trainer_state.json

{
  "best_metric": 1.0,
  "best_model_checkpoint": "./hu_results/checkpoint-300",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 900,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.99625,
      "eval_classification_report": {
        "accuracy": 0.99625,
        "macro avg": {
          "f1-score": 0.9962499941406158,
          "precision": 0.9962531015818848,
          "recall": 0.9962500000000001,
          "support": 800.0
        },
        "neural": {
          "f1-score": 0.9962546816479401,
          "precision": 0.9950124688279302,
          "recall": 0.9975,
          "support": 400.0
        },
        "real": {
          "f1-score": 0.9962453066332916,
          "precision": 0.9974937343358395,
          "recall": 0.995,
          "support": 400.0
        },
        "weighted avg": {
          "f1-score": 0.9962499941406158,
          "precision": 0.9962531015818848,
          "recall": 0.99625,
          "support": 800.0
        }
      },
      "eval_loss": 0.022499747574329376,
      "eval_runtime": 35.4884,
      "eval_samples_per_second": 22.543,
      "eval_steps_per_second": 1.409,
      "step": 150
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 1.0,
      "eval_classification_report": {
        "accuracy": 1.0,
        "macro avg": {
          "f1-score": 1.0,
          "precision": 1.0,
          "recall": 1.0,
          "support": 800.0
        },
        "neural": {
          "f1-score": 1.0,
          "precision": 1.0,
          "recall": 1.0,
          "support": 400.0
        },
        "real": {
          "f1-score": 1.0,
          "precision": 1.0,
          "recall": 1.0,
          "support": 400.0
        },
        "weighted avg": {
          "f1-score": 1.0,
          "precision": 1.0,
          "recall": 1.0,
          "support": 800.0
        }
      },
      "eval_loss": 0.0003398692642804235,
      "eval_runtime": 27.3624,
      "eval_samples_per_second": 29.237,
      "eval_steps_per_second": 1.827,
      "step": 300
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 1.0,
      "eval_classification_report": {
        "accuracy": 1.0,
        "macro avg": {
          "f1-score": 1.0,
          "precision": 1.0,
          "recall": 1.0,
          "support": 800.0
        },
        "neural": {
          "f1-score": 1.0,
          "precision": 1.0,
          "recall": 1.0,
          "support": 400.0
        },
        "real": {
          "f1-score": 1.0,
          "precision": 1.0,
          "recall": 1.0,
          "support": 400.0
        },
        "weighted avg": {
          "f1-score": 1.0,
          "precision": 1.0,
          "recall": 1.0,
          "support": 800.0
        }
      },
      "eval_loss": 0.0012723351828753948,
      "eval_runtime": 27.6619,
      "eval_samples_per_second": 28.921,
      "eval_steps_per_second": 1.808,
      "step": 450
    },
    {
      "epoch": 3.33,
      "learning_rate": 5e-05,
      "loss": 0.1899,
      "step": 500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 1.0,
      "eval_classification_report": {
        "accuracy": 1.0,
        "macro avg": {
          "f1-score": 1.0,
          "precision": 1.0,
          "recall": 1.0,
          "support": 800.0
        },
        "neural": {
          "f1-score": 1.0,
          "precision": 1.0,
          "recall": 1.0,
          "support": 400.0
        },
        "real": {
          "f1-score": 1.0,
          "precision": 1.0,
          "recall": 1.0,
          "support": 400.0
        },
        "weighted avg": {
          "f1-score": 1.0,
          "precision": 1.0,
          "recall": 1.0,
          "support": 800.0
        }
      },
      "eval_loss": 3.821239079115912e-05,
      "eval_runtime": 27.9176,
      "eval_samples_per_second": 28.656,
      "eval_steps_per_second": 1.791,
      "step": 600
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 1.0,
      "eval_classification_report": {
        "accuracy": 1.0,
        "macro avg": {
          "f1-score": 1.0,
          "precision": 1.0,
          "recall": 1.0,
          "support": 800.0
        },
        "neural": {
          "f1-score": 1.0,
          "precision": 1.0,
          "recall": 1.0,
          "support": 400.0
        },
        "real": {
          "f1-score": 1.0,
          "precision": 1.0,
          "recall": 1.0,
          "support": 400.0
        },
        "weighted avg": {
          "f1-score": 1.0,
          "precision": 1.0,
          "recall": 1.0,
          "support": 800.0
        }
      },
      "eval_loss": 1.9715977032319643e-05,
      "eval_runtime": 35.5634,
      "eval_samples_per_second": 22.495,
      "eval_steps_per_second": 1.406,
      "step": 750
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 1.0,
      "eval_classification_report": {
        "accuracy": 1.0,
        "macro avg": {
          "f1-score": 1.0,
          "precision": 1.0,
          "recall": 1.0,
          "support": 800.0
        },
        "neural": {
          "f1-score": 1.0,
          "precision": 1.0,
          "recall": 1.0,
          "support": 400.0
        },
        "real": {
          "f1-score": 1.0,
          "precision": 1.0,
          "recall": 1.0,
          "support": 400.0
        },
        "weighted avg": {
          "f1-score": 1.0,
          "precision": 1.0,
          "recall": 1.0,
          "support": 800.0
        }
      },
      "eval_loss": 1.313230677624233e-05,
      "eval_runtime": 27.0249,
      "eval_samples_per_second": 29.602,
      "eval_steps_per_second": 1.85,
      "step": 900
    }
  ],
  "logging_steps": 500,
  "max_steps": 15000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 500,
  "total_flos": 3788799197184000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}