finetuned_entity_categorical_classification/checkpoint-3346/trainer_state.json

{
  "best_metric": 0.10625720769166946,
  "best_model_checkpoint": "finetuned_entity_categorical_classification/checkpoint-1673",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 3346,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3,
      "learning_rate": 1.7011356843992828e-05,
      "loss": 0.1126,
      "step": 500
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.4022713687985656e-05,
      "loss": 0.1165,
      "step": 1000
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.1034070531978483e-05,
      "loss": 0.117,
      "step": 1500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9715951562266407,
      "eval_loss": 0.10625720769166946,
      "eval_runtime": 2.3554,
      "eval_samples_per_second": 2839.909,
      "eval_steps_per_second": 177.892,
      "step": 1673
    },
    {
      "epoch": 1.2,
      "learning_rate": 8.04542737597131e-06,
      "loss": 0.0894,
      "step": 2000
    },
    {
      "epoch": 1.49,
      "learning_rate": 5.056784219964137e-06,
      "loss": 0.0827,
      "step": 2500
    },
    {
      "epoch": 1.79,
      "learning_rate": 2.068141063956964e-06,
      "loss": 0.0755,
      "step": 3000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9706981611601136,
      "eval_loss": 0.1135576069355011,
      "eval_runtime": 2.4092,
      "eval_samples_per_second": 2776.427,
      "eval_steps_per_second": 173.916,
      "step": 3346
    }
  ],
  "logging_steps": 500,
  "max_steps": 3346,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 209706294909150.0,
  "trial_name": null,
  "trial_params": null
}