{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.11406844106463879,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0038022813688212928,
      "eval_loss": 11.936347007751465,
      "eval_runtime": 0.9627,
      "eval_samples_per_second": 115.295,
      "eval_steps_per_second": 58.167,
      "step": 1
    },
    {
      "epoch": 0.011406844106463879,
      "grad_norm": 0.09513615071773529,
      "learning_rate": 6e-05,
      "loss": 11.933,
      "step": 3
    },
    {
      "epoch": 0.022813688212927757,
      "grad_norm": 0.0826341062784195,
      "learning_rate": 0.00012,
      "loss": 11.9352,
      "step": 6
    },
    {
      "epoch": 0.030418250950570342,
      "eval_loss": 11.935516357421875,
      "eval_runtime": 0.9429,
      "eval_samples_per_second": 117.723,
      "eval_steps_per_second": 59.392,
      "step": 8
    },
    {
      "epoch": 0.034220532319391636,
      "grad_norm": 0.07712804526090622,
      "learning_rate": 0.00018,
      "loss": 11.93,
      "step": 9
    },
    {
      "epoch": 0.045627376425855515,
      "grad_norm": 0.08069154620170593,
      "learning_rate": 0.00019510565162951537,
      "loss": 11.9328,
      "step": 12
    },
    {
      "epoch": 0.057034220532319393,
      "grad_norm": 0.08474593609571457,
      "learning_rate": 0.00017071067811865476,
      "loss": 11.9296,
      "step": 15
    },
    {
      "epoch": 0.060836501901140684,
      "eval_loss": 11.933499336242676,
      "eval_runtime": 0.9746,
      "eval_samples_per_second": 113.896,
      "eval_steps_per_second": 57.461,
      "step": 16
    },
    {
      "epoch": 0.06844106463878327,
      "grad_norm": 0.08808320760726929,
      "learning_rate": 0.00013090169943749476,
      "loss": 11.9332,
      "step": 18
    },
    {
      "epoch": 0.07984790874524715,
      "grad_norm": 0.08765470236539841,
      "learning_rate": 8.435655349597689e-05,
      "loss": 11.9328,
      "step": 21
    },
    {
      "epoch": 0.09125475285171103,
      "grad_norm": 0.08531386405229568,
      "learning_rate": 4.12214747707527e-05,
      "loss": 11.9329,
      "step": 24
    },
    {
      "epoch": 0.09125475285171103,
      "eval_loss": 11.932276725769043,
      "eval_runtime": 0.9451,
      "eval_samples_per_second": 117.442,
      "eval_steps_per_second": 59.25,
      "step": 24
    },
    {
      "epoch": 0.10266159695817491,
      "grad_norm": 0.08210892230272293,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 11.9275,
      "step": 27
    },
    {
      "epoch": 0.11406844106463879,
      "grad_norm": 0.09073318541049957,
      "learning_rate": 0.0,
      "loss": 11.9314,
      "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
}