trainer_state.json

{
  "best_metric": 0.31558218598365784,
  "best_model_checkpoint": "gal_ptsp_mBERT/checkpoint-500",
  "epoch": 3.0,
  "global_step": 750,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8995338567222767,
      "eval_f1": 0.6327821382305876,
      "eval_loss": 0.3579872250556946,
      "eval_precision": 0.6700016136840407,
      "eval_recall": 0.5994802194628934,
      "eval_runtime": 5.7508,
      "eval_samples_per_second": 173.367,
      "eval_steps_per_second": 10.955,
      "step": 250
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.9600000000000002e-05,
      "loss": 0.4329,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9130888125613347,
      "eval_f1": 0.6942777696472998,
      "eval_loss": 0.31558218598365784,
      "eval_precision": 0.7038575667655786,
      "eval_recall": 0.6849552411204158,
      "eval_runtime": 5.8676,
      "eval_samples_per_second": 169.916,
      "eval_steps_per_second": 10.737,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9141928361138371,
      "eval_f1": 0.7064961051954548,
      "eval_loss": 0.3165477216243744,
      "eval_precision": 0.6994481392387152,
      "eval_recall": 0.7136875541438059,
      "eval_runtime": 5.7029,
      "eval_samples_per_second": 174.823,
      "eval_steps_per_second": 11.047,
      "step": 750
    }
  ],
  "max_steps": 25000,
  "num_train_epochs": 100,
  "total_flos": 467350292245200.0,
  "trial_name": null,
  "trial_params": null
}