{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 8915,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 1.905051827430725,
      "learning_rate": 4e-05,
      "loss": 1.3911,
      "step": 1783
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.6610555052757263,
      "eval_rouge1": 0.4074,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.4062,
      "eval_rougeLsum": 0.4066,
      "eval_runtime": 114.1926,
      "eval_samples_per_second": 6.559,
      "eval_steps_per_second": 0.21,
      "step": 1783
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.241516351699829,
      "learning_rate": 3e-05,
      "loss": 0.8526,
      "step": 3566
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.6166712045669556,
      "eval_rouge1": 0.5108,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.515,
      "eval_rougeLsum": 0.51,
      "eval_runtime": 113.6094,
      "eval_samples_per_second": 6.593,
      "eval_steps_per_second": 0.211,
      "step": 3566
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.1109647750854492,
      "learning_rate": 2e-05,
      "loss": 0.7928,
      "step": 5349
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.5968391299247742,
      "eval_rouge1": 0.4966,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.5042,
      "eval_rougeLsum": 0.4969,
      "eval_runtime": 114.0147,
      "eval_samples_per_second": 6.569,
      "eval_steps_per_second": 0.21,
      "step": 5349
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.4407908916473389,
      "learning_rate": 1e-05,
      "loss": 0.7651,
      "step": 7132
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.5860394835472107,
      "eval_rouge1": 0.5171,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.5228,
      "eval_rougeLsum": 0.5173,
      "eval_runtime": 114.1886,
      "eval_samples_per_second": 6.559,
      "eval_steps_per_second": 0.21,
      "step": 7132
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.6015982627868652,
      "learning_rate": 0.0,
      "loss": 0.7528,
      "step": 8915
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.5838220119476318,
      "eval_rouge1": 0.5174,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.523,
      "eval_rougeLsum": 0.5165,
      "eval_runtime": 113.9414,
      "eval_samples_per_second": 6.574,
      "eval_steps_per_second": 0.211,
      "step": 8915
    },
    {
      "epoch": 5.0,
      "step": 8915,
      "total_flos": 7.466029945887744e+16,
      "train_loss": 0.9108704058293606,
      "train_runtime": 5154.4687,
      "train_samples_per_second": 13.836,
      "train_steps_per_second": 1.73
    }
  ],
  "logging_steps": 500,
  "max_steps": 8915,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 7.466029945887744e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}