trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.49367088607595,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9254942164969132,
      "eval_f1": 0.5899065420560747,
      "eval_loss": 0.2620357871055603,
      "eval_precision": 0.6196335078534031,
      "eval_recall": 0.5629013079667063,
      "eval_runtime": 9.86,
      "eval_samples_per_second": 63.894,
      "eval_steps_per_second": 4.057,
      "step": 158
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9576990795426686,
      "eval_f1": 0.8084220268394261,
      "eval_loss": 0.13847729563713074,
      "eval_precision": 0.7871142149132687,
      "eval_recall": 0.8309155766944114,
      "eval_runtime": 9.7783,
      "eval_samples_per_second": 64.428,
      "eval_steps_per_second": 4.091,
      "step": 316
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9653435556843255,
      "eval_f1": 0.8456001857441375,
      "eval_loss": 0.11949469894170761,
      "eval_precision": 0.8260376502608301,
      "eval_recall": 0.8661117717003567,
      "eval_runtime": 9.7534,
      "eval_samples_per_second": 64.593,
      "eval_steps_per_second": 4.101,
      "step": 474
    },
    {
      "epoch": 3.16,
      "learning_rate": 1.5189873417721521e-05,
      "loss": 0.5092,
      "step": 500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9678842853640598,
      "eval_f1": 0.8628684609111034,
      "eval_loss": 0.11460543423891068,
      "eval_precision": 0.845820009136592,
      "eval_recall": 0.8806183115338883,
      "eval_runtime": 9.7942,
      "eval_samples_per_second": 64.324,
      "eval_steps_per_second": 4.084,
      "step": 632
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9680625821836903,
      "eval_f1": 0.8695449784708483,
      "eval_loss": 0.11910449713468552,
      "eval_precision": 0.8514129443938013,
      "eval_recall": 0.8884661117717003,
      "eval_runtime": 9.7653,
      "eval_samples_per_second": 64.514,
      "eval_steps_per_second": 4.096,
      "step": 790
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9688426307695737,
      "eval_f1": 0.8747533372025537,
      "eval_loss": 0.11907244473695755,
      "eval_precision": 0.854421768707483,
      "eval_recall": 0.8960760998810939,
      "eval_runtime": 9.72,
      "eval_samples_per_second": 64.815,
      "eval_steps_per_second": 4.115,
      "step": 948
    },
    {
      "epoch": 6.33,
      "learning_rate": 8.157524613220817e-06,
      "loss": 0.0551,
      "step": 1000
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9694666696382803,
      "eval_f1": 0.879330388281795,
      "eval_loss": 0.12043958157300949,
      "eval_precision": 0.8601319081191722,
      "eval_recall": 0.8994054696789536,
      "eval_runtime": 9.8003,
      "eval_samples_per_second": 64.284,
      "eval_steps_per_second": 4.082,
      "step": 1106
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9703581537364327,
      "eval_f1": 0.8830837106699176,
      "eval_loss": 0.12078419327735901,
      "eval_precision": 0.8627495462794919,
      "eval_recall": 0.9043995243757431,
      "eval_runtime": 9.7367,
      "eval_samples_per_second": 64.704,
      "eval_steps_per_second": 4.108,
      "step": 1264
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.970335866633979,
      "eval_f1": 0.8844769534424707,
      "eval_loss": 0.12255486100912094,
      "eval_precision": 0.8641107078039928,
      "eval_recall": 0.9058263971462545,
      "eval_runtime": 9.7627,
      "eval_samples_per_second": 64.531,
      "eval_steps_per_second": 4.097,
      "step": 1422
    },
    {
      "epoch": 9.49,
      "learning_rate": 1.1251758087201126e-06,
      "loss": 0.0342,
      "step": 1500
    }
  ],
  "max_steps": 1580,
  "num_train_epochs": 10,
  "total_flos": 5349608480859192.0,
  "trial_name": null,
  "trial_params": null
}