{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.010796221322537112,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010796221322537112,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 10.2027,
      "step": 1
    },
    {
      "epoch": 0.0010796221322537112,
      "eval_loss": NaN,
      "eval_runtime": 18.5517,
      "eval_samples_per_second": 21.022,
      "eval_steps_per_second": 10.511,
      "step": 1
    },
    {
      "epoch": 0.0021592442645074223,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0032388663967611335,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 5.298,
      "step": 3
    },
    {
      "epoch": 0.0032388663967611335,
      "eval_loss": NaN,
      "eval_runtime": 17.4139,
      "eval_samples_per_second": 22.396,
      "eval_steps_per_second": 11.198,
      "step": 3
    },
    {
      "epoch": 0.004318488529014845,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 13.3949,
      "step": 4
    },
    {
      "epoch": 0.005398110661268556,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.006477732793522267,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.006477732793522267,
      "eval_loss": NaN,
      "eval_runtime": 17.4791,
      "eval_samples_per_second": 22.312,
      "eval_steps_per_second": 11.156,
      "step": 6
    },
    {
      "epoch": 0.007557354925775978,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.00863697705802969,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 15.0364,
      "step": 8
    },
    {
      "epoch": 0.009716599190283401,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.009716599190283401,
      "eval_loss": NaN,
      "eval_runtime": 17.4346,
      "eval_samples_per_second": 22.369,
      "eval_steps_per_second": 11.185,
      "step": 9
    },
    {
      "epoch": 0.010796221322537112,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "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": 2852094423859200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}