{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1340782122905028,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004469273743016759,
      "eval_loss": NaN,
      "eval_runtime": 12.4061,
      "eval_samples_per_second": 7.658,
      "eval_steps_per_second": 3.869,
      "step": 1
    },
    {
      "epoch": 0.013407821229050279,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.026815642458100558,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.035754189944134075,
      "eval_loss": NaN,
      "eval_runtime": 11.5199,
      "eval_samples_per_second": 8.247,
      "eval_steps_per_second": 4.167,
      "step": 8
    },
    {
      "epoch": 0.04022346368715084,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.053631284916201116,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0670391061452514,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.07150837988826815,
      "eval_loss": NaN,
      "eval_runtime": 11.5003,
      "eval_samples_per_second": 8.261,
      "eval_steps_per_second": 4.174,
      "step": 16
    },
    {
      "epoch": 0.08044692737430167,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.09385474860335195,
      "grad_norm": NaN,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.10726256983240223,
      "grad_norm": NaN,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.10726256983240223,
      "eval_loss": NaN,
      "eval_runtime": 11.4761,
      "eval_samples_per_second": 8.278,
      "eval_steps_per_second": 4.183,
      "step": 24
    },
    {
      "epoch": 0.12067039106145251,
      "grad_norm": NaN,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.1340782122905028,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 70,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.112830925340672e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}