| { | |
| "best_metric": 0.6137931034482759, | |
| "best_model_checkpoint": "convnextv2-base-22k-224-finetuned-tekno24/checkpoint-860", | |
| "epoch": 11.961661341853034, | |
| "eval_steps": 500, | |
| "global_step": 936, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12779552715654952, | |
| "grad_norm": 11.641097068786621, | |
| "learning_rate": 5.319148936170213e-06, | |
| "loss": 1.4077, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.25559105431309903, | |
| "grad_norm": 10.328614234924316, | |
| "learning_rate": 1.0638297872340426e-05, | |
| "loss": 1.3907, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.38338658146964855, | |
| "grad_norm": 11.496760368347168, | |
| "learning_rate": 1.595744680851064e-05, | |
| "loss": 1.3597, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5111821086261981, | |
| "grad_norm": 9.975175857543945, | |
| "learning_rate": 2.1276595744680852e-05, | |
| "loss": 1.354, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6389776357827476, | |
| "grad_norm": 11.381126403808594, | |
| "learning_rate": 2.6595744680851064e-05, | |
| "loss": 1.3266, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7667731629392971, | |
| "grad_norm": 9.771955490112305, | |
| "learning_rate": 3.191489361702128e-05, | |
| "loss": 1.291, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.8945686900958466, | |
| "grad_norm": 21.0851993560791, | |
| "learning_rate": 3.617021276595745e-05, | |
| "loss": 1.3179, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.9968051118210862, | |
| "eval_accuracy": 0.4206896551724138, | |
| "eval_f1": 0.39792953648489043, | |
| "eval_loss": 1.2415151596069336, | |
| "eval_precision": 0.4642161976696202, | |
| "eval_recall": 0.4206896551724138, | |
| "eval_runtime": 4.2118, | |
| "eval_samples_per_second": 103.281, | |
| "eval_steps_per_second": 6.648, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.0223642172523961, | |
| "grad_norm": 19.948223114013672, | |
| "learning_rate": 4.148936170212766e-05, | |
| "loss": 1.2668, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.1501597444089458, | |
| "grad_norm": 11.563603401184082, | |
| "learning_rate": 4.680851063829788e-05, | |
| "loss": 1.2202, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.2779552715654952, | |
| "grad_norm": 9.605425834655762, | |
| "learning_rate": 4.97624703087886e-05, | |
| "loss": 1.2626, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.4057507987220448, | |
| "grad_norm": 10.846478462219238, | |
| "learning_rate": 4.9168646080760093e-05, | |
| "loss": 1.251, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.5335463258785942, | |
| "grad_norm": 10.546998023986816, | |
| "learning_rate": 4.8574821852731594e-05, | |
| "loss": 1.2136, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.6613418530351438, | |
| "grad_norm": 10.678705215454102, | |
| "learning_rate": 4.798099762470309e-05, | |
| "loss": 1.1764, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.7891373801916934, | |
| "grad_norm": 10.283668518066406, | |
| "learning_rate": 4.738717339667459e-05, | |
| "loss": 1.2624, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.9169329073482428, | |
| "grad_norm": 10.07646656036377, | |
| "learning_rate": 4.679334916864608e-05, | |
| "loss": 1.1998, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.9936102236421727, | |
| "eval_accuracy": 0.5103448275862069, | |
| "eval_f1": 0.4525112700085999, | |
| "eval_loss": 1.0768730640411377, | |
| "eval_precision": 0.5309344450319118, | |
| "eval_recall": 0.5103448275862069, | |
| "eval_runtime": 4.2293, | |
| "eval_samples_per_second": 102.853, | |
| "eval_steps_per_second": 6.62, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 2.0447284345047922, | |
| "grad_norm": 10.981221199035645, | |
| "learning_rate": 4.6199524940617575e-05, | |
| "loss": 1.1287, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.1725239616613417, | |
| "grad_norm": 6.460533142089844, | |
| "learning_rate": 4.5605700712589075e-05, | |
| "loss": 1.1806, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.3003194888178915, | |
| "grad_norm": 7.450798511505127, | |
| "learning_rate": 4.501187648456057e-05, | |
| "loss": 1.1834, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.428115015974441, | |
| "grad_norm": 5.972067832946777, | |
| "learning_rate": 4.441805225653207e-05, | |
| "loss": 1.1639, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.5559105431309903, | |
| "grad_norm": 10.565897941589355, | |
| "learning_rate": 4.382422802850357e-05, | |
| "loss": 1.143, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.68370607028754, | |
| "grad_norm": 11.751137733459473, | |
| "learning_rate": 4.323040380047506e-05, | |
| "loss": 1.1911, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.8115015974440896, | |
| "grad_norm": 8.518805503845215, | |
| "learning_rate": 4.263657957244656e-05, | |
| "loss": 1.169, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.939297124600639, | |
| "grad_norm": 7.631802558898926, | |
| "learning_rate": 4.204275534441806e-05, | |
| "loss": 1.168, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.9904153354632586, | |
| "eval_accuracy": 0.5494252873563218, | |
| "eval_f1": 0.5033023418313557, | |
| "eval_loss": 1.0573328733444214, | |
| "eval_precision": 0.5604674717576669, | |
| "eval_recall": 0.5494252873563218, | |
| "eval_runtime": 4.2015, | |
| "eval_samples_per_second": 103.535, | |
| "eval_steps_per_second": 6.664, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 3.0670926517571884, | |
| "grad_norm": 7.9839911460876465, | |
| "learning_rate": 4.144893111638955e-05, | |
| "loss": 1.1172, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.194888178913738, | |
| "grad_norm": 8.082262992858887, | |
| "learning_rate": 4.0855106888361044e-05, | |
| "loss": 1.1659, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.3226837060702876, | |
| "grad_norm": 5.319189548492432, | |
| "learning_rate": 4.0261282660332545e-05, | |
| "loss": 1.1493, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.450479233226837, | |
| "grad_norm": 8.54591178894043, | |
| "learning_rate": 3.966745843230404e-05, | |
| "loss": 1.1158, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.5782747603833864, | |
| "grad_norm": 9.336274147033691, | |
| "learning_rate": 3.907363420427554e-05, | |
| "loss": 1.1638, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.7060702875399363, | |
| "grad_norm": 8.625086784362793, | |
| "learning_rate": 3.847980997624703e-05, | |
| "loss": 1.0932, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.8338658146964857, | |
| "grad_norm": 9.026288032531738, | |
| "learning_rate": 3.7885985748218526e-05, | |
| "loss": 1.1056, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.961661341853035, | |
| "grad_norm": 10.40346622467041, | |
| "learning_rate": 3.7292161520190026e-05, | |
| "loss": 1.1107, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5540229885057472, | |
| "eval_f1": 0.5163004360032211, | |
| "eval_loss": 0.9923611879348755, | |
| "eval_precision": 0.525717492734745, | |
| "eval_recall": 0.5540229885057472, | |
| "eval_runtime": 4.1795, | |
| "eval_samples_per_second": 104.079, | |
| "eval_steps_per_second": 6.699, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 4.0894568690095845, | |
| "grad_norm": 6.684942722320557, | |
| "learning_rate": 3.669833729216152e-05, | |
| "loss": 1.1252, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.217252396166134, | |
| "grad_norm": 10.904282569885254, | |
| "learning_rate": 3.6104513064133013e-05, | |
| "loss": 1.1098, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.345047923322683, | |
| "grad_norm": 9.764264106750488, | |
| "learning_rate": 3.5510688836104514e-05, | |
| "loss": 1.096, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.472843450479234, | |
| "grad_norm": 8.857853889465332, | |
| "learning_rate": 3.4916864608076014e-05, | |
| "loss": 1.0528, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.600638977635783, | |
| "grad_norm": 7.500421524047852, | |
| "learning_rate": 3.432304038004751e-05, | |
| "loss": 1.1455, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.728434504792332, | |
| "grad_norm": 9.362208366394043, | |
| "learning_rate": 3.372921615201901e-05, | |
| "loss": 1.0993, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 4.856230031948882, | |
| "grad_norm": 9.38844108581543, | |
| "learning_rate": 3.31353919239905e-05, | |
| "loss": 1.0855, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.984025559105431, | |
| "grad_norm": 6.451258659362793, | |
| "learning_rate": 3.2541567695961995e-05, | |
| "loss": 1.1062, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 4.996805111821086, | |
| "eval_accuracy": 0.5747126436781609, | |
| "eval_f1": 0.5507051314754062, | |
| "eval_loss": 1.0018237829208374, | |
| "eval_precision": 0.5659922189344513, | |
| "eval_recall": 0.5747126436781609, | |
| "eval_runtime": 4.1822, | |
| "eval_samples_per_second": 104.012, | |
| "eval_steps_per_second": 6.695, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 5.111821086261981, | |
| "grad_norm": 8.044933319091797, | |
| "learning_rate": 3.1947743467933496e-05, | |
| "loss": 1.0556, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.23961661341853, | |
| "grad_norm": 9.200007438659668, | |
| "learning_rate": 3.135391923990499e-05, | |
| "loss": 1.056, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 5.36741214057508, | |
| "grad_norm": 9.929868698120117, | |
| "learning_rate": 3.076009501187649e-05, | |
| "loss": 1.0098, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 5.49520766773163, | |
| "grad_norm": 7.43991231918335, | |
| "learning_rate": 3.0166270783847983e-05, | |
| "loss": 1.1396, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 5.623003194888179, | |
| "grad_norm": 7.019424915313721, | |
| "learning_rate": 2.9572446555819477e-05, | |
| "loss": 1.0659, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 5.7507987220447285, | |
| "grad_norm": 7.227243900299072, | |
| "learning_rate": 2.8978622327790977e-05, | |
| "loss": 1.0453, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 5.878594249201278, | |
| "grad_norm": 9.71042537689209, | |
| "learning_rate": 2.838479809976247e-05, | |
| "loss": 1.0331, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 5.993610223642173, | |
| "eval_accuracy": 0.593103448275862, | |
| "eval_f1": 0.5768496494171164, | |
| "eval_loss": 0.9901189208030701, | |
| "eval_precision": 0.6202225107325855, | |
| "eval_recall": 0.593103448275862, | |
| "eval_runtime": 4.1789, | |
| "eval_samples_per_second": 104.095, | |
| "eval_steps_per_second": 6.7, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 6.006389776357827, | |
| "grad_norm": 6.03436279296875, | |
| "learning_rate": 2.7790973871733968e-05, | |
| "loss": 1.135, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 6.134185303514377, | |
| "grad_norm": 7.317747592926025, | |
| "learning_rate": 2.7197149643705465e-05, | |
| "loss": 1.0316, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 6.261980830670926, | |
| "grad_norm": 7.093214511871338, | |
| "learning_rate": 2.6603325415676962e-05, | |
| "loss": 1.0445, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 6.389776357827476, | |
| "grad_norm": 8.44990348815918, | |
| "learning_rate": 2.6009501187648455e-05, | |
| "loss": 1.064, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.517571884984026, | |
| "grad_norm": 8.586387634277344, | |
| "learning_rate": 2.5415676959619956e-05, | |
| "loss": 1.0428, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 6.645367412140575, | |
| "grad_norm": 8.286543846130371, | |
| "learning_rate": 2.482185273159145e-05, | |
| "loss": 1.0424, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 6.773162939297125, | |
| "grad_norm": 11.05722427368164, | |
| "learning_rate": 2.4228028503562946e-05, | |
| "loss": 1.0486, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 6.900958466453674, | |
| "grad_norm": 11.715845108032227, | |
| "learning_rate": 2.3634204275534443e-05, | |
| "loss": 1.0409, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 6.9904153354632586, | |
| "eval_accuracy": 0.5747126436781609, | |
| "eval_f1": 0.5723268617274374, | |
| "eval_loss": 0.9633908867835999, | |
| "eval_precision": 0.5722167544506434, | |
| "eval_recall": 0.5747126436781609, | |
| "eval_runtime": 4.2036, | |
| "eval_samples_per_second": 103.482, | |
| "eval_steps_per_second": 6.661, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 7.0287539936102235, | |
| "grad_norm": 9.900256156921387, | |
| "learning_rate": 2.3040380047505937e-05, | |
| "loss": 1.021, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 7.156549520766773, | |
| "grad_norm": 11.22358226776123, | |
| "learning_rate": 2.2446555819477437e-05, | |
| "loss": 1.0387, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 7.284345047923322, | |
| "grad_norm": 6.466274738311768, | |
| "learning_rate": 2.1852731591448934e-05, | |
| "loss": 1.0166, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 7.412140575079873, | |
| "grad_norm": 9.685991287231445, | |
| "learning_rate": 2.1258907363420428e-05, | |
| "loss": 1.0459, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 7.539936102236422, | |
| "grad_norm": 9.211965560913086, | |
| "learning_rate": 2.0665083135391925e-05, | |
| "loss": 0.9852, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 7.667731629392971, | |
| "grad_norm": 9.930057525634766, | |
| "learning_rate": 2.0071258907363422e-05, | |
| "loss": 1.0176, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 7.795527156549521, | |
| "grad_norm": 12.529800415039062, | |
| "learning_rate": 1.947743467933492e-05, | |
| "loss": 1.0465, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 7.92332268370607, | |
| "grad_norm": 9.018549919128418, | |
| "learning_rate": 1.8883610451306412e-05, | |
| "loss": 1.0176, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.593103448275862, | |
| "eval_f1": 0.5833555266825051, | |
| "eval_loss": 0.9504066705703735, | |
| "eval_precision": 0.5813528993323179, | |
| "eval_recall": 0.593103448275862, | |
| "eval_runtime": 4.1774, | |
| "eval_samples_per_second": 104.131, | |
| "eval_steps_per_second": 6.703, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 8.05111821086262, | |
| "grad_norm": 8.328828811645508, | |
| "learning_rate": 1.828978622327791e-05, | |
| "loss": 0.9516, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 8.178913738019169, | |
| "grad_norm": 7.750000476837158, | |
| "learning_rate": 1.7695961995249406e-05, | |
| "loss": 0.972, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 8.30670926517572, | |
| "grad_norm": 6.95557165145874, | |
| "learning_rate": 1.7102137767220903e-05, | |
| "loss": 0.9842, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 8.434504792332268, | |
| "grad_norm": 8.893524169921875, | |
| "learning_rate": 1.65083135391924e-05, | |
| "loss": 1.02, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 8.562300319488818, | |
| "grad_norm": 9.984440803527832, | |
| "learning_rate": 1.5914489311163897e-05, | |
| "loss": 0.97, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 8.690095846645367, | |
| "grad_norm": 8.314949989318848, | |
| "learning_rate": 1.5320665083135394e-05, | |
| "loss": 1.0366, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 8.817891373801917, | |
| "grad_norm": 9.685540199279785, | |
| "learning_rate": 1.4726840855106888e-05, | |
| "loss": 1.0284, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 8.945686900958467, | |
| "grad_norm": 10.43076229095459, | |
| "learning_rate": 1.4133016627078385e-05, | |
| "loss": 0.995, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 8.996805111821086, | |
| "eval_accuracy": 0.5908045977011495, | |
| "eval_f1": 0.5853582114263199, | |
| "eval_loss": 0.9584209322929382, | |
| "eval_precision": 0.5853113777126823, | |
| "eval_recall": 0.5908045977011495, | |
| "eval_runtime": 4.2105, | |
| "eval_samples_per_second": 103.314, | |
| "eval_steps_per_second": 6.65, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 9.073482428115016, | |
| "grad_norm": 8.847938537597656, | |
| "learning_rate": 1.3539192399049882e-05, | |
| "loss": 0.9524, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 9.201277955271566, | |
| "grad_norm": 8.750248908996582, | |
| "learning_rate": 1.2945368171021377e-05, | |
| "loss": 0.9846, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 9.329073482428115, | |
| "grad_norm": 9.161256790161133, | |
| "learning_rate": 1.2351543942992874e-05, | |
| "loss": 0.9751, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 9.456869009584665, | |
| "grad_norm": 9.544412612915039, | |
| "learning_rate": 1.1757719714964371e-05, | |
| "loss": 0.9417, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 9.584664536741213, | |
| "grad_norm": 9.703606605529785, | |
| "learning_rate": 1.1163895486935868e-05, | |
| "loss": 0.9707, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 9.712460063897764, | |
| "grad_norm": 9.677326202392578, | |
| "learning_rate": 1.0570071258907365e-05, | |
| "loss": 1.0009, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 9.840255591054314, | |
| "grad_norm": 8.860432624816895, | |
| "learning_rate": 9.97624703087886e-06, | |
| "loss": 0.9817, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 9.968051118210862, | |
| "grad_norm": 8.743229866027832, | |
| "learning_rate": 9.382422802850356e-06, | |
| "loss": 0.9937, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 9.993610223642172, | |
| "eval_accuracy": 0.6022988505747127, | |
| "eval_f1": 0.5934331301305344, | |
| "eval_loss": 0.9338871240615845, | |
| "eval_precision": 0.5893665058889589, | |
| "eval_recall": 0.6022988505747127, | |
| "eval_runtime": 4.2268, | |
| "eval_samples_per_second": 102.915, | |
| "eval_steps_per_second": 6.624, | |
| "step": 782 | |
| }, | |
| { | |
| "epoch": 10.095846645367413, | |
| "grad_norm": 7.1755900382995605, | |
| "learning_rate": 8.788598574821852e-06, | |
| "loss": 0.9908, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 10.223642172523961, | |
| "grad_norm": 8.917673110961914, | |
| "learning_rate": 8.19477434679335e-06, | |
| "loss": 0.9361, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 10.351437699680512, | |
| "grad_norm": 15.518793106079102, | |
| "learning_rate": 7.6009501187648464e-06, | |
| "loss": 0.9495, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 10.47923322683706, | |
| "grad_norm": 12.074665069580078, | |
| "learning_rate": 7.007125890736342e-06, | |
| "loss": 0.9689, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 10.60702875399361, | |
| "grad_norm": 9.314558982849121, | |
| "learning_rate": 6.4133016627078396e-06, | |
| "loss": 0.983, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 10.73482428115016, | |
| "grad_norm": 9.714004516601562, | |
| "learning_rate": 5.819477434679335e-06, | |
| "loss": 1.0, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 10.86261980830671, | |
| "grad_norm": 9.66527271270752, | |
| "learning_rate": 5.225653206650832e-06, | |
| "loss": 0.9036, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 10.99041533546326, | |
| "grad_norm": 11.544416427612305, | |
| "learning_rate": 4.631828978622328e-06, | |
| "loss": 0.9387, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 10.99041533546326, | |
| "eval_accuracy": 0.6137931034482759, | |
| "eval_f1": 0.5996477650763593, | |
| "eval_loss": 0.9119637608528137, | |
| "eval_precision": 0.596855024118962, | |
| "eval_recall": 0.6137931034482759, | |
| "eval_runtime": 4.2091, | |
| "eval_samples_per_second": 103.347, | |
| "eval_steps_per_second": 6.652, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 11.118210862619808, | |
| "grad_norm": 9.786779403686523, | |
| "learning_rate": 4.038004750593825e-06, | |
| "loss": 0.911, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 11.246006389776358, | |
| "grad_norm": 10.40623664855957, | |
| "learning_rate": 3.4441805225653207e-06, | |
| "loss": 0.9683, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 11.373801916932907, | |
| "grad_norm": 10.116272926330566, | |
| "learning_rate": 2.850356294536817e-06, | |
| "loss": 0.9074, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 11.501597444089457, | |
| "grad_norm": 9.423429489135742, | |
| "learning_rate": 2.2565320665083133e-06, | |
| "loss": 0.908, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 11.629392971246006, | |
| "grad_norm": 11.146402359008789, | |
| "learning_rate": 1.6627078384798101e-06, | |
| "loss": 0.9744, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 11.757188498402556, | |
| "grad_norm": 11.125927925109863, | |
| "learning_rate": 1.0688836104513065e-06, | |
| "loss": 0.9541, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 11.884984025559106, | |
| "grad_norm": 10.135693550109863, | |
| "learning_rate": 4.750593824228029e-07, | |
| "loss": 0.9324, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 11.961661341853034, | |
| "eval_accuracy": 0.5954022988505747, | |
| "eval_f1": 0.5878627034099811, | |
| "eval_loss": 0.9134895205497742, | |
| "eval_precision": 0.5865253155328708, | |
| "eval_recall": 0.5954022988505747, | |
| "eval_runtime": 4.3073, | |
| "eval_samples_per_second": 100.992, | |
| "eval_steps_per_second": 6.501, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 11.961661341853034, | |
| "step": 936, | |
| "total_flos": 4.743827088137626e+18, | |
| "train_loss": 1.079931161342523, | |
| "train_runtime": 2308.5403, | |
| "train_samples_per_second": 26.027, | |
| "train_steps_per_second": 0.405 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 936, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 12, | |
| "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": 4.743827088137626e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |