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": 1.4231,
      "step": 1
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.8756,
      "step": 133
    },
    {
      "epoch": 1.0,
      "eval_Macro F1": 0.6559577437042121,
      "eval_Macro Precision": 0.6414383471396911,
      "eval_Macro Recall": 0.6726779588705305,
      "eval_Micro F1": 0.869914853358562,
      "eval_Micro Precision": 0.869914853358562,
      "eval_Micro Recall": 0.869914853358562,
      "eval_Weighted F1": 0.8557169411489111,
      "eval_Weighted Precision": 0.8436710960059746,
      "eval_Weighted Recall": 0.869914853358562,
      "eval_accuracy": 0.869914853358562,
      "eval_loss": 0.452942818403244,
      "eval_runtime": 45.2965,
      "eval_samples_per_second": 46.67,
      "eval_steps_per_second": 0.751,
      "step": 133
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.2e-05,
      "loss": 0.4097,
      "step": 266
    },
    {
      "epoch": 2.0,
      "eval_Macro F1": 0.7826498896982309,
      "eval_Macro Precision": 0.8743465956410477,
      "eval_Macro Recall": 0.763545504951241,
      "eval_Micro F1": 0.902554399243141,
      "eval_Micro Precision": 0.902554399243141,
      "eval_Micro Recall": 0.902554399243141,
      "eval_Weighted F1": 0.8981990872046596,
      "eval_Weighted Precision": 0.9058995948483624,
      "eval_Weighted Recall": 0.902554399243141,
      "eval_accuracy": 0.902554399243141,
      "eval_loss": 0.31955790519714355,
      "eval_runtime": 46.2695,
      "eval_samples_per_second": 45.689,
      "eval_steps_per_second": 0.735,
      "step": 266
    },
    {
      "epoch": 3.0,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.3147,
      "step": 399
    },
    {
      "epoch": 3.0,
      "eval_Macro F1": 0.8469888698710597,
      "eval_Macro Precision": 0.8751072643902021,
      "eval_Macro Recall": 0.8318917244382616,
      "eval_Micro F1": 0.9115421002838221,
      "eval_Micro Precision": 0.9115421002838221,
      "eval_Micro Recall": 0.9115421002838221,
      "eval_Weighted F1": 0.9110995447372147,
      "eval_Weighted Precision": 0.9138453932389957,
      "eval_Weighted Recall": 0.9115421002838221,
      "eval_accuracy": 0.9115421002838221,
      "eval_loss": 0.2824004292488098,
      "eval_runtime": 44.6739,
      "eval_samples_per_second": 47.321,
      "eval_steps_per_second": 0.761,
      "step": 399
    },
    {
      "epoch": 4.0,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.2685,
      "step": 532
    },
    {
      "epoch": 4.0,
      "eval_Macro F1": 0.8681032986279441,
      "eval_Macro Precision": 0.8797074213841205,
      "eval_Macro Recall": 0.8601906345542645,
      "eval_Micro F1": 0.9186376537369915,
      "eval_Micro Precision": 0.9186376537369915,
      "eval_Micro Recall": 0.9186376537369915,
      "eval_Weighted F1": 0.918722301523608,
      "eval_Weighted Precision": 0.9202617437649651,
      "eval_Weighted Recall": 0.9186376537369915,
      "eval_accuracy": 0.9186376537369915,
      "eval_loss": 0.26486265659332275,
      "eval_runtime": 44.116,
      "eval_samples_per_second": 47.919,
      "eval_steps_per_second": 0.771,
      "step": 532
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0,
      "loss": 0.2479,
      "step": 665
    },
    {
      "epoch": 5.0,
      "eval_Macro F1": 0.8749369503373983,
      "eval_Macro Precision": 0.8821869512033577,
      "eval_Macro Recall": 0.8684302125750863,
      "eval_Micro F1": 0.9167455061494797,
      "eval_Micro Precision": 0.9167455061494797,
      "eval_Micro Recall": 0.9167455061494797,
      "eval_Weighted F1": 0.9165697427628363,
      "eval_Weighted Precision": 0.9168439952197603,
      "eval_Weighted Recall": 0.9167455061494797,
      "eval_accuracy": 0.9167455061494797,
      "eval_loss": 0.26428648829460144,
      "eval_runtime": 44.094,
      "eval_samples_per_second": 47.943,
      "eval_steps_per_second": 0.771,
      "step": 665
    },
    {
      "epoch": 5.0,
      "step": 665,
      "total_flos": 283497743040960.0,
      "train_loss": 0.42408741363009117,
      "train_runtime": 3111.9997,
      "train_samples_per_second": 13.586,
      "train_steps_per_second": 0.214
    }
  ],
  "max_steps": 665,
  "num_train_epochs": 5,
  "total_flos": 283497743040960.0,
  "trial_name": null,
  "trial_params": null
}