| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.30936605738740364, | |
| "eval_steps": 500, | |
| "global_step": 1500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014437082678078837, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0028874165356157673, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004331124803423651, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005774833071231535, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.007218541339039418, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.008662249606847302, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.010105957874655186, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.01154966614246307, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6000000000000006e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.012993374410270953, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.3e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.014437082678078837, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.015880790945886722, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.7e-05, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.017324499213694604, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.4e-05, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.01876820748150249, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.1e-05, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.02021191574931037, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.8e-05, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.021655624017118257, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999685283773504e-05, | |
| "loss": 0.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.02309933228492614, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.998187325055106e-05, | |
| "loss": 0.0, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.024543040552734024, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.995456138403733e-05, | |
| "loss": 0.0, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.025986748820541906, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991492397698826e-05, | |
| "loss": 0.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.02743045708834979, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.986297080934089e-05, | |
| "loss": 0.0, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.028874165356157673, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.979871469976196e-05, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.03031787362396556, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.972217150248503e-05, | |
| "loss": 0.0, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.031761581891773444, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.963336010339868e-05, | |
| "loss": 0.0, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.033205290159581326, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.953230241538674e-05, | |
| "loss": 0.0, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.03464899842738921, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.941902337292155e-05, | |
| "loss": 0.0, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.03609270669519709, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.92935509259118e-05, | |
| "loss": 0.0, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.03753641496300498, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.915591603280631e-05, | |
| "loss": 0.0, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.03898012323081286, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.900615265295552e-05, | |
| "loss": 0.0, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.04042383149862074, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.884429773823239e-05, | |
| "loss": 0.0, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.041867539766428624, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.867039122391527e-05, | |
| "loss": 0.0, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.04331124803423651, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.848447601883435e-05, | |
| "loss": 0.0, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.044754956302044395, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.828659799478456e-05, | |
| "loss": 0.0, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.04619866456985228, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.807680597520746e-05, | |
| "loss": 0.0, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.04764237283766016, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.785515172314463e-05, | |
| "loss": 0.0, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.04908608110546805, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.762168992846614e-05, | |
| "loss": 0.0, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.05052978937327593, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.737647819437645e-05, | |
| "loss": 0.0, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.05197349764108381, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.711957702320175e-05, | |
| "loss": 0.0, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.05341720590889169, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.685104980146193e-05, | |
| "loss": 0.0, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.05486091417669958, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.657096278423093e-05, | |
| "loss": 0.0, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.056304622444507464, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.627938507878917e-05, | |
| "loss": 0.0, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.057748330712315346, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.597638862757255e-05, | |
| "loss": 0.0, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.05919203898012323, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.566204819042152e-05, | |
| "loss": 0.0, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.06063574724793112, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.533644132613541e-05, | |
| "loss": 0.0, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.062079455515739, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.49996483733358e-05, | |
| "loss": 0.0, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.06352316378354689, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.465175243064428e-05, | |
| "loss": 0.0, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.06496687205135476, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.4292839336179e-05, | |
| "loss": 0.0, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.06641058031916265, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.39229976463755e-05, | |
| "loss": 0.0, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.06785428858697053, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.354231861413668e-05, | |
| "loss": 0.0, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 0.06929799685477842, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.315089616631752e-05, | |
| "loss": 0.0, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.0707417051225863, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.274882688055005e-05, | |
| "loss": 0.0, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 0.07218541339039418, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.233620996141421e-05, | |
| "loss": 0.0, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.07362912165820207, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.191314721596072e-05, | |
| "loss": 0.0, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 0.07507282992600996, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.147974302859157e-05, | |
| "loss": 0.0, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.07651653819381783, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.103610433530483e-05, | |
| "loss": 0.0, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 0.07796024646162572, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.058234059730976e-05, | |
| "loss": 0.0, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 0.0794039547294336, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.01185637740189e-05, | |
| "loss": 0.0, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.08084766299724148, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.964488829542377e-05, | |
| "loss": 0.0, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 0.08229137126504937, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.916143103386093e-05, | |
| "loss": 0.0, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 0.08373507953285725, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.866831127517557e-05, | |
| "loss": 0.0, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 0.08517878780066514, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.81656506892894e-05, | |
| "loss": 0.0, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 0.08662249606847303, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.765357330018056e-05, | |
| "loss": 0.0, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.0880662043362809, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.71322054552824e-05, | |
| "loss": 0.0, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 0.08950991260408879, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.660167579430927e-05, | |
| "loss": 0.0, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 0.09095362087189666, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.606211521751652e-05, | |
| "loss": 0.0, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 0.09239732913970455, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.551365685340285e-05, | |
| "loss": 0.0, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 0.09384103740751244, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.495643602586287e-05, | |
| "loss": 0.0, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.09528474567532032, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.439059022079789e-05, | |
| "loss": 0.0, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 0.0967284539431282, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.381625905219339e-05, | |
| "loss": 0.0, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 0.0981721622109361, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.32335842276713e-05, | |
| "loss": 0.0, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 0.09961587047874397, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.264270951352581e-05, | |
| "loss": 0.0, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 0.10105957874655186, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.20437806992512e-05, | |
| "loss": 0.0, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.10250328701435975, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.143694556157046e-05, | |
| "loss": 0.0, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 0.10394699528216762, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.082235382797349e-05, | |
| "loss": 0.0, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 0.10539070354997551, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.020015713977427e-05, | |
| "loss": 0.0, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 0.10683441181778339, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.957050901469545e-05, | |
| "loss": 0.0, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 0.10827812008559128, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.89335648089903e-05, | |
| "loss": 0.0, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.10972182835339916, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.828948167911074e-05, | |
| "loss": 0.0, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 0.11116553662120704, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.763841854293145e-05, | |
| "loss": 0.0, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 0.11260924488901493, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.698053604053922e-05, | |
| "loss": 0.0, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 0.11405295315682282, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.631599649459744e-05, | |
| "loss": 0.0, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 0.11549666142463069, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.564496387029532e-05, | |
| "loss": 0.0, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.11694036969243858, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.496760373489202e-05, | |
| "loss": 0.0, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 0.11838407796024646, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.428408321686541e-05, | |
| "loss": 0.0, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 0.11982778622805434, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.35945709646756e-05, | |
| "loss": 0.0, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 0.12127149449586223, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.289923710515339e-05, | |
| "loss": 0.0, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 0.12271520276367011, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.219825320152411e-05, | |
| "loss": 0.0, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.124158911031478, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.149179221107694e-05, | |
| "loss": 0.0, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 0.12560261929928587, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.078002844249032e-05, | |
| "loss": 0.0, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 0.12704632756709378, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.006313751282372e-05, | |
| "loss": 0.0, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 0.12849003583490165, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.934129630418701e-05, | |
| "loss": 0.0, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 0.12993374410270953, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.861468292009727e-05, | |
| "loss": 0.0, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.13137745237051743, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.788347664153447e-05, | |
| "loss": 0.0, | |
| "step": 637 | |
| }, | |
| { | |
| "epoch": 0.1328211606383253, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.714785788270658e-05, | |
| "loss": 0.0, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 0.13426486890613318, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.640800814653503e-05, | |
| "loss": 0.0, | |
| "step": 651 | |
| }, | |
| { | |
| "epoch": 0.13570857717394105, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.566410997987163e-05, | |
| "loss": 0.0, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 0.13715228544174896, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.49163469284578e-05, | |
| "loss": 0.0, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.13859599370955683, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.416490349163748e-05, | |
| "loss": 0.0, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 0.1400397019773647, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.340996507683458e-05, | |
| "loss": 0.0, | |
| "step": 679 | |
| }, | |
| { | |
| "epoch": 0.1414834102451726, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.265171795380659e-05, | |
| "loss": 0.0, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 0.14292711851298048, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.189034920868522e-05, | |
| "loss": 0.0, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 0.14437082678078836, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.112604669781572e-05, | |
| "loss": 0.0, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.14581453504859626, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.0358999001406156e-05, | |
| "loss": 0.0, | |
| "step": 707 | |
| }, | |
| { | |
| "epoch": 0.14725824331640414, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9589395376998e-05, | |
| "loss": 0.0, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 0.148701951584212, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.8817425712769794e-05, | |
| "loss": 0.0, | |
| "step": 721 | |
| }, | |
| { | |
| "epoch": 0.1501456598520199, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.804328048068492e-05, | |
| "loss": 0.0, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 0.1515893681198278, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.7267150689495644e-05, | |
| "loss": 0.0, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.15303307638763566, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.648922783761443e-05, | |
| "loss": 0.0, | |
| "step": 742 | |
| }, | |
| { | |
| "epoch": 0.15447678465544357, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.570970386586469e-05, | |
| "loss": 0.0, | |
| "step": 749 | |
| }, | |
| { | |
| "epoch": 0.15592049292325144, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.492877111012218e-05, | |
| "loss": 0.0, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 0.15736420119105932, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.414662225385903e-05, | |
| "loss": 0.0, | |
| "step": 763 | |
| }, | |
| { | |
| "epoch": 0.1588079094588672, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.336345028060199e-05, | |
| "loss": 0.0, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.1602516177266751, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.257944842631658e-05, | |
| "loss": 0.0, | |
| "step": 777 | |
| }, | |
| { | |
| "epoch": 0.16169532599448297, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.179481013172912e-05, | |
| "loss": 0.0, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 0.16313903426229084, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.100972899459796e-05, | |
| "loss": 0.0, | |
| "step": 791 | |
| }, | |
| { | |
| "epoch": 0.16458274253009875, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.022439872194629e-05, | |
| "loss": 0.0, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 0.16602645079790662, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.943901308226771e-05, | |
| "loss": 0.0, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.1674701590657145, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.865376585771687e-05, | |
| "loss": 0.0, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 0.1689138673335224, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7868850796296495e-05, | |
| "loss": 0.0, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 0.17035757560133027, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.708446156405307e-05, | |
| "loss": 0.0, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 0.17180128386913815, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.630079169729257e-05, | |
| "loss": 0.0, | |
| "step": 833 | |
| }, | |
| { | |
| "epoch": 0.17324499213694605, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.551803455482833e-05, | |
| "loss": 0.0, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.17468870040475393, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.473638327027259e-05, | |
| "loss": 0.0, | |
| "step": 847 | |
| }, | |
| { | |
| "epoch": 0.1761324086725618, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.395603070438373e-05, | |
| "loss": 0.0, | |
| "step": 854 | |
| }, | |
| { | |
| "epoch": 0.1775761169403697, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.31771693974807e-05, | |
| "loss": 0.0, | |
| "step": 861 | |
| }, | |
| { | |
| "epoch": 0.17901982520817758, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.239999152193664e-05, | |
| "loss": 0.0, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 0.18046353347598545, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.162468883476319e-05, | |
| "loss": 0.0, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.18190724174379333, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.085145263029726e-05, | |
| "loss": 0.0, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 0.18335095001160123, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.008047369300218e-05, | |
| "loss": 0.0, | |
| "step": 889 | |
| }, | |
| { | |
| "epoch": 0.1847946582794091, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9311942250394276e-05, | |
| "loss": 0.0, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 0.18623836654721698, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8546047926107256e-05, | |
| "loss": 0.0, | |
| "step": 903 | |
| }, | |
| { | |
| "epoch": 0.18768207481502489, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.778297969310529e-05, | |
| "loss": 0.0, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.18912578308283276, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7022925827056884e-05, | |
| "loss": 0.0, | |
| "step": 917 | |
| }, | |
| { | |
| "epoch": 0.19056949135064064, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.62660738598805e-05, | |
| "loss": 0.0, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 0.19201319961844854, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.551261053347404e-05, | |
| "loss": 0.0, | |
| "step": 931 | |
| }, | |
| { | |
| "epoch": 0.1934569078862564, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4762721753638995e-05, | |
| "loss": 0.0, | |
| "step": 938 | |
| }, | |
| { | |
| "epoch": 0.1949006161540643, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.401659254421094e-05, | |
| "loss": 0.0, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.1963443244218722, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3274407001407735e-05, | |
| "loss": 0.0, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 0.19778803268968007, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.2536348248406534e-05, | |
| "loss": 0.0, | |
| "step": 959 | |
| }, | |
| { | |
| "epoch": 0.19923174095748794, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1802598390160784e-05, | |
| "loss": 0.0, | |
| "step": 966 | |
| }, | |
| { | |
| "epoch": 0.20067544922529584, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.107333846846872e-05, | |
| "loss": 0.0, | |
| "step": 973 | |
| }, | |
| { | |
| "epoch": 0.20211915749310372, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0348748417303823e-05, | |
| "loss": 0.0, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.2035628657609116, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9629007018418985e-05, | |
| "loss": 0.0, | |
| "step": 987 | |
| }, | |
| { | |
| "epoch": 0.2050065740287195, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8914291857234636e-05, | |
| "loss": 0.0, | |
| "step": 994 | |
| }, | |
| { | |
| "epoch": 0.20645028229652737, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8204779279022276e-05, | |
| "loss": 0.0, | |
| "step": 1001 | |
| }, | |
| { | |
| "epoch": 0.20789399056433525, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7500644345393943e-05, | |
| "loss": 0.0, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 0.20933769883214312, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.68020607911083e-05, | |
| "loss": 0.0, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 0.21078140709995102, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.610920098120424e-05, | |
| "loss": 0.0, | |
| "step": 1022 | |
| }, | |
| { | |
| "epoch": 0.2122251153677589, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5422235868472345e-05, | |
| "loss": 0.0, | |
| "step": 1029 | |
| }, | |
| { | |
| "epoch": 0.21366882363556677, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4741334951274947e-05, | |
| "loss": 0.0, | |
| "step": 1036 | |
| }, | |
| { | |
| "epoch": 0.21511253190337468, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.40666662317248e-05, | |
| "loss": 0.0, | |
| "step": 1043 | |
| }, | |
| { | |
| "epoch": 0.21655624017118255, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3398396174233178e-05, | |
| "loss": 0.0, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.21799994843899043, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2736689664437217e-05, | |
| "loss": 0.0, | |
| "step": 1057 | |
| }, | |
| { | |
| "epoch": 0.21944365670679833, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2081709968516866e-05, | |
| "loss": 0.0, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 0.2208873649746062, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1433618692911467e-05, | |
| "loss": 0.0, | |
| "step": 1071 | |
| }, | |
| { | |
| "epoch": 0.22233107324241408, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0792575744445653e-05, | |
| "loss": 0.0, | |
| "step": 1078 | |
| }, | |
| { | |
| "epoch": 0.22377478151022198, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.015873929087482e-05, | |
| "loss": 0.0, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 0.22521848977802986, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.95322657218596e-05, | |
| "loss": 0.0, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 0.22666219804583773, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8913309610379015e-05, | |
| "loss": 0.0, | |
| "step": 1099 | |
| }, | |
| { | |
| "epoch": 0.22810590631364563, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8302023674591935e-05, | |
| "loss": 0.0, | |
| "step": 1106 | |
| }, | |
| { | |
| "epoch": 0.2295496145814535, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7698558740156135e-05, | |
| "loss": 0.0, | |
| "step": 1113 | |
| }, | |
| { | |
| "epoch": 0.23099332284926138, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7103063703014372e-05, | |
| "loss": 0.0, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.23243703111706926, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6515685492656467e-05, | |
| "loss": 0.0, | |
| "step": 1127 | |
| }, | |
| { | |
| "epoch": 0.23388073938487716, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.59365690358667e-05, | |
| "loss": 0.0, | |
| "step": 1134 | |
| }, | |
| { | |
| "epoch": 0.23532444765268504, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5365857220965275e-05, | |
| "loss": 0.0, | |
| "step": 1141 | |
| }, | |
| { | |
| "epoch": 0.2367681559204929, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4803690862552755e-05, | |
| "loss": 0.0, | |
| "step": 1148 | |
| }, | |
| { | |
| "epoch": 0.23821186418830081, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4250208666766235e-05, | |
| "loss": 0.0, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 0.2396555724561087, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3705547197055584e-05, | |
| "loss": 0.0, | |
| "step": 1162 | |
| }, | |
| { | |
| "epoch": 0.24109928072391656, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3169840840488501e-05, | |
| "loss": 0.0, | |
| "step": 1169 | |
| }, | |
| { | |
| "epoch": 0.24254298899172447, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2643221774592518e-05, | |
| "loss": 0.0, | |
| "step": 1176 | |
| }, | |
| { | |
| "epoch": 0.24398669725953234, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2125819934742188e-05, | |
| "loss": 0.0, | |
| "step": 1183 | |
| }, | |
| { | |
| "epoch": 0.24543040552734022, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1617762982099446e-05, | |
| "loss": 0.0, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.24687411379514812, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1119176272115128e-05, | |
| "loss": 0.0, | |
| "step": 1197 | |
| }, | |
| { | |
| "epoch": 0.248317822062956, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0630182823599399e-05, | |
| "loss": 0.0, | |
| "step": 1204 | |
| }, | |
| { | |
| "epoch": 0.24976153033076387, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0150903288368741e-05, | |
| "loss": 0.0, | |
| "step": 1211 | |
| }, | |
| { | |
| "epoch": 0.25120523859857175, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.681455921476839e-06, | |
| "loss": 0.0, | |
| "step": 1218 | |
| }, | |
| { | |
| "epoch": 0.2526489468663796, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.221956552036992e-06, | |
| "loss": 0.0, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.25409265513418755, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.772518554642973e-06, | |
| "loss": 0.0, | |
| "step": 1232 | |
| }, | |
| { | |
| "epoch": 0.2555363634019954, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.333252821395526e-06, | |
| "loss": 0.0, | |
| "step": 1239 | |
| }, | |
| { | |
| "epoch": 0.2569800716698033, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.904267734541498e-06, | |
| "loss": 0.0, | |
| "step": 1246 | |
| }, | |
| { | |
| "epoch": 0.2584237799376112, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.485669139732004e-06, | |
| "loss": 0.0, | |
| "step": 1253 | |
| }, | |
| { | |
| "epoch": 0.25986748820541905, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.077560319906695e-06, | |
| "loss": 0.0, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.2613111964732269, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.680041969810203e-06, | |
| "loss": 0.0, | |
| "step": 1267 | |
| }, | |
| { | |
| "epoch": 0.26275490474103486, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.293212171147206e-06, | |
| "loss": 0.0, | |
| "step": 1274 | |
| }, | |
| { | |
| "epoch": 0.26419861300884273, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.917166368382277e-06, | |
| "loss": 0.0, | |
| "step": 1281 | |
| }, | |
| { | |
| "epoch": 0.2656423212766506, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.5519973451903405e-06, | |
| "loss": 0.0, | |
| "step": 1288 | |
| }, | |
| { | |
| "epoch": 0.2670860295444585, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.197795201563743e-06, | |
| "loss": 0.0, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 0.26852973781226636, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8546473315813856e-06, | |
| "loss": 0.0, | |
| "step": 1302 | |
| }, | |
| { | |
| "epoch": 0.26997344608007423, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.522638401845547e-06, | |
| "loss": 0.0, | |
| "step": 1309 | |
| }, | |
| { | |
| "epoch": 0.2714171543478821, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2018503305916775e-06, | |
| "loss": 0.0, | |
| "step": 1316 | |
| }, | |
| { | |
| "epoch": 0.27286086261569004, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.892362267476313e-06, | |
| "loss": 0.0, | |
| "step": 1323 | |
| }, | |
| { | |
| "epoch": 0.2743045708834979, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5942505740480582e-06, | |
| "loss": 0.0, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.2757482791513058, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3075888049065196e-06, | |
| "loss": 0.0, | |
| "step": 1337 | |
| }, | |
| { | |
| "epoch": 0.27719198741911366, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.03244768955383e-06, | |
| "loss": 0.0, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 0.27863569568692154, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7688951149431595e-06, | |
| "loss": 0.0, | |
| "step": 1351 | |
| }, | |
| { | |
| "epoch": 0.2800794039547294, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5169961087286974e-06, | |
| "loss": 0.0, | |
| "step": 1358 | |
| }, | |
| { | |
| "epoch": 0.28152311222253734, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.276812823220964e-06, | |
| "loss": 0.0, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 0.2829668204903452, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.048404520051722e-06, | |
| "loss": 0.0, | |
| "step": 1372 | |
| }, | |
| { | |
| "epoch": 0.2844105287581531, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8318275555520237e-06, | |
| "loss": 0.0, | |
| "step": 1379 | |
| }, | |
| { | |
| "epoch": 0.28585423702596097, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6271353668471655e-06, | |
| "loss": 0.0, | |
| "step": 1386 | |
| }, | |
| { | |
| "epoch": 0.28729794529376884, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4343784586718311e-06, | |
| "loss": 0.0, | |
| "step": 1393 | |
| }, | |
| { | |
| "epoch": 0.2887416535615767, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2536043909088191e-06, | |
| "loss": 0.0, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.29018536182938465, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0848577668543802e-06, | |
| "loss": 0.0, | |
| "step": 1407 | |
| }, | |
| { | |
| "epoch": 0.2916290700971925, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.281802222129765e-07, | |
| "loss": 0.0, | |
| "step": 1414 | |
| }, | |
| { | |
| "epoch": 0.2930727783650004, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.836104148243484e-07, | |
| "loss": 0.0, | |
| "step": 1421 | |
| }, | |
| { | |
| "epoch": 0.29451648663280827, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.511840151252169e-07, | |
| "loss": 0.0, | |
| "step": 1428 | |
| }, | |
| { | |
| "epoch": 0.29596019490061615, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.309336973481683e-07, | |
| "loss": 0.0, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 0.297403903168424, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.228891314597694e-07, | |
| "loss": 0.0, | |
| "step": 1442 | |
| }, | |
| { | |
| "epoch": 0.2988476114362319, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.2707697583995167e-07, | |
| "loss": 0.0, | |
| "step": 1449 | |
| }, | |
| { | |
| "epoch": 0.3002913197040398, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4352087070443895e-07, | |
| "loss": 0.0, | |
| "step": 1456 | |
| }, | |
| { | |
| "epoch": 0.3017350279718477, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7224143227190236e-07, | |
| "loss": 0.0, | |
| "step": 1463 | |
| }, | |
| { | |
| "epoch": 0.3031787362396556, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.132562476771959e-07, | |
| "loss": 0.0, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.30462244450746345, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.657987063200533e-08, | |
| "loss": 0.0, | |
| "step": 1477 | |
| }, | |
| { | |
| "epoch": 0.3060661527752713, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.2223817833931805e-08, | |
| "loss": 0.0, | |
| "step": 1484 | |
| }, | |
| { | |
| "epoch": 0.3075098610430792, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.019656612492592e-08, | |
| "loss": 0.0, | |
| "step": 1491 | |
| }, | |
| { | |
| "epoch": 0.30895356931088713, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.035503997385949e-10, | |
| "loss": 0.0, | |
| "step": 1498 | |
| } | |
| ], | |
| "logging_steps": 7, | |
| "max_steps": 1500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 5.5368921120768e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |