| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9977241693218024, | |
| "eval_steps": 69, | |
| "global_step": 274, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0036413290851160674, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0036413290851160674, | |
| "eval_loss": NaN, | |
| "eval_runtime": 55.4813, | |
| "eval_samples_per_second": 8.345, | |
| "eval_steps_per_second": 2.091, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007282658170232135, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010923987255348202, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01456531634046427, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.018206645425580335, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.021847974510696404, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02548930359581247, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02913063268092854, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.032771961766044605, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03641329085116067, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04005461993627674, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04369594902139281, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.047337278106508875, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.2000000000000004e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.05097860719162494, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6000000000000006e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05461993627674101, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05826126536185708, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.400000000000001e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.061902594446973144, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.800000000000001e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06554392353208921, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.2e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06918525261720528, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.6e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.07282658170232134, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07646791078743742, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.4e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08010923987255349, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.800000000000001e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.08375056895766955, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.200000000000001e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.08739189804278562, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.6e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09103322712790168, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09467455621301775, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010400000000000001, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.09831588529813381, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010800000000000001, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.10195721438324988, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011200000000000001, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.10559854346836596, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000116, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.10923987255348203, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11288120163859809, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000124, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.11652253072371416, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012800000000000002, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.12016385980883022, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000132, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.12380518889394629, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013600000000000003, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.12744651797906237, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.13108784706417842, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000144, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1347291761492945, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000148, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.13837050523441055, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000152, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.14201183431952663, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015600000000000002, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.14565316340464268, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14929449248975876, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000164, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.15293582157487484, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000168, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1565771506599909, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000172, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.16021847974510697, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017600000000000002, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.16385980883022302, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1675011379153391, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018400000000000003, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.17114246700045516, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000188, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.17478379608557124, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000192, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1784251251706873, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000196, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.18206645425580337, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.18570778334091945, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019999016517595753, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.1893491124260355, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019996066263830531, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.19299044151115158, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001999114981900887, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.19663177059626763, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019984268150178167, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.2002730996813837, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019975422610938462, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.20391442876649976, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019964614941176195, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.20755575785161584, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001995184726672197, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.21119708693673192, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019937122098932428, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.21483841602184797, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019920442334196248, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.21847974510696405, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019901811253364456, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2221210741920801, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019881232521105089, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.22576240327719618, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001985871018518236, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.22940373236231223, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019834248675660486, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.23304506144742831, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.23668639053254437, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019779527762272877, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.24032771961766045, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019749279121818235, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.24396904870277653, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001971711283246951, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.24761037778789258, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019683035221222618, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.25125170687300863, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001964705299102376, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.25125170687300863, | |
| "eval_loss": NaN, | |
| "eval_runtime": 55.3493, | |
| "eval_samples_per_second": 8.365, | |
| "eval_steps_per_second": 2.096, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.25489303595812474, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019609173219450998, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2585343650432408, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001956940335732209, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.26217569412835684, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019527751227228963, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.2658170232134729, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001948422502199903, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.269458352298589, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019438833303083678, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.27309968138370505, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001939158499887428, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.2767410104688211, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019342489402945998, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.2803823395539372, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019291556172229785, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.28402366863905326, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.2876649977241693, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019184217239468212, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.29130632680928537, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019127832650613189, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2949476558944015, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019069652649198005, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.2985889849795175, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001900968867902419, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.3022303140646336, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018947952534793661, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.3058716431497497, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018884456359788724, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.30951297223486574, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001881921264348355, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.3131543013199818, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018752234219087538, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.31679563040509784, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018683534261021057, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.32043695949021395, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018613126282324092, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.32407828857533, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018541024131998274, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.32771961766044605, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018467241992282843, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.33136094674556216, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018391794375865024, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.3350022758306782, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.33864360491579426, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018235962398719147, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.3422849340009103, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018155608689592604, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.3459262630860264, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018073650800937624, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.34956759217114247, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017990104853582493, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.3532089212562585, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017904987280721035, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.3568502503413746, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000178183148246803, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.3604915794264907, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001773010453362737, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.36413290851160673, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017640373758216077, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3677742375967228, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001754914014817416, | |
| "loss": 0.0, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.3714155666818389, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017456421648831655, | |
| "loss": 0.0, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.37505689576695495, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017362236497591094, | |
| "loss": 0.0, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.378698224852071, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001726660322034027, | |
| "loss": 0.0, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.38233955393718705, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017169540627808274, | |
| "loss": 0.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.38598088302230316, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.3896222121074192, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016971204141768233, | |
| "loss": 0.0, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.39326354119253526, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016869969260349018, | |
| "loss": 0.0, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.39690487027765137, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016767383080152742, | |
| "loss": 0.0, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.4005461993627674, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001666346577952004, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.40418752844788347, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016558237798618245, | |
| "loss": 0.0, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.4078288575329995, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016451719835420877, | |
| "loss": 0.0, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.41147018661811563, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016343932841636456, | |
| "loss": 0.0, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.4151115157032317, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016234898018587337, | |
| "loss": 0.0, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.41875284478834773, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016124636813039502, | |
| "loss": 0.0, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.42239417387346384, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016013170912984058, | |
| "loss": 0.0, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.4260355029585799, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015900522243371282, | |
| "loss": 0.0, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.42967683204369594, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001578671296179806, | |
| "loss": 0.0, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.433318161128812, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015671765454149559, | |
| "loss": 0.0, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.4369594902139281, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.44060081929904416, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015438546419145488, | |
| "loss": 0.0, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.4442421483841602, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015320320765153367, | |
| "loss": 0.0, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.44788347746927626, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015201048622789747, | |
| "loss": 0.0, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.45152480655439237, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015080753452465296, | |
| "loss": 0.0, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.4551661356395084, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001495945891581668, | |
| "loss": 0.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.45880746472462447, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000148371888710524, | |
| "loss": 0.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.4624487938097406, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001471396736825998, | |
| "loss": 0.0, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.46609012289485663, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014589818644675378, | |
| "loss": 0.0, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.4697314519799727, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014464767119915629, | |
| "loss": 0.0, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.47337278106508873, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014338837391175582, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.47701411015020484, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001421205422838971, | |
| "loss": 0.0, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.4806554392353209, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014084442569359964, | |
| "loss": 0.0, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.48429676832043694, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001395602751485059, | |
| "loss": 0.0, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.48793809740555305, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.0, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.4915794264906691, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013696888407606952, | |
| "loss": 0.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.49522075557578515, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001356621532662313, | |
| "loss": 0.0, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.4988620846609012, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001343484078363461, | |
| "loss": 0.0, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.5025034137460173, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013302790619551674, | |
| "loss": 0.0, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.5025034137460173, | |
| "eval_loss": NaN, | |
| "eval_runtime": 55.2669, | |
| "eval_samples_per_second": 8.378, | |
| "eval_steps_per_second": 2.099, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.5061447428311333, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013170090808176883, | |
| "loss": 0.0, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.5097860719162495, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013036767451096148, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5134274010013655, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012902846772544624, | |
| "loss": 0.0, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.5170687300864816, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012768355114248494, | |
| "loss": 0.0, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.5207100591715976, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012633318930243648, | |
| "loss": 0.0, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.5243513882567137, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001249776478167227, | |
| "loss": 0.0, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.5279927173418297, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012361719331558345, | |
| "loss": 0.0, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.5316340464269458, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012225209339563145, | |
| "loss": 0.0, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.535275375512062, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000120882616567217, | |
| "loss": 0.0, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.538916704597178, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.0, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.542558033682294, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011813161047802985, | |
| "loss": 0.0, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.5461993627674101, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011675062233047364, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5498406918525262, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000115366339394453, | |
| "loss": 0.0, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.5534820209376422, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011397903395354996, | |
| "loss": 0.0, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.5571233500227583, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011258897888586255, | |
| "loss": 0.0, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.5607646791078744, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011119644761033078, | |
| "loss": 0.0, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.5644060081929905, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001098017140329561, | |
| "loss": 0.0, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.5680473372781065, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010840505249292476, | |
| "loss": 0.0, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.5716886663632226, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010700673770864673, | |
| "loss": 0.0, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.5753299954483386, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010560704472371919, | |
| "loss": 0.0, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.5789713245334547, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010420624885282653, | |
| "loss": 0.0, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.5826126536185707, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001028046256275869, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.5862539827036869, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010140245074235624, | |
| "loss": 0.0, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.589895311788803, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.593536640873919, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.859754925764378e-05, | |
| "loss": 0.0, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.597177969959035, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.719537437241312e-05, | |
| "loss": 0.0, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.6008192990441511, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.579375114717351e-05, | |
| "loss": 0.0, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.6044606281292672, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.439295527628081e-05, | |
| "loss": 0.0, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.6081019572143832, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.299326229135326e-05, | |
| "loss": 0.0, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.6117432862994994, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.159494750707526e-05, | |
| "loss": 0.0, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.019828596704394e-05, | |
| "loss": 0.0, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.6190259444697315, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.880355238966923e-05, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.6226672735548475, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.741102111413748e-05, | |
| "loss": 0.0, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.6263086026399636, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.602096604645009e-05, | |
| "loss": 0.0, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.6299499317250796, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.463366060554698e-05, | |
| "loss": 0.0, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.6335912608101957, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.324937766952638e-05, | |
| "loss": 0.0, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.6372325898953118, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.186838952197018e-05, | |
| "loss": 0.0, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.6408739189804279, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 0.0, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.6445152480655439, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.911738343278304e-05, | |
| "loss": 0.0, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.64815657715066, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.774790660436858e-05, | |
| "loss": 0.0, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.651797906235776, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.63828066844166e-05, | |
| "loss": 0.0, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.6554392353208921, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.502235218327731e-05, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.6590805644060082, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.366681069756352e-05, | |
| "loss": 0.0, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.6627218934911243, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.231644885751507e-05, | |
| "loss": 0.0, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.6663632225762404, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.097153227455379e-05, | |
| "loss": 0.0, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.6700045516613564, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.963232548903853e-05, | |
| "loss": 0.0, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.6736458807464725, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.829909191823121e-05, | |
| "loss": 0.0, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.6772872098315885, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.697209380448333e-05, | |
| "loss": 0.0, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.6809285389167046, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.565159216365389e-05, | |
| "loss": 0.0, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.6845698680018206, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.43378467337687e-05, | |
| "loss": 0.0, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.6882111970869367, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.30311159239305e-05, | |
| "loss": 0.0, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.6918525261720528, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.6954938552571689, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.043972485149414e-05, | |
| "loss": 0.0, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.6991351843422849, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9155574306400395e-05, | |
| "loss": 0.0, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.702776513427401, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.787945771610296e-05, | |
| "loss": 0.0, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.706417842512517, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6611626088244194e-05, | |
| "loss": 0.0, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.7100591715976331, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.5352328800843724e-05, | |
| "loss": 0.0, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.7137005006827492, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.410181355324622e-05, | |
| "loss": 0.0, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.7173418297678653, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.286032631740023e-05, | |
| "loss": 0.0, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.7209831588529814, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.162811128947602e-05, | |
| "loss": 0.0, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.7246244879380974, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.0405410841833253e-05, | |
| "loss": 0.0, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.7282658170232135, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.919246547534708e-05, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7319071461083295, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7989513772102537e-05, | |
| "loss": 0.0, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.7355484751934456, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6796792348466356e-05, | |
| "loss": 0.0, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.7391898042785616, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.561453580854516e-05, | |
| "loss": 0.0, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.7428311333636778, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.0, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.7464724624487938, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.328234545850442e-05, | |
| "loss": 0.0, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.7501137915339099, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.213287038201943e-05, | |
| "loss": 0.0, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.7537551206190259, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.0994777566287204e-05, | |
| "loss": 0.0, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.7537551206190259, | |
| "eval_loss": NaN, | |
| "eval_runtime": 55.3157, | |
| "eval_samples_per_second": 8.37, | |
| "eval_steps_per_second": 2.097, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.757396449704142, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9868290870159405e-05, | |
| "loss": 0.0, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.761037778789258, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.875363186960499e-05, | |
| "loss": 0.0, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.7646791078743741, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7651019814126654e-05, | |
| "loss": 0.0, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.7683204369594903, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6560671583635467e-05, | |
| "loss": 0.0, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.7719617660446063, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.548280164579126e-05, | |
| "loss": 0.0, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.7756030951297224, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4417622013817595e-05, | |
| "loss": 0.0, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.7792444242148384, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.336534220479961e-05, | |
| "loss": 0.0, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.7828857532999545, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.2326169198472556e-05, | |
| "loss": 0.0, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.7865270823850705, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.130030739650983e-05, | |
| "loss": 0.0, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.7901684114701866, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0287958582317676e-05, | |
| "loss": 0.0, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.7938097405553027, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.0, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.7974510696404188, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8304593721917285e-05, | |
| "loss": 0.0, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.8010923987255348, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7333967796597315e-05, | |
| "loss": 0.0, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.8047337278106509, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6377635024089087e-05, | |
| "loss": 0.0, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.8083750568957669, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5435783511683443e-05, | |
| "loss": 0.0, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.812016385980883, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.450859851825842e-05, | |
| "loss": 0.0, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.815657715065999, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3596262417839255e-05, | |
| "loss": 0.0, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.8192990441511152, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.26989546637263e-05, | |
| "loss": 0.0, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.8229403732362313, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.181685175319702e-05, | |
| "loss": 0.0, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.8265817023213473, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.095012719278966e-05, | |
| "loss": 0.0, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.8302230314064634, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.009895146417512e-05, | |
| "loss": 0.0, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.8338643604915794, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.926349199062376e-05, | |
| "loss": 0.0, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.8375056895766955, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8443913104073983e-05, | |
| "loss": 0.0, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.8411470186618115, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7640376012808536e-05, | |
| "loss": 0.0, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.8447883477469277, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 0.0, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.8484296768320437, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6082056241349786e-05, | |
| "loss": 0.0, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.8520710059171598, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5327580077171587e-05, | |
| "loss": 0.0, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.8557123350022758, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4589758680017263e-05, | |
| "loss": 0.0, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.8593536640873919, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3868737176759106e-05, | |
| "loss": 0.0, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.8629949931725079, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3164657389789458e-05, | |
| "loss": 0.0, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.866636322257624, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2477657809124631e-05, | |
| "loss": 0.0, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.8702776513427402, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1807873565164506e-05, | |
| "loss": 0.0, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.8739189804278562, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1155436402112785e-05, | |
| "loss": 0.0, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.8775603095129723, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0520474652063394e-05, | |
| "loss": 0.0, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.8812016385980883, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.903113209758096e-06, | |
| "loss": 0.0, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.8848429676832044, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.303473508019944e-06, | |
| "loss": 0.0, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.8884842967683204, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.72167349386811e-06, | |
| "loss": 0.0, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.8921256258534365, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.157827605317892e-06, | |
| "loss": 0.0, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.8957669549385525, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.0, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.8994082840236687, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.084438277702188e-06, | |
| "loss": 0.0, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.9030496131087847, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.5751059705400295e-06, | |
| "loss": 0.0, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.9066909421939008, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.084150011257239e-06, | |
| "loss": 0.0, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.9103322712790168, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.611666969163243e-06, | |
| "loss": 0.0, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.9139736003641329, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.157749780009735e-06, | |
| "loss": 0.0, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.9176149294492489, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.722487727710368e-06, | |
| "loss": 0.0, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.921256258534365, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.305966426779118e-06, | |
| "loss": 0.0, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.9248975876194812, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.908267805490051e-06, | |
| "loss": 0.0, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.9285389167045972, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.529470089762421e-06, | |
| "loss": 0.0, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.9321802457897133, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.169647787773866e-06, | |
| "loss": 0.0, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.9358215748748293, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8288716753049005e-06, | |
| "loss": 0.0, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.9394629039599454, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5072087818176382e-06, | |
| "loss": 0.0, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.9431042330450614, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.20472237727124e-06, | |
| "loss": 0.0, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.9467455621301775, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 0.0, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.9503868912152936, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.657513243395159e-06, | |
| "loss": 0.0, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.9540282203004097, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4128981481764115e-06, | |
| "loss": 0.0, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.9576695493855257, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1876747889491223e-06, | |
| "loss": 0.0, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.9613108784706418, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.818874663554357e-07, | |
| "loss": 0.0, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.9649522075557578, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.955766580375335e-07, | |
| "loss": 0.0, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.9685935366408739, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.287790106757396e-07, | |
| "loss": 0.0, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.9722348657259899, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.815273327803182e-07, | |
| "loss": 0.0, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.9758761948111061, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5385058823809156e-07, | |
| "loss": 0.0, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.9795175238962222, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.457738906153972e-07, | |
| "loss": 0.0, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.9831588529813382, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5731849821833954e-07, | |
| "loss": 0.0, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.9868001820664543, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.850180991131219e-08, | |
| "loss": 0.0, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.9904415111515703, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.933736169471347e-08, | |
| "loss": 0.0, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.9940828402366864, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.834824042498358e-09, | |
| "loss": 0.0, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.9977241693218024, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 274 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 274, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 69, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.706308131705324e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |