| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.7684295008623486, | |
| "eval_steps": 10000.0, | |
| "global_step": 90000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.538105565137207e-06, | |
| "grad_norm": 6.5811052322387695, | |
| "learning_rate": 1.7073587160662455e-08, | |
| "loss": 0.9425575733184814, | |
| "memory(GiB)": 4.21, | |
| "step": 1, | |
| "train_speed(iter/s)": 0.107952 | |
| }, | |
| { | |
| "epoch": 0.004269052782568603, | |
| "grad_norm": 0.775414764881134, | |
| "learning_rate": 8.536793580331227e-06, | |
| "loss": 0.2293025076030968, | |
| "memory(GiB)": 5.71, | |
| "step": 500, | |
| "train_speed(iter/s)": 0.938128 | |
| }, | |
| { | |
| "epoch": 0.008538105565137207, | |
| "grad_norm": 0.5124035477638245, | |
| "learning_rate": 1.7073587160662455e-05, | |
| "loss": 0.05007815933227539, | |
| "memory(GiB)": 5.71, | |
| "step": 1000, | |
| "train_speed(iter/s)": 0.946051 | |
| }, | |
| { | |
| "epoch": 0.012807158347705811, | |
| "grad_norm": 0.34229570627212524, | |
| "learning_rate": 2.5610380740993682e-05, | |
| "loss": 0.036965576171875, | |
| "memory(GiB)": 5.71, | |
| "step": 1500, | |
| "train_speed(iter/s)": 0.980261 | |
| }, | |
| { | |
| "epoch": 0.017076211130274414, | |
| "grad_norm": 0.29022017121315, | |
| "learning_rate": 3.414717432132491e-05, | |
| "loss": 0.030718547821044922, | |
| "memory(GiB)": 5.71, | |
| "step": 2000, | |
| "train_speed(iter/s)": 1.013563 | |
| }, | |
| { | |
| "epoch": 0.02134526391284302, | |
| "grad_norm": 0.2701531946659088, | |
| "learning_rate": 4.268396790165614e-05, | |
| "loss": 0.026950979232788087, | |
| "memory(GiB)": 5.71, | |
| "step": 2500, | |
| "train_speed(iter/s)": 1.038614 | |
| }, | |
| { | |
| "epoch": 0.025614316695411622, | |
| "grad_norm": 0.1944938600063324, | |
| "learning_rate": 5.1220761481987364e-05, | |
| "loss": 0.025618917465209962, | |
| "memory(GiB)": 5.71, | |
| "step": 3000, | |
| "train_speed(iter/s)": 1.081032 | |
| }, | |
| { | |
| "epoch": 0.029883369477980225, | |
| "grad_norm": 0.15646104514598846, | |
| "learning_rate": 5.9757555062318595e-05, | |
| "loss": 0.0239105281829834, | |
| "memory(GiB)": 5.71, | |
| "step": 3500, | |
| "train_speed(iter/s)": 1.023247 | |
| }, | |
| { | |
| "epoch": 0.03415242226054883, | |
| "grad_norm": 0.12373720854520798, | |
| "learning_rate": 6.829434864264982e-05, | |
| "loss": 0.021082000732421877, | |
| "memory(GiB)": 5.71, | |
| "step": 4000, | |
| "train_speed(iter/s)": 0.971265 | |
| }, | |
| { | |
| "epoch": 0.03842147504311743, | |
| "grad_norm": 0.11245039105415344, | |
| "learning_rate": 7.683114222298106e-05, | |
| "loss": 0.020011337280273437, | |
| "memory(GiB)": 5.71, | |
| "step": 4500, | |
| "train_speed(iter/s)": 0.934224 | |
| }, | |
| { | |
| "epoch": 0.04269052782568604, | |
| "grad_norm": 0.12453507632017136, | |
| "learning_rate": 8.536793580331228e-05, | |
| "loss": 0.019226245880126953, | |
| "memory(GiB)": 5.71, | |
| "step": 5000, | |
| "train_speed(iter/s)": 0.906199 | |
| }, | |
| { | |
| "epoch": 0.04695958060825464, | |
| "grad_norm": 0.08364573866128922, | |
| "learning_rate": 9.39047293836435e-05, | |
| "loss": 0.018570756912231444, | |
| "memory(GiB)": 5.71, | |
| "step": 5500, | |
| "train_speed(iter/s)": 0.887629 | |
| }, | |
| { | |
| "epoch": 0.051228633390823244, | |
| "grad_norm": 0.08422534167766571, | |
| "learning_rate": 9.999959243761552e-05, | |
| "loss": 0.018008022308349608, | |
| "memory(GiB)": 5.71, | |
| "step": 6000, | |
| "train_speed(iter/s)": 0.882382 | |
| }, | |
| { | |
| "epoch": 0.05549768617339185, | |
| "grad_norm": 0.0722428560256958, | |
| "learning_rate": 9.999175989726746e-05, | |
| "loss": 0.016920005798339844, | |
| "memory(GiB)": 5.71, | |
| "step": 6500, | |
| "train_speed(iter/s)": 0.887128 | |
| }, | |
| { | |
| "epoch": 0.05976673895596045, | |
| "grad_norm": 0.0696873590350151, | |
| "learning_rate": 9.997396381339795e-05, | |
| "loss": 0.016275758743286132, | |
| "memory(GiB)": 5.71, | |
| "step": 7000, | |
| "train_speed(iter/s)": 0.896874 | |
| }, | |
| { | |
| "epoch": 0.06403579173852905, | |
| "grad_norm": 0.0715385377407074, | |
| "learning_rate": 9.994620773283261e-05, | |
| "loss": 0.03211669921875, | |
| "memory(GiB)": 5.71, | |
| "step": 7500, | |
| "train_speed(iter/s)": 0.906916 | |
| }, | |
| { | |
| "epoch": 0.06830484452109765, | |
| "grad_norm": 0.07314470410346985, | |
| "learning_rate": 9.990849718746144e-05, | |
| "loss": 0.014735573768615723, | |
| "memory(GiB)": 5.71, | |
| "step": 8000, | |
| "train_speed(iter/s)": 0.915054 | |
| }, | |
| { | |
| "epoch": 0.07257389730366626, | |
| "grad_norm": 0.0624830424785614, | |
| "learning_rate": 9.986083969313632e-05, | |
| "loss": 0.014247347831726074, | |
| "memory(GiB)": 5.71, | |
| "step": 8500, | |
| "train_speed(iter/s)": 0.923566 | |
| }, | |
| { | |
| "epoch": 0.07684295008623486, | |
| "grad_norm": 0.054315660148859024, | |
| "learning_rate": 9.980324474817292e-05, | |
| "loss": 0.014038642883300782, | |
| "memory(GiB)": 5.71, | |
| "step": 9000, | |
| "train_speed(iter/s)": 0.931957 | |
| }, | |
| { | |
| "epoch": 0.08111200286880348, | |
| "grad_norm": 0.04966143146157265, | |
| "learning_rate": 9.973572383145782e-05, | |
| "loss": 0.013697422027587891, | |
| "memory(GiB)": 5.71, | |
| "step": 9500, | |
| "train_speed(iter/s)": 0.939331 | |
| }, | |
| { | |
| "epoch": 0.08538105565137208, | |
| "grad_norm": 0.055357128381729126, | |
| "learning_rate": 9.965829040016061e-05, | |
| "loss": 0.013380534172058105, | |
| "memory(GiB)": 5.71, | |
| "step": 10000, | |
| "train_speed(iter/s)": 0.946434 | |
| }, | |
| { | |
| "epoch": 0.08965010843394068, | |
| "grad_norm": 0.05234465003013611, | |
| "learning_rate": 9.957095988705193e-05, | |
| "loss": 0.013177488327026367, | |
| "memory(GiB)": 5.71, | |
| "step": 10500, | |
| "train_speed(iter/s)": 0.960222 | |
| }, | |
| { | |
| "epoch": 0.09391916121650928, | |
| "grad_norm": 0.053024690598249435, | |
| "learning_rate": 9.947374969742755e-05, | |
| "loss": 0.013030742645263672, | |
| "memory(GiB)": 5.71, | |
| "step": 11000, | |
| "train_speed(iter/s)": 0.973308 | |
| }, | |
| { | |
| "epoch": 0.09818821399907789, | |
| "grad_norm": 0.04746083542704582, | |
| "learning_rate": 9.936667920563951e-05, | |
| "loss": 0.012802671432495118, | |
| "memory(GiB)": 5.71, | |
| "step": 11500, | |
| "train_speed(iter/s)": 0.985248 | |
| }, | |
| { | |
| "epoch": 0.10245726678164649, | |
| "grad_norm": 0.045355405658483505, | |
| "learning_rate": 9.924976975123472e-05, | |
| "loss": 0.012366548538208007, | |
| "memory(GiB)": 5.71, | |
| "step": 12000, | |
| "train_speed(iter/s)": 0.996787 | |
| }, | |
| { | |
| "epoch": 0.10672631956421509, | |
| "grad_norm": 0.0430605448782444, | |
| "learning_rate": 9.912304463470185e-05, | |
| "loss": 0.018324718475341797, | |
| "memory(GiB)": 5.71, | |
| "step": 12500, | |
| "train_speed(iter/s)": 1.007619 | |
| }, | |
| { | |
| "epoch": 0.1109953723467837, | |
| "grad_norm": 0.03760723024606705, | |
| "learning_rate": 9.89865291128276e-05, | |
| "loss": 0.011288459777832032, | |
| "memory(GiB)": 5.71, | |
| "step": 13000, | |
| "train_speed(iter/s)": 1.017831 | |
| }, | |
| { | |
| "epoch": 0.1152644251293523, | |
| "grad_norm": 0.04123725742101669, | |
| "learning_rate": 9.884025039366274e-05, | |
| "loss": 0.011067386627197265, | |
| "memory(GiB)": 5.71, | |
| "step": 13500, | |
| "train_speed(iter/s)": 1.027479 | |
| }, | |
| { | |
| "epoch": 0.1195334779119209, | |
| "grad_norm": 0.046554189175367355, | |
| "learning_rate": 9.868423763109962e-05, | |
| "loss": 0.010972289085388184, | |
| "memory(GiB)": 5.71, | |
| "step": 14000, | |
| "train_speed(iter/s)": 1.0366 | |
| }, | |
| { | |
| "epoch": 0.1238025306944895, | |
| "grad_norm": 0.04529291018843651, | |
| "learning_rate": 9.851852191906155e-05, | |
| "loss": 0.010918002128601074, | |
| "memory(GiB)": 5.71, | |
| "step": 14500, | |
| "train_speed(iter/s)": 1.045276 | |
| }, | |
| { | |
| "epoch": 0.1280715834770581, | |
| "grad_norm": 0.039391227066516876, | |
| "learning_rate": 9.834313628530574e-05, | |
| "loss": 0.010901000022888184, | |
| "memory(GiB)": 5.71, | |
| "step": 15000, | |
| "train_speed(iter/s)": 1.053467 | |
| }, | |
| { | |
| "epoch": 0.13234063625962672, | |
| "grad_norm": 0.050082143396139145, | |
| "learning_rate": 9.81581156848408e-05, | |
| "loss": 0.010822629928588868, | |
| "memory(GiB)": 5.71, | |
| "step": 15500, | |
| "train_speed(iter/s)": 1.061046 | |
| }, | |
| { | |
| "epoch": 0.1366096890421953, | |
| "grad_norm": 0.04181528836488724, | |
| "learning_rate": 9.79634969929599e-05, | |
| "loss": 0.01061639404296875, | |
| "memory(GiB)": 5.71, | |
| "step": 16000, | |
| "train_speed(iter/s)": 1.068454 | |
| }, | |
| { | |
| "epoch": 0.14087874182476393, | |
| "grad_norm": 0.037736013531684875, | |
| "learning_rate": 9.775931899789159e-05, | |
| "loss": 0.01050139808654785, | |
| "memory(GiB)": 5.71, | |
| "step": 16500, | |
| "train_speed(iter/s)": 1.075513 | |
| }, | |
| { | |
| "epoch": 0.14514779460733251, | |
| "grad_norm": 0.03446267917752266, | |
| "learning_rate": 9.754562239306902e-05, | |
| "loss": 0.010301560401916503, | |
| "memory(GiB)": 5.71, | |
| "step": 17000, | |
| "train_speed(iter/s)": 1.08225 | |
| }, | |
| { | |
| "epoch": 0.14941684738990113, | |
| "grad_norm": 0.035218626260757446, | |
| "learning_rate": 9.732244976901965e-05, | |
| "loss": 0.010299022674560548, | |
| "memory(GiB)": 5.71, | |
| "step": 17500, | |
| "train_speed(iter/s)": 1.088656 | |
| }, | |
| { | |
| "epoch": 0.15368590017246972, | |
| "grad_norm": 0.034140028059482574, | |
| "learning_rate": 9.708984560487677e-05, | |
| "loss": 0.010085094451904296, | |
| "memory(GiB)": 5.71, | |
| "step": 18000, | |
| "train_speed(iter/s)": 1.094769 | |
| }, | |
| { | |
| "epoch": 0.15795495295503834, | |
| "grad_norm": 0.040227197110652924, | |
| "learning_rate": 9.684785625951468e-05, | |
| "loss": 0.009981593132019044, | |
| "memory(GiB)": 5.71, | |
| "step": 18500, | |
| "train_speed(iter/s)": 1.100633 | |
| }, | |
| { | |
| "epoch": 0.16222400573760695, | |
| "grad_norm": 0.03376320004463196, | |
| "learning_rate": 9.659652996230917e-05, | |
| "loss": 0.009874713897705079, | |
| "memory(GiB)": 5.71, | |
| "step": 19000, | |
| "train_speed(iter/s)": 1.106243 | |
| }, | |
| { | |
| "epoch": 0.16649305852017554, | |
| "grad_norm": 0.03337237238883972, | |
| "learning_rate": 9.633591680352522e-05, | |
| "loss": 0.009621439933776855, | |
| "memory(GiB)": 5.71, | |
| "step": 19500, | |
| "train_speed(iter/s)": 1.111407 | |
| }, | |
| { | |
| "epoch": 0.17076211130274416, | |
| "grad_norm": 0.03156784921884537, | |
| "learning_rate": 9.606606872433384e-05, | |
| "loss": 0.01175856876373291, | |
| "memory(GiB)": 5.73, | |
| "step": 20000, | |
| "train_speed(iter/s)": 1.116578 | |
| }, | |
| { | |
| "epoch": 0.17503116408531275, | |
| "grad_norm": 0.06789804250001907, | |
| "learning_rate": 9.578703950645998e-05, | |
| "loss": 0.008876850128173828, | |
| "memory(GiB)": 5.73, | |
| "step": 20500, | |
| "train_speed(iter/s)": 1.121386 | |
| }, | |
| { | |
| "epoch": 0.17930021686788136, | |
| "grad_norm": 0.029559865593910217, | |
| "learning_rate": 9.549888476146366e-05, | |
| "loss": 0.008808825492858887, | |
| "memory(GiB)": 5.73, | |
| "step": 21000, | |
| "train_speed(iter/s)": 1.126144 | |
| }, | |
| { | |
| "epoch": 0.18356926965044995, | |
| "grad_norm": 0.027149997651576996, | |
| "learning_rate": 9.52016619196564e-05, | |
| "loss": 0.008746042251586914, | |
| "memory(GiB)": 5.73, | |
| "step": 21500, | |
| "train_speed(iter/s)": 1.130706 | |
| }, | |
| { | |
| "epoch": 0.18783832243301857, | |
| "grad_norm": 0.031270887702703476, | |
| "learning_rate": 9.489543021865507e-05, | |
| "loss": 0.008727970123291016, | |
| "memory(GiB)": 5.73, | |
| "step": 22000, | |
| "train_speed(iter/s)": 1.135093 | |
| }, | |
| { | |
| "epoch": 0.19210737521558716, | |
| "grad_norm": 0.03134565427899361, | |
| "learning_rate": 9.458025069157563e-05, | |
| "loss": 0.008822738647460937, | |
| "memory(GiB)": 5.73, | |
| "step": 22500, | |
| "train_speed(iter/s)": 1.139318 | |
| }, | |
| { | |
| "epoch": 0.19637642799815577, | |
| "grad_norm": 0.02970048598945141, | |
| "learning_rate": 9.425618615486908e-05, | |
| "loss": 0.008724775314331055, | |
| "memory(GiB)": 5.73, | |
| "step": 23000, | |
| "train_speed(iter/s)": 1.143306 | |
| }, | |
| { | |
| "epoch": 0.20064548078072436, | |
| "grad_norm": 0.037413984537124634, | |
| "learning_rate": 9.392330119580186e-05, | |
| "loss": 0.008617961883544922, | |
| "memory(GiB)": 5.73, | |
| "step": 23500, | |
| "train_speed(iter/s)": 1.147167 | |
| }, | |
| { | |
| "epoch": 0.20491453356329298, | |
| "grad_norm": 0.031085532158613205, | |
| "learning_rate": 9.358166215958333e-05, | |
| "loss": 0.008613507270812988, | |
| "memory(GiB)": 5.73, | |
| "step": 24000, | |
| "train_speed(iter/s)": 1.150974 | |
| }, | |
| { | |
| "epoch": 0.2091835863458616, | |
| "grad_norm": 0.030068758875131607, | |
| "learning_rate": 9.323133713614297e-05, | |
| "loss": 0.008516620635986329, | |
| "memory(GiB)": 5.73, | |
| "step": 24500, | |
| "train_speed(iter/s)": 1.154635 | |
| }, | |
| { | |
| "epoch": 0.21345263912843018, | |
| "grad_norm": 0.030049536377191544, | |
| "learning_rate": 9.287239594655976e-05, | |
| "loss": 0.00915114688873291, | |
| "memory(GiB)": 5.73, | |
| "step": 25000, | |
| "train_speed(iter/s)": 1.158172 | |
| }, | |
| { | |
| "epoch": 0.2177216919109988, | |
| "grad_norm": 0.03236347809433937, | |
| "learning_rate": 9.250491012914668e-05, | |
| "loss": 0.008387946128845214, | |
| "memory(GiB)": 5.73, | |
| "step": 25500, | |
| "train_speed(iter/s)": 1.161598 | |
| }, | |
| { | |
| "epoch": 0.2219907446935674, | |
| "grad_norm": 0.028227701783180237, | |
| "learning_rate": 9.212895292519276e-05, | |
| "loss": 0.008091423034667969, | |
| "memory(GiB)": 5.73, | |
| "step": 26000, | |
| "train_speed(iter/s)": 1.164914 | |
| }, | |
| { | |
| "epoch": 0.226259797476136, | |
| "grad_norm": 0.026642831042408943, | |
| "learning_rate": 9.17445992643658e-05, | |
| "loss": 0.008073025703430176, | |
| "memory(GiB)": 5.73, | |
| "step": 26500, | |
| "train_speed(iter/s)": 1.168129 | |
| }, | |
| { | |
| "epoch": 0.2305288502587046, | |
| "grad_norm": 0.029216019436717033, | |
| "learning_rate": 9.135192574977873e-05, | |
| "loss": 0.008088951110839843, | |
| "memory(GiB)": 5.73, | |
| "step": 27000, | |
| "train_speed(iter/s)": 1.169593 | |
| }, | |
| { | |
| "epoch": 0.2347979030412732, | |
| "grad_norm": 0.02682262659072876, | |
| "learning_rate": 9.09510106427222e-05, | |
| "loss": 0.007971211433410645, | |
| "memory(GiB)": 5.73, | |
| "step": 27500, | |
| "train_speed(iter/s)": 1.172618 | |
| }, | |
| { | |
| "epoch": 0.2390669558238418, | |
| "grad_norm": 0.027296727523207664, | |
| "learning_rate": 9.054193384706688e-05, | |
| "loss": 0.007928550243377686, | |
| "memory(GiB)": 5.73, | |
| "step": 28000, | |
| "train_speed(iter/s)": 1.165921 | |
| }, | |
| { | |
| "epoch": 0.24333600860641041, | |
| "grad_norm": 0.03066374734044075, | |
| "learning_rate": 9.012477689333834e-05, | |
| "loss": 0.007805256366729736, | |
| "memory(GiB)": 5.73, | |
| "step": 28500, | |
| "train_speed(iter/s)": 1.155767 | |
| }, | |
| { | |
| "epoch": 0.247605061388979, | |
| "grad_norm": 0.027467776089906693, | |
| "learning_rate": 8.96996229224676e-05, | |
| "loss": 0.007825798034667968, | |
| "memory(GiB)": 5.73, | |
| "step": 29000, | |
| "train_speed(iter/s)": 1.147611 | |
| }, | |
| { | |
| "epoch": 0.2518741141715476, | |
| "grad_norm": 0.028940001502633095, | |
| "learning_rate": 8.926655666922102e-05, | |
| "loss": 0.007748476028442383, | |
| "memory(GiB)": 5.73, | |
| "step": 29500, | |
| "train_speed(iter/s)": 1.139656 | |
| }, | |
| { | |
| "epoch": 0.2561431669541162, | |
| "grad_norm": 0.0281364805996418, | |
| "learning_rate": 8.882566444531216e-05, | |
| "loss": 0.007644564628601074, | |
| "memory(GiB)": 5.73, | |
| "step": 30000, | |
| "train_speed(iter/s)": 1.131607 | |
| }, | |
| { | |
| "epoch": 0.2604122197366848, | |
| "grad_norm": 0.03272758424282074, | |
| "learning_rate": 8.837703412219962e-05, | |
| "loss": 0.007614383697509766, | |
| "memory(GiB)": 5.73, | |
| "step": 30500, | |
| "train_speed(iter/s)": 1.123907 | |
| }, | |
| { | |
| "epoch": 0.26468127251925344, | |
| "grad_norm": 0.033637482672929764, | |
| "learning_rate": 8.7920755113574e-05, | |
| "loss": 0.007485725402832031, | |
| "memory(GiB)": 5.73, | |
| "step": 31000, | |
| "train_speed(iter/s)": 1.118652 | |
| }, | |
| { | |
| "epoch": 0.26895032530182206, | |
| "grad_norm": 0.028677962720394135, | |
| "learning_rate": 8.745691835753724e-05, | |
| "loss": 0.007466458320617676, | |
| "memory(GiB)": 5.73, | |
| "step": 31500, | |
| "train_speed(iter/s)": 1.114283 | |
| }, | |
| { | |
| "epoch": 0.2732193780843906, | |
| "grad_norm": 0.026501238346099854, | |
| "learning_rate": 8.698561629847851e-05, | |
| "loss": 0.00739455795288086, | |
| "memory(GiB)": 5.73, | |
| "step": 32000, | |
| "train_speed(iter/s)": 1.110807 | |
| }, | |
| { | |
| "epoch": 0.27748843086695923, | |
| "grad_norm": 0.03185174614191055, | |
| "learning_rate": 8.650694286864957e-05, | |
| "loss": 0.007317279815673828, | |
| "memory(GiB)": 5.73, | |
| "step": 32500, | |
| "train_speed(iter/s)": 1.109657 | |
| }, | |
| { | |
| "epoch": 0.28175748364952785, | |
| "grad_norm": 0.031619079411029816, | |
| "learning_rate": 8.602099346944379e-05, | |
| "loss": 0.007236574649810791, | |
| "memory(GiB)": 5.73, | |
| "step": 33000, | |
| "train_speed(iter/s)": 1.109762 | |
| }, | |
| { | |
| "epoch": 0.28602653643209647, | |
| "grad_norm": 0.028590602800250053, | |
| "learning_rate": 8.552786495238226e-05, | |
| "loss": 0.00712824535369873, | |
| "memory(GiB)": 5.73, | |
| "step": 33500, | |
| "train_speed(iter/s)": 1.10959 | |
| }, | |
| { | |
| "epoch": 0.29029558921466503, | |
| "grad_norm": 0.026914609596133232, | |
| "learning_rate": 8.502765559981091e-05, | |
| "loss": 0.007133237838745117, | |
| "memory(GiB)": 5.73, | |
| "step": 34000, | |
| "train_speed(iter/s)": 1.108437 | |
| }, | |
| { | |
| "epoch": 0.29456464199723364, | |
| "grad_norm": 0.03186658397316933, | |
| "learning_rate": 8.452046510531258e-05, | |
| "loss": 0.00705194091796875, | |
| "memory(GiB)": 5.73, | |
| "step": 34500, | |
| "train_speed(iter/s)": 1.111376 | |
| }, | |
| { | |
| "epoch": 0.29883369477980226, | |
| "grad_norm": 0.022866345942020416, | |
| "learning_rate": 8.400639455383754e-05, | |
| "loss": 0.006991560935974121, | |
| "memory(GiB)": 5.73, | |
| "step": 35000, | |
| "train_speed(iter/s)": 1.103171 | |
| }, | |
| { | |
| "epoch": 0.3031027475623709, | |
| "grad_norm": 0.027075253427028656, | |
| "learning_rate": 8.348554640155709e-05, | |
| "loss": 0.006916217803955078, | |
| "memory(GiB)": 5.73, | |
| "step": 35500, | |
| "train_speed(iter/s)": 1.094784 | |
| }, | |
| { | |
| "epoch": 0.30737180034493944, | |
| "grad_norm": 0.027598075568675995, | |
| "learning_rate": 8.295802445544345e-05, | |
| "loss": 0.0068712844848632815, | |
| "memory(GiB)": 5.73, | |
| "step": 36000, | |
| "train_speed(iter/s)": 1.087037 | |
| }, | |
| { | |
| "epoch": 0.31164085312750806, | |
| "grad_norm": 0.022508256137371063, | |
| "learning_rate": 8.242393385258083e-05, | |
| "loss": 0.006878099918365479, | |
| "memory(GiB)": 5.73, | |
| "step": 36500, | |
| "train_speed(iter/s)": 1.080097 | |
| }, | |
| { | |
| "epoch": 0.31590990591007667, | |
| "grad_norm": 0.02388549968600273, | |
| "learning_rate": 8.188338103921109e-05, | |
| "loss": 0.006974416732788086, | |
| "memory(GiB)": 5.73, | |
| "step": 37000, | |
| "train_speed(iter/s)": 1.073446 | |
| }, | |
| { | |
| "epoch": 0.3201789586926453, | |
| "grad_norm": 0.025459734722971916, | |
| "learning_rate": 8.13364737495187e-05, | |
| "loss": 0.0067239184379577635, | |
| "memory(GiB)": 5.73, | |
| "step": 37500, | |
| "train_speed(iter/s)": 1.067642 | |
| }, | |
| { | |
| "epoch": 0.3244480114752139, | |
| "grad_norm": 0.023768454790115356, | |
| "learning_rate": 8.078332098415881e-05, | |
| "loss": 0.006635515213012695, | |
| "memory(GiB)": 5.73, | |
| "step": 38000, | |
| "train_speed(iter/s)": 1.067385 | |
| }, | |
| { | |
| "epoch": 0.32871706425778247, | |
| "grad_norm": 0.028179064393043518, | |
| "learning_rate": 8.022403298853317e-05, | |
| "loss": 0.00661515998840332, | |
| "memory(GiB)": 5.73, | |
| "step": 38500, | |
| "train_speed(iter/s)": 1.067485 | |
| }, | |
| { | |
| "epoch": 0.3329861170403511, | |
| "grad_norm": 0.026124022901058197, | |
| "learning_rate": 7.965872123081765e-05, | |
| "loss": 0.006523737907409668, | |
| "memory(GiB)": 5.73, | |
| "step": 39000, | |
| "train_speed(iter/s)": 1.067501 | |
| }, | |
| { | |
| "epoch": 0.3372551698229197, | |
| "grad_norm": 0.02668868564069271, | |
| "learning_rate": 7.908749837974632e-05, | |
| "loss": 0.006474626541137695, | |
| "memory(GiB)": 5.73, | |
| "step": 39500, | |
| "train_speed(iter/s)": 1.067703 | |
| }, | |
| { | |
| "epoch": 0.3415242226054883, | |
| "grad_norm": 0.02441154234111309, | |
| "learning_rate": 7.851047828215611e-05, | |
| "loss": 0.006419078826904297, | |
| "memory(GiB)": 5.73, | |
| "step": 40000, | |
| "train_speed(iter/s)": 1.06808 | |
| }, | |
| { | |
| "epoch": 0.3457932753880569, | |
| "grad_norm": 0.0254750307649374, | |
| "learning_rate": 7.792777594029674e-05, | |
| "loss": 0.006350691795349121, | |
| "memory(GiB)": 5.73, | |
| "step": 40500, | |
| "train_speed(iter/s)": 1.068683 | |
| }, | |
| { | |
| "epoch": 0.3500623281706255, | |
| "grad_norm": 0.027933409437537193, | |
| "learning_rate": 7.73395074889103e-05, | |
| "loss": 0.006355803966522217, | |
| "memory(GiB)": 5.73, | |
| "step": 41000, | |
| "train_speed(iter/s)": 1.064808 | |
| }, | |
| { | |
| "epoch": 0.3543313809531941, | |
| "grad_norm": 0.022553391754627228, | |
| "learning_rate": 7.67457901720852e-05, | |
| "loss": 0.006336944103240967, | |
| "memory(GiB)": 5.73, | |
| "step": 41500, | |
| "train_speed(iter/s)": 1.060284 | |
| }, | |
| { | |
| "epoch": 0.3586004337357627, | |
| "grad_norm": 0.027581321075558662, | |
| "learning_rate": 7.614674231988903e-05, | |
| "loss": 0.00619974422454834, | |
| "memory(GiB)": 5.73, | |
| "step": 42000, | |
| "train_speed(iter/s)": 1.055658 | |
| }, | |
| { | |
| "epoch": 0.3628694865183313, | |
| "grad_norm": 0.02141967974603176, | |
| "learning_rate": 7.554248332478485e-05, | |
| "loss": 0.006249521732330322, | |
| "memory(GiB)": 5.73, | |
| "step": 42500, | |
| "train_speed(iter/s)": 1.051341 | |
| }, | |
| { | |
| "epoch": 0.3671385393008999, | |
| "grad_norm": 0.025843387469649315, | |
| "learning_rate": 7.49331336178358e-05, | |
| "loss": 0.006162589550018311, | |
| "memory(GiB)": 5.73, | |
| "step": 43000, | |
| "train_speed(iter/s)": 1.046866 | |
| }, | |
| { | |
| "epoch": 0.3714075920834685, | |
| "grad_norm": 0.02431940846145153, | |
| "learning_rate": 7.431881464470293e-05, | |
| "loss": 0.0060729503631591795, | |
| "memory(GiB)": 5.73, | |
| "step": 43500, | |
| "train_speed(iter/s)": 1.042554 | |
| }, | |
| { | |
| "epoch": 0.37567664486603713, | |
| "grad_norm": 0.0244905948638916, | |
| "learning_rate": 7.369964884144047e-05, | |
| "loss": 0.006033665180206299, | |
| "memory(GiB)": 5.73, | |
| "step": 44000, | |
| "train_speed(iter/s)": 1.041578 | |
| }, | |
| { | |
| "epoch": 0.37994569764860575, | |
| "grad_norm": 0.02309691719710827, | |
| "learning_rate": 7.307575961009385e-05, | |
| "loss": 0.006005731582641602, | |
| "memory(GiB)": 5.73, | |
| "step": 44500, | |
| "train_speed(iter/s)": 1.041875 | |
| }, | |
| { | |
| "epoch": 0.3842147504311743, | |
| "grad_norm": 0.023321352899074554, | |
| "learning_rate": 7.24472712941053e-05, | |
| "loss": 0.005931224346160889, | |
