trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "global_step": 665,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 1.9969924812030075e-05,
      "loss": 1.355,
      "step": 1
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.2255,
      "step": 133
    },
    {
      "epoch": 1.0,
      "eval_Macro F1": 0.14874720660368068,
      "eval_Macro Precision": 0.22846464167062175,
      "eval_Macro Recall": 0.2506841990271725,
      "eval_Micro F1": 0.413434247871334,
      "eval_Micro Precision": 0.413434247871334,
      "eval_Micro Recall": 0.413434247871334,
      "eval_Weighted F1": 0.24374830457829116,
      "eval_Weighted Precision": 0.2652376477201957,
      "eval_Weighted Recall": 0.413434247871334,
      "eval_accuracy": 0.413434247871334,
      "eval_loss": 1.1365216970443726,
      "eval_runtime": 4.9797,
      "eval_samples_per_second": 424.526,
      "eval_steps_per_second": 6.828,
      "step": 133
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.2e-05,
      "loss": 1.1337,
      "step": 266
    },
    {
      "epoch": 2.0,
      "eval_Macro F1": 0.2539122945315465,
      "eval_Macro Precision": 0.27045292732351167,
      "eval_Macro Recall": 0.31610570012534067,
      "eval_Micro F1": 0.4531693472090823,
      "eval_Micro Precision": 0.4531693472090823,
      "eval_Micro Recall": 0.4531693472090823,
      "eval_Weighted F1": 0.3257022348814709,
      "eval_Weighted Precision": 0.3014929354313833,
      "eval_Weighted Recall": 0.4531693472090823,
      "eval_accuracy": 0.4531693472090823,
      "eval_loss": 1.0851175785064697,
      "eval_runtime": 5.0249,
      "eval_samples_per_second": 420.706,
      "eval_steps_per_second": 6.766,
      "step": 266
    },
    {
      "epoch": 3.0,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.0847,
      "step": 399
    },
    {
      "epoch": 3.0,
      "eval_Macro F1": 0.29146318011221783,
      "eval_Macro Precision": 0.4941561809223257,
      "eval_Macro Recall": 0.3519927370002771,
      "eval_Micro F1": 0.47587511825922424,
      "eval_Micro Precision": 0.47587511825922424,
      "eval_Micro Recall": 0.47587511825922424,
      "eval_Weighted F1": 0.35909819845877977,
      "eval_Weighted Precision": 0.6351629101542547,
      "eval_Weighted Recall": 0.47587511825922424,
      "eval_accuracy": 0.47587511825922424,
      "eval_loss": 1.0384365320205688,
      "eval_runtime": 5.0385,
      "eval_samples_per_second": 419.567,
      "eval_steps_per_second": 6.748,
      "step": 399
    },
    {
      "epoch": 4.0,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.05,
      "step": 532
    },
    {
      "epoch": 4.0,
      "eval_Macro F1": 0.3205588999330816,
      "eval_Macro Precision": 0.4596183152865385,
      "eval_Macro Recall": 0.3782911164189696,
      "eval_Micro F1": 0.49621570482497634,
      "eval_Micro Precision": 0.49621570482497634,
      "eval_Micro Recall": 0.49621570482497634,
      "eval_Weighted F1": 0.3917006514214786,
      "eval_Weighted Precision": 0.584561005399218,
      "eval_Weighted Recall": 0.49621570482497634,
      "eval_accuracy": 0.49621570482497634,
      "eval_loss": 1.0111591815948486,
      "eval_runtime": 5.0498,
      "eval_samples_per_second": 418.628,
      "eval_steps_per_second": 6.733,
      "step": 532
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0,
      "loss": 1.0309,
      "step": 665
    },
    {
      "epoch": 5.0,
      "eval_Macro F1": 0.3282454852143253,
      "eval_Macro Precision": 0.4547967339236757,
      "eval_Macro Recall": 0.3834764306870363,
      "eval_Micro F1": 0.5014191106906338,
      "eval_Micro Precision": 0.5014191106906338,
      "eval_Micro Recall": 0.5014191106906338,
      "eval_Weighted F1": 0.4022689273065864,
      "eval_Weighted Precision": 0.5783027384112047,
      "eval_Weighted Recall": 0.5014191106906338,
      "eval_accuracy": 0.5014191106906338,
      "eval_loss": 1.003102421760559,
      "eval_runtime": 5.016,
      "eval_samples_per_second": 421.451,
      "eval_steps_per_second": 6.778,
      "step": 665
    },
    {
      "epoch": 5.0,
      "step": 665,
      "total_flos": 9687083333760.0,
      "train_loss": 1.1051450449721258,
      "train_runtime": 307.9,
      "train_samples_per_second": 137.317,
      "train_steps_per_second": 2.16
    }
  ],
  "max_steps": 665,
  "num_train_epochs": 5,
  "total_flos": 9687083333760.0,
  "trial_name": null,
  "trial_params": null
}