{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0013417715857503858,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.472571952501286e-05,
      "eval_loss": 2.629952907562256,
      "eval_runtime": 1209.655,
      "eval_samples_per_second": 7.783,
      "eval_steps_per_second": 3.892,
      "step": 1
    },
    {
      "epoch": 0.00013417715857503857,
      "grad_norm": 3.2652931213378906,
      "learning_rate": 6e-05,
      "loss": 2.3093,
      "step": 3
    },
    {
      "epoch": 0.00026835431715007714,
      "grad_norm": 3.7356064319610596,
      "learning_rate": 0.00012,
      "loss": 2.0523,
      "step": 6
    },
    {
      "epoch": 0.00035780575620010286,
      "eval_loss": 1.4996869564056396,
      "eval_runtime": 1214.5936,
      "eval_samples_per_second": 7.752,
      "eval_steps_per_second": 3.876,
      "step": 8
    },
    {
      "epoch": 0.00040253147572511574,
      "grad_norm": 3.593679189682007,
      "learning_rate": 0.00018,
      "loss": 1.637,
      "step": 9
    },
    {
      "epoch": 0.0005367086343001543,
      "grad_norm": 3.111470937728882,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.3384,
      "step": 12
    },
    {
      "epoch": 0.0006708857928751929,
      "grad_norm": 2.3601317405700684,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.1994,
      "step": 15
    },
    {
      "epoch": 0.0007156115124002057,
      "eval_loss": 1.271549940109253,
      "eval_runtime": 1213.4516,
      "eval_samples_per_second": 7.759,
      "eval_steps_per_second": 3.88,
      "step": 16
    },
    {
      "epoch": 0.0008050629514502315,
      "grad_norm": 3.759420156478882,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.1576,
      "step": 18
    },
    {
      "epoch": 0.0009392401100252701,
      "grad_norm": 3.0076560974121094,
      "learning_rate": 8.435655349597689e-05,
      "loss": 1.014,
      "step": 21
    },
    {
      "epoch": 0.0010734172686003086,
      "grad_norm": 2.5883312225341797,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.9327,
      "step": 24
    },
    {
      "epoch": 0.0010734172686003086,
      "eval_loss": 1.1616003513336182,
      "eval_runtime": 1213.2642,
      "eval_samples_per_second": 7.76,
      "eval_steps_per_second": 3.88,
      "step": 24
    },
    {
      "epoch": 0.0012075944271753472,
      "grad_norm": 2.797869920730591,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 1.2156,
      "step": 27
    },
    {
      "epoch": 0.0013417715857503858,
      "grad_norm": 2.5307955741882324,
      "learning_rate": 0.0,
      "loss": 1.1796,
      "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": 1.112830925340672e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}