{
  "best_global_step": 244,
  "best_metric": 0.2577258348464966,
  "best_model_checkpoint": "lora_qwen7b_java_adiff_v2/checkpoint-244",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 244,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.041109969167523124,
      "grad_norm": 0.19480174779891968,
      "learning_rate": 3.648648648648649e-06,
      "loss": 0.5966,
      "step": 10
    },
    {
      "epoch": 0.08221993833504625,
      "grad_norm": 0.15218280255794525,
      "learning_rate": 7.702702702702703e-06,
      "loss": 0.5917,
      "step": 20
    },
    {
      "epoch": 0.12332990750256938,
      "grad_norm": 0.19138699769973755,
      "learning_rate": 1.1756756756756757e-05,
      "loss": 0.566,
      "step": 30
    },
    {
      "epoch": 0.1644398766700925,
      "grad_norm": 0.3009093403816223,
      "learning_rate": 1.5810810810810808e-05,
      "loss": 0.5276,
      "step": 40
    },
    {
      "epoch": 0.20554984583761562,
      "grad_norm": 0.2303069680929184,
      "learning_rate": 1.9864864864864866e-05,
      "loss": 0.4148,
      "step": 50
    },
    {
      "epoch": 0.24665981500513876,
      "grad_norm": 0.10509632527828217,
      "learning_rate": 2.3918918918918917e-05,
      "loss": 0.344,
      "step": 60
    },
    {
      "epoch": 0.28776978417266186,
      "grad_norm": 0.09443257004022598,
      "learning_rate": 2.7972972972972975e-05,
      "loss": 0.3244,
      "step": 70
    },
    {
      "epoch": 0.328879753340185,
      "grad_norm": 0.07592365890741348,
      "learning_rate": 2.9772036474164135e-05,
      "loss": 0.3107,
      "step": 80
    },
    {
      "epoch": 0.3699897225077081,
      "grad_norm": 0.06483208388090134,
      "learning_rate": 2.9316109422492404e-05,
      "loss": 0.2978,
      "step": 90
    },
    {
      "epoch": 0.41109969167523125,
      "grad_norm": 0.07318229973316193,
      "learning_rate": 2.886018237082067e-05,
      "loss": 0.2807,
      "step": 100
    },
    {
      "epoch": 0.4522096608427544,
      "grad_norm": 0.07056762278079987,
      "learning_rate": 2.8404255319148935e-05,
      "loss": 0.2844,
      "step": 110
    },
    {
      "epoch": 0.4933196300102775,
      "grad_norm": 0.0744948536157608,
      "learning_rate": 2.7948328267477204e-05,
      "loss": 0.2819,
      "step": 120
    },
    {
      "epoch": 0.5344295991778006,
      "grad_norm": 0.06527914851903915,
      "learning_rate": 2.7492401215805473e-05,
      "loss": 0.2682,
      "step": 130
    },
    {
      "epoch": 0.5755395683453237,
      "grad_norm": 0.0773576870560646,
      "learning_rate": 2.7036474164133738e-05,
      "loss": 0.2673,
      "step": 140
    },
    {
      "epoch": 0.6166495375128469,
      "grad_norm": 0.06686092913150787,
      "learning_rate": 2.6580547112462007e-05,
      "loss": 0.2675,
      "step": 150
    },
    {
      "epoch": 0.65775950668037,
      "grad_norm": 0.10009180009365082,
      "learning_rate": 2.6124620060790272e-05,
      "loss": 0.2597,
      "step": 160
    },
    {
      "epoch": 0.6988694758478932,
      "grad_norm": 0.08303786814212799,
      "learning_rate": 2.566869300911854e-05,
      "loss": 0.2582,
      "step": 170
    },
    {
      "epoch": 0.7399794450154162,
      "grad_norm": 0.10950975120067596,
      "learning_rate": 2.521276595744681e-05,
      "loss": 0.2513,
      "step": 180
    },
    {
      "epoch": 0.7810894141829393,
      "grad_norm": 0.09281215071678162,
      "learning_rate": 2.4756838905775076e-05,
      "loss": 0.2579,
      "step": 190
    },
    {
      "epoch": 0.8221993833504625,
      "grad_norm": 0.11291969567537308,
      "learning_rate": 2.4300911854103345e-05,
      "loss": 0.2638,
      "step": 200
    },
    {
      "epoch": 0.8633093525179856,
      "grad_norm": 0.09836319833993912,
      "learning_rate": 2.3844984802431613e-05,
      "loss": 0.247,
      "step": 210
    },
    {
      "epoch": 0.9044193216855088,
      "grad_norm": 0.11001324653625488,
      "learning_rate": 2.338905775075988e-05,
      "loss": 0.2478,
      "step": 220
    },
    {
      "epoch": 0.9455292908530318,
      "grad_norm": 0.109553761780262,
      "learning_rate": 2.2933130699088144e-05,
      "loss": 0.2347,
      "step": 230
    },
    {
      "epoch": 0.986639260020555,
      "grad_norm": 0.18094155192375183,
      "learning_rate": 2.2477203647416413e-05,
      "loss": 0.2381,
      "step": 240
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.2577258348464966,
      "eval_runtime": 47.9357,
      "eval_samples_per_second": 13.602,
      "eval_steps_per_second": 3.4,
      "step": 244
    }
  ],
  "logging_steps": 10,
  "max_steps": 732,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.303280380444549e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}