{
  "best_global_step": 2049,
  "best_metric": 0.6610541727672035,
  "best_model_checkpoint": "./saved_models/graphcodebert/checkpoint-2049",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 3415,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07320644216691069,
      "grad_norm": 1.5853087902069092,
      "learning_rate": 1.971303074670571e-05,
      "loss": 0.6901,
      "step": 50
    },
    {
      "epoch": 0.14641288433382138,
      "grad_norm": 2.419438123703003,
      "learning_rate": 1.942020497803807e-05,
      "loss": 0.6902,
      "step": 100
    },
    {
      "epoch": 0.21961932650073207,
      "grad_norm": 1.6440658569335938,
      "learning_rate": 1.9127379209370426e-05,
      "loss": 0.685,
      "step": 150
    },
    {
      "epoch": 0.29282576866764276,
      "grad_norm": 1.883244514465332,
      "learning_rate": 1.8834553440702785e-05,
      "loss": 0.6857,
      "step": 200
    },
    {
      "epoch": 0.36603221083455345,
      "grad_norm": 3.6438748836517334,
      "learning_rate": 1.854172767203514e-05,
      "loss": 0.682,
      "step": 250
    },
    {
      "epoch": 0.43923865300146414,
      "grad_norm": 3.641892194747925,
      "learning_rate": 1.8248901903367496e-05,
      "loss": 0.6656,
      "step": 300
    },
    {
      "epoch": 0.5124450951683748,
      "grad_norm": 2.7403852939605713,
      "learning_rate": 1.7956076134699855e-05,
      "loss": 0.6656,
      "step": 350
    },
    {
      "epoch": 0.5856515373352855,
      "grad_norm": 1.8151828050613403,
      "learning_rate": 1.766325036603221e-05,
      "loss": 0.6762,
      "step": 400
    },
    {
      "epoch": 0.6588579795021962,
      "grad_norm": 2.336029291152954,
      "learning_rate": 1.737042459736457e-05,
      "loss": 0.6701,
      "step": 450
    },
    {
      "epoch": 0.7320644216691069,
      "grad_norm": 2.9843106269836426,
      "learning_rate": 1.7077598828696925e-05,
      "loss": 0.6661,
      "step": 500
    },
    {
      "epoch": 0.8052708638360175,
      "grad_norm": 2.4253265857696533,
      "learning_rate": 1.6784773060029284e-05,
      "loss": 0.6776,
      "step": 550
    },
    {
      "epoch": 0.8784773060029283,
      "grad_norm": 3.049626350402832,
      "learning_rate": 1.649194729136164e-05,
      "loss": 0.6626,
      "step": 600
    },
    {
      "epoch": 0.9516837481698389,
      "grad_norm": 2.690331220626831,
      "learning_rate": 1.6199121522694e-05,
      "loss": 0.658,
      "step": 650
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6332357247437774,
      "eval_loss": 0.6321774125099182,
      "eval_runtime": 11.6506,
      "eval_samples_per_second": 234.494,
      "eval_steps_per_second": 3.691,
      "step": 683
    },
    {
      "epoch": 1.0248901903367496,
      "grad_norm": 3.389944553375244,
      "learning_rate": 1.5906295754026355e-05,
      "loss": 0.645,
      "step": 700
    },
    {
      "epoch": 1.0980966325036603,
      "grad_norm": 2.976720094680786,
      "learning_rate": 1.5613469985358714e-05,
      "loss": 0.633,
      "step": 750
    },
    {
      "epoch": 1.171303074670571,
      "grad_norm": 3.046492576599121,
      "learning_rate": 1.532064421669107e-05,
      "loss": 0.63,
      "step": 800
    },
    {
      "epoch": 1.2445095168374818,
      "grad_norm": 2.867762804031372,
      "learning_rate": 1.5027818448023428e-05,
      "loss": 0.6293,
      "step": 850
    },
    {
      "epoch": 1.3177159590043923,
      "grad_norm": 3.334984064102173,
      "learning_rate": 1.4734992679355784e-05,
      "loss": 0.6251,
      "step": 900
    },
    {
      "epoch": 1.390922401171303,
      "grad_norm": 4.373927116394043,
      "learning_rate": 1.4442166910688143e-05,
      "loss": 0.6224,
      "step": 950
    },
    {
      "epoch": 1.4641288433382138,
      "grad_norm": 3.5130934715270996,
      "learning_rate": 1.4149341142020499e-05,
      "loss": 0.6182,
      "step": 1000
    },
    {
      "epoch": 1.5373352855051245,
      "grad_norm": 3.466965675354004,
      "learning_rate": 1.3856515373352856e-05,
      "loss": 0.6139,
      "step": 1050
    },
    {
      "epoch": 1.610541727672035,
      "grad_norm": 4.486567974090576,
      "learning_rate": 1.3563689604685213e-05,
      "loss": 0.6221,
      "step": 1100
    },
    {
      "epoch": 1.6837481698389458,
      "grad_norm": 3.9357879161834717,
      "learning_rate": 1.327086383601757e-05,
      "loss": 0.6185,
      "step": 1150
    },
    {
      "epoch": 1.7569546120058566,
      "grad_norm": 3.294029474258423,
      "learning_rate": 1.2978038067349928e-05,
      "loss": 0.6048,
      "step": 1200
    },
    {
      "epoch": 1.830161054172767,
      "grad_norm": 4.328296661376953,
      "learning_rate": 1.2685212298682286e-05,
      "loss": 0.6191,
      "step": 1250
    },
    {
      "epoch": 1.903367496339678,
      "grad_norm": 3.7641713619232178,
      "learning_rate": 1.2392386530014641e-05,
      "loss": 0.6028,
      "step": 1300
    },
    {
      "epoch": 1.9765739385065886,
      "grad_norm": 4.414918422698975,
      "learning_rate": 1.2099560761347e-05,
      "loss": 0.5892,
      "step": 1350
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.636896046852123,
      "eval_loss": 0.6083204746246338,
      "eval_runtime": 11.6592,
      "eval_samples_per_second": 234.32,
      "eval_steps_per_second": 3.688,
      "step": 1366
    },
    {
      "epoch": 2.049780380673499,
      "grad_norm": 5.577649116516113,
      "learning_rate": 1.1806734992679356e-05,
      "loss": 0.5804,
      "step": 1400
    },
    {
      "epoch": 2.12298682284041,
      "grad_norm": 5.713629722595215,
      "learning_rate": 1.1513909224011715e-05,
      "loss": 0.5494,
      "step": 1450
    },
    {
      "epoch": 2.1961932650073206,
      "grad_norm": 14.552216529846191,
      "learning_rate": 1.122108345534407e-05,
      "loss": 0.5611,
      "step": 1500
    },
    {
      "epoch": 2.269399707174231,
      "grad_norm": 4.35590124130249,
      "learning_rate": 1.092825768667643e-05,
      "loss": 0.5653,
      "step": 1550
    },
    {
      "epoch": 2.342606149341142,
      "grad_norm": 4.740884304046631,
      "learning_rate": 1.0635431918008785e-05,
      "loss": 0.5658,
      "step": 1600
    },
    {
      "epoch": 2.4158125915080526,
      "grad_norm": 6.103859901428223,
      "learning_rate": 1.0342606149341143e-05,
      "loss": 0.5605,
      "step": 1650
    },
    {
      "epoch": 2.4890190336749636,
      "grad_norm": 5.405401229858398,
      "learning_rate": 1.00497803806735e-05,
      "loss": 0.5657,
      "step": 1700
    },
    {
      "epoch": 2.562225475841874,
      "grad_norm": 5.416690349578857,
      "learning_rate": 9.756954612005857e-06,
      "loss": 0.545,
      "step": 1750
    },
    {
      "epoch": 2.6354319180087846,
      "grad_norm": 3.8133316040039062,
      "learning_rate": 9.464128843338215e-06,
      "loss": 0.5518,
      "step": 1800
    },
    {
      "epoch": 2.7086383601756956,
      "grad_norm": 11.942543029785156,
      "learning_rate": 9.171303074670572e-06,
      "loss": 0.5516,
      "step": 1850
    },
    {
      "epoch": 2.781844802342606,
      "grad_norm": 7.067141532897949,
      "learning_rate": 8.87847730600293e-06,
      "loss": 0.5597,
      "step": 1900
    },
    {
      "epoch": 2.855051244509517,
      "grad_norm": 5.501221656799316,
      "learning_rate": 8.585651537335287e-06,
      "loss": 0.536,
      "step": 1950
    },
    {
      "epoch": 2.9282576866764276,
      "grad_norm": 9.329773902893066,
      "learning_rate": 8.292825768667644e-06,
      "loss": 0.5298,
      "step": 2000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6610541727672035,
      "eval_loss": 0.6209500432014465,
      "eval_runtime": 11.6196,
      "eval_samples_per_second": 235.121,
      "eval_steps_per_second": 3.701,
      "step": 2049
    },
    {
      "epoch": 3.001464128843338,
      "grad_norm": 4.468164443969727,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.5594,
      "step": 2050
    },
    {
      "epoch": 3.074670571010249,
      "grad_norm": 6.163565158843994,
      "learning_rate": 7.707174231332359e-06,
      "loss": 0.488,
      "step": 2100
    },
    {
      "epoch": 3.1478770131771596,
      "grad_norm": 6.804717063903809,
      "learning_rate": 7.414348462664715e-06,
      "loss": 0.491,
      "step": 2150
    },
    {
      "epoch": 3.22108345534407,
      "grad_norm": 7.049874782562256,
      "learning_rate": 7.1215226939970725e-06,
      "loss": 0.4866,
      "step": 2200
    },
    {
      "epoch": 3.294289897510981,
      "grad_norm": 10.319636344909668,
      "learning_rate": 6.82869692532943e-06,
      "loss": 0.4837,
      "step": 2250
    },
    {
      "epoch": 3.3674963396778916,
      "grad_norm": 7.2100677490234375,
      "learning_rate": 6.535871156661787e-06,
      "loss": 0.4773,
      "step": 2300
    },
    {
      "epoch": 3.440702781844802,
      "grad_norm": 10.271724700927734,
      "learning_rate": 6.2430453879941446e-06,
      "loss": 0.5051,
      "step": 2350
    },
    {
      "epoch": 3.513909224011713,
      "grad_norm": 6.702558517456055,
      "learning_rate": 5.950219619326502e-06,
      "loss": 0.4979,
      "step": 2400
    },
    {
      "epoch": 3.5871156661786237,
      "grad_norm": 7.939746856689453,
      "learning_rate": 5.657393850658858e-06,
      "loss": 0.5013,
      "step": 2450
    },
    {
      "epoch": 3.660322108345534,
      "grad_norm": 7.762535095214844,
      "learning_rate": 5.364568081991216e-06,
      "loss": 0.4999,
      "step": 2500
    },
    {
      "epoch": 3.733528550512445,
      "grad_norm": 7.71613073348999,
      "learning_rate": 5.071742313323573e-06,
      "loss": 0.4935,
      "step": 2550
    },
    {
      "epoch": 3.8067349926793557,
      "grad_norm": 6.267000675201416,
      "learning_rate": 4.77891654465593e-06,
      "loss": 0.4855,
      "step": 2600
    },
    {
      "epoch": 3.8799414348462666,
      "grad_norm": 10.031179428100586,
      "learning_rate": 4.486090775988287e-06,
      "loss": 0.4932,
      "step": 2650
    },
    {
      "epoch": 3.953147877013177,
      "grad_norm": 5.606414794921875,
      "learning_rate": 4.193265007320644e-06,
      "loss": 0.4849,
      "step": 2700
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6442166910688141,
      "eval_loss": 0.6546101570129395,
      "eval_runtime": 11.6102,
      "eval_samples_per_second": 235.31,
      "eval_steps_per_second": 3.704,
      "step": 2732
    },
    {
      "epoch": 4.026354319180088,
      "grad_norm": 7.047442436218262,
      "learning_rate": 3.900439238653002e-06,
      "loss": 0.4756,
      "step": 2750
    },
    {
      "epoch": 4.099560761346998,
      "grad_norm": 8.444013595581055,
      "learning_rate": 3.607613469985359e-06,
      "loss": 0.4465,
      "step": 2800
    },
    {
      "epoch": 4.172767203513909,
      "grad_norm": 8.391129493713379,
      "learning_rate": 3.314787701317716e-06,
      "loss": 0.4532,
      "step": 2850
    },
    {
      "epoch": 4.24597364568082,
      "grad_norm": 8.165177345275879,
      "learning_rate": 3.0219619326500732e-06,
      "loss": 0.4591,
      "step": 2900
    },
    {
      "epoch": 4.31918008784773,
      "grad_norm": 10.9652099609375,
      "learning_rate": 2.7291361639824306e-06,
      "loss": 0.4126,
      "step": 2950
    },
    {
      "epoch": 4.392386530014641,
      "grad_norm": 7.355696201324463,
      "learning_rate": 2.436310395314788e-06,
      "loss": 0.4195,
      "step": 3000
    },
    {
      "epoch": 4.465592972181552,
      "grad_norm": 9.898347854614258,
      "learning_rate": 2.1434846266471453e-06,
      "loss": 0.4476,
      "step": 3050
    },
    {
      "epoch": 4.538799414348462,
      "grad_norm": 12.907100677490234,
      "learning_rate": 1.8506588579795024e-06,
      "loss": 0.441,
      "step": 3100
    },
    {
      "epoch": 4.612005856515373,
      "grad_norm": 6.766877174377441,
      "learning_rate": 1.5578330893118595e-06,
      "loss": 0.4316,
      "step": 3150
    },
    {
      "epoch": 4.685212298682284,
      "grad_norm": 6.144525527954102,
      "learning_rate": 1.2650073206442169e-06,
      "loss": 0.4415,
      "step": 3200
    },
    {
      "epoch": 4.758418740849194,
      "grad_norm": 12.745665550231934,
      "learning_rate": 9.72181551976574e-07,
      "loss": 0.4525,
      "step": 3250
    },
    {
      "epoch": 4.831625183016105,
      "grad_norm": 8.909607887268066,
      "learning_rate": 6.793557833089313e-07,
      "loss": 0.4426,
      "step": 3300
    },
    {
      "epoch": 4.904831625183016,
      "grad_norm": 8.444921493530273,
      "learning_rate": 3.865300146412885e-07,
      "loss": 0.4379,
      "step": 3350
    },
    {
      "epoch": 4.978038067349927,
      "grad_norm": 9.61002254486084,
      "learning_rate": 9.370424597364569e-08,
      "loss": 0.4603,
      "step": 3400
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6548316251830161,
      "eval_loss": 0.687939465045929,
      "eval_runtime": 11.6277,
      "eval_samples_per_second": 234.957,
      "eval_steps_per_second": 3.698,
      "step": 3415
    }
  ],
  "logging_steps": 50,
  "max_steps": 3415,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 1.43750725095936e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}