finetuned_entity_categorical_classification/checkpoint-3362/trainer_state.json

{
  "best_metric": 0.07765195518732071,
  "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": 0.1008,
      "step": 500
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.405116002379536e-05,
      "loss": 0.1133,
      "step": 1000
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.1076740035693041e-05,
      "loss": 0.1023,
      "step": 1500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9753086419753086,
      "eval_loss": 0.07765195518732071,
      "eval_runtime": 2.2887,
      "eval_samples_per_second": 2937.427,
      "eval_steps_per_second": 183.944,
      "step": 1681
    },
    {
      "epoch": 1.19,
      "learning_rate": 8.10232004759072e-06,
      "loss": 0.0827,
      "step": 2000
    },
    {
      "epoch": 1.49,
      "learning_rate": 5.1279000594884e-06,
      "loss": 0.0702,
      "step": 2500
    },
    {
      "epoch": 1.78,
      "learning_rate": 2.1534800713860798e-06,
      "loss": 0.0834,
      "step": 3000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9747136694927859,
      "eval_loss": 0.08629146963357925,
      "eval_runtime": 2.3024,
      "eval_samples_per_second": 2919.969,
      "eval_steps_per_second": 182.851,
      "step": 3362
    }
  ],
  "logging_steps": 500,
  "max_steps": 3362,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 213673546900476.0,
  "trial_name": null,
  "trial_params": null
}