{
  "best_global_step": 100,
  "best_metric": 0.9380687925372826,
  "best_model_checkpoint": "/home/ubuntu/context_aware_modeling/fine_tuning/checkpoints/qwen3-8b_r32/checkpoint-100",
  "epoch": 0.24721878862793573,
  "eval_steps": 20,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.049443757725587144,
      "eval_accuracy": 0.8436902004230034,
      "eval_balanced_accuracy": 0.8472440944881889,
      "eval_loss": 0.08851692080497742,
      "eval_macro_f1": 0.8408735233374638,
      "eval_runtime": 312.5896,
      "eval_samples_per_second": 31.764,
      "eval_steps_per_second": 0.499,
      "step": 20
    },
    {
      "epoch": 0.09888751545117429,
      "eval_accuracy": 0.8329136871789707,
      "eval_balanced_accuracy": 0.8367125984251969,
      "eval_loss": 0.08733776211738586,
      "eval_macro_f1": 0.8293845897499257,
      "eval_runtime": 313.202,
      "eval_samples_per_second": 31.702,
      "eval_steps_per_second": 0.498,
      "step": 40
    },
    {
      "epoch": 0.12360939431396786,
      "grad_norm": 0.05077357962727547,
      "learning_rate": 9.974176168365123e-05,
      "loss": 0.2648,
      "step": 50
    },
    {
      "epoch": 0.14833127317676142,
      "eval_accuracy": 0.8986806324906839,
      "eval_balanced_accuracy": 0.900984251968504,
      "eval_loss": 0.08656006306409836,
      "eval_macro_f1": 0.8980595649006062,
      "eval_runtime": 312.2111,
      "eval_samples_per_second": 31.802,
      "eval_steps_per_second": 0.5,
      "step": 60
    },
    {
      "epoch": 0.19777503090234858,
      "eval_accuracy": 0.9188236479000906,
      "eval_balanced_accuracy": 0.9206692913385827,
      "eval_loss": 0.0858699306845665,
      "eval_macro_f1": 0.9185504903922079,
      "eval_runtime": 317.4539,
      "eval_samples_per_second": 31.277,
      "eval_steps_per_second": 0.491,
      "step": 80
    },
    {
      "epoch": 0.24721878862793573,
      "grad_norm": 0.16177131235599518,
      "learning_rate": 9.866002634083497e-05,
      "loss": 0.0864,
      "step": 100
    },
    {
      "epoch": 0.24721878862793573,
      "eval_accuracy": 0.9381609426931211,
      "eval_balanced_accuracy": 0.9395669291338582,
      "eval_loss": 0.08397365361452103,
      "eval_macro_f1": 0.9380687925372826,
      "eval_runtime": 316.3562,
      "eval_samples_per_second": 31.386,
      "eval_steps_per_second": 0.493,
      "step": 100
    }
  ],
  "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": 0
      }
    },
    "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
}