| { | |
| "best_metric": 0.9545624852180481, | |
| "best_model_checkpoint": "./lora-alpaca/checkpoint-2000", | |
| "epoch": 2.542911633820725, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.6999999999999996e-05, | |
| "loss": 1.6482, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 5.399999999999999e-05, | |
| "loss": 1.5884, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 8.4e-05, | |
| "loss": 1.5166, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00011399999999999999, | |
| "loss": 1.3197, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00014399999999999998, | |
| "loss": 1.1732, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00017399999999999997, | |
| "loss": 1.1358, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.000204, | |
| "loss": 1.0792, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.000234, | |
| "loss": 1.062, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00026399999999999997, | |
| "loss": 1.0665, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.000294, | |
| "loss": 1.0641, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00029893711248892826, | |
| "loss": 1.0449, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00029760850310008854, | |
| "loss": 1.0356, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0002962798937112489, | |
| "loss": 1.0537, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0002949512843224092, | |
| "loss": 1.0285, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0002936226749335695, | |
| "loss": 1.0197, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0002922940655447298, | |
| "loss": 1.0171, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00029096545615589015, | |
| "loss": 1.0112, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0002896368467670505, | |
| "loss": 1.0299, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00028830823737821076, | |
| "loss": 1.0243, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0002869796279893711, | |
| "loss": 1.0118, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.0055800676345825, | |
| "eval_runtime": 82.8279, | |
| "eval_samples_per_second": 24.146, | |
| "eval_steps_per_second": 0.761, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00028565101860053143, | |
| "loss": 0.9956, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00028432240921169176, | |
| "loss": 1.0039, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00028299379982285204, | |
| "loss": 1.0026, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00028166519043401237, | |
| "loss": 1.0148, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0002803365810451727, | |
| "loss": 1.0065, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00027900797165633304, | |
| "loss": 0.9965, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0002776793622674933, | |
| "loss": 1.0037, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00027635075287865365, | |
| "loss": 1.0149, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.000275022143489814, | |
| "loss": 1.0136, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00027369353410097426, | |
| "loss": 0.9937, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0002723649247121346, | |
| "loss": 0.987, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0002710363153232949, | |
| "loss": 1.016, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00026970770593445526, | |
| "loss": 1.0136, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00026837909654561554, | |
| "loss": 0.9926, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00026705048715677587, | |
| "loss": 0.9922, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0002657218777679362, | |
| "loss": 0.9883, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00026439326837909654, | |
| "loss": 1.0076, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0002630646589902568, | |
| "loss": 0.9873, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0002617360496014172, | |
| "loss": 0.988, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0002604074402125775, | |
| "loss": 0.9902, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 0.9863091111183167, | |
| "eval_runtime": 82.9481, | |
| "eval_samples_per_second": 24.111, | |
| "eval_steps_per_second": 0.76, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00025907883082373776, | |
| "loss": 0.9966, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00025775022143489815, | |
| "loss": 0.9914, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0002564216120460584, | |
| "loss": 0.9924, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00025509300265721876, | |
| "loss": 0.9948, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0002537643932683791, | |
| "loss": 0.9879, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002524357838795394, | |
| "loss": 0.988, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0002511071744906997, | |
| "loss": 0.9928, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00024977856510186003, | |
| "loss": 0.9916, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00024844995571302037, | |
| "loss": 0.994, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0002471213463241807, | |
| "loss": 0.996, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.000245792736935341, | |
| "loss": 0.9783, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0002444641275465013, | |
| "loss": 0.9798, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00024313551815766162, | |
| "loss": 0.9791, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00024180690876882195, | |
| "loss": 0.9894, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00024047829937998225, | |
| "loss": 0.9904, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00023914968999114256, | |
| "loss": 0.9942, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0002378210806023029, | |
| "loss": 0.9897, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.0002364924712134632, | |
| "loss": 0.9741, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00023516386182462353, | |
| "loss": 0.9631, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00023383525243578384, | |
| "loss": 0.9784, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 0.9769166111946106, | |
| "eval_runtime": 78.8243, | |
| "eval_samples_per_second": 25.373, | |
| "eval_steps_per_second": 0.799, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0002325066430469442, | |
| "loss": 0.9703, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00023117803365810448, | |
| "loss": 0.9914, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00022984942426926484, | |
| "loss": 0.9522, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00022852081488042514, | |
| "loss": 0.9773, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00022719220549158547, | |
| "loss": 0.9954, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00022586359610274578, | |
| "loss": 0.9768, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0002245349867139061, | |
| "loss": 0.9908, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00022320637732506642, | |
| "loss": 0.9944, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00022187776793622672, | |
| "loss": 0.9772, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00022054915854738706, | |
| "loss": 0.9697, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.00021922054915854736, | |
| "loss": 0.9652, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0002178919397697077, | |
| "loss": 0.9738, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.000216563330380868, | |
| "loss": 0.9892, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00021523472099202833, | |
| "loss": 0.9731, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.00021390611160318864, | |
| "loss": 0.985, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00021257750221434897, | |
| "loss": 0.9918, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00021124889282550928, | |
| "loss": 0.9603, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0002099202834366696, | |
| "loss": 0.9686, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.00020859167404782992, | |
| "loss": 0.9761, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00020726306465899025, | |
| "loss": 0.9812, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_loss": 0.970382571220398, | |
| "eval_runtime": 78.9078, | |
| "eval_samples_per_second": 25.346, | |
| "eval_steps_per_second": 0.798, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.00020593445527015056, | |
| "loss": 0.95, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.0002046058458813109, | |
| "loss": 0.9575, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.0002032772364924712, | |
| "loss": 0.9826, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0002019486271036315, | |
| "loss": 0.973, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00020062001771479183, | |
| "loss": 0.9623, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.00019929140832595214, | |
| "loss": 0.9618, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00019796279893711247, | |
| "loss": 0.9594, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00019663418954827278, | |
| "loss": 0.9827, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0001953055801594331, | |
| "loss": 0.9608, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.00019397697077059342, | |
| "loss": 0.967, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00019264836138175375, | |
| "loss": 0.9498, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00019131975199291405, | |
| "loss": 0.972, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.0001899911426040744, | |
| "loss": 0.9677, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0001886625332152347, | |
| "loss": 0.9715, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00018733392382639503, | |
| "loss": 0.9758, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00018600531443755533, | |
| "loss": 0.9667, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.00018467670504871564, | |
| "loss": 0.9719, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.00018334809565987597, | |
| "loss": 0.9584, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00018201948627103628, | |
| "loss": 0.9591, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.00018069087688219664, | |
| "loss": 0.959, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_loss": 0.9663413166999817, | |
| "eval_runtime": 83.6093, | |
| "eval_samples_per_second": 23.921, | |
| "eval_steps_per_second": 0.754, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.00017936226749335691, | |
| "loss": 0.9545, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.00017803365810451727, | |
| "loss": 0.9675, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00017670504871567758, | |
| "loss": 0.961, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.0001753764393268379, | |
| "loss": 0.9575, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00017404782993799822, | |
| "loss": 0.9636, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.00017271922054915855, | |
| "loss": 0.9687, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00017139061116031886, | |
| "loss": 0.9656, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.0001700620017714792, | |
| "loss": 0.9493, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.0001687333923826395, | |
| "loss": 0.9681, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00016740478299379983, | |
| "loss": 0.9537, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.00016607617360496013, | |
| "loss": 0.9468, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.00016474756421612044, | |
| "loss": 0.957, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.00016341895482728077, | |
| "loss": 0.9697, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.00016209034543844108, | |
| "loss": 0.9689, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.0001607617360496014, | |
| "loss": 0.9691, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.00015943312666076172, | |
| "loss": 0.9678, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.00015810451727192205, | |
| "loss": 0.967, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.00015677590788308235, | |
| "loss": 0.9742, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.0001554472984942427, | |
| "loss": 0.9438, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.000154118689105403, | |
| "loss": 0.9688, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_loss": 0.9622219204902649, | |
| "eval_runtime": 78.9396, | |
| "eval_samples_per_second": 25.336, | |
| "eval_steps_per_second": 0.798, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 0.00015279007971656333, | |
| "loss": 0.9655, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.00015146147032772363, | |
| "loss": 0.957, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.00015013286093888396, | |
| "loss": 0.9667, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.00014880425155004427, | |
| "loss": 0.9554, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.0001474756421612046, | |
| "loss": 0.9691, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0001461470327723649, | |
| "loss": 0.9587, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.00014481842338352524, | |
| "loss": 0.9461, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.00014348981399468555, | |
| "loss": 0.9607, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.00014216120460584588, | |
| "loss": 0.9528, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.00014083259521700619, | |
| "loss": 0.9469, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.00013950398582816652, | |
| "loss": 0.9415, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00013817537643932682, | |
| "loss": 0.9628, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.00013684676705048713, | |
| "loss": 0.9562, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.00013551815766164746, | |
| "loss": 0.9579, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.00013418954827280777, | |
| "loss": 0.9578, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0001328609388839681, | |
| "loss": 0.9508, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.0001315323294951284, | |
| "loss": 0.9596, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.00013020372010628874, | |
| "loss": 0.9446, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.00012887511071744907, | |
| "loss": 0.9418, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.00012754650132860938, | |
| "loss": 0.9447, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "eval_loss": 0.9596577286720276, | |
| "eval_runtime": 78.8874, | |
| "eval_samples_per_second": 25.353, | |
| "eval_steps_per_second": 0.799, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.0001262178919397697, | |
| "loss": 0.9597, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.00012488928255093002, | |
| "loss": 0.9601, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.00012356067316209035, | |
| "loss": 0.9794, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.00012223206377325066, | |
| "loss": 0.9295, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.00012090345438441097, | |
| "loss": 0.9418, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.00011957484499557128, | |
| "loss": 0.941, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.0001182462356067316, | |
| "loss": 0.9504, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.00011691762621789192, | |
| "loss": 0.9489, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.00011558901682905224, | |
| "loss": 0.9482, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.00011426040744021257, | |
| "loss": 0.9435, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.00011293179805137289, | |
| "loss": 0.953, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.00011160318866253321, | |
| "loss": 0.9468, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.00011027457927369353, | |
| "loss": 0.9289, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.00010894596988485385, | |
| "loss": 0.9533, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.00010761736049601417, | |
| "loss": 0.9591, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.00010628875110717449, | |
| "loss": 0.951, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0001049601417183348, | |
| "loss": 0.9171, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 0.00010363153232949512, | |
| "loss": 0.9375, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.00010230292294065544, | |
| "loss": 0.9568, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 0.00010097431355181575, | |
| "loss": 0.9633, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_loss": 0.9573116302490234, | |
| "eval_runtime": 79.0309, | |
| "eval_samples_per_second": 25.307, | |
| "eval_steps_per_second": 0.797, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 9.964570416297607e-05, | |
| "loss": 0.9424, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 9.831709477413639e-05, | |
| "loss": 0.9243, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 9.698848538529671e-05, | |
| "loss": 0.9415, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 9.565987599645703e-05, | |
| "loss": 0.9434, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 9.433126660761735e-05, | |
| "loss": 0.9467, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 9.300265721877767e-05, | |
| "loss": 0.9516, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 9.167404782993798e-05, | |
| "loss": 0.9617, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 9.034543844109832e-05, | |
| "loss": 0.9379, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 8.901682905225864e-05, | |
| "loss": 0.9455, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 8.768821966341896e-05, | |
| "loss": 0.9477, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 8.635961027457928e-05, | |
| "loss": 0.9448, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 8.50310008857396e-05, | |
| "loss": 0.9361, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 8.370239149689991e-05, | |
| "loss": 0.922, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 8.237378210806022e-05, | |
| "loss": 0.9442, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 8.104517271922054e-05, | |
| "loss": 0.9575, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 7.971656333038086e-05, | |
| "loss": 0.929, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 7.838795394154118e-05, | |
| "loss": 0.9312, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 7.70593445527015e-05, | |
| "loss": 0.943, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 7.573073516386182e-05, | |
| "loss": 0.9416, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 7.440212577502214e-05, | |
| "loss": 0.9455, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "eval_loss": 0.9558648467063904, | |
| "eval_runtime": 79.0765, | |
| "eval_samples_per_second": 25.292, | |
| "eval_steps_per_second": 0.797, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 7.307351638618245e-05, | |
| "loss": 0.9307, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 7.174490699734277e-05, | |
| "loss": 0.9517, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 7.041629760850309e-05, | |
| "loss": 0.9298, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 6.908768821966341e-05, | |
| "loss": 0.936, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 6.775907883082373e-05, | |
| "loss": 0.944, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 6.643046944198405e-05, | |
| "loss": 0.9521, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 6.510186005314437e-05, | |
| "loss": 0.9579, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 6.377325066430469e-05, | |
| "loss": 0.9412, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 6.244464127546501e-05, | |
| "loss": 0.9268, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 6.111603188662533e-05, | |
| "loss": 0.9343, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 5.978742249778564e-05, | |
| "loss": 0.9517, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 5.845881310894596e-05, | |
| "loss": 0.944, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 5.7130203720106285e-05, | |
| "loss": 0.9384, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 5.5801594331266605e-05, | |
| "loss": 0.9462, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 5.4472984942426924e-05, | |
| "loss": 0.9317, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 5.314437555358724e-05, | |
| "loss": 0.9354, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 5.181576616474756e-05, | |
| "loss": 0.9261, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 5.0487156775907875e-05, | |
| "loss": 0.9317, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 4.9158547387068194e-05, | |
| "loss": 0.932, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 4.7829937998228513e-05, | |
| "loss": 0.9323, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "eval_loss": 0.9545624852180481, | |
| "eval_runtime": 78.9727, | |
| "eval_samples_per_second": 25.325, | |
| "eval_steps_per_second": 0.798, | |
| "step": 2000 | |
| } | |
| ], | |
| "max_steps": 2358, | |
| "num_train_epochs": 3, | |
| "total_flos": 6.572646890393829e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |