{
  "best_global_step": 229,
  "best_metric": 0.22333618998527527,
  "best_model_checkpoint": "./lora_qwen7b_python_abdiff_v1/checkpoint-229",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 687,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.043835616438356165,
      "grad_norm": 0.210234135389328,
      "learning_rate": 3.913043478260869e-06,
      "loss": 0.6169,
      "step": 10
    },
    {
      "epoch": 0.08767123287671233,
      "grad_norm": 0.25168153643608093,
      "learning_rate": 8.260869565217392e-06,
      "loss": 0.6133,
      "step": 20
    },
    {
      "epoch": 0.13150684931506848,
      "grad_norm": 0.19567625224590302,
      "learning_rate": 1.2608695652173912e-05,
      "loss": 0.5688,
      "step": 30
    },
    {
      "epoch": 0.17534246575342466,
      "grad_norm": 0.30335545539855957,
      "learning_rate": 1.6956521739130433e-05,
      "loss": 0.5225,
      "step": 40
    },
    {
      "epoch": 0.2191780821917808,
      "grad_norm": 0.24670398235321045,
      "learning_rate": 2.1304347826086958e-05,
      "loss": 0.3971,
      "step": 50
    },
    {
      "epoch": 0.26301369863013696,
      "grad_norm": 0.12593719363212585,
      "learning_rate": 2.565217391304348e-05,
      "loss": 0.2952,
      "step": 60
    },
    {
      "epoch": 0.30684931506849317,
      "grad_norm": 0.11282460391521454,
      "learning_rate": 3e-05,
      "loss": 0.2592,
      "step": 70
    },
    {
      "epoch": 0.3506849315068493,
      "grad_norm": 0.10163664072751999,
      "learning_rate": 2.9514563106796115e-05,
      "loss": 0.2402,
      "step": 80
    },
    {
      "epoch": 0.39452054794520547,
      "grad_norm": 0.09871397167444229,
      "learning_rate": 2.9029126213592237e-05,
      "loss": 0.2251,
      "step": 90
    },
    {
      "epoch": 0.4383561643835616,
      "grad_norm": 0.09532774984836578,
      "learning_rate": 2.854368932038835e-05,
      "loss": 0.2132,
      "step": 100
    },
    {
      "epoch": 0.4821917808219178,
      "grad_norm": 0.08755984157323837,
      "learning_rate": 2.8058252427184466e-05,
      "loss": 0.2086,
      "step": 110
    },
    {
      "epoch": 0.5260273972602739,
      "grad_norm": 0.09590521454811096,
      "learning_rate": 2.757281553398058e-05,
      "loss": 0.198,
      "step": 120
    },
    {
      "epoch": 0.5698630136986301,
      "grad_norm": 0.09363297373056412,
      "learning_rate": 2.7087378640776702e-05,
      "loss": 0.1954,
      "step": 130
    },
    {
      "epoch": 0.6136986301369863,
      "grad_norm": 0.09872984886169434,
      "learning_rate": 2.6601941747572816e-05,
      "loss": 0.1902,
      "step": 140
    },
    {
      "epoch": 0.6575342465753424,
      "grad_norm": 0.12371695041656494,
      "learning_rate": 2.611650485436893e-05,
      "loss": 0.1892,
      "step": 150
    },
    {
      "epoch": 0.7013698630136986,
      "grad_norm": 0.10814935714006424,
      "learning_rate": 2.563106796116505e-05,
      "loss": 0.1808,
      "step": 160
    },
    {
      "epoch": 0.7452054794520548,
      "grad_norm": 0.12739220261573792,
      "learning_rate": 2.5145631067961167e-05,
      "loss": 0.1815,
      "step": 170
    },
    {
      "epoch": 0.7890410958904109,
      "grad_norm": 0.1482655555009842,
      "learning_rate": 2.466019417475728e-05,
      "loss": 0.1652,
      "step": 180
    },
    {
      "epoch": 0.8328767123287671,
      "grad_norm": 0.13323327898979187,
      "learning_rate": 2.41747572815534e-05,
      "loss": 0.1663,
      "step": 190
    },
    {
      "epoch": 0.8767123287671232,
      "grad_norm": 0.1497439742088318,
      "learning_rate": 2.3689320388349514e-05,
      "loss": 0.1693,
      "step": 200
    },
    {
      "epoch": 0.9205479452054794,
      "grad_norm": 0.16727504134178162,
      "learning_rate": 2.3203883495145632e-05,
      "loss": 0.1588,
      "step": 210
    },
    {
      "epoch": 0.9643835616438357,
      "grad_norm": 0.159692645072937,
      "learning_rate": 2.2718446601941746e-05,
      "loss": 0.1489,
      "step": 220
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.22333618998527527,
      "eval_runtime": 65.6094,
      "eval_samples_per_second": 18.808,
      "eval_steps_per_second": 9.404,
      "step": 229
    },
    {
