loss": 11.927234649658203,
      "eval_runtime": 0.7783,
      "eval_samples_per_second": 138.757,
      "eval_steps_per_second": 46.252,
      "step": 6
    },
    {
      "epoch": 0.09929078014184398,
      "grad_norm": 0.23150305449962616,
      "learning_rate": 0.00014,
      "loss": 11.93,
      "step": 7
    },
    {
      "epoch": 0.11347517730496454,
      "grad_norm": 0.2856377959251404,
      "learning_rate": 0.00016,
      "loss": 11.9245,
      "step": 8
    },
    {
      "epoch": 0.1276595744680851,
      "grad_norm": 0.30839478969573975,
      "learning_rate": 0.00018,
      "loss": 11.9249,
      "step": 9
    },
    {
      "epoch": 0.1276595744680851,
      "eval_loss": 11.922473907470703,
      "eval_runtime": 0.7593,
      "eval_samples_per_second": 142.243,
      "eval_steps_per_second": 47.414,
      "step": 9
    },
    {
      "epoch": 0.14184397163120568,
      "grad_norm": 0.2909541130065918,
      "learning_rate": 0.0002,
      "loss": 11.9263,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7617081507840.0,
  "train_batch_size": 3,
  "trial_name": null,
  "trial_params": null
}