trainer_state.json

{
  "best_metric": 1.0,
  "best_model_checkpoint": "./en_results/checkpoint-150",
  "epoch": 5.0,
  "eval_steps": 500,
  "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": 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": 0.0007810367387719452,
      "eval_runtime": 41.5114,
      "eval_samples_per_second": 19.272,
      "eval_steps_per_second": 1.204,
      "step": 150
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.99625,
      "eval_classification_report": {
        "accuracy": 0.99625,
        "macro avg": {
          "f1-score": 0.9962499472648834,
          "precision": 0.9962779156327544,
          "recall": 0.9962500000000001,
          "support": 800.0
        },
        "neural": {
          "f1-score": 0.9962358845671266,
          "precision": 1.0,
          "recall": 0.9925,
          "support": 400.0
        },
        "real": {
          "f1-score": 0.9962640099626401,
          "precision": 0.9925558312655087,
          "recall": 1.0,
          "support": 400.0
        },
        "weighted avg": {
          "f1-score": 0.9962499472648834,
          "precision": 0.9962779156327544,
          "recall": 0.99625,
          "support": 800.0
        }
      },
      "eval_loss": 0.02056434564292431,
      "eval_runtime": 42.6494,
      "eval_samples_per_second": 18.758,
      "eval_steps_per_second": 1.172,
      "step": 300
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.99625,
      "eval_classification_report": {
        "accuracy": 0.99625,
        "macro avg": {
          "f1-score": 0.9962499472648834,
          "precision": 0.9962779156327544,
          "recall": 0.9962500000000001,
          "support": 800.0
        },
        "neural": {
          "f1-score": 0.9962358845671266,
          "precision": 1.0,
          "recall": 0.9925,
          "support": 400.0
        },
        "real": {
          "f1-score": 0.9962640099626401,
          "precision": 0.9925558312655087,
          "recall": 1.0,
          "support": 400.0
        },
        "weighted avg": {
          "f1-score": 0.9962499472648834,
          "precision": 0.9962779156327544,
          "recall": 0.99625,
          "support": 800.0
        }
      },
      "eval_loss": 0.025120796635746956,
      "eval_runtime": 41.1287,
      "eval_samples_per_second": 19.451,
      "eval_steps_per_second": 1.216,
      "step": 450
    },
    {
      "epoch": 3.33,
      "learning_rate": 5e-05,
      "loss": 0.1053,
      "step": 500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9975,
      "eval_classification_report": {
        "accuracy": 0.9975,
        "macro avg": {
          "f1-score": 0.9974999843749024,
          "precision": 0.9975124378109452,
          "recall": 0.9975,
          "support": 800.0
        },
        "neural": {
          "f1-score": 0.9975062344139651,
          "precision": 0.9950248756218906,
          "recall": 1.0,
          "support": 400.0
        },
        "real": {
          "f1-score": 0.9974937343358395,
          "precision": 1.0,
          "recall": 0.995,
          "support": 400.0
        },
        "weighted avg": {
          "f1-score": 0.9974999843749024,
          "precision": 0.9975124378109453,
          "recall": 0.9975,
          "support": 800.0
        }
      },
      "eval_loss": 0.014787975698709488,
      "eval_runtime": 40.7396,
      "eval_samples_per_second": 19.637,
      "eval_steps_per_second": 1.227,
      "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": 1.6821481040096842e-05,
      "eval_runtime": 30.459,
      "eval_samples_per_second": 26.265,
      "eval_steps_per_second": 1.642,
      "step": 750
    }
  ],
  "logging_steps": 500,
  "max_steps": 15000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 500,
  "total_flos": 3157332664320000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}