checkpoint-21342/trainer_state.json

{
  "best_metric": 0.0023566017149643857,
  "best_model_checkpoint": "ProtBert-finetuned-1000-labels/checkpoint-10671",
  "epoch": 6.0,
  "global_step": 21342,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 0.1046,
      "step": 3557
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.0,
      "eval_f1": 0.0015764799415315758,
      "eval_loss": 0.10419555753469467,
      "eval_precision": 0.0013009841827768013,
      "eval_recall": 0.002,
      "eval_runtime": 36.7492,
      "eval_samples_per_second": 774.166,
      "eval_steps_per_second": 24.218,
      "step": 3557
    },
    {
      "epoch": 2.0,
      "learning_rate": 4.9e-05,
      "loss": 0.1047,
      "step": 7114
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.0,
      "eval_f1": 0.0015764799415315758,
      "eval_loss": 0.10421660542488098,
      "eval_precision": 0.0013009841827768013,
      "eval_recall": 0.002,
      "eval_runtime": 36.6962,
      "eval_samples_per_second": 775.284,
      "eval_steps_per_second": 24.253,
      "step": 7114
    },
    {
      "epoch": 3.0,
      "learning_rate": 4.85e-05,
      "loss": 0.1046,
      "step": 10671
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.0,
      "eval_f1": 0.0023566017149643857,
      "eval_loss": 0.10416813939809799,
      "eval_precision": 0.0019404920913884008,
      "eval_recall": 0.003,
      "eval_runtime": 36.5239,
      "eval_samples_per_second": 778.941,
      "eval_steps_per_second": 24.368,
      "step": 10671
    },
    {
      "epoch": 4.0,
      "learning_rate": 4.8e-05,
      "loss": 0.1046,
      "step": 14228
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.0,
      "eval_f1": 0.0023566017149643857,
      "eval_loss": 0.10419166833162308,
      "eval_precision": 0.0019404920913884008,
      "eval_recall": 0.003,
      "eval_runtime": 36.7991,
      "eval_samples_per_second": 773.116,
      "eval_steps_per_second": 24.185,
      "step": 14228
    },
    {
      "epoch": 5.0,
      "learning_rate": 4.75e-05,
      "loss": 0.1046,
      "step": 17785
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.0,
      "eval_f1": 0.0023566017149643857,
      "eval_loss": 0.10412722080945969,
      "eval_precision": 0.0019404920913884008,
      "eval_recall": 0.003,
      "eval_runtime": 37.0346,
      "eval_samples_per_second": 768.201,
      "eval_steps_per_second": 24.032,
      "step": 17785
    },
    {
      "epoch": 6.0,
      "learning_rate": 4.7e-05,
      "loss": 0.1046,
      "step": 21342
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.0,
      "eval_f1": 0.0023566017149643857,
      "eval_loss": 0.10410485416650772,
      "eval_precision": 0.0019404920913884008,
      "eval_recall": 0.003,
      "eval_runtime": 36.6252,
      "eval_samples_per_second": 776.788,
      "eval_steps_per_second": 24.3,
      "step": 21342
    }
  ],
  "max_steps": 355700,
  "num_train_epochs": 100,
  "total_flos": 4669737633892224.0,
  "trial_name": null,
  "trial_params": null
}