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": 0.9548451024890077, | |
| "best_model_checkpoint": "taskA-unixcoder-focal/checkpoint-1000", | |
| "epoch": 0.06117704637220115, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006117704637220115, | |
| "grad_norm": 5.2196149826049805, | |
| "learning_rate": 9.178990311065784e-08, | |
| "loss": 0.2114, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001223540927444023, | |
| "grad_norm": 2.4952661991119385, | |
| "learning_rate": 1.937786843447221e-07, | |
| "loss": 0.179, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0018353113911660345, | |
| "grad_norm": 3.8488683700561523, | |
| "learning_rate": 2.9576746557878637e-07, | |
| "loss": 0.1949, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002447081854888046, | |
| "grad_norm": 3.7437973022460938, | |
| "learning_rate": 3.9775624681285064e-07, | |
| "loss": 0.2007, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0030588523186100575, | |
| "grad_norm": 3.8342156410217285, | |
| "learning_rate": 4.997450280469149e-07, | |
| "loss": 0.1828, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.003670622782332069, | |
| "grad_norm": 3.510793685913086, | |
| "learning_rate": 6.017338092809792e-07, | |
| "loss": 0.1875, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0042823932460540805, | |
| "grad_norm": 3.223860740661621, | |
| "learning_rate": 7.037225905150434e-07, | |
| "loss": 0.1661, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.004894163709776092, | |
| "grad_norm": 3.791808605194092, | |
| "learning_rate": 8.057113717491076e-07, | |
| "loss": 0.1762, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0055059341734981036, | |
| "grad_norm": 3.8649113178253174, | |
| "learning_rate": 9.077001529831719e-07, | |
| "loss": 0.1774, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.006117704637220115, | |
| "grad_norm": 2.9645302295684814, | |
| "learning_rate": 1.0096889342172361e-06, | |
| "loss": 0.1741, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.006729475100942127, | |
| "grad_norm": 2.9103174209594727, | |
| "learning_rate": 1.1116777154513005e-06, | |
| "loss": 0.1808, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.007341245564664138, | |
| "grad_norm": 2.3954272270202637, | |
| "learning_rate": 1.2136664966853646e-06, | |
| "loss": 0.161, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.00795301602838615, | |
| "grad_norm": 3.030513048171997, | |
| "learning_rate": 1.3156552779194289e-06, | |
| "loss": 0.1689, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.008564786492108161, | |
| "grad_norm": 1.7593587636947632, | |
| "learning_rate": 1.4176440591534932e-06, | |
| "loss": 0.1595, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.009176556955830173, | |
| "grad_norm": 1.9787609577178955, | |
| "learning_rate": 1.5196328403875573e-06, | |
| "loss": 0.1429, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.009788327419552184, | |
| "grad_norm": 2.549748659133911, | |
| "learning_rate": 1.6216216216216219e-06, | |
| "loss": 0.154, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.010400097883274196, | |
| "grad_norm": 2.4056687355041504, | |
| "learning_rate": 1.723610402855686e-06, | |
| "loss": 0.1582, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.011011868346996207, | |
| "grad_norm": 3.3082435131073, | |
| "learning_rate": 1.8255991840897503e-06, | |
| "loss": 0.1502, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.011623638810718219, | |
| "grad_norm": 3.446185350418091, | |
| "learning_rate": 1.9275879653238146e-06, | |
| "loss": 0.1452, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.01223540927444023, | |
| "grad_norm": 2.6021993160247803, | |
| "learning_rate": 2.029576746557879e-06, | |
| "loss": 0.1404, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.012847179738162242, | |
| "grad_norm": 2.1967263221740723, | |
| "learning_rate": 2.1315655277919432e-06, | |
| "loss": 0.1421, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.013458950201884253, | |
| "grad_norm": 1.9831513166427612, | |
| "learning_rate": 2.233554309026007e-06, | |
| "loss": 0.1431, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.014070720665606265, | |
| "grad_norm": 1.7445921897888184, | |
| "learning_rate": 2.3355430902600715e-06, | |
| "loss": 0.1242, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.014682491129328276, | |
| "grad_norm": 2.7725071907043457, | |
| "learning_rate": 2.4375318714941358e-06, | |
| "loss": 0.1346, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.015294261593050288, | |
| "grad_norm": 1.7258802652359009, | |
| "learning_rate": 2.5395206527282e-06, | |
| "loss": 0.1371, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.0159060320567723, | |
| "grad_norm": 2.1158506870269775, | |
| "learning_rate": 2.6415094339622644e-06, | |
| "loss": 0.1271, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.01651780252049431, | |
| "grad_norm": 2.0771985054016113, | |
| "learning_rate": 2.7434982151963283e-06, | |
| "loss": 0.1214, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.017129572984216322, | |
| "grad_norm": 2.924894332885742, | |
| "learning_rate": 2.8454869964303926e-06, | |
| "loss": 0.1281, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.017741343447938332, | |
| "grad_norm": 2.122687578201294, | |
| "learning_rate": 2.947475777664457e-06, | |
| "loss": 0.132, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.018353113911660345, | |
| "grad_norm": 3.2565481662750244, | |
| "learning_rate": 3.0494645588985217e-06, | |
| "loss": 0.1336, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.018964884375382355, | |
| "grad_norm": 1.2805263996124268, | |
| "learning_rate": 3.151453340132586e-06, | |
| "loss": 0.1183, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.019576654839104368, | |
| "grad_norm": 2.420628786087036, | |
| "learning_rate": 3.25344212136665e-06, | |
| "loss": 0.1125, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.020188425302826378, | |
| "grad_norm": 2.887117862701416, | |
| "learning_rate": 3.3554309026007142e-06, | |
| "loss": 0.1041, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.02080019576654839, | |
| "grad_norm": 1.6021567583084106, | |
| "learning_rate": 3.4574196838347786e-06, | |
| "loss": 0.1221, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.0214119662302704, | |
| "grad_norm": 2.9132304191589355, | |
| "learning_rate": 3.5594084650688425e-06, | |
| "loss": 0.1094, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.022023736693992414, | |
| "grad_norm": 2.5460691452026367, | |
| "learning_rate": 3.6613972463029068e-06, | |
| "loss": 0.1096, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.022635507157714424, | |
| "grad_norm": 2.2170896530151367, | |
| "learning_rate": 3.763386027536971e-06, | |
| "loss": 0.0933, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.023247277621436437, | |
| "grad_norm": 3.799591541290283, | |
| "learning_rate": 3.865374808771036e-06, | |
| "loss": 0.1142, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.023859048085158447, | |
| "grad_norm": 4.609161376953125, | |
| "learning_rate": 3.9673635900051e-06, | |
| "loss": 0.0948, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.02447081854888046, | |
| "grad_norm": 3.329650402069092, | |
| "learning_rate": 4.0693523712391645e-06, | |
| "loss": 0.0944, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.02508258901260247, | |
| "grad_norm": 2.135805368423462, | |
| "learning_rate": 4.171341152473228e-06, | |
| "loss": 0.0847, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.025694359476324483, | |
| "grad_norm": 2.006049156188965, | |
| "learning_rate": 4.273329933707292e-06, | |
| "loss": 0.1077, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.026306129940046493, | |
| "grad_norm": 5.709030628204346, | |
| "learning_rate": 4.375318714941357e-06, | |
| "loss": 0.099, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.026917900403768506, | |
| "grad_norm": 2.466867446899414, | |
| "learning_rate": 4.477307496175421e-06, | |
| "loss": 0.0771, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.027529670867490516, | |
| "grad_norm": 2.3829548358917236, | |
| "learning_rate": 4.579296277409485e-06, | |
| "loss": 0.0802, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.02814144133121253, | |
| "grad_norm": 2.990241050720215, | |
| "learning_rate": 4.6812850586435496e-06, | |
| "loss": 0.1048, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.02875321179493454, | |
| "grad_norm": 3.7126529216766357, | |
| "learning_rate": 4.783273839877614e-06, | |
| "loss": 0.0879, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.029364982258656552, | |
| "grad_norm": 2.6238865852355957, | |
| "learning_rate": 4.885262621111678e-06, | |
| "loss": 0.0825, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.029976752722378562, | |
| "grad_norm": 2.1882681846618652, | |
| "learning_rate": 4.987251402345742e-06, | |
| "loss": 0.0821, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.030588523186100575, | |
| "grad_norm": 2.1399929523468018, | |
| "learning_rate": 5.089240183579807e-06, | |
| "loss": 0.0926, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.030588523186100575, | |
| "eval_accuracy": 0.8732, | |
| "eval_f1_weighted": 0.8728301347090768, | |
| "eval_loss": 0.08081420511007309, | |
| "eval_macro_f1": 0.8730387325792941, | |
| "eval_precision": 0.8842823474890878, | |
| "eval_recall": 0.8732, | |
| "eval_runtime": 1731.362, | |
| "eval_samples_per_second": 57.758, | |
| "eval_steps_per_second": 0.903, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.031200293649822585, | |
| "grad_norm": 4.9644694328308105, | |
| "learning_rate": 5.191228964813872e-06, | |
| "loss": 0.0846, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.0318120641135446, | |
| "grad_norm": 3.2999346256256104, | |
| "learning_rate": 5.293217746047935e-06, | |
| "loss": 0.0774, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.03242383457726661, | |
| "grad_norm": 1.9823625087738037, | |
| "learning_rate": 5.395206527281999e-06, | |
| "loss": 0.0781, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.03303560504098862, | |
| "grad_norm": 2.010012149810791, | |
| "learning_rate": 5.497195308516063e-06, | |
| "loss": 0.0748, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.033647375504710635, | |
| "grad_norm": 1.7753310203552246, | |
| "learning_rate": 5.599184089750128e-06, | |
| "loss": 0.0687, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.034259145968432644, | |
| "grad_norm": 1.4343310594558716, | |
| "learning_rate": 5.701172870984192e-06, | |
| "loss": 0.0729, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.034870916432154654, | |
| "grad_norm": 2.562145948410034, | |
| "learning_rate": 5.803161652218257e-06, | |
| "loss": 0.0712, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.035482686895876664, | |
| "grad_norm": 1.727373480796814, | |
| "learning_rate": 5.9051504334523206e-06, | |
| "loss": 0.0605, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.03609445735959868, | |
| "grad_norm": 1.8711422681808472, | |
| "learning_rate": 6.007139214686385e-06, | |
| "loss": 0.071, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.03670622782332069, | |
| "grad_norm": 7.535566329956055, | |
| "learning_rate": 6.10912799592045e-06, | |
| "loss": 0.067, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.0373179982870427, | |
| "grad_norm": 3.9871439933776855, | |
| "learning_rate": 6.211116777154513e-06, | |
| "loss": 0.063, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.03792976875076471, | |
| "grad_norm": 2.457789659500122, | |
| "learning_rate": 6.313105558388578e-06, | |
| "loss": 0.0905, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.03854153921448673, | |
| "grad_norm": 4.795208930969238, | |
| "learning_rate": 6.415094339622642e-06, | |
| "loss": 0.0611, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.039153309678208736, | |
| "grad_norm": 3.688422441482544, | |
| "learning_rate": 6.5170831208567065e-06, | |
| "loss": 0.0657, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.039765080141930746, | |
| "grad_norm": 4.9787116050720215, | |
| "learning_rate": 6.61907190209077e-06, | |
| "loss": 0.0593, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.040376850605652756, | |
| "grad_norm": 6.09706974029541, | |
| "learning_rate": 6.721060683324835e-06, | |
| "loss": 0.0803, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.04098862106937477, | |
| "grad_norm": 1.9047552347183228, | |
| "learning_rate": 6.8230494645589e-06, | |
| "loss": 0.0486, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.04160039153309678, | |
| "grad_norm": 3.514389753341675, | |
| "learning_rate": 6.925038245792963e-06, | |
| "loss": 0.058, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.04221216199681879, | |
| "grad_norm": 3.366957187652588, | |
| "learning_rate": 7.027027027027028e-06, | |
| "loss": 0.0651, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.0428239324605408, | |
| "grad_norm": 4.780582904815674, | |
| "learning_rate": 7.1290158082610916e-06, | |
| "loss": 0.0561, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.04343570292426282, | |
| "grad_norm": 2.457082748413086, | |
| "learning_rate": 7.231004589495156e-06, | |
| "loss": 0.0611, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.04404747338798483, | |
| "grad_norm": 1.283014178276062, | |
| "learning_rate": 7.33299337072922e-06, | |
| "loss": 0.0601, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.04465924385170684, | |
| "grad_norm": 3.092107057571411, | |
| "learning_rate": 7.434982151963285e-06, | |
| "loss": 0.0598, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.04527101431542885, | |
| "grad_norm": 1.26460599899292, | |
| "learning_rate": 7.536970933197348e-06, | |
| "loss": 0.0503, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.045882784779150865, | |
| "grad_norm": 2.9157862663269043, | |
| "learning_rate": 7.638959714431414e-06, | |
| "loss": 0.0507, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.046494555242872875, | |
| "grad_norm": 5.487971782684326, | |
| "learning_rate": 7.740948495665478e-06, | |
| "loss": 0.0525, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.047106325706594884, | |
| "grad_norm": 2.9894769191741943, | |
| "learning_rate": 7.842937276899541e-06, | |
| "loss": 0.0656, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.047718096170316894, | |
| "grad_norm": 2.7786455154418945, | |
| "learning_rate": 7.944926058133606e-06, | |
| "loss": 0.0521, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.04832986663403891, | |
| "grad_norm": 1.3629153966903687, | |
| "learning_rate": 8.04691483936767e-06, | |
| "loss": 0.0529, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.04894163709776092, | |
| "grad_norm": 4.066152572631836, | |
| "learning_rate": 8.148903620601734e-06, | |
| "loss": 0.047, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.04955340756148293, | |
| "grad_norm": 2.162338972091675, | |
| "learning_rate": 8.250892401835799e-06, | |
| "loss": 0.0583, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.05016517802520494, | |
| "grad_norm": 1.5794885158538818, | |
| "learning_rate": 8.352881183069863e-06, | |
| "loss": 0.0415, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.05077694848892696, | |
| "grad_norm": 5.697793960571289, | |
| "learning_rate": 8.454869964303928e-06, | |
| "loss": 0.0614, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.05138871895264897, | |
| "grad_norm": 2.243929386138916, | |
| "learning_rate": 8.556858745537991e-06, | |
| "loss": 0.0836, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.052000489416370976, | |
| "grad_norm": 1.272515892982483, | |
| "learning_rate": 8.658847526772056e-06, | |
| "loss": 0.05, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.052612259880092986, | |
| "grad_norm": 1.4770886898040771, | |
| "learning_rate": 8.760836308006119e-06, | |
| "loss": 0.0403, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.053224030343815, | |
| "grad_norm": 3.411848306655884, | |
| "learning_rate": 8.862825089240184e-06, | |
| "loss": 0.0478, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.05383580080753701, | |
| "grad_norm": 8.478028297424316, | |
| "learning_rate": 8.964813870474248e-06, | |
| "loss": 0.0855, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.05444757127125902, | |
| "grad_norm": 0.6067395806312561, | |
| "learning_rate": 9.066802651708313e-06, | |
| "loss": 0.0366, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.05505934173498103, | |
| "grad_norm": 2.6501152515411377, | |
| "learning_rate": 9.168791432942376e-06, | |
| "loss": 0.0358, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.05567111219870305, | |
| "grad_norm": 1.1650569438934326, | |
| "learning_rate": 9.270780214176441e-06, | |
| "loss": 0.0733, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.05628288266242506, | |
| "grad_norm": 2.4513559341430664, | |
| "learning_rate": 9.372768995410506e-06, | |
| "loss": 0.0535, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.05689465312614707, | |
| "grad_norm": 0.8360533714294434, | |
| "learning_rate": 9.47475777664457e-06, | |
| "loss": 0.0453, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.05750642358986908, | |
| "grad_norm": 2.2937448024749756, | |
| "learning_rate": 9.576746557878635e-06, | |
| "loss": 0.0655, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.058118194053591095, | |
| "grad_norm": 2.025761127471924, | |
| "learning_rate": 9.678735339112698e-06, | |
| "loss": 0.06, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.058729964517313105, | |
| "grad_norm": 2.6468706130981445, | |
| "learning_rate": 9.780724120346763e-06, | |
| "loss": 0.0416, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.059341734981035114, | |
| "grad_norm": 3.626215934753418, | |
| "learning_rate": 9.882712901580826e-06, | |
| "loss": 0.0239, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.059953505444757124, | |
| "grad_norm": 2.599356174468994, | |
| "learning_rate": 9.984701682814891e-06, | |
| "loss": 0.0395, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.06056527590847914, | |
| "grad_norm": 2.4896769523620605, | |
| "learning_rate": 1.0086690464048956e-05, | |
| "loss": 0.0703, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.06117704637220115, | |
| "grad_norm": 2.18449068069458, | |
| "learning_rate": 1.018867924528302e-05, | |
| "loss": 0.0306, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.06117704637220115, | |
| "eval_accuracy": 0.95488, | |
| "eval_f1_weighted": 0.9549029721025599, | |
| "eval_loss": 0.03926030173897743, | |
| "eval_macro_f1": 0.9548451024890077, | |
| "eval_precision": 0.955565530093091, | |
| "eval_recall": 0.95488, | |
| "eval_runtime": 1718.0831, | |
| "eval_samples_per_second": 58.204, | |
| "eval_steps_per_second": 0.91, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 16346, | |
| "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": 8415771550099200.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |