| { |
| "best_global_step": 1550, |
| "best_metric": 0.6134094606232656, |
| "best_model_checkpoint": "output_checkpoints/graphcodebert-best/checkpoint-1550", |
| "epoch": 1.6144814090019568, |
| "eval_steps": 50, |
| "global_step": 1650, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.009784735812133072, |
| "grad_norm": 165951.1875, |
| "learning_rate": 4.411764705882353e-08, |
| "loss": 0.8416, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.019569471624266144, |
| "grad_norm": 206132.796875, |
| "learning_rate": 9.313725490196079e-08, |
| "loss": 0.8378, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.029354207436399216, |
| "grad_norm": 171197.53125, |
| "learning_rate": 1.4215686274509803e-07, |
| "loss": 0.8388, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.03913894324853229, |
| "grad_norm": 206661.828125, |
| "learning_rate": 1.9117647058823527e-07, |
| "loss": 0.847, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.04892367906066536, |
| "grad_norm": 230268.96875, |
| "learning_rate": 2.4019607843137255e-07, |
| "loss": 0.8411, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.05870841487279843, |
| "grad_norm": 133248.28125, |
| "learning_rate": 2.8921568627450984e-07, |
| "loss": 0.8412, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.0684931506849315, |
| "grad_norm": 147768.828125, |
| "learning_rate": 3.3823529411764707e-07, |
| "loss": 0.8431, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.07827788649706457, |
| "grad_norm": 167327.53125, |
| "learning_rate": 3.872549019607843e-07, |
| "loss": 0.8431, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.08806262230919765, |
| "grad_norm": 151943.75, |
| "learning_rate": 4.3627450980392154e-07, |
| "loss": 0.8311, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.09784735812133072, |
| "grad_norm": 149971.59375, |
| "learning_rate": 4.852941176470588e-07, |
| "loss": 0.8412, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.10763209393346379, |
| "grad_norm": 162329.40625, |
| "learning_rate": 5.34313725490196e-07, |
| "loss": 0.8356, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.11741682974559686, |
| "grad_norm": 158769.765625, |
| "learning_rate": 5.833333333333334e-07, |
| "loss": 0.8351, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.12720156555772993, |
| "grad_norm": 157725.59375, |
| "learning_rate": 6.323529411764706e-07, |
| "loss": 0.8331, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.136986301369863, |
| "grad_norm": 205733.0, |
| "learning_rate": 6.813725490196079e-07, |
| "loss": 0.8366, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.14677103718199608, |
| "grad_norm": 172581.328125, |
| "learning_rate": 7.30392156862745e-07, |
| "loss": 0.831, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.15655577299412915, |
| "grad_norm": 137428.0, |
| "learning_rate": 7.794117647058823e-07, |
| "loss": 0.8326, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.16634050880626222, |
| "grad_norm": 151189.203125, |
| "learning_rate": 8.284313725490196e-07, |
| "loss": 0.8281, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.1761252446183953, |
| "grad_norm": 145620.625, |
| "learning_rate": 8.774509803921568e-07, |
| "loss": 0.8252, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.18590998043052837, |
| "grad_norm": 169938.84375, |
| "learning_rate": 9.264705882352941e-07, |
| "loss": 0.8308, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.19569471624266144, |
| "grad_norm": 138760.015625, |
| "learning_rate": 9.754901960784313e-07, |
| "loss": 0.824, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.2054794520547945, |
| "grad_norm": 107872.125, |
| "learning_rate": 9.99631294374483e-07, |
| "loss": 0.8254, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.21526418786692758, |
| "grad_norm": 113610.8359375, |
| "learning_rate": 9.966849112204936e-07, |
| "loss": 0.8267, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.22504892367906065, |
| "grad_norm": 172441.515625, |
| "learning_rate": 9.908095200725339e-07, |
| "loss": 0.8198, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.23483365949119372, |
| "grad_norm": 128079.9140625, |
| "learning_rate": 9.82039768787326e-07, |
| "loss": 0.8143, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.2446183953033268, |
| "grad_norm": 98149.8984375, |
| "learning_rate": 9.70427373595903e-07, |
| "loss": 0.8191, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.25440313111545987, |
| "grad_norm": 147377.4375, |
| "learning_rate": 9.560408141270531e-07, |
| "loss": 0.8178, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.26418786692759294, |
| "grad_norm": 156439.40625, |
| "learning_rate": 9.389649295750781e-07, |
| "loss": 0.8085, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.273972602739726, |
| "grad_norm": 131892.015625, |
| "learning_rate": 9.193004183933174e-07, |
| "loss": 0.8172, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.2837573385518591, |
| "grad_norm": 132474.5, |
| "learning_rate": 8.971632444637971e-07, |
| "loss": 0.8136, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.29354207436399216, |
| "grad_norm": 112619.109375, |
| "learning_rate": 8.726839532448928e-07, |
| "loss": 0.8065, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.30332681017612523, |
| "grad_norm": 94225.5703125, |
| "learning_rate": 8.460069019297606e-07, |
| "loss": 0.813, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.3131115459882583, |
| "grad_norm": 117812.8203125, |
| "learning_rate": 8.172894081553822e-07, |
| "loss": 0.8022, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.32289628180039137, |
| "grad_norm": 143287.125, |
| "learning_rate": 7.86700822282382e-07, |
| "loss": 0.8061, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.33268101761252444, |
| "grad_norm": 107456.25, |
| "learning_rate": 7.544215287164917e-07, |
| "loss": 0.8006, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.3424657534246575, |
| "grad_norm": 101521.171875, |
| "learning_rate": 7.206418821609812e-07, |
| "loss": 0.8055, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.3522504892367906, |
| "grad_norm": 118311.5234375, |
| "learning_rate": 6.855610850731017e-07, |
| "loss": 0.8081, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.36203522504892366, |
| "grad_norm": 89621.828125, |
| "learning_rate": 6.493860129443046e-07, |
| "loss": 0.8058, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.37181996086105673, |
| "grad_norm": 143168.65625, |
| "learning_rate": 6.123299943316975e-07, |
| "loss": 0.8028, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.3816046966731898, |
| "grad_norm": 118598.2890625, |
| "learning_rate": 5.746115528350295e-07, |
| "loss": 0.8032, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.3913894324853229, |
| "grad_norm": 111807.8203125, |
| "learning_rate": 5.364531184379139e-07, |
| "loss": 0.8014, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.40117416829745595, |
| "grad_norm": 124106.1328125, |
| "learning_rate": 4.980797158126566e-07, |
| "loss": 0.8045, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.410958904109589, |
| "grad_norm": 102746.4765625, |
| "learning_rate": 4.597176373239061e-07, |
| "loss": 0.7996, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.4207436399217221, |
| "grad_norm": 108317.5859375, |
| "learning_rate": 4.215931085565761e-07, |
| "loss": 0.8037, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.43052837573385516, |
| "grad_norm": 113342.515625, |
| "learning_rate": 3.8393095423757764e-07, |
| "loss": 0.8047, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.44031311154598823, |
| "grad_norm": 111908.90625, |
| "learning_rate": 3.469532724185699e-07, |
| "loss": 0.8021, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.4500978473581213, |
| "grad_norm": 85004.15625, |
| "learning_rate": 3.1087812473822845e-07, |
| "loss": 0.8012, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.4598825831702544, |
| "grad_norm": 98335.1796875, |
| "learning_rate": 2.7591825048770643e-07, |
| "loss": 0.7977, |
| "step": 470 |
| }, |
| { |
| "epoch": 0.46966731898238745, |
| "grad_norm": 110674.03125, |
| "learning_rate": 2.422798120625886e-07, |
| "loss": 0.7979, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.4794520547945205, |
| "grad_norm": 114861.5390625, |
| "learning_rate": 2.1016117919955512e-07, |
| "loss": 0.8014, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.4892367906066536, |
| "grad_norm": 130109.5703125, |
| "learning_rate": 1.7975175916725031e-07, |
| "loss": 0.7994, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.49902152641878667, |
| "grad_norm": 93286.4296875, |
| "learning_rate": 1.5123087980985606e-07, |
| "loss": 0.8039, |
| "step": 510 |
| }, |
| { |
| "epoch": 0.5088062622309197, |
| "grad_norm": 123646.703125, |
| "learning_rate": 1.2476673203018728e-07, |
| "loss": 0.7917, |
| "step": 520 |
| }, |
| { |
| "epoch": 0.5185909980430529, |
| "grad_norm": 98060.2265625, |
| "learning_rate": 1.0051537794861287e-07, |
| "loss": 0.7945, |
| "step": 530 |
| }, |
| { |
| "epoch": 0.5283757338551859, |
| "grad_norm": 91181.1796875, |
| "learning_rate": 7.861983058679871e-08, |
| "loss": 0.7952, |
| "step": 540 |
| }, |
| { |
| "epoch": 0.538160469667319, |
| "grad_norm": 97605.3984375, |
| "learning_rate": 5.920921050348626e-08, |
| "loss": 0.7963, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.538160469667319, |
| "eval_accuracy": 0.767, |
| "eval_loss": 0.662277102470398, |
| "eval_macro_f1": 0.5341406895117674, |
| "eval_precision": 0.6105222734254993, |
| "eval_recall": 0.5415245482510056, |
| "eval_runtime": 16.9722, |
| "eval_samples_per_second": 58.92, |
| "eval_steps_per_second": 0.059, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.547945205479452, |
| "grad_norm": 101627.8046875, |
| "learning_rate": 4.23979843557199e-08, |
| "loss": 0.7962, |
| "step": 560 |
| }, |
| { |
| "epoch": 0.5577299412915852, |
| "grad_norm": 73889.578125, |
| "learning_rate": 2.8285289875818407e-08, |
| "loss": 0.794, |
| "step": 570 |
| }, |
| { |
| "epoch": 0.5675146771037182, |
| "grad_norm": 87191.0546875, |
| "learning_rate": 1.695435124477512e-08, |
| "loss": 0.7984, |
| "step": 580 |
| }, |
| { |
| "epoch": 0.5772994129158513, |
| "grad_norm": 105470.234375, |
| "learning_rate": 8.471988309699807e-09, |
| "loss": 0.7924, |
| "step": 590 |
| }, |
| { |
| "epoch": 0.5870841487279843, |
| "grad_norm": 81710.7265625, |
| "learning_rate": 2.8882225395023275e-09, |
| "loss": 0.8005, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.5870841487279843, |
| "eval_accuracy": 0.767, |
| "eval_loss": 0.6623347401618958, |
| "eval_macro_f1": 0.5341406895117674, |
| "eval_precision": 0.6105222734254993, |
| "eval_recall": 0.5415245482510056, |
| "eval_runtime": 17.0174, |
| "eval_samples_per_second": 58.763, |
| "eval_steps_per_second": 0.059, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.5968688845401174, |
| "grad_norm": 97212.125, |
| "learning_rate": 2.35982042542604e-10, |
| "loss": 0.7981, |
| "step": 610 |
| }, |
| { |
| "epoch": 0.6066536203522505, |
| "grad_norm": 100700.640625, |
| "learning_rate": 9.994690926142082e-07, |
| "loss": 0.8006, |
| "step": 620 |
| }, |
| { |
| "epoch": 0.6164383561643836, |
| "grad_norm": 88023.046875, |
| "learning_rate": 9.962287406393883e-07, |
| "loss": 0.7976, |
| "step": 630 |
| }, |
| { |
| "epoch": 0.6262230919765166, |
| "grad_norm": 118936.609375, |
| "learning_rate": 9.900620707609317e-07, |
| "loss": 0.7961, |
| "step": 640 |
| }, |
| { |
| "epoch": 0.6360078277886497, |
| "grad_norm": 91811.3984375, |
| "learning_rate": 9.810054485397043e-07, |
| "loss": 0.7904, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.6360078277886497, |
| "eval_accuracy": 0.757, |
| "eval_loss": 0.6629467606544495, |
| "eval_macro_f1": 0.5299579283330915, |
| "eval_precision": 0.5844492268452096, |
| "eval_recall": 0.5366881936388663, |
| "eval_runtime": 17.0504, |
| "eval_samples_per_second": 58.65, |
| "eval_steps_per_second": 0.059, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.6457925636007827, |
| "grad_norm": 118632.46875, |
| "learning_rate": 9.69112281917613e-07, |
| "loss": 0.7927, |
| "step": 660 |
| }, |
| { |
| "epoch": 0.6555772994129159, |
| "grad_norm": 70413.0390625, |
| "learning_rate": 9.544527062648345e-07, |
| "loss": 0.785, |
| "step": 670 |
| }, |
| { |
| "epoch": 0.6653620352250489, |
| "grad_norm": 84746.4453125, |
| "learning_rate": 9.371131707834789e-07, |
| "loss": 0.7861, |
| "step": 680 |
| }, |
| { |
| "epoch": 0.675146771037182, |
| "grad_norm": 92019.0390625, |
| "learning_rate": 9.171959287067115e-07, |
| "loss": 0.7892, |
| "step": 690 |
| }, |
| { |
| "epoch": 0.684931506849315, |
| "grad_norm": 70649.2578125, |
| "learning_rate": 8.948184342996868e-07, |
| "loss": 0.789, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.684931506849315, |
| "eval_accuracy": 0.751, |
| "eval_loss": 0.6648359894752502, |
| "eval_macro_f1": 0.5514410631387237, |
| "eval_precision": 0.589223697650664, |
| "eval_recall": 0.5504123598294002, |
| "eval_runtime": 17.0124, |
| "eval_samples_per_second": 58.781, |
| "eval_steps_per_second": 0.059, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.6947162426614482, |
| "grad_norm": 80338.796875, |
| "learning_rate": 8.701126502182503e-07, |
| "loss": 0.7907, |
| "step": 710 |
| }, |
| { |
| "epoch": 0.7045009784735812, |
| "grad_norm": 69257.328125, |
| "learning_rate": 8.432242693099946e-07, |
| "loss": 0.7881, |
| "step": 720 |
| }, |
| { |
| "epoch": 0.7142857142857143, |
| "grad_norm": 95345.15625, |
| "learning_rate": 8.14311855446795e-07, |
| "loss": 0.7849, |
| "step": 730 |
| }, |
| { |
| "epoch": 0.7240704500978473, |
| "grad_norm": 94407.8984375, |
| "learning_rate": 7.835459084554374e-07, |
| "loss": 0.7868, |
| "step": 740 |
| }, |
| { |
| "epoch": 0.7338551859099804, |
| "grad_norm": 74418.0625, |
| "learning_rate": 7.511078586605484e-07, |
| "loss": 0.783, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.7338551859099804, |
| "eval_accuracy": 0.742, |
| "eval_loss": 0.6660248637199402, |
| "eval_macro_f1": 0.5532467532467532, |
| "eval_precision": 0.579727791757989, |
| "eval_recall": 0.5510154613293626, |
| "eval_runtime": 16.9303, |
| "eval_samples_per_second": 59.066, |
| "eval_steps_per_second": 0.059, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.7436399217221135, |
| "grad_norm": 95142.0546875, |
| "learning_rate": 7.171889969691225e-07, |
| "loss": 0.7861, |
| "step": 760 |
| }, |
| { |
| "epoch": 0.7534246575342466, |
| "grad_norm": 118907.203125, |
| "learning_rate": 6.819893468060643e-07, |
| "loss": 0.7878, |
| "step": 770 |
| }, |
| { |
| "epoch": 0.7632093933463796, |
| "grad_norm": 66268.78125, |
| "learning_rate": 6.457164845530662e-07, |
| "loss": 0.7859, |
| "step": 780 |
| }, |
| { |
| "epoch": 0.7729941291585127, |
| "grad_norm": 81464.265625, |
| "learning_rate": 6.085843154468354e-07, |
| "loss": 0.7819, |
| "step": 790 |
| }, |
| { |
| "epoch": 0.7827788649706457, |
| "grad_norm": 87098.984375, |
| "learning_rate": 5.708118121553318e-07, |
| "loss": 0.7801, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.7827788649706457, |
| "eval_accuracy": 0.734, |
| "eval_loss": 0.667039155960083, |
| "eval_macro_f1": 0.5514001038862917, |
| "eval_precision": 0.5710358542434345, |
| "eval_recall": 0.5490647598270917, |
| "eval_runtime": 17.0236, |
| "eval_samples_per_second": 58.742, |
| "eval_steps_per_second": 0.059, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.7925636007827789, |
| "grad_norm": 70466.7109375, |
| "learning_rate": 5.326217234707852e-07, |
| "loss": 0.7782, |
| "step": 810 |
| }, |
| { |
| "epoch": 0.8023483365949119, |
| "grad_norm": 78038.6015625, |
| "learning_rate": 4.942392607344717e-07, |
| "loss": 0.786, |
| "step": 820 |
| }, |
| { |
| "epoch": 0.812133072407045, |
| "grad_norm": 91227.28125, |
| "learning_rate": 4.558907697395553e-07, |
| "loss": 0.7781, |
| "step": 830 |
| }, |
| { |
| "epoch": 0.821917808219178, |
| "grad_norm": 85470.5625, |
| "learning_rate": 4.1780239594393807e-07, |
| "loss": 0.7806, |
| "step": 840 |
| }, |
| { |
| "epoch": 0.8317025440313112, |
| "grad_norm": 73229.96875, |
| "learning_rate": 3.8019875086450787e-07, |
| "loss": 0.7823, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.8317025440313112, |
| "eval_accuracy": 0.725, |
| "eval_loss": 0.668379545211792, |
| "eval_macro_f1": 0.5541786430494829, |
| "eval_precision": 0.5667714002224962, |
| "eval_recall": 0.5512665131499213, |
| "eval_runtime": 16.9299, |
| "eval_samples_per_second": 59.067, |
| "eval_steps_per_second": 0.059, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.8414872798434442, |
| "grad_norm": 84347.0546875, |
| "learning_rate": 3.4330158751721504e-07, |
| "loss": 0.7805, |
| "step": 860 |
| }, |
| { |
| "epoch": 0.8512720156555773, |
| "grad_norm": 60984.21875, |
| "learning_rate": 3.0732849271405547e-07, |
| "loss": 0.779, |
| "step": 870 |
| }, |
| { |
| "epoch": 0.8610567514677103, |
| "grad_norm": 72854.8046875, |
| "learning_rate": 2.7249160392863903e-07, |
| "loss": 0.7811, |
| "step": 880 |
| }, |
| { |
| "epoch": 0.8708414872798435, |
| "grad_norm": 69136.65625, |
| "learning_rate": 2.3899635829713077e-07, |
| "loss": 0.7811, |
| "step": 890 |
| }, |
| { |
| "epoch": 0.8806262230919765, |
| "grad_norm": 74345.7421875, |
| "learning_rate": 2.0704028113185306e-07, |
| "loss": 0.7845, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.8806262230919765, |
| "eval_accuracy": 0.726, |
| "eval_loss": 0.6684988737106323, |
| "eval_macro_f1": 0.5584519389438943, |
| "eval_precision": 0.5706882639048261, |
| "eval_recall": 0.555107317439156, |
| "eval_runtime": 16.9904, |
| "eval_samples_per_second": 58.857, |
| "eval_steps_per_second": 0.059, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.8904109589041096, |
| "grad_norm": 75862.8046875, |
| "learning_rate": 1.768118210918219e-07, |
| "loss": 0.7821, |
| "step": 910 |
| }, |
| { |
| "epoch": 0.9001956947162426, |
| "grad_norm": 60382.25, |
| "learning_rate": 1.484892388793511e-07, |
| "loss": 0.7811, |
| "step": 920 |
| }, |
| { |
| "epoch": 0.9099804305283757, |
| "grad_norm": 67346.859375, |
| "learning_rate": 1.2223955601620633e-07, |
| "loss": 0.781, |
| "step": 930 |
| }, |
| { |
| "epoch": 0.9197651663405088, |
| "grad_norm": 81895.7265625, |
| "learning_rate": 9.821756989850016e-08, |
| "loss": 0.7816, |
| "step": 940 |
| }, |
| { |
| "epoch": 0.9295499021526419, |
| "grad_norm": 87715.9453125, |
| "learning_rate": 7.656494093865984e-08, |
| "loss": 0.7815, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.9295499021526419, |
| "eval_accuracy": 0.723, |
| "eval_loss": 0.6687072515487671, |
| "eval_macro_f1": 0.5562540149399822, |
| "eval_precision": 0.5672044579297467, |
| "eval_recall": 0.553176815508654, |
| "eval_runtime": 16.997, |
| "eval_samples_per_second": 58.834, |
| "eval_steps_per_second": 0.059, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.9393346379647749, |
| "grad_norm": 62333.75390625, |
| "learning_rate": 5.740935717769707e-08, |
| "loss": 0.775, |
| "step": 960 |
| }, |
| { |
| "epoch": 0.949119373776908, |
| "grad_norm": 67404.265625, |
| "learning_rate": 4.0863781294158185e-08, |
| "loss": 0.78, |
| "step": 970 |
| }, |
| { |
| "epoch": 0.958904109589041, |
| "grad_norm": 75798.1328125, |
| "learning_rate": 2.702578445022852e-08, |
| "loss": 0.7808, |
| "step": 980 |
| }, |
| { |
| "epoch": 0.9686888454011742, |
| "grad_norm": 77483.9609375, |
| "learning_rate": 1.597697090337763e-08, |
| "loss": 0.7804, |
| "step": 990 |
| }, |
| { |
| "epoch": 0.9784735812133072, |
| "grad_norm": 82261.78125, |
| "learning_rate": 7.782496776675695e-09, |
| "loss": 0.7795, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.9784735812133072, |
| "eval_accuracy": 0.723, |
| "eval_loss": 0.6687466502189636, |
| "eval_macro_f1": 0.5579874225879597, |
| "eval_precision": 0.5685547947184422, |
| "eval_recall": 0.5547754673315212, |
| "eval_runtime": 16.934, |
| "eval_samples_per_second": 59.053, |
| "eval_steps_per_second": 0.059, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.9882583170254403, |
| "grad_norm": 68659.8671875, |
| "learning_rate": 2.4906858256491524e-09, |
| "loss": 0.78, |
| "step": 1010 |
| }, |
| { |
| "epoch": 0.9980430528375733, |
| "grad_norm": 92298.78125, |
| "learning_rate": 1.3274446754157898e-10, |
| "loss": 0.7824, |
| "step": 1020 |
| }, |
| { |
| "epoch": 1.0078277886497065, |
| "grad_norm": 47534.20703125, |
| "learning_rate": 2.607950146993215e-08, |
| "loss": 0.7439, |
| "step": 1030 |
| }, |
| { |
| "epoch": 1.0176125244618395, |
| "grad_norm": 43369.4765625, |
| "learning_rate": 2.09146573606756e-08, |
| "loss": 0.741, |
| "step": 1040 |
| }, |
| { |
| "epoch": 1.0273972602739727, |
| "grad_norm": 48618.94140625, |
| "learning_rate": 1.6308405330324294e-08, |
| "loss": 0.742, |
| "step": 1050 |
| }, |
| { |
| "epoch": 1.0273972602739727, |
| "eval_accuracy": 0.723, |
| "eval_loss": 0.668785035610199, |
| "eval_macro_f1": 0.5597017416418834, |
| "eval_precision": 0.5698832417582418, |
| "eval_recall": 0.5563741191543882, |
| "eval_runtime": 17.6735, |
| "eval_samples_per_second": 56.582, |
| "eval_steps_per_second": 0.057, |
| "step": 1050 |
| }, |
| { |
| "epoch": 1.0371819960861057, |
| "grad_norm": 47853.890625, |
| "learning_rate": 1.2266116062696951e-08, |
| "loss": 0.7434, |
| "step": 1060 |
| }, |
| { |
| "epoch": 1.0469667318982387, |
| "grad_norm": 58555.92578125, |
| "learning_rate": 8.792502686258752e-09, |
| "loss": 0.7448, |
| "step": 1070 |
| }, |
| { |
| "epoch": 1.0567514677103718, |
| "grad_norm": 54508.24609375, |
| "learning_rate": 5.891615278823537e-09, |
| "loss": 0.7406, |
| "step": 1080 |
| }, |
| { |
| "epoch": 1.0665362035225048, |
| "grad_norm": 51657.953125, |
| "learning_rate": 3.5668361453450313e-09, |
| "loss": 0.7427, |
| "step": 1090 |
| }, |
| { |
| "epoch": 1.076320939334638, |
| "grad_norm": 54486.4921875, |
| "learning_rate": 1.8208758743000207e-09, |
| "loss": 0.7444, |
| "step": 1100 |
| }, |
| { |
| "epoch": 1.076320939334638, |
| "eval_accuracy": 0.723, |
| "eval_loss": 0.6687813997268677, |
| "eval_macro_f1": 0.5597017416418834, |
| "eval_precision": 0.5698832417582418, |
| "eval_recall": 0.5563741191543882, |
| "eval_runtime": 17.4461, |
| "eval_samples_per_second": 57.319, |
| "eval_steps_per_second": 0.057, |
| "step": 1100 |
| }, |
| { |
| "epoch": 1.086105675146771, |
| "grad_norm": 42684.90625, |
| "learning_rate": 6.557701772635371e-10, |
| "loss": 0.7402, |
| "step": 1110 |
| }, |
| { |
| "epoch": 1.095890410958904, |
| "grad_norm": 43652.2265625, |
| "learning_rate": 7.287751536050324e-11, |
| "loss": 0.742, |
| "step": 1120 |
| }, |
| { |
| "epoch": 1.1056751467710373, |
| "grad_norm": 55561.12890625, |
| "learning_rate": 9.999271224846395e-07, |
| "loss": 0.7405, |
| "step": 1130 |
| }, |
| { |
| "epoch": 1.1154598825831703, |
| "grad_norm": 57599.58984375, |
| "learning_rate": 9.993442298227364e-07, |
| "loss": 0.7397, |
| "step": 1140 |
| }, |
| { |
| "epoch": 1.1252446183953033, |
| "grad_norm": 43188.921875, |
| "learning_rate": 9.981791241257e-07, |
| "loss": 0.7405, |
| "step": 1150 |
| }, |
| { |
| "epoch": 1.1252446183953033, |
| "eval_accuracy": 0.723, |
| "eval_loss": 0.6686130166053772, |
| "eval_macro_f1": 0.5630742537166292, |
| "eval_precision": 0.572477811481856, |
| "eval_recall": 0.5595714228001223, |
| "eval_runtime": 17.3251, |
| "eval_samples_per_second": 57.72, |
| "eval_steps_per_second": 0.058, |
| "step": 1150 |
| }, |
| { |
| "epoch": 1.1350293542074363, |
| "grad_norm": 42596.6796875, |
| "learning_rate": 9.964331638546548e-07, |
| "loss": 0.7397, |
| "step": 1160 |
| }, |
| { |
| "epoch": 1.1448140900195694, |
| "grad_norm": 60584.2890625, |
| "learning_rate": 9.941083847211764e-07, |
| "loss": 0.7417, |
| "step": 1170 |
| }, |
| { |
| "epoch": 1.1545988258317026, |
| "grad_norm": 61568.48046875, |
| "learning_rate": 9.912074973137411e-07, |
| "loss": 0.7405, |
| "step": 1180 |
| }, |
| { |
| "epoch": 1.1643835616438356, |
| "grad_norm": 50988.54296875, |
| "learning_rate": 9.87733883937303e-07, |
| "loss": 0.7381, |
| "step": 1190 |
| }, |
| { |
| "epoch": 1.1741682974559686, |
| "grad_norm": 48960.01171875, |
| "learning_rate": 9.836915946696757e-07, |
| "loss": 0.7377, |
| "step": 1200 |
| }, |
| { |
| "epoch": 1.1741682974559686, |
| "eval_accuracy": 0.716, |
| "eval_loss": 0.6701745986938477, |
| "eval_macro_f1": 0.5807350718065004, |
| "eval_precision": 0.582848916337505, |
| "eval_recall": 0.5790466956386239, |
| "eval_runtime": 17.3208, |
| "eval_samples_per_second": 57.734, |
| "eval_steps_per_second": 0.058, |
| "step": 1200 |
| }, |
| { |
| "epoch": 1.1839530332681019, |
| "grad_norm": 50420.14453125, |
| "learning_rate": 9.790853426393242e-07, |
| "loss": 0.7393, |
| "step": 1210 |
| }, |
| { |
| "epoch": 1.1937377690802349, |
| "grad_norm": 39574.37890625, |
| "learning_rate": 9.73920498530068e-07, |
| "loss": 0.7388, |
| "step": 1220 |
| }, |
| { |
| "epoch": 1.203522504892368, |
| "grad_norm": 51037.01953125, |
| "learning_rate": 9.68203084319102e-07, |
| "loss": 0.739, |
| "step": 1230 |
| }, |
| { |
| "epoch": 1.213307240704501, |
| "grad_norm": 40847.125, |
| "learning_rate": 9.619397662556433e-07, |
| "loss": 0.7377, |
| "step": 1240 |
| }, |
| { |
| "epoch": 1.223091976516634, |
| "grad_norm": 54462.5703125, |
| "learning_rate": 9.55137847088381e-07, |
| "loss": 0.7361, |
| "step": 1250 |
| }, |
| { |
| "epoch": 1.223091976516634, |
| "eval_accuracy": 0.701, |
| "eval_loss": 0.671897292137146, |
| "eval_macro_f1": 0.5884212859150606, |
| "eval_precision": 0.5853845179540225, |
| "eval_recall": 0.5933739633291203, |
| "eval_runtime": 17.4826, |
| "eval_samples_per_second": 57.2, |
| "eval_steps_per_second": 0.057, |
| "step": 1250 |
| }, |
| { |
| "epoch": 1.2328767123287672, |
| "grad_norm": 49697.23046875, |
| "learning_rate": 9.478052575507982e-07, |
| "loss": 0.737, |
| "step": 1260 |
| }, |
| { |
| "epoch": 1.2426614481409002, |
| "grad_norm": 40874.4921875, |
| "learning_rate": 9.39950547114292e-07, |
| "loss": 0.7343, |
| "step": 1270 |
| }, |
| { |
| "epoch": 1.2524461839530332, |
| "grad_norm": 63225.41796875, |
| "learning_rate": 9.315828740198713e-07, |
| "loss": 0.7346, |
| "step": 1280 |
| }, |
| { |
| "epoch": 1.2622309197651664, |
| "grad_norm": 42103.6328125, |
| "learning_rate": 9.227119946000589e-07, |
| "loss": 0.733, |
| "step": 1290 |
| }, |
| { |
| "epoch": 1.2720156555772995, |
| "grad_norm": 53617.17578125, |
| "learning_rate": 9.133482519034428e-07, |
| "loss": 0.7334, |
| "step": 1300 |
| }, |
| { |
| "epoch": 1.2720156555772995, |
| "eval_accuracy": 0.699, |
| "eval_loss": 0.6714372038841248, |
| "eval_macro_f1": 0.586855697342288, |
| "eval_precision": 0.5837743615591398, |
| "eval_recall": 0.592086962042119, |
| "eval_runtime": 17.5108, |
| "eval_samples_per_second": 57.108, |
| "eval_steps_per_second": 0.057, |
| "step": 1300 |
| }, |
| { |
| "epoch": 1.2818003913894325, |
| "grad_norm": 49828.37890625, |
| "learning_rate": 9.035025636351454e-07, |
| "loss": 0.7325, |
| "step": 1310 |
| }, |
| { |
| "epoch": 1.2915851272015655, |
| "grad_norm": 52261.57421875, |
| "learning_rate": 8.931864094272663e-07, |
| "loss": 0.7311, |
| "step": 1320 |
| }, |
| { |
| "epoch": 1.3013698630136985, |
| "grad_norm": 44072.09765625, |
| "learning_rate": 8.824118174541462e-07, |
| "loss": 0.7327, |
| "step": 1330 |
| }, |
| { |
| "epoch": 1.3111545988258317, |
| "grad_norm": 46144.7578125, |
| "learning_rate": 8.711913504080533e-07, |
| "loss": 0.73, |
| "step": 1340 |
| }, |
| { |
| "epoch": 1.3209393346379648, |
| "grad_norm": 40000.671875, |
| "learning_rate": 8.595380908516452e-07, |
| "loss": 0.7327, |
| "step": 1350 |
| }, |
| { |
| "epoch": 1.3209393346379648, |
| "eval_accuracy": 0.697, |
| "eval_loss": 0.6719282865524292, |
| "eval_macro_f1": 0.5986622073578596, |
| "eval_precision": 0.5941197969142022, |
| "eval_recall": 0.6099837826295225, |
| "eval_runtime": 17.375, |
| "eval_samples_per_second": 57.554, |
| "eval_steps_per_second": 0.058, |
| "step": 1350 |
| }, |
| { |
| "epoch": 1.3307240704500978, |
| "grad_norm": 35656.375, |
| "learning_rate": 8.474656259642874e-07, |
| "loss": 0.7292, |
| "step": 1360 |
| }, |
| { |
| "epoch": 1.340508806262231, |
| "grad_norm": 40683.66796875, |
| "learning_rate": 8.349880317000082e-07, |
| "loss": 0.7295, |
| "step": 1370 |
| }, |
| { |
| "epoch": 1.350293542074364, |
| "grad_norm": 41085.30078125, |
| "learning_rate": 8.221198563755681e-07, |
| "loss": 0.7309, |
| "step": 1380 |
| }, |
| { |
| "epoch": 1.360078277886497, |
| "grad_norm": 45236.1171875, |
| "learning_rate": 8.088761037077715e-07, |
| "loss": 0.7315, |
| "step": 1390 |
| }, |
| { |
| "epoch": 1.36986301369863, |
| "grad_norm": 37422.8671875, |
| "learning_rate": 7.952722153198053e-07, |
| "loss": 0.7275, |
| "step": 1400 |
| }, |
| { |
| "epoch": 1.36986301369863, |
| "eval_accuracy": 0.695, |
| "eval_loss": 0.6719865202903748, |
| "eval_macro_f1": 0.6001735640004142, |
| "eval_precision": 0.5955075279261778, |
| "eval_recall": 0.6134927368111225, |
| "eval_runtime": 17.4181, |
| "eval_samples_per_second": 57.412, |
| "eval_steps_per_second": 0.057, |
| "step": 1400 |
| }, |
| { |
| "epoch": 1.379647749510763, |
| "grad_norm": 0.6123355031013489, |
| "learning_rate": 8.815093721181899e-07, |
| "loss": 0.7295, |
| "step": 1410 |
| }, |
| { |
| "epoch": 1.3894324853228963, |
| "grad_norm": 0.7243862748146057, |
| "learning_rate": 8.688188004496398e-07, |
| "loss": 0.7316, |
| "step": 1420 |
| }, |
| { |
| "epoch": 1.3992172211350293, |
| "grad_norm": 0.6597609519958496, |
| "learning_rate": 8.555842865150007e-07, |
| "loss": 0.7315, |
| "step": 1430 |
| }, |
| { |
| "epoch": 1.4090019569471623, |
| "grad_norm": 0.5748956203460693, |
| "learning_rate": 8.418253488732276e-07, |
| "loss": 0.7288, |
| "step": 1440 |
| }, |
| { |
| "epoch": 1.4187866927592956, |
| "grad_norm": 0.6559261679649353, |
| "learning_rate": 8.275622795151589e-07, |
| "loss": 0.7285, |
| "step": 1450 |
| }, |
| { |
| "epoch": 1.4187866927592956, |
| "eval_accuracy": 0.692, |
| "eval_loss": 0.6723695993423462, |
| "eval_macro_f1": 0.6046720575022462, |
| "eval_precision": 0.5999736781495739, |
| "eval_recall": 0.62275279764069, |
| "eval_runtime": 7.5196, |
| "eval_samples_per_second": 132.986, |
| "eval_steps_per_second": 0.266, |
| "step": 1450 |
| }, |
| { |
| "epoch": 1.4285714285714286, |
| "grad_norm": 0.6027814745903015, |
| "learning_rate": 8.128161139364327e-07, |
| "loss": 0.7278, |
| "step": 1460 |
| }, |
| { |
| "epoch": 1.4383561643835616, |
| "grad_norm": 0.6246464252471924, |
| "learning_rate": 7.976086001138633e-07, |
| "loss": 0.7292, |
| "step": 1470 |
| }, |
| { |
| "epoch": 1.4481409001956946, |
| "grad_norm": 0.6013718247413635, |
| "learning_rate": 7.819621664310375e-07, |
| "loss": 0.7257, |
| "step": 1480 |
| }, |
| { |
| "epoch": 1.4579256360078277, |
| "grad_norm": 0.5971313714981079, |
| "learning_rate": 7.658998886004268e-07, |
| "loss": 0.7266, |
| "step": 1490 |
| }, |
| { |
| "epoch": 1.467710371819961, |
| "grad_norm": 0.691210925579071, |
| "learning_rate": 7.494454556308112e-07, |
| "loss": 0.7292, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.467710371819961, |
| "eval_accuracy": 0.696, |
| "eval_loss": 0.6721649765968323, |
| "eval_macro_f1": 0.6107434799532893, |
| "eval_precision": 0.6055948182597334, |
| "eval_recall": 0.6301227556832938, |
| "eval_runtime": 7.4797, |
| "eval_samples_per_second": 133.696, |
| "eval_steps_per_second": 0.267, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.477495107632094, |
| "grad_norm": 0.6443959474563599, |
| "learning_rate": 7.326231348901924e-07, |
| "loss": 0.7281, |
| "step": 1510 |
| }, |
| { |
| "epoch": 1.487279843444227, |
| "grad_norm": 0.6890615820884705, |
| "learning_rate": 7.154577363157363e-07, |
| "loss": 0.7252, |
| "step": 1520 |
| }, |
| { |
| "epoch": 1.4970645792563602, |
| "grad_norm": 0.5993087291717529, |
| "learning_rate": 6.979745758235166e-07, |
| "loss": 0.7263, |
| "step": 1530 |
| }, |
| { |
| "epoch": 1.5068493150684932, |
| "grad_norm": 0.6016016602516174, |
| "learning_rate": 6.801994379720355e-07, |
| "loss": 0.7255, |
| "step": 1540 |
| }, |
| { |
| "epoch": 1.5166340508806262, |
| "grad_norm": 0.6525799632072449, |
| "learning_rate": 6.621585379345729e-07, |
| "loss": 0.7216, |
| "step": 1550 |
| }, |
| { |
| "epoch": 1.5166340508806262, |
| "eval_accuracy": 0.697, |
| "eval_loss": 0.672131359577179, |
| "eval_macro_f1": 0.6134094606232656, |
| "eval_precision": 0.6081358079904591, |
| "eval_recall": 0.6339635599725286, |
| "eval_runtime": 7.506, |
| "eval_samples_per_second": 133.227, |
| "eval_steps_per_second": 0.266, |
| "step": 1550 |
| }, |
| { |
| "epoch": 1.5264187866927594, |
| "grad_norm": 0.6760383248329163, |
| "learning_rate": 6.438784828364623e-07, |
| "loss": 0.7266, |
| "step": 1560 |
| }, |
| { |
| "epoch": 1.5362035225048922, |
| "grad_norm": 0.5501950979232788, |
| "learning_rate": 6.253862325143006e-07, |
| "loss": 0.7235, |
| "step": 1570 |
| }, |
| { |
| "epoch": 1.5459882583170255, |
| "grad_norm": 0.6858824491500854, |
| "learning_rate": 6.067090597549778e-07, |
| "loss": 0.7282, |
| "step": 1580 |
| }, |
| { |
| "epoch": 1.5557729941291585, |
| "grad_norm": 0.6812397241592407, |
| "learning_rate": 5.878745100731532e-07, |
| "loss": 0.7225, |
| "step": 1590 |
| }, |
| { |
| "epoch": 1.5655577299412915, |
| "grad_norm": 0.8024822473526001, |
| "learning_rate": 5.689103610865153e-07, |
| "loss": 0.7293, |
| "step": 1600 |
| }, |
| { |
| "epoch": 1.5655577299412915, |
| "eval_accuracy": 0.689, |
| "eval_loss": 0.6729016900062561, |
| "eval_macro_f1": 0.6104704539960596, |
| "eval_precision": 0.606289924506388, |
| "eval_recall": 0.6352101621159918, |
| "eval_runtime": 7.4663, |
| "eval_samples_per_second": 133.936, |
| "eval_steps_per_second": 0.268, |
| "step": 1600 |
| }, |
| { |
| "epoch": 1.5753424657534247, |
| "grad_norm": 0.6455201506614685, |
| "learning_rate": 5.498445815487207e-07, |
| "loss": 0.7284, |
| "step": 1610 |
| }, |
| { |
| "epoch": 1.5851272015655578, |
| "grad_norm": 0.6250964403152466, |
| "learning_rate": 5.307052901004523e-07, |
| "loss": 0.7229, |
| "step": 1620 |
| }, |
| { |
| "epoch": 1.5949119373776908, |
| "grad_norm": 0.8491455316543579, |
| "learning_rate": 5.115207137994109e-07, |
| "loss": 0.7269, |
| "step": 1630 |
| }, |
| { |
| "epoch": 1.604696673189824, |
| "grad_norm": 0.6143584847450256, |
| "learning_rate": 4.923191464904187e-07, |
| "loss": 0.7244, |
| "step": 1640 |
| }, |
| { |
| "epoch": 1.6144814090019568, |
| "grad_norm": 0.6323517560958862, |
| "learning_rate": 4.73128907077017e-07, |
| "loss": 0.7235, |
| "step": 1650 |
| }, |
| { |
| "epoch": 1.6144814090019568, |
| "eval_accuracy": 0.686, |
| "eval_loss": 0.6727749705314636, |
| "eval_macro_f1": 0.6071542957802867, |
| "eval_precision": 0.6033547896122016, |
| "eval_recall": 0.6316810083626228, |
| "eval_runtime": 7.8151, |
| "eval_samples_per_second": 127.957, |
| "eval_steps_per_second": 0.256, |
| "step": 1650 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 2044, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 50, |
| "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": 2.2221991380228096e+17, |
| "train_batch_size": 512, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
