Instructions to use dzungpham/graphcodebert-code-classification with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dzungpham/graphcodebert-code-classification with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("dzungpham/graphcodebert-code-classification", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "best_global_step": 1000, | |
| "best_metric": 0.7549859375827388, | |
| "best_model_checkpoint": "./output_checkpoints/graphcodebert-robust/checkpoint-1000", | |
| "epoch": 0.0768, | |
| "eval_steps": 1000, | |
| "global_step": 1200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00064, | |
| "grad_norm": 1.6144306659698486, | |
| "learning_rate": 1.1520000000000002e-08, | |
| "loss": 0.729, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00128, | |
| "grad_norm": 2.0952296257019043, | |
| "learning_rate": 2.4320000000000002e-08, | |
| "loss": 0.7295, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00192, | |
| "grad_norm": 1.3587689399719238, | |
| "learning_rate": 3.7120000000000004e-08, | |
| "loss": 0.73, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00256, | |
| "grad_norm": 1.2531732320785522, | |
| "learning_rate": 4.9920000000000006e-08, | |
| "loss": 0.7221, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0032, | |
| "grad_norm": 1.437932014465332, | |
| "learning_rate": 6.272000000000001e-08, | |
| "loss": 0.7209, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00384, | |
| "grad_norm": 1.418426752090454, | |
| "learning_rate": 7.552e-08, | |
| "loss": 0.729, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.00448, | |
| "grad_norm": 1.9476298093795776, | |
| "learning_rate": 8.832e-08, | |
| "loss": 0.7242, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.00512, | |
| "grad_norm": 1.7948051691055298, | |
| "learning_rate": 1.0112000000000001e-07, | |
| "loss": 0.7227, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.00576, | |
| "grad_norm": 1.6534360647201538, | |
| "learning_rate": 1.1392e-07, | |
| "loss": 0.7234, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0064, | |
| "grad_norm": 1.0920158624649048, | |
| "learning_rate": 1.2672e-07, | |
| "loss": 0.7328, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.00704, | |
| "grad_norm": 1.977837085723877, | |
| "learning_rate": 1.3952000000000002e-07, | |
| "loss": 0.7263, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.00768, | |
| "grad_norm": 1.388983130455017, | |
| "learning_rate": 1.5232000000000003e-07, | |
| "loss": 0.7286, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.00832, | |
| "grad_norm": 1.2956682443618774, | |
| "learning_rate": 1.6512e-07, | |
| "loss": 0.7251, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.00896, | |
| "grad_norm": 1.8125052452087402, | |
| "learning_rate": 1.7792e-07, | |
| "loss": 0.7251, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.0096, | |
| "grad_norm": 1.626846194267273, | |
| "learning_rate": 1.9072e-07, | |
| "loss": 0.727, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.01024, | |
| "grad_norm": 2.3243086338043213, | |
| "learning_rate": 2.0352e-07, | |
| "loss": 0.726, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.01088, | |
| "grad_norm": 1.4734737873077393, | |
| "learning_rate": 2.1632e-07, | |
| "loss": 0.7252, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.01152, | |
| "grad_norm": 2.090498685836792, | |
| "learning_rate": 2.2912e-07, | |
| "loss": 0.7273, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.01216, | |
| "grad_norm": 1.7563093900680542, | |
| "learning_rate": 2.4192000000000004e-07, | |
| "loss": 0.719, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.0128, | |
| "grad_norm": 1.449843168258667, | |
| "learning_rate": 2.5472000000000005e-07, | |
| "loss": 0.7237, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.01344, | |
| "grad_norm": 141396.296875, | |
| "learning_rate": 5.350742447516642e-07, | |
| "loss": 0.7217, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.01408, | |
| "grad_norm": 102339.1640625, | |
| "learning_rate": 5.606758832565284e-07, | |
| "loss": 0.7215, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.01472, | |
| "grad_norm": 134052.9375, | |
| "learning_rate": 5.862775217613928e-07, | |
| "loss": 0.7115, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.01536, | |
| "grad_norm": 87181.984375, | |
| "learning_rate": 6.118791602662571e-07, | |
| "loss": 0.7241, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.016, | |
| "grad_norm": 100231.328125, | |
| "learning_rate": 6.374807987711214e-07, | |
| "loss": 0.71, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.01664, | |
| "grad_norm": 136721.484375, | |
| "learning_rate": 6.630824372759858e-07, | |
| "loss": 0.7188, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.01728, | |
| "grad_norm": 115868.8125, | |
| "learning_rate": 6.8868407578085e-07, | |
| "loss": 0.7199, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.01792, | |
| "grad_norm": 70205.1484375, | |
| "learning_rate": 7.142857142857143e-07, | |
| "loss": 0.7299, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.01856, | |
| "grad_norm": 98926.4453125, | |
| "learning_rate": 7.398873527905787e-07, | |
| "loss": 0.7159, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.0192, | |
| "grad_norm": 134108.140625, | |
| "learning_rate": 7.65488991295443e-07, | |
| "loss": 0.7122, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.01984, | |
| "grad_norm": 103719.140625, | |
| "learning_rate": 7.910906298003073e-07, | |
| "loss": 0.7185, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.02048, | |
| "grad_norm": 85624.953125, | |
| "learning_rate": 8.166922683051716e-07, | |
| "loss": 0.718, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.02112, | |
| "grad_norm": 138824.15625, | |
| "learning_rate": 8.422939068100359e-07, | |
| "loss": 0.713, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.02176, | |
| "grad_norm": 73629.0859375, | |
| "learning_rate": 8.678955453149002e-07, | |
| "loss": 0.7186, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.0224, | |
| "grad_norm": 132493.0, | |
| "learning_rate": 8.934971838197646e-07, | |
| "loss": 0.7133, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.02304, | |
| "grad_norm": 85223.625, | |
| "learning_rate": 9.190988223246289e-07, | |
| "loss": 0.7124, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.02368, | |
| "grad_norm": 77868.78125, | |
| "learning_rate": 9.447004608294931e-07, | |
| "loss": 0.7058, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.02432, | |
| "grad_norm": 75874.3046875, | |
| "learning_rate": 9.703020993343575e-07, | |
| "loss": 0.7139, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.02496, | |
| "grad_norm": 151937.703125, | |
| "learning_rate": 9.959037378392218e-07, | |
| "loss": 0.713, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.0256, | |
| "grad_norm": 161711.671875, | |
| "learning_rate": 1.021505376344086e-06, | |
| "loss": 0.7137, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.02624, | |
| "grad_norm": 90800.234375, | |
| "learning_rate": 1.0471070148489503e-06, | |
| "loss": 0.7091, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.02688, | |
| "grad_norm": 82131.34375, | |
| "learning_rate": 1.0727086533538148e-06, | |
| "loss": 0.7098, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.02752, | |
| "grad_norm": 92818.9140625, | |
| "learning_rate": 1.0983102918586791e-06, | |
| "loss": 0.7099, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.02816, | |
| "grad_norm": 88555.5078125, | |
| "learning_rate": 1.1239119303635434e-06, | |
| "loss": 0.7086, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.0288, | |
| "grad_norm": 73428.6015625, | |
| "learning_rate": 1.1495135688684077e-06, | |
| "loss": 0.7117, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.02944, | |
| "grad_norm": 128938.7421875, | |
| "learning_rate": 1.175115207373272e-06, | |
| "loss": 0.7182, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.03008, | |
| "grad_norm": 102742.3359375, | |
| "learning_rate": 1.2007168458781362e-06, | |
| "loss": 0.7108, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.03072, | |
| "grad_norm": 73825.8125, | |
| "learning_rate": 1.2263184843830007e-06, | |
| "loss": 0.7087, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.03136, | |
| "grad_norm": 110930.75, | |
| "learning_rate": 1.251920122887865e-06, | |
| "loss": 0.7232, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.032, | |
| "grad_norm": 95068.84375, | |
| "learning_rate": 1.2775217613927293e-06, | |
| "loss": 0.703, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.03264, | |
| "grad_norm": 118731.9296875, | |
| "learning_rate": 1.3031233998975938e-06, | |
| "loss": 0.7063, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.03328, | |
| "grad_norm": 80511.828125, | |
| "learning_rate": 1.3287250384024578e-06, | |
| "loss": 0.7143, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.03392, | |
| "grad_norm": 84864.484375, | |
| "learning_rate": 1.354326676907322e-06, | |
| "loss": 0.7055, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.03456, | |
| "grad_norm": 107800.109375, | |
| "learning_rate": 1.3799283154121864e-06, | |
| "loss": 0.7119, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.0352, | |
| "grad_norm": 83667.671875, | |
| "learning_rate": 1.4055299539170509e-06, | |
| "loss": 0.7082, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.03584, | |
| "grad_norm": 75656.4140625, | |
| "learning_rate": 1.4311315924219151e-06, | |
| "loss": 0.7062, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.03648, | |
| "grad_norm": 79985.875, | |
| "learning_rate": 1.4567332309267796e-06, | |
| "loss": 0.7155, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.03712, | |
| "grad_norm": 76334.078125, | |
| "learning_rate": 1.4823348694316437e-06, | |
| "loss": 0.7075, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.03776, | |
| "grad_norm": 140764.03125, | |
| "learning_rate": 1.507936507936508e-06, | |
| "loss": 0.7065, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.0384, | |
| "grad_norm": 100877.296875, | |
| "learning_rate": 1.5335381464413722e-06, | |
| "loss": 0.7096, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.03904, | |
| "grad_norm": 104088.1171875, | |
| "learning_rate": 1.5591397849462367e-06, | |
| "loss": 0.6987, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.03968, | |
| "grad_norm": 80806.2265625, | |
| "learning_rate": 1.584741423451101e-06, | |
| "loss": 0.707, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.04032, | |
| "grad_norm": 109884.765625, | |
| "learning_rate": 1.6103430619559655e-06, | |
| "loss": 0.6991, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.04096, | |
| "grad_norm": 79944.890625, | |
| "learning_rate": 1.6359447004608298e-06, | |
| "loss": 0.7047, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.0416, | |
| "grad_norm": 93673.3828125, | |
| "learning_rate": 1.6615463389656938e-06, | |
| "loss": 0.6971, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.04224, | |
| "grad_norm": 76641.265625, | |
| "learning_rate": 1.6871479774705581e-06, | |
| "loss": 0.6957, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.04288, | |
| "grad_norm": 73583.5546875, | |
| "learning_rate": 1.7127496159754226e-06, | |
| "loss": 0.7028, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.04352, | |
| "grad_norm": 75177.9609375, | |
| "learning_rate": 1.7383512544802869e-06, | |
| "loss": 0.7012, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.04416, | |
| "grad_norm": 78340.8515625, | |
| "learning_rate": 1.7639528929851512e-06, | |
| "loss": 0.6987, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.0448, | |
| "grad_norm": 86004.1171875, | |
| "learning_rate": 1.7895545314900157e-06, | |
| "loss": 0.7061, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.04544, | |
| "grad_norm": 94212.0390625, | |
| "learning_rate": 1.8151561699948797e-06, | |
| "loss": 0.6993, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.04608, | |
| "grad_norm": 83918.2421875, | |
| "learning_rate": 1.840757808499744e-06, | |
| "loss": 0.7009, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.04672, | |
| "grad_norm": 68374.3125, | |
| "learning_rate": 1.8663594470046085e-06, | |
| "loss": 0.6964, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.04736, | |
| "grad_norm": 90348.78125, | |
| "learning_rate": 1.8919610855094728e-06, | |
| "loss": 0.7011, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.048, | |
| "grad_norm": 146658.0, | |
| "learning_rate": 1.9175627240143373e-06, | |
| "loss": 0.7003, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.04864, | |
| "grad_norm": 112037.1640625, | |
| "learning_rate": 1.9431643625192015e-06, | |
| "loss": 0.7051, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.04928, | |
| "grad_norm": 70628.625, | |
| "learning_rate": 1.9687660010240654e-06, | |
| "loss": 0.6923, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.04992, | |
| "grad_norm": 109922.125, | |
| "learning_rate": 1.99436763952893e-06, | |
| "loss": 0.6893, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.05056, | |
| "grad_norm": 135306.375, | |
| "learning_rate": 2.0199692780337944e-06, | |
| "loss": 0.7008, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.0512, | |
| "grad_norm": 82354.8046875, | |
| "learning_rate": 2.0455709165386586e-06, | |
| "loss": 0.705, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.05184, | |
| "grad_norm": 95951.671875, | |
| "learning_rate": 2.071172555043523e-06, | |
| "loss": 0.6912, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.05248, | |
| "grad_norm": 96797.4609375, | |
| "learning_rate": 2.096774193548387e-06, | |
| "loss": 0.6922, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.05312, | |
| "grad_norm": 87190.625, | |
| "learning_rate": 2.122375832053252e-06, | |
| "loss": 0.6946, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.05376, | |
| "grad_norm": 87958.5625, | |
| "learning_rate": 2.1479774705581158e-06, | |
| "loss": 0.6949, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.0544, | |
| "grad_norm": 77217.1796875, | |
| "learning_rate": 2.17357910906298e-06, | |
| "loss": 0.6928, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.05504, | |
| "grad_norm": 117156.5546875, | |
| "learning_rate": 2.1991807475678443e-06, | |
| "loss": 0.692, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.05568, | |
| "grad_norm": 94618.6875, | |
| "learning_rate": 2.224782386072709e-06, | |
| "loss": 0.6976, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.05632, | |
| "grad_norm": 71444.6484375, | |
| "learning_rate": 2.2503840245775733e-06, | |
| "loss": 0.6989, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.05696, | |
| "grad_norm": 159991.609375, | |
| "learning_rate": 2.2759856630824376e-06, | |
| "loss": 0.6928, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.0576, | |
| "grad_norm": 81899.6875, | |
| "learning_rate": 2.301587301587302e-06, | |
| "loss": 0.691, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.05824, | |
| "grad_norm": 110817.3671875, | |
| "learning_rate": 2.327188940092166e-06, | |
| "loss": 0.6858, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.05888, | |
| "grad_norm": 105698.109375, | |
| "learning_rate": 2.3527905785970304e-06, | |
| "loss": 0.6965, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.05952, | |
| "grad_norm": 76475.0, | |
| "learning_rate": 2.3783922171018947e-06, | |
| "loss": 0.6901, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.06016, | |
| "grad_norm": 96672.6796875, | |
| "learning_rate": 2.403993855606759e-06, | |
| "loss": 0.6908, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.0608, | |
| "grad_norm": 114510.8125, | |
| "learning_rate": 2.4295954941116232e-06, | |
| "loss": 0.6904, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.06144, | |
| "grad_norm": 62412.4375, | |
| "learning_rate": 2.455197132616488e-06, | |
| "loss": 0.6855, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.06208, | |
| "grad_norm": 92860.7109375, | |
| "learning_rate": 2.4807987711213518e-06, | |
| "loss": 0.6752, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.06272, | |
| "grad_norm": 75184.359375, | |
| "learning_rate": 2.506400409626216e-06, | |
| "loss": 0.6868, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.06336, | |
| "grad_norm": 77771.1640625, | |
| "learning_rate": 2.5320020481310808e-06, | |
| "loss": 0.6941, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.064, | |
| "grad_norm": 65366.796875, | |
| "learning_rate": 2.557603686635945e-06, | |
| "loss": 0.6808, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.064, | |
| "eval_accuracy": 0.75744, | |
| "eval_loss": 0.6539617776870728, | |
| "eval_macro_f1": 0.7549859375827388, | |
| "eval_runtime": 1576.6702, | |
| "eval_samples_per_second": 63.425, | |
| "eval_steps_per_second": 0.496, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.06464, | |
| "grad_norm": 73310.6171875, | |
| "learning_rate": 2.583205325140809e-06, | |
| "loss": 0.6866, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.06528, | |
| "grad_norm": 80602.859375, | |
| "learning_rate": 2.6088069636456736e-06, | |
| "loss": 0.6873, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.06592, | |
| "grad_norm": 121537.0234375, | |
| "learning_rate": 2.634408602150538e-06, | |
| "loss": 0.6806, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.06656, | |
| "grad_norm": 105537.46875, | |
| "learning_rate": 2.6600102406554026e-06, | |
| "loss": 0.6835, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.0672, | |
| "grad_norm": 188847.71875, | |
| "learning_rate": 2.6856118791602664e-06, | |
| "loss": 0.687, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.06784, | |
| "grad_norm": 73677.8359375, | |
| "learning_rate": 2.7112135176651307e-06, | |
| "loss": 0.6848, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.06848, | |
| "grad_norm": 72158.984375, | |
| "learning_rate": 2.736815156169995e-06, | |
| "loss": 0.6833, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.06912, | |
| "grad_norm": 73585.1015625, | |
| "learning_rate": 2.7624167946748593e-06, | |
| "loss": 0.6766, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.06976, | |
| "grad_norm": 78721.0390625, | |
| "learning_rate": 2.788018433179724e-06, | |
| "loss": 0.6796, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.0704, | |
| "grad_norm": 72044.3515625, | |
| "learning_rate": 2.813620071684588e-06, | |
| "loss": 0.673, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.07104, | |
| "grad_norm": 100059.984375, | |
| "learning_rate": 2.8392217101894525e-06, | |
| "loss": 0.6783, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.07168, | |
| "grad_norm": 92175.921875, | |
| "learning_rate": 2.864823348694317e-06, | |
| "loss": 0.6901, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.07232, | |
| "grad_norm": 86143.453125, | |
| "learning_rate": 2.8904249871991806e-06, | |
| "loss": 0.6769, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.07296, | |
| "grad_norm": 101410.171875, | |
| "learning_rate": 2.9160266257040453e-06, | |
| "loss": 0.6781, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.0736, | |
| "grad_norm": 67173.296875, | |
| "learning_rate": 2.9416282642089096e-06, | |
| "loss": 0.6737, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.07424, | |
| "grad_norm": 100701.8203125, | |
| "learning_rate": 2.967229902713774e-06, | |
| "loss": 0.6741, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.07488, | |
| "grad_norm": 75457.328125, | |
| "learning_rate": 2.992831541218638e-06, | |
| "loss": 0.6742, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.07552, | |
| "grad_norm": 97755.9921875, | |
| "learning_rate": 3.018433179723503e-06, | |
| "loss": 0.6845, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.07616, | |
| "grad_norm": 53426.1171875, | |
| "learning_rate": 3.0440348182283667e-06, | |
| "loss": 0.6718, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.0768, | |
| "grad_norm": 71654.625, | |
| "learning_rate": 3.069636456733231e-06, | |
| "loss": 0.6798, | |
| "step": 1200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 78125, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 200, | |
| "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": 1.010052097089216e+16, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |