{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3973509933774834,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013245033112582781,
      "eval_loss": 11.936422348022461,
      "eval_runtime": 0.2005,
      "eval_samples_per_second": 159.612,
      "eval_steps_per_second": 79.806,
      "step": 1
    },
    {
      "epoch": 0.039735099337748346,
      "grad_norm": 0.1323738545179367,
      "learning_rate": 6e-05,
      "loss": 11.9332,
      "step": 3
    },
    {
      "epoch": 0.07947019867549669,
      "grad_norm": 0.12155948579311371,
      "learning_rate": 0.00012,
      "loss": 11.9342,
      "step": 6
    },
    {
      "epoch": 0.10596026490066225,
      "eval_loss": 11.935389518737793,
      "eval_runtime": 0.2017,
      "eval_samples_per_second": 158.681,
      "eval_steps_per_second": 79.34,
      "step": 8
    },
    {
      "epoch": 0.11920529801324503,
      "grad_norm": 0.10506781190633774,
      "learning_rate": 0.00018,
      "loss": 11.9332,
      "step": 9
    },
    {
      "epoch": 0.15894039735099338,
      "grad_norm": 0.08760907500982285,
      "learning_rate": 0.00019510565162951537,
      "loss": 11.934,
      "step": 12
    },
    {
      "epoch": 0.1986754966887417,
      "grad_norm": 0.12427657097578049,
      "learning_rate": 0.00017071067811865476,
      "loss": 11.931,
      "step": 15
    },
    {
      "epoch": 0.2119205298013245,
      "eval_loss": 11.93264389038086,
      "eval_runtime": 0.2144,
      "eval_samples_per_second": 149.221,
      "eval_steps_per_second": 74.611,
      "step": 16
    },
    {
      "epoch": 0.23841059602649006,
      "grad_norm": 0.11470351368188858,
      "learning_rate": 0.00013090169943749476,
      "loss": 11.9316,
      "step": 18
    },
    {
      "epoch": 0.2781456953642384,
      "grad_norm": 0.11147727817296982,
      "learning_rate": 8.435655349597689e-05,
      "loss": 11.9301,
      "step": 21
    },
    {
      "epoch": 0.31788079470198677,
      "grad_norm": 0.11154735833406448,
      "learning_rate": 4.12214747707527e-05,
      "loss": 11.9326,
      "step": 24
    },
    {
      "epoch": 0.31788079470198677,
      "eval_loss": 11.930855751037598,
      "eval_runtime": 0.2067,
      "eval_samples_per_second": 154.781,
      "eval_steps_per_second": 77.39,
      "step": 24
    },
    {
      "epoch": 0.3576158940397351,
      "grad_norm": 0.1380121409893036,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 11.927,
      "step": 27
    },
    {
      "epoch": 0.3973509933774834,
      "grad_norm": 0.11876049637794495,
      "learning_rate": 0.0,
      "loss": 11.9312,
      "step": 30
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 11242045440.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}