finetune/lexical_content_the_control/trainer_state.json

{
  "best_metric": 0.9991216512955644,
  "best_model_checkpoint": "final_models/glue_models/structroberta_s2_50ep//finetune/lexical_content_the_control/checkpoint-200",
  "epoch": 10.0,
  "global_step": 1420,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.41,
      "eval_accuracy": 0.9991208910942078,
      "eval_f1": 0.9991216512955644,
      "eval_loss": 0.005907877814024687,
      "eval_mcc": 0.9982433012346493,
      "eval_runtime": 38.5838,
      "eval_samples_per_second": 471.701,
      "eval_steps_per_second": 58.963,
      "step": 200
    },
    {
      "epoch": 2.82,
      "eval_accuracy": 0.9959890246391296,
      "eval_f1": 0.9959764096345698,
      "eval_loss": 0.01726224645972252,
      "eval_mcc": 0.9919974823779373,
      "eval_runtime": 39.062,
      "eval_samples_per_second": 465.926,
      "eval_steps_per_second": 58.241,
      "step": 400
    },
    {
      "epoch": 3.52,
      "learning_rate": 3.23943661971831e-05,
      "loss": 0.0236,
      "step": 500
    },
    {
      "epoch": 4.23,
      "eval_accuracy": 0.9976373910903931,
      "eval_f1": 0.9976317673624497,
      "eval_loss": 0.00972041580826044,
      "eval_mcc": 0.9952858368179264,
      "eval_runtime": 38.7408,
      "eval_samples_per_second": 469.789,
      "eval_steps_per_second": 58.724,
      "step": 600
    },
    {
      "epoch": 5.63,
      "eval_accuracy": 0.9800549745559692,
      "eval_f1": 0.9796490441217693,
      "eval_loss": 0.05039139464497566,
      "eval_mcc": 0.9608746763848224,
      "eval_runtime": 38.5935,
      "eval_samples_per_second": 471.582,
      "eval_steps_per_second": 58.948,
      "step": 800
    },
    {
      "epoch": 7.04,
      "learning_rate": 1.4788732394366198e-05,
      "loss": 0.0011,
      "step": 1000
    },
    {
      "epoch": 7.04,
      "eval_accuracy": 0.9964835047721863,
      "eval_f1": 0.9964726631393299,
      "eval_loss": 0.010653842240571976,
      "eval_mcc": 0.9929858352436999,
      "eval_runtime": 39.2401,
      "eval_samples_per_second": 463.811,
      "eval_steps_per_second": 57.976,
      "step": 1000
    },
    {
      "epoch": 8.45,
      "eval_accuracy": 0.9964835047721863,
      "eval_f1": 0.9964711071901191,
      "eval_loss": 0.011649108491837978,
      "eval_mcc": 0.9929915912562117,
      "eval_runtime": 38.9591,
      "eval_samples_per_second": 467.157,
      "eval_steps_per_second": 58.395,
      "step": 1200
    },
    {
      "epoch": 9.86,
      "eval_accuracy": 0.9961538314819336,
      "eval_f1": 0.9961389961389961,
      "eval_loss": 0.012363024987280369,
      "eval_mcc": 0.9923370518263848,
      "eval_runtime": 41.8965,
      "eval_samples_per_second": 434.403,
      "eval_steps_per_second": 54.3,
      "step": 1400
    },
    {
      "epoch": 10.0,
      "step": 1420,
      "total_flos": 8323141417113600.0,
      "train_loss": 0.00880957562738741,
      "train_runtime": 763.4034,
      "train_samples_per_second": 119.02,
      "train_steps_per_second": 1.86
    }
  ],
  "max_steps": 1420,
  "num_train_epochs": 10,
  "total_flos": 8323141417113600.0,
  "trial_name": null,
  "trial_params": null
}