trainer_state.json

{
  "best_metric": 0.46609172224998474,
  "best_model_checkpoint": "./results_classification/checkpoint-1008",
  "epoch": 15.0,
  "global_step": 1890,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.47876061969015493,
      "eval_f1": 0.4269991937425738,
      "eval_loss": 2.655285120010376,
      "eval_precision": 0.5494019355743038,
      "eval_recall": 0.47876061969015493,
      "eval_runtime": 7.4841,
      "eval_samples_per_second": 267.365,
      "eval_steps_per_second": 4.276,
      "step": 126
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7426286856571714,
      "eval_f1": 0.7138537650916374,
      "eval_loss": 1.5136545896530151,
      "eval_precision": 0.7537780922874874,
      "eval_recall": 0.7426286856571714,
      "eval_runtime": 7.5247,
      "eval_samples_per_second": 265.923,
      "eval_steps_per_second": 4.253,
      "step": 252
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8235882058970515,
      "eval_f1": 0.8100185021709088,
      "eval_loss": 0.9697439074516296,
      "eval_precision": 0.8502379869379162,
      "eval_recall": 0.8235882058970515,
      "eval_runtime": 7.5422,
      "eval_samples_per_second": 265.307,
      "eval_steps_per_second": 4.243,
      "step": 378
    },
    {
      "epoch": 3.97,
      "learning_rate": 1.0002499375156212e-05,
      "loss": 2.0929,
      "step": 500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8680659670164917,
      "eval_f1": 0.8634639903385385,
      "eval_loss": 0.713852047920227,
      "eval_precision": 0.882324990578513,
      "eval_recall": 0.8680659670164917,
      "eval_runtime": 7.4941,
      "eval_samples_per_second": 267.008,
      "eval_steps_per_second": 4.27,
      "step": 504
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.895552223888056,
      "eval_f1": 0.8937627825776138,
      "eval_loss": 0.5724937319755554,
      "eval_precision": 0.9001995344818834,
      "eval_recall": 0.895552223888056,
      "eval_runtime": 7.508,
      "eval_samples_per_second": 266.516,
      "eval_steps_per_second": 4.262,
      "step": 630
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9025487256371814,
      "eval_f1": 0.9015269347270028,
      "eval_loss": 0.5064622759819031,
      "eval_precision": 0.9098775744608221,
      "eval_recall": 0.9025487256371814,
      "eval_runtime": 7.5479,
      "eval_samples_per_second": 265.106,
      "eval_steps_per_second": 4.24,
      "step": 756
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9045477261369316,
      "eval_f1": 0.9043691796671066,
      "eval_loss": 0.47243431210517883,
      "eval_precision": 0.9103961233141646,
      "eval_recall": 0.9045477261369316,
      "eval_runtime": 7.5019,
      "eval_samples_per_second": 266.734,
      "eval_steps_per_second": 4.266,
      "step": 882
    },
    {
      "epoch": 7.94,
      "learning_rate": 4.998750312421895e-09,
      "loss": 0.5401,
      "step": 1000
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9035482258870565,
      "eval_f1": 0.9032948555406941,
      "eval_loss": 0.46609172224998474,
      "eval_precision": 0.9089395111974776,
      "eval_recall": 0.9035482258870565,
      "eval_runtime": 7.5877,
      "eval_samples_per_second": 263.717,
      "eval_steps_per_second": 4.217,
      "step": 1008
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9035482258870565,
      "eval_f1": 0.9032948555406941,
      "eval_loss": 0.46609172224998474,
      "eval_precision": 0.9089395111974776,
      "eval_recall": 0.9035482258870565,
      "eval_runtime": 7.5072,
      "eval_samples_per_second": 266.546,
      "eval_steps_per_second": 4.263,
      "step": 1134
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.9035482258870565,
      "eval_f1": 0.9032948555406941,
      "eval_loss": 0.46609172224998474,
      "eval_precision": 0.9089395111974776,
      "eval_recall": 0.9035482258870565,
      "eval_runtime": 7.553,
      "eval_samples_per_second": 264.929,
      "eval_steps_per_second": 4.237,
      "step": 1260
    },
    {
      "epoch": 11.0,
      "eval_accuracy": 0.9035482258870565,
      "eval_f1": 0.9032948555406941,
      "eval_loss": 0.46609172224998474,
      "eval_precision": 0.9089395111974776,
      "eval_recall": 0.9035482258870565,
      "eval_runtime": 7.5371,
      "eval_samples_per_second": 265.487,
      "eval_steps_per_second": 4.246,
      "step": 1386
    },
    {
      "epoch": 11.9,
      "learning_rate": 0.0,
      "loss": 0.4189,
      "step": 1500
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.9035482258870565,
      "eval_f1": 0.9032948555406941,
      "eval_loss": 0.46609172224998474,
      "eval_precision": 0.9089395111974776,
      "eval_recall": 0.9035482258870565,
      "eval_runtime": 7.515,
      "eval_samples_per_second": 266.269,
      "eval_steps_per_second": 4.258,
      "step": 1512
    },
    {
      "epoch": 13.0,
      "eval_accuracy": 0.9035482258870565,
      "eval_f1": 0.9032948555406941,
      "eval_loss": 0.46609172224998474,
      "eval_precision": 0.9089395111974776,
      "eval_recall": 0.9035482258870565,
      "eval_runtime": 7.5178,
      "eval_samples_per_second": 266.167,
      "eval_steps_per_second": 4.257,
      "step": 1638
    },
    {
      "epoch": 14.0,
      "eval_accuracy": 0.9035482258870565,
      "eval_f1": 0.9032948555406941,
      "eval_loss": 0.46609172224998474,
      "eval_precision": 0.9089395111974776,
      "eval_recall": 0.9035482258870565,
      "eval_runtime": 7.4943,
      "eval_samples_per_second": 267.004,
      "eval_steps_per_second": 4.27,
      "step": 1764
    },
    {
      "epoch": 15.0,
      "eval_accuracy": 0.9035482258870565,
      "eval_f1": 0.9032948555406941,
      "eval_loss": 0.46609172224998474,
      "eval_precision": 0.9089395111974776,
      "eval_recall": 0.9035482258870565,
      "eval_runtime": 7.5368,
      "eval_samples_per_second": 265.499,
      "eval_steps_per_second": 4.246,
      "step": 1890
    }
  ],
  "max_steps": 1890,
  "num_train_epochs": 15,
  "total_flos": 5925466237910400.0,
  "trial_name": null,
  "trial_params": null
}