| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 25.0, | |
| "eval_steps": 500, | |
| "global_step": 1725, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5.780346820809248e-07, | |
| "loss": 0.005, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 5.202312138728324e-06, | |
| "loss": 0.0008, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.0404624277456647e-05, | |
| "loss": 0.0019, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.5606936416184973e-05, | |
| "loss": 0.0019, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.0809248554913295e-05, | |
| "loss": 0.0016, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 2.6011560693641617e-05, | |
| "loss": 0.0027, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 3.1213872832369946e-05, | |
| "loss": 0.0032, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.6416184971098265e-05, | |
| "loss": 0.0013, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.002811400219798088, | |
| "eval_max_distance": 2, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 1.9415, | |
| "eval_samples_per_second": 42.235, | |
| "eval_steps_per_second": 1.545, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 4.161849710982659e-05, | |
| "loss": 0.0033, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 4.6820809248554915e-05, | |
| "loss": 0.0034, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 5.2023121387283234e-05, | |
| "loss": 0.0015, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 5.722543352601156e-05, | |
| "loss": 0.0042, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 6.242774566473989e-05, | |
| "loss": 0.0025, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 6.763005780346822e-05, | |
| "loss": 0.0012, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 7.283236994219653e-05, | |
| "loss": 0.002, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 7.803468208092485e-05, | |
| "loss": 0.0006, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.0026117784436792135, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 1.9167, | |
| "eval_samples_per_second": 42.781, | |
| "eval_steps_per_second": 1.565, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 8.323699421965318e-05, | |
| "loss": 0.001, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 8.84393063583815e-05, | |
| "loss": 0.0016, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 9.364161849710983e-05, | |
| "loss": 0.0011, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 9.884393063583816e-05, | |
| "loss": 0.001, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 9.954896907216495e-05, | |
| "loss": 0.0026, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 9.896907216494846e-05, | |
| "loss": 0.0008, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 9.838917525773196e-05, | |
| "loss": 0.0022, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 9.780927835051546e-05, | |
| "loss": 0.0025, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.003930480219423771, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 1.9341, | |
| "eval_samples_per_second": 42.396, | |
| "eval_steps_per_second": 1.551, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 9.722938144329897e-05, | |
| "loss": 0.0019, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 9.664948453608248e-05, | |
| "loss": 0.0024, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 9.606958762886598e-05, | |
| "loss": 0.0007, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 9.54896907216495e-05, | |
| "loss": 0.0026, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 9.490979381443299e-05, | |
| "loss": 0.0009, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 9.43298969072165e-05, | |
| "loss": 0.0012, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 9.375e-05, | |
| "loss": 0.0004, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.0036886015441268682, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 1.9271, | |
| "eval_samples_per_second": 42.551, | |
| "eval_steps_per_second": 1.557, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 9.317010309278351e-05, | |
