{
  "best_global_step": 244,
  "best_metric": 0.241361603140831,
  "best_model_checkpoint": "lora_qwen7b_java_abdiff_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": 0.17571452260017395,
      "learning_rate": 3.648648648648649e-06,
      "loss": 0.5537,
      "step": 10
    },
    {
      "epoch": 0.08221993833504625,
      "grad_norm": 0.12462153285741806,
      "learning_rate": 7.702702702702703e-06,
      "loss": 0.5427,
      "step": 20
    },
    {
      "epoch": 0.12332990750256938,
      "grad_norm": 0.13460873067378998,
      "learning_rate": 1.1756756756756757e-05,
      "loss": 0.5255,
      "step": 30
    },
    {
      "epoch": 0.1644398766700925,
      "grad_norm": 0.2371131032705307,
      "learning_rate": 1.5810810810810808e-05,
      "loss": 0.4849,
      "step": 40
    },
    {
      "epoch": 0.20554984583761562,
      "grad_norm": 0.2611907720565796,
      "learning_rate": 1.9864864864864866e-05,
      "loss": 0.3981,
      "step": 50
    },
    {
      "epoch": 0.24665981500513876,
      "grad_norm": 0.10762301832437515,
      "learning_rate": 2.3918918918918917e-05,
      "loss": 0.3275,
      "step": 60
    },
    {
      "epoch": 0.28776978417266186,
      "grad_norm": 0.06910783052444458,
      "learning_rate": 2.7972972972972975e-05,
      "loss": 0.2976,
      "step": 70
    },
    {
      "epoch": 0.328879753340185,
      "grad_norm": 0.10020674765110016,
      "learning_rate": 2.9772036474164135e-05,
      "loss": 0.2958,
      "step": 80
    },
    {
      "epoch": 0.3699897225077081,
      "grad_norm": 0.06338030099868774,
      "learning_rate": 2.9316109422492404e-05,
      "loss": 0.2775,
      "step": 90
    },
    {
      "epoch": 0.41109969167523125,
      "grad_norm": 0.06356582045555115,
      "learning_rate": 2.886018237082067e-05,
      "loss": 0.2671,
      "step": 100
    },
    {
      "epoch": 0.4522096608427544,
      "grad_norm": 0.06176166608929634,
      "learning_rate": 2.8404255319148935e-05,
      "loss": 0.273,
      "step": 110
    },
    {
      "epoch": 0.4933196300102775,
      "grad_norm": 0.0641980841755867,
      "learning_rate": 2.7948328267477204e-05,
      "loss": 0.2708,
      "step": 120
    },
    {
      "epoch": 0.5344295991778006,
      "grad_norm": 0.060578711330890656,
      "learning_rate": 2.7492401215805473e-05,
      "loss": 0.2492,
      "step": 130
    },
    {
      "epoch": 0.5755395683453237,
      "grad_norm": 0.07500634342432022,
      "learning_rate": 2.7036474164133738e-05,
      "loss": 0.2516,
      "step": 140
    },
    {
      "epoch": 0.6166495375128469,
      "grad_norm": 0.06346568465232849,
      "learning_rate": 2.6580547112462007e-05,
      "loss": 0.2423,
      "step": 150
    },
    {
      "epoch": 0.65775950668037,
      "grad_norm": 0.214496448636055,
      "learning_rate": 2.6124620060790272e-05,
      "loss": 0.245,
      "step": 160
    },
    {
      "epoch": 0.6988694758478932,
      "grad_norm": 0.07425080984830856,
      "learning_rate": 2.566869300911854e-05,
      "loss": 0.2455,
      "step": 170
    },
    {
      "epoch": 0.7399794450154162,
      "grad_norm": 0.08862721920013428,
      "learning_rate": 2.521276595744681e-05,
      "loss": 0.2377,
      "step": 180
    },
    {
      "epoch": 0.7810894141829393,
      "grad_norm": 0.09345080703496933,
      "learning_rate": 2.4756838905775076e-05,
      "loss": 0.2493,
      "step": 190
    },
    {
      "epoch": 0.8221993833504625,
      "grad_norm": 0.12085441499948502,
      "learning_rate": 2.4300911854103345e-05,
      "loss": 0.243,
      "step": 200
    },
    {
      "epoch": 0.8633093525179856,
      "grad_norm": 0.09944415092468262,
      "learning_rate": 2.3844984802431613e-05,
      "loss": 0.2276,
      "step": 210
    },
    {
      "epoch": 0.9044193216855088,
      "grad_norm": 0.11600342392921448,
      "learning_rate": 2.338905775075988e-05,
      "loss": 0.2288,
      "step": 220
    },
    {
      "epoch": 0.9455292908530318,
      "grad_norm": 0.11351948231458664,
      "learning_rate": 2.2933130699088144e-05,
      "loss": 0.2136,
      "step": 230
    },
    {
      "epoch": 0.986639260020555,
      "grad_norm": 0.12985852360725403,
      "learning_rate": 2.2477203647416413e-05,
      "loss": 0.2166,
      "step": 240
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.241361603140831,
      "eval_runtime": 48.3711,
      "eval_samples_per_second": 13.479,
      "eval_steps_per_second": 3.37,
      "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": 3.369854600141783e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}