{
  "best_global_step": 60,
  "best_metric": 0.8713209596281215,
  "best_model_checkpoint": "/home/ubuntu/context_aware_modeling/fine_tuning/checkpoints/qwen3-4b-instruct_r32/checkpoint-60",
  "epoch": 0.29666254635352285,
  "eval_steps": 20,
  "global_step": 120,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.049443757725587144,
      "eval_accuracy": 0.48595024675193876,
      "eval_balanced_accuracy": 0.4749015748031496,
      "eval_loss": 0.09321743249893188,
      "eval_macro_f1": 0.3270299579774976,
      "eval_runtime": 221.9955,
      "eval_samples_per_second": 44.726,
      "eval_steps_per_second": 0.703,
      "step": 20
    },
    {
      "epoch": 0.09888751545117429,
      "eval_accuracy": 0.8564810152079766,
      "eval_balanced_accuracy": 0.8560164608986673,
      "eval_loss": 0.08692961931228638,
      "eval_macro_f1": 0.8562523605398756,
      "eval_runtime": 219.4762,
      "eval_samples_per_second": 45.24,
      "eval_steps_per_second": 0.711,
      "step": 40
    },
    {
      "epoch": 0.12360939431396786,
      "grad_norm": 0.08445104211568832,
      "learning_rate": 9.974176168365123e-05,
      "loss": 0.2714,
      "step": 50
    },
    {
      "epoch": 0.14833127317676142,
      "eval_accuracy": 0.8716889918420787,
      "eval_balanced_accuracy": 0.8734059543082996,
      "eval_loss": 0.08331040292978287,
      "eval_macro_f1": 0.8713209596281215,
      "eval_runtime": 222.322,
      "eval_samples_per_second": 44.66,
      "eval_steps_per_second": 0.702,
      "step": 60
    },
    {
      "epoch": 0.19777503090234858,
      "eval_accuracy": 0.8590996072111995,
      "eval_balanced_accuracy": 0.8592460211781632,
      "eval_loss": 0.07730897516012192,
      "eval_macro_f1": 0.8590731672698886,
      "eval_runtime": 220.5576,
      "eval_samples_per_second": 45.018,
      "eval_steps_per_second": 0.707,
      "step": 80
    },
    {
      "epoch": 0.24721878862793573,
      "grad_norm": 0.1737745851278305,
      "learning_rate": 9.866002634083497e-05,
      "loss": 0.0786,
      "step": 100
    },
    {
      "epoch": 0.24721878862793573,
      "eval_accuracy": 0.7493201732299325,
      "eval_balanced_accuracy": 0.7537630739676823,
      "eval_loss": 0.07370100170373917,
      "eval_macro_f1": 0.7415462894347242,
      "eval_runtime": 220.8073,
      "eval_samples_per_second": 44.967,
      "eval_steps_per_second": 0.706,
      "step": 100
    },
    {
      "epoch": 0.29666254635352285,
      "eval_accuracy": 0.7912176452814986,
      "eval_balanced_accuracy": 0.7902769951755617,
      "eval_loss": 0.07204873859882355,
      "eval_macro_f1": 0.7904928530739057,
      "eval_runtime": 219.0776,
      "eval_samples_per_second": 45.322,
      "eval_steps_per_second": 0.712,
      "step": 120
    }
  ],
  "logging_steps": 50,
  "max_steps": 1215,
  "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": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7456771738527334e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}