trainer_state.json

{
  "best_metric": 0.3014024496078491,
  "best_model_checkpoint": "gal_pt_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": 0.8764106967615309,
      "eval_f1": 0.5194326468467025,
      "eval_loss": 0.4419800043106079,
      "eval_precision": 0.583648478300018,
      "eval_recall": 0.4679468668784291,
      "eval_runtime": 5.1555,
      "eval_samples_per_second": 193.384,
      "eval_steps_per_second": 12.22,
      "step": 250
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.9600000000000002e-05,
      "loss": 0.5661,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8951177625122669,
      "eval_f1": 0.6106744516805149,
      "eval_loss": 0.3635525107383728,
      "eval_precision": 0.634074304368102,
      "eval_recall": 0.5889402252382328,
      "eval_runtime": 5.1045,
      "eval_samples_per_second": 195.319,
      "eval_steps_per_second": 12.342,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8999938665358195,
      "eval_f1": 0.6414069202173291,
      "eval_loss": 0.33455267548561096,
      "eval_precision": 0.6352308128009062,
      "eval_recall": 0.6477043026277793,
      "eval_runtime": 5.0422,
      "eval_samples_per_second": 197.733,
      "eval_steps_per_second": 12.495,
      "step": 750
    },
    {
      "epoch": 4.0,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 0.2931,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9071700196270854,
      "eval_f1": 0.6772389380530973,
      "eval_loss": 0.3290555477142334,
      "eval_precision": 0.6643978330323657,
      "eval_recall": 0.6905861969390702,
      "eval_runtime": 5.0586,
      "eval_samples_per_second": 197.092,
      "eval_steps_per_second": 12.454,
      "step": 1000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9161248773307163,
      "eval_f1": 0.7046489769358687,
      "eval_loss": 0.3014024496078491,
      "eval_precision": 0.7057204923968139,
      "eval_recall": 0.7035807103667341,
      "eval_runtime": 5.0677,
      "eval_samples_per_second": 196.736,
      "eval_steps_per_second": 12.432,
      "step": 1250
    },
    {
      "epoch": 6.0,
      "learning_rate": 1.88e-05,
      "loss": 0.2199,
      "step": 1500
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9111567713444554,
      "eval_f1": 0.6965250965250965,
      "eval_loss": 0.317579060792923,
      "eval_precision": 0.6778248394589425,
      "eval_recall": 0.7162864568293387,
      "eval_runtime": 5.1483,
      "eval_samples_per_second": 193.655,
      "eval_steps_per_second": 12.237,
      "step": 1500
    }
  ],
  "max_steps": 25000,
  "num_train_epochs": 100,
  "total_flos": 925793237842200.0,
  "trial_name": null,
  "trial_params": null
}