trainer_state.json

{
  "best_global_step": 1365,
  "best_metric": 0.8920863309352518,
  "best_model_checkpoint": "evaluation_results/student_run_20250630_205323/checkpoint-1365",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1365,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8878048780487805,
      "eval_f1": 0.8570026178010471,
      "eval_loss": 0.2749616503715515,
      "eval_precision": 0.9056016597510373,
      "eval_recall": 0.8133540372670808,
      "eval_runtime": 99.4939,
      "eval_samples_per_second": 78.296,
      "eval_steps_per_second": 9.79,
      "step": 273
    },
    {
      "epoch": 1.8315018315018317,
      "grad_norm": 2.6613881587982178,
      "learning_rate": 8.172161172161172e-06,
      "loss": 0.2475,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9003851091142491,
      "eval_f1": 0.8750402576489533,
      "eval_loss": 0.2577052414417267,
      "eval_precision": 0.908695652173913,
      "eval_recall": 0.8437888198757764,
      "eval_runtime": 105.9957,
      "eval_samples_per_second": 73.494,
      "eval_steps_per_second": 9.189,
      "step": 546
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.902824133504493,
      "eval_f1": 0.885320405999091,
      "eval_loss": 0.2662721276283264,
      "eval_precision": 0.8642413487133984,
      "eval_recall": 0.9074534161490683,
      "eval_runtime": 110.1943,
      "eval_samples_per_second": 70.693,
      "eval_steps_per_second": 8.839,
      "step": 819
    },
    {
      "epoch": 3.663003663003663,
      "grad_norm": 2.496551990509033,
      "learning_rate": 6.340659340659341e-06,
      "loss": 0.1213,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9061617458279846,
      "eval_f1": 0.8839498333068742,
      "eval_loss": 0.2616208493709564,
      "eval_precision": 0.9041896719714193,
      "eval_recall": 0.8645962732919255,
      "eval_runtime": 103.6645,
      "eval_samples_per_second": 75.146,
      "eval_steps_per_second": 9.396,
      "step": 1092
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9114249037227214,
      "eval_f1": 0.8920863309352518,
      "eval_loss": 0.29260820150375366,
      "eval_precision": 0.8985507246376812,
      "eval_recall": 0.8857142857142857,
      "eval_runtime": 109.3416,
      "eval_samples_per_second": 71.245,
      "eval_steps_per_second": 8.908,
      "step": 1365
    }
  ],
  "logging_steps": 500,
  "max_steps": 2730,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.168704518472448e+16,
  "train_batch_size": 200,
  "trial_name": null,
  "trial_params": null
}