{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.4492753623188406,
  "eval_steps": 100,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.48,
      "grad_norm": 0.33149510622024536,
      "learning_rate": 0.00018810000000000002,
      "loss": 3.162,
      "step": 100
    },
    {
      "epoch": 0.48,
      "eval_loss": 2.6494271755218506,
      "eval_runtime": 61.8673,
      "eval_samples_per_second": 13.125,
      "eval_steps_per_second": 1.649,
      "eval_wer": 1.0,
      "step": 100
    },
    {
      "epoch": 0.97,
      "grad_norm": NaN,
      "learning_rate": 0.00037620000000000004,
      "loss": 2.8381,
      "step": 200
    },
    {
      "epoch": 0.97,
      "eval_loss": 2.6534550189971924,
      "eval_runtime": 62.5126,
      "eval_samples_per_second": 12.989,
      "eval_steps_per_second": 1.632,
      "eval_wer": 1.0,
      "step": 200
    },
    {
      "epoch": 1.45,
      "grad_norm": 2.830345392227173,
      "learning_rate": 0.0005643,
      "loss": 2.7335,
      "step": 300
    },
    {
      "epoch": 1.45,
      "eval_loss": 2.6320128440856934,
      "eval_runtime": 61.8571,
      "eval_samples_per_second": 13.127,
      "eval_steps_per_second": 1.649,
      "eval_wer": 1.0,
      "step": 300
    }
  ],
  "logging_steps": 100,
  "max_steps": 6210,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 30,
  "save_steps": 100,
  "total_flos": 6.074148194971436e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}