{
  "best_global_step": 80,
  "best_metric": 0.9958399986721193,
  "best_model_checkpoint": "/home/ubuntu/context_aware_modeling/fine_tuning/checkpoints/qwen3-8b_r32/checkpoint-80",
  "epoch": 1.8181818181818183,
  "eval_steps": 20,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.36363636363636365,
      "eval_accuracy": 0.9044056525353283,
      "eval_balanced_accuracy": 0.901877133105802,
      "eval_loss": 0.08732637017965317,
      "eval_macro_f1": 0.90297659081011,
      "eval_runtime": 39.9812,
      "eval_samples_per_second": 30.089,
      "eval_steps_per_second": 0.475,
      "step": 20
    },
    {
      "epoch": 0.7272727272727273,
      "eval_accuracy": 0.742310889443059,
      "eval_balanced_accuracy": 0.735494880546075,
      "eval_loss": 0.08577165752649307,
      "eval_macro_f1": 0.7197970138129186,
      "eval_runtime": 39.9877,
      "eval_samples_per_second": 30.084,
      "eval_steps_per_second": 0.475,
      "step": 40
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.41501519083976746,
      "learning_rate": 8.517573744099741e-05,
      "loss": 0.26,
      "step": 50
    },
    {
      "epoch": 1.0909090909090908,
      "eval_accuracy": 0.9858686616791354,
      "eval_balanced_accuracy": 0.985494880546075,
      "eval_loss": 0.08195541054010391,
      "eval_macro_f1": 0.9858461282921714,
      "eval_runtime": 39.8666,
      "eval_samples_per_second": 30.176,
      "eval_steps_per_second": 0.477,
      "step": 60
    },
    {
      "epoch": 1.4545454545454546,
      "eval_accuracy": 0.9958437240232751,
      "eval_balanced_accuracy": 0.9957337883959044,
      "eval_loss": 0.07636160403490067,
      "eval_macro_f1": 0.9958399986721193,
      "eval_runtime": 39.884,
      "eval_samples_per_second": 30.162,
      "eval_steps_per_second": 0.476,
      "step": 80
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.09980760514736176,
      "learning_rate": 3.845094616073783e-05,
      "loss": 0.0789,
      "step": 100
    },
    {
      "epoch": 1.8181818181818183,
      "eval_accuracy": 0.9958437240232751,
      "eval_balanced_accuracy": 0.9957337883959044,
      "eval_loss": 0.07304411381483078,
      "eval_macro_f1": 0.9958399986721193,
      "eval_runtime": 39.9125,
      "eval_samples_per_second": 30.141,
      "eval_steps_per_second": 0.476,
      "step": 100
    }
  ],
  "logging_steps": 50,
  "max_steps": 165,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 20,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.010343436759859e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}