| "loss": 0.0018, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 9.259020618556701e-05, | |
| "loss": 0.0017, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 9.201030927835051e-05, | |
| "loss": 0.0014, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 9.143041237113402e-05, | |
| "loss": 0.0005, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 9.085051546391753e-05, | |
| "loss": 0.001, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 9.027061855670103e-05, | |
| "loss": 0.002, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 8.969072164948454e-05, | |
| "loss": 0.0016, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 8.911082474226806e-05, | |
| "loss": 0.0005, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.009117466397583485, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 1.9694, | |
| "eval_samples_per_second": 41.638, | |
| "eval_steps_per_second": 1.523, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 8.853092783505154e-05, | |
| "loss": 0.0005, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 8.795103092783505e-05, | |
| "loss": 0.0051, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "learning_rate": 8.737113402061856e-05, | |
| "loss": 0.0004, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 8.679123711340206e-05, | |
| "loss": 0.0012, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 8.621134020618558e-05, | |
| "loss": 0.001, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 5.74, | |
| "learning_rate": 8.563144329896907e-05, | |
| "loss": 0.0015, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 5.87, | |
| "learning_rate": 8.505154639175259e-05, | |
| "loss": 0.0016, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 8.447164948453608e-05, | |
| "loss": 0.0009, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.0005720060435123742, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 1.9399, | |
| "eval_samples_per_second": 42.271, | |
| "eval_steps_per_second": 1.546, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "learning_rate": 8.38917525773196e-05, | |
| "loss": 0.0005, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 6.26, | |
| "learning_rate": 8.331185567010311e-05, | |
| "loss": 0.0006, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 8.273195876288659e-05, | |
| "loss": 0.0014, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "learning_rate": 8.21520618556701e-05, | |
| "loss": 0.0019, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 6.65, | |
| "learning_rate": 8.157216494845362e-05, | |
| "loss": 0.001, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 6.78, | |
| "learning_rate": 8.099226804123711e-05, | |
| "loss": 0.0008, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "learning_rate": 8.041237113402063e-05, | |
| "loss": 0.0016, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.00027213190332986414, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 1.9188, | |
| "eval_samples_per_second": 42.735, | |
| "eval_steps_per_second": 1.563, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 7.983247422680414e-05, | |
| "loss": 0.0006, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 7.17, | |
| "learning_rate": 7.925257731958762e-05, | |
| "loss": 0.007, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "learning_rate": 7.867268041237113e-05, | |
| "loss": 0.0004, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 7.43, | |
| "learning_rate": 7.809278350515465e-05, | |
| "loss": 0.0016, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "learning_rate": 7.751288659793814e-05, | |
| "loss": 0.0006, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 7.7, | |
| "learning_rate": 7.693298969072166e-05, | |
| "loss": 0.0011, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 7.83, | |
| "learning_rate": 7.635309278350515e-05, | |
| "loss": 0.0014, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 7.577319587628867e-05, | |
| "loss": 0.0012, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.011139851063489914, | |
| "eval_max_distance": 5, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 1.9435, | |
| "eval_samples_per_second": 42.193, | |
| "eval_steps_per_second": 1.544, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 8.09, | |
| "learning_rate": 7.519329896907217e-05, | |
| "loss": 0.0008, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "learning_rate": 7.461340206185568e-05, | |
| "loss": 0.0011, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 8.35, | |
| "learning_rate": 7.403350515463919e-05, | |
| "loss": 0.0025, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "learning_rate": 7.345360824742269e-05, | |
| "loss": 0.003, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 8.61, | |
| "learning_rate": 7.287371134020619e-05, | |
| "loss": 0.004, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 8.74, | |
| "learning_rate": 7.22938144329897e-05, | |
| "loss": 0.002, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 8.87, | |
| "learning_rate": 7.17139175257732e-05, | |
| "loss": 0.0007, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 7.113402061855671e-05, | |
| "loss": 0.0008, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.0003953798732254654, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 1.995, | |
| "eval_samples_per_second": 41.102, | |
| "eval_steps_per_second": 1.504, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "learning_rate": 7.055412371134022e-05, | |
| "loss": 0.0005, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 9.26, | |
| "learning_rate": 6.99742268041237e-05, | |
| "loss": 0.0004, | |
| "step": 639 | |
| }, | |
| { | |
| "epoch": 9.39, | |
| "learning_rate": 6.939432989690722e-05, | |
| "loss": 0.0013, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "learning_rate": 6.881443298969073e-05, | |
| "loss": 0.0002, | |
| "step": 657 | |
| }, | |
| { | |
| "epoch": 9.65, | |
| "learning_rate": 6.823453608247423e-05, | |
| "loss": 0.0011, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "learning_rate": 6.765463917525774e-05, | |
| "loss": 0.0018, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "learning_rate": 6.707474226804124e-05, | |
| "loss": 0.0018, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.00027754431357607245, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 1.9222, | |
| "eval_samples_per_second": 42.659, | |
| "eval_steps_per_second": 1.561, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 10.04, | |
| "learning_rate": 6.649484536082475e-05, | |
| "loss": 0.0011, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 10.17, | |
| "learning_rate": 6.591494845360825e-05, | |
| "loss": 0.0006, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 10.3, | |
| "learning_rate": 6.533505154639176e-05, | |
| "loss": 0.0011, | |
| "step": 711 | |
| }, | |
| { | |
| "epoch": 10.43, | |
| "learning_rate": 6.475515463917527e-05, | |
| "loss": 0.0013, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 10.57, | |
| "learning_rate": 6.417525773195877e-05, | |
| "loss": 0.0006, | |
| "step": 729 | |
| }, | |
| { | |
| "epoch": 10.7, | |
| "learning_rate": 6.359536082474227e-05, | |
| "loss": 0.0018, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 10.83, | |
| "learning_rate": 6.301546391752578e-05, | |
| "loss": 0.0016, | |
| "step": 747 | |
| }, | |
| { | |
| "epoch": 10.96, | |
| "learning_rate": 6.243556701030928e-05, | |
| "loss": 0.0028, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.00033258015173487365, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 1.9385, | |
| "eval_samples_per_second": 42.301, | |
| "eval_steps_per_second": 1.548, | |
| "step": 759 | |
| }, | |
| { | |
| "epoch": 11.09, | |
| "learning_rate": 6.185567010309279e-05, | |
| "loss": 0.0009, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "learning_rate": 6.12757731958763e-05, | |
| "loss": 0.0005, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 11.35, | |
| "learning_rate": 6.069587628865979e-05, | |
| "loss": 0.0011, | |
| "step": 783 | |
| }, | |
| { | |
| "epoch": 11.48, | |
| "learning_rate": 6.01159793814433e-05, | |
| "loss": 0.0007, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 11.61, | |
| "learning_rate": 5.953608247422681e-05, | |
| "loss": 0.0012, | |
| "step": 801 | |
| }, | |
| { | |
| "epoch": 11.74, | |
| "learning_rate": 5.8956185567010315e-05, | |
| "loss": 0.0021, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 11.87, | |
| "learning_rate": 5.837628865979382e-05, | |
| "loss": 0.0006, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 5.779639175257732e-05, | |
| "loss": 0.0008, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.0002690624096430838, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 1.9448, | |
| "eval_samples_per_second": 42.163, | |
| "eval_steps_per_second": 1.543, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 12.13, | |
| "learning_rate": 5.721649484536082e-05, | |
| "loss": 0.001, | |
| "step": 837 | |
| }, | |
| { | |
| "epoch": 12.26, | |
| "learning_rate": 5.663659793814433e-05, | |
| "loss": 0.0012, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 12.39, | |
| "learning_rate": 5.605670103092784e-05, | |
| "loss": 0.0005, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 12.52, | |
| "learning_rate": 5.5476804123711345e-05, | |
| "loss": 0.0011, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 12.65, | |
| "learning_rate": 5.489690721649485e-05, | |
| "loss": 0.0026, | |
| "step": 873 | |
| }, | |
| { | |
| "epoch": 12.78, | |
| "learning_rate": 5.431701030927835e-05, | |
| "loss": 0.0009, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 12.91, | |
| "learning_rate": 5.3737113402061854e-05, | |
| "loss": 0.001, | |
| "step": 891 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.0004277784610167146, | |
| "eval_max_distance": 2, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 1.9315, | |
| "eval_samples_per_second": 42.454, | |
| "eval_steps_per_second": 1.553, | |
| "step": 897 | |
| }, | |
| { | |
| "epoch": 13.04, | |
| "learning_rate": 5.3157216494845366e-05, | |
| "loss": 0.0007, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 13.17, | |
| "learning_rate": 5.257731958762887e-05, | |
| "loss": 0.0008, | |
| "step": 909 | |
| }, | |
| { | |
| "epoch": 13.3, | |
| "learning_rate": 5.1997422680412376e-05, | |
| "loss": 0.0005, | |
| "step": 918 | |
| }, | |
| { | |
| "epoch": 13.43, | |
| "learning_rate": 5.1417525773195874e-05, | |
| "loss": 0.0004, | |
| "step": 927 | |
| }, | |
| { | |
| "epoch": 13.57, | |
| "learning_rate": 5.083762886597938e-05, | |
| "loss": 0.0006, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 13.7, | |
| "learning_rate": 5.025773195876289e-05, | |
| "loss": 0.0025, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 13.83, | |
| "learning_rate": 4.9677835051546396e-05, | |
| "loss": 0.0009, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 13.96, | |
| "learning_rate": 4.9097938144329895e-05, | |
| "loss": 0.0026, | |
| "step": 963 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.0005385838449001312, | |
| "eval_max_distance": 2, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 1.993, | |
| "eval_samples_per_second": 41.144, | |
| "eval_steps_per_second": 1.505, | |
| "step": 966 | |
| }, | |
| { | |
| "epoch": 14.09, | |
| "learning_rate": 4.8518041237113407e-05, | |
| "loss": 0.0016, | |
| "step": 972 | |
| }, | |
| { | |
| "epoch": 14.22, | |
| "learning_rate": 4.793814432989691e-05, | |
| "loss": 0.0014, | |
| "step": 981 | |
| }, | |
| { | |
| "epoch": 14.35, | |
| "learning_rate": 4.735824742268041e-05, | |
| "loss": 0.0007, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 14.48, | |
| "learning_rate": 4.677835051546392e-05, | |
| "loss": 0.0031, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 14.61, | |
| "learning_rate": 4.619845360824743e-05, | |
| "loss": 0.0008, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 14.74, | |
| "learning_rate": 4.561855670103093e-05, | |
| "loss": 0.0028, | |
| "step": 1017 | |
| }, | |
| { | |
| "epoch": 14.87, | |
| "learning_rate": 4.503865979381444e-05, | |
| "loss": 0.0004, | |
| "step": 1026 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 4.4458762886597936e-05, | |
| "loss": 0.0015, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.0007138837827369571, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 1.9688, | |
| "eval_samples_per_second": 41.651, | |
| "eval_steps_per_second": 1.524, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 15.13, | |
| "learning_rate": 4.387886597938145e-05, | |
| "loss": 0.0005, | |
| "step": 1044 | |
| }, | |
| { | |
| "epoch": 15.26, | |
| "learning_rate": 4.329896907216495e-05, | |
| "loss": 0.0011, | |
| "step": 1053 | |
| }, | |
| { | |
| "epoch": 15.39, | |
| "learning_rate": 4.271907216494845e-05, | |
| "loss": 0.0001, | |
| "step": 1062 | |
| }, | |
| { | |
| "epoch": 15.52, | |
| "learning_rate": 4.213917525773196e-05, | |
| "loss": 0.0009, | |
| "step": 1071 | |
| }, | |
| { | |
| "epoch": 15.65, | |
| "learning_rate": 4.155927835051547e-05, | |
| "loss": 0.0017, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 15.78, | |
| "learning_rate": 4.097938144329897e-05, | |
| "loss": 0.0013, | |
| "step": 1089 | |
| }, | |
| { | |
| "epoch": 15.91, | |
| "learning_rate": 4.039948453608248e-05, | |
| "loss": 0.0009, | |
| "step": 1098 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.0006717974320054054, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 1.9244, | |
| "eval_samples_per_second": 42.612, | |
| "eval_steps_per_second": 1.559, | |
| "step": 1104 | |
| }, | |
| { | |
| "epoch": 16.04, | |
| "learning_rate": 3.9819587628865976e-05, | |
| "loss": 0.0015, | |
| "step": 1107 | |
| }, | |
| { | |
| "epoch": 16.17, | |
| "learning_rate": 3.923969072164949e-05, | |
| "loss": 0.0003, | |
| "step": 1116 | |
| }, | |
| { | |
| "epoch": 16.3, | |
| "learning_rate": 3.865979381443299e-05, | |
| "loss": 0.0006, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 16.43, | |
| "learning_rate": 3.807989690721649e-05, | |
| "loss": 0.0013, | |
| "step": 1134 | |
| }, | |
| { | |
| "epoch": 16.57, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.0009, | |
| "step": 1143 | |
| }, | |
| { | |
| "epoch": 16.7, | |
| "learning_rate": 3.692010309278351e-05, | |
| "loss": 0.0004, | |
| "step": 1152 | |
| }, | |
| { | |
| "epoch": 16.83, | |
| "learning_rate": 3.6340206185567014e-05, | |
| "loss": 0.0008, | |
| "step": 1161 | |
| }, | |
| { | |
| "epoch": 16.96, | |
| "learning_rate": 3.576030927835052e-05, | |
| "loss": 0.0014, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 0.00033988503855653107, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 1.9136, | |
| "eval_samples_per_second": 42.851, | |
| "eval_steps_per_second": 1.568, | |
| "step": 1173 | |
| }, | |
| { | |
| "epoch": 17.09, | |
| "learning_rate": 3.5180412371134024e-05, | |
| "loss": 0.0016, | |
| "step": 1179 | |
| }, | |
| { | |
| "epoch": 17.22, | |
| "learning_rate": 3.460051546391753e-05, | |
| "loss": 0.0004, | |
| "step": 1188 | |
| }, | |
| { | |
| "epoch": 17.35, | |
| "learning_rate": 3.4020618556701034e-05, | |
| "loss": 0.002, | |
| "step": 1197 | |
| }, | |
| { | |
| "epoch": 17.48, | |
| "learning_rate": 3.344072164948453e-05, | |
| "loss": 0.0012, | |
| "step": 1206 | |
| }, | |
| { | |
| "epoch": 17.61, | |
| "learning_rate": 3.2860824742268044e-05, | |
| "loss": 0.0002, | |
| "step": 1215 | |
| }, | |
| { | |
| "epoch": 17.74, | |
| "learning_rate": 3.228092783505155e-05, | |
| "loss": 0.0006, | |
| "step": 1224 | |
| }, | |
| { | |
| "epoch": 17.87, | |
| "learning_rate": 3.1701030927835054e-05, | |
| "loss": 0.0044, | |
| "step": 1233 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 3.112113402061856e-05, | |
| "loss": 0.001, | |
| "step": 1242 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 0.00037691937177442014, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 1.9496, | |
| "eval_samples_per_second": 42.059, | |
| "eval_steps_per_second": 1.539, | |
| "step": 1242 | |
| }, | |
| { | |
| "epoch": 18.13, | |
| "learning_rate": 3.0541237113402065e-05, | |
| "loss": 0.0005, | |
| "step": 1251 | |
| }, | |
| { | |
| "epoch": 18.26, | |
| "learning_rate": 2.9961340206185566e-05, | |
| "loss": 0.0009, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 18.39, | |
| "learning_rate": 2.9381443298969075e-05, | |
| "loss": 0.0008, | |
| "step": 1269 | |
| }, | |
| { | |
| "epoch": 18.52, | |
| "learning_rate": 2.8801546391752577e-05, | |
| "loss": 0.0007, | |
| "step": 1278 | |
| }, | |
| { | |
| "epoch": 18.65, | |
| "learning_rate": 2.8221649484536085e-05, | |
| "loss": 0.0016, | |
| "step": 1287 | |
| }, | |
| { | |
| "epoch": 18.78, | |
| "learning_rate": 2.764175257731959e-05, | |
| "loss": 0.0012, | |
| "step": 1296 | |
| }, | |
| { | |
| "epoch": 18.91, | |
| "learning_rate": 2.7061855670103092e-05, | |
| "loss": 0.0007, | |
| "step": 1305 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 0.001327142701484263, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 1.9144, | |
| "eval_samples_per_second": 42.834, | |
| "eval_steps_per_second": 1.567, | |
| "step": 1311 | |
| }, | |
| { | |
| "epoch": 19.04, | |
| "learning_rate": 2.64819587628866e-05, | |
| "loss": 0.0005, | |
| "step": 1314 | |
| }, | |
| { | |
| "epoch": 19.17, | |
| "learning_rate": 2.5902061855670106e-05, | |
| "loss": 0.0011, | |
| "step": 1323 | |
| }, | |
| { | |
| "epoch": 19.3, | |
| "learning_rate": 2.5322164948453607e-05, | |
| "loss": 0.0006, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 19.43, | |
| "learning_rate": 2.4742268041237116e-05, | |
| "loss": 0.0004, | |
| "step": 1341 | |
| }, | |
| { | |
| "epoch": 19.57, | |
| "learning_rate": 2.416237113402062e-05, | |
| "loss": 0.002, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 19.7, | |
| "learning_rate": 2.3582474226804126e-05, | |
| "loss": 0.0003, | |
| "step": 1359 | |
| }, | |
| { | |
| "epoch": 19.83, | |
| "learning_rate": 2.3002577319587628e-05, | |
| "loss": 0.0011, | |
| "step": 1368 | |
| }, | |
| { | |
| "epoch": 19.96, | |
| "learning_rate": 2.2422680412371136e-05, | |
| "loss": 0.0013, | |
| "step": 1377 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.0012958323350176215, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 1.9255, | |
| "eval_samples_per_second": 42.587, | |
| "eval_steps_per_second": 1.558, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 20.09, | |
| "learning_rate": 2.184278350515464e-05, | |
| "loss": 0.0017, | |
| "step": 1386 | |
| }, | |
| { | |
| "epoch": 20.22, | |
| "learning_rate": 2.1262886597938146e-05, | |
| "loss": 0.0011, | |
| "step": 1395 | |
| }, | |
| { | |
| "epoch": 20.35, | |
| "learning_rate": 2.0682989690721648e-05, | |
| "loss": 0.0014, | |
| "step": 1404 | |
| }, | |
| { | |
| "epoch": 20.48, | |
| "learning_rate": 2.0103092783505157e-05, | |
| "loss": 0.0006, | |
| "step": 1413 | |
| }, | |
| { | |
| "epoch": 20.61, | |
| "learning_rate": 1.952319587628866e-05, | |
| "loss": 0.0003, | |
| "step": 1422 | |
| }, | |
| { | |
| "epoch": 20.74, | |
| "learning_rate": 1.8943298969072167e-05, | |
| "loss": 0.0002, | |
| "step": 1431 | |
| }, | |
| { | |
| "epoch": 20.87, | |
| "learning_rate": 1.8363402061855672e-05, | |
| "loss": 0.0024, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 1.7783505154639177e-05, | |
| "loss": 0.0007, | |
| "step": 1449 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 0.0002567500632721931, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 1.9342, | |
| "eval_samples_per_second": 42.395, | |
| "eval_steps_per_second": 1.551, | |
| "step": 1449 | |
| }, | |
| { | |
| "epoch": 21.13, | |
| "learning_rate": 1.7203608247422682e-05, | |
| "loss": 0.0006, | |
| "step": 1458 | |
| }, | |
| { | |
| "epoch": 21.26, | |
| "learning_rate": 1.6623711340206187e-05, | |
| "loss": 0.002, | |
| "step": 1467 | |
| }, | |
| { | |
| "epoch": 21.39, | |
| "learning_rate": 1.6043814432989692e-05, | |
| "loss": 0.0007, | |
| "step": 1476 | |
| }, | |
| { | |
| "epoch": 21.52, | |
| "learning_rate": 1.5463917525773197e-05, | |
| "loss": 0.0007, | |
| "step": 1485 | |
| }, | |
| { | |
| "epoch": 21.65, | |
| "learning_rate": 1.4884020618556702e-05, | |
| "loss": 0.0016, | |
| "step": 1494 | |
| }, | |
| { | |
| "epoch": 21.78, | |
| "learning_rate": 1.4304123711340206e-05, | |
| "loss": 0.0008, | |
| "step": 1503 | |
| }, | |
| { | |
| "epoch": 21.91, | |
| "learning_rate": 1.3724226804123713e-05, | |
| "loss": 0.0016, | |
| "step": 1512 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 0.0002821955131366849, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 1.9113, | |
| "eval_samples_per_second": 42.902, | |
