finetune/control_raising_lexical_content_the/trainer_state.json

{
  "best_metric": 0.494088272012925,
  "best_model_checkpoint": "final_models/glue_models/structroberta_s2_final//finetune/control_raising_lexical_content_the/checkpoint-400",
  "epoch": 10.0,
  "global_step": 570,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.02,
      "eval_accuracy": 0.6656312346458435,
      "eval_f1": 0.494088272012925,
      "eval_loss": 3.040160655975342,
      "eval_mcc": 0.43895218658919233,
      "eval_runtime": 40.034,
      "eval_samples_per_second": 514.637,
      "eval_steps_per_second": 64.345,
      "step": 400
    },
    {
      "epoch": 8.77,
      "learning_rate": 6.140350877192982e-06,
      "loss": 0.0132,
      "step": 500
    },
    {
      "epoch": 10.0,
      "step": 570,
      "total_flos": 5687886662369280.0,
      "train_loss": 0.011623076279239173,
      "train_runtime": 335.2215,
      "train_samples_per_second": 203.328,
      "train_steps_per_second": 1.7
    }
  ],
  "max_steps": 570,
  "num_train_epochs": 10,
  "total_flos": 5687886662369280.0,
  "trial_name": null,
  "trial_params": null
}