{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.25806451612903225,
  "eval_steps": 1000,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 2.5e-08,
      "loss": 0.7748,
      "step": 25
    },
    {
      "epoch": 0.01,
      "learning_rate": 5e-08,
      "loss": 1.2926,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 7.5e-08,
      "loss": 0.7723,
      "step": 75
    },
    {
      "epoch": 0.03,
      "learning_rate": 1e-07,
      "loss": 1.3901,
      "step": 100
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.25e-07,
      "loss": 0.7494,
      "step": 125
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.5e-07,
      "loss": 1.1551,
      "step": 150
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.75e-07,
      "loss": 0.5737,
      "step": 175
    },
    {
      "epoch": 0.05,
      "learning_rate": 2e-07,
      "loss": 0.7115,
      "step": 200
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.25e-07,
      "loss": 0.2719,
      "step": 225
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.5e-07,
      "loss": 0.4535,
      "step": 250
    },
    {
      "epoch": 0.07,
      "learning_rate": 2.75e-07,
      "loss": 0.2216,
      "step": 275
    },
    {
      "epoch": 0.08,
      "learning_rate": 3e-07,
      "loss": 0.3218,
      "step": 300
    },
    {
      "epoch": 0.08,
      "learning_rate": 3.25e-07,
      "loss": 0.1867,
      "step": 325
    },
    {
      "epoch": 0.09,
      "learning_rate": 3.5e-07,
      "loss": 0.34,
      "step": 350
    },
    {
      "epoch": 0.1,
      "learning_rate": 3.75e-07,
      "loss": 0.1971,
      "step": 375
    },
    {
      "epoch": 0.1,
      "learning_rate": 4e-07,
      "loss": 0.2871,
      "step": 400
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.2499999999999995e-07,
      "loss": 0.1857,
      "step": 425
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.5e-07,
      "loss": 0.247,
      "step": 450
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.7499999999999995e-07,
      "loss": 0.167,
      "step": 475
    },
    {
      "epoch": 0.13,
      "learning_rate": 5e-07,
      "loss": 0.2332,
      "step": 500
    },
    {
      "epoch": 0.14,
      "learning_rate": 5.25e-07,
      "loss": 0.1908,
      "step": 525
    },
    {
      "epoch": 0.14,
      "learning_rate": 5.5e-07,
      "loss": 0.2329,
      "step": 550
    },
    {
      "epoch": 0.15,
      "learning_rate": 5.749999999999999e-07,
      "loss": 0.1589,
      "step": 575
    },
    {
      "epoch": 0.15,
      "learning_rate": 6e-07,
      "loss": 0.2232,
      "step": 600
    },
    {
      "epoch": 0.16,
      "learning_rate": 6.249999999999999e-07,
      "loss": 0.166,
      "step": 625
    },
    {
      "epoch": 0.17,
      "learning_rate": 6.5e-07,
      "loss": 0.2115,
      "step": 650
    },
    {
      "epoch": 0.17,
      "learning_rate": 6.75e-07,
      "loss": 0.1378,
      "step": 675
    },
    {
      "epoch": 0.18,
      "learning_rate": 7e-07,
      "loss": 0.1946,
      "step": 700
    },
    {
      "epoch": 0.19,
      "learning_rate": 7.249999999999999e-07,
      "loss": 0.1553,
      "step": 725
    },
    {
      "epoch": 0.19,
      "learning_rate": 7.5e-07,
      "loss": 0.2011,
      "step": 750
    },
    {
      "epoch": 0.2,
      "learning_rate": 7.75e-07,
      "loss": 0.1491,
      "step": 775
    },
    {
      "epoch": 0.21,
      "learning_rate": 8e-07,
      "loss": 0.1517,
      "step": 800
    },
    {
      "epoch": 0.21,
      "learning_rate": 8.249999999999999e-07,
      "loss": 0.1266,
      "step": 825
    },
    {
      "epoch": 0.22,
      "learning_rate": 8.499999999999999e-07,
      "loss": 0.1926,
      "step": 850
    },
    {
      "epoch": 0.23,
      "learning_rate": 8.75e-07,
      "loss": 0.1404,
      "step": 875
    },
    {
      "epoch": 0.23,
      "learning_rate": 9e-07,
      "loss": 0.1729,
      "step": 900
    },
    {
      "epoch": 0.24,
      "learning_rate": 9.25e-07,
      "loss": 0.137,
      "step": 925
    },
    {
      "epoch": 0.25,
      "learning_rate": 9.499999999999999e-07,
      "loss": 0.1753,
      "step": 950
    },
    {
      "epoch": 0.25,
      "learning_rate": 9.75e-07,
      "loss": 0.1408,
      "step": 975
    },
    {
      "epoch": 0.26,
      "learning_rate": 1e-06,
      "loss": 0.1819,
      "step": 1000
    },
    {
      "epoch": 0.26,
      "eval_loss": 0.14837130904197693,
      "eval_runtime": 179172.9142,
      "eval_samples_per_second": 0.052,
      "eval_steps_per_second": 0.007,
      "eval_wer": 0.10759534583063995,
      "step": 1000
    }
  ],
  "logging_steps": 25,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 1000,
  "total_flos": 2.717998645248e+19,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}