| "eval_steps_per_second": 1.57, | |
| "step": 1518 | |
| }, | |
| { | |
| "epoch": 22.04, | |
| "learning_rate": 1.3144329896907218e-05, | |
| "loss": 0.0018, | |
| "step": 1521 | |
| }, | |
| { | |
| "epoch": 22.17, | |
| "learning_rate": 1.2564432989690723e-05, | |
| "loss": 0.0027, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 22.3, | |
| "learning_rate": 1.1984536082474228e-05, | |
| "loss": 0.0002, | |
| "step": 1539 | |
| }, | |
| { | |
| "epoch": 22.43, | |
| "learning_rate": 1.1404639175257733e-05, | |
| "loss": 0.001, | |
| "step": 1548 | |
| }, | |
| { | |
| "epoch": 22.57, | |
| "learning_rate": 1.0824742268041238e-05, | |
| "loss": 0.0007, | |
| "step": 1557 | |
| }, | |
| { | |
| "epoch": 22.7, | |
| "learning_rate": 1.0244845360824743e-05, | |
| "loss": 0.0009, | |
| "step": 1566 | |
| }, | |
| { | |
| "epoch": 22.83, | |
| "learning_rate": 9.664948453608248e-06, | |
| "loss": 0.0012, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 22.96, | |
| "learning_rate": 9.085051546391753e-06, | |
| "loss": 0.0013, | |
| "step": 1584 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 0.00030223012436181307, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 1.9675, | |
| "eval_samples_per_second": 41.677, | |
| "eval_steps_per_second": 1.525, | |
| "step": 1587 | |
| }, | |
| { | |
| "epoch": 23.09, | |
| "learning_rate": 8.505154639175259e-06, | |
| "loss": 0.0025, | |
| "step": 1593 | |
| }, | |
| { | |
| "epoch": 23.22, | |
| "learning_rate": 7.925257731958764e-06, | |
| "loss": 0.001, | |
| "step": 1602 | |
| }, | |
| { | |
| "epoch": 23.35, | |
| "learning_rate": 7.345360824742269e-06, | |
| "loss": 0.0004, | |
| "step": 1611 | |
| }, | |
| { | |
| "epoch": 23.48, | |
| "learning_rate": 6.765463917525773e-06, | |
| "loss": 0.0006, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 23.61, | |
| "learning_rate": 6.185567010309279e-06, | |
| "loss": 0.001, | |
| "step": 1629 | |
| }, | |
| { | |
| "epoch": 23.74, | |
| "learning_rate": 5.605670103092784e-06, | |
| "loss": 0.0012, | |
| "step": 1638 | |
| }, | |
| { | |
| "epoch": 23.87, | |
| "learning_rate": 5.025773195876289e-06, | |
| "loss": 0.0013, | |
| "step": 1647 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 4.445876288659794e-06, | |
| "loss": 0.0004, | |
| "step": 1656 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 0.0002631743554957211, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 1.9278, | |
| "eval_samples_per_second": 42.536, | |
| "eval_steps_per_second": 1.556, | |
| "step": 1656 | |
| }, | |
| { | |
| "epoch": 24.13, | |
| "learning_rate": 3.865979381443299e-06, | |
| "loss": 0.0018, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 24.26, | |
| "learning_rate": 3.2860824742268044e-06, | |
| "loss": 0.0006, | |
| "step": 1674 | |
| }, | |
| { | |
| "epoch": 24.39, | |
| "learning_rate": 2.7061855670103095e-06, | |
| "loss": 0.0012, | |
| "step": 1683 | |
| }, | |
| { | |
| "epoch": 24.52, | |
| "learning_rate": 2.1262886597938146e-06, | |
| "loss": 0.0009, | |
| "step": 1692 | |
| }, | |
| { | |
| "epoch": 24.65, | |
| "learning_rate": 1.5463917525773197e-06, | |
| "loss": 0.0007, | |
| "step": 1701 | |
| }, | |
| { | |
| "epoch": 24.78, | |
| "learning_rate": 9.664948453608248e-07, | |
| "loss": 0.0009, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 24.91, | |
| "learning_rate": 3.8659793814432993e-07, | |
| "loss": 0.001, | |
| "step": 1719 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 0.0002593309909570962, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.0449, | |
| "eval_samples_per_second": 40.1, | |
| "eval_steps_per_second": 1.467, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "step": 1725, | |
| "total_flos": 459342194208768.0, | |
| "train_loss": 0.0013090899151048043, | |
| "train_runtime": 199.817, | |
| "train_samples_per_second": 256.61, | |
| "train_steps_per_second": 8.633 | |
| } | |
| ], | |
| "logging_steps": 9, | |
| "max_steps": 1725, | |
| "num_train_epochs": 25, | |
| "save_steps": 18, | |
| "total_flos": 459342194208768.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |