{
  "best_global_step": 1000,
  "best_metric": 0.9613078781032101,
  "best_model_checkpoint": "taskA-unixcoder-focal/checkpoint-1000",
  "epoch": 0.064,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00064,
      "grad_norm": 3.3732223510742188,
      "learning_rate": 9.6e-08,
      "loss": 0.2065,
      "step": 10
    },
    {
      "epoch": 0.00128,
      "grad_norm": 2.8028833866119385,
      "learning_rate": 2.0266666666666668e-07,
      "loss": 0.2003,
      "step": 20
    },
    {
      "epoch": 0.00192,
      "grad_norm": 3.137962818145752,
      "learning_rate": 3.0933333333333335e-07,
      "loss": 0.2119,
      "step": 30
    },
    {
      "epoch": 0.00256,
      "grad_norm": 2.2841057777404785,
      "learning_rate": 4.16e-07,
      "loss": 0.1858,
      "step": 40
    },
    {
      "epoch": 0.0032,
      "grad_norm": 2.4040842056274414,
      "learning_rate": 5.226666666666667e-07,
      "loss": 0.1755,
      "step": 50
    },
    {
      "epoch": 0.00384,
      "grad_norm": 2.1078808307647705,
      "learning_rate": 6.293333333333334e-07,
      "loss": 0.1836,
      "step": 60
    },
    {
      "epoch": 0.00448,
      "grad_norm": 2.1723551750183105,
      "learning_rate": 7.36e-07,
      "loss": 0.182,
      "step": 70
    },
    {
      "epoch": 0.00512,
      "grad_norm": 3.8697516918182373,
      "learning_rate": 8.426666666666668e-07,
      "loss": 0.1893,
      "step": 80
    },
    {
      "epoch": 0.00576,
      "grad_norm": 2.2711849212646484,
      "learning_rate": 9.493333333333334e-07,
      "loss": 0.1645,
      "step": 90
    },
    {
      "epoch": 0.0064,
      "grad_norm": 2.9138245582580566,
      "learning_rate": 1.0560000000000001e-06,
      "loss": 0.1753,
      "step": 100
    },
    {
      "epoch": 0.00704,
      "grad_norm": 2.136301279067993,
      "learning_rate": 1.1626666666666667e-06,
      "loss": 0.1639,
      "step": 110
    },
    {
      "epoch": 0.00768,
      "grad_norm": 3.216343641281128,
      "learning_rate": 1.2693333333333335e-06,
      "loss": 0.1623,
      "step": 120
    },
    {
      "epoch": 0.00832,
      "grad_norm": 3.192094326019287,
      "learning_rate": 1.376e-06,
      "loss": 0.1607,
      "step": 130
    },
    {
      "epoch": 0.00896,
      "grad_norm": 4.722238540649414,
      "learning_rate": 1.4826666666666666e-06,
      "loss": 0.1653,
      "step": 140
    },
    {
      "epoch": 0.0096,
      "grad_norm": 4.088972568511963,
      "learning_rate": 1.5893333333333336e-06,
      "loss": 0.1557,
      "step": 150
    },
    {
      "epoch": 0.01024,
      "grad_norm": 2.2773237228393555,
      "learning_rate": 1.6960000000000002e-06,
      "loss": 0.1634,
      "step": 160
    },
    {
      "epoch": 0.01088,
      "grad_norm": 2.53987193107605,
      "learning_rate": 1.8026666666666667e-06,
      "loss": 0.1435,
      "step": 170
    },
    {
      "epoch": 0.01152,
      "grad_norm": 3.688382387161255,
      "learning_rate": 1.9093333333333335e-06,
      "loss": 0.1396,
      "step": 180
    },
    {
      "epoch": 0.01216,
      "grad_norm": 1.8855538368225098,
      "learning_rate": 2.0160000000000003e-06,
      "loss": 0.1476,
      "step": 190
    },
    {
      "epoch": 0.0128,
      "grad_norm": 2.2272040843963623,
      "learning_rate": 2.1226666666666666e-06,
      "loss": 0.144,
      "step": 200
    },
    {
      "epoch": 0.01344,
      "grad_norm": 3.505934476852417,
      "learning_rate": 2.229333333333334e-06,
      "loss": 0.1306,
      "step": 210
    },
    {
      "epoch": 0.01408,
      "grad_norm": 1.8632491827011108,
      "learning_rate": 2.336e-06,
      "loss": 0.1504,
      "step": 220
    },
    {
      "epoch": 0.01472,
      "grad_norm": 2.191713333129883,
      "learning_rate": 2.442666666666667e-06,
      "loss": 0.1346,
      "step": 230
    },
    {
      "epoch": 0.01536,
      "grad_norm": 1.9042261838912964,
      "learning_rate": 2.5493333333333337e-06,
      "loss": 0.135,
      "step": 240
    },
    {
      "epoch": 0.016,
      "grad_norm": 2.266148090362549,
      "learning_rate": 2.656e-06,
      "loss": 0.1356,
      "step": 250
    },
    {
      "epoch": 0.01664,
      "grad_norm": 2.4776418209075928,
      "learning_rate": 2.762666666666667e-06,
      "loss": 0.129,
      "step": 260
    },
    {
      "epoch": 0.01728,
      "grad_norm": 2.340693712234497,
      "learning_rate": 2.8693333333333336e-06,
      "loss": 0.1236,
      "step": 270
    },
    {
      "epoch": 0.01792,
      "grad_norm": 1.6849262714385986,
      "learning_rate": 2.976e-06,
      "loss": 0.1152,
      "step": 280
    },
    {
      "epoch": 0.01856,
      "grad_norm": 3.5535154342651367,
      "learning_rate": 3.082666666666667e-06,
      "loss": 0.1335,
      "step": 290
    },
    {
      "epoch": 0.0192,
      "grad_norm": 2.9307031631469727,
      "learning_rate": 3.1893333333333335e-06,
      "loss": 0.1136,
      "step": 300
    },
    {
      "epoch": 0.01984,
      "grad_norm": 3.0100226402282715,
      "learning_rate": 3.2960000000000003e-06,
      "loss": 0.1186,
      "step": 310
    },
    {
      "epoch": 0.02048,
      "grad_norm": 2.088911771774292,
      "learning_rate": 3.402666666666667e-06,
      "loss": 0.1051,
      "step": 320
    },
    {
      "epoch": 0.02112,
      "grad_norm": 4.332556247711182,
      "learning_rate": 3.5093333333333334e-06,
      "loss": 0.1075,
      "step": 330
    },
    {
      "epoch": 0.02176,
      "grad_norm": 2.954036235809326,
      "learning_rate": 3.616e-06,
      "loss": 0.11,
      "step": 340
    },
    {
      "epoch": 0.0224,
      "grad_norm": 2.262308359146118,
      "learning_rate": 3.7226666666666674e-06,
      "loss": 0.1057,
      "step": 350
    },
    {
      "epoch": 0.02304,
      "grad_norm": 1.5145989656448364,
      "learning_rate": 3.829333333333334e-06,
      "loss": 0.1049,
      "step": 360
    },
    {
      "epoch": 0.02368,
      "grad_norm": 1.740663766860962,
      "learning_rate": 3.936e-06,
      "loss": 0.0964,
      "step": 370
    },
    {
      "epoch": 0.02432,
      "grad_norm": 1.7438851594924927,
      "learning_rate": 4.042666666666667e-06,
      "loss": 0.0936,
      "step": 380
    },
    {
      "epoch": 0.02496,
      "grad_norm": 3.946115493774414,
      "learning_rate": 4.149333333333334e-06,
      "loss": 0.1038,
      "step": 390
    },
    {
      "epoch": 0.0256,
      "grad_norm": 5.289428234100342,
      "learning_rate": 4.256e-06,
      "loss": 0.1015,
      "step": 400
    },
    {
      "epoch": 0.02624,
      "grad_norm": 1.9344863891601562,
      "learning_rate": 4.362666666666667e-06,
      "loss": 0.0855,
      "step": 410
    },
    {
      "epoch": 0.02688,
      "grad_norm": 7.482412338256836,
      "learning_rate": 4.469333333333334e-06,
      "loss": 0.1031,
      "step": 420
    },
    {
      "epoch": 0.02752,
      "grad_norm": 2.5646328926086426,
      "learning_rate": 4.576000000000001e-06,
      "loss": 0.0777,
      "step": 430
    },
    {
      "epoch": 0.02816,
      "grad_norm": 1.473496437072754,
      "learning_rate": 4.682666666666667e-06,
      "loss": 0.0854,
      "step": 440
    },
    {
      "epoch": 0.0288,
      "grad_norm": 2.204341411590576,
      "learning_rate": 4.7893333333333334e-06,
      "loss": 0.0739,
      "step": 450
    },
    {
      "epoch": 0.02944,
      "grad_norm": 3.1363987922668457,
      "learning_rate": 4.896e-06,
      "loss": 0.0886,
      "step": 460
    },
    {
      "epoch": 0.03008,
      "grad_norm": 2.0473029613494873,
      "learning_rate": 5.002666666666667e-06,
      "loss": 0.0794,
      "step": 470
    },
    {
      "epoch": 0.03072,
      "grad_norm": 1.6088207960128784,
      "learning_rate": 5.109333333333334e-06,
      "loss": 0.0604,
      "step": 480
    },
    {
      "epoch": 0.03136,
      "grad_norm": 2.974717617034912,
      "learning_rate": 5.216e-06,
      "loss": 0.0827,
      "step": 490
    },
    {
      "epoch": 0.032,
      "grad_norm": 6.114630699157715,
      "learning_rate": 5.322666666666667e-06,
      "loss": 0.0631,
      "step": 500
    },
    {
      "epoch": 0.032,
      "eval_accuracy": 0.88603,
      "eval_f1_weighted": 0.8857328199768308,
      "eval_loss": 0.08366190642118454,
      "eval_macro_f1": 0.8859061279979327,
      "eval_precision": 0.8966428429175579,
      "eval_recall": 0.88603,
      "eval_runtime": 1629.6546,
      "eval_samples_per_second": 61.363,
      "eval_steps_per_second": 0.959,
      "step": 500
    },
    {
      "epoch": 0.03264,
      "grad_norm": 1.4639947414398193,
      "learning_rate": 5.429333333333334e-06,
      "loss": 0.0724,
      "step": 510
    },
    {
      "epoch": 0.03328,
      "grad_norm": 4.234114646911621,
      "learning_rate": 5.536e-06,
      "loss": 0.0737,
      "step": 520
    },
    {
      "epoch": 0.03392,
      "grad_norm": 1.9391822814941406,
      "learning_rate": 5.642666666666668e-06,
      "loss": 0.0875,
      "step": 530
    },
    {
      "epoch": 0.03456,
      "grad_norm": 2.0388095378875732,
      "learning_rate": 5.7493333333333336e-06,
      "loss": 0.0661,
      "step": 540
    },
    {
      "epoch": 0.0352,
      "grad_norm": 1.9697074890136719,
      "learning_rate": 5.856e-06,
      "loss": 0.0647,
      "step": 550
    },
    {
      "epoch": 0.03584,
      "grad_norm": 3.9906229972839355,
      "learning_rate": 5.962666666666666e-06,
      "loss": 0.0696,
      "step": 560
    },
    {
      "epoch": 0.03648,
      "grad_norm": 1.5516153573989868,
      "learning_rate": 6.069333333333334e-06,
      "loss": 0.0576,
      "step": 570
    },
    {
      "epoch": 0.03712,
      "grad_norm": 3.5216825008392334,
      "learning_rate": 6.176000000000001e-06,
      "loss": 0.0793,
      "step": 580
    },
    {
      "epoch": 0.03776,
      "grad_norm": 6.22791051864624,
      "learning_rate": 6.282666666666667e-06,
      "loss": 0.0757,
      "step": 590
    },
    {
      "epoch": 0.0384,
      "grad_norm": 1.8255369663238525,
      "learning_rate": 6.389333333333334e-06,
      "loss": 0.0602,
      "step": 600
    },
    {
      "epoch": 0.03904,
      "grad_norm": 2.506188154220581,
      "learning_rate": 6.496e-06,
      "loss": 0.0643,
      "step": 610
    },
    {
      "epoch": 0.03968,
      "grad_norm": 1.5877528190612793,
      "learning_rate": 6.602666666666667e-06,
      "loss": 0.0501,
      "step": 620
    },
    {
      "epoch": 0.04032,
      "grad_norm": 2.1468632221221924,
      "learning_rate": 6.7093333333333345e-06,
      "loss": 0.0521,
      "step": 630
    },
    {
      "epoch": 0.04096,
      "grad_norm": 2.6225597858428955,
      "learning_rate": 6.8160000000000005e-06,
      "loss": 0.068,
      "step": 640
    },
    {
      "epoch": 0.0416,
      "grad_norm": 3.1171772480010986,
      "learning_rate": 6.922666666666667e-06,
      "loss": 0.0644,
      "step": 650
    },
    {
      "epoch": 0.04224,
      "grad_norm": 2.7589240074157715,
      "learning_rate": 7.029333333333333e-06,
      "loss": 0.0763,
      "step": 660
    },
    {
      "epoch": 0.04288,
      "grad_norm": 2.3155124187469482,
      "learning_rate": 7.136000000000001e-06,
      "loss": 0.0451,
      "step": 670
    },
    {
      "epoch": 0.04352,
      "grad_norm": 0.9795209169387817,
      "learning_rate": 7.242666666666667e-06,
      "loss": 0.0552,
      "step": 680
    },
    {
      "epoch": 0.04416,
      "grad_norm": 6.224135398864746,
      "learning_rate": 7.3493333333333335e-06,
      "loss": 0.0614,
      "step": 690
    },
    {
      "epoch": 0.0448,
      "grad_norm": 1.9188823699951172,
      "learning_rate": 7.456000000000001e-06,
      "loss": 0.0539,
      "step": 700
    },
    {
      "epoch": 0.04544,
      "grad_norm": 2.0834364891052246,
      "learning_rate": 7.562666666666667e-06,
      "loss": 0.0545,
      "step": 710
    },
    {
      "epoch": 0.04608,
      "grad_norm": 2.081609010696411,
      "learning_rate": 7.669333333333335e-06,
      "loss": 0.0563,
      "step": 720
    },
    {
      "epoch": 0.04672,
      "grad_norm": 1.461228370666504,
      "learning_rate": 7.776e-06,
      "loss": 0.0495,
      "step": 730
    },
    {
      "epoch": 0.04736,
      "grad_norm": 2.7746951580047607,
      "learning_rate": 7.882666666666667e-06,
      "loss": 0.0517,
      "step": 740
    },
    {
      "epoch": 0.048,
      "grad_norm": 1.2801299095153809,
      "learning_rate": 7.989333333333335e-06,
      "loss": 0.034,
      "step": 750
    },
    {
      "epoch": 0.04864,
      "grad_norm": 3.921491861343384,
      "learning_rate": 8.096e-06,
      "loss": 0.0537,
      "step": 760
    },
    {
      "epoch": 0.04928,
      "grad_norm": 1.9986109733581543,
      "learning_rate": 8.202666666666667e-06,
      "loss": 0.0444,
      "step": 770
    },
    {
      "epoch": 0.04992,
      "grad_norm": 4.678001403808594,
      "learning_rate": 8.309333333333334e-06,
      "loss": 0.0589,
      "step": 780
    },
    {
      "epoch": 0.05056,
      "grad_norm": 1.7302327156066895,
      "learning_rate": 8.416e-06,
      "loss": 0.043,
      "step": 790
    },
    {
      "epoch": 0.0512,
      "grad_norm": 2.5643601417541504,
      "learning_rate": 8.522666666666667e-06,
      "loss": 0.0671,
      "step": 800
    },
    {
      "epoch": 0.05184,
      "grad_norm": 2.8869082927703857,
      "learning_rate": 8.629333333333334e-06,
      "loss": 0.0565,
      "step": 810
    },
    {
      "epoch": 0.05248,
      "grad_norm": 3.723088264465332,
      "learning_rate": 8.736e-06,
      "loss": 0.0428,
      "step": 820
    },
    {
      "epoch": 0.05312,
      "grad_norm": 4.387404441833496,
      "learning_rate": 8.842666666666667e-06,
      "loss": 0.0559,
      "step": 830
    },
    {
      "epoch": 0.05376,
      "grad_norm": 1.889413833618164,
      "learning_rate": 8.949333333333334e-06,
      "loss": 0.0405,
      "step": 840
    },
    {
      "epoch": 0.0544,
      "grad_norm": 1.4773402214050293,
      "learning_rate": 9.056000000000001e-06,
      "loss": 0.0414,
      "step": 850
    },
    {
      "epoch": 0.05504,
      "grad_norm": 0.4495583176612854,
      "learning_rate": 9.162666666666668e-06,
      "loss": 0.0446,
      "step": 860
    },
    {
      "epoch": 0.05568,
      "grad_norm": 1.158181071281433,
      "learning_rate": 9.269333333333335e-06,
      "loss": 0.0432,
      "step": 870
    },
    {
      "epoch": 0.05632,
      "grad_norm": 2.434063196182251,
      "learning_rate": 9.376000000000001e-06,
      "loss": 0.0502,
      "step": 880
    },
    {
      "epoch": 0.05696,
      "grad_norm": 1.2009385824203491,
      "learning_rate": 9.482666666666668e-06,
      "loss": 0.0473,
      "step": 890
    },
    {
      "epoch": 0.0576,
      "grad_norm": 3.9361023902893066,
      "learning_rate": 9.589333333333333e-06,
      "loss": 0.046,
      "step": 900
    },
    {
      "epoch": 0.05824,
      "grad_norm": 2.926988124847412,
      "learning_rate": 9.696000000000002e-06,
      "loss": 0.0464,
      "step": 910
    },
    {
      "epoch": 0.05888,
      "grad_norm": 2.215726375579834,
      "learning_rate": 9.802666666666667e-06,
      "loss": 0.0471,
      "step": 920
    },
    {
      "epoch": 0.05952,
      "grad_norm": 2.4104645252227783,
      "learning_rate": 9.909333333333334e-06,
      "loss": 0.0482,
      "step": 930
    },
    {
      "epoch": 0.06016,
      "grad_norm": 5.664385795593262,
      "learning_rate": 1.0016000000000002e-05,
      "loss": 0.044,
      "step": 940
    },
    {
      "epoch": 0.0608,
      "grad_norm": 1.7977851629257202,
      "learning_rate": 1.0122666666666667e-05,
      "loss": 0.0429,
      "step": 950
    },
    {
      "epoch": 0.06144,
      "grad_norm": 2.953789472579956,
      "learning_rate": 1.0229333333333334e-05,
      "loss": 0.0533,
      "step": 960
    },
    {
      "epoch": 0.06208,
      "grad_norm": 1.6272608041763306,
      "learning_rate": 1.0336000000000002e-05,
      "loss": 0.0307,
      "step": 970
    },
    {
      "epoch": 0.06272,
      "grad_norm": 2.8621678352355957,
      "learning_rate": 1.0442666666666667e-05,
      "loss": 0.0461,
      "step": 980
    },
    {
      "epoch": 0.06336,
      "grad_norm": 3.70019793510437,
      "learning_rate": 1.0549333333333334e-05,
      "loss": 0.0546,
      "step": 990
    },
    {
      "epoch": 0.064,
      "grad_norm": 1.1777608394622803,
      "learning_rate": 1.0656000000000003e-05,
      "loss": 0.0508,
      "step": 1000
    },
    {
      "epoch": 0.064,
      "eval_accuracy": 0.96139,
      "eval_f1_weighted": 0.9613900534763816,
      "eval_loss": 0.031560152769088745,
      "eval_macro_f1": 0.9613078781032101,
      "eval_precision": 0.9613901086866451,
      "eval_recall": 0.96139,
      "eval_runtime": 1630.3285,
      "eval_samples_per_second": 61.337,
      "eval_steps_per_second": 0.959,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 15625,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 8415459105720960.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}