{
  "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": 2.067873001098633,
      "learning_rate": 4e-05,
      "loss": 1.3917,
      "step": 1783
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.6615284085273743,
      "eval_rouge1": 0.5471,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.5464,
      "eval_rougeLsum": 0.5441,
      "eval_runtime": 113.2569,
      "eval_samples_per_second": 6.622,
      "eval_steps_per_second": 0.212,
      "step": 1783
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.6221102476119995,
      "learning_rate": 3e-05,
      "loss": 0.854,
      "step": 3566
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.6180859208106995,
      "eval_rouge1": 0.4511,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.4501,
      "eval_rougeLsum": 0.4463,
      "eval_runtime": 112.5406,
      "eval_samples_per_second": 6.664,
      "eval_steps_per_second": 0.213,
      "step": 3566
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.800586462020874,
      "learning_rate": 2e-05,
      "loss": 0.7905,
      "step": 5349
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.5925126671791077,
      "eval_rouge1": 0.421,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.4197,
      "eval_rougeLsum": 0.4168,
      "eval_runtime": 112.6751,
      "eval_samples_per_second": 6.656,
      "eval_steps_per_second": 0.213,
      "step": 5349
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.7010269165039062,
      "learning_rate": 1e-05,
      "loss": 0.7624,
      "step": 7132
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.5808362364768982,
      "eval_rouge1": 0.438,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.4378,
      "eval_rougeLsum": 0.433,
      "eval_runtime": 112.7701,
      "eval_samples_per_second": 6.651,
      "eval_steps_per_second": 0.213,
      "step": 7132
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.4592366218566895,
      "learning_rate": 0.0,
      "loss": 0.751,
      "step": 8915
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 1.0,
      "eval_loss": 0.5829301476478577,
      "eval_rouge1": 0.4334,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.4324,
      "eval_rougeLsum": 0.4298,
      "eval_runtime": 112.6735,
      "eval_samples_per_second": 6.656,
      "eval_steps_per_second": 0.213,
      "step": 8915
    },
    {
      "epoch": 5.0,
      "step": 8915,
      "total_flos": 7.546206748253184e+16,
      "train_loss": 0.9099474502024327,
      "train_runtime": 5183.9644,
      "train_samples_per_second": 13.756,
      "train_steps_per_second": 1.72
    }
  ],
  "logging_steps": 500,
  "max_steps": 8915,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 7.546206748253184e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}