trainer_state.json

{
  "best_metric": 0.28885045647621155,
  "best_model_checkpoint": "gal_ensp_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": 0.8957617762512267,
      "eval_f1": 0.617335823218176,
      "eval_loss": 0.3761306405067444,
      "eval_precision": 0.6694228822139723,
      "eval_recall": 0.5727692751949177,
      "eval_runtime": 5.0562,
      "eval_samples_per_second": 197.183,
      "eval_steps_per_second": 12.46,
      "step": 250
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.9600000000000002e-05,
      "loss": 0.4522,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9119234543670265,
      "eval_f1": 0.6876344484830503,
      "eval_loss": 0.3176829218864441,
      "eval_precision": 0.7070938215102975,
      "eval_recall": 0.6692174415246895,
      "eval_runtime": 5.216,
      "eval_samples_per_second": 191.144,
      "eval_steps_per_second": 12.078,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9176275760549558,
      "eval_f1": 0.7181533200341977,
      "eval_loss": 0.3025570511817932,
      "eval_precision": 0.7088607594936709,
      "eval_recall": 0.727692751949177,
      "eval_runtime": 5.1889,
      "eval_samples_per_second": 192.141,
      "eval_steps_per_second": 12.141,
      "step": 750
    },
    {
      "epoch": 4.0,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 0.2398,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9157875368007851,
      "eval_f1": 0.7138426839582747,
      "eval_loss": 0.30776312947273254,
      "eval_precision": 0.6973285596254475,
      "eval_recall": 0.7311579555298874,
      "eval_runtime": 5.0995,
      "eval_samples_per_second": 195.511,
      "eval_steps_per_second": 12.354,
      "step": 1000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9252024043179587,
      "eval_f1": 0.7407407407407408,
      "eval_loss": 0.28885045647621155,
      "eval_precision": 0.7496673074079551,
      "eval_recall": 0.732024256425065,
      "eval_runtime": 5.0736,
      "eval_samples_per_second": 196.509,
      "eval_steps_per_second": 12.417,
      "step": 1250
    },
    {
      "epoch": 6.0,
      "learning_rate": 1.88e-05,
      "loss": 0.1758,
      "step": 1500
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9213076545632973,
      "eval_f1": 0.7337823466855725,
      "eval_loss": 0.30206623673439026,
      "eval_precision": 0.7208524864187212,
      "eval_recall": 0.7471845220906729,
      "eval_runtime": 5.127,
      "eval_samples_per_second": 194.461,
      "eval_steps_per_second": 12.288,
      "step": 1500
    }
  ],
  "max_steps": 25000,
  "num_train_epochs": 100,
  "total_flos": 925793237842200.0,
  "trial_name": null,
  "trial_params": null
}