| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 20.0, | |
| "eval_steps": 500, | |
| "global_step": 71480, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.3989927252378289e-08, | |
| "loss": 0.0035, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 5.008393956351427e-06, | |
| "loss": 0.0009, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.0016787912702854e-05, | |
| "loss": 0.001, | |
| "step": 716 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.502518186905428e-05, | |
| "loss": 0.0008, | |
| "step": 1074 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.0033575825405708e-05, | |
| "loss": 0.0007, | |
| "step": 1432 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.5041969781757136e-05, | |
| "loss": 0.0007, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.005036373810856e-05, | |
| "loss": 0.0007, | |
| "step": 2148 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.505875769445999e-05, | |
| "loss": 0.0007, | |
| "step": 2506 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.0067151650811416e-05, | |
| "loss": 0.0006, | |
| "step": 2864 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.507554560716285e-05, | |
| "loss": 0.0006, | |
| "step": 3222 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 4.419351284923323e-07, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.5506, | |
| "eval_samples_per_second": 19.603, | |
| "eval_steps_per_second": 0.784, | |
| "step": 3574 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5.008393956351427e-05, | |
| "loss": 0.0007, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 5.5092333519865704e-05, | |
| "loss": 0.0006, | |
| "step": 3938 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 6.010072747621712e-05, | |
| "loss": 0.0007, | |
| "step": 4296 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 6.510912143256855e-05, | |
| "loss": 0.0007, | |
| "step": 4654 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 7.011751538891998e-05, | |
| "loss": 0.0006, | |
| "step": 5012 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 7.51259093452714e-05, | |
| "loss": 0.0006, | |
| "step": 5370 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 8.013430330162283e-05, | |
| "loss": 0.0006, | |
| "step": 5728 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 8.514269725797426e-05, | |
| "loss": 0.0007, | |
| "step": 6086 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 9.01510912143257e-05, | |
| "loss": 0.0006, | |
| "step": 6444 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 9.515948517067713e-05, | |
| "loss": 0.0005, | |
| "step": 6802 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 7.104979999894567e-07, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.5602, | |
| "eval_samples_per_second": 19.53, | |
| "eval_steps_per_second": 0.781, | |
| "step": 7148 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 9.99813467636635e-05, | |
| "loss": 0.0008, | |
| "step": 7160 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 9.942485854629112e-05, | |
| "loss": 0.0006, | |
| "step": 7518 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 9.886837032891874e-05, | |
| "loss": 0.0007, | |
| "step": 7876 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 9.831188211154637e-05, | |
| "loss": 0.0006, | |
| "step": 8234 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 9.775539389417398e-05, | |
| "loss": 0.0006, | |
| "step": 8592 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 9.71989056768016e-05, | |
| "loss": 0.0007, | |
| "step": 8950 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 9.664241745942921e-05, | |
| "loss": 0.0007, | |
| "step": 9308 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 9.608592924205684e-05, | |
| "loss": 0.0006, | |
| "step": 9666 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 9.552944102468445e-05, | |
| "loss": 0.0007, | |
| "step": 10024 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 9.497295280731208e-05, | |
| "loss": 0.0007, | |
| "step": 10382 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 6.182289325806778e-06, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.5755, | |
| "eval_samples_per_second": 19.414, | |
| "eval_steps_per_second": 0.777, | |
| "step": 10722 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 9.441646458993969e-05, | |
| "loss": 0.0008, | |
| "step": 10740 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 9.385997637256732e-05, | |
| "loss": 0.0006, | |
| "step": 11098 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 9.330348815519493e-05, | |
| "loss": 0.0006, | |
| "step": 11456 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 9.274699993782255e-05, | |
| "loss": 0.0006, | |
| "step": 11814 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 9.219051172045016e-05, | |
| "loss": 0.0006, | |
| "step": 12172 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 9.163402350307779e-05, | |
| "loss": 0.0005, | |
| "step": 12530 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 9.10775352857054e-05, | |
| "loss": 0.0005, | |
| "step": 12888 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 9.052104706833303e-05, | |
| "loss": 0.0007, | |
| "step": 13246 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 8.996455885096065e-05, | |
| "loss": 0.0006, | |
| "step": 13604 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 8.940807063358827e-05, | |
| "loss": 0.0008, | |
| "step": 13962 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 2.7662836146191694e-06, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.5596, | |
| "eval_samples_per_second": 19.535, | |
| "eval_steps_per_second": 0.781, | |
| "step": 14296 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 8.885158241621589e-05, | |
| "loss": 0.0007, | |
| "step": 14320 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 8.82950941988435e-05, | |
| "loss": 0.0005, | |
| "step": 14678 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 8.773860598147112e-05, | |
| "loss": 0.0006, | |
| "step": 15036 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 8.718211776409875e-05, | |
| "loss": 0.0006, | |
| "step": 15394 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 8.662562954672636e-05, | |
| "loss": 0.0007, | |
| "step": 15752 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 8.606914132935397e-05, | |
| "loss": 0.0006, | |
| "step": 16110 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 8.55126531119816e-05, | |
| "loss": 0.0006, | |
| "step": 16468 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 8.495616489460922e-05, | |
| "loss": 0.0006, | |
| "step": 16826 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 8.439967667723684e-05, | |
| "loss": 0.0007, | |
| "step": 17184 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 8.384318845986446e-05, | |
| "loss": 0.0006, | |
| "step": 17542 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 9.952082109521143e-07, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.5707, | |
| "eval_samples_per_second": 19.45, | |
| "eval_steps_per_second": 0.778, | |
| "step": 17870 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 8.328670024249207e-05, | |
| "loss": 0.0006, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 8.273021202511969e-05, | |
| "loss": 0.0007, | |
| "step": 18258 | |
| }, | |
| { | |
| "epoch": 5.21, | |
| "learning_rate": 8.217372380774731e-05, | |
| "loss": 0.0006, | |
| "step": 18616 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "learning_rate": 8.161723559037493e-05, | |
| "loss": 0.0006, | |
| "step": 18974 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 8.106074737300256e-05, | |
| "loss": 0.0006, | |
| "step": 19332 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "learning_rate": 8.050425915563017e-05, | |
| "loss": 0.0005, | |
| "step": 19690 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 7.99477709382578e-05, | |
| "loss": 0.0005, | |
| "step": 20048 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 7.939128272088541e-05, | |
| "loss": 0.0005, | |
| "step": 20406 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "learning_rate": 7.883479450351303e-05, | |
| "loss": 0.0005, | |
| "step": 20764 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 7.827830628614064e-05, | |
| "loss": 0.0006, | |
| "step": 21122 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 4.1270132555837336e-07, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.5607, | |
| "eval_samples_per_second": 19.526, | |
| "eval_steps_per_second": 0.781, | |
| "step": 21444 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 7.772181806876827e-05, | |
| "loss": 0.0005, | |
| "step": 21480 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 7.716532985139588e-05, | |
| "loss": 0.0005, | |
| "step": 21838 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "learning_rate": 7.660884163402351e-05, | |
| "loss": 0.0006, | |
| "step": 22196 | |
| }, | |
| { | |
| "epoch": 6.31, | |
| "learning_rate": 7.605235341665112e-05, | |
| "loss": 0.0007, | |
| "step": 22554 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "learning_rate": 7.549586519927875e-05, | |
| "loss": 0.0004, | |
| "step": 22912 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 7.493937698190637e-05, | |
| "loss": 0.0005, | |
| "step": 23270 | |
| }, | |
| { | |
| "epoch": 6.61, | |
| "learning_rate": 7.438288876453398e-05, | |
| "loss": 0.0007, | |
| "step": 23628 | |
| }, | |
| { | |
| "epoch": 6.71, | |
| "learning_rate": 7.38264005471616e-05, | |
| "loss": 0.0004, | |
| "step": 23986 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "learning_rate": 7.326991232978922e-05, | |
| "loss": 0.0005, | |
| "step": 24344 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "learning_rate": 7.271342411241684e-05, | |
| "loss": 0.0005, | |
| "step": 24702 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 3.9943967067301855e-07, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.5544, | |
| "eval_samples_per_second": 19.574, | |
| "eval_steps_per_second": 0.783, | |
| "step": 25018 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 7.215693589504446e-05, | |
| "loss": 0.0005, | |
| "step": 25060 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "learning_rate": 7.160044767767208e-05, | |
| "loss": 0.0005, | |
| "step": 25418 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 7.10439594602997e-05, | |
| "loss": 0.0005, | |
| "step": 25776 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 7.048747124292732e-05, | |
| "loss": 0.0005, | |
| "step": 26134 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "learning_rate": 6.993098302555494e-05, | |
| "loss": 0.0005, | |
| "step": 26492 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "learning_rate": 6.937449480818255e-05, | |
| "loss": 0.0004, | |
| "step": 26850 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "learning_rate": 6.881800659081018e-05, | |
| "loss": 0.0005, | |
| "step": 27208 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "learning_rate": 6.826151837343779e-05, | |
| "loss": 0.0006, | |
| "step": 27566 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "learning_rate": 6.770503015606542e-05, | |
| "loss": 0.0004, | |
| "step": 27924 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 6.714854193869303e-05, | |
| "loss": 0.0005, | |
| "step": 28282 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 2.2114301145848003e-07, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.5528, | |
| "eval_samples_per_second": 19.587, | |
| "eval_steps_per_second": 0.783, | |
| "step": 28592 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 6.659205372132066e-05, | |
| "loss": 0.0004, | |
| "step": 28640 | |
| }, | |
| { | |
| "epoch": 8.11, | |
| "learning_rate": 6.603556550394828e-05, | |
| "loss": 0.0005, | |
| "step": 28998 | |
| }, | |
| { | |
| "epoch": 8.21, | |
| "learning_rate": 6.547907728657589e-05, | |
| "loss": 0.0004, | |
| "step": 29356 | |
| }, | |
| { | |
| "epoch": 8.31, | |
| "learning_rate": 6.49225890692035e-05, | |
| "loss": 0.0005, | |
| "step": 29714 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "learning_rate": 6.436610085183112e-05, | |
| "loss": 0.0004, | |
| "step": 30072 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "learning_rate": 6.380961263445875e-05, | |
| "loss": 0.0005, | |
| "step": 30430 | |
| }, | |
| { | |
| "epoch": 8.61, | |
| "learning_rate": 6.325312441708636e-05, | |
| "loss": 0.0006, | |
| "step": 30788 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "learning_rate": 6.269663619971399e-05, | |
| "loss": 0.0005, | |
| "step": 31146 | |
| }, | |
| { | |
| "epoch": 8.81, | |
| "learning_rate": 6.21401479823416e-05, | |
| "loss": 0.0005, | |
| "step": 31504 | |
| }, | |
| { | |
| "epoch": 8.91, | |
| "learning_rate": 6.158365976496923e-05, | |
| "loss": 0.0005, | |
| "step": 31862 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.2389272114887717e-06, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.565, | |
| "eval_samples_per_second": 19.493, | |
| "eval_steps_per_second": 0.78, | |
| "step": 32166 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 6.102717154759684e-05, | |
| "loss": 0.0004, | |
| "step": 32220 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 6.0470683330224465e-05, | |
| "loss": 0.0005, | |
| "step": 32578 | |
| }, | |
| { | |
| "epoch": 9.22, | |
| "learning_rate": 5.991419511285208e-05, | |
| "loss": 0.0004, | |
| "step": 32936 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 5.93577068954797e-05, | |
| "loss": 0.0004, | |
| "step": 33294 | |
| }, | |
| { | |
| "epoch": 9.42, | |
| "learning_rate": 5.8801218678107315e-05, | |
| "loss": 0.0005, | |
| "step": 33652 | |
| }, | |
| { | |
| "epoch": 9.52, | |
| "learning_rate": 5.824473046073494e-05, | |
| "loss": 0.0004, | |
| "step": 34010 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 5.7688242243362557e-05, | |
| "loss": 0.0005, | |
| "step": 34368 | |
| }, | |
| { | |
| "epoch": 9.72, | |
| "learning_rate": 5.713175402599018e-05, | |
| "loss": 0.0005, | |
| "step": 34726 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "learning_rate": 5.657526580861779e-05, | |
| "loss": 0.0005, | |
| "step": 35084 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 5.601877759124542e-05, | |
| "loss": 0.0004, | |
| "step": 35442 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 5.33479237674328e-07, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.5624, | |
| "eval_samples_per_second": 19.513, | |
| "eval_steps_per_second": 0.781, | |
| "step": 35740 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "learning_rate": 5.5462289373873034e-05, | |
| "loss": 0.0005, | |
| "step": 35800 | |
| }, | |
| { | |
| "epoch": 10.12, | |
| "learning_rate": 5.4905801156500655e-05, | |
| "loss": 0.0004, | |
| "step": 36158 | |
| }, | |
| { | |
| "epoch": 10.22, | |
| "learning_rate": 5.434931293912827e-05, | |
| "loss": 0.0005, | |
| "step": 36516 | |
| }, | |
| { | |
| "epoch": 10.32, | |
| "learning_rate": 5.37928247217559e-05, | |
| "loss": 0.0005, | |
| "step": 36874 | |
| }, | |
| { | |
| "epoch": 10.42, | |
| "learning_rate": 5.323633650438351e-05, | |
| "loss": 0.0005, | |
| "step": 37232 | |
| }, | |
| { | |
| "epoch": 10.52, | |
| "learning_rate": 5.267984828701113e-05, | |
| "loss": 0.0004, | |
| "step": 37590 | |
| }, | |
| { | |
| "epoch": 10.62, | |
| "learning_rate": 5.2123360069638746e-05, | |
| "loss": 0.0005, | |
| "step": 37948 | |
| }, | |
| { | |
| "epoch": 10.72, | |
| "learning_rate": 5.1566871852266374e-05, | |
| "loss": 0.0004, | |
| "step": 38306 | |
| }, | |
| { | |
| "epoch": 10.82, | |
| "learning_rate": 5.101038363489399e-05, | |
| "loss": 0.0006, | |
| "step": 38664 | |
| }, | |
| { | |
| "epoch": 10.92, | |
| "learning_rate": 5.0453895417521616e-05, | |
| "loss": 0.0005, | |
| "step": 39022 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 3.300738171674311e-07, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.5519, | |
| "eval_samples_per_second": 19.593, | |
| "eval_steps_per_second": 0.784, | |
| "step": 39314 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 4.9897407200149224e-05, | |
| "loss": 0.0004, | |
| "step": 39380 | |
| }, | |
| { | |
| "epoch": 11.12, | |
| "learning_rate": 4.9340918982776845e-05, | |
| "loss": 0.0004, | |
| "step": 39738 | |
| }, | |
| { | |
| "epoch": 11.22, | |
| "learning_rate": 4.8784430765404466e-05, | |
| "loss": 0.0005, | |
| "step": 40096 | |
| }, | |
| { | |
| "epoch": 11.32, | |
| "learning_rate": 4.8227942548032087e-05, | |
| "loss": 0.0004, | |
| "step": 40454 | |
| }, | |
| { | |
| "epoch": 11.42, | |
| "learning_rate": 4.76714543306597e-05, | |
| "loss": 0.0005, | |
| "step": 40812 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "learning_rate": 4.711496611328732e-05, | |
| "loss": 0.0004, | |
| "step": 41170 | |
| }, | |
| { | |
| "epoch": 11.62, | |
| "learning_rate": 4.655847789591494e-05, | |
| "loss": 0.0004, | |
| "step": 41528 | |
| }, | |
| { | |
| "epoch": 11.72, | |
| "learning_rate": 4.6001989678542564e-05, | |
| "loss": 0.0005, | |
| "step": 41886 | |
| }, | |
| { | |
| "epoch": 11.82, | |
| "learning_rate": 4.544550146117018e-05, | |
| "loss": 0.0004, | |
| "step": 42244 | |
| }, | |
| { | |
| "epoch": 11.92, | |
| "learning_rate": 4.48890132437978e-05, | |
| "loss": 0.0004, | |
| "step": 42602 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 3.465572717686882e-07, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.5595, | |
| "eval_samples_per_second": 19.535, | |
| "eval_steps_per_second": 0.781, | |
| "step": 42888 | |
| }, | |
| { | |
| "epoch": 12.02, | |
| "learning_rate": 4.433252502642542e-05, | |
| "loss": 0.0005, | |
| "step": 42960 | |
| }, | |
| { | |
| "epoch": 12.12, | |
| "learning_rate": 4.377603680905304e-05, | |
| "loss": 0.0004, | |
| "step": 43318 | |
| }, | |
| { | |
| "epoch": 12.22, | |
| "learning_rate": 4.3219548591680655e-05, | |
| "loss": 0.0004, | |
| "step": 43676 | |
| }, | |
| { | |
| "epoch": 12.32, | |
| "learning_rate": 4.2663060374308276e-05, | |
| "loss": 0.0004, | |
| "step": 44034 | |
| }, | |
| { | |
| "epoch": 12.42, | |
| "learning_rate": 4.21065721569359e-05, | |
| "loss": 0.0004, | |
| "step": 44392 | |
| }, | |
| { | |
| "epoch": 12.52, | |
| "learning_rate": 4.155008393956352e-05, | |
| "loss": 0.0004, | |
| "step": 44750 | |
| }, | |
| { | |
| "epoch": 12.62, | |
| "learning_rate": 4.099359572219114e-05, | |
| "loss": 0.0003, | |
| "step": 45108 | |
| }, | |
| { | |
| "epoch": 12.72, | |
| "learning_rate": 4.0437107504818753e-05, | |
| "loss": 0.0004, | |
| "step": 45466 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 3.9880619287446375e-05, | |
| "loss": 0.0004, | |
| "step": 45824 | |
| }, | |
| { | |
| "epoch": 12.92, | |
| "learning_rate": 3.9324131070073996e-05, | |
| "loss": 0.0004, | |
| "step": 46182 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 2.838061732290953e-07, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.5426, | |
| "eval_samples_per_second": 19.665, | |
| "eval_steps_per_second": 0.787, | |
| "step": 46462 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 3.8767642852701617e-05, | |
| "loss": 0.0005, | |
| "step": 46540 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "learning_rate": 3.821115463532923e-05, | |
| "loss": 0.0004, | |
| "step": 46898 | |
| }, | |
| { | |
| "epoch": 13.22, | |
| "learning_rate": 3.765466641795685e-05, | |
| "loss": 0.0004, | |
| "step": 47256 | |
| }, | |
| { | |
| "epoch": 13.32, | |
| "learning_rate": 3.709817820058447e-05, | |
| "loss": 0.0004, | |
| "step": 47614 | |
| }, | |
| { | |
| "epoch": 13.42, | |
| "learning_rate": 3.6541689983212094e-05, | |
| "loss": 0.0003, | |
| "step": 47972 | |
| }, | |
| { | |
| "epoch": 13.52, | |
| "learning_rate": 3.598520176583971e-05, | |
| "loss": 0.0005, | |
| "step": 48330 | |
| }, | |
| { | |
| "epoch": 13.62, | |
| "learning_rate": 3.542871354846733e-05, | |
| "loss": 0.0004, | |
| "step": 48688 | |
| }, | |
| { | |
| "epoch": 13.72, | |
| "learning_rate": 3.487222533109495e-05, | |
| "loss": 0.0004, | |
| "step": 49046 | |
| }, | |
| { | |
| "epoch": 13.82, | |
| "learning_rate": 3.431573711372257e-05, | |
| "loss": 0.0004, | |
| "step": 49404 | |
| }, | |
| { | |
| "epoch": 13.92, | |
| "learning_rate": 3.3759248896350185e-05, | |
| "loss": 0.0004, | |
| "step": 49762 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 2.3388430747672828e-07, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.5618, | |
| "eval_samples_per_second": 19.517, | |
| "eval_steps_per_second": 0.781, | |
| "step": 50036 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 3.3202760678977806e-05, | |
| "loss": 0.0004, | |
| "step": 50120 | |
| }, | |
| { | |
| "epoch": 14.12, | |
| "learning_rate": 3.264627246160543e-05, | |
| "loss": 0.0004, | |
| "step": 50478 | |
| }, | |
| { | |
| "epoch": 14.22, | |
| "learning_rate": 3.208978424423304e-05, | |
| "loss": 0.0005, | |
| "step": 50836 | |
| }, | |
| { | |
| "epoch": 14.32, | |
| "learning_rate": 3.153329602686066e-05, | |
| "loss": 0.0003, | |
| "step": 51194 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 3.097680780948828e-05, | |
| "loss": 0.0004, | |
| "step": 51552 | |
| }, | |
| { | |
| "epoch": 14.52, | |
| "learning_rate": 3.0420319592115898e-05, | |
| "loss": 0.0004, | |
| "step": 51910 | |
| }, | |
| { | |
| "epoch": 14.62, | |
| "learning_rate": 2.986383137474352e-05, | |
| "loss": 0.0004, | |
| "step": 52268 | |
| }, | |
| { | |
| "epoch": 14.72, | |
| "learning_rate": 2.9307343157371136e-05, | |
| "loss": 0.0003, | |
| "step": 52626 | |
| }, | |
| { | |
| "epoch": 14.82, | |
| "learning_rate": 2.8750854939998757e-05, | |
| "loss": 0.0004, | |
| "step": 52984 | |
| }, | |
| { | |
| "epoch": 14.93, | |
| "learning_rate": 2.8194366722626375e-05, | |
| "loss": 0.0004, | |
| "step": 53342 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 3.5529723163563176e-07, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.5603, | |
| "eval_samples_per_second": 19.529, | |
| "eval_steps_per_second": 0.781, | |
| "step": 53610 | |
| }, | |
| { | |
| "epoch": 15.03, | |
| "learning_rate": 2.7637878505253996e-05, | |
| "loss": 0.0004, | |
| "step": 53700 | |
| }, | |
| { | |
| "epoch": 15.13, | |
| "learning_rate": 2.7081390287881614e-05, | |
| "loss": 0.0004, | |
| "step": 54058 | |
| }, | |
| { | |
| "epoch": 15.23, | |
| "learning_rate": 2.6524902070509235e-05, | |
| "loss": 0.0003, | |
| "step": 54416 | |
| }, | |
| { | |
| "epoch": 15.33, | |
| "learning_rate": 2.5968413853136852e-05, | |
| "loss": 0.0003, | |
| "step": 54774 | |
| }, | |
| { | |
| "epoch": 15.43, | |
| "learning_rate": 2.5411925635764473e-05, | |
| "loss": 0.0003, | |
| "step": 55132 | |
| }, | |
| { | |
| "epoch": 15.53, | |
| "learning_rate": 2.485543741839209e-05, | |
| "loss": 0.0003, | |
| "step": 55490 | |
| }, | |
| { | |
| "epoch": 15.63, | |
| "learning_rate": 2.4298949201019712e-05, | |
| "loss": 0.0004, | |
| "step": 55848 | |
| }, | |
| { | |
| "epoch": 15.73, | |
| "learning_rate": 2.374246098364733e-05, | |
| "loss": 0.0004, | |
| "step": 56206 | |
| }, | |
| { | |
| "epoch": 15.83, | |
| "learning_rate": 2.318597276627495e-05, | |
| "loss": 0.0005, | |
| "step": 56564 | |
| }, | |
| { | |
| "epoch": 15.93, | |
| "learning_rate": 2.2629484548902568e-05, | |
| "loss": 0.0004, | |
| "step": 56922 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 1.6842723482568545e-07, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.5459, | |
| "eval_samples_per_second": 19.64, | |
| "eval_steps_per_second": 0.786, | |
| "step": 57184 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 2.207299633153019e-05, | |
| "loss": 0.0004, | |
| "step": 57280 | |
| }, | |
| { | |
| "epoch": 16.13, | |
| "learning_rate": 2.1516508114157807e-05, | |
| "loss": 0.0004, | |
| "step": 57638 | |
| }, | |
| { | |
| "epoch": 16.23, | |
| "learning_rate": 2.0960019896785428e-05, | |
| "loss": 0.0003, | |
| "step": 57996 | |
| }, | |
| { | |
| "epoch": 16.33, | |
| "learning_rate": 2.0403531679413045e-05, | |
| "loss": 0.0004, | |
| "step": 58354 | |
| }, | |
| { | |
| "epoch": 16.43, | |
| "learning_rate": 1.9847043462040666e-05, | |
| "loss": 0.0003, | |
| "step": 58712 | |
| }, | |
| { | |
| "epoch": 16.53, | |
| "learning_rate": 1.9290555244668284e-05, | |
| "loss": 0.0003, | |
| "step": 59070 | |
| }, | |
| { | |
| "epoch": 16.63, | |
| "learning_rate": 1.8734067027295905e-05, | |
| "loss": 0.0003, | |
| "step": 59428 | |
| }, | |
| { | |
| "epoch": 16.73, | |
| "learning_rate": 1.8177578809923522e-05, | |
| "loss": 0.0004, | |
| "step": 59786 | |
| }, | |
| { | |
| "epoch": 16.83, | |
| "learning_rate": 1.7621090592551143e-05, | |
| "loss": 0.0003, | |
| "step": 60144 | |
| }, | |
| { | |
| "epoch": 16.93, | |
| "learning_rate": 1.706460237517876e-05, | |
| "loss": 0.0003, | |
| "step": 60502 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 1.6692392534878309e-07, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.572, | |
| "eval_samples_per_second": 19.44, | |
| "eval_steps_per_second": 0.778, | |
| "step": 60758 | |
| }, | |
| { | |
| "epoch": 17.03, | |
| "learning_rate": 1.6508114157806382e-05, | |
| "loss": 0.0004, | |
| "step": 60860 | |
| }, | |
| { | |
| "epoch": 17.13, | |
| "learning_rate": 1.5951625940434e-05, | |
| "loss": 0.0003, | |
| "step": 61218 | |
| }, | |
| { | |
| "epoch": 17.23, | |
| "learning_rate": 1.5395137723061617e-05, | |
| "loss": 0.0003, | |
| "step": 61576 | |
| }, | |
| { | |
| "epoch": 17.33, | |
| "learning_rate": 1.4838649505689237e-05, | |
| "loss": 0.0004, | |
| "step": 61934 | |
| }, | |
| { | |
| "epoch": 17.43, | |
| "learning_rate": 1.4282161288316856e-05, | |
| "loss": 0.0003, | |
| "step": 62292 | |
| }, | |
| { | |
| "epoch": 17.53, | |
| "learning_rate": 1.3725673070944475e-05, | |
| "loss": 0.0004, | |
| "step": 62650 | |
| }, | |
| { | |
| "epoch": 17.63, | |
| "learning_rate": 1.3169184853572095e-05, | |
| "loss": 0.0003, | |
| "step": 63008 | |
| }, | |
| { | |
| "epoch": 17.73, | |
| "learning_rate": 1.2612696636199714e-05, | |
| "loss": 0.0003, | |
| "step": 63366 | |
| }, | |
| { | |
| "epoch": 17.83, | |
| "learning_rate": 1.2056208418827333e-05, | |
| "loss": 0.0004, | |
| "step": 63724 | |
| }, | |
| { | |
| "epoch": 17.93, | |
| "learning_rate": 1.1499720201454953e-05, | |
| "loss": 0.0003, | |
| "step": 64082 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 1.2040422348036373e-07, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.5484, | |
| "eval_samples_per_second": 19.62, | |
| "eval_steps_per_second": 0.785, | |
| "step": 64332 | |
| }, | |
| { | |
| "epoch": 18.03, | |
| "learning_rate": 1.0943231984082572e-05, | |
| "loss": 0.0004, | |
| "step": 64440 | |
| }, | |
| { | |
| "epoch": 18.13, | |
| "learning_rate": 1.0386743766710191e-05, | |
| "loss": 0.0004, | |
| "step": 64798 | |
| }, | |
| { | |
| "epoch": 18.23, | |
| "learning_rate": 9.83025554933781e-06, | |
| "loss": 0.0004, | |
| "step": 65156 | |
| }, | |
| { | |
| "epoch": 18.33, | |
| "learning_rate": 9.27376733196543e-06, | |
| "loss": 0.0003, | |
| "step": 65514 | |
| }, | |
| { | |
| "epoch": 18.43, | |
| "learning_rate": 8.717279114593049e-06, | |
| "loss": 0.0004, | |
| "step": 65872 | |
| }, | |
| { | |
| "epoch": 18.53, | |
| "learning_rate": 8.160790897220668e-06, | |
| "loss": 0.0003, | |
| "step": 66230 | |
| }, | |
| { | |
| "epoch": 18.63, | |
| "learning_rate": 7.604302679848288e-06, | |
| "loss": 0.0003, | |
| "step": 66588 | |
| }, | |
| { | |
| "epoch": 18.73, | |
| "learning_rate": 7.047814462475906e-06, | |
| "loss": 0.0004, | |
| "step": 66946 | |
| }, | |
| { | |
| "epoch": 18.83, | |
| "learning_rate": 6.4913262451035254e-06, | |
| "loss": 0.0004, | |
| "step": 67304 | |
| }, | |
| { | |
| "epoch": 18.93, | |
| "learning_rate": 5.934838027731145e-06, | |
| "loss": 0.0003, | |
| "step": 67662 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 1.5021944932414044e-07, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.5611, | |
| "eval_samples_per_second": 19.523, | |
| "eval_steps_per_second": 0.781, | |
| "step": 67906 | |
| }, | |
| { | |
| "epoch": 19.03, | |
| "learning_rate": 5.378349810358764e-06, | |
| "loss": 0.0004, | |
| "step": 68020 | |
| }, | |
| { | |
| "epoch": 19.13, | |
| "learning_rate": 4.821861592986383e-06, | |
| "loss": 0.0003, | |
| "step": 68378 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 4.265373375614003e-06, | |
| "loss": 0.0003, | |
| "step": 68736 | |
| }, | |
| { | |
| "epoch": 19.33, | |
| "learning_rate": 3.708885158241622e-06, | |
| "loss": 0.0004, | |
| "step": 69094 | |
| }, | |
| { | |
| "epoch": 19.43, | |
| "learning_rate": 3.152396940869241e-06, | |
| "loss": 0.0003, | |
| "step": 69452 | |
| }, | |
| { | |
| "epoch": 19.53, | |
| "learning_rate": 2.59590872349686e-06, | |
| "loss": 0.0004, | |
| "step": 69810 | |
| }, | |
| { | |
| "epoch": 19.63, | |
| "learning_rate": 2.0394205061244795e-06, | |
| "loss": 0.0004, | |
| "step": 70168 | |
| }, | |
| { | |
| "epoch": 19.73, | |
| "learning_rate": 1.4829322887520986e-06, | |
| "loss": 0.0005, | |
| "step": 70526 | |
| }, | |
| { | |
| "epoch": 19.83, | |
| "learning_rate": 9.264440713797177e-07, | |
| "loss": 0.0003, | |
| "step": 70884 | |
| }, | |
| { | |
| "epoch": 19.93, | |
| "learning_rate": 3.6995585400733695e-07, | |
| "loss": 0.0004, | |
| "step": 71242 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 1.4148230320643052e-07, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.545, | |
| "eval_samples_per_second": 19.646, | |
| "eval_steps_per_second": 0.786, | |
| "step": 71480 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 71480, | |
| "total_flos": 4.280579565218611e+16, | |
| "train_loss": 0.0004841739220773227, | |
| "train_runtime": 6809.3357, | |
| "train_samples_per_second": 314.85, | |
| "train_steps_per_second": 10.497 | |
| } | |
| ], | |
| "logging_steps": 358, | |
| "max_steps": 71480, | |
| "num_train_epochs": 20, | |
| "save_steps": 715, | |
| "total_flos": 4.280579565218611e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |