| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 15.0, | |
| "eval_steps": 500, | |
| "global_step": 45885, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2.1791239921551537e-08, | |
| "loss": 0.0002, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 5.011985181956853e-06, | |
| "loss": 0.0017, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.0023970363913707e-05, | |
| "loss": 0.0012, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.503595554587056e-05, | |
| "loss": 0.0008, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 2.0047940727827413e-05, | |
| "loss": 0.001, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 2.5059925909784264e-05, | |
| "loss": 0.0008, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 3.007191109174112e-05, | |
| "loss": 0.0007, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 3.5083896273697975e-05, | |
| "loss": 0.0007, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.0095881455654826e-05, | |
| "loss": 0.0006, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.5107866637611684e-05, | |
| "loss": 0.0006, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5.011985181956853e-05, | |
| "loss": 0.0005, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 5.5131837001525385e-05, | |
| "loss": 0.0004, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 6.014382218348224e-05, | |
| "loss": 0.0003, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 6.51558073654391e-05, | |
| "loss": 0.0004, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.002156034577637911, | |
| "eval_max_distance": 12, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 31.367, | |
| "eval_samples_per_second": 18.778, | |
| "eval_steps_per_second": 0.128, | |
| "step": 3059 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 7.016779254739595e-05, | |
| "loss": 0.0004, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 7.517977772935281e-05, | |
| "loss": 0.0003, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 8.019176291130965e-05, | |
| "loss": 0.0004, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 8.520374809326651e-05, | |
| "loss": 0.0003, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 9.021573327522337e-05, | |
| "loss": 0.0004, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 9.522771845718021e-05, | |
| "loss": 0.0003, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 9.997336303758234e-05, | |
| "loss": 0.0003, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 9.941640836884929e-05, | |
| "loss": 0.0003, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 9.885945370011624e-05, | |
| "loss": 0.0004, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 9.830249903138319e-05, | |
| "loss": 0.0003, | |
| "step": 5290 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 9.774554436265014e-05, | |
| "loss": 0.0004, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 9.718858969391709e-05, | |
| "loss": 0.0003, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 9.663163502518404e-05, | |
| "loss": 0.0003, | |
| "step": 5980 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.0011327904649078846, | |
| "eval_max_distance": 5, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 30.6053, | |
| "eval_samples_per_second": 19.245, | |
| "eval_steps_per_second": 0.131, | |
| "step": 6118 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 9.6074680356451e-05, | |
| "loss": 0.0003, | |
| "step": 6210 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 9.551772568771794e-05, | |
| "loss": 0.0003, | |
| "step": 6440 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 9.496077101898489e-05, | |
| "loss": 0.0003, | |
| "step": 6670 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 9.440381635025185e-05, | |
| "loss": 0.0003, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 9.384686168151879e-05, | |
| "loss": 0.0004, | |
| "step": 7130 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 9.328990701278575e-05, | |
| "loss": 0.0003, | |
| "step": 7360 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 9.273295234405269e-05, | |
| "loss": 0.0003, | |
| "step": 7590 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 9.217599767531964e-05, | |
| "loss": 0.0003, | |
| "step": 7820 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 9.16190430065866e-05, | |
| "loss": 0.0003, | |
| "step": 8050 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 9.106208833785354e-05, | |
| "loss": 0.0003, | |
| "step": 8280 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 9.05051336691205e-05, | |
| "loss": 0.0003, | |
| "step": 8510 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 8.994817900038746e-05, | |
| "loss": 0.0003, | |
| "step": 8740 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 8.939122433165439e-05, | |
| "loss": 0.0003, | |
| "step": 8970 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.0010147562716156244, | |
| "eval_max_distance": 6, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 30.7374, | |
| "eval_samples_per_second": 19.162, | |
| "eval_steps_per_second": 0.13, | |
| "step": 9177 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 8.883426966292136e-05, | |
| "loss": 0.0003, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 8.82773149941883e-05, | |
| "loss": 0.0002, | |
| "step": 9430 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 8.772036032545526e-05, | |
| "loss": 0.0003, | |
| "step": 9660 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 8.716340565672221e-05, | |
| "loss": 0.0002, | |
| "step": 9890 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 8.660645098798916e-05, | |
| "loss": 0.0003, | |
| "step": 10120 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 8.604949631925611e-05, | |
| "loss": 0.0003, | |
| "step": 10350 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 8.549254165052306e-05, | |
| "loss": 0.0003, | |
| "step": 10580 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 8.493558698179001e-05, | |
| "loss": 0.0003, | |
| "step": 10810 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 8.437863231305696e-05, | |
| "loss": 0.0003, | |
| "step": 11040 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 8.382167764432391e-05, | |
| "loss": 0.0003, | |
| "step": 11270 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 8.326472297559086e-05, | |
| "loss": 0.0003, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 8.270776830685781e-05, | |
| "loss": 0.0003, | |
| "step": 11730 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 8.215081363812476e-05, | |
| "loss": 0.0003, | |
| "step": 11960 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 8.159385896939171e-05, | |
| "loss": 0.0003, | |
| "step": 12190 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.0011835404438897967, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 30.6791, | |
| "eval_samples_per_second": 19.199, | |
| "eval_steps_per_second": 0.13, | |
| "step": 12236 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 8.103690430065866e-05, | |
| "loss": 0.0003, | |
| "step": 12420 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 8.047994963192561e-05, | |
| "loss": 0.0003, | |
| "step": 12650 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 7.992299496319256e-05, | |
| "loss": 0.0003, | |
| "step": 12880 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 7.936604029445953e-05, | |
| "loss": 0.0002, | |
| "step": 13110 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 7.880908562572646e-05, | |
| "loss": 0.0003, | |
| "step": 13340 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 7.825213095699341e-05, | |
| "loss": 0.0003, | |
| "step": 13570 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 7.769517628826036e-05, | |
| "loss": 0.0003, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 7.713822161952731e-05, | |
| "loss": 0.0003, | |
| "step": 14030 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 7.658126695079428e-05, | |
| "loss": 0.0002, | |
| "step": 14260 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 7.602431228206122e-05, | |
| "loss": 0.0003, | |
| "step": 14490 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 7.546735761332817e-05, | |
| "loss": 0.0003, | |
| "step": 14720 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 7.491040294459513e-05, | |
| "loss": 0.0002, | |
| "step": 14950 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 7.435344827586207e-05, | |
| "loss": 0.0003, | |
| "step": 15180 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.000761075527407229, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 30.6946, | |
| "eval_samples_per_second": 19.189, | |
| "eval_steps_per_second": 0.13, | |
| "step": 15295 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 7.379649360712903e-05, | |
| "loss": 0.0002, | |
| "step": 15410 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 7.323953893839598e-05, | |
| "loss": 0.0002, | |
| "step": 15640 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "learning_rate": 7.268258426966292e-05, | |
| "loss": 0.0003, | |
| "step": 15870 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "learning_rate": 7.212562960092988e-05, | |
| "loss": 0.0002, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "learning_rate": 7.156867493219682e-05, | |
| "loss": 0.0003, | |
| "step": 16330 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 7.101172026346378e-05, | |
| "loss": 0.0002, | |
| "step": 16560 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 7.045476559473073e-05, | |
| "loss": 0.0002, | |
| "step": 16790 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 6.989781092599767e-05, | |
| "loss": 0.0003, | |
| "step": 17020 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "learning_rate": 6.934085625726463e-05, | |
| "loss": 0.0003, | |
| "step": 17250 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 6.878390158853158e-05, | |
| "loss": 0.0002, | |
| "step": 17480 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 6.822694691979853e-05, | |
| "loss": 0.0003, | |
| "step": 17710 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 6.766999225106548e-05, | |
| "loss": 0.0003, | |
| "step": 17940 | |
| }, | |
| { | |
| "epoch": 5.94, | |
| "learning_rate": 6.711303758233242e-05, | |
| "loss": 0.0002, | |
| "step": 18170 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.0009165782830677927, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 30.7001, | |
| "eval_samples_per_second": 19.186, | |
| "eval_steps_per_second": 0.13, | |
| "step": 18354 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 6.655608291359938e-05, | |
| "loss": 0.0003, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "learning_rate": 6.599912824486634e-05, | |
| "loss": 0.0002, | |
| "step": 18630 | |
| }, | |
| { | |
| "epoch": 6.17, | |
| "learning_rate": 6.544217357613329e-05, | |
| "loss": 0.0002, | |
| "step": 18860 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 6.488521890740024e-05, | |
| "loss": 0.0003, | |
| "step": 19090 | |
| }, | |
| { | |
| "epoch": 6.32, | |
| "learning_rate": 6.432826423866719e-05, | |
| "loss": 0.0002, | |
| "step": 19320 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 6.377130956993414e-05, | |
| "loss": 0.0002, | |
| "step": 19550 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 6.321435490120109e-05, | |
| "loss": 0.0003, | |
| "step": 19780 | |
| }, | |
| { | |
| "epoch": 6.54, | |
| "learning_rate": 6.265740023246804e-05, | |
| "loss": 0.0002, | |
| "step": 20010 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 6.210044556373499e-05, | |
| "loss": 0.0002, | |
| "step": 20240 | |
| }, | |
| { | |
| "epoch": 6.69, | |
| "learning_rate": 6.154349089500194e-05, | |
| "loss": 0.0003, | |
| "step": 20470 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "learning_rate": 6.098653622626889e-05, | |
| "loss": 0.0002, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 6.84, | |
| "learning_rate": 6.042958155753584e-05, | |
| "loss": 0.0002, | |
| "step": 20930 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "learning_rate": 5.9872626888802796e-05, | |
| "loss": 0.0003, | |
