| { |
| "best_global_step": 200, |
| "best_metric": 0.5962545254252696, |
| "best_model_checkpoint": "output_checkpoints/graphcodebert-vanilla/checkpoint-200", |
| "epoch": 0.29354207436399216, |
| "eval_steps": 50, |
| "global_step": 300, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.004892367906066536, |
| "grad_norm": 33435.953125, |
| "learning_rate": 1.3071895424836603e-07, |
| "loss": 0.7006, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.009784735812133072, |
| "grad_norm": 34831.7421875, |
| "learning_rate": 2.9411764705882356e-07, |
| "loss": 0.7023, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.014677103718199608, |
| "grad_norm": 32986.62109375, |
| "learning_rate": 4.5751633986928105e-07, |
| "loss": 0.7019, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.019569471624266144, |
| "grad_norm": 34257.4921875, |
| "learning_rate": 6.209150326797386e-07, |
| "loss": 0.7025, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.02446183953033268, |
| "grad_norm": 35511.3359375, |
| "learning_rate": 7.843137254901962e-07, |
| "loss": 0.7032, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.029354207436399216, |
| "grad_norm": 33043.3515625, |
| "learning_rate": 9.477124183006536e-07, |
| "loss": 0.6968, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.03424657534246575, |
| "grad_norm": 38538.30078125, |
| "learning_rate": 1.111111111111111e-06, |
| "loss": 0.6992, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.03913894324853229, |
| "grad_norm": 43255.37890625, |
| "learning_rate": 1.2745098039215686e-06, |
| "loss": 0.6991, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.04403131115459882, |
| "grad_norm": 34170.8046875, |
| "learning_rate": 1.4379084967320261e-06, |
| "loss": 0.6996, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.04892367906066536, |
| "grad_norm": 35399.70703125, |
| "learning_rate": 1.6013071895424837e-06, |
| "loss": 0.6937, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.04892367906066536, |
| "eval_accuracy": 0.771, |
| "eval_loss": 0.6569265127182007, |
| "eval_macro_f1": 0.5082027063884254, |
| "eval_precision": 0.6109971743687904, |
| "eval_recall": 0.5281120325963375, |
| "eval_runtime": 17.5156, |
| "eval_samples_per_second": 57.092, |
| "eval_steps_per_second": 0.057, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.053816046966731895, |
| "grad_norm": 34677.1796875, |
| "learning_rate": 1.7647058823529414e-06, |
| "loss": 0.6963, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.05870841487279843, |
| "grad_norm": 31789.291015625, |
| "learning_rate": 1.928104575163399e-06, |
| "loss": 0.6971, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.06360078277886497, |
| "grad_norm": 30762.345703125, |
| "learning_rate": 2.0915032679738565e-06, |
| "loss": 0.6946, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.0684931506849315, |
| "grad_norm": 29590.083984375, |
| "learning_rate": 2.254901960784314e-06, |
| "loss": 0.693, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.07338551859099804, |
| "grad_norm": 29346.84765625, |
| "learning_rate": 2.4183006535947716e-06, |
| "loss": 0.6905, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.07827788649706457, |
| "grad_norm": 37289.77734375, |
| "learning_rate": 2.581699346405229e-06, |
| "loss": 0.6942, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.08317025440313111, |
| "grad_norm": 33970.94140625, |
| "learning_rate": 2.7450980392156867e-06, |
| "loss": 0.69, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.08806262230919765, |
| "grad_norm": 28671.583984375, |
| "learning_rate": 2.9084967320261443e-06, |
| "loss": 0.6889, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.09295499021526418, |
| "grad_norm": 30156.005859375, |
| "learning_rate": 3.071895424836602e-06, |
| "loss": 0.6866, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.09784735812133072, |
| "grad_norm": 33484.71484375, |
| "learning_rate": 3.2352941176470594e-06, |
| "loss": 0.6888, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.09784735812133072, |
| "eval_accuracy": 0.767, |
| "eval_loss": 0.6559821367263794, |
| "eval_macro_f1": 0.5260673147136775, |
| "eval_precision": 0.6062366452991452, |
| "eval_recall": 0.5367285927824044, |
| "eval_runtime": 17.3972, |
| "eval_samples_per_second": 57.481, |
| "eval_steps_per_second": 0.057, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.10273972602739725, |
| "grad_norm": 35390.96484375, |
| "learning_rate": 3.398692810457517e-06, |
| "loss": 0.6893, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.10763209393346379, |
| "grad_norm": 34452.11328125, |
| "learning_rate": 3.562091503267974e-06, |
| "loss": 0.6849, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.11252446183953033, |
| "grad_norm": 41847.0625, |
| "learning_rate": 3.7254901960784316e-06, |
| "loss": 0.6853, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.11741682974559686, |
| "grad_norm": 31951.4140625, |
| "learning_rate": 3.88888888888889e-06, |
| "loss": 0.6802, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.1223091976516634, |
| "grad_norm": 34176.79296875, |
| "learning_rate": 4.052287581699347e-06, |
| "loss": 0.6871, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.12720156555772993, |
| "grad_norm": 35482.6640625, |
| "learning_rate": 4.215686274509805e-06, |
| "loss": 0.6789, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.13209393346379647, |
| "grad_norm": 60289.4296875, |
| "learning_rate": 4.379084967320262e-06, |
| "loss": 0.6844, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.136986301369863, |
| "grad_norm": 41964.47265625, |
| "learning_rate": 4.542483660130719e-06, |
| "loss": 0.6808, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.14187866927592954, |
| "grad_norm": 35805.8203125, |
| "learning_rate": 4.705882352941177e-06, |
| "loss": 0.6748, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.14677103718199608, |
| "grad_norm": 25688.607421875, |
| "learning_rate": 4.869281045751634e-06, |
| "loss": 0.6769, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.14677103718199608, |
| "eval_accuracy": 0.728, |
| "eval_loss": 0.6580190658569336, |
| "eval_macro_f1": 0.5668100015926103, |
| "eval_precision": 0.5782073308365263, |
| "eval_recall": 0.5627889260176255, |
| "eval_runtime": 17.3848, |
| "eval_samples_per_second": 57.521, |
| "eval_steps_per_second": 0.058, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.15166340508806261, |
| "grad_norm": 30171.484375, |
| "learning_rate": 5.032679738562092e-06, |
| "loss": 0.6706, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.15655577299412915, |
| "grad_norm": 29393.716796875, |
| "learning_rate": 5.19607843137255e-06, |
| "loss": 0.6764, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.16144814090019569, |
| "grad_norm": 34377.2578125, |
| "learning_rate": 5.359477124183007e-06, |
| "loss": 0.6688, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.16634050880626222, |
| "grad_norm": 34805.3671875, |
| "learning_rate": 5.522875816993465e-06, |
| "loss": 0.6673, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.17123287671232876, |
| "grad_norm": 29948.095703125, |
| "learning_rate": 5.686274509803922e-06, |
| "loss": 0.6652, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.1761252446183953, |
| "grad_norm": 34735.33984375, |
| "learning_rate": 5.84967320261438e-06, |
| "loss": 0.6709, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.18101761252446183, |
| "grad_norm": 36469.0703125, |
| "learning_rate": 6.0130718954248365e-06, |
| "loss": 0.6606, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.18590998043052837, |
| "grad_norm": 27843.798828125, |
| "learning_rate": 6.176470588235295e-06, |
| "loss": 0.6666, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.1908023483365949, |
| "grad_norm": 27965.966796875, |
| "learning_rate": 6.3398692810457515e-06, |
| "loss": 0.6626, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.19569471624266144, |
| "grad_norm": 28469.09375, |
| "learning_rate": 6.5032679738562095e-06, |
| "loss": 0.6601, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.19569471624266144, |
| "eval_accuracy": 0.698, |
| "eval_loss": 0.6574791669845581, |
| "eval_macro_f1": 0.5962545254252696, |
| "eval_precision": 0.591974921630094, |
| "eval_recall": 0.605831327804422, |
| "eval_runtime": 17.3909, |
| "eval_samples_per_second": 57.501, |
| "eval_steps_per_second": 0.058, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.20058708414872797, |
| "grad_norm": 26626.736328125, |
| "learning_rate": 6.666666666666667e-06, |
| "loss": 0.6598, |
| "step": 205 |
| }, |
| { |
| "epoch": 0.2054794520547945, |
| "grad_norm": 26082.599609375, |
| "learning_rate": 6.830065359477125e-06, |
| "loss": 0.6568, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.21037181996086105, |
| "grad_norm": 33339.375, |
| "learning_rate": 6.993464052287582e-06, |
| "loss": 0.6563, |
| "step": 215 |
| }, |
| { |
| "epoch": 0.21526418786692758, |
| "grad_norm": 30894.603515625, |
| "learning_rate": 7.15686274509804e-06, |
| "loss": 0.652, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.22015655577299412, |
| "grad_norm": 29593.958984375, |
| "learning_rate": 7.320261437908497e-06, |
| "loss": 0.6491, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.22504892367906065, |
| "grad_norm": 39939.2890625, |
| "learning_rate": 7.483660130718955e-06, |
| "loss": 0.6479, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.2299412915851272, |
| "grad_norm": 32097.01953125, |
| "learning_rate": 7.647058823529411e-06, |
| "loss": 0.6464, |
| "step": 235 |
| }, |
| { |
| "epoch": 0.23483365949119372, |
| "grad_norm": 31191.142578125, |
| "learning_rate": 7.81045751633987e-06, |
| "loss": 0.6469, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.23972602739726026, |
| "grad_norm": 30402.431640625, |
| "learning_rate": 7.973856209150329e-06, |
| "loss": 0.6407, |
| "step": 245 |
| }, |
| { |
| "epoch": 0.2446183953033268, |
| "grad_norm": 30825.1328125, |
| "learning_rate": 8.137254901960784e-06, |
| "loss": 0.6391, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.2446183953033268, |
| "eval_accuracy": 0.623, |
| "eval_loss": 0.6709860563278198, |
| "eval_macro_f1": 0.5814715106436125, |
| "eval_precision": 0.6025402726146221, |
| "eval_recall": 0.6470932816224296, |
| "eval_runtime": 17.5511, |
| "eval_samples_per_second": 56.977, |
| "eval_steps_per_second": 0.057, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.24951076320939333, |
| "grad_norm": 26645.732421875, |
| "learning_rate": 8.300653594771243e-06, |
| "loss": 0.6397, |
| "step": 255 |
| }, |
| { |
| "epoch": 0.25440313111545987, |
| "grad_norm": 29653.92578125, |
| "learning_rate": 8.4640522875817e-06, |
| "loss": 0.6437, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.25929549902152643, |
| "grad_norm": 31826.6484375, |
| "learning_rate": 8.627450980392157e-06, |
| "loss": 0.6373, |
| "step": 265 |
| }, |
| { |
| "epoch": 0.26418786692759294, |
| "grad_norm": 35353.4765625, |
| "learning_rate": 8.790849673202614e-06, |
| "loss": 0.6319, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.2690802348336595, |
| "grad_norm": 30883.482421875, |
| "learning_rate": 8.954248366013073e-06, |
| "loss": 0.6355, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.273972602739726, |
| "grad_norm": 26454.451171875, |
| "learning_rate": 9.11764705882353e-06, |
| "loss": 0.6261, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.2788649706457926, |
| "grad_norm": 27102.65234375, |
| "learning_rate": 9.281045751633987e-06, |
| "loss": 0.6291, |
| "step": 285 |
| }, |
| { |
| "epoch": 0.2837573385518591, |
| "grad_norm": 26538.755859375, |
| "learning_rate": 9.444444444444445e-06, |
| "loss": 0.6265, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.28864970645792565, |
| "grad_norm": 27230.40625, |
| "learning_rate": 9.607843137254903e-06, |
| "loss": 0.617, |
| "step": 295 |
| }, |
| { |
| "epoch": 0.29354207436399216, |
| "grad_norm": 27588.068359375, |
| "learning_rate": 9.77124183006536e-06, |
| "loss": 0.618, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.29354207436399216, |
| "eval_accuracy": 0.59, |
| "eval_loss": 0.6805335283279419, |
| "eval_macro_f1": 0.5635902261241277, |
| "eval_precision": 0.6075875666060336, |
| "eval_recall": 0.6546334931985156, |
| "eval_runtime": 17.4391, |
| "eval_samples_per_second": 57.342, |
| "eval_steps_per_second": 0.057, |
| "step": 300 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 3066, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 2 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.0413858103296e+16, |
| "train_batch_size": 512, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
