{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.21164021164021163,
  "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": 1.25e-08,
      "loss": 0.5815,
      "step": 25
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.5e-08,
      "loss": 0.9607,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.75e-08,
      "loss": 0.5678,
      "step": 75
    },
    {
      "epoch": 0.02,
      "learning_rate": 5e-08,
      "loss": 0.9329,
      "step": 100
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.25e-08,
      "loss": 0.5937,
      "step": 125
    },
    {
      "epoch": 0.03,
      "learning_rate": 7.5e-08,
      "loss": 0.9153,
      "step": 150
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.75e-08,
      "loss": 0.5232,
      "step": 175
    },
    {
      "epoch": 0.04,
      "learning_rate": 1e-07,
      "loss": 0.8711,
      "step": 200
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.125e-07,
      "loss": 0.4636,
      "step": 225
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.25e-07,
      "loss": 0.6875,
      "step": 250
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.375e-07,
      "loss": 0.3447,
      "step": 275
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.5e-07,
      "loss": 0.4347,
      "step": 300
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.625e-07,
      "loss": 0.2261,
      "step": 325
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.75e-07,
      "loss": 0.3323,
      "step": 350
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.875e-07,
      "loss": 0.2093,
      "step": 375
    },
    {
      "epoch": 0.08,
      "learning_rate": 2e-07,
      "loss": 0.2357,
      "step": 400
    },
    {
      "epoch": 0.09,
      "learning_rate": 2.1249999999999998e-07,
      "loss": 0.1632,
      "step": 425
    },
    {
      "epoch": 0.1,
      "learning_rate": 2.25e-07,
      "loss": 0.2114,
      "step": 450
    },
    {
      "epoch": 0.1,
      "learning_rate": 2.3749999999999998e-07,
      "loss": 0.1587,
      "step": 475
    },
    {
      "epoch": 0.11,
      "learning_rate": 2.5e-07,
      "loss": 0.2634,
      "step": 500
    },
    {
      "epoch": 0.11,
      "learning_rate": 2.625e-07,
      "loss": 0.1897,
      "step": 525
    },
    {
      "epoch": 0.12,
      "learning_rate": 2.75e-07,
      "loss": 0.2373,
      "step": 550
    },
    {
      "epoch": 0.12,
      "learning_rate": 2.8749999999999995e-07,
      "loss": 0.1154,
      "step": 575
    },
    {
      "epoch": 0.13,
      "learning_rate": 3e-07,
      "loss": 0.1733,
      "step": 600
    },
    {
      "epoch": 0.13,
      "learning_rate": 3.1249999999999997e-07,
      "loss": 0.1558,
      "step": 625
    },
    {
      "epoch": 0.14,
      "learning_rate": 3.25e-07,
      "loss": 0.2124,
      "step": 650
    },
    {
      "epoch": 0.14,
      "learning_rate": 3.375e-07,
      "loss": 0.1478,
      "step": 675
    },
    {
      "epoch": 0.15,
      "learning_rate": 3.5e-07,
      "loss": 0.1925,
      "step": 700
    },
    {
      "epoch": 0.15,
      "learning_rate": 3.6249999999999997e-07,
      "loss": 0.1349,
      "step": 725
    },
    {
      "epoch": 0.16,
      "learning_rate": 3.75e-07,
      "loss": 0.2101,
      "step": 750
    },
    {
      "epoch": 0.16,
      "learning_rate": 3.875e-07,
      "loss": 0.1556,
      "step": 775
    },
    {
      "epoch": 0.17,
      "learning_rate": 4e-07,
      "loss": 0.1572,
      "step": 800
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.1249999999999997e-07,
      "loss": 0.1339,
      "step": 825
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.2499999999999995e-07,
      "loss": 0.2275,
      "step": 850
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.375e-07,
      "loss": 0.1529,
      "step": 875
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.5e-07,
      "loss": 0.2102,
      "step": 900
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.625e-07,
      "loss": 0.1567,
      "step": 925
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.7499999999999995e-07,
      "loss": 0.2087,
      "step": 950
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.875e-07,
      "loss": 0.1155,
      "step": 975
    },
    {
      "epoch": 0.21,
      "learning_rate": 5e-07,
      "loss": 0.163,
      "step": 1000
    },
    {
      "epoch": 0.21,
      "eval_loss": 0.13766534626483917,
      "eval_runtime": 257216.5334,
      "eval_samples_per_second": 0.037,
      "eval_steps_per_second": 0.005,
      "eval_wer": 0.0962566844919786,
      "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
}