{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 3770,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_gen_len": 114.58,
      "eval_loss": 2.4033706188201904,
      "eval_rouge1": 0.3258037600187694,
      "eval_rouge2": 0.08003474229428373,
      "eval_rougeL": 0.20739237956049256,
      "eval_rougeLsum": 0.2230784420688168,
      "eval_runtime": 989.0997,
      "eval_samples_per_second": 1.011,
      "eval_steps_per_second": 0.064,
      "step": 377
    },
    {
      "epoch": 1.3262599469496021,
      "grad_norm": 3.424102306365967,
      "learning_rate": 2.8726803935335058e-06,
      "loss": 2.5193,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_gen_len": 113.452,
      "eval_loss": 2.340730905532837,
      "eval_rouge1": 0.32476949134280386,
      "eval_rouge2": 0.07874634827290394,
      "eval_rougeL": 0.21000147880278136,
      "eval_rougeLsum": 0.22603538175456714,
      "eval_runtime": 997.6459,
      "eval_samples_per_second": 1.002,
      "eval_steps_per_second": 0.063,
      "step": 754
    },
    {
      "epoch": 2.6525198938992043,
      "grad_norm": 3.1680996417999268,
      "learning_rate": 2.510489126644959e-06,
      "loss": 2.3392,
      "step": 1000
    },
    {
      "epoch": 3.0,
      "eval_gen_len": 112.564,
      "eval_loss": 2.3039560317993164,
      "eval_rouge1": 0.32059271290891156,
      "eval_rouge2": 0.07500377265811553,
      "eval_rougeL": 0.20560349340841416,
      "eval_rougeLsum": 0.21866034362863596,
      "eval_runtime": 1134.6335,
      "eval_samples_per_second": 0.881,
      "eval_steps_per_second": 0.056,
      "step": 1131
    },
    {
      "epoch": 3.9787798408488064,
      "grad_norm": 3.4218506813049316,
      "learning_rate": 1.976582554006042e-06,
      "loss": 2.2626,
      "step": 1500
    },
    {
      "epoch": 4.0,
      "eval_gen_len": 113.102,
      "eval_loss": 2.2713050842285156,
      "eval_rouge1": 0.3188878832812406,
      "eval_rouge2": 0.07552561950583175,
      "eval_rougeL": 0.20580794751959977,
      "eval_rougeLsum": 0.21840355661823818,
      "eval_runtime": 1342.8107,
      "eval_samples_per_second": 0.745,
      "eval_steps_per_second": 0.047,
      "step": 1508
    },
    {
      "epoch": 5.0,
      "eval_gen_len": 108.076,
      "eval_loss": 2.2622933387756348,
      "eval_rouge1": 0.3220955459492587,
      "eval_rouge2": 0.07576255906806914,
      "eval_rougeL": 0.2069475588748002,
      "eval_rougeLsum": 0.21979050526677296,
      "eval_runtime": 1537.4132,
      "eval_samples_per_second": 0.65,
      "eval_steps_per_second": 0.041,
      "step": 1885
    },
    {
      "epoch": 5.305039787798409,
      "grad_norm": 3.1164140701293945,
      "learning_rate": 1.3602064545876772e-06,
      "loss": 2.209,
      "step": 2000
    },
    {
      "epoch": 6.0,
      "eval_gen_len": 111.277,
      "eval_loss": 2.247816801071167,
      "eval_rouge1": 0.31907757245587076,
      "eval_rouge2": 0.07415047575742183,
      "eval_rougeL": 0.20518250100183638,
      "eval_rougeLsum": 0.21723476148216042,
      "eval_runtime": 1624.5789,
      "eval_samples_per_second": 0.616,
      "eval_steps_per_second": 0.039,
      "step": 2262
    },
    {
      "epoch": 6.63129973474801,
      "grad_norm": 3.0489401817321777,
      "learning_rate": 7.677498585764536e-07,
      "loss": 2.1706,
      "step": 2500
    },
    {
      "epoch": 7.0,
      "eval_gen_len": 108.655,
      "eval_loss": 2.2410194873809814,
      "eval_rouge1": 0.32212385903573537,
      "eval_rouge2": 0.07536919970473052,
      "eval_rougeL": 0.20648069011418652,
      "eval_rougeLsum": 0.21908203834574824,
      "eval_runtime": 1614.3024,
      "eval_samples_per_second": 0.619,
      "eval_steps_per_second": 0.039,
      "step": 2639
    },
    {
      "epoch": 7.957559681697613,
      "grad_norm": 3.88566517829895,
      "learning_rate": 3.005855977799911e-07,
      "loss": 2.1506,
      "step": 3000
    },
    {
      "epoch": 8.0,
      "eval_gen_len": 108.303,
      "eval_loss": 2.2375478744506836,
      "eval_rouge1": 0.32285486927261353,
      "eval_rouge2": 0.0742826049179253,
      "eval_rougeL": 0.20526480763464744,
      "eval_rougeLsum": 0.21783648885941626,
      "eval_runtime": 1614.4824,
      "eval_samples_per_second": 0.619,
      "eval_steps_per_second": 0.039,
      "step": 3016
    },
    {
      "epoch": 9.0,
      "eval_gen_len": 108.217,
      "eval_loss": 2.236407995223999,
      "eval_rouge1": 0.32342426871285435,
      "eval_rouge2": 0.0748472633333527,
      "eval_rougeL": 0.20594698388820035,
      "eval_rougeLsum": 0.21901668088377402,
      "eval_runtime": 1593.8828,
      "eval_samples_per_second": 0.627,
      "eval_steps_per_second": 0.04,
      "step": 3393
    },
    {
      "epoch": 9.283819628647215,
      "grad_norm": 3.319697141647339,
      "learning_rate": 3.89306660307448e-08,
      "loss": 2.1426,
      "step": 3500
    },
    {
      "epoch": 10.0,
      "eval_gen_len": 108.113,
      "eval_loss": 2.2360377311706543,
      "eval_rouge1": 0.3225991249221293,
      "eval_rouge2": 0.07423068760947925,
      "eval_rougeL": 0.20558156696804017,
      "eval_rougeLsum": 0.21800338685798093,
      "eval_runtime": 1476.193,
      "eval_samples_per_second": 0.677,
      "eval_steps_per_second": 0.043,
      "step": 3770
    }
  ],
  "logging_steps": 500,
  "max_steps": 3770,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4448339676299264e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}