{
  "best_global_step": 100,
  "best_metric": 0.4344141185283661,
  "best_model_checkpoint": "./qwen_coder_results/checkpoint-100",
  "epoch": 0.35555555555555557,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0035555555555555557,
      "grad_norm": 0.9296601414680481,
      "learning_rate": 0.0,
      "loss": 0.9575080871582031,
      "step": 1
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 0.47108322381973267,
      "learning_rate": 0.0001994398216007982,
      "loss": 0.6088941891988119,
      "step": 25
    },
    {
      "epoch": 0.08888888888888889,
      "eval_loss": 0.5020237565040588,
      "eval_runtime": 853.513,
      "eval_samples_per_second": 0.586,
      "eval_steps_per_second": 0.293,
      "step": 25
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 0.43385034799575806,
      "learning_rate": 0.0001921040354671897,
      "loss": 0.46405830383300783,
      "step": 50
    },
    {
      "epoch": 0.17777777777777778,
      "eval_loss": 0.4648200273513794,
      "eval_runtime": 852.8241,
      "eval_samples_per_second": 0.586,
      "eval_steps_per_second": 0.293,
      "step": 50
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.385348379611969,
      "learning_rate": 0.00017685596144214108,
      "loss": 0.4479352951049805,
      "step": 75
    },
    {
      "epoch": 0.26666666666666666,
      "eval_loss": 0.44333434104919434,
      "eval_runtime": 855.082,
      "eval_samples_per_second": 0.585,
      "eval_steps_per_second": 0.292,
      "step": 75
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.33071649074554443,
      "learning_rate": 0.00015500550034448413,
      "loss": 0.42900867462158204,
      "step": 100
    },
    {
      "epoch": 0.35555555555555557,
      "eval_loss": 0.4344141185283661,
      "eval_runtime": 855.1679,
      "eval_samples_per_second": 0.585,
      "eval_steps_per_second": 0.292,
      "step": 100
    }
  ],
  "logging_steps": 25,
  "max_steps": 282,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "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": 1.1711404920489984e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}