| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.4253490870032223, | |
| "eval_steps": 50, | |
| "global_step": 99, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004296455424274973, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004296455424274973, | |
| "eval_loss": NaN, | |
| "eval_runtime": 35.4972, | |
| "eval_samples_per_second": 11.043, | |
| "eval_steps_per_second": 1.38, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008592910848549946, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01288936627282492, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.017185821697099892, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.021482277121374866, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00025, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02577873254564984, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03007518796992481, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00035, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.034371643394199784, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0004, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03866809881847476, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00045000000000000004, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04296455424274973, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0005, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.047261009667024706, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0004998442655654946, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05155746509129968, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0004993772562876909, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.055853920515574654, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0004985995540019955, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06015037593984962, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0004975121276286136, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0644468313641246, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0004961163319653958, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06874328678839957, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0004944139059999286, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.07303974221267455, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000492406970742972, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07733619763694952, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0004900980265859448, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08163265306122448, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0004874899501857477, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.08592910848549946, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00048458599088080736, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09022556390977443, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0004813897666428053, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.09452201933404941, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00047790525956913543, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.09881847475832438, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0004741368109217071, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.10311493018259936, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00047008911571827283, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.10741138560687433, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00046576721688302105, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11170784103114931, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0004611764989637205, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.11600429645542427, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0004563226814232444, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.12030075187969924, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0004512118115138315, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.12459720730397422, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0004458502567429631, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.1288936627282492, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00044024469694024196, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13319011815252416, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00043440211593515554, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.13748657357679914, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0004283297928560951, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.14178302900107412, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0004220352930614672, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1460794844253491, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00041552645871420013, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.15037593984962405, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00040881139901138467, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.15467239527389903, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00040189848008122475, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.158968850698174, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00039479631455988334, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.16326530612244897, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003875137508612103, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.16756176154672395, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00038005986215272055, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.17185821697099893, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003724439350515571, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1761546723952739, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003646754580545226, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.18045112781954886, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000356764109716594, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.18474758324382384, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00034871974659264783, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.18904403866809882, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003405523909574206, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1933404940923738, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003322722183190025, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.19763694951664876, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003238895447414211, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.20193340494092374, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003154148139921102, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.20622986036519872, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00030685858453027663, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002982315163523742, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.21482277121374865, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000289544357711076, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.21482277121374865, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.13, | |
| "eval_samples_per_second": 346.907, | |
| "eval_steps_per_second": 43.363, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.21911922663802363, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002808079317242896, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.22341568206229862, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002720331228909005, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.22771213748657357, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00026323086353004075, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.23200859291084855, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002544121201607822, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.23630504833512353, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00024558787983921783, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.24060150375939848, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002367691364699592, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.24489795918367346, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00022796687710909964, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.24919441460794844, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00021919206827571036, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.2534908700322234, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00021045564228892402, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.2577873254564984, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00020176848364762578, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2620837808807734, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019314141546972343, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.2663802363050483, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018458518600788986, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.2706766917293233, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017611045525857898, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.2749731471535983, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001677277816809975, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.27926960257787325, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015944760904257942, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.28356605800214824, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001512802534073522, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.2878625134264232, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014323589028340596, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.2921589688506982, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013532454194547733, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.2964554242749731, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012755606494844294, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.3007518796992481, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011994013784727947, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.3050483351235231, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011248624913878966, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.30934479054779807, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001052036854401166, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.31364124597207305, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.810151991877531e-05, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.317937701396348, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.118860098861537e-05, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.322234156820623, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.44735412857999e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.32653061224489793, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.79647069385328e-05, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.3308270676691729, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.167020714390501e-05, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.3351235230934479, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.559788406484446e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.3394199785177229, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.975530305975807e-05, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.34371643394199786, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.414974325703686e-05, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.34801288936627284, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8788188486168616e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.3523093447905478, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.367731857675569e-05, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.35660580021482274, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.882350103627952e-05, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.3609022556390977, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.423278311697897e-05, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.3651987110633727, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9910884281727225e-05, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.3694951664876477, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.586318907829291e-05, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.37379162191192267, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.209474043086457e-05, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.37808807733619765, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.861023335719475e-05, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.38238453276047263, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5414009119192633e-05, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.3866809881847476, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.25100498142523e-05, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.39097744360902253, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.901973414055187e-06, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.3952738990332975, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.593029257027956e-06, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.3995703544575725, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.5860940000714015e-06, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.4038668098818475, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8836680346041594e-06, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.40816326530612246, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.487872371386424e-06, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.41245972073039744, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4004459980045125e-06, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.4167561761546724, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.22743712309054e-07, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.557344345054501e-07, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.4253490870032223, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 99 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 99, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 300, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.5109091185655808e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |