| { |
| "best_metric": 0.8681809306144714, |
| "best_model_checkpoint": "./lora-warewe/checkpoint-400", |
| "epoch": 2.483122526577171, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.02, |
| "learning_rate": 2.9999999999999997e-05, |
| "loss": 1.9531, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 5.9999999999999995e-05, |
| "loss": 1.8714, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 8.999999999999999e-05, |
| "loss": 1.7052, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 0.00011999999999999999, |
| "loss": 1.3201, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 0.00015, |
| "loss": 1.1551, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 0.00017999999999999998, |
| "loss": 1.1199, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 0.00020999999999999998, |
| "loss": 1.0598, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 0.00023999999999999998, |
| "loss": 1.0233, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.00027, |
| "loss": 1.0086, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 0.0003, |
| "loss": 0.999, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 0.0002972875226039783, |
| "loss": 0.9961, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 0.00029457504520795656, |
| "loss": 0.9831, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 0.0002918625678119349, |
| "loss": 0.9637, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 0.00028915009041591315, |
| "loss": 0.9546, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 0.0002864376130198915, |
| "loss": 0.9575, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 0.00028372513562386974, |
| "loss": 0.9337, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 0.00028101265822784807, |
| "loss": 0.942, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 0.0002783001808318264, |
| "loss": 0.9265, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 0.0002755877034358047, |
| "loss": 0.9324, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 0.000272875226039783, |
| "loss": 0.9288, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.5, |
| "eval_loss": 0.9210162162780762, |
| "eval_runtime": 559.4854, |
| "eval_samples_per_second": 3.575, |
| "eval_steps_per_second": 0.447, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 0.00027016274864376125, |
| "loss": 0.9201, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 0.00026745027124773957, |
| "loss": 0.9242, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.57, |
| "learning_rate": 0.0002647377938517179, |
| "loss": 0.9114, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 0.00026202531645569616, |
| "loss": 0.9223, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 0.0002593128390596745, |
| "loss": 0.9018, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.65, |
| "learning_rate": 0.0002566003616636528, |
| "loss": 0.9038, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 0.0002538878842676311, |
| "loss": 0.9087, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 0.0002511754068716094, |
| "loss": 0.9141, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.72, |
| "learning_rate": 0.00024846292947558766, |
| "loss": 0.8942, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 0.000245750452079566, |
| "loss": 0.8865, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.77, |
| "learning_rate": 0.00024303797468354428, |
| "loss": 0.8863, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.79, |
| "learning_rate": 0.00024032549728752258, |
| "loss": 0.8981, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.82, |
| "learning_rate": 0.0002376130198915009, |
| "loss": 0.8837, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 0.0002349005424954792, |
| "loss": 0.8887, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.87, |
| "learning_rate": 0.0002321880650994575, |
| "loss": 0.8781, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.89, |
| "learning_rate": 0.00022947558770343578, |
| "loss": 0.891, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 0.00022676311030741408, |
| "loss": 0.8852, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 0.00022405063291139237, |
| "loss": 0.8736, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.97, |
| "learning_rate": 0.0002213381555153707, |
| "loss": 0.8799, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.99, |
| "learning_rate": 0.000218625678119349, |
| "loss": 0.8847, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.99, |
| "eval_loss": 0.8681809306144714, |
| "eval_runtime": 405.865, |
| "eval_samples_per_second": 4.928, |
| "eval_steps_per_second": 0.616, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.02, |
| "learning_rate": 0.0002159132007233273, |
| "loss": 0.8731, |
| "step": 410 |
| }, |
| { |
| "epoch": 1.04, |
| "learning_rate": 0.0002132007233273056, |
| "loss": 0.8677, |
| "step": 420 |
| }, |
| { |
| "epoch": 1.07, |
| "learning_rate": 0.00021048824593128388, |
| "loss": 0.8784, |
| "step": 430 |
| }, |
| { |
| "epoch": 1.09, |
| "learning_rate": 0.00020777576853526217, |
| "loss": 0.8688, |
| "step": 440 |
| }, |
| { |
| "epoch": 1.12, |
| "learning_rate": 0.0002050632911392405, |
| "loss": 0.8663, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.14, |
| "learning_rate": 0.0002023508137432188, |
| "loss": 0.8748, |
| "step": 460 |
| }, |
| { |
| "epoch": 1.17, |
| "learning_rate": 0.00019963833634719708, |
| "loss": 0.8619, |
| "step": 470 |
| }, |
| { |
| "epoch": 1.19, |
| "learning_rate": 0.0001969258589511754, |
| "loss": 0.8544, |
| "step": 480 |
| }, |
| { |
| "epoch": 1.22, |
| "learning_rate": 0.0001942133815551537, |
| "loss": 0.871, |
| "step": 490 |
| }, |
| { |
| "epoch": 1.24, |
| "learning_rate": 0.000191500904159132, |
| "loss": 0.8748, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.27, |
| "learning_rate": 0.00018933092224231464, |
| "loss": 0.8753, |
| "step": 510 |
| }, |
| { |
| "epoch": 1.29, |
| "learning_rate": 0.00018824593128390595, |
| "loss": 1.8069, |
| "step": 520 |
| }, |
| { |
| "epoch": 1.32, |
| "learning_rate": 0.00018634719710669076, |
| "loss": 4.3811, |
| "step": 530 |
| }, |
| { |
| "epoch": 1.34, |
| "learning_rate": 0.00018390596745027123, |
| "loss": 5.8063, |
| "step": 540 |
| }, |
| { |
| "epoch": 1.37, |
| "learning_rate": 0.00018119349005424955, |
| "loss": 5.2762, |
| "step": 550 |
| }, |
| { |
| "epoch": 1.39, |
| "learning_rate": 0.00017848101265822782, |
| "loss": 3.0862, |
| "step": 560 |
| }, |
| { |
| "epoch": 1.42, |
| "learning_rate": 0.00017576853526220611, |
| "loss": 1.7397, |
| "step": 570 |
| }, |
| { |
| "epoch": 1.44, |
| "learning_rate": 0.00017305605786618444, |
| "loss": 1.5362, |
| "step": 580 |
| }, |
| { |
| "epoch": 1.47, |
| "learning_rate": 0.0001706148282097649, |
| "loss": 3.644, |
| "step": 590 |
| }, |
| { |
| "epoch": 1.49, |
| "learning_rate": 0.0001679023508137432, |
| "loss": 6.1529, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.49, |
| "eval_loss": 6.275171756744385, |
| "eval_runtime": 401.4674, |
| "eval_samples_per_second": 4.982, |
| "eval_steps_per_second": 0.623, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.51, |
| "learning_rate": 0.00016573236889692584, |
| "loss": 4.6504, |
| "step": 610 |
| }, |
| { |
| "epoch": 1.54, |
| "learning_rate": 0.00016301989150090414, |
| "loss": 3.3039, |
| "step": 620 |
| }, |
| { |
| "epoch": 1.56, |
| "learning_rate": 0.00016030741410488246, |
| "loss": 2.7266, |
| "step": 630 |
| }, |
| { |
| "epoch": 1.59, |
| "learning_rate": 0.00015759493670886075, |
| "loss": 4.5256, |
| "step": 640 |
| }, |
| { |
| "epoch": 1.61, |
| "learning_rate": 0.0001551537070524412, |
| "loss": 3.9326, |
| "step": 650 |
| }, |
| { |
| "epoch": 1.64, |
| "learning_rate": 0.00015244122965641952, |
| "loss": 1.6396, |
| "step": 660 |
| }, |
| { |
| "epoch": 1.66, |
| "learning_rate": 0.00014972875226039781, |
| "loss": 1.1304, |
| "step": 670 |
| }, |
| { |
| "epoch": 1.69, |
| "learning_rate": 0.0001470162748643761, |
| "loss": 1.0282, |
| "step": 680 |
| }, |
| { |
| "epoch": 1.71, |
| "learning_rate": 0.00014430379746835443, |
| "loss": 0.9902, |
| "step": 690 |
| }, |
| { |
| "epoch": 1.74, |
| "learning_rate": 0.00014159132007233273, |
| "loss": 0.9785, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.76, |
| "learning_rate": 0.00013887884267631102, |
| "loss": 0.9422, |
| "step": 710 |
| }, |
| { |
| "epoch": 1.79, |
| "learning_rate": 0.00013616636528028932, |
| "loss": 0.9466, |
| "step": 720 |
| }, |
| { |
| "epoch": 1.81, |
| "learning_rate": 0.0001334538878842676, |
| "loss": 0.9254, |
| "step": 730 |
| }, |
| { |
| "epoch": 1.84, |
| "learning_rate": 0.0001307414104882459, |
| "loss": 0.9257, |
| "step": 740 |
| }, |
| { |
| "epoch": 1.86, |
| "learning_rate": 0.00012802893309222423, |
| "loss": 0.9179, |
| "step": 750 |
| }, |
| { |
| "epoch": 1.89, |
| "learning_rate": 0.00012531645569620252, |
| "loss": 0.9247, |
| "step": 760 |
| }, |
| { |
| "epoch": 1.91, |
| "learning_rate": 0.00012260397830018082, |
| "loss": 0.9186, |
| "step": 770 |
| }, |
| { |
| "epoch": 1.94, |
| "learning_rate": 0.00011989150090415911, |
| "loss": 0.9253, |
| "step": 780 |
| }, |
| { |
| "epoch": 1.96, |
| "learning_rate": 0.00011717902350813742, |
| "loss": 0.9193, |
| "step": 790 |
| }, |
| { |
| "epoch": 1.99, |
| "learning_rate": 0.00011446654611211573, |
| "loss": 0.9141, |
| "step": 800 |
| }, |
| { |
| "epoch": 1.99, |
| "eval_loss": 0.9085212349891663, |
| "eval_runtime": 400.6517, |
| "eval_samples_per_second": 4.992, |
| "eval_steps_per_second": 0.624, |
| "step": 800 |
| }, |
| { |
| "epoch": 2.01, |
| "learning_rate": 0.00011175406871609403, |
| "loss": 0.9057, |
| "step": 810 |
| }, |
| { |
| "epoch": 2.04, |
| "learning_rate": 0.00010904159132007232, |
| "loss": 0.9083, |
| "step": 820 |
| }, |
| { |
| "epoch": 2.06, |
| "learning_rate": 0.00010632911392405062, |
| "loss": 0.9091, |
| "step": 830 |
| }, |
| { |
| "epoch": 2.09, |
| "learning_rate": 0.00010361663652802893, |
| "loss": 0.9186, |
| "step": 840 |
| }, |
| { |
| "epoch": 2.11, |
| "learning_rate": 0.00010090415913200722, |
| "loss": 0.9018, |
| "step": 850 |
| }, |
| { |
| "epoch": 2.14, |
| "learning_rate": 9.819168173598552e-05, |
| "loss": 0.8989, |
| "step": 860 |
| }, |
| { |
| "epoch": 2.16, |
| "learning_rate": 9.547920433996383e-05, |
| "loss": 0.9275, |
| "step": 870 |
| }, |
| { |
| "epoch": 2.19, |
| "learning_rate": 9.276672694394213e-05, |
| "loss": 0.9063, |
| "step": 880 |
| }, |
| { |
| "epoch": 2.21, |
| "learning_rate": 9.005424954792042e-05, |
| "loss": 0.8921, |
| "step": 890 |
| }, |
| { |
| "epoch": 2.23, |
| "learning_rate": 8.734177215189872e-05, |
| "loss": 0.8981, |
| "step": 900 |
| }, |
| { |
| "epoch": 2.26, |
| "learning_rate": 8.462929475587703e-05, |
| "loss": 0.9099, |
| "step": 910 |
| }, |
| { |
| "epoch": 2.28, |
| "learning_rate": 8.191681735985534e-05, |
| "loss": 0.8956, |
| "step": 920 |
| }, |
| { |
| "epoch": 2.31, |
| "learning_rate": 7.920433996383362e-05, |
| "loss": 0.8983, |
| "step": 930 |
| }, |
| { |
| "epoch": 2.33, |
| "learning_rate": 7.649186256781193e-05, |
| "loss": 0.9192, |
| "step": 940 |
| }, |
| { |
| "epoch": 2.36, |
| "learning_rate": 7.377938517179023e-05, |
| "loss": 0.9199, |
| "step": 950 |
| }, |
| { |
| "epoch": 2.38, |
| "learning_rate": 7.106690777576854e-05, |
| "loss": 0.8857, |
| "step": 960 |
| }, |
| { |
| "epoch": 2.41, |
| "learning_rate": 6.835443037974683e-05, |
| "loss": 0.8871, |
| "step": 970 |
| }, |
| { |
| "epoch": 2.43, |
| "learning_rate": 6.564195298372513e-05, |
| "loss": 0.9054, |
| "step": 980 |
| }, |
| { |
| "epoch": 2.46, |
| "learning_rate": 6.292947558770344e-05, |
| "loss": 0.9167, |
| "step": 990 |
| }, |
| { |
| "epoch": 2.48, |
| "learning_rate": 6.021699819168174e-05, |
| "loss": 0.9023, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.48, |
| "eval_loss": 0.9026673436164856, |
| "eval_runtime": 401.9867, |
| "eval_samples_per_second": 4.975, |
| "eval_steps_per_second": 0.622, |
| "step": 1000 |
| } |
| ], |
| "max_steps": 1206, |
| "num_train_epochs": 3, |
| "total_flos": 1.256386002199511e+18, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
