| { | |
| "best_metric": 0.01938004605472088, | |
| "best_model_checkpoint": "runs/deepseek_lora_/home/mac/air2/runs/deepseek_lora_20240422-141601/checkpoint-30000_20240423-210253/checkpoint-2000", | |
| "epoch": 1.5664160401002505, | |
| "eval_steps": 500, | |
| "global_step": 5000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 1.4201024770736694, | |
| "learning_rate": 4.0000000000000003e-07, | |
| "loss": 1.4508, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 1.6313552856445312, | |
| "learning_rate": 8.000000000000001e-07, | |
| "loss": 1.4463, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 1.2772644758224487, | |
| "learning_rate": 1.2000000000000002e-06, | |
| "loss": 1.4462, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 1.3495179414749146, | |
| "learning_rate": 1.6000000000000001e-06, | |
| "loss": 1.463, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 1.3023079633712769, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.4931, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 1.2231166362762451, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 1.4886, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 1.5659693479537964, | |
| "learning_rate": 2.8000000000000003e-06, | |
| "loss": 1.4963, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 1.8523041009902954, | |
| "learning_rate": 3.2000000000000003e-06, | |
| "loss": 1.3668, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 1.399263620376587, | |
| "learning_rate": 3.6000000000000003e-06, | |
| "loss": 1.296, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 1.6715140342712402, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.2411, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 1.1111788749694824, | |
| "learning_rate": 4.4e-06, | |
| "loss": 1.0886, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.9370793104171753, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 1.0653, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 1.3835300207138062, | |
| "learning_rate": 5.2e-06, | |
| "loss": 0.8878, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 1.646286129951477, | |
| "learning_rate": 5.600000000000001e-06, | |
| "loss": 0.7921, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 1.2522785663604736, | |
| "learning_rate": 6e-06, | |
| "loss": 0.7373, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.9030014872550964, | |
| "learning_rate": 6.4000000000000006e-06, | |
| "loss": 0.5454, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.8196408152580261, | |
| "learning_rate": 6.800000000000001e-06, | |
| "loss": 0.4356, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.4333338141441345, | |
| "learning_rate": 7.2000000000000005e-06, | |
| "loss": 0.3329, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.37946629524230957, | |
| "learning_rate": 7.600000000000001e-06, | |
| "loss": 0.2524, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 1.2624123096466064, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.1601, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.7884108424186707, | |
| "learning_rate": 8.400000000000001e-06, | |
| "loss": 0.1937, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.46105730533599854, | |
| "learning_rate": 8.8e-06, | |
| "loss": 0.0807, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.6495872735977173, | |
| "learning_rate": 9.200000000000002e-06, | |
| "loss": 0.1566, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.9866824150085449, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 0.2515, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.31797927618026733, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0861, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.07518763095140457, | |
| "learning_rate": 1.04e-05, | |
| "loss": 0.0498, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.23027415573596954, | |
| "learning_rate": 1.0800000000000002e-05, | |
| "loss": 0.0473, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.22770297527313232, | |
| "learning_rate": 1.1200000000000001e-05, | |
| "loss": 0.0469, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.22862806916236877, | |
| "learning_rate": 1.16e-05, | |
| "loss": 0.0974, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.3330214023590088, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.0597, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.966628909111023, | |
| "learning_rate": 1.2400000000000002e-05, | |
| "loss": 0.0315, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.022704431787133217, | |
| "learning_rate": 1.2800000000000001e-05, | |
| "loss": 0.042, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.216924786567688, | |
| "learning_rate": 1.3200000000000002e-05, | |
| "loss": 0.0353, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.6081690192222595, | |
| "learning_rate": 1.3600000000000002e-05, | |
| "loss": 0.0247, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.012569287791848183, | |
| "learning_rate": 1.4e-05, | |
| "loss": 0.0251, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.010333358310163021, | |
| "learning_rate": 1.4400000000000001e-05, | |
| "loss": 0.0236, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.37758347392082214, | |
| "learning_rate": 1.48e-05, | |
| "loss": 0.0268, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.015816116705536842, | |
| "learning_rate": 1.5200000000000002e-05, | |
| "loss": 0.0107, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.025576846674084663, | |
| "learning_rate": 1.5600000000000003e-05, | |
| "loss": 0.0213, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.31375065445899963, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.0177, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.008338396437466145, | |
| "learning_rate": 1.64e-05, | |
| "loss": 0.023, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.24885450303554535, | |
| "learning_rate": 1.6800000000000002e-05, | |
| "loss": 0.013, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.0110774552449584, | |
| "learning_rate": 1.72e-05, | |
| "loss": 0.0397, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.006729575805366039, | |
| "learning_rate": 1.76e-05, | |
| "loss": 0.0155, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.01409532967954874, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.0198, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.3871189057826996, | |
| "learning_rate": 1.8400000000000003e-05, | |
| "loss": 0.0212, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.006107095163315535, | |
| "learning_rate": 1.88e-05, | |
| "loss": 0.07, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.010062485933303833, | |
| "learning_rate": 1.9200000000000003e-05, | |
| "loss": 0.0157, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.1705617755651474, | |
| "learning_rate": 1.9600000000000002e-05, | |
| "loss": 0.0241, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.5236091613769531, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0208, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 0.04813479632139206, | |
| "eval_runtime": 105.8284, | |
| "eval_samples_per_second": 9.449, | |
| "eval_steps_per_second": 9.449, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.007713190745562315, | |
| "learning_rate": 1.9955555555555557e-05, | |
| "loss": 0.007, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.028844956308603287, | |
| "learning_rate": 1.9911111111111112e-05, | |
| "loss": 0.018, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.004528562072664499, | |
| "learning_rate": 1.9866666666666667e-05, | |
| "loss": 0.0519, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.5867981910705566, | |
| "learning_rate": 1.9822222222222226e-05, | |
| "loss": 0.0193, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.08260989189147949, | |
| "learning_rate": 1.977777777777778e-05, | |
| "loss": 0.0359, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.005006667226552963, | |
| "learning_rate": 1.9733333333333336e-05, | |
| "loss": 0.0187, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.017591852694749832, | |
| "learning_rate": 1.968888888888889e-05, | |
| "loss": 0.0143, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.8018626570701599, | |
| "learning_rate": 1.9644444444444447e-05, | |
| "loss": 0.0161, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.005714430473744869, | |
| "learning_rate": 1.9600000000000002e-05, | |
| "loss": 0.0159, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.006446035113185644, | |
| "learning_rate": 1.9555555555555557e-05, | |
| "loss": 0.0249, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.00910472497344017, | |
| "learning_rate": 1.9511111111111113e-05, | |
| "loss": 0.009, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.0680340826511383, | |
| "learning_rate": 1.9466666666666668e-05, | |
| "loss": 0.01, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.009966106154024601, | |
| "learning_rate": 1.9422222222222223e-05, | |
| "loss": 0.0189, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.004922552965581417, | |
| "learning_rate": 1.9377777777777778e-05, | |
| "loss": 0.0189, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.0045297518372535706, | |
| "learning_rate": 1.9333333333333333e-05, | |
| "loss": 0.0636, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.17961235344409943, | |
| "learning_rate": 1.928888888888889e-05, | |
| "loss": 0.0077, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.010727491229772568, | |
| "learning_rate": 1.9244444444444444e-05, | |
| "loss": 0.0338, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.14529484510421753, | |
| "learning_rate": 1.9200000000000003e-05, | |
| "loss": 0.0162, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.011789410375058651, | |
| "learning_rate": 1.9155555555555558e-05, | |
| "loss": 0.0371, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.03757067024707794, | |
| "learning_rate": 1.9111111111111113e-05, | |
| "loss": 0.0082, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.11487198621034622, | |
| "learning_rate": 1.9066666666666668e-05, | |
| "loss": 0.0039, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.005442380905151367, | |
| "learning_rate": 1.9022222222222223e-05, | |
| "loss": 0.0108, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.005606868304312229, | |
| "learning_rate": 1.897777777777778e-05, | |
| "loss": 0.0016, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.00637522479519248, | |
| "learning_rate": 1.8933333333333334e-05, | |
| "loss": 0.0268, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.1989319920539856, | |
| "learning_rate": 1.888888888888889e-05, | |
| "loss": 0.0227, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.13159094750881195, | |
| "learning_rate": 1.8844444444444444e-05, | |
| "loss": 0.0313, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 3.0459349155426025, | |
| "learning_rate": 1.88e-05, | |
| "loss": 0.0201, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 1.1915451288223267, | |
| "learning_rate": 1.8755555555555558e-05, | |
| "loss": 0.0245, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.013696914538741112, | |
| "learning_rate": 1.8711111111111113e-05, | |
| "loss": 0.0018, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 1.1634104251861572, | |
| "learning_rate": 1.866666666666667e-05, | |
| "loss": 0.026, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.007169550750404596, | |
| "learning_rate": 1.8622222222222224e-05, | |
| "loss": 0.0071, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.004371534567326307, | |
| "learning_rate": 1.857777777777778e-05, | |
| "loss": 0.0153, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.020073844119906425, | |
| "learning_rate": 1.8533333333333334e-05, | |
| "loss": 0.0096, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.008414236828684807, | |
| "learning_rate": 1.848888888888889e-05, | |
| "loss": 0.007, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.003889534855261445, | |
| "learning_rate": 1.8444444444444448e-05, | |
| "loss": 0.002, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.002301928121596575, | |
| "learning_rate": 1.8400000000000003e-05, | |
| "loss": 0.0025, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.002069896785542369, | |
| "learning_rate": 1.835555555555556e-05, | |
| "loss": 0.0147, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.0038117747753858566, | |
| "learning_rate": 1.8311111111111114e-05, | |
| "loss": 0.0414, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.007180278189480305, | |
| "learning_rate": 1.826666666666667e-05, | |
| "loss": 0.0007, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.722541332244873, | |
| "learning_rate": 1.8222222222222224e-05, | |
| "loss": 0.0173, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.021056558936834335, | |
| "learning_rate": 1.817777777777778e-05, | |
| "loss": 0.0111, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.009726395830512047, | |
| "learning_rate": 1.8133333333333335e-05, | |
| "loss": 0.0045, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.00808757171034813, | |
| "learning_rate": 1.808888888888889e-05, | |
| "loss": 0.0021, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.3323584794998169, | |
| "learning_rate": 1.8044444444444445e-05, | |
| "loss": 0.0052, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.45399293303489685, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.0095, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.43379417061805725, | |
| "learning_rate": 1.7955555555555556e-05, | |
| "loss": 0.0401, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.7372444868087769, | |
| "learning_rate": 1.791111111111111e-05, | |
| "loss": 0.0184, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.013180572539567947, | |
| "learning_rate": 1.7866666666666666e-05, | |
| "loss": 0.0116, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.008782428689301014, | |
| "learning_rate": 1.782222222222222e-05, | |
| "loss": 0.0223, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.011336304247379303, | |
| "learning_rate": 1.7777777777777777e-05, | |
| "loss": 0.0026, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 0.02973618172109127, | |
| "eval_runtime": 105.7708, | |
| "eval_samples_per_second": 9.454, | |
| "eval_steps_per_second": 9.454, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.0016499263001605868, | |
| "learning_rate": 1.7733333333333335e-05, | |
| "loss": 0.0055, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.005521496757864952, | |
| "learning_rate": 1.768888888888889e-05, | |
| "loss": 0.0103, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.011227923445403576, | |
| "learning_rate": 1.7644444444444446e-05, | |
| "loss": 0.0271, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.1072327122092247, | |
| "learning_rate": 1.76e-05, | |
| "loss": 0.0061, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.1942812204360962, | |
| "learning_rate": 1.7555555555555556e-05, | |
| "loss": 0.0068, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.0058549391105771065, | |
| "learning_rate": 1.751111111111111e-05, | |
| "loss": 0.0056, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.003338587237522006, | |
| "learning_rate": 1.7466666666666667e-05, | |
| "loss": 0.004, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.0738811194896698, | |
| "learning_rate": 1.7422222222222222e-05, | |
| "loss": 0.0446, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.03248901665210724, | |
| "learning_rate": 1.737777777777778e-05, | |
| "loss": 0.0159, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.005992035381495953, | |
| "learning_rate": 1.7333333333333336e-05, | |
| "loss": 0.018, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.12098544836044312, | |
| "learning_rate": 1.728888888888889e-05, | |
| "loss": 0.0293, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.007133137434720993, | |
| "learning_rate": 1.7244444444444446e-05, | |
| "loss": 0.008, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.17562967538833618, | |
| "learning_rate": 1.72e-05, | |
| "loss": 0.0133, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.6992379426956177, | |
| "learning_rate": 1.7155555555555557e-05, | |
| "loss": 0.0144, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.004463555756956339, | |
| "learning_rate": 1.7111111111111112e-05, | |
| "loss": 0.0506, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.0051247915253043175, | |
| "learning_rate": 1.706666666666667e-05, | |
| "loss": 0.0084, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 0.007146921940147877, | |
| "learning_rate": 1.7022222222222226e-05, | |
| "loss": 0.0048, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 0.0036419702228158712, | |
| "learning_rate": 1.697777777777778e-05, | |
| "loss": 0.0039, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 0.043528199195861816, | |
| "learning_rate": 1.6933333333333336e-05, | |
| "loss": 0.0126, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.004960165359079838, | |
| "learning_rate": 1.688888888888889e-05, | |
| "loss": 0.0371, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.4058115780353546, | |
| "learning_rate": 1.6844444444444447e-05, | |
| "loss": 0.0022, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.19414691627025604, | |
| "learning_rate": 1.6800000000000002e-05, | |
| "loss": 0.001, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.005380582995712757, | |
| "learning_rate": 1.6755555555555557e-05, | |
| "loss": 0.014, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.004692175891250372, | |
| "learning_rate": 1.6711111111111112e-05, | |
| "loss": 0.0046, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.002111697569489479, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0015, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.004453285597264767, | |
| "learning_rate": 1.6622222222222223e-05, | |
| "loss": 0.018, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.5204005241394043, | |
| "learning_rate": 1.6577777777777778e-05, | |
| "loss": 0.0041, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.002364647574722767, | |
| "learning_rate": 1.6533333333333333e-05, | |
| "loss": 0.0026, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.012862365692853928, | |
| "learning_rate": 1.648888888888889e-05, | |
| "loss": 0.0188, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.007581356912851334, | |
| "learning_rate": 1.6444444444444444e-05, | |
| "loss": 0.0073, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.21286563575267792, | |
| "learning_rate": 1.64e-05, | |
| "loss": 0.0054, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.003324658377096057, | |
| "learning_rate": 1.6355555555555557e-05, | |
| "loss": 0.0116, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.37529128789901733, | |
| "learning_rate": 1.6311111111111113e-05, | |
| "loss": 0.0055, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.10134778171777725, | |
| "learning_rate": 1.6266666666666668e-05, | |
| "loss": 0.0123, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.002546050352975726, | |
| "learning_rate": 1.6222222222222223e-05, | |
| "loss": 0.0004, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.11726546287536621, | |
| "learning_rate": 1.617777777777778e-05, | |
| "loss": 0.0725, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.0032152272760868073, | |
| "learning_rate": 1.6133333333333334e-05, | |
| "loss": 0.0065, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.14680413901805878, | |
| "learning_rate": 1.608888888888889e-05, | |
| "loss": 0.0137, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.004721660166978836, | |
| "learning_rate": 1.6044444444444444e-05, | |
| "loss": 0.0065, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.003223953302949667, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.006, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.0024323295801877975, | |
| "learning_rate": 1.5955555555555558e-05, | |
| "loss": 0.0005, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.08590155094861984, | |
| "learning_rate": 1.5911111111111113e-05, | |
| "loss": 0.04, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.12949270009994507, | |
| "learning_rate": 1.586666666666667e-05, | |
| "loss": 0.0012, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.17392052710056305, | |
| "learning_rate": 1.5822222222222224e-05, | |
| "loss": 0.0171, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.3131588399410248, | |
| "learning_rate": 1.577777777777778e-05, | |
| "loss": 0.015, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.04804832488298416, | |
| "learning_rate": 1.5733333333333334e-05, | |
| "loss": 0.0027, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.0027218549512326717, | |
| "learning_rate": 1.5688888888888893e-05, | |
| "loss": 0.0023, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.5712968111038208, | |
| "learning_rate": 1.5644444444444448e-05, | |
| "loss": 0.0161, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.005681733135133982, | |
| "learning_rate": 1.5600000000000003e-05, | |
| "loss": 0.0078, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.29326629638671875, | |
| "learning_rate": 1.555555555555556e-05, | |
| "loss": 0.0069, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 0.02430753782391548, | |
| "eval_runtime": 105.8642, | |
| "eval_samples_per_second": 9.446, | |
| "eval_steps_per_second": 9.446, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.007336648181080818, | |
| "learning_rate": 1.5511111111111114e-05, | |
| "loss": 0.0126, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.13389843702316284, | |
| "learning_rate": 1.546666666666667e-05, | |
| "loss": 0.0041, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.006098288577049971, | |
| "learning_rate": 1.5422222222222224e-05, | |
| "loss": 0.0256, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.0023613509256392717, | |
| "learning_rate": 1.537777777777778e-05, | |
| "loss": 0.0226, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.011803489178419113, | |
| "learning_rate": 1.5333333333333334e-05, | |
| "loss": 0.0223, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.08194795995950699, | |
| "learning_rate": 1.528888888888889e-05, | |
| "loss": 0.0024, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.0029789546970278025, | |
| "learning_rate": 1.5244444444444447e-05, | |
| "loss": 0.0026, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.001265739556401968, | |
| "learning_rate": 1.5200000000000002e-05, | |
| "loss": 0.0268, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.012406809255480766, | |
| "learning_rate": 1.5155555555555557e-05, | |
| "loss": 0.0067, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.6606098413467407, | |
| "learning_rate": 1.5111111111111112e-05, | |
| "loss": 0.0189, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.014978533610701561, | |
| "learning_rate": 1.5066666666666668e-05, | |
| "loss": 0.0176, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.08984213322401047, | |
| "learning_rate": 1.5022222222222223e-05, | |
| "loss": 0.008, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.0033486252650618553, | |
| "learning_rate": 1.497777777777778e-05, | |
| "loss": 0.0112, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.002099987817928195, | |
| "learning_rate": 1.4933333333333335e-05, | |
| "loss": 0.0258, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.3023240268230438, | |
| "learning_rate": 1.488888888888889e-05, | |
| "loss": 0.0056, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.8300777077674866, | |
| "learning_rate": 1.4844444444444445e-05, | |
| "loss": 0.0258, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.0023328212555497885, | |
| "learning_rate": 1.48e-05, | |
| "loss": 0.0021, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.3725988566875458, | |
| "learning_rate": 1.4755555555555556e-05, | |
| "loss": 0.0086, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.14515481889247894, | |
| "learning_rate": 1.4711111111111111e-05, | |
| "loss": 0.0054, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.0050906166434288025, | |
| "learning_rate": 1.4666666666666666e-05, | |
| "loss": 0.0097, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.6300042271614075, | |
| "learning_rate": 1.4622222222222225e-05, | |
| "loss": 0.0121, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.010772451758384705, | |
| "learning_rate": 1.457777777777778e-05, | |
| "loss": 0.0162, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.05193562060594559, | |
| "learning_rate": 1.4533333333333335e-05, | |
| "loss": 0.014, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.3744001090526581, | |
| "learning_rate": 1.448888888888889e-05, | |
| "loss": 0.0055, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.07020632922649384, | |
| "learning_rate": 1.4444444444444446e-05, | |
| "loss": 0.0025, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.002155319321900606, | |
| "learning_rate": 1.4400000000000001e-05, | |
| "loss": 0.0002, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.0031439345329999924, | |
| "learning_rate": 1.4355555555555556e-05, | |
| "loss": 0.0102, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.33559954166412354, | |
| "learning_rate": 1.4311111111111111e-05, | |
| "loss": 0.0106, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.09780018031597137, | |
| "learning_rate": 1.4266666666666668e-05, | |
| "loss": 0.0006, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.21637512743473053, | |
| "learning_rate": 1.4222222222222224e-05, | |
| "loss": 0.0081, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.19896027445793152, | |
| "learning_rate": 1.4177777777777779e-05, | |
| "loss": 0.002, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.46836480498313904, | |
| "learning_rate": 1.4133333333333334e-05, | |
| "loss": 0.01, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.0012917339336127043, | |
| "learning_rate": 1.408888888888889e-05, | |
| "loss": 0.0007, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.0009248697315342724, | |
| "learning_rate": 1.4044444444444445e-05, | |
| "loss": 0.0065, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.0015130062820389867, | |
| "learning_rate": 1.4e-05, | |
| "loss": 0.0138, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.015873389318585396, | |
| "learning_rate": 1.3955555555555558e-05, | |
| "loss": 0.0104, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.0025395406410098076, | |
| "learning_rate": 1.3911111111111114e-05, | |
| "loss": 0.0091, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.0019395744893699884, | |
| "learning_rate": 1.3866666666666669e-05, | |
| "loss": 0.0154, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.001661272719502449, | |
| "learning_rate": 1.3822222222222224e-05, | |
| "loss": 0.0069, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.48684021830558777, | |
| "learning_rate": 1.377777777777778e-05, | |
| "loss": 0.0047, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.8865891695022583, | |
| "learning_rate": 1.3733333333333335e-05, | |
| "loss": 0.0181, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.0010564266704022884, | |
| "learning_rate": 1.368888888888889e-05, | |
| "loss": 0.0047, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.10301809757947922, | |
| "learning_rate": 1.3644444444444445e-05, | |
| "loss": 0.0056, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.22648899257183075, | |
| "learning_rate": 1.3600000000000002e-05, | |
| "loss": 0.0013, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.0013131586601957679, | |
| "learning_rate": 1.3555555555555557e-05, | |
| "loss": 0.0048, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.0011880842503160238, | |
| "learning_rate": 1.3511111111111112e-05, | |
| "loss": 0.0101, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.0013722589937970042, | |
| "learning_rate": 1.3466666666666668e-05, | |
| "loss": 0.0028, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.001899394323118031, | |
| "learning_rate": 1.3422222222222223e-05, | |
| "loss": 0.0418, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.0032492605969309807, | |
| "learning_rate": 1.3377777777777778e-05, | |
| "loss": 0.0013, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 0.0010039942571893334, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.0044, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 0.01938004605472088, | |
| "eval_runtime": 106.0395, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 9.43, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 0.001601343508809805, | |
| "learning_rate": 1.3288888888888889e-05, | |
| "loss": 0.0111, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 0.006534218788146973, | |
| "learning_rate": 1.3244444444444447e-05, | |
| "loss": 0.0041, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.11454477906227112, | |
| "learning_rate": 1.3200000000000002e-05, | |
| "loss": 0.0148, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.0012094610137864947, | |
| "learning_rate": 1.3155555555555558e-05, | |
| "loss": 0.0001, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.017126798629760742, | |
| "learning_rate": 1.3111111111111113e-05, | |
| "loss": 0.0035, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.0010203116107732058, | |
| "learning_rate": 1.3066666666666668e-05, | |
| "loss": 0.0185, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.07288641482591629, | |
| "learning_rate": 1.3022222222222223e-05, | |
| "loss": 0.0091, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.0013487342512235045, | |
| "learning_rate": 1.2977777777777779e-05, | |
| "loss": 0.0156, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.28272658586502075, | |
| "learning_rate": 1.2933333333333334e-05, | |
| "loss": 0.0146, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.4402059018611908, | |
| "learning_rate": 1.288888888888889e-05, | |
| "loss": 0.0157, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.00559567753225565, | |
| "learning_rate": 1.2844444444444446e-05, | |
| "loss": 0.0093, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.02444939874112606, | |
| "learning_rate": 1.2800000000000001e-05, | |
| "loss": 0.0065, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.0012545145582407713, | |
| "learning_rate": 1.2755555555555556e-05, | |
| "loss": 0.0057, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.001707903342321515, | |
| "learning_rate": 1.2711111111111112e-05, | |
| "loss": 0.0162, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.0023830528371036053, | |
| "learning_rate": 1.2666666666666667e-05, | |
| "loss": 0.0276, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.0030489948112517595, | |
| "learning_rate": 1.2622222222222222e-05, | |
| "loss": 0.014, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.0017784954980015755, | |
| "learning_rate": 1.257777777777778e-05, | |
| "loss": 0.0206, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.06302628666162491, | |
| "learning_rate": 1.2533333333333336e-05, | |
| "loss": 0.0023, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.0011160870781168342, | |
| "learning_rate": 1.2488888888888891e-05, | |
| "loss": 0.0204, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.0013328393688425422, | |
| "learning_rate": 1.2444444444444446e-05, | |
| "loss": 0.0071, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.0011977130779996514, | |
| "learning_rate": 1.2400000000000002e-05, | |
| "loss": 0.011, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.28556379675865173, | |
| "learning_rate": 1.2355555555555557e-05, | |
| "loss": 0.0032, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.001730318646878004, | |
| "learning_rate": 1.2311111111111112e-05, | |
| "loss": 0.0085, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.7156691551208496, | |
| "learning_rate": 1.2266666666666667e-05, | |
| "loss": 0.0243, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.09367219358682632, | |
| "learning_rate": 1.2222222222222224e-05, | |
| "loss": 0.0108, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.0033970875665545464, | |
| "learning_rate": 1.217777777777778e-05, | |
| "loss": 0.0013, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.13453590869903564, | |
| "learning_rate": 1.2133333333333335e-05, | |
| "loss": 0.0171, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.0015542698092758656, | |
| "learning_rate": 1.208888888888889e-05, | |
| "loss": 0.0082, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.0018359808018431067, | |
| "learning_rate": 1.2044444444444445e-05, | |
| "loss": 0.0035, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.002221127972006798, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.015, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.0010089320130646229, | |
| "learning_rate": 1.1955555555555556e-05, | |
| "loss": 0.012, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.0028728065080940723, | |
| "learning_rate": 1.191111111111111e-05, | |
| "loss": 0.0118, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.001342312665656209, | |
| "learning_rate": 1.186666666666667e-05, | |
| "loss": 0.0153, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.2403033971786499, | |
| "learning_rate": 1.1822222222222225e-05, | |
| "loss": 0.0077, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.04793378338217735, | |
| "learning_rate": 1.177777777777778e-05, | |
| "loss": 0.0129, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.0022574837785214186, | |
| "learning_rate": 1.1733333333333335e-05, | |
| "loss": 0.0073, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.26575639843940735, | |
| "learning_rate": 1.168888888888889e-05, | |
| "loss": 0.0089, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.0020264522172510624, | |
| "learning_rate": 1.1644444444444446e-05, | |
| "loss": 0.0045, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.0012554072309285402, | |
| "learning_rate": 1.16e-05, | |
| "loss": 0.0031, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.0011454842751845717, | |
| "learning_rate": 1.1555555555555556e-05, | |
| "loss": 0.0023, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.20630207657814026, | |
| "learning_rate": 1.1511111111111113e-05, | |
| "loss": 0.0023, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.0007169468444772065, | |
| "learning_rate": 1.1466666666666668e-05, | |
| "loss": 0.0121, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.0023526553995907307, | |
| "learning_rate": 1.1422222222222223e-05, | |
| "loss": 0.0052, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.39723196625709534, | |
| "learning_rate": 1.1377777777777779e-05, | |
| "loss": 0.0211, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.4188237190246582, | |
| "learning_rate": 1.1333333333333334e-05, | |
| "loss": 0.0107, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.8699719905853271, | |
| "learning_rate": 1.1288888888888889e-05, | |
| "loss": 0.0065, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.030738549306988716, | |
| "learning_rate": 1.1244444444444444e-05, | |
| "loss": 0.0136, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.000931159476749599, | |
| "learning_rate": 1.1200000000000001e-05, | |
| "loss": 0.0227, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.0705338716506958, | |
| "learning_rate": 1.1155555555555556e-05, | |
| "loss": 0.0027, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.0007929333951324224, | |
| "learning_rate": 1.1111111111111113e-05, | |
| "loss": 0.0133, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 0.020793654024600983, | |
| "eval_runtime": 105.636, | |
| "eval_samples_per_second": 9.466, | |
| "eval_steps_per_second": 9.466, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.0016222142148762941, | |
| "learning_rate": 1.1066666666666669e-05, | |
| "loss": 0.0435, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.002197889843955636, | |
| "learning_rate": 1.1022222222222224e-05, | |
| "loss": 0.002, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.33299392461776733, | |
| "learning_rate": 1.0977777777777779e-05, | |
| "loss": 0.0326, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.0010998391080647707, | |
| "learning_rate": 1.0933333333333334e-05, | |
| "loss": 0.0001, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.0011729354737326503, | |
| "learning_rate": 1.088888888888889e-05, | |
| "loss": 0.001, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.000858838262502104, | |
| "learning_rate": 1.0844444444444446e-05, | |
| "loss": 0.0037, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.38744401931762695, | |
| "learning_rate": 1.0800000000000002e-05, | |
| "loss": 0.0065, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.2493005245923996, | |
| "learning_rate": 1.0755555555555557e-05, | |
| "loss": 0.0043, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.20194557309150696, | |
| "learning_rate": 1.0711111111111112e-05, | |
| "loss": 0.0115, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.0024039980489760637, | |
| "learning_rate": 1.0666666666666667e-05, | |
| "loss": 0.0084, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.0008128687040880322, | |
| "learning_rate": 1.0622222222222223e-05, | |
| "loss": 0.0061, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.0018899840069934726, | |
| "learning_rate": 1.0577777777777778e-05, | |
| "loss": 0.007, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.01610325276851654, | |
| "learning_rate": 1.0533333333333333e-05, | |
| "loss": 0.007, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 0.0006350704934448004, | |
| "learning_rate": 1.048888888888889e-05, | |
| "loss": 0.0066, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 0.09355136752128601, | |
| "learning_rate": 1.0444444444444445e-05, | |
| "loss": 0.0255, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 0.3234637975692749, | |
| "learning_rate": 1.04e-05, | |
| "loss": 0.0076, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.05527418851852417, | |
| "learning_rate": 1.0355555555555557e-05, | |
| "loss": 0.0012, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.0009735400672070682, | |
| "learning_rate": 1.0311111111111113e-05, | |
| "loss": 0.0045, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.0008769531850703061, | |
| "learning_rate": 1.0266666666666668e-05, | |
| "loss": 0.0172, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 0.006668600253760815, | |
| "learning_rate": 1.0222222222222223e-05, | |
| "loss": 0.0012, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 0.07360995560884476, | |
| "learning_rate": 1.0177777777777778e-05, | |
| "loss": 0.0145, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 0.08141136914491653, | |
| "learning_rate": 1.0133333333333335e-05, | |
| "loss": 0.0039, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.027105676010251045, | |
| "learning_rate": 1.008888888888889e-05, | |
| "loss": 0.0035, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.0010070588905364275, | |
| "learning_rate": 1.0044444444444446e-05, | |
| "loss": 0.0011, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.007085401564836502, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0096, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.0018968915101140738, | |
| "learning_rate": 9.955555555555556e-06, | |
| "loss": 0.0057, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 0.0006910761003382504, | |
| "learning_rate": 9.911111111111113e-06, | |
| "loss": 0.007, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 0.0008984303567558527, | |
| "learning_rate": 9.866666666666668e-06, | |
| "loss": 0.02, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 0.0017594619421288371, | |
| "learning_rate": 9.822222222222223e-06, | |
| "loss": 0.0037, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.0012592363636940718, | |
| "learning_rate": 9.777777777777779e-06, | |
| "loss": 0.0058, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.0005507588502950966, | |
| "learning_rate": 9.733333333333334e-06, | |
| "loss": 0.0152, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.09182553738355637, | |
| "learning_rate": 9.688888888888889e-06, | |
| "loss": 0.02, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.08707510679960251, | |
| "learning_rate": 9.644444444444444e-06, | |
| "loss": 0.0076, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.20231454074382782, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 0.0104, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.011587344110012054, | |
| "learning_rate": 9.555555555555556e-06, | |
| "loss": 0.0034, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.001095921266824007, | |
| "learning_rate": 9.511111111111112e-06, | |
| "loss": 0.0096, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.0018781009130179882, | |
| "learning_rate": 9.466666666666667e-06, | |
| "loss": 0.0121, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.0017853602766990662, | |
| "learning_rate": 9.422222222222222e-06, | |
| "loss": 0.0033, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 0.0022252665366977453, | |
| "learning_rate": 9.377777777777779e-06, | |
| "loss": 0.0172, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 0.02110256254673004, | |
| "learning_rate": 9.333333333333334e-06, | |
| "loss": 0.0084, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 0.0018381946720182896, | |
| "learning_rate": 9.28888888888889e-06, | |
| "loss": 0.0155, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 0.0018717021448537707, | |
| "learning_rate": 9.244444444444445e-06, | |
| "loss": 0.0037, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.003086686599999666, | |
| "learning_rate": 9.200000000000002e-06, | |
| "loss": 0.0039, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.0013741503935307264, | |
| "learning_rate": 9.155555555555557e-06, | |
| "loss": 0.005, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.0013554570032283664, | |
| "learning_rate": 9.111111111111112e-06, | |
| "loss": 0.0013, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 0.0009741095709614456, | |
| "learning_rate": 9.066666666666667e-06, | |
| "loss": 0.0053, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 0.3708273768424988, | |
| "learning_rate": 9.022222222222223e-06, | |
| "loss": 0.0085, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 0.0005603479221463203, | |
| "learning_rate": 8.977777777777778e-06, | |
| "loss": 0.0008, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.0005208374932408333, | |
| "learning_rate": 8.933333333333333e-06, | |
| "loss": 0.0037, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.0006605735397897661, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 0.0079, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 0.024190960451960564, | |
| "eval_runtime": 106.0996, | |
| "eval_samples_per_second": 9.425, | |
| "eval_steps_per_second": 9.425, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.6728457808494568, | |
| "learning_rate": 8.844444444444445e-06, | |
| "loss": 0.0112, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 0.0006901975139044225, | |
| "learning_rate": 8.8e-06, | |
| "loss": 0.0048, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 0.0037365430034697056, | |
| "learning_rate": 8.755555555555556e-06, | |
| "loss": 0.0015, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 0.16512754559516907, | |
| "learning_rate": 8.711111111111111e-06, | |
| "loss": 0.0159, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.0016021672636270523, | |
| "learning_rate": 8.666666666666668e-06, | |
| "loss": 0.006, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.002898729406297207, | |
| "learning_rate": 8.622222222222223e-06, | |
| "loss": 0.0099, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.2749406397342682, | |
| "learning_rate": 8.577777777777778e-06, | |
| "loss": 0.0058, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.0005188034847378731, | |
| "learning_rate": 8.533333333333335e-06, | |
| "loss": 0.0052, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 0.2788861095905304, | |
| "learning_rate": 8.48888888888889e-06, | |
| "loss": 0.0022, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 0.00042978368583135307, | |
| "learning_rate": 8.444444444444446e-06, | |
| "loss": 0.0157, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 0.0011739007895812392, | |
| "learning_rate": 8.400000000000001e-06, | |
| "loss": 0.026, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.008115693926811218, | |
| "learning_rate": 8.355555555555556e-06, | |
| "loss": 0.0035, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.001202278072014451, | |
| "learning_rate": 8.311111111111111e-06, | |
| "loss": 0.0202, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.000537244020961225, | |
| "learning_rate": 8.266666666666667e-06, | |
| "loss": 0.0122, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 0.21055370569229126, | |
| "learning_rate": 8.222222222222222e-06, | |
| "loss": 0.0017, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 0.0015918203862383962, | |
| "learning_rate": 8.177777777777779e-06, | |
| "loss": 0.0069, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 0.0006304767448455095, | |
| "learning_rate": 8.133333333333334e-06, | |
| "loss": 0.0018, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.00048176213749684393, | |
| "learning_rate": 8.08888888888889e-06, | |
| "loss": 0.0085, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.0005605188198387623, | |
| "learning_rate": 8.044444444444444e-06, | |
| "loss": 0.0041, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.407652884721756, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.005, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 0.043511051684617996, | |
| "learning_rate": 7.955555555555557e-06, | |
| "loss": 0.0016, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 0.07123250514268875, | |
| "learning_rate": 7.911111111111112e-06, | |
| "loss": 0.0187, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 0.0005245661013759673, | |
| "learning_rate": 7.866666666666667e-06, | |
| "loss": 0.0039, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.07147853076457977, | |
| "learning_rate": 7.822222222222224e-06, | |
| "loss": 0.0014, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.0022907687816768885, | |
| "learning_rate": 7.77777777777778e-06, | |
| "loss": 0.0029, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.0005335509194992483, | |
| "learning_rate": 7.733333333333334e-06, | |
| "loss": 0.0022, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 0.5879516005516052, | |
| "learning_rate": 7.68888888888889e-06, | |
| "loss": 0.0114, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 0.0005007328581996262, | |
| "learning_rate": 7.644444444444445e-06, | |
| "loss": 0.0008, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 0.000808278564363718, | |
| "learning_rate": 7.600000000000001e-06, | |
| "loss": 0.0003, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 0.0009639998315833509, | |
| "learning_rate": 7.555555555555556e-06, | |
| "loss": 0.0043, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 0.21140816807746887, | |
| "learning_rate": 7.511111111111111e-06, | |
| "loss": 0.0063, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 0.07628853619098663, | |
| "learning_rate": 7.4666666666666675e-06, | |
| "loss": 0.0055, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 0.3622307777404785, | |
| "learning_rate": 7.422222222222223e-06, | |
| "loss": 0.0544, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 0.11922428011894226, | |
| "learning_rate": 7.377777777777778e-06, | |
| "loss": 0.0042, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 0.005126808770000935, | |
| "learning_rate": 7.333333333333333e-06, | |
| "loss": 0.0034, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 0.0009374683722853661, | |
| "learning_rate": 7.28888888888889e-06, | |
| "loss": 0.0055, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 0.0010315098334103823, | |
| "learning_rate": 7.244444444444445e-06, | |
| "loss": 0.0068, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 0.0023387514520436525, | |
| "learning_rate": 7.2000000000000005e-06, | |
| "loss": 0.0165, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 0.5151880979537964, | |
| "learning_rate": 7.155555555555556e-06, | |
| "loss": 0.0019, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 0.0006280681700445712, | |
| "learning_rate": 7.111111111111112e-06, | |
| "loss": 0.0016, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 0.05279850959777832, | |
| "learning_rate": 7.066666666666667e-06, | |
| "loss": 0.0027, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 0.0003787504101637751, | |
| "learning_rate": 7.022222222222222e-06, | |
| "loss": 0.0026, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 0.0009172603604383767, | |
| "learning_rate": 6.977777777777779e-06, | |
| "loss": 0.0055, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 0.0016954115126281977, | |
| "learning_rate": 6.9333333333333344e-06, | |
| "loss": 0.0077, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 0.0003665974363684654, | |
| "learning_rate": 6.88888888888889e-06, | |
| "loss": 0.0014, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 0.0005018340889364481, | |
| "learning_rate": 6.844444444444445e-06, | |
| "loss": 0.0079, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 0.00042706538806669414, | |
| "learning_rate": 6.800000000000001e-06, | |
| "loss": 0.0018, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 0.10292913764715195, | |
| "learning_rate": 6.755555555555556e-06, | |
| "loss": 0.0066, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 0.4878827631473541, | |
| "learning_rate": 6.711111111111111e-06, | |
| "loss": 0.0117, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 0.0002568361524026841, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.006, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_loss": 0.02246909774839878, | |
| "eval_runtime": 105.9805, | |
| "eval_samples_per_second": 9.436, | |
| "eval_steps_per_second": 9.436, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 0.0013885730877518654, | |
| "learning_rate": 6.6222222222222236e-06, | |
| "loss": 0.0089, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 0.00039995237602852285, | |
| "learning_rate": 6.577777777777779e-06, | |
| "loss": 0.002, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 0.1092824637889862, | |
| "learning_rate": 6.533333333333334e-06, | |
| "loss": 0.0199, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 0.0009667383274063468, | |
| "learning_rate": 6.488888888888889e-06, | |
| "loss": 0.003, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 0.0005986980977468193, | |
| "learning_rate": 6.444444444444445e-06, | |
| "loss": 0.0011, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.0008668617811053991, | |
| "learning_rate": 6.4000000000000006e-06, | |
| "loss": 0.0072, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.00075616902904585, | |
| "learning_rate": 6.355555555555556e-06, | |
| "loss": 0.0044, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.00048376142513006926, | |
| "learning_rate": 6.311111111111111e-06, | |
| "loss": 0.0023, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.0010572660248726606, | |
| "learning_rate": 6.266666666666668e-06, | |
| "loss": 0.0009, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 0.0005315226735547185, | |
| "learning_rate": 6.222222222222223e-06, | |
| "loss": 0.0006, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 0.0009846779284998775, | |
| "learning_rate": 6.177777777777778e-06, | |
| "loss": 0.0022, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 0.0004815957508981228, | |
| "learning_rate": 6.133333333333334e-06, | |
| "loss": 0.0027, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 0.0925995334982872, | |
| "learning_rate": 6.08888888888889e-06, | |
| "loss": 0.0013, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 0.0006595251616090536, | |
| "learning_rate": 6.044444444444445e-06, | |
| "loss": 0.0039, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 0.0003916506830137223, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0024, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 0.2614765465259552, | |
| "learning_rate": 5.955555555555555e-06, | |
| "loss": 0.0069, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 0.07495523989200592, | |
| "learning_rate": 5.911111111111112e-06, | |
| "loss": 0.0075, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 0.00033707538386806846, | |
| "learning_rate": 5.8666666666666675e-06, | |
| "loss": 0.0036, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 0.47413933277130127, | |
| "learning_rate": 5.822222222222223e-06, | |
| "loss": 0.0205, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 0.3025084435939789, | |
| "learning_rate": 5.777777777777778e-06, | |
| "loss": 0.0041, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 0.0008836881606839597, | |
| "learning_rate": 5.733333333333334e-06, | |
| "loss": 0.0073, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 0.0095978993922472, | |
| "learning_rate": 5.688888888888889e-06, | |
| "loss": 0.0195, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 0.0003117706801276654, | |
| "learning_rate": 5.6444444444444445e-06, | |
| "loss": 0.0029, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 0.00034295892692171037, | |
| "learning_rate": 5.600000000000001e-06, | |
| "loss": 0.0039, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 0.013034949079155922, | |
| "learning_rate": 5.555555555555557e-06, | |
| "loss": 0.0031, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 0.0005166982300579548, | |
| "learning_rate": 5.511111111111112e-06, | |
| "loss": 0.0024, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 0.0005639269948005676, | |
| "learning_rate": 5.466666666666667e-06, | |
| "loss": 0.0162, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 0.0016196731012314558, | |
| "learning_rate": 5.422222222222223e-06, | |
| "loss": 0.0016, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 0.04477536678314209, | |
| "learning_rate": 5.3777777777777784e-06, | |
| "loss": 0.0128, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 0.00038292576209641993, | |
| "learning_rate": 5.333333333333334e-06, | |
| "loss": 0.0027, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 0.000574207108002156, | |
| "learning_rate": 5.288888888888889e-06, | |
| "loss": 0.0011, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.00024517590645700693, | |
| "learning_rate": 5.244444444444445e-06, | |
| "loss": 0.0054, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.022648360580205917, | |
| "learning_rate": 5.2e-06, | |
| "loss": 0.0016, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.0010837001027539372, | |
| "learning_rate": 5.155555555555556e-06, | |
| "loss": 0.0044, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 0.00025768097839318216, | |
| "learning_rate": 5.1111111111111115e-06, | |
| "loss": 0.0014, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 0.34753185510635376, | |
| "learning_rate": 5.0666666666666676e-06, | |
| "loss": 0.0053, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 0.000370951893273741, | |
| "learning_rate": 5.022222222222223e-06, | |
| "loss": 0.0054, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 0.00029738256125710905, | |
| "learning_rate": 4.977777777777778e-06, | |
| "loss": 0.0017, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 0.15227927267551422, | |
| "learning_rate": 4.933333333333334e-06, | |
| "loss": 0.0019, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 0.1128775030374527, | |
| "learning_rate": 4.888888888888889e-06, | |
| "loss": 0.0052, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 0.00027570247766561806, | |
| "learning_rate": 4.8444444444444446e-06, | |
| "loss": 0.0005, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 0.005237150471657515, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 0.0129, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 0.6701110005378723, | |
| "learning_rate": 4.755555555555556e-06, | |
| "loss": 0.0044, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 0.00061286665732041, | |
| "learning_rate": 4.711111111111111e-06, | |
| "loss": 0.0001, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 0.0007666970486752689, | |
| "learning_rate": 4.666666666666667e-06, | |
| "loss": 0.0049, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 0.0005051186308264732, | |
| "learning_rate": 4.622222222222222e-06, | |
| "loss": 0.0044, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 0.0005429310840554535, | |
| "learning_rate": 4.5777777777777785e-06, | |
| "loss": 0.0128, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.00036512824590317905, | |
| "learning_rate": 4.533333333333334e-06, | |
| "loss": 0.0057, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.025857826694846153, | |
| "learning_rate": 4.488888888888889e-06, | |
| "loss": 0.0003, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.01597726158797741, | |
| "learning_rate": 4.444444444444444e-06, | |
| "loss": 0.0028, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_loss": 0.02211879752576351, | |
| "eval_runtime": 105.9232, | |
| "eval_samples_per_second": 9.441, | |
| "eval_steps_per_second": 9.441, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 0.12713465094566345, | |
| "learning_rate": 4.4e-06, | |
| "loss": 0.0046, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 0.0022403071634471416, | |
| "learning_rate": 4.3555555555555555e-06, | |
| "loss": 0.0039, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 0.3125491738319397, | |
| "learning_rate": 4.3111111111111115e-06, | |
| "loss": 0.0147, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 0.0007740085129626095, | |
| "learning_rate": 4.266666666666668e-06, | |
| "loss": 0.0031, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 0.07295132428407669, | |
| "learning_rate": 4.222222222222223e-06, | |
| "loss": 0.0172, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 0.0005750702694058418, | |
| "learning_rate": 4.177777777777778e-06, | |
| "loss": 0.0021, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.008953329175710678, | |
| "learning_rate": 4.133333333333333e-06, | |
| "loss": 0.0019, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.00033226358937099576, | |
| "learning_rate": 4.088888888888889e-06, | |
| "loss": 0.0046, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.0006687557324767113, | |
| "learning_rate": 4.044444444444445e-06, | |
| "loss": 0.004, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.009847434237599373, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0045, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 0.00036680695484392345, | |
| "learning_rate": 3.955555555555556e-06, | |
| "loss": 0.0036, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 0.2396153211593628, | |
| "learning_rate": 3.911111111111112e-06, | |
| "loss": 0.0092, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 0.40363165736198425, | |
| "learning_rate": 3.866666666666667e-06, | |
| "loss": 0.0051, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 0.058287497609853745, | |
| "learning_rate": 3.8222222222222224e-06, | |
| "loss": 0.0034, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 0.0005693346611224115, | |
| "learning_rate": 3.777777777777778e-06, | |
| "loss": 0.0089, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 0.1548708975315094, | |
| "learning_rate": 3.7333333333333337e-06, | |
| "loss": 0.0076, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 0.1720203459262848, | |
| "learning_rate": 3.688888888888889e-06, | |
| "loss": 0.0072, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 0.00042649006354622543, | |
| "learning_rate": 3.644444444444445e-06, | |
| "loss": 0.0049, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 0.015147966332733631, | |
| "learning_rate": 3.6000000000000003e-06, | |
| "loss": 0.0018, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 0.000541534333024174, | |
| "learning_rate": 3.555555555555556e-06, | |
| "loss": 0.0007, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 0.0003232716699130833, | |
| "learning_rate": 3.511111111111111e-06, | |
| "loss": 0.0003, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 0.00029635836835950613, | |
| "learning_rate": 3.4666666666666672e-06, | |
| "loss": 0.0059, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 0.000614231510553509, | |
| "learning_rate": 3.4222222222222224e-06, | |
| "loss": 0.0089, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 0.00032767339143902063, | |
| "learning_rate": 3.377777777777778e-06, | |
| "loss": 0.0039, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 0.00045120881986804307, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.003, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 0.0003937460423912853, | |
| "learning_rate": 3.2888888888888894e-06, | |
| "loss": 0.0034, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 0.0006157084717415273, | |
| "learning_rate": 3.2444444444444446e-06, | |
| "loss": 0.0025, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 0.0005464738933369517, | |
| "learning_rate": 3.2000000000000003e-06, | |
| "loss": 0.0539, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 0.00032850648858584464, | |
| "learning_rate": 3.1555555555555555e-06, | |
| "loss": 0.0031, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 0.0006490522064268589, | |
| "learning_rate": 3.1111111111111116e-06, | |
| "loss": 0.0019, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 0.0008282049675472081, | |
| "learning_rate": 3.066666666666667e-06, | |
| "loss": 0.0019, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 0.0007463882211595774, | |
| "learning_rate": 3.0222222222222225e-06, | |
| "loss": 0.0173, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 0.10642620921134949, | |
| "learning_rate": 2.9777777777777777e-06, | |
| "loss": 0.0155, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 0.00021003976871725172, | |
| "learning_rate": 2.9333333333333338e-06, | |
| "loss": 0.0083, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 0.003369180951267481, | |
| "learning_rate": 2.888888888888889e-06, | |
| "loss": 0.0047, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 0.31446290016174316, | |
| "learning_rate": 2.8444444444444446e-06, | |
| "loss": 0.0158, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 0.4788835644721985, | |
| "learning_rate": 2.8000000000000003e-06, | |
| "loss": 0.0058, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 0.0008424910483881831, | |
| "learning_rate": 2.755555555555556e-06, | |
| "loss": 0.0035, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 0.0002819730725605041, | |
| "learning_rate": 2.7111111111111116e-06, | |
| "loss": 0.0061, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 0.14431558549404144, | |
| "learning_rate": 2.666666666666667e-06, | |
| "loss": 0.0021, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 0.00966221559792757, | |
| "learning_rate": 2.6222222222222225e-06, | |
| "loss": 0.0102, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 0.394972026348114, | |
| "learning_rate": 2.577777777777778e-06, | |
| "loss": 0.0035, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 0.0002667000226210803, | |
| "learning_rate": 2.5333333333333338e-06, | |
| "loss": 0.004, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 0.6008601784706116, | |
| "learning_rate": 2.488888888888889e-06, | |
| "loss": 0.0102, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 0.3898264765739441, | |
| "learning_rate": 2.4444444444444447e-06, | |
| "loss": 0.0069, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 0.0005270984838716686, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 0.0046, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 0.5697627067565918, | |
| "learning_rate": 2.3555555555555555e-06, | |
| "loss": 0.0109, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 0.18540015816688538, | |
| "learning_rate": 2.311111111111111e-06, | |
| "loss": 0.0088, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 0.031030097976326942, | |
| "learning_rate": 2.266666666666667e-06, | |
| "loss": 0.0035, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 0.0005811112932860851, | |
| "learning_rate": 2.222222222222222e-06, | |
| "loss": 0.0019, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "eval_loss": 0.017604324966669083, | |
| "eval_runtime": 105.8228, | |
| "eval_samples_per_second": 9.45, | |
| "eval_steps_per_second": 9.45, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 0.00042306468822062016, | |
| "learning_rate": 2.1777777777777777e-06, | |
| "loss": 0.0037, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 0.27694016695022583, | |
| "learning_rate": 2.133333333333334e-06, | |
| "loss": 0.0028, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 0.0005545311141759157, | |
| "learning_rate": 2.088888888888889e-06, | |
| "loss": 0.0078, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 0.000449089624453336, | |
| "learning_rate": 2.0444444444444447e-06, | |
| "loss": 0.0009, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 0.00020077303634025156, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.0026, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 0.00046969045069999993, | |
| "learning_rate": 1.955555555555556e-06, | |
| "loss": 0.0025, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 0.00019804837938863784, | |
| "learning_rate": 1.9111111111111112e-06, | |
| "loss": 0.001, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 0.0003414790553506464, | |
| "learning_rate": 1.8666666666666669e-06, | |
| "loss": 0.0012, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.0005488083697855473, | |
| "learning_rate": 1.8222222222222225e-06, | |
| "loss": 0.0139, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.0003426743787713349, | |
| "learning_rate": 1.777777777777778e-06, | |
| "loss": 0.0132, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.0003723677364178002, | |
| "learning_rate": 1.7333333333333336e-06, | |
| "loss": 0.0047, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 0.00019281951244920492, | |
| "learning_rate": 1.688888888888889e-06, | |
| "loss": 0.0037, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 0.00028308393666520715, | |
| "learning_rate": 1.6444444444444447e-06, | |
| "loss": 0.0175, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 0.0002835668856278062, | |
| "learning_rate": 1.6000000000000001e-06, | |
| "loss": 0.0012, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 0.10114676505327225, | |
| "learning_rate": 1.5555555555555558e-06, | |
| "loss": 0.0067, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 0.10014703124761581, | |
| "learning_rate": 1.5111111111111112e-06, | |
| "loss": 0.0141, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 0.0002140298020094633, | |
| "learning_rate": 1.4666666666666669e-06, | |
| "loss": 0.004, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 0.00019562234228942543, | |
| "learning_rate": 1.4222222222222223e-06, | |
| "loss": 0.0019, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 1.0138946771621704, | |
| "learning_rate": 1.377777777777778e-06, | |
| "loss": 0.0105, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 0.06462077796459198, | |
| "learning_rate": 1.3333333333333334e-06, | |
| "loss": 0.0009, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 0.000309393391944468, | |
| "learning_rate": 1.288888888888889e-06, | |
| "loss": 0.0025, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 0.27942171692848206, | |
| "learning_rate": 1.2444444444444445e-06, | |
| "loss": 0.0037, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 0.21164338290691376, | |
| "learning_rate": 1.2000000000000002e-06, | |
| "loss": 0.0162, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 0.3361373841762543, | |
| "learning_rate": 1.1555555555555556e-06, | |
| "loss": 0.0077, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 0.0007883062935434282, | |
| "learning_rate": 1.111111111111111e-06, | |
| "loss": 0.0136, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 0.0004852807614952326, | |
| "learning_rate": 1.066666666666667e-06, | |
| "loss": 0.0004, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 0.37207266688346863, | |
| "learning_rate": 1.0222222222222223e-06, | |
| "loss": 0.0204, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.0012206656392663717, | |
| "learning_rate": 9.77777777777778e-07, | |
| "loss": 0.0265, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.000247218762524426, | |
| "learning_rate": 9.333333333333334e-07, | |
| "loss": 0.0021, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.19631250202655792, | |
| "learning_rate": 8.88888888888889e-07, | |
| "loss": 0.014, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 0.00041647368925623596, | |
| "learning_rate": 8.444444444444445e-07, | |
| "loss": 0.0027, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 0.0005213326658122241, | |
| "learning_rate": 8.000000000000001e-07, | |
| "loss": 0.0127, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 0.10857554525136948, | |
| "learning_rate": 7.555555555555556e-07, | |
| "loss": 0.0109, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 0.14191143214702606, | |
| "learning_rate": 7.111111111111112e-07, | |
| "loss": 0.0039, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 0.036222055554389954, | |
| "learning_rate": 6.666666666666667e-07, | |
| "loss": 0.0143, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 0.0002471502812113613, | |
| "learning_rate": 6.222222222222223e-07, | |
| "loss": 0.0029, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 0.0002270705153932795, | |
| "learning_rate": 5.777777777777778e-07, | |
| "loss": 0.0167, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 0.00021865036978852004, | |
| "learning_rate": 5.333333333333335e-07, | |
| "loss": 0.0023, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 0.002427297178655863, | |
| "learning_rate": 4.88888888888889e-07, | |
| "loss": 0.0012, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 0.00024957634741440415, | |
| "learning_rate": 4.444444444444445e-07, | |
| "loss": 0.0099, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 0.5699187517166138, | |
| "learning_rate": 4.0000000000000003e-07, | |
| "loss": 0.0316, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 0.000845414528157562, | |
| "learning_rate": 3.555555555555556e-07, | |
| "loss": 0.0032, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 0.00035873273736797273, | |
| "learning_rate": 3.111111111111111e-07, | |
| "loss": 0.0053, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 0.00040514240390621126, | |
| "learning_rate": 2.666666666666667e-07, | |
| "loss": 0.0015, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 0.0003163764195051044, | |
| "learning_rate": 2.2222222222222224e-07, | |
| "loss": 0.0031, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 0.0004442491626832634, | |
| "learning_rate": 1.777777777777778e-07, | |
| "loss": 0.0119, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 0.0004997169016860425, | |
| "learning_rate": 1.3333333333333336e-07, | |
| "loss": 0.0173, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 0.00029198831180110574, | |
| "learning_rate": 8.88888888888889e-08, | |
| "loss": 0.0056, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 0.0015217772452160716, | |
| "learning_rate": 4.444444444444445e-08, | |
| "loss": 0.0066, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": 0.0002698723692446947, | |
| "learning_rate": 0.0, | |
| "loss": 0.0115, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "eval_loss": 0.022028431296348572, | |
| "eval_runtime": 105.7251, | |
| "eval_samples_per_second": 9.458, | |
| "eval_steps_per_second": 9.458, | |
| "step": 5000 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 5000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 1000, | |
| "total_flos": 8.05066044384215e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |