{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00012304421224634436,
  "eval_steps": 500,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2e-05,
      "loss": 1.3413,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 4e-05,
      "loss": 2.5983,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 6e-05,
      "loss": 1.5431,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 8e-05,
      "loss": 1.7992,
      "step": 4
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001,
      "loss": 1.2091,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00012,
      "loss": 2.7719,
      "step": 6
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00012,
      "loss": 3.317,
      "step": 7
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00014,
      "loss": 1.1447,
      "step": 8
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00016,
      "loss": 1.4177,
      "step": 9
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00018,
      "loss": 1.851,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 1.9526,
      "step": 11
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00019781476007338058,
      "loss": 1.7479,
      "step": 12
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001913545457642601,
      "loss": 1.3683,
      "step": 13
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.527,
      "step": 14
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00016691306063588583,
      "loss": 2.01,
      "step": 15
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.2848,
      "step": 16
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.2189,
      "step": 17
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00011045284632676536,
      "loss": 1.4882,
      "step": 18
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.5045,
      "step": 19
    },
    {
      "epoch": 0.0,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.454,
      "step": 20
    },
    {
      "epoch": 0.0,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.2887,
      "step": 21
    },
    {
      "epoch": 0.0,
      "learning_rate": 3.308693936411421e-05,
      "loss": 0.8272,
      "step": 22
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 1.6697,
      "step": 23
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.645454235739903e-06,
      "loss": 1.6019,
      "step": 24
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 1.0745,
      "step": 25
    },
    {
      "epoch": 0.0,
      "eval_loss": NaN,
      "eval_runtime": 4150.2492,
      "eval_samples_per_second": 11.575,
      "eval_steps_per_second": 11.575,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 183123718963200.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}