| "step": 21160 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 5.931567222006974e-05, | |
| "loss": 0.0002, | |
| "step": 21390 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.0007532148738391697, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 31.1332, | |
| "eval_samples_per_second": 18.919, | |
| "eval_steps_per_second": 0.128, | |
| "step": 21413 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "learning_rate": 5.87587175513367e-05, | |
| "loss": 0.0003, | |
| "step": 21620 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 5.820176288260365e-05, | |
| "loss": 0.0002, | |
| "step": 21850 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "learning_rate": 5.764480821387059e-05, | |
| "loss": 0.0002, | |
| "step": 22080 | |
| }, | |
| { | |
| "epoch": 7.29, | |
| "learning_rate": 5.708785354513755e-05, | |
| "loss": 0.0002, | |
| "step": 22310 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 5.653089887640449e-05, | |
| "loss": 0.0003, | |
| "step": 22540 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "learning_rate": 5.597394420767145e-05, | |
| "loss": 0.0003, | |
| "step": 22770 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 5.54169895389384e-05, | |
| "loss": 0.0002, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 7.59, | |
| "learning_rate": 5.486003487020534e-05, | |
| "loss": 0.0002, | |
| "step": 23230 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "learning_rate": 5.43030802014723e-05, | |
| "loss": 0.0003, | |
| "step": 23460 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 5.374612553273926e-05, | |
| "loss": 0.0002, | |
| "step": 23690 | |
| }, | |
| { | |
| "epoch": 7.82, | |
| "learning_rate": 5.31891708640062e-05, | |
| "loss": 0.0002, | |
| "step": 23920 | |
| }, | |
| { | |
| "epoch": 7.89, | |
| "learning_rate": 5.263221619527316e-05, | |
| "loss": 0.0002, | |
| "step": 24150 | |
| }, | |
| { | |
| "epoch": 7.97, | |
| "learning_rate": 5.20752615265401e-05, | |
| "loss": 0.0002, | |
| "step": 24380 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.0007926285616122186, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 30.7407, | |
| "eval_samples_per_second": 19.16, | |
| "eval_steps_per_second": 0.13, | |
| "step": 24472 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "learning_rate": 5.151830685780705e-05, | |
| "loss": 0.0002, | |
| "step": 24610 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 5.096135218907401e-05, | |
| "loss": 0.0002, | |
| "step": 24840 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "learning_rate": 5.040439752034095e-05, | |
| "loss": 0.0002, | |
| "step": 25070 | |
| }, | |
| { | |
| "epoch": 8.27, | |
| "learning_rate": 4.984744285160791e-05, | |
| "loss": 0.0002, | |
| "step": 25300 | |
| }, | |
| { | |
| "epoch": 8.35, | |
| "learning_rate": 4.929048818287485e-05, | |
| "loss": 0.0002, | |
| "step": 25530 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "learning_rate": 4.873353351414181e-05, | |
| "loss": 0.0002, | |
| "step": 25760 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "learning_rate": 4.817657884540876e-05, | |
| "loss": 0.0002, | |
| "step": 25990 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 4.761962417667571e-05, | |
| "loss": 0.0002, | |
| "step": 26220 | |
| }, | |
| { | |
| "epoch": 8.65, | |
| "learning_rate": 4.706266950794266e-05, | |
| "loss": 0.0002, | |
| "step": 26450 | |
| }, | |
| { | |
| "epoch": 8.72, | |
| "learning_rate": 4.650571483920961e-05, | |
| "loss": 0.0002, | |
| "step": 26680 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 4.594876017047656e-05, | |
| "loss": 0.0002, | |
| "step": 26910 | |
| }, | |
| { | |
| "epoch": 8.87, | |
| "learning_rate": 4.539180550174351e-05, | |
| "loss": 0.0003, | |
| "step": 27140 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "learning_rate": 4.483485083301046e-05, | |
| "loss": 0.0002, | |
| "step": 27370 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.0007057118928059936, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 30.795, | |
| "eval_samples_per_second": 19.127, | |
| "eval_steps_per_second": 0.13, | |
| "step": 27531 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 4.427789616427741e-05, | |
| "loss": 0.0002, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 4.372094149554436e-05, | |
| "loss": 0.0002, | |
| "step": 27830 | |
| }, | |
| { | |
| "epoch": 9.17, | |
| "learning_rate": 4.3163986826811313e-05, | |
| "loss": 0.0002, | |
| "step": 28060 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 4.2607032158078264e-05, | |
| "loss": 0.0002, | |
| "step": 28290 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 4.205007748934522e-05, | |
| "loss": 0.0002, | |
| "step": 28520 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 4.149312282061217e-05, | |
| "loss": 0.0002, | |
| "step": 28750 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 4.0936168151879115e-05, | |
| "loss": 0.0002, | |
| "step": 28980 | |
| }, | |
| { | |
| "epoch": 9.55, | |
| "learning_rate": 4.0379213483146065e-05, | |
| "loss": 0.0002, | |
| "step": 29210 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 3.982225881441302e-05, | |
| "loss": 0.0002, | |
| "step": 29440 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "learning_rate": 3.926530414567997e-05, | |
| "loss": 0.0003, | |
| "step": 29670 | |
| }, | |
| { | |
| "epoch": 9.77, | |
| "learning_rate": 3.870834947694692e-05, | |
| "loss": 0.0002, | |
| "step": 29900 | |
| }, | |
| { | |
| "epoch": 9.85, | |
| "learning_rate": 3.8151394808213873e-05, | |
| "loss": 0.0002, | |
| "step": 30130 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 3.7594440139480824e-05, | |
| "loss": 0.0002, | |
| "step": 30360 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 3.7037485470747774e-05, | |
| "loss": 0.0002, | |
| "step": 30590 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.000787499884609133, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 30.7843, | |
| "eval_samples_per_second": 19.133, | |
| "eval_steps_per_second": 0.13, | |
| "step": 30590 | |
| }, | |
| { | |
| "epoch": 10.08, | |
| "learning_rate": 3.6480530802014724e-05, | |
| "loss": 0.0002, | |
| "step": 30820 | |
| }, | |
| { | |
| "epoch": 10.15, | |
| "learning_rate": 3.5923576133281675e-05, | |
| "loss": 0.0002, | |
| "step": 31050 | |
| }, | |
| { | |
| "epoch": 10.23, | |
| "learning_rate": 3.5366621464548625e-05, | |
| "loss": 0.0002, | |
| "step": 31280 | |
| }, | |
| { | |
| "epoch": 10.3, | |
| "learning_rate": 3.4809666795815576e-05, | |
| "loss": 0.0002, | |
| "step": 31510 | |
| }, | |
| { | |
| "epoch": 10.38, | |
| "learning_rate": 3.4252712127082526e-05, | |
| "loss": 0.0002, | |
| "step": 31740 | |
| }, | |
| { | |
| "epoch": 10.45, | |
| "learning_rate": 3.369575745834948e-05, | |
| "loss": 0.0002, | |
| "step": 31970 | |
| }, | |
| { | |
| "epoch": 10.53, | |
| "learning_rate": 3.313880278961643e-05, | |
| "loss": 0.0002, | |
| "step": 32200 | |
| }, | |
| { | |
| "epoch": 10.6, | |
| "learning_rate": 3.258184812088338e-05, | |
| "loss": 0.0002, | |
| "step": 32430 | |
| }, | |
| { | |
| "epoch": 10.68, | |
| "learning_rate": 3.202489345215033e-05, | |
| "loss": 0.0002, | |
| "step": 32660 | |
| }, | |
| { | |
| "epoch": 10.75, | |
| "learning_rate": 3.1467938783417284e-05, | |
| "loss": 0.0002, | |
| "step": 32890 | |
| }, | |
| { | |
| "epoch": 10.83, | |
| "learning_rate": 3.0910984114684235e-05, | |
| "loss": 0.0002, | |
| "step": 33120 | |
| }, | |
| { | |
| "epoch": 10.9, | |
| "learning_rate": 3.0354029445951182e-05, | |
| "loss": 0.0002, | |
| "step": 33350 | |
| }, | |
| { | |
| "epoch": 10.98, | |
| "learning_rate": 2.9797074777218132e-05, | |
| "loss": 0.0002, | |
| "step": 33580 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.000802784226834774, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 30.8756, | |
| "eval_samples_per_second": 19.077, | |
| "eval_steps_per_second": 0.13, | |
| "step": 33649 | |
| }, | |
| { | |
| "epoch": 11.05, | |
| "learning_rate": 2.9240120108485086e-05, | |
| "loss": 0.0002, | |
| "step": 33810 | |
| }, | |
| { | |
| "epoch": 11.13, | |
| "learning_rate": 2.8683165439752036e-05, | |
| "loss": 0.0002, | |
| "step": 34040 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 2.8126210771018983e-05, | |
| "loss": 0.0002, | |
| "step": 34270 | |
| }, | |
| { | |
| "epoch": 11.28, | |
| "learning_rate": 2.756925610228594e-05, | |
| "loss": 0.0002, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 11.35, | |
| "learning_rate": 2.7012301433552887e-05, | |
| "loss": 0.0002, | |
| "step": 34730 | |
| }, | |
| { | |
| "epoch": 11.43, | |
| "learning_rate": 2.6455346764819838e-05, | |
| "loss": 0.0002, | |
| "step": 34960 | |
| }, | |
| { | |
| "epoch": 11.5, | |
| "learning_rate": 2.5898392096086788e-05, | |
| "loss": 0.0002, | |
| "step": 35190 | |
| }, | |
| { | |
| "epoch": 11.58, | |
| "learning_rate": 2.5341437427353742e-05, | |
| "loss": 0.0002, | |
| "step": 35420 | |
| }, | |
| { | |
| "epoch": 11.65, | |
| "learning_rate": 2.4784482758620692e-05, | |
| "loss": 0.0002, | |
| "step": 35650 | |
| }, | |
| { | |
| "epoch": 11.73, | |
| "learning_rate": 2.4227528089887643e-05, | |
| "loss": 0.0002, | |
| "step": 35880 | |
| }, | |
| { | |
| "epoch": 11.8, | |
| "learning_rate": 2.3670573421154593e-05, | |
| "loss": 0.0002, | |
| "step": 36110 | |
| }, | |
| { | |
| "epoch": 11.88, | |
| "learning_rate": 2.3113618752421543e-05, | |
| "loss": 0.0002, | |
| "step": 36340 | |
| }, | |
| { | |
| "epoch": 11.95, | |
| "learning_rate": 2.2556664083688494e-05, | |
| "loss": 0.0002, | |
| "step": 36570 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.0007881763740442693, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 30.7194, | |
| "eval_samples_per_second": 19.174, | |
| "eval_steps_per_second": 0.13, | |
| "step": 36708 | |
| }, | |
| { | |
| "epoch": 12.03, | |
| "learning_rate": 2.1999709414955444e-05, | |
| "loss": 0.0002, | |
| "step": 36800 | |
| }, | |
| { | |
| "epoch": 12.11, | |
| "learning_rate": 2.1442754746222398e-05, | |
| "loss": 0.0002, | |
| "step": 37030 | |
| }, | |
| { | |
| "epoch": 12.18, | |
| "learning_rate": 2.0885800077489345e-05, | |
| "loss": 0.0002, | |
| "step": 37260 | |
| }, | |
| { | |
| "epoch": 12.26, | |
| "learning_rate": 2.03288454087563e-05, | |
| "loss": 0.0002, | |
| "step": 37490 | |
| }, | |
| { | |
| "epoch": 12.33, | |
| "learning_rate": 1.9771890740023245e-05, | |
| "loss": 0.0002, | |
| "step": 37720 | |
| }, | |
| { | |
| "epoch": 12.41, | |
| "learning_rate": 1.92149360712902e-05, | |
| "loss": 0.0002, | |
| "step": 37950 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "learning_rate": 1.865798140255715e-05, | |
| "loss": 0.0002, | |
| "step": 38180 | |
| }, | |
| { | |
| "epoch": 12.56, | |
| "learning_rate": 1.81010267338241e-05, | |
| "loss": 0.0002, | |
| "step": 38410 | |
| }, | |
| { | |
| "epoch": 12.63, | |
| "learning_rate": 1.754407206509105e-05, | |
| "loss": 0.0002, | |
| "step": 38640 | |
| }, | |
| { | |
| "epoch": 12.71, | |
| "learning_rate": 1.6987117396358e-05, | |
| "loss": 0.0002, | |
| "step": 38870 | |
| }, | |
| { | |
| "epoch": 12.78, | |
| "learning_rate": 1.6430162727624954e-05, | |
| "loss": 0.0002, | |
| "step": 39100 | |
| }, | |
| { | |
| "epoch": 12.86, | |
| "learning_rate": 1.5873208058891905e-05, | |
| "loss": 0.0002, | |
| "step": 39330 | |
| }, | |
| { | |
| "epoch": 12.93, | |
| "learning_rate": 1.5316253390158855e-05, | |
| "loss": 0.0002, | |
| "step": 39560 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.000838827807456255, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 30.7487, | |
| "eval_samples_per_second": 19.155, | |
| "eval_steps_per_second": 0.13, | |
| "step": 39767 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 1.4759298721425804e-05, | |
| "loss": 0.0002, | |
| "step": 39790 | |
| }, | |
| { | |
| "epoch": 13.08, | |
| "learning_rate": 1.4202344052692756e-05, | |
| "loss": 0.0002, | |
| "step": 40020 | |
| }, | |
| { | |
| "epoch": 13.16, | |
| "learning_rate": 1.3645389383959706e-05, | |
| "loss": 0.0002, | |
| "step": 40250 | |
| }, | |
| { | |
| "epoch": 13.23, | |
| "learning_rate": 1.3088434715226658e-05, | |
| "loss": 0.0002, | |
| "step": 40480 | |
| }, | |
| { | |
| "epoch": 13.31, | |
| "learning_rate": 1.2531480046493607e-05, | |
| "loss": 0.0002, | |
| "step": 40710 | |
| }, | |
| { | |
| "epoch": 13.38, | |
| "learning_rate": 1.1974525377760557e-05, | |
| "loss": 0.0002, | |
| "step": 40940 | |
| }, | |
| { | |
| "epoch": 13.46, | |
| "learning_rate": 1.141757070902751e-05, | |
| "loss": 0.0002, | |
| "step": 41170 | |
| }, | |
| { | |
| "epoch": 13.53, | |
| "learning_rate": 1.0860616040294461e-05, | |
| "loss": 0.0002, | |
| "step": 41400 | |
| }, | |
| { | |
| "epoch": 13.61, | |
| "learning_rate": 1.0303661371561412e-05, | |
| "loss": 0.0002, | |
| "step": 41630 | |
| }, | |
| { | |
| "epoch": 13.68, | |
| "learning_rate": 9.746706702828362e-06, | |
| "loss": 0.0002, | |
| "step": 41860 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "learning_rate": 9.189752034095312e-06, | |
| "loss": 0.0002, | |
| "step": 42090 | |
| }, | |
| { | |
| "epoch": 13.83, | |
| "learning_rate": 8.632797365362263e-06, | |
| "loss": 0.0002, | |
| "step": 42320 | |
| }, | |
| { | |
| "epoch": 13.91, | |
| "learning_rate": 8.075842696629215e-06, | |
| "loss": 0.0002, | |
| "step": 42550 | |
| }, | |
| { | |
| "epoch": 13.98, | |
| "learning_rate": 7.518888027896165e-06, | |
| "loss": 0.0002, | |
| "step": 42780 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.0008361997315660119, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 30.9876, | |
| "eval_samples_per_second": 19.008, | |
| "eval_steps_per_second": 0.129, | |
| "step": 42826 | |
| }, | |
| { | |
| "epoch": 14.06, | |
| "learning_rate": 6.9619333591631155e-06, | |
| "loss": 0.0002, | |
| "step": 43010 | |
| }, | |
| { | |
| "epoch": 14.14, | |
| "learning_rate": 6.404978690430067e-06, | |
| "loss": 0.0002, | |
| "step": 43240 | |
| }, | |
| { | |
| "epoch": 14.21, | |
| "learning_rate": 5.848024021697017e-06, | |
| "loss": 0.0002, | |
| "step": 43470 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "learning_rate": 5.291069352963967e-06, | |
| "loss": 0.0002, | |
| "step": 43700 | |
| }, | |
| { | |
| "epoch": 14.36, | |
| "learning_rate": 4.7341146842309186e-06, | |
| "loss": 0.0002, | |
| "step": 43930 | |
| }, | |
| { | |
| "epoch": 14.44, | |
| "learning_rate": 4.177160015497869e-06, | |
| "loss": 0.0002, | |
| "step": 44160 | |
| }, | |
| { | |
| "epoch": 14.51, | |
| "learning_rate": 3.6202053467648197e-06, | |
| "loss": 0.0002, | |
| "step": 44390 | |
| }, | |
| { | |
| "epoch": 14.59, | |
| "learning_rate": 3.063250678031771e-06, | |
| "loss": 0.0002, | |
| "step": 44620 | |
| }, | |
| { | |
| "epoch": 14.66, | |
| "learning_rate": 2.5062960092987217e-06, | |
| "loss": 0.0002, | |
| "step": 44850 | |
| }, | |
| { | |
| "epoch": 14.74, | |
| "learning_rate": 1.949341340565672e-06, | |
| "loss": 0.0002, | |
| "step": 45080 | |
| }, | |
| { | |
| "epoch": 14.81, | |
| "learning_rate": 1.392386671832623e-06, | |
| "loss": 0.0002, | |
| "step": 45310 | |
| }, | |
| { | |
| "epoch": 14.89, | |
| "learning_rate": 8.354320030995738e-07, | |
| "loss": 0.0002, | |
| "step": 45540 | |
| }, | |
| { | |
| "epoch": 14.96, | |
| "learning_rate": 2.784773343665246e-07, | |
| "loss": 0.0002, | |
| "step": 45770 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.0008401814266107976, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 30.8673, | |
| "eval_samples_per_second": 19.082, | |
| "eval_steps_per_second": 0.13, | |
| "step": 45885 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "step": 45885, | |
| "total_flos": 7.988818341631795e+16, | |
| "train_loss": 0.0002746593983470409, | |
| "train_runtime": 6476.6732, | |
| "train_samples_per_second": 531.266, | |
| "train_steps_per_second": 7.085 | |
| } | |
| ], | |
| "logging_steps": 230, | |
| "max_steps": 45885, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 15, | |
| "save_steps": 4589, | |
| "total_flos": 7.988818341631795e+16, | |
| "train_batch_size": 75, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |