{
  "best_metric": 0.000484466552734375,
  "best_model_checkpoint": "model_fewrel_1_2-task3/checkpoint-1680",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 2100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.005573272705078125,
      "eval_rouge1": 99.5247,
      "eval_rouge2": 99.1868,
      "eval_rougeL": 99.3767,
      "eval_rougeLsum": 99.523,
      "eval_runtime": 32.5017,
      "eval_samples_per_second": 34.46,
      "eval_steps_per_second": 1.077,
      "step": 210
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.003314971923828125,
      "eval_rouge1": 99.6944,
      "eval_rouge2": 99.4612,
      "eval_rougeL": 99.5701,
      "eval_rougeLsum": 99.6944,
      "eval_runtime": 31.661,
      "eval_samples_per_second": 35.375,
      "eval_steps_per_second": 1.105,
      "step": 420
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 1.6153414249420166,
      "learning_rate": 0.0008665259359149131,
      "loss": 0.0413,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.0029888153076171875,
      "eval_rouge1": 99.779,
      "eval_rouge2": 99.6013,
      "eval_rougeL": 99.6771,
      "eval_rougeLsum": 99.7743,
      "eval_runtime": 32.3166,
      "eval_samples_per_second": 34.657,
      "eval_steps_per_second": 1.083,
      "step": 630
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.002841949462890625,
      "eval_rouge1": 99.6692,
      "eval_rouge2": 99.4798,
      "eval_rougeL": 99.5698,
      "eval_rougeLsum": 99.667,
      "eval_runtime": 32.5644,
      "eval_samples_per_second": 34.393,
      "eval_steps_per_second": 1.075,
      "step": 840
    },
    {
      "epoch": 4.761904761904762,
      "grad_norm": 0.001943291281349957,
      "learning_rate": 0.0005373650467932121,
      "loss": 0.0055,
      "step": 1000
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.0016384124755859375,
      "eval_rouge1": 99.8226,
      "eval_rouge2": 99.6738,
      "eval_rougeL": 99.7404,
      "eval_rougeLsum": 99.8124,
      "eval_runtime": 32.1973,
      "eval_samples_per_second": 34.786,
      "eval_steps_per_second": 1.087,
      "step": 1050
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.0015192031860351562,
      "eval_rouge1": 99.8683,
      "eval_rouge2": 99.77,
      "eval_rougeL": 99.8145,
      "eval_rougeLsum": 99.8683,
      "eval_runtime": 31.6836,
      "eval_samples_per_second": 35.35,
      "eval_steps_per_second": 1.105,
      "step": 1260
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.001491546630859375,
      "eval_rouge1": 99.9154,
      "eval_rouge2": 99.8424,
      "eval_rougeL": 99.8778,
      "eval_rougeLsum": 99.9154,
      "eval_runtime": 31.7073,
      "eval_samples_per_second": 35.323,
      "eval_steps_per_second": 1.104,
      "step": 1470
    },
    {
      "epoch": 7.142857142857143,
      "grad_norm": 0.034123487770557404,
      "learning_rate": 0.00018825509907063325,
      "loss": 0.0014,
      "step": 1500
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.000484466552734375,
      "eval_rouge1": 99.9577,
      "eval_rouge2": 99.9212,
      "eval_rougeL": 99.9389,
      "eval_rougeLsum": 99.9577,
      "eval_runtime": 31.5909,
      "eval_samples_per_second": 35.453,
      "eval_steps_per_second": 1.108,
      "step": 1680
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.0007829666137695312,
      "eval_rouge1": 99.9577,
      "eval_rouge2": 99.9212,
      "eval_rougeL": 99.9389,
      "eval_rougeLsum": 99.9577,
      "eval_runtime": 31.712,
      "eval_samples_per_second": 35.318,
      "eval_steps_per_second": 1.104,
      "step": 1890
    },
    {
      "epoch": 9.523809523809524,
      "grad_norm": 3.215530887246132e-05,
      "learning_rate": 5.5845868874357386e-06,
      "loss": 0.0007,
      "step": 2000
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.0007658004760742188,
      "eval_rouge1": 99.9577,
      "eval_rouge2": 99.9212,
      "eval_rougeL": 99.9389,
      "eval_rougeLsum": 99.9577,
      "eval_runtime": 31.6985,
      "eval_samples_per_second": 35.333,
      "eval_steps_per_second": 1.104,
      "step": 2100
    }
  ],
  "logging_steps": 500,
  "max_steps": 2100,
  "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": 2.3099168784384e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}