      "epoch": 1.0043835616438357,
      "grad_norm": 0.18387436866760254,
      "learning_rate": 2.2233009708737864e-05,
      "loss": 0.1542,
      "step": 230
    },
    {
      "epoch": 1.0482191780821917,
      "grad_norm": 0.17115731537342072,
      "learning_rate": 2.1747572815533982e-05,
      "loss": 0.1419,
      "step": 240
    },
    {
      "epoch": 1.0920547945205479,
      "grad_norm": 0.20462283492088318,
      "learning_rate": 2.1262135922330097e-05,
      "loss": 0.1291,
      "step": 250
    },
    {
      "epoch": 1.135890410958904,
      "grad_norm": 0.21275432407855988,
      "learning_rate": 2.0776699029126215e-05,
      "loss": 0.1345,
      "step": 260
    },
    {
      "epoch": 1.1797260273972603,
      "grad_norm": 0.19069133698940277,
      "learning_rate": 2.029126213592233e-05,
      "loss": 0.1304,
      "step": 270
    },
    {
      "epoch": 1.2235616438356165,
      "grad_norm": 0.23898746073246002,
      "learning_rate": 1.9805825242718447e-05,
      "loss": 0.1286,
      "step": 280
    },
    {
      "epoch": 1.2673972602739725,
      "grad_norm": 0.22382740676403046,
      "learning_rate": 1.9320388349514565e-05,
      "loss": 0.1257,
      "step": 290
    },
    {
      "epoch": 1.3112328767123287,
      "grad_norm": 0.21581463515758514,
      "learning_rate": 1.883495145631068e-05,
      "loss": 0.1075,
      "step": 300
    },
    {
      "epoch": 1.355068493150685,
      "grad_norm": 0.20519264042377472,
      "learning_rate": 1.8349514563106795e-05,
      "loss": 0.114,
      "step": 310
    },
    {
      "epoch": 1.398904109589041,
      "grad_norm": 0.24191145598888397,
      "learning_rate": 1.7864077669902913e-05,
      "loss": 0.1084,
      "step": 320
    },
    {
      "epoch": 1.4427397260273973,
      "grad_norm": 0.2942422032356262,
      "learning_rate": 1.737864077669903e-05,
      "loss": 0.1169,
      "step": 330
    },
    {
      "epoch": 1.4865753424657533,
      "grad_norm": 0.29472362995147705,
      "learning_rate": 1.6893203883495145e-05,
      "loss": 0.1048,
      "step": 340
    },
    {
      "epoch": 1.5304109589041097,
      "grad_norm": 0.27294427156448364,
      "learning_rate": 1.6407766990291263e-05,
      "loss": 0.104,
      "step": 350
    },
    {
      "epoch": 1.5742465753424657,
      "grad_norm": 0.3031008243560791,
      "learning_rate": 1.592233009708738e-05,
      "loss": 0.1064,
      "step": 360
    },
    {
      "epoch": 1.618082191780822,
      "grad_norm": 0.3000255227088928,
      "learning_rate": 1.5436893203883496e-05,
      "loss": 0.0965,
      "step": 370
    },
    {
      "epoch": 1.6619178082191781,
      "grad_norm": 0.3417374789714813,
      "learning_rate": 1.4951456310679612e-05,
      "loss": 0.103,
      "step": 380
    },
    {
      "epoch": 1.705753424657534,
      "grad_norm": 0.260896235704422,
      "learning_rate": 1.4466019417475728e-05,
      "loss": 0.0949,
      "step": 390
    },
    {
      "epoch": 1.7495890410958905,
      "grad_norm": 0.3573839068412781,
      "learning_rate": 1.3980582524271846e-05,
      "loss": 0.1005,
      "step": 400
    },
    {
      "epoch": 1.7934246575342465,
      "grad_norm": 0.32356780767440796,
      "learning_rate": 1.349514563106796e-05,
      "loss": 0.0924,
      "step": 410
    },
    {
      "epoch": 1.8372602739726027,
      "grad_norm": 0.3374144434928894,
      "learning_rate": 1.3009708737864079e-05,
      "loss": 0.0962,
      "step": 420
    },
    {
      "epoch": 1.881095890410959,
      "grad_norm": 0.30275803804397583,
      "learning_rate": 1.2524271844660193e-05,
      "loss": 0.098,
      "step": 430
    },
    {
      "epoch": 1.924931506849315,
      "grad_norm": 0.2706526815891266,
      "learning_rate": 1.2038834951456311e-05,
      "loss": 0.093,
      "step": 440
    },
    {
      "epoch": 1.9687671232876713,
      "grad_norm": 0.30319514870643616,
      "learning_rate": 1.1553398058252427e-05,
      "loss": 0.0932,
      "step": 450
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.23950284719467163,
      "eval_runtime": 65.404,
      "eval_samples_per_second": 18.867,
      "eval_steps_per_second": 9.434,
      "step": 458
    },
    {
      "epoch": 2.0087671232876714,
      "grad_norm": 0.3190622627735138,
      "learning_rate": 1.1067961165048544e-05,
      "loss": 0.0796,
      "step": 460
    },
    {
      "epoch": 2.0526027397260274,
      "grad_norm": 0.20361511409282684,
      "learning_rate": 1.058252427184466e-05,
      "loss": 0.0852,
      "step": 470
    },
    {
      "epoch": 2.0964383561643833,
      "grad_norm": 0.29404351115226746,
      "learning_rate": 1.0097087378640776e-05,
      "loss": 0.0745,
      "step": 480
    },
    {
      "epoch": 2.1402739726027398,
      "grad_norm": 0.2433903068304062,
      "learning_rate": 9.611650485436894e-06,
      "loss": 0.0793,
      "step": 490
    },
    {
      "epoch": 2.1841095890410958,
      "grad_norm": 0.31765592098236084,
      "learning_rate": 9.12621359223301e-06,
      "loss": 0.086,
      "step": 500
    },
    {
      "epoch": 2.227945205479452,
      "grad_norm": 0.28951069712638855,
      "learning_rate": 8.640776699029127e-06,
      "loss": 0.0814,
      "step": 510
    },
    {
      "epoch": 2.271780821917808,
      "grad_norm": 0.3745494782924652,
      "learning_rate": 8.155339805825243e-06,
      "loss": 0.0856,
      "step": 520
    },
    {
      "epoch": 2.315616438356164,
      "grad_norm": 0.2525760531425476,
      "learning_rate": 7.66990291262136e-06,
      "loss": 0.078,
      "step": 530
    },
    {
      "epoch": 2.3594520547945206,
      "grad_norm": 0.2950601279735565,
      "learning_rate": 7.1844660194174755e-06,
      "loss": 0.0758,
      "step": 540
    },
    {
      "epoch": 2.4032876712328766,
      "grad_norm": 0.23691079020500183,
      "learning_rate": 6.699029126213593e-06,
      "loss": 0.0706,
      "step": 550
    },
    {
      "epoch": 2.447123287671233,
      "grad_norm": 0.2603223919868469,
      "learning_rate": 6.213592233009709e-06,
      "loss": 0.0711,
      "step": 560
    },
    {
      "epoch": 2.490958904109589,
      "grad_norm": 0.2159614861011505,
      "learning_rate": 5.728155339805826e-06,
      "loss": 0.075,
      "step": 570
    },
    {
      "epoch": 2.534794520547945,
      "grad_norm": 0.23896284401416779,
      "learning_rate": 5.242718446601942e-06,
      "loss": 0.0824,
      "step": 580
    },
    {
      "epoch": 2.5786301369863014,
      "grad_norm": 0.2901216149330139,
      "learning_rate": 4.7572815533980585e-06,
      "loss": 0.0903,
      "step": 590
    },
    {
      "epoch": 2.6224657534246574,
      "grad_norm": 0.29583826661109924,
      "learning_rate": 4.271844660194175e-06,
      "loss": 0.0796,
      "step": 600
    },
    {
      "epoch": 2.666301369863014,
      "grad_norm": 0.3026266098022461,
      "learning_rate": 3.7864077669902915e-06,
      "loss": 0.0733,
      "step": 610
    },
    {
      "epoch": 2.71013698630137,
      "grad_norm": 0.2562008202075958,
      "learning_rate": 3.3009708737864078e-06,
      "loss": 0.0797,
      "step": 620
    },
    {
      "epoch": 2.7539726027397258,
      "grad_norm": 0.30706337094306946,
      "learning_rate": 2.815533980582524e-06,
      "loss": 0.0755,
      "step": 630
    },
    {
      "epoch": 2.797808219178082,
      "grad_norm": 0.32250040769577026,
      "learning_rate": 2.3300970873786407e-06,
      "loss": 0.0717,
      "step": 640
    },
    {
      "epoch": 2.8416438356164386,
      "grad_norm": 0.301578164100647,
      "learning_rate": 1.8446601941747572e-06,
      "loss": 0.0663,
      "step": 650
    },
    {
      "epoch": 2.8854794520547946,
      "grad_norm": 0.26296401023864746,
      "learning_rate": 1.359223300970874e-06,
      "loss": 0.0817,
      "step": 660
    },
    {
      "epoch": 2.9293150684931506,
      "grad_norm": 0.32804426550865173,
      "learning_rate": 8.737864077669904e-07,
      "loss": 0.0778,
      "step": 670
    },
    {
      "epoch": 2.9731506849315066,
      "grad_norm": 0.3096996247768402,
      "learning_rate": 3.883495145631068e-07,
      "loss": 0.0776,
      "step": 680
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.2448684424161911,
      "eval_runtime": 65.3239,
      "eval_samples_per_second": 18.89,
      "eval_steps_per_second": 9.445,
      "step": 687
    }
  ],
  "logging_steps": 10,
  "max_steps": 687,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.379988366727496e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}