{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.045662100456621,
  "eval_steps": 500,
  "global_step": 20,
  "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": 1.3112,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 4e-05,
      "loss": 1.8308,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 6e-05,
      "loss": 1.2929,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 8e-05,
      "loss": 1.5119,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001,
      "loss": 1.3236,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00012,
      "loss": 1.2433,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00014,
      "loss": 1.2271,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016,
      "loss": 1.1561,
      "step": 8
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00018,
      "loss": 1.3968,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 1.5378,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.3701,
      "step": 11
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.0534,
      "step": 12
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00015877852522924732,
      "loss": 1.3834,
      "step": 13
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.114,
      "step": 14
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001,
      "loss": 1.4828,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.307,
      "step": 16
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.4476,
      "step": 17
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 1.3964,
      "step": 18
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 1.3003,
      "step": 19
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0,
      "loss": 1.3201,
      "step": 20
    },
    {
      "epoch": 0.05,
      "eval_loss": 1.278823971748352,
      "eval_runtime": 2.6566,
      "eval_samples_per_second": 37.642,
      "eval_steps_per_second": 37.642,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 146498975170560.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}