{
  "best_global_step": 40,
  "best_metric": 0.9622239004272388,
  "best_model_checkpoint": "/home/ubuntu/context_aware_modeling/fine_tuning/checkpoints/qwen2.5-7b_r32/checkpoint-40",
  "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": 0.7408601067579816,
      "eval_balanced_accuracy": 0.746751968503937,
      "eval_loss": 0.08867038041353226,
      "eval_macro_f1": 0.7255929552023894,
      "eval_runtime": 282.8839,
      "eval_samples_per_second": 35.099,
      "eval_steps_per_second": 0.551,
      "step": 20
    },
    {
      "epoch": 0.09888751545117429,
      "eval_accuracy": 0.9622318461073622,
      "eval_balanced_accuracy": 0.9630905511811023,
      "eval_loss": 0.08623240143060684,
      "eval_macro_f1": 0.9622239004272388,
      "eval_runtime": 283.697,
      "eval_samples_per_second": 34.999,
      "eval_steps_per_second": 0.55,
      "step": 40
    },
    {
      "epoch": 0.12360939431396786,
      "grad_norm": 0.08448316156864166,
      "learning_rate": 9.974176168365123e-05,
      "loss": 0.1612,
      "step": 50
    },
    {
      "epoch": 0.14833127317676142,
      "eval_accuracy": 0.771376775103233,
      "eval_balanced_accuracy": 0.7765748031496063,
      "eval_loss": 0.09103064239025116,
      "eval_macro_f1": 0.761310791599737,
      "eval_runtime": 285.1904,
      "eval_samples_per_second": 34.815,
      "eval_steps_per_second": 0.547,
      "step": 60
    },
    {
      "epoch": 0.19777503090234858,
      "eval_accuracy": 0.848625239198308,
      "eval_balanced_accuracy": 0.8520669291338583,
      "eval_loss": 0.07813651859760284,
      "eval_macro_f1": 0.8460994129171107,
      "eval_runtime": 284.4486,
      "eval_samples_per_second": 34.906,
      "eval_steps_per_second": 0.548,
      "step": 80
    },
    {
      "epoch": 0.24721878862793573,
      "grad_norm": 0.12635913491249084,
      "learning_rate": 9.866002634083497e-05,
      "loss": 0.08,
      "step": 100
    },
    {
      "epoch": 0.24721878862793573,
      "eval_accuracy": 0.8696746903011381,
      "eval_balanced_accuracy": 0.8726377952755906,
      "eval_loss": 0.07484585791826248,
      "eval_macro_f1": 0.8681635985041394,
      "eval_runtime": 282.8829,
      "eval_samples_per_second": 35.099,
      "eval_steps_per_second": 0.551,
      "step": 100
    },
    {
      "epoch": 0.29666254635352285,
      "eval_accuracy": 0.9457145734716487,
      "eval_balanced_accuracy": 0.9469488188976378,
      "eval_loss": 0.07700207084417343,
      "eval_macro_f1": 0.9456622867070287,
      "eval_runtime": 279.2884,
      "eval_samples_per_second": 35.551,
      "eval_steps_per_second": 0.559,
      "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": 4
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.374434686389453e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}