finetuned_entity_categorical_classification/checkpoint-3362/trainer_state.json

{
  "best_metric": 0.10296357423067093,
  "best_model_checkpoint": "finetuned_entity_categorical_classification/checkpoint-1681",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 3362,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3,
      "learning_rate": 1.7025580011897683e-05,
      "loss": 0.1045,
      "step": 500
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.405116002379536e-05,
      "loss": 0.1056,
      "step": 1000
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.1076740035693041e-05,
      "loss": 0.1041,
      "step": 1500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9721850364420646,
      "eval_loss": 0.10296357423067093,
      "eval_runtime": 2.316,
      "eval_samples_per_second": 2902.854,
      "eval_steps_per_second": 181.779,
      "step": 1681
    },
    {
      "epoch": 1.19,
      "learning_rate": 8.10232004759072e-06,
      "loss": 0.0776,
      "step": 2000
    },
    {
      "epoch": 1.49,
      "learning_rate": 5.1279000594884e-06,
      "loss": 0.0675,
      "step": 2500
    },
    {
      "epoch": 1.78,
      "learning_rate": 2.1534800713860798e-06,
      "loss": 0.0773,
      "step": 3000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9708463483563885,
      "eval_loss": 0.11056160181760788,
      "eval_runtime": 2.2742,
      "eval_samples_per_second": 2956.182,
      "eval_steps_per_second": 185.119,
      "step": 3362
    }
  ],
  "logging_steps": 500,
  "max_steps": 3362,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 216609059710134.0,
  "trial_name": null,
  "trial_params": null
}