{
  "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": 0.9311900734901428,
      "learning_rate": 0.0008,
      "loss": 3.0485,
      "step": 892
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 1.0,
      "eval_loss": 2.009058713912964,
      "eval_rouge1": 0.7257,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.7217,
      "eval_rougeLsum": 0.7197,
      "eval_runtime": 52.1613,
      "eval_samples_per_second": 14.359,
      "eval_steps_per_second": 0.46,
      "step": 892
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.9934630393981934,
      "learning_rate": 0.0006,
      "loss": 2.4113,
      "step": 1784
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 1.0,
      "eval_loss": 1.6974738836288452,
      "eval_rouge1": 0.723,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.7191,
      "eval_rougeLsum": 0.7182,
      "eval_runtime": 51.4774,
      "eval_samples_per_second": 14.55,
      "eval_steps_per_second": 0.466,
      "step": 1784
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.2730742692947388,
      "learning_rate": 0.0004,
      "loss": 2.156,
      "step": 2676
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 1.0,
      "eval_loss": 1.5238491296768188,
      "eval_rouge1": 0.7284,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.7246,
      "eval_rougeLsum": 0.7242,
      "eval_runtime": 51.3126,
      "eval_samples_per_second": 14.597,
      "eval_steps_per_second": 0.468,
      "step": 2676
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.9294344186782837,
      "learning_rate": 0.0002,
      "loss": 1.969,
      "step": 3568
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 1.0,
      "eval_loss": 1.4055782556533813,
      "eval_rouge1": 0.6992,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.6997,
      "eval_rougeLsum": 0.6977,
      "eval_runtime": 52.4927,
      "eval_samples_per_second": 14.269,
      "eval_steps_per_second": 0.457,
      "step": 3568
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.1058984994888306,
      "learning_rate": 0.0,
      "loss": 1.8249,
      "step": 4460
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 1.0,
      "eval_loss": 1.334100365638733,
      "eval_rouge1": 0.7266,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.7247,
      "eval_rougeLsum": 0.7239,
      "eval_runtime": 52.9997,
      "eval_samples_per_second": 14.132,
      "eval_steps_per_second": 0.453,
      "step": 4460
    },
    {
      "epoch": 5.0,
      "step": 4460,
      "total_flos": 5.530684398501888e+16,
      "train_loss": 2.281923631060818,
      "train_runtime": 5654.6105,
      "train_samples_per_second": 12.612,
      "train_steps_per_second": 0.789
    }
  ],
  "logging_steps": 500,
  "max_steps": 4460,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 5.530684398501888e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}