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
graphcodebert-code-classification / codebert-base-cross-entropy /checkpoint-2000 /trainer_state.json
| { | |
| "best_global_step": 2000, | |
| "best_metric": 0.743516265066894, | |
| "best_model_checkpoint": "./output_checkpoints/codebert-base-cross-entropy/checkpoint-2000", | |
| "epoch": 0.2559836170485089, | |
| "eval_steps": 500, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012799180852425445, | |
| "grad_norm": 3.6954128742218018, | |
| "learning_rate": 3.840409643695328e-08, | |
| "loss": 0.7763, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002559836170485089, | |
| "grad_norm": 3.3660645484924316, | |
| "learning_rate": 8.10753147002347e-08, | |
| "loss": 0.7763, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0038397542557276334, | |
| "grad_norm": 4.491067886352539, | |
| "learning_rate": 1.2374653296351612e-07, | |
| "loss": 0.7889, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005119672340970178, | |
| "grad_norm": 1.5920521020889282, | |
| "learning_rate": 1.6641775122679754e-07, | |
| "loss": 0.7888, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006399590426212722, | |
| "grad_norm": 4.410898208618164, | |
| "learning_rate": 2.0908896949007894e-07, | |
| "loss": 0.7692, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007679508511455267, | |
| "grad_norm": 2.5669264793395996, | |
| "learning_rate": 2.517601877533604e-07, | |
| "loss": 0.7735, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.008959426596697812, | |
| "grad_norm": 6.190986156463623, | |
| "learning_rate": 2.944314060166418e-07, | |
| "loss": 0.7679, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.010239344681940356, | |
| "grad_norm": 5.736413478851318, | |
| "learning_rate": 3.371026242799232e-07, | |
| "loss": 0.744, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.011519262767182901, | |
| "grad_norm": 4.278866767883301, | |
| "learning_rate": 3.7977384254320464e-07, | |
| "loss": 0.7542, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.012799180852425445, | |
| "grad_norm": 5.565455436706543, | |
| "learning_rate": 4.22445060806486e-07, | |
| "loss": 0.752, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01407909893766799, | |
| "grad_norm": 4.031781196594238, | |
| "learning_rate": 4.651162790697675e-07, | |
| "loss": 0.7614, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.015359017022910534, | |
| "grad_norm": 2.484126329421997, | |
| "learning_rate": 5.077874973330489e-07, | |
| "loss": 0.7664, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.016638935108153077, | |
| "grad_norm": 2.7525155544281006, | |
| "learning_rate": 5.504587155963304e-07, | |
| "loss": 0.7521, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.017918853193395624, | |
| "grad_norm": 1.6374385356903076, | |
| "learning_rate": 5.931299338596117e-07, | |
| "loss": 0.7436, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.019198771278638168, | |
| "grad_norm": 2.370774269104004, | |
| "learning_rate": 6.358011521228932e-07, | |
| "loss": 0.7429, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.02047868936388071, | |
| "grad_norm": 2.8948566913604736, | |
| "learning_rate": 6.784723703861745e-07, | |
| "loss": 0.7333, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.021758607449123255, | |
| "grad_norm": 2.7481186389923096, | |
| "learning_rate": 7.21143588649456e-07, | |
| "loss": 0.7294, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.023038525534365802, | |
| "grad_norm": 2.0159404277801514, | |
| "learning_rate": 7.638148069127374e-07, | |
| "loss": 0.731, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.024318443619608346, | |
| "grad_norm": 3.6898131370544434, | |
| "learning_rate": 8.064860251760189e-07, | |
| "loss": 0.7153, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.02559836170485089, | |
| "grad_norm": 3.2842342853546143, | |
| "learning_rate": 8.491572434393003e-07, | |
| "loss": 0.7245, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.02559836170485089, | |
| "eval_accuracy": 0.47695, | |
| "eval_loss": 0.7148504853248596, | |
| "eval_macro_f1": 0.3229290091066048, | |
| "eval_precision": 0.238475, | |
| "eval_recall": 0.5, | |
| "eval_runtime": 1641.324, | |
| "eval_samples_per_second": 60.926, | |
| "eval_steps_per_second": 0.476, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.026878279790093433, | |
| "grad_norm": 2.294558048248291, | |
| "learning_rate": 8.918284617025817e-07, | |
| "loss": 0.718, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.02815819787533598, | |
| "grad_norm": 2.9467175006866455, | |
| "learning_rate": 9.344996799658632e-07, | |
| "loss": 0.7076, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.029438115960578524, | |
| "grad_norm": 2.6889193058013916, | |
| "learning_rate": 9.771708982291445e-07, | |
| "loss": 0.7019, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.030718034045821067, | |
