{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 4460,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.9051845669746399,
      "learning_rate": 0.0008,
      "loss": 1.2322,
      "step": 892
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.7490009665489197,
      "eval_rouge1": 0.7095,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.7102,
      "eval_rougeLsum": 0.7047,
      "eval_runtime": 34.7466,
      "eval_samples_per_second": 21.498,
      "eval_steps_per_second": 0.691,
      "step": 892
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.6380248069763184,
      "learning_rate": 0.0006,
      "loss": 0.6879,
      "step": 1784
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.6347340941429138,
      "eval_rouge1": 0.7342,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.7339,
      "eval_rougeLsum": 0.7326,
      "eval_runtime": 35.8554,
      "eval_samples_per_second": 20.834,
      "eval_steps_per_second": 0.669,
      "step": 1784
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.7358594536781311,
      "learning_rate": 0.0004,
      "loss": 0.4916,
      "step": 2676
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.6006747484207153,
      "eval_rouge1": 0.7021,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.7036,
      "eval_rougeLsum": 0.7024,
      "eval_runtime": 35.3096,
      "eval_samples_per_second": 21.156,
      "eval_steps_per_second": 0.68,
      "step": 2676
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.6418809294700623,
      "learning_rate": 0.0002,
      "loss": 0.3445,
      "step": 3568
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.626953661441803,
      "eval_rouge1": 0.7205,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.7213,
      "eval_rougeLsum": 0.7183,
      "eval_runtime": 34.5923,
      "eval_samples_per_second": 21.594,
      "eval_steps_per_second": 0.694,
      "step": 3568
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.6559532284736633,
      "learning_rate": 0.0,
      "loss": 0.2065,
      "step": 4460
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.6843562126159668,
      "eval_rouge1": 0.7295,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.7315,
      "eval_rougeLsum": 0.7272,
      "eval_runtime": 35.1124,
      "eval_samples_per_second": 21.275,
      "eval_steps_per_second": 0.684,
      "step": 4460
    },
    {
      "epoch": 5.0,
      "step": 4460,
      "total_flos": 4.884374195011584e+16,
      "train_loss": 0.5925334092212899,
      "train_runtime": 4323.2769,
      "train_samples_per_second": 16.499,
      "train_steps_per_second": 1.032
    }
  ],
  "logging_steps": 500,
  "max_steps": 4460,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 4.884374195011584e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}