{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 799.8,
  "global_step": 1600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 49.8,
      "learning_rate": 5.5799999999999994e-05,
      "loss": 42.4143,
      "step": 100
    },
    {
      "epoch": 49.8,
      "eval_loss": 21.511550903320312,
      "eval_runtime": 22.3742,
      "eval_samples_per_second": 2.413,
      "eval_steps_per_second": 0.313,
      "eval_wer": 1.0,
      "step": 100
    },
    {
      "epoch": 99.8,
      "learning_rate": 0.0001158,
      "loss": 5.9884,
      "step": 200
    },
    {
      "epoch": 99.8,
      "eval_loss": 31.79755401611328,
      "eval_runtime": 0.9499,
      "eval_samples_per_second": 56.846,
      "eval_steps_per_second": 7.369,
      "eval_wer": 1.0,
      "step": 200
    },
    {
      "epoch": 149.8,
      "learning_rate": 0.00017579999999999996,
      "loss": 4.0043,
      "step": 300
    },
    {
      "epoch": 149.8,
      "eval_loss": 3.482863187789917,
      "eval_runtime": 0.9439,
      "eval_samples_per_second": 57.208,
      "eval_steps_per_second": 7.416,
      "eval_wer": 1.0,
      "step": 300
    },
    {
      "epoch": 199.8,
      "learning_rate": 0.00023579999999999999,
      "loss": 3.653,
      "step": 400
    },
    {
      "epoch": 199.8,
      "eval_loss": 3.6417062282562256,
      "eval_runtime": 0.9393,
      "eval_samples_per_second": 57.489,
      "eval_steps_per_second": 7.452,
      "eval_wer": 1.0,
      "step": 400
    },
    {
      "epoch": 249.8,
      "learning_rate": 0.0002958,
      "loss": 3.5207,
      "step": 500
    },
    {
      "epoch": 249.8,
      "eval_loss": 3.508103370666504,
      "eval_runtime": 0.9443,
      "eval_samples_per_second": 57.187,
      "eval_steps_per_second": 7.413,
      "eval_wer": 1.0,
      "step": 500
    },
    {
      "epoch": 299.8,
      "learning_rate": 0.0002746363636363636,
      "loss": 3.63,
      "step": 600
    },
    {
      "epoch": 299.8,
      "eval_loss": 3.4835526943206787,
      "eval_runtime": 0.943,
      "eval_samples_per_second": 57.264,
      "eval_steps_per_second": 7.423,
      "eval_wer": 1.0,
      "step": 600
    },
    {
      "epoch": 349.8,
      "learning_rate": 0.00024736363636363633,
      "loss": 3.648,
      "step": 700
    },
    {
      "epoch": 349.8,
      "eval_loss": 3.4515135288238525,
      "eval_runtime": 0.9803,
      "eval_samples_per_second": 55.084,
      "eval_steps_per_second": 7.141,
      "eval_wer": 1.0,
      "step": 700
    },
    {
      "epoch": 399.8,
      "learning_rate": 0.00022009090909090907,
      "loss": 3.6448,
      "step": 800
    },
    {
      "epoch": 399.8,
      "eval_loss": 3.4646780490875244,
      "eval_runtime": 0.9384,
      "eval_samples_per_second": 57.547,
      "eval_steps_per_second": 7.46,
      "eval_wer": 1.0,
      "step": 800
    },
    {
      "epoch": 449.8,
      "learning_rate": 0.0001928181818181818,
      "loss": 3.6872,
      "step": 900
    },
    {
      "epoch": 449.8,
      "eval_loss": 3.4371423721313477,
      "eval_runtime": 0.938,
      "eval_samples_per_second": 57.568,
      "eval_steps_per_second": 7.463,
      "eval_wer": 1.0,
      "step": 900
    },
    {
      "epoch": 499.8,
      "learning_rate": 0.0001655454545454545,
      "loss": 3.6892,
      "step": 1000
    },
    {
      "epoch": 499.8,
      "eval_loss": 3.4336819648742676,
      "eval_runtime": 0.9476,
      "eval_samples_per_second": 56.988,
      "eval_steps_per_second": 7.387,
      "eval_wer": 1.0,
      "step": 1000
    },
    {
      "epoch": 549.8,
      "learning_rate": 0.00013827272727272728,
      "loss": 3.684,
      "step": 1100
    },
    {
      "epoch": 549.8,
      "eval_loss": 3.437472343444824,
      "eval_runtime": 0.94,
      "eval_samples_per_second": 57.449,
      "eval_steps_per_second": 7.447,
      "eval_wer": 1.0,
      "step": 1100
    },
    {
      "epoch": 599.8,
      "learning_rate": 0.00011099999999999999,
      "loss": 3.6843,
      "step": 1200
    },
    {
      "epoch": 599.8,
      "eval_loss": 3.4452097415924072,
      "eval_runtime": 0.9463,
      "eval_samples_per_second": 57.067,
      "eval_steps_per_second": 7.398,
      "eval_wer": 1.0,
      "step": 1200
    },
    {
      "epoch": 649.8,
      "learning_rate": 8.372727272727272e-05,
      "loss": 3.6842,
      "step": 1300
    },
    {
      "epoch": 649.8,
      "eval_loss": 3.441551446914673,
      "eval_runtime": 0.9462,
      "eval_samples_per_second": 57.068,
      "eval_steps_per_second": 7.398,
      "eval_wer": 1.0,
      "step": 1300
    },
    {
      "epoch": 699.8,
      "learning_rate": 5.645454545454545e-05,
      "loss": 3.6819,
      "step": 1400
    },
    {
      "epoch": 699.8,
      "eval_loss": 3.4498231410980225,
      "eval_runtime": 0.9402,
      "eval_samples_per_second": 57.435,
      "eval_steps_per_second": 7.445,
      "eval_wer": 1.0,
      "step": 1400
    },
    {
      "epoch": 749.8,
      "learning_rate": 2.918181818181818e-05,
      "loss": 3.6832,
      "step": 1500
    },
    {
      "epoch": 749.8,
      "eval_loss": 3.4524271488189697,
      "eval_runtime": 0.9511,
      "eval_samples_per_second": 56.778,
      "eval_steps_per_second": 7.36,
      "eval_wer": 1.0,
      "step": 1500
    },
    {
      "epoch": 799.8,
      "learning_rate": 1.909090909090909e-06,
      "loss": 3.6828,
      "step": 1600
    },
    {
      "epoch": 799.8,
      "eval_loss": 3.4495346546173096,
      "eval_runtime": 0.9541,
      "eval_samples_per_second": 56.598,
      "eval_steps_per_second": 7.337,
      "eval_wer": 1.0,
      "step": 1600
    }
  ],
  "max_steps": 1600,
  "num_train_epochs": 800,
  "total_flos": 1.8719390163492864e+18,
  "trial_name": null,
  "trial_params": null
}