trainer_state.json

{
  "best_metric": 0.2923365533351898,
  "best_model_checkpoint": "gal_ptsp_XLM-R/checkpoint-1250",
  "epoch": 6.0,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9011592247301276,
      "eval_f1": 0.6440599412946084,
      "eval_loss": 0.3590831756591797,
      "eval_precision": 0.6925249169435216,
      "eval_recall": 0.6019347386658966,
      "eval_runtime": 5.2467,
      "eval_samples_per_second": 190.025,
      "eval_steps_per_second": 12.008,
      "step": 250
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.9600000000000002e-05,
      "loss": 0.4538,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.914622178606477,
      "eval_f1": 0.6995495828103079,
      "eval_loss": 0.3113715350627899,
      "eval_precision": 0.7158833308145686,
      "eval_recall": 0.6839445567427086,
      "eval_runtime": 5.3257,
      "eval_samples_per_second": 187.205,
      "eval_steps_per_second": 11.829,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9168608930323847,
      "eval_f1": 0.7153035052721572,
      "eval_loss": 0.301097571849823,
      "eval_precision": 0.7060478199718706,
      "eval_recall": 0.7248050822985851,
      "eval_runtime": 5.2545,
      "eval_samples_per_second": 189.743,
      "eval_steps_per_second": 11.99,
      "step": 750
    },
    {
      "epoch": 4.0,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 0.2434,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.913211481844946,
      "eval_f1": 0.7058080808080809,
      "eval_loss": 0.316134512424469,
      "eval_precision": 0.6863574351978172,
      "eval_recall": 0.7263933006064106,
      "eval_runtime": 5.308,
      "eval_samples_per_second": 187.829,
      "eval_steps_per_second": 11.869,
      "step": 1000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9226263493621197,
      "eval_f1": 0.7294493216280925,
      "eval_loss": 0.2923365533351898,
      "eval_precision": 0.7331194399883331,
      "eval_recall": 0.7258157666762922,
      "eval_runtime": 5.3391,
      "eval_samples_per_second": 186.734,
      "eval_steps_per_second": 11.8,
      "step": 1250
    },
    {
      "epoch": 6.0,
      "learning_rate": 1.88e-05,
      "loss": 0.1827,
      "step": 1500
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9170755642787046,
      "eval_f1": 0.7170290878282971,
      "eval_loss": 0.308558851480484,
      "eval_precision": 0.7015750207239569,
      "eval_recall": 0.7331793242853017,
      "eval_runtime": 5.2881,
      "eval_samples_per_second": 188.538,
      "eval_steps_per_second": 11.914,
      "step": 1500
    }
  ],
  "max_steps": 25000,
  "num_train_epochs": 100,
  "total_flos": 925793237842200.0,
  "trial_name": null,
  "trial_params": null
}