| "grad_norm": 0.7491384744644165, | |
| "learning_rate": 1.0198421164924258e-06, | |
| "loss": 0.7046, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.031997952131063614, | |
| "grad_norm": 2.0363433361053467, | |
| "learning_rate": 1.0625133347557074e-06, | |
| "loss": 0.7085, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.033277870216306155, | |
| "grad_norm": 1.1431337594985962, | |
| "learning_rate": 1.1051845530189888e-06, | |
| "loss": 0.7008, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.0345577883015487, | |
| "grad_norm": 3.7735233306884766, | |
| "learning_rate": 1.1478557712822702e-06, | |
| "loss": 0.7015, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.03583770638679125, | |
| "grad_norm": 0.7889328002929688, | |
| "learning_rate": 1.1905269895455517e-06, | |
| "loss": 0.699, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.03711762447203379, | |
| "grad_norm": 0.8796226382255554, | |
| "learning_rate": 1.233198207808833e-06, | |
| "loss": 0.6922, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.038397542557276336, | |
| "grad_norm": 0.7966652512550354, | |
| "learning_rate": 1.2758694260721145e-06, | |
| "loss": 0.6949, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.039677460642518876, | |
| "grad_norm": 0.7029069066047668, | |
| "learning_rate": 1.318540644335396e-06, | |
| "loss": 0.695, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.04095737872776142, | |
| "grad_norm": 2.04327392578125, | |
| "learning_rate": 1.3612118625986772e-06, | |
| "loss": 0.6944, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.04223729681300397, | |
| "grad_norm": 0.918025553226471, | |
| "learning_rate": 1.4038830808619588e-06, | |
| "loss": 0.6863, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.04351721489824651, | |
| "grad_norm": 0.9528706073760986, | |
| "learning_rate": 1.4465542991252401e-06, | |
| "loss": 0.6907, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.04479713298348906, | |
| "grad_norm": 1.071359634399414, | |
| "learning_rate": 1.4892255173885215e-06, | |
| "loss": 0.6873, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.046077051068731605, | |
| "grad_norm": 1.9875625371932983, | |
| "learning_rate": 1.531896735651803e-06, | |
| "loss": 0.6942, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.047356969153974145, | |
| "grad_norm": 2.0222439765930176, | |
| "learning_rate": 1.5745679539150842e-06, | |
| "loss": 0.6898, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.04863688723921669, | |
| "grad_norm": 1.7827857732772827, | |
| "learning_rate": 1.6172391721783658e-06, | |
| "loss": 0.6909, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.04991680532445923, | |
| "grad_norm": 1.065674901008606, | |
| "learning_rate": 1.6599103904416472e-06, | |
| "loss": 0.6877, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.05119672340970178, | |
| "grad_norm": 0.8346193432807922, | |
| "learning_rate": 1.7025816087049288e-06, | |
| "loss": 0.6889, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.05119672340970178, | |
| "eval_accuracy": 0.54043, | |
| "eval_loss": 0.6827595233917236, | |
| "eval_macro_f1": 0.41833840347598905, | |
| "eval_precision": 0.5839205994464474, | |
| "eval_recall": 0.5204152767503025, | |
| "eval_runtime": 1634.6244, | |
| "eval_samples_per_second": 61.176, | |
| "eval_steps_per_second": 0.478, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.052476641494944326, | |
| "grad_norm": 0.8074935674667358, | |
| "learning_rate": 1.7452528269682101e-06, | |
| "loss": 0.684, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.053756559580186866, | |
| "grad_norm": 0.8965069651603699, | |
| "learning_rate": 1.7879240452314913e-06, | |
| "loss": 0.6922, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.05503647766542941, | |
| "grad_norm": 2.597215414047241, | |
| "learning_rate": 1.8305952634947729e-06, | |
| "loss": 0.6909, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.05631639575067196, | |
| "grad_norm": 0.8233373165130615, | |
| "learning_rate": 1.8732664817580542e-06, | |
| "loss": 0.6831, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.0575963138359145, | |
| "grad_norm": 1.0624489784240723, | |
| "learning_rate": 1.915937700021336e-06, | |
| "loss": 0.6817, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.05887623192115705, | |
| "grad_norm": 2.0623559951782227, | |
| "learning_rate": 1.958608918284617e-06, | |
| "loss": 0.6819, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.06015615000639959, | |
| "grad_norm": 0.912433922290802, | |
| "learning_rate": 2.0012801365478988e-06, | |
| "loss": 0.686, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.061436068091642135, | |
| "grad_norm": 0.6926271319389343, | |
| "learning_rate": 2.04395135481118e-06, | |
| "loss": 0.6834, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.06271598617688467, | |
| "grad_norm": 1.498634934425354, | |
| "learning_rate": 2.0866225730744615e-06, | |
| "loss": 0.6805, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.06399590426212723, | |
| "grad_norm": 1.1818156242370605, | |
| "learning_rate": 2.129293791337743e-06, | |
| "loss": 0.6805, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.06527582234736977, | |
| "grad_norm": 1.4476051330566406, | |
| "learning_rate": 2.1719650096010242e-06, | |
| "loss": 0.6773, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.06655574043261231, | |
| "grad_norm": 1.1143743991851807, | |
| "learning_rate": 2.214636227864306e-06, | |
| "loss": 0.6801, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.06783565851785486, | |
| "grad_norm": 1.7030247449874878, | |
| "learning_rate": 2.257307446127587e-06, | |
| "loss": 0.6794, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.0691155766030974, | |
| "grad_norm": 0.8592290282249451, | |
| "learning_rate": 2.2999786643908685e-06, | |
| "loss": 0.6736, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.07039549468833994, | |
| "grad_norm": 0.8231940865516663, | |
| "learning_rate": 2.34264988265415e-06, | |
| "loss": 0.67, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.0716754127735825, | |
| "grad_norm": 0.88897705078125, | |
| "learning_rate": 2.3853211009174317e-06, | |
| "loss": 0.685, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.07295533085882504, | |
| "grad_norm": 1.6297541856765747, | |
| "learning_rate": 2.427992319180713e-06, | |
| "loss": 0.6797, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.07423524894406758, | |
| "grad_norm": 2.9297447204589844, | |
| "learning_rate": 2.470663537443994e-06, | |
| "loss": 0.6766, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.07551516702931012, | |
| "grad_norm": 0.9277703762054443, | |
| "learning_rate": 2.5133347557072756e-06, | |
| "loss": 0.6824, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.07679508511455267, | |
| "grad_norm": 0.5883333683013916, | |
| "learning_rate": 2.556005973970557e-06, | |
| "loss": 0.6818, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.07679508511455267, | |
| "eval_accuracy": 0.63909, | |
| "eval_loss": 0.6700075268745422, | |
| "eval_macro_f1": 0.621848143053056, | |
| "eval_precision": 0.6524313071088819, | |
| "eval_recall": 0.6305863955136095, | |
| "eval_runtime": 1633.9732, | |
| "eval_samples_per_second": 61.201, | |
| "eval_steps_per_second": 0.479, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.07807500319979521, | |
| "grad_norm": 0.7149448394775391, | |
| "learning_rate": 2.5986771922338383e-06, | |
| "loss": 0.6746, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.07935492128503775, | |
| "grad_norm": 2.0167856216430664, | |
| "learning_rate": 2.64134841049712e-06, | |
| "loss": 0.682, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.0806348393702803, | |
| "grad_norm": 1.303001880645752, | |
| "learning_rate": 2.6840196287604015e-06, | |
| "loss": 0.6735, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.08191475745552285, | |
| "grad_norm": 2.0516321659088135, | |
| "learning_rate": 2.7266908470236826e-06, | |
| "loss": 0.6705, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.08319467554076539, | |
| "grad_norm": 2.242105484008789, | |
| "learning_rate": 2.7693620652869642e-06, | |
| "loss": 0.6798, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.08447459362600794, | |
| "grad_norm": 1.1836538314819336, | |
| "learning_rate": 2.812033283550246e-06, | |
| "loss": 0.6684, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.08575451171125048, | |
| "grad_norm": 0.8640874624252319, | |
| "learning_rate": 2.8547045018135274e-06, | |
| "loss": 0.6783, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.08703442979649302, | |
| "grad_norm": 0.6901177763938904, | |
| "learning_rate": 2.897375720076808e-06, | |
| "loss": 0.6724, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.08831434788173557, | |
| "grad_norm": 1.3443949222564697, | |
| "learning_rate": 2.9400469383400897e-06, | |
| "loss": 0.67, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.08959426596697811, | |
| "grad_norm": 0.7775189280509949, | |
| "learning_rate": 2.9827181566033713e-06, | |
| "loss": 0.6733, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.09087418405222066, | |
| "grad_norm": 1.16916823387146, | |
| "learning_rate": 3.025389374866653e-06, | |
| "loss": 0.6713, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.09215410213746321, | |
| "grad_norm": 1.707152009010315, | |
| "learning_rate": 3.068060593129934e-06, | |
| "loss": 0.6659, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.09343402022270575, | |
| "grad_norm": 0.9780622124671936, | |
| "learning_rate": 3.1107318113932156e-06, | |
| "loss": 0.6639, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.09471393830794829, | |
| "grad_norm": 2.3687374591827393, | |
| "learning_rate": 3.153403029656497e-06, | |
| "loss": 0.6666, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.09599385639319083, | |
| "grad_norm": 0.8506460189819336, | |
| "learning_rate": 3.1960742479197783e-06, | |
| "loss": 0.6778, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.09727377447843338, | |
| "grad_norm": 1.0102107524871826, | |
| "learning_rate": 3.23874546618306e-06, | |
| "loss": 0.6635, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.09855369256367592, | |
| "grad_norm": 1.1480194330215454, | |
| "learning_rate": 3.2814166844463415e-06, | |
| "loss": 0.6709, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.09983361064891846, | |
| "grad_norm": 1.3119179010391235, | |
| "learning_rate": 3.324087902709623e-06, | |
| "loss": 0.6564, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.10111352873416102, | |
| "grad_norm": 0.681377649307251, | |
| "learning_rate": 3.3667591209729038e-06, | |
| "loss": 0.6656, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.10239344681940356, | |
| "grad_norm": 1.022257685661316, | |
| "learning_rate": 3.4094303392361854e-06, | |
| "loss": 0.6709, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.10239344681940356, | |
| "eval_accuracy": 0.66247, | |
| "eval_loss": 0.6552017331123352, | |
| "eval_macro_f1": 0.6514270557181998, | |
| "eval_precision": 0.6718270655389242, | |
| "eval_recall": 0.6556580720913894, | |
| "eval_runtime": 1633.5478, | |
| "eval_samples_per_second": 61.216, | |
| "eval_steps_per_second": 0.479, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.1036733649046461, | |
| "grad_norm": 1.0268975496292114, | |
| "learning_rate": 3.452101557499467e-06, | |
| "loss": 0.6602, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.10495328298988865, | |
| "grad_norm": 2.6206603050231934, | |
| "learning_rate": 3.494772775762748e-06, | |
| "loss": 0.6705, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.10623320107513119, | |
| "grad_norm": 1.035157561302185, | |
| "learning_rate": 3.5374439940260297e-06, | |
| "loss": 0.6643, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.10751311916037373, | |
| "grad_norm": 1.736412763595581, | |
| "learning_rate": 3.5801152122893113e-06, | |
| "loss": 0.6612, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.10879303724561629, | |
| "grad_norm": 0.6906964778900146, | |
| "learning_rate": 3.622786430552593e-06, | |
| "loss": 0.6576, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.11007295533085883, | |
| "grad_norm": 0.8148729801177979, | |
| "learning_rate": 3.665457648815874e-06, | |
| "loss": 0.6561, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.11135287341610137, | |
| "grad_norm": 1.0217723846435547, | |
| "learning_rate": 3.7081288670791556e-06, | |
| "loss": 0.6581, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.11263279150134392, | |
| "grad_norm": 1.2743115425109863, | |
| "learning_rate": 3.750800085342437e-06, | |
| "loss": 0.6606, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.11391270958658646, | |
| "grad_norm": 0.6405361294746399, | |
| "learning_rate": 3.793471303605718e-06, | |
| "loss": 0.652, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.115192627671829, | |
| "grad_norm": 0.8357161283493042, | |
| "learning_rate": 3.836142521869e-06, | |
| "loss": 0.6558, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.11647254575707154, | |
| "grad_norm": 1.3505173921585083, | |
| "learning_rate": 3.8788137401322815e-06, | |
| "loss": 0.6576, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.1177524638423141, | |
| "grad_norm": 1.2253319025039673, | |
| "learning_rate": 3.921484958395563e-06, | |
| "loss": 0.6548, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.11903238192755664, | |
| "grad_norm": 0.6269568800926208, | |
| "learning_rate": 3.964156176658844e-06, | |
| "loss": 0.6562, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.12031230001279918, | |
| "grad_norm": 0.9413424134254456, | |
| "learning_rate": 4.006827394922125e-06, | |
| "loss": 0.6461, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.12159221809804173, | |
| "grad_norm": 1.0903513431549072, | |
| "learning_rate": 4.049498613185407e-06, | |
| "loss": 0.6457, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.12287213618328427, | |
| "grad_norm": 2.0023152828216553, | |
| "learning_rate": 4.092169831448688e-06, | |
| "loss": 0.6458, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.12415205426852681, | |
| "grad_norm": 0.9638109803199768, | |
| "learning_rate": 4.134841049711969e-06, | |
| "loss": 0.6486, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.12543197235376935, | |
| "grad_norm": 0.9894546270370483, | |
| "learning_rate": 4.177512267975251e-06, | |
| "loss": 0.6453, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.1267118904390119, | |
| "grad_norm": 1.2289057970046997, | |
| "learning_rate": 4.220183486238532e-06, | |
| "loss": 0.6605, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.12799180852425446, | |
| "grad_norm": 1.119125247001648, | |
| "learning_rate": 4.262854704501814e-06, | |
| "loss": 0.6564, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.12799180852425446, | |
| "eval_accuracy": 0.69068, | |
| "eval_loss": 0.6396247148513794, | |
| "eval_macro_f1": 0.689588440856387, | |
| "eval_precision": 0.6900076024604327, | |
| "eval_recall": 0.6894114140312133, | |
| "eval_runtime": 1634.4321, | |
| "eval_samples_per_second": 61.183, | |
| "eval_steps_per_second": 0.478, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.12927172660949698, | |
| "grad_norm": 2.02966046333313, | |
| "learning_rate": 4.3055259227650956e-06, | |
| "loss": 0.646, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.13055164469473954, | |
| "grad_norm": 0.7430800199508667, | |
| "learning_rate": 4.348197141028377e-06, | |
| "loss": 0.6453, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.1318315627799821, | |
| "grad_norm": 1.031962275505066, | |
| "learning_rate": 4.390868359291658e-06, | |
| "loss": 0.6425, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.13311148086522462, | |
| "grad_norm": 1.0249106884002686, | |
| "learning_rate": 4.4335395775549394e-06, | |
| "loss": 0.6426, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.13439139895046717, | |
| "grad_norm": 0.7375448942184448, | |
| "learning_rate": 4.476210795818221e-06, | |
| "loss": 0.6401, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.13567131703570973, | |
| "grad_norm": 1.295983076095581, | |
| "learning_rate": 4.518882014081503e-06, | |
| "loss": 0.6449, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.13695123512095225, | |
| "grad_norm": 1.6978998184204102, | |
| "learning_rate": 4.561553232344783e-06, | |
| "loss": 0.6484, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.1382311532061948, | |
| "grad_norm": 0.7747512459754944, | |
| "learning_rate": 4.604224450608065e-06, | |
| "loss": 0.6526, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.13951107129143736, | |
| "grad_norm": 0.7895913124084473, | |
| "learning_rate": 4.6468956688713465e-06, | |
| "loss": 0.6311, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.1407909893766799, | |
| "grad_norm": 0.6975072026252747, | |
| "learning_rate": 4.689566887134628e-06, | |
| "loss": 0.6454, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.14207090746192244, | |
| "grad_norm": 0.8316811919212341, | |
| "learning_rate": 4.73223810539791e-06, | |
| "loss": 0.6447, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.143350825547165, | |
| "grad_norm": 0.6887441277503967, | |
| "learning_rate": 4.774909323661191e-06, | |
| "loss": 0.6325, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.14463074363240752, | |
| "grad_norm": 1.0218420028686523, | |
| "learning_rate": 4.817580541924473e-06, | |
| "loss": 0.6308, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.14591066171765008, | |
| "grad_norm": 0.7663633823394775, | |
| "learning_rate": 4.8602517601877535e-06, | |
| "loss": 0.6227, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.1471905798028926, | |
| "grad_norm": 1.5115224123001099, | |
| "learning_rate": 4.902922978451035e-06, | |
| "loss": 0.6315, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.14847049788813516, | |
| "grad_norm": 0.8011078238487244, | |
| "learning_rate": 4.945594196714317e-06, | |
| "loss": 0.6428, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.1497504159733777, | |
| "grad_norm": 1.3246116638183594, | |
| "learning_rate": 4.9882654149775974e-06, | |
| "loss": 0.6397, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.15103033405862024, | |
| "grad_norm": 0.979498565196991, | |
| "learning_rate": 5.030936633240879e-06, | |
| "loss": 0.6308, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.1523102521438628, | |
| "grad_norm": 0.8756135106086731, | |
| "learning_rate": 5.073607851504161e-06, | |
| "loss": 0.6373, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.15359017022910534, | |
| "grad_norm": 0.845967710018158, | |
| "learning_rate": 5.116279069767442e-06, | |
| "loss": 0.6322, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.15359017022910534, | |
| "eval_accuracy": 0.69931, | |
| "eval_loss": 0.6224722862243652, | |
| "eval_macro_f1": 0.6985627236986651, | |
| "eval_precision": 0.6986454338713279, | |
| "eval_recall": 0.6984991383538209, | |
| "eval_runtime": 692.1526, | |
| "eval_samples_per_second": 144.477, | |
| "eval_steps_per_second": 2.258, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.15487008831434787, | |
| "grad_norm": 2.0670483112335205, | |
| "learning_rate": 1.032010243277849e-05, | |
| "loss": 0.6386, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.15615000639959042, | |
| "grad_norm": 2.482168436050415, | |
| "learning_rate": 1.0405463081519421e-05, | |
| "loss": 0.6281, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.15742992448483298, | |
| "grad_norm": 1.4530706405639648, | |
| "learning_rate": 1.049082373026035e-05, | |
| "loss": 0.6277, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.1587098425700755, | |
| "grad_norm": 2.9233577251434326, | |
| "learning_rate": 1.0576184379001282e-05, | |
| "loss": 0.6363, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.15998976065531806, | |
| "grad_norm": 0.6975642442703247, | |
| "learning_rate": 1.0661545027742212e-05, | |
| "loss": 0.6344, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.1612696787405606, | |
| "grad_norm": 2.3634731769561768, | |
| "learning_rate": 1.0746905676483142e-05, | |
| "loss": 0.6217, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.16254959682580314, | |
| "grad_norm": 0.8812585473060608, | |
| "learning_rate": 1.0832266325224072e-05, | |
| "loss": 0.6311, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.1638295149110457, | |
| "grad_norm": 1.8986798524856567, | |
| "learning_rate": 1.0917626973965003e-05, | |
| "loss": 0.6304, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.16510943299628825, | |
| "grad_norm": 0.8174984455108643, | |
| "learning_rate": 1.1002987622705935e-05, | |
| "loss": 0.6176, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.16638935108153077, | |
| "grad_norm": 1.0268642902374268, | |
| "learning_rate": 1.1088348271446865e-05, | |
| "loss": 0.6233, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.16766926916677333, | |
| "grad_norm": 1.047821044921875, | |
| "learning_rate": 1.1173708920187793e-05, | |
| "loss": 0.6127, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.16894918725201588, | |
| "grad_norm": 0.9875057935714722, | |
| "learning_rate": 1.1259069568928724e-05, | |
| "loss": 0.6211, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.1702291053372584, | |
| "grad_norm": 1.0082708597183228, | |
| "learning_rate": 1.1344430217669656e-05, | |
| "loss": 0.6202, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.17150902342250096, | |
| "grad_norm": 0.7229795455932617, | |
| "learning_rate": 1.1429790866410586e-05, | |
| "loss": 0.6071, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.17278894150774352, | |
| "grad_norm": 0.7687681317329407, | |
| "learning_rate": 1.1515151515151517e-05, | |
| "loss": 0.6218, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.17406885959298604, | |
| "grad_norm": 1.1643378734588623, | |
| "learning_rate": 1.1600512163892445e-05, | |
| "loss": 0.6208, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.1753487776782286, | |
| "grad_norm": 0.7338509559631348, | |
| "learning_rate": 1.1685872812633377e-05, | |
| "loss": 0.6105, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.17662869576347115, | |
| "grad_norm": 0.7444656491279602, | |
| "learning_rate": 1.1771233461374307e-05, | |
| "loss": 0.6183, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.17790861384871368, | |
| "grad_norm": 1.1902283430099487, | |
| "learning_rate": 1.1856594110115238e-05, | |
| "loss": 0.6209, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.17918853193395623, | |
| "grad_norm": 1.0872228145599365, | |
| "learning_rate": 1.194195475885617e-05, | |
| "loss": 0.6172, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.18046845001919878, | |
| "grad_norm": 1.8439041376113892, | |
| "learning_rate": 1.2027315407597098e-05, | |
| "loss": 0.6086, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.1817483681044413, | |
| "grad_norm": 0.8699899911880493, | |
| "learning_rate": 1.211267605633803e-05, | |
| "loss": 0.6247, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.18302828618968386, | |
| "grad_norm": 1.1468650102615356, | |
| "learning_rate": 1.2198036705078959e-05, | |
| "loss": 0.6114, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.18430820427492642, | |
| "grad_norm": 1.0204615592956543, | |
| "learning_rate": 1.228339735381989e-05, | |
| "loss": 0.6015, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.18558812236016894, | |
| "grad_norm": 2.660583257675171, | |
| "learning_rate": 1.236875800256082e-05, | |
| "loss": 0.6002, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.1868680404454115, | |
| "grad_norm": 1.1916371583938599, | |
| "learning_rate": 1.2454118651301752e-05, | |
| "loss": 0.6076, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.18814795853065402, | |
| "grad_norm": 0.8097987174987793, | |
| "learning_rate": 1.253947930004268e-05, | |
| "loss": 0.6126, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.18942787661589658, | |
| "grad_norm": 1.978747010231018, | |
| "learning_rate": 1.2624839948783612e-05, | |
| "loss": 0.5962, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.19070779470113913, | |
| "grad_norm": 1.0975425243377686, | |
| "learning_rate": 1.2710200597524543e-05, | |
| "loss": 0.587, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.19198771278638166, | |
| "grad_norm": 2.150351047515869, | |
| "learning_rate": 1.2795561246265473e-05, | |
| "loss": 0.5962, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.19198771278638166, | |
| "eval_accuracy": 0.72526, | |
| "eval_loss": 0.5823243856430054, | |
| "eval_macro_f1": 0.7252418839884757, | |
| "eval_precision": 0.7275813809678697, | |
| "eval_recall": 0.7271797416587706, | |
| "eval_runtime": 708.4119, | |
| "eval_samples_per_second": 141.161, | |
| "eval_steps_per_second": 1.104, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.1932676308716242, | |
| "grad_norm": 1.8355706930160522, | |
| "learning_rate": 1.2880921895006405e-05, | |
| "loss": 0.6133, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.19454754895686677, | |
| "grad_norm": 1.4349753856658936, | |
| "learning_rate": 1.2966282543747333e-05, | |
| "loss": 0.6062, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.1958274670421093, | |
| "grad_norm": 1.8322596549987793, | |
| "learning_rate": 1.3051643192488264e-05, | |
| "loss": 0.5982, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.19710738512735185, | |
| "grad_norm": 1.509338617324829, | |
| "learning_rate": 1.3137003841229194e-05, | |
| "loss": 0.5961, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.1983873032125944, | |
| "grad_norm": 0.9844911098480225, | |
| "learning_rate": 1.3222364489970126e-05, | |
| "loss": 0.583, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.19966722129783693, | |
| "grad_norm": 1.035900354385376, | |
| "learning_rate": 1.3307725138711055e-05, | |
| "loss": 0.598, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.20094713938307948, | |
| "grad_norm": 0.7891924977302551, | |
| "learning_rate": 1.3393085787451985e-05, | |
| "loss": 0.6064, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.20222705746832204, | |
| "grad_norm": 1.4326112270355225, | |
| "learning_rate": 1.3478446436192915e-05, | |
| "loss": 0.5954, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.20350697555356456, | |
| "grad_norm": 0.9054266214370728, | |
| "learning_rate": 1.3563807084933847e-05, | |
| "loss": 0.59, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.20478689363880712, | |
| "grad_norm": 1.0216469764709473, | |
| "learning_rate": 1.3649167733674778e-05, | |
| "loss": 0.5845, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.20606681172404967, | |
| "grad_norm": 1.0591177940368652, | |
| "learning_rate": 1.3734528382415708e-05, | |
| "loss": 0.599, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.2073467298092922, | |
| "grad_norm": 0.7826931476593018, | |
| "learning_rate": 1.3819889031156638e-05, | |
| "loss": 0.5898, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.20862664789453475, | |
| "grad_norm": 0.755007803440094, | |
| "learning_rate": 1.3905249679897568e-05, | |
| "loss": 0.5769, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.2099065659797773, | |
| "grad_norm": 1.3526090383529663, | |
| "learning_rate": 1.3990610328638499e-05, | |
| "loss": 0.5819, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.21118648406501983, | |
| "grad_norm": 0.7078200578689575, | |
| "learning_rate": 1.4075970977379429e-05, | |
| "loss": 0.5884, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.21246640215026238, | |
| "grad_norm": 0.80736243724823, | |
| "learning_rate": 1.416133162612036e-05, | |
| "loss": 0.5991, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.21374632023550494, | |
| "grad_norm": 0.6882274150848389, | |
| "learning_rate": 1.4246692274861289e-05, | |
| "loss": 0.5825, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.21502623832074746, | |
| "grad_norm": 0.7223654985427856, | |
| "learning_rate": 1.433205292360222e-05, | |
| "loss": 0.5689, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.21630615640599002, | |
| "grad_norm": 0.6446322798728943, | |
| "learning_rate": 1.4417413572343152e-05, | |
| "loss": 0.5773, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.21758607449123257, | |
| "grad_norm": 1.505007266998291, | |
| "learning_rate": 1.4502774221084081e-05, | |
| "loss": 0.5677, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.2188659925764751, | |
| "grad_norm": 1.1939284801483154, | |
| "learning_rate": 1.4588134869825013e-05, | |
| "loss": 0.5805, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.22014591066171765, | |
| "grad_norm": 2.848264217376709, | |
| "learning_rate": 1.4673495518565943e-05, | |
| "loss": 0.5712, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.2214258287469602, | |
| "grad_norm": 1.2117749452590942, | |
| "learning_rate": 1.4758856167306873e-05, | |
| "loss": 0.582, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.22270574683220273, | |
| "grad_norm": 2.2297441959381104, | |
| "learning_rate": 1.4844216816047802e-05, | |
| "loss": 0.5751, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.2239856649174453, | |
| "grad_norm": 1.211978554725647, | |
| "learning_rate": 1.4929577464788734e-05, | |
| "loss": 0.5607, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.22526558300268784, | |
| "grad_norm": 0.8025451898574829, | |
| "learning_rate": 1.5014938113529664e-05, | |
| "loss": 0.5803, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.22654550108793037, | |
| "grad_norm": 1.2300900220870972, | |
| "learning_rate": 1.5100298762270595e-05, | |
| "loss": 0.5827, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.22782541917317292, | |
| "grad_norm": 1.0382864475250244, | |
| "learning_rate": 1.5185659411011523e-05, | |
| "loss": 0.5916, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.22910533725841545, | |
| "grad_norm": 1.4876656532287598, | |
| "learning_rate": 1.5271020059752453e-05, | |
| "loss": 0.5536, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.230385255343658, | |
| "grad_norm": 1.1409252882003784, | |
| "learning_rate": 1.5356380708493386e-05, | |
| "loss": 0.5484, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.23166517342890056, | |
| "grad_norm": 0.7180280089378357, | |
| "learning_rate": 1.5441741357234316e-05, | |
| "loss": 0.5712, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.23294509151414308, | |
| "grad_norm": 1.5890289545059204, | |
| "learning_rate": 1.5527102005975246e-05, | |
| "loss": 0.5758, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.23422500959938564, | |
| "grad_norm": 0.6635769605636597, | |
| "learning_rate": 1.5612462654716176e-05, | |
| "loss": 0.5543, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.2355049276846282, | |
| "grad_norm": 0.8864602446556091, | |
| "learning_rate": 1.5697823303457106e-05, | |
| "loss": 0.5536, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.23678484576987072, | |
| "grad_norm": 0.8372675776481628, | |
| "learning_rate": 1.578318395219804e-05, | |
| "loss": 0.5743, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.23806476385511327, | |
| "grad_norm": 0.7532811164855957, | |
| "learning_rate": 1.586854460093897e-05, | |
| "loss": 0.5593, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.23934468194035582, | |
| "grad_norm": 0.7231799960136414, | |
| "learning_rate": 1.59539052496799e-05, | |
| "loss": 0.5831, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.24062460002559835, | |
| "grad_norm": 1.124228596687317, | |
| "learning_rate": 1.603926589842083e-05, | |
| "loss": 0.5936, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.2419045181108409, | |
| "grad_norm": 1.0107067823410034, | |
| "learning_rate": 1.612462654716176e-05, | |
| "loss": 0.5598, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.24318443619608346, | |
| "grad_norm": 1.6117154359817505, | |
| "learning_rate": 1.620998719590269e-05, | |
| "loss": 0.5605, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.24446435428132599, | |
| "grad_norm": 1.5564496517181396, | |
| "learning_rate": 1.629534784464362e-05, | |
| "loss": 0.5666, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.24574427236656854, | |
| "grad_norm": 0.8275917768478394, | |
| "learning_rate": 1.638070849338455e-05, | |
| "loss": 0.5597, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.2470241904518111, | |
| "grad_norm": 0.8956324458122253, | |
| "learning_rate": 1.646606914212548e-05, | |
| "loss": 0.5453, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.24830410853705362, | |
| "grad_norm": 1.9644063711166382, | |
| "learning_rate": 1.655142979086641e-05, | |
| "loss": 0.5732, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.24958402662229617, | |
| "grad_norm": 0.7495090365409851, | |
| "learning_rate": 1.663679043960734e-05, | |
| "loss": 0.5549, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.2508639447075387, | |
| "grad_norm": 0.9346863627433777, | |
| "learning_rate": 1.6722151088348274e-05, | |
| "loss": 0.5803, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.2521438627927813, | |
| "grad_norm": 0.5847868919372559, | |
| "learning_rate": 1.6807511737089204e-05, | |
| "loss": 0.5705, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.2534237808780238, | |
| "grad_norm": 1.5892306566238403, | |
| "learning_rate": 1.6892872385830134e-05, | |
| "loss": 0.5371, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.25470369896326633, | |
| "grad_norm": 0.8782947063446045, | |
| "learning_rate": 1.6978233034571063e-05, | |
| "loss": 0.565, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.2559836170485089, | |
| "grad_norm": 1.0143548250198364, | |
| "learning_rate": 1.7063593683311993e-05, | |
| "loss": 0.557, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.2559836170485089, | |
| "eval_accuracy": 0.74427, | |
| "eval_loss": 0.5308485627174377, | |
| "eval_macro_f1": 0.743516265066894, | |
| "eval_precision": 0.7538937627554241, | |
| "eval_recall": 0.7483595020974525, | |
| "eval_runtime": 708.2272, | |
| "eval_samples_per_second": 141.198, | |
| "eval_steps_per_second": 1.104, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 23439, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 3.367821508608e+16, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |