{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0002971459135008246,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.4857295675041229e-05,
      "eval_loss": 4.196361064910889,
      "eval_runtime": 2181.3068,
      "eval_samples_per_second": 12.992,
      "eval_steps_per_second": 6.496,
      "step": 1
    },
    {
      "epoch": 4.4571887025123685e-05,
      "grad_norm": 5.534646511077881,
      "learning_rate": 6e-05,
      "loss": 16.8096,
      "step": 3
    },
    {
      "epoch": 7.428647837520615e-05,
      "eval_loss": 4.047337532043457,
      "eval_runtime": 2185.3691,
      "eval_samples_per_second": 12.968,
      "eval_steps_per_second": 6.484,
      "step": 5
    },
    {
      "epoch": 8.914377405024737e-05,
      "grad_norm": 4.0268330574035645,
      "learning_rate": 0.00012,
      "loss": 16.3914,
      "step": 6
    },
    {
      "epoch": 0.00013371566107537106,
      "grad_norm": 2.374159812927246,
      "learning_rate": 0.00018,
      "loss": 15.7503,
      "step": 9
    },
    {
      "epoch": 0.0001485729567504123,
      "eval_loss": 3.818822145462036,
      "eval_runtime": 2186.0509,
      "eval_samples_per_second": 12.964,
      "eval_steps_per_second": 6.482,
      "step": 10
    },
    {
      "epoch": 0.00017828754810049474,
      "grad_norm": 3.9854671955108643,
      "learning_rate": 0.00019510565162951537,
      "loss": 15.3687,
      "step": 12
    },
    {
      "epoch": 0.00022285943512561843,
      "grad_norm": 2.397183656692505,
      "learning_rate": 0.00017071067811865476,
      "loss": 15.2833,
      "step": 15
    },
    {
      "epoch": 0.00022285943512561843,
      "eval_loss": 3.755824565887451,
      "eval_runtime": 2187.7125,
      "eval_samples_per_second": 12.954,
      "eval_steps_per_second": 6.477,
      "step": 15
    },
    {
      "epoch": 0.0002674313221507421,
      "grad_norm": 3.5765700340270996,
      "learning_rate": 0.00013090169943749476,
      "loss": 15.0293,
      "step": 18
    },
    {
      "epoch": 0.0002971459135008246,
      "eval_loss": 3.7156450748443604,
      "eval_runtime": 2186.844,
      "eval_samples_per_second": 12.959,
      "eval_steps_per_second": 6.48,
      "step": 20
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6616264294268928.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}