| "memory(GiB)": 5.73, | |
| "step": 45000, | |
| "train_speed(iter/s)": 1.044453 | |
| }, | |
| { | |
| "epoch": 0.38848380321374293, | |
| "grad_norm": 0.024199847131967545, | |
| "learning_rate": 7.181430915353171e-05, | |
| "loss": 0.0059114408493041995, | |
| "memory(GiB)": 5.73, | |
| "step": 45500, | |
| "train_speed(iter/s)": 1.047147 | |
| }, | |
| { | |
| "epoch": 0.39275285599631155, | |
| "grad_norm": 0.02660815231502056, | |
| "learning_rate": 7.117699934007987e-05, | |
| "loss": 0.005867915630340576, | |
| "memory(GiB)": 5.73, | |
| "step": 46000, | |
| "train_speed(iter/s)": 1.049798 | |
| }, | |
| { | |
| "epoch": 0.39702190877888016, | |
| "grad_norm": 0.02538706362247467, | |
| "learning_rate": 7.053546887196391e-05, | |
| "loss": 0.005895719528198242, | |
| "memory(GiB)": 5.73, | |
| "step": 46500, | |
| "train_speed(iter/s)": 1.052318 | |
| }, | |
| { | |
| "epoch": 0.4012909615614487, | |
| "grad_norm": 0.023992260918021202, | |
| "learning_rate": 6.988984560859009e-05, | |
| "loss": 0.005823767662048339, | |
| "memory(GiB)": 5.73, | |
| "step": 47000, | |
| "train_speed(iter/s)": 1.054874 | |
| }, | |
| { | |
| "epoch": 0.40556001434401734, | |
| "grad_norm": 0.024961460381746292, | |
| "learning_rate": 6.924025822507398e-05, | |
| "loss": 0.005796549797058105, | |
| "memory(GiB)": 5.73, | |
| "step": 47500, | |
| "train_speed(iter/s)": 1.057392 | |
| }, | |
| { | |
| "epoch": 0.40982906712658596, | |
| "grad_norm": 0.026839323341846466, | |
| "learning_rate": 6.858683618659509e-05, | |
| "loss": 0.0057229394912719726, | |
| "memory(GiB)": 5.73, | |
| "step": 48000, | |
| "train_speed(iter/s)": 1.059871 | |
| }, | |
| { | |
| "epoch": 0.41409811990915457, | |
| "grad_norm": 0.026930488646030426, | |
| "learning_rate": 6.792970972259381e-05, | |
| "loss": 0.005688785552978515, | |
| "memory(GiB)": 5.73, | |
| "step": 48500, | |
| "train_speed(iter/s)": 1.062309 | |
| }, | |
| { | |
| "epoch": 0.4183671726917232, | |
| "grad_norm": 0.024773526936769485, | |
| "learning_rate": 6.726900980081639e-05, | |
| "loss": 0.005612356185913086, | |
| "memory(GiB)": 5.73, | |
| "step": 49000, | |
| "train_speed(iter/s)": 1.06471 | |
| }, | |
| { | |
| "epoch": 0.42263622547429175, | |
| "grad_norm": 0.025835830718278885, | |
| "learning_rate": 6.660486810121244e-05, | |
| "loss": 0.005570381164550781, | |
| "memory(GiB)": 5.73, | |
| "step": 49500, | |
| "train_speed(iter/s)": 1.067072 | |
| }, | |
| { | |
| "epoch": 0.42690527825686037, | |
| "grad_norm": 0.028116557747125626, | |
| "learning_rate": 6.593741698969073e-05, | |
| "loss": 0.005553098201751709, | |
| "memory(GiB)": 5.73, | |
| "step": 50000, | |
| "train_speed(iter/s)": 1.069395 | |
| }, | |
| { | |
| "epoch": 0.431174331039429, | |
| "grad_norm": 0.026658741757273674, | |
| "learning_rate": 6.526678949173808e-05, | |
| "loss": 0.005453477859497071, | |
| "memory(GiB)": 5.73, | |
| "step": 50500, | |
| "train_speed(iter/s)": 1.065559 | |
| }, | |
| { | |
| "epoch": 0.4354433838219976, | |
| "grad_norm": 0.02522198110818863, | |
| "learning_rate": 6.459311926590695e-05, | |
| "loss": 0.005405562877655029, | |
| "memory(GiB)": 5.73, | |
| "step": 51000, | |
| "train_speed(iter/s)": 1.061202 | |
| }, | |
| { | |
| "epoch": 0.43971243660456616, | |
| "grad_norm": 0.019938671961426735, | |
| "learning_rate": 6.391654057717676e-05, | |
| "loss": 0.005375346183776855, | |
| "memory(GiB)": 5.73, | |
| "step": 51500, | |
| "train_speed(iter/s)": 1.05697 | |
| }, | |
| { | |
| "epoch": 0.4439814893871348, | |
| "grad_norm": 0.02449255809187889, | |
| "learning_rate": 6.32371882701944e-05, | |
| "loss": 0.00538975715637207, | |
| "memory(GiB)": 5.73, | |
| "step": 52000, | |
| "train_speed(iter/s)": 1.053086 | |
| }, | |
| { | |
| "epoch": 0.4482505421697034, | |
| "grad_norm": 0.027349578216671944, | |
| "learning_rate": 6.25551977423992e-05, | |
| "loss": 0.005338613510131836, | |
| "memory(GiB)": 5.73, | |
| "step": 52500, | |
| "train_speed(iter/s)": 1.049655 | |
| }, | |
| { | |
| "epoch": 0.452519594952272, | |
| "grad_norm": 0.02677008882164955, | |
| "learning_rate": 6.187070491703767e-05, | |
| "loss": 0.005392338752746582, | |
| "memory(GiB)": 5.73, | |
| "step": 53000, | |
| "train_speed(iter/s)": 1.046434 | |
| }, | |
| { | |
| "epoch": 0.45678864773484057, | |
| "grad_norm": 0.021387379616498947, | |
| "learning_rate": 6.118384621607356e-05, | |
| "loss": 0.0052757196426391605, | |
| "memory(GiB)": 5.73, | |
| "step": 53500, | |
| "train_speed(iter/s)": 1.043484 | |
| }, | |
| { | |
| "epoch": 0.4610577005174092, | |
| "grad_norm": 0.021920237690210342, | |
| "learning_rate": 6.0494758532998397e-05, | |
| "loss": 0.0052754092216491695, | |
| "memory(GiB)": 5.73, | |
| "step": 54000, | |
| "train_speed(iter/s)": 1.040652 | |
| }, | |
| { | |
| "epoch": 0.4653267532999778, | |
| "grad_norm": 0.02255011908710003, | |
| "learning_rate": 5.980357920554813e-05, | |
| "loss": 0.005176177024841308, | |
| "memory(GiB)": 5.73, | |
| "step": 54500, | |
| "train_speed(iter/s)": 1.03761 | |
| }, | |
| { | |
| "epoch": 0.4695958060825464, | |
| "grad_norm": 0.023933693766593933, | |
| "learning_rate": 5.91104459883312e-05, | |
| "loss": 0.00518220043182373, | |
| "memory(GiB)": 5.73, | |
| "step": 55000, | |
| "train_speed(iter/s)": 1.03464 | |
| }, | |
| { | |
| "epoch": 0.47386485886511504, | |
| "grad_norm": 0.02640974149107933, | |
| "learning_rate": 5.8415497025373545e-05, | |
| "loss": 0.0051289405822753905, | |
| "memory(GiB)": 5.73, | |
| "step": 55500, | |
| "train_speed(iter/s)": 1.032562 | |
| }, | |
| { | |
| "epoch": 0.4781339116476836, | |
| "grad_norm": 0.027417296543717384, | |
| "learning_rate": 5.771887082258598e-05, | |
| "loss": 0.005091516494750976, | |
| "memory(GiB)": 5.73, | |
| "step": 56000, | |
| "train_speed(iter/s)": 1.031309 | |
| }, | |
| { | |
| "epoch": 0.4824029644302522, | |
| "grad_norm": 0.02626318484544754, | |
| "learning_rate": 5.7020706220159446e-05, | |
| "loss": 0.005014698505401611, | |
| "memory(GiB)": 5.73, | |
| "step": 56500, | |
| "train_speed(iter/s)": 1.030475 | |
| }, | |
| { | |
| "epoch": 0.48667201721282083, | |
| "grad_norm": 0.022486470639705658, | |
| "learning_rate": 5.6321142364893655e-05, | |
| "loss": 0.00502289867401123, | |
| "memory(GiB)": 5.73, | |
| "step": 57000, | |
| "train_speed(iter/s)": 1.029867 | |
| }, | |
| { | |
| "epoch": 0.49094106999538945, | |
| "grad_norm": 0.024762239307165146, | |
| "learning_rate": 5.562031868246459e-05, | |
| "loss": 0.004976710319519043, | |
| "memory(GiB)": 5.73, | |
| "step": 57500, | |
| "train_speed(iter/s)": 1.029133 | |
| }, | |
| { | |
| "epoch": 0.495210122777958, | |
| "grad_norm": 0.02197747305035591, | |
| "learning_rate": 5.49183748496365e-05, | |
| "loss": 0.004930309295654297, | |
| "memory(GiB)": 5.73, | |
| "step": 58000, | |
| "train_speed(iter/s)": 1.03126 | |
| }, | |
| { | |
| "epoch": 0.4994791755605266, | |
| "grad_norm": 0.017993444576859474, | |
| "learning_rate": 5.421545076642376e-05, | |
| "loss": 0.004885564804077149, | |
| "memory(GiB)": 5.73, | |
| "step": 58500, | |
| "train_speed(iter/s)": 1.033407 | |
| }, | |
| { | |
| "epoch": 0.5037482283430952, | |
| "grad_norm": 0.023290056735277176, | |
| "learning_rate": 5.351168652820825e-05, | |
| "loss": 0.004815481662750244, | |
| "memory(GiB)": 5.73, | |
| "step": 59000, | |
| "train_speed(iter/s)": 1.035534 | |
| }, | |
| { | |
| "epoch": 0.5080172811256638, | |
| "grad_norm": 0.02278745174407959, | |
| "learning_rate": 5.2807222397817946e-05, | |
| "loss": 0.0048018951416015625, | |
| "memory(GiB)": 5.73, | |
| "step": 59500, | |
| "train_speed(iter/s)": 1.037635 | |
| }, | |
| { | |
| "epoch": 0.5122863339082324, | |
| "grad_norm": 0.01709616929292679, | |
| "learning_rate": 5.210219877757185e-05, | |
| "loss": 0.004790943622589111, | |
| "memory(GiB)": 5.73, | |
| "step": 60000, | |
| "train_speed(iter/s)": 1.039708 | |
| }, | |
| { | |
| "epoch": 0.516555386690801, | |
| "grad_norm": 0.024141253903508186, | |
| "learning_rate": 5.139675618129741e-05, | |
| "loss": 0.0047971105575561526, | |
| "memory(GiB)": 5.73, | |
| "step": 60500, | |
| "train_speed(iter/s)": 1.041714 | |
| }, | |
| { | |
| "epoch": 0.5208244394733696, | |
| "grad_norm": 0.025403697043657303, | |
| "learning_rate": 5.069103520632558e-05, | |
| "loss": 0.0046922645568847655, | |
| "memory(GiB)": 5.73, | |
| "step": 61000, | |
| "train_speed(iter/s)": 1.043735 | |
| }, | |
| { | |
| "epoch": 0.5250934922559383, | |
| "grad_norm": 0.023161958903074265, | |
| "learning_rate": 4.998517650546916e-05, | |
| "loss": 0.0046929998397827145, | |
| "memory(GiB)": 5.73, | |
| "step": 61500, | |
| "train_speed(iter/s)": 1.045718 | |
| }, | |
| { | |
| "epoch": 0.5293625450385069, | |
| "grad_norm": 0.022052627056837082, | |
| "learning_rate": 4.927932075899032e-05, | |
| "loss": 0.004638696193695068, | |
| "memory(GiB)": 5.73, | |
| "step": 62000, | |
| "train_speed(iter/s)": 1.043334 | |
| }, | |
| { | |
| "epoch": 0.5336315978210755, | |
| "grad_norm": 0.023017114028334618, | |
| "learning_rate": 4.857360864656229e-05, | |
| "loss": 0.004680471420288086, | |
| "memory(GiB)": 5.73, | |
| "step": 62500, | |
| "train_speed(iter/s)": 1.041039 | |
| }, | |
| { | |
| "epoch": 0.5379006506036441, | |
| "grad_norm": 0.023162037134170532, | |
| "learning_rate": 4.7868180819231614e-05, | |
| "loss": 0.004635006904602051, | |
| "memory(GiB)": 5.73, | |
| "step": 63000, | |
| "train_speed(iter/s)": 1.039508 | |
| }, | |
| { | |
| "epoch": 0.5421697033862126, | |
| "grad_norm": 0.02154356613755226, | |
| "learning_rate": 4.7163177871385713e-05, | |
| "loss": 0.004594725131988525, | |
| "memory(GiB)": 5.73, | |
| "step": 63500, | |
| "train_speed(iter/s)": 1.037869 | |
| }, | |
| { | |
| "epoch": 0.5464387561687812, | |
| "grad_norm": 0.024489399045705795, | |
| "learning_rate": 4.6458740312731915e-05, | |
| "loss": 0.004505970001220703, | |
| "memory(GiB)": 5.73, | |
| "step": 64000, | |
| "train_speed(iter/s)": 1.036001 | |
| }, | |
| { | |
| "epoch": 0.5507078089513499, | |
| "grad_norm": 0.02230563387274742, | |
| "learning_rate": 4.575500854029343e-05, | |
| "loss": 0.004512208938598633, | |
| "memory(GiB)": 5.73, | |
| "step": 64500, | |
| "train_speed(iter/s)": 1.034042 | |
| }, | |
| { | |
| "epoch": 0.5549768617339185, | |
| "grad_norm": 0.024222563952207565, | |
| "learning_rate": 4.5052122810427655e-05, | |
| "loss": 0.004453976154327393, | |
| "memory(GiB)": 5.73, | |
| "step": 65000, | |
| "train_speed(iter/s)": 1.033383 | |
| }, | |
| { | |
| "epoch": 0.5592459145164871, | |
| "grad_norm": 0.024108612909913063, | |
| "learning_rate": 4.435022321087251e-05, | |
| "loss": 0.004433969497680664, | |
| "memory(GiB)": 5.73, | |
| "step": 65500, | |
| "train_speed(iter/s)": 1.031504 | |
| }, | |
| { | |
| "epoch": 0.5635149672990557, | |
| "grad_norm": 0.02404128573834896, | |
| "learning_rate": 4.3649449632826524e-05, | |
| "loss": 0.004369840621948242, | |
| "memory(GiB)": 5.73, | |
| "step": 66000, | |
| "train_speed(iter/s)": 1.029515 | |
| }, | |
| { | |
| "epoch": 0.5677840200816243, | |
| "grad_norm": 0.02122694067656994, | |
| "learning_rate": 4.294994174306796e-05, | |
| "loss": 0.00436569881439209, | |
| "memory(GiB)": 5.73, | |
| "step": 66500, | |
| "train_speed(iter/s)": 1.027863 | |
| }, | |
| { | |
| "epoch": 0.5720530728641929, | |
| "grad_norm": 0.02231895923614502, | |
| "learning_rate": 4.2251838956118646e-05, | |
| "loss": 0.004324491500854492, | |
| "memory(GiB)": 5.73, | |
| "step": 67000, | |
| "train_speed(iter/s)": 1.026447 | |
| }, | |
| { | |
| "epoch": 0.5763221256467616, | |
| "grad_norm": 0.01995609700679779, | |
| "learning_rate": 4.1555280406458243e-05, | |
| "loss": 0.004273086071014404, | |
| "memory(GiB)": 5.73, | |
| "step": 67500, | |
| "train_speed(iter/s)": 1.025095 | |
| }, | |
| { | |
| "epoch": 0.5805911784293301, | |
| "grad_norm": 0.023028602823615074, | |
| "learning_rate": 4.086040492079418e-05, | |
| "loss": 0.004247576713562012, | |
| "memory(GiB)": 5.73, | |
| "step": 68000, | |
| "train_speed(iter/s)": 1.024105 | |
| }, | |
| { | |
| "epoch": 0.5848602312118987, | |
| "grad_norm": 0.02473682351410389, | |
| "learning_rate": 4.016735099039299e-05, | |
| "loss": 0.004212839603424072, | |
| "memory(GiB)": 5.73, | |
| "step": 68500, | |
| "train_speed(iter/s)": 1.025833 | |
| }, | |
| { | |
| "epoch": 0.5891292839944673, | |
| "grad_norm": 0.02591153420507908, | |
| "learning_rate": 3.947625674347842e-05, | |
| "loss": 0.004188227653503418, | |
| "memory(GiB)": 5.73, | |
| "step": 69000, | |
| "train_speed(iter/s)": 1.027676 | |
| }, | |
| { | |
| "epoch": 0.5933983367770359, | |
| "grad_norm": 0.022372225299477577, | |
| "learning_rate": 3.878725991770206e-05, | |
| "loss": 0.00420154619216919, | |
| "memory(GiB)": 5.73, | |
| "step": 69500, | |
| "train_speed(iter/s)": 1.029494 | |
| }, | |
| { | |
| "epoch": 0.5976673895596045, | |
| "grad_norm": 0.020848704501986504, | |
| "learning_rate": 3.810049783269169e-05, | |
| "loss": 0.004149648189544677, | |
| "memory(GiB)": 5.73, | |
| "step": 70000, | |
| "train_speed(iter/s)": 1.031265 | |
| }, | |
| { | |
| "epoch": 0.6019364423421731, | |
| "grad_norm": 0.020646043121814728, | |
| "learning_rate": 3.7416107362682874e-05, | |
| "loss": 0.004120903968811035, | |
| "memory(GiB)": 5.73, | |
| "step": 70500, | |
| "train_speed(iter/s)": 1.03288 | |
| }, | |
| { | |
| "epoch": 0.6062054951247418, | |
| "grad_norm": 0.02318960428237915, | |
| "learning_rate": 3.673422490923957e-05, | |
| "loss": 0.004070096492767334, | |
| "memory(GiB)": 5.73, | |
| "step": 71000, | |
| "train_speed(iter/s)": 1.031156 | |
| }, | |
| { | |
| "epoch": 0.6104745479073104, | |
| "grad_norm": 0.01929691806435585, | |
| "learning_rate": 3.605498637406871e-05, | |
| "loss": 0.0040385212898254395, | |
| "memory(GiB)": 5.73, | |
| "step": 71500, | |
| "train_speed(iter/s)": 1.029013 | |
| }, | |
| { | |
| "epoch": 0.6147436006898789, | |
| "grad_norm": 0.0221713837236166, | |
| "learning_rate": 3.5378527131934415e-05, | |
| "loss": 0.004040939807891846, | |
| "memory(GiB)": 5.73, | |
| "step": 72000, | |
| "train_speed(iter/s)": 1.027147 | |
| }, | |
| { | |
| "epoch": 0.6190126534724475, | |
| "grad_norm": 0.026295281946659088, | |
| "learning_rate": 3.470498200367745e-05, | |
| "loss": 0.003968184471130371, | |
| "memory(GiB)": 5.73, | |
| "step": 72500, | |
| "train_speed(iter/s)": 1.025599 | |
| }, | |
| { | |
| "epoch": 0.6232817062550161, | |
| "grad_norm": 0.022878218442201614, | |
| "learning_rate": 3.403448522934484e-05, | |
| "loss": 0.00394676160812378, | |
| "memory(GiB)": 5.73, | |
| "step": 73000, | |
| "train_speed(iter/s)": 1.024666 | |
| }, | |
| { | |
| "epoch": 0.6275507590375847, | |
| "grad_norm": 0.017653649672865868, | |
| "learning_rate": 3.3367170441435326e-05, | |
| "loss": 0.003906076669692993, | |
| "memory(GiB)": 5.73, | |
| "step": 73500, | |
| "train_speed(iter/s)": 1.023811 | |
| }, | |
| { | |
| "epoch": 0.6318198118201533, | |
| "grad_norm": 0.021848097443580627, | |
| "learning_rate": 3.270317063826594e-05, | |
| "loss": 0.0038814377784729005, | |
| "memory(GiB)": 5.73, | |
| "step": 74000, | |
| "train_speed(iter/s)": 1.023855 | |
| }, | |
| { | |
| "epoch": 0.636088864602722, | |
| "grad_norm": 0.022029753774404526, | |
| "learning_rate": 3.204261815746496e-05, | |
| "loss": 0.003879170894622803, | |
| "memory(GiB)": 5.73, | |
| "step": 74500, | |
| "train_speed(iter/s)": 1.024885 | |
| }, | |
| { | |
| "epoch": 0.6403579173852906, | |
| "grad_norm": 0.02403407171368599, | |
| "learning_rate": 3.1385644649596445e-05, | |
| "loss": 0.003841569900512695, | |
| "memory(GiB)": 5.73, | |
| "step": 75000, | |
| "train_speed(iter/s)": 1.026583 | |
| }, | |
| { | |
| "epoch": 0.6446269701678592, | |
| "grad_norm": 0.023609979078173637, | |
| "learning_rate": 3.073238105192191e-05, | |
| "loss": 0.0038005766868591307, | |
| "memory(GiB)": 5.73, | |
| "step": 75500, | |
| "train_speed(iter/s)": 1.028269 | |
| }, | |
| { | |
| "epoch": 0.6488960229504278, | |
| "grad_norm": 0.01760837249457836, | |
| "learning_rate": 3.008295756230397e-05, | |
| "loss": 0.0037522752285003664, | |
| "memory(GiB)": 5.73, | |
| "step": 76000, | |
| "train_speed(iter/s)": 1.029938 | |
| }, | |
| { | |
| "epoch": 0.6531650757329963, | |
| "grad_norm": 0.021126747131347656, | |
| "learning_rate": 2.943750361325739e-05, | |
| "loss": 0.003741382837295532, | |
| "memory(GiB)": 5.73, | |
| "step": 76500, | |
| "train_speed(iter/s)": 1.03159 | |
| }, | |
| { | |
| "epoch": 0.6574341285155649, | |
| "grad_norm": 0.02278253622353077, | |
| "learning_rate": 2.879614784615281e-05, | |
| "loss": 0.0037315216064453126, | |
| "memory(GiB)": 5.73, | |
| "step": 77000, | |
| "train_speed(iter/s)": 1.033224 | |
| }, | |
| { | |
| "epoch": 0.6617031812981335, | |
| "grad_norm": 0.023599898442626, | |
| "learning_rate": 2.8159018085577936e-05, | |
| "loss": 0.0037167372703552247, | |
| "memory(GiB)": 5.73, | |
| "step": 77500, | |
| "train_speed(iter/s)": 1.034809 | |
| }, | |
| { | |
| "epoch": 0.6659722340807022, | |
| "grad_norm": 0.02341049537062645, | |
| "learning_rate": 2.752624131386169e-05, | |
| "loss": 0.0036745924949645997, | |
| "memory(GiB)": 5.73, | |
| "step": 78000, | |
| "train_speed(iter/s)": 1.036412 | |
| }, | |
| { | |
| "epoch": 0.6702412868632708, | |
| "grad_norm": 0.021224385127425194, | |
| "learning_rate": 2.68979436457661e-05, | |
| "loss": 0.0036270735263824465, | |
| "memory(GiB)": 5.73, | |
| "step": 78500, | |
| "train_speed(iter/s)": 1.035171 | |
| }, | |
| { | |
| "epoch": 0.6745103396458394, | |
| "grad_norm": 0.02113701030611992, | |
| "learning_rate": 2.6274250303351277e-05, | |
| "loss": 0.003653192758560181, | |
| "memory(GiB)": 5.73, | |
| "step": 79000, | |
| "train_speed(iter/s)": 1.033322 | |
| }, | |
| { | |
| "epoch": 0.678779392428408, | |
| "grad_norm": 0.02273395285010338, | |
| "learning_rate": 2.5655285591018053e-05, | |
| "loss": 0.003600950241088867, | |
| "memory(GiB)": 5.73, | |
| "step": 79500, | |
| "train_speed(iter/s)": 1.03175 | |
| }, | |
| { | |
| "epoch": 0.6830484452109766, | |
| "grad_norm": 0.01843477226793766, | |
| "learning_rate": 2.5041172870733688e-05, | |
| "loss": 0.003576310634613037, | |
| "memory(GiB)": 5.73, | |
| "step": 80000, | |
| "train_speed(iter/s)": 1.030732 | |
| }, | |
| { | |
| "epoch": 0.6873174979935452, | |
| "grad_norm": 0.021858269348740578, | |
| "learning_rate": 2.4432034537445504e-05, | |
| "loss": 0.0035532989501953125, | |
| "memory(GiB)": 5.73, | |
| "step": 80500, | |
| "train_speed(iter/s)": 1.030234 | |
| }, | |
| { | |
| "epoch": 0.6915865507761138, | |
| "grad_norm": 0.02257091924548149, | |
| "learning_rate": 2.3827991994686855e-05, | |
| "loss": 0.0034713072776794435, | |
| "memory(GiB)": 5.73, | |
| "step": 81000, | |
| "train_speed(iter/s)": 1.029758 | |
| }, | |
| { | |
| "epoch": 0.6958556035586824, | |
| "grad_norm": 0.02086802013218403, | |
| "learning_rate": 2.3229165630381254e-05, | |
| "loss": 0.0035013933181762694, | |
| "memory(GiB)": 5.73, | |
| "step": 81500, | |
| "train_speed(iter/s)": 1.029855 | |
| }, | |
| { | |
| "epoch": 0.700124656341251, | |
| "grad_norm": 0.02159390039741993, | |
| "learning_rate": 2.263567479284836e-05, | |
| "loss": 0.0034512946605682374, | |
| "memory(GiB)": 5.73, | |
| "step": 82000, | |
| "train_speed(iter/s)": 1.031396 | |
| }, | |
| { | |
| "epoch": 0.7043937091238196, | |
| "grad_norm": 0.02238837257027626, | |
| "learning_rate": 2.2047637767017594e-05, | |
| "loss": 0.0034342200756073, | |
| "memory(GiB)": 5.73, | |
| "step": 82500, | |
| "train_speed(iter/s)": 1.029892 | |
| }, | |
| { | |
| "epoch": 0.7086627619063882, | |
| "grad_norm": 0.022957606241106987, | |
| "learning_rate": 2.1465171750853386e-05, | |
| "loss": 0.003412749528884888, | |
| "memory(GiB)": 5.73, | |
| "step": 83000, | |
| "train_speed(iter/s)": 1.02831 | |
| }, | |
| { | |
| "epoch": 0.7129318146889568, | |
| "grad_norm": 0.019689923152327538, | |
| "learning_rate": 2.0888392831997238e-05, | |
| "loss": 0.00341141414642334, | |
| "memory(GiB)": 5.73, | |
| "step": 83500, | |
| "train_speed(iter/s)": 1.026956 | |
| }, | |
| { | |
| "epoch": 0.7172008674715254, | |
| "grad_norm": 0.023503178730607033, | |
| "learning_rate": 2.03174159646311e-05, | |
| "loss": 0.0033840060234069822, | |
| "memory(GiB)": 5.73, | |
| "step": 84000, | |
| "train_speed(iter/s)": 1.025661 | |
| }, | |
| { | |
| "epoch": 0.7214699202540941, | |
| "grad_norm": 0.02037668041884899, | |
| "learning_rate": 1.9752354946566354e-05, | |
| "loss": 0.0033505113124847412, | |
| "memory(GiB)": 5.73, | |
| "step": 84500, | |
| "train_speed(iter/s)": 1.02442 | |
| }, | |
| { | |
| "epoch": 0.7257389730366626, | |
| "grad_norm": 0.025251047685742378, | |
| "learning_rate": 1.9193322396563785e-05, | |
| "loss": 0.0033303892612457277, | |
| "memory(GiB)": 5.73, | |
| "step": 85000, | |
| "train_speed(iter/s)": 1.023539 | |
| }, | |
| { | |
| "epoch": 0.7300080258192312, | |
| "grad_norm": 0.01954658329486847, | |
| "learning_rate": 1.8640429731887998e-05, | |
| "loss": 0.003283708333969116, | |
| "memory(GiB)": 5.73, | |
| "step": 85500, | |
| "train_speed(iter/s)": 1.023297 | |
| }, | |
| { | |
| "epoch": 0.7342770786017998, | |
| "grad_norm": 0.0188963171094656, | |
| "learning_rate": 1.809378714610167e-05, | |
| "loss": 0.003271867275238037, | |
| "memory(GiB)": 5.73, | |
| "step": 86000, | |
| "train_speed(iter/s)": 1.023267 | |
| }, | |
| { | |
| "epoch": 0.7385461313843684, | |
| "grad_norm": 0.02359418198466301, | |
| "learning_rate": 1.7553503587103505e-05, | |
| "loss": 0.0032482266426086424, | |
| "memory(GiB)": 5.73, | |
| "step": 86500, | |
| "train_speed(iter/s)": 1.023221 | |
| }, | |
| { | |
| "epoch": 0.742815184166937, | |
| "grad_norm": 0.020105060189962387, | |
| "learning_rate": 1.701968673541458e-05, | |
| "loss": 0.003266146183013916, | |
| "memory(GiB)": 5.73, | |
| "step": 87000, | |
| "train_speed(iter/s)": 1.023208 | |
| }, | |
| { | |
| "epoch": 0.7470842369495057, | |
| "grad_norm": 0.018053073436021805, | |
| "learning_rate": 1.649244298271714e-05, | |
| "loss": 0.003204747676849365, | |
| "memory(GiB)": 5.73, | |
| "step": 87500, | |
| "train_speed(iter/s)": 1.023206 | |
| }, | |
| { | |
| "epoch": 0.7513532897320743, | |
| "grad_norm": 0.021992964670062065, | |
| "learning_rate": 1.5971877410650354e-05, | |
| "loss": 0.0031999170780181883, | |
| "memory(GiB)": 5.73, | |
| "step": 88000, | |
| "train_speed(iter/s)": 1.023363 | |
| }, | |
| { | |
| "epoch": 0.7556223425146429, | |
| "grad_norm": 0.022893013432621956, | |
| "learning_rate": 1.545809376986727e-05, | |
| "loss": 0.0031597645282745363, | |
| "memory(GiB)": 5.73, | |
| "step": 88500, | |
| "train_speed(iter/s)": 1.023915 | |
| }, | |
| { | |
| "epoch": 0.7598913952972115, | |
| "grad_norm": 0.021105078980326653, | |
| "learning_rate": 1.4951194459356693e-05, | |
| "loss": 0.003171279191970825, | |
| "memory(GiB)": 5.73, | |
| "step": 89000, | |
| "train_speed(iter/s)": 1.024754 | |
| }, | |
| { | |
| "epoch": 0.76416044807978, | |
| "grad_norm": 0.01919909007847309, | |
| "learning_rate": 1.445128050603493e-05, | |
| "loss": 0.0031237168312072752, | |
| "memory(GiB)": 5.73, | |
| "step": 89500, | |
| "train_speed(iter/s)": 1.026165 | |
| }, | |
| { | |
| "epoch": 0.7684295008623486, | |
| "grad_norm": 0.02016974799335003, | |
| "learning_rate": 1.39584515446106e-05, | |
| "loss": 0.003100724697113037, | |
| "memory(GiB)": 5.73, | |
| "step": 90000, | |
| "train_speed(iter/s)": 1.027578 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 117122, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.069758781932123